aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/core_marvel.c6
-rw-r--r--arch/alpha/kernel/core_t2.c24
-rw-r--r--arch/alpha/kernel/core_titan.c34
-rw-r--r--arch/alpha/kernel/core_tsunami.c28
-rw-r--r--arch/alpha/kernel/module.c6
-rw-r--r--arch/alpha/kernel/pci.c2
-rw-r--r--arch/alpha/kernel/pci_iommu.c34
-rw-r--r--arch/alpha/kernel/smp.c4
-rw-r--r--arch/alpha/kernel/srm_env.c2
-rw-r--r--arch/alpha/kernel/sys_alcor.c2
-rw-r--r--arch/alpha/kernel/sys_marvel.c12
-rw-r--r--arch/alpha/kernel/sys_sable.c6
-rw-r--r--arch/alpha/kernel/sys_sio.c2
-rw-r--r--arch/alpha/kernel/traps.c5
-rw-r--r--arch/arm/mach-at91/at91sam9261_devices.c11
-rw-r--r--arch/arm/mach-at91/at91sam9rl_devices.c14
-rw-r--r--arch/avr32/kernel/setup.c2
-rw-r--r--arch/cris/mm/init.c1
-rw-r--r--arch/frv/kernel/traps.c31
-rw-r--r--arch/ia64/Kconfig3
-rw-r--r--arch/ia64/Makefile1
-rw-r--r--arch/ia64/kvm/Kconfig49
-rw-r--r--arch/ia64/kvm/Makefile58
-rw-r--r--arch/ia64/kvm/asm-offsets.c251
-rw-r--r--arch/ia64/kvm/kvm-ia64.c1806
-rw-r--r--arch/ia64/kvm/kvm_fw.c500
-rw-r--r--arch/ia64/kvm/kvm_minstate.h273
-rw-r--r--arch/ia64/kvm/lapic.h25
-rw-r--r--arch/ia64/kvm/misc.h93
-rw-r--r--arch/ia64/kvm/mmio.c341
-rw-r--r--arch/ia64/kvm/optvfault.S918
-rw-r--r--arch/ia64/kvm/process.c970
-rw-r--r--arch/ia64/kvm/trampoline.S1038
-rw-r--r--arch/ia64/kvm/vcpu.c2163
-rw-r--r--arch/ia64/kvm/vcpu.h740
-rw-r--r--arch/ia64/kvm/vmm.c66
-rw-r--r--arch/ia64/kvm/vmm_ivt.S1424
-rw-r--r--arch/ia64/kvm/vti.h290
-rw-r--r--arch/ia64/kvm/vtlb.c636
-rw-r--r--arch/ia64/mm/init.c9
-rw-r--r--arch/m68k/kernel/ints.c10
-rw-r--r--arch/m68k/mac/oss.c4
-rw-r--r--arch/m68k/mm/init.c1
-rw-r--r--arch/m68k/q40/q40ints.c2
-rw-r--r--arch/mips/Kconfig38
-rw-r--r--arch/mips/Kconfig.debug10
-rw-r--r--arch/mips/Makefile12
-rw-r--r--arch/mips/au1000/common/cputable.c5
-rw-r--r--arch/mips/au1000/common/dbdma.c6
-rw-r--r--arch/mips/au1000/common/dbg_io.c6
-rw-r--r--arch/mips/au1000/common/dma.c5
-rw-r--r--arch/mips/au1000/common/gpio.c5
-rw-r--r--arch/mips/au1000/common/irq.c8
-rw-r--r--arch/mips/au1000/common/pci.c2
-rw-r--r--arch/mips/au1000/common/platform.c117
-rw-r--r--arch/mips/au1000/common/power.c11
-rw-r--r--arch/mips/au1000/common/prom.c2
-rw-r--r--arch/mips/au1000/common/puts.c1
-rw-r--r--arch/mips/au1000/common/reset.c8
-rw-r--r--arch/mips/au1000/common/setup.c11
-rw-r--r--arch/mips/au1000/common/sleeper.S2
-rw-r--r--arch/mips/au1000/common/time.c35
-rw-r--r--arch/mips/au1000/db1x00/board_setup.c15
-rw-r--r--arch/mips/au1000/db1x00/init.c5
-rw-r--r--arch/mips/au1000/db1x00/irqmap.c19
-rw-r--r--arch/mips/au1000/mtx-1/board_setup.c12
-rw-r--r--arch/mips/au1000/mtx-1/init.c6
-rw-r--r--arch/mips/au1000/mtx-1/irqmap.c19
-rw-r--r--arch/mips/au1000/mtx-1/platform.c1
-rw-r--r--arch/mips/au1000/pb1000/board_setup.c11
-rw-r--r--arch/mips/au1000/pb1000/init.c6
-rw-r--r--arch/mips/au1000/pb1000/irqmap.c18
-rw-r--r--arch/mips/au1000/pb1100/board_setup.c11
-rw-r--r--arch/mips/au1000/pb1100/init.c6
-rw-r--r--arch/mips/au1000/pb1100/irqmap.c19
-rw-r--r--arch/mips/au1000/pb1200/Makefile1
-rw-r--r--arch/mips/au1000/pb1200/board_setup.c20
-rw-r--r--arch/mips/au1000/pb1200/init.c6
-rw-r--r--arch/mips/au1000/pb1200/irqmap.c20
-rw-r--r--arch/mips/au1000/pb1200/platform.c84
-rw-r--r--arch/mips/au1000/pb1500/board_setup.c11
-rw-r--r--arch/mips/au1000/pb1500/init.c6
-rw-r--r--arch/mips/au1000/pb1500/irqmap.c19
-rw-r--r--arch/mips/au1000/pb1550/board_setup.c13
-rw-r--r--arch/mips/au1000/pb1550/init.c6
-rw-r--r--arch/mips/au1000/pb1550/irqmap.c19
-rw-r--r--arch/mips/au1000/xxs1500/board_setup.c11
-rw-r--r--arch/mips/au1000/xxs1500/init.c6
-rw-r--r--arch/mips/au1000/xxs1500/irqmap.c19
-rw-r--r--arch/mips/configs/mipssim_defconfig1
-rw-r--r--arch/mips/configs/pnx8550-jbs_defconfig1
-rw-r--r--arch/mips/configs/pnx8550-stb810_defconfig1
-rw-r--r--arch/mips/dec/time.c71
-rw-r--r--arch/mips/jmr3927/rbhma3100/setup.c11
-rw-r--r--arch/mips/kernel/Makefile8
-rw-r--r--arch/mips/kernel/asm-offsets.c404
-rw-r--r--arch/mips/kernel/cevt-ds1287.c129
-rw-r--r--arch/mips/kernel/cevt-gt641xx.c2
-rw-r--r--arch/mips/kernel/cpu-probe.c21
-rw-r--r--arch/mips/kernel/csrc-ioasic.c65
-rw-r--r--arch/mips/kernel/gpio_txx9.c87
-rw-r--r--arch/mips/kernel/irq-gic.c295
-rw-r--r--arch/mips/kernel/irq-msc01.c10
-rw-r--r--arch/mips/kernel/signal-common.h2
-rw-r--r--arch/mips/kernel/smp-cmp.c265
-rw-r--r--arch/mips/kernel/smp-mt.c143
-rw-r--r--arch/mips/kernel/smp.c4
-rw-r--r--arch/mips/kernel/smtc.c11
-rw-r--r--arch/mips/kernel/spram.c221
-rw-r--r--arch/mips/kernel/sync-r4k.c159
-rw-r--r--arch/mips/kernel/time.c5
-rw-r--r--arch/mips/kernel/traps.c213
-rw-r--r--arch/mips/math-emu/ieee754dp.h2
-rw-r--r--arch/mips/math-emu/ieee754sp.h2
-rw-r--r--arch/mips/mips-boards/generic/Makefile1
-rw-r--r--arch/mips/mips-boards/generic/amon.c80
-rw-r--r--arch/mips/mips-boards/generic/init.c23
-rw-r--r--arch/mips/mips-boards/generic/memory.c4
-rw-r--r--arch/mips/mips-boards/generic/time.c31
-rw-r--r--arch/mips/mips-boards/malta/Makefile1
-rw-r--r--arch/mips/mips-boards/malta/malta_int.c354
-rw-r--r--arch/mips/mips-boards/malta/malta_setup.c10
-rw-r--r--arch/mips/mipssim/sim_setup.c6
-rw-r--r--arch/mips/mm/Makefile37
-rw-r--r--arch/mips/mm/c-r4k.c62
-rw-r--r--arch/mips/mm/cache.c31
-rw-r--r--arch/mips/mm/init.c11
-rw-r--r--arch/mips/mm/page.c684
-rw-r--r--arch/mips/mm/pg-r4k.c534
-rw-r--r--arch/mips/mm/pg-sb1.c302
-rw-r--r--arch/mips/mm/pgtable.c1
-rw-r--r--arch/mips/mm/tlb-r4k.c2
-rw-r--r--arch/mips/mm/uasm.c26
-rw-r--r--arch/mips/mm/uasm.h4
-rw-r--r--arch/mips/nxp/pnx8550/common/Makefile (renamed from arch/mips/philips/pnx8550/common/Makefile)0
-rw-r--r--arch/mips/nxp/pnx8550/common/gdb_hook.c (renamed from arch/mips/philips/pnx8550/common/gdb_hook.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/int.c (renamed from arch/mips/philips/pnx8550/common/int.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/pci.c (renamed from arch/mips/philips/pnx8550/common/pci.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/platform.c (renamed from arch/mips/philips/pnx8550/common/platform.c)2
-rw-r--r--arch/mips/nxp/pnx8550/common/proc.c (renamed from arch/mips/philips/pnx8550/common/proc.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/prom.c (renamed from arch/mips/philips/pnx8550/common/prom.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/reset.c (renamed from arch/mips/philips/pnx8550/common/reset.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/setup.c (renamed from arch/mips/philips/pnx8550/common/setup.c)0
-rw-r--r--arch/mips/nxp/pnx8550/common/time.c (renamed from arch/mips/philips/pnx8550/common/time.c)0
-rw-r--r--arch/mips/nxp/pnx8550/jbs/Makefile (renamed from arch/mips/philips/pnx8550/jbs/Makefile)2
-rw-r--r--arch/mips/nxp/pnx8550/jbs/board_setup.c (renamed from arch/mips/philips/pnx8550/jbs/board_setup.c)0
-rw-r--r--arch/mips/nxp/pnx8550/jbs/init.c (renamed from arch/mips/philips/pnx8550/jbs/init.c)2
-rw-r--r--arch/mips/nxp/pnx8550/jbs/irqmap.c (renamed from arch/mips/philips/pnx8550/jbs/irqmap.c)3
-rw-r--r--arch/mips/nxp/pnx8550/stb810/Makefile (renamed from arch/mips/philips/pnx8550/stb810/Makefile)2
-rw-r--r--arch/mips/nxp/pnx8550/stb810/board_setup.c (renamed from arch/mips/philips/pnx8550/stb810/board_setup.c)2
-rw-r--r--arch/mips/nxp/pnx8550/stb810/irqmap.c (renamed from arch/mips/philips/pnx8550/stb810/irqmap.c)3
-rw-r--r--arch/mips/nxp/pnx8550/stb810/prom_init.c (renamed from arch/mips/philips/pnx8550/stb810/prom_init.c)2
-rw-r--r--arch/mips/oprofile/common.c1
-rw-r--r--arch/mips/oprofile/op_impl.h1
-rw-r--r--arch/mips/oprofile/op_model_mipsxx.c39
-rw-r--r--arch/mips/pci/fixup-au1000.c5
-rw-r--r--arch/mips/pci/ops-pnx8550.c4
-rw-r--r--arch/mips/sgi-ip32/ip32-reset.c2
-rw-r--r--arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c2
-rw-r--r--arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c2
-rw-r--r--arch/mips/tx4938/common/dbgio.c4
-rw-r--r--arch/mips/tx4938/common/prom.c11
-rw-r--r--arch/mips/tx4938/toshiba_rbtx4938/irq.c46
-rw-r--r--arch/mips/tx4938/toshiba_rbtx4938/setup.c199
-rw-r--r--arch/mips/vr41xx/common/init.c4
-rw-r--r--arch/mips/vr41xx/common/siu.c36
-rw-r--r--arch/parisc/mm/init.c11
-rw-r--r--arch/powerpc/Kconfig84
-rw-r--r--arch/powerpc/Kconfig.debug3
-rw-r--r--arch/powerpc/Makefile1
-rw-r--r--arch/powerpc/boot/.gitignore1
-rw-r--r--arch/powerpc/boot/Makefile2
-rw-r--r--arch/powerpc/boot/dts/canyonlands.dts37
-rw-r--r--arch/powerpc/boot/dts/glacier.dts37
-rw-r--r--arch/powerpc/boot/dts/mpc8610_hpcd.dts12
-rw-r--r--arch/powerpc/boot/ns16550.c5
-rw-r--r--arch/powerpc/kernel/Makefile9
-rw-r--r--arch/powerpc/kernel/asm-offsets.c39
-rw-r--r--arch/powerpc/kernel/cpu_setup_44x.S1
-rw-r--r--arch/powerpc/kernel/cpu_setup_6xx.S8
-rw-r--r--arch/powerpc/kernel/cputable.c4
-rw-r--r--arch/powerpc/kernel/head_fsl_booke.S11
-rw-r--r--arch/powerpc/kernel/misc_32.S6
-rw-r--r--arch/powerpc/kernel/misc_64.S20
-rw-r--r--arch/powerpc/kernel/of_platform.c2
-rw-r--r--arch/powerpc/kernel/paca.c87
-rw-r--r--arch/powerpc/kernel/ppc32.h2
-rw-r--r--arch/powerpc/kernel/process.c31
-rw-r--r--arch/powerpc/kernel/prom.c4
-rw-r--r--arch/powerpc/kernel/prom_init_check.sh58
-rw-r--r--arch/powerpc/kernel/ptrace32.c27
-rw-r--r--arch/powerpc/kernel/setup_64.c5
-rw-r--r--arch/powerpc/kernel/stacktrace.c1
-rw-r--r--arch/powerpc/kernel/udbg.c4
-rw-r--r--arch/powerpc/kvm/44x_tlb.c224
-rw-r--r--arch/powerpc/kvm/44x_tlb.h91
-rw-r--r--arch/powerpc/kvm/Kconfig42
-rw-r--r--arch/powerpc/kvm/Makefile15
-rw-r--r--arch/powerpc/kvm/booke_guest.c615
-rw-r--r--arch/powerpc/kvm/booke_host.c83
-rw-r--r--arch/powerpc/kvm/booke_interrupts.S436
-rw-r--r--arch/powerpc/kvm/emulate.c760
-rw-r--r--arch/powerpc/kvm/powerpc.c436
-rw-r--r--arch/powerpc/mm/fsl_booke_mmu.c2
-rw-r--r--arch/powerpc/mm/hash_low_32.S4
-rw-r--r--arch/powerpc/mm/init_32.c13
-rw-r--r--arch/powerpc/mm/init_64.c3
-rw-r--r--arch/powerpc/mm/mem.c46
-rw-r--r--arch/powerpc/mm/numa.c1
-rw-r--r--arch/powerpc/mm/pgtable_32.c23
-rw-r--r--arch/powerpc/platforms/86xx/mpc8610_hpcd.c190
-rw-r--r--arch/powerpc/platforms/Kconfig1
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype4
-rw-r--r--arch/powerpc/platforms/Makefile1
-rw-r--r--arch/powerpc/platforms/cell/Kconfig13
-rw-r--r--arch/powerpc/platforms/cell/Makefile20
-rw-r--r--arch/powerpc/platforms/cell/axon_msi.c6
-rw-r--r--arch/powerpc/platforms/cell/beat.c (renamed from arch/powerpc/platforms/celleb/beat.c)2
-rw-r--r--arch/powerpc/platforms/cell/beat.h (renamed from arch/powerpc/platforms/celleb/beat.h)0
-rw-r--r--arch/powerpc/platforms/cell/beat_htab.c (renamed from arch/powerpc/platforms/celleb/htab.c)0
-rw-r--r--arch/powerpc/platforms/cell/beat_hvCall.S (renamed from arch/powerpc/platforms/celleb/hvCall.S)0
-rw-r--r--arch/powerpc/platforms/cell/beat_interrupt.c (renamed from arch/powerpc/platforms/celleb/interrupt.c)2
-rw-r--r--arch/powerpc/platforms/cell/beat_interrupt.h (renamed from arch/powerpc/platforms/celleb/interrupt.h)0
-rw-r--r--arch/powerpc/platforms/cell/beat_iommu.c (renamed from arch/powerpc/platforms/celleb/iommu.c)0
-rw-r--r--arch/powerpc/platforms/cell/beat_smp.c (renamed from arch/powerpc/platforms/celleb/smp.c)2
-rw-r--r--arch/powerpc/platforms/cell/beat_spu_priv1.c (renamed from arch/powerpc/platforms/celleb/spu_priv1.c)0
-rw-r--r--arch/powerpc/platforms/cell/beat_syscall.h (renamed from arch/powerpc/platforms/celleb/beat_syscall.h)0
-rw-r--r--arch/powerpc/platforms/cell/beat_udbg.c (renamed from arch/powerpc/platforms/celleb/udbg_beat.c)0
-rw-r--r--arch/powerpc/platforms/cell/beat_wrapper.h (renamed from arch/powerpc/platforms/celleb/beat_wrapper.h)0
-rw-r--r--arch/powerpc/platforms/cell/celleb_pci.c (renamed from arch/powerpc/platforms/celleb/pci.c)50
-rw-r--r--arch/powerpc/platforms/cell/celleb_pci.h (renamed from arch/powerpc/platforms/celleb/pci.h)19
-rw-r--r--arch/powerpc/platforms/cell/celleb_scc.h (renamed from arch/powerpc/platforms/celleb/scc.h)87
-rw-r--r--arch/powerpc/platforms/cell/celleb_scc_epci.c (renamed from arch/powerpc/platforms/celleb/scc_epci.c)77
-rw-r--r--arch/powerpc/platforms/cell/celleb_scc_pciex.c547
-rw-r--r--arch/powerpc/platforms/cell/celleb_scc_sio.c (renamed from arch/powerpc/platforms/celleb/scc_sio.c)0
-rw-r--r--arch/powerpc/platforms/cell/celleb_scc_uhc.c (renamed from arch/powerpc/platforms/celleb/scc_uhc.c)2
-rw-r--r--arch/powerpc/platforms/cell/celleb_setup.c (renamed from arch/powerpc/platforms/celleb/setup.c)12
-rw-r--r--arch/powerpc/platforms/cell/io-workarounds.c358
-rw-r--r--arch/powerpc/platforms/cell/io-workarounds.h49
-rw-r--r--arch/powerpc/platforms/cell/setup.c43
-rw-r--r--arch/powerpc/platforms/cell/spider-pci.c184
-rw-r--r--arch/powerpc/platforms/celleb/Kconfig12
-rw-r--r--arch/powerpc/platforms/celleb/Makefile9
-rw-r--r--arch/powerpc/platforms/celleb/io-workarounds.c280
-rw-r--r--arch/powerpc/platforms/iseries/exception.S27
-rw-r--r--arch/powerpc/platforms/ps3/os-area.c1
-rw-r--r--arch/powerpc/platforms/pseries/Kconfig5
-rw-r--r--arch/powerpc/platforms/pseries/Makefile4
-rw-r--r--arch/powerpc/platforms/pseries/eeh.c1
-rw-r--r--arch/powerpc/platforms/pseries/eeh_cache.c1
-rw-r--r--arch/powerpc/platforms/pseries/firmware.c10
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c39
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c36
-rw-r--r--arch/powerpc/platforms/pseries/ras.c4
-rw-r--r--arch/powerpc/platforms/pseries/rtasd.c14
-rw-r--r--arch/powerpc/platforms/pseries/scanlog.c23
-rw-r--r--arch/powerpc/platforms/pseries/setup.c17
-rw-r--r--arch/powerpc/platforms/pseries/smp.c11
-rw-r--r--arch/powerpc/platforms/pseries/xics.c1
-rw-r--r--arch/powerpc/sysdev/axonram.c5
-rw-r--r--arch/powerpc/sysdev/fsl_soc.c41
-rw-r--r--arch/powerpc/sysdev/fsl_soc.h23
-rw-r--r--arch/powerpc/sysdev/mv64x60_dev.c52
-rw-r--r--arch/powerpc/sysdev/mv64x60_udbg.c2
-rw-r--r--arch/ppc/8260_io/fcc_enet.c19
-rw-r--r--arch/ppc/8xx_io/enet.c23
-rw-r--r--arch/ppc/Kconfig82
-rw-r--r--arch/ppc/configs/ads8272_defconfig930
-rw-r--r--arch/ppc/configs/mpc86x_ads_defconfig633
-rw-r--r--arch/ppc/configs/mpc885ads_defconfig622
-rw-r--r--arch/ppc/kernel/ppc_ksyms.c1
-rw-r--r--arch/ppc/lib/string.S14
-rw-r--r--arch/ppc/platforms/Makefile4
-rw-r--r--arch/ppc/platforms/fads.h25
-rw-r--r--arch/ppc/platforms/mpc8272ads_setup.c367
-rw-r--r--arch/ppc/platforms/mpc885ads.h93
-rw-r--r--arch/ppc/platforms/mpc885ads_setup.c476
-rw-r--r--arch/ppc/platforms/pq2ads.c53
-rw-r--r--arch/ppc/platforms/pq2ads.h94
-rw-r--r--arch/ppc/platforms/pq2ads_pd.h32
-rw-r--r--arch/ppc/syslib/m8260_setup.c6
-rw-r--r--arch/ppc/syslib/m82xx_pci.c38
-rw-r--r--arch/ppc/syslib/m8xx_setup.c10
-rw-r--r--arch/s390/Kconfig14
-rw-r--r--arch/s390/Makefile2
-rw-r--r--arch/s390/kernel/early.c4
-rw-r--r--arch/s390/kernel/setup.c14
-rw-r--r--arch/s390/kernel/vtime.c1
-rw-r--r--arch/s390/kvm/Kconfig46
-rw-r--r--arch/s390/kvm/Makefile14
-rw-r--r--arch/s390/kvm/diag.c67
-rw-r--r--arch/s390/kvm/gaccess.h274
-rw-r--r--arch/s390/kvm/intercept.c216
-rw-r--r--arch/s390/kvm/interrupt.c592
-rw-r--r--arch/s390/kvm/kvm-s390.c685
-rw-r--r--arch/s390/kvm/kvm-s390.h64
-rw-r--r--arch/s390/kvm/priv.c323
-rw-r--r--arch/s390/kvm/sie64a.S47
-rw-r--r--arch/s390/kvm/sigp.c288
-rw-r--r--arch/s390/mm/pgtable.c65
-rw-r--r--arch/sh/mm/init.c9
-rw-r--r--arch/sparc/kernel/process.c2
-rw-r--r--arch/sparc/kernel/signal.c260
-rw-r--r--arch/sparc/kernel/sys_sparc.c14
-rw-r--r--arch/sparc64/Kconfig85
-rw-r--r--arch/sparc64/defconfig23
-rw-r--r--arch/sparc64/kernel/Makefile6
-rw-r--r--arch/sparc64/kernel/audit.c6
-rw-r--r--arch/sparc64/kernel/irq.c3
-rw-r--r--arch/sparc64/kernel/isa.c191
-rw-r--r--arch/sparc64/kernel/of_device.c6
-rw-r--r--arch/sparc64/kernel/pci.c2
-rw-r--r--arch/sparc64/kernel/process.c12
-rw-r--r--arch/sparc64/kernel/signal.c16
-rw-r--r--arch/sparc64/kernel/signal32.c272
-rw-r--r--arch/sparc64/kernel/smp.c27
-rw-r--r--arch/sparc64/kernel/sparc64_ksyms.c2
-rw-r--r--arch/sparc64/kernel/sys_sparc.c4
-rw-r--r--arch/sparc64/kernel/sys_sparc32.c11
-rw-r--r--arch/sparc64/mm/init.c16
-rw-r--r--arch/um/Kconfig.x86_647
-rw-r--r--arch/um/drivers/chan_kern.c15
-rw-r--r--arch/um/drivers/line.c2
-rw-r--r--arch/um/drivers/mcast_kern.c2
-rw-r--r--arch/um/drivers/mconsole_user.c2
-rw-r--r--arch/um/drivers/net_kern.c6
-rw-r--r--arch/um/drivers/port_user.c2
-rw-r--r--arch/um/drivers/slip_kern.c4
-rw-r--r--arch/um/drivers/stdio_console.c4
-rw-r--r--arch/um/drivers/ubd_kern.c385
-rw-r--r--arch/um/include/chan_kern.h2
-rw-r--r--arch/um/kernel/um_arch.c7
-rw-r--r--arch/um/os-Linux/helper.c1
-rw-r--r--arch/um/os-Linux/start_up.c14
-rw-r--r--arch/um/os-Linux/sys-i386/task_size.c12
-rw-r--r--arch/um/sys-i386/Makefile2
-rw-r--r--arch/um/sys-x86_64/Makefile2
-rw-r--r--arch/x86/Kconfig41
-rw-r--r--arch/x86/Kconfig.cpu11
-rw-r--r--arch/x86/Kconfig.debug24
-rw-r--r--arch/x86/boot/.gitignore5
-rw-r--r--arch/x86/boot/header.S6
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/ia32/ia32_signal.c10
-rw-r--r--arch/x86/ia32/ia32entry.S2
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/boot.c4
-rw-r--r--arch/x86/kernel/acpi/realmode/.gitignore3
-rw-r--r--arch/x86/kernel/alternative.c39
-rw-r--r--arch/x86/kernel/apic_32.c3
-rw-r--r--arch/x86/kernel/apic_64.c3
-rw-r--r--arch/x86/kernel/apm_32.c3
-rw-r--r--arch/x86/kernel/cpu/Makefile1
-rw-r--r--arch/x86/kernel/cpu/amd.c6
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c10
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_64.c18
-rw-r--r--arch/x86/kernel/cpu/nexgen.c59
-rw-r--r--arch/x86/kernel/cpu/perfctr-watchdog.c14
-rw-r--r--arch/x86/kernel/crash.c3
-rw-r--r--arch/x86/kernel/e820_64.c35
-rw-r--r--arch/x86/kernel/entry_32.S12
-rw-r--r--arch/x86/kernel/genapic_64.c2
-rw-r--r--arch/x86/kernel/head64.c25
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/i8253.c6
-rw-r--r--arch/x86/kernel/io_apic_32.c3
-rw-r--r--arch/x86/kernel/io_apic_64.c2
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/kdebugfs.c163
-rw-r--r--arch/x86/kernel/kvm.c248
-rw-r--r--arch/x86/kernel/kvmclock.c187
-rw-r--r--arch/x86/kernel/mfgpt_32.c11
-rw-r--r--arch/x86/kernel/mpparse.c39
-rw-r--r--arch/x86/kernel/paravirt.c12
-rw-r--r--arch/x86/kernel/pci-calgary_64.c1
-rw-r--r--arch/x86/kernel/process.c117
-rw-r--r--arch/x86/kernel/process_32.c118
-rw-r--r--arch/x86/kernel/process_64.c123
-rw-r--r--arch/x86/kernel/ptrace.c95
-rw-r--r--arch/x86/kernel/reboot.c17
-rw-r--r--arch/x86/kernel/setup_32.c10
-rw-r--r--arch/x86/kernel/setup_64.c36
-rw-r--r--arch/x86/kernel/signal_32.c35
-rw-r--r--arch/x86/kernel/signal_64.c30
-rw-r--r--arch/x86/kernel/smpboot.c8
-rw-r--r--arch/x86/kernel/summit_32.c5
-rw-r--r--arch/x86/kernel/tlb_64.c4
-rw-r--r--arch/x86/kernel/trampoline_32.S2
-rw-r--r--arch/x86/kernel/traps_32.c2
-rw-r--r--arch/x86/kernel/vmi_32.c22
-rw-r--r--arch/x86/kernel/vmlinux_64.lds.S6
-rw-r--r--arch/x86/kvm/Kconfig13
-rw-r--r--arch/x86/kvm/Makefile6
-rw-r--r--arch/x86/kvm/i8254.c611
-rw-r--r--arch/x86/kvm/i8254.h63
-rw-r--r--arch/x86/kvm/irq.c18
-rw-r--r--arch/x86/kvm/irq.h3
-rw-r--r--arch/x86/kvm/kvm_svm.h2
-rw-r--r--arch/x86/kvm/lapic.c35
-rw-r--r--arch/x86/kvm/mmu.c672
-rw-r--r--arch/x86/kvm/mmu.h6
-rw-r--r--arch/x86/kvm/paging_tmpl.h86
-rw-r--r--arch/x86/kvm/segment_descriptor.h29
-rw-r--r--arch/x86/kvm/svm.c352
-rw-r--r--arch/x86/kvm/svm.h3
-rw-r--r--arch/x86/kvm/tss.h59
-rw-r--r--arch/x86/kvm/vmx.c278
-rw-r--r--arch/x86/kvm/vmx.h10
-rw-r--r--arch/x86/kvm/x86.c897
-rw-r--r--arch/x86/kvm/x86_emulate.c285
-rw-r--r--arch/x86/lib/Makefile3
-rw-r--r--arch/x86/lib/bitops_32.c70
-rw-r--r--arch/x86/lib/bitops_64.c175
-rw-r--r--arch/x86/mach-voyager/voyager_smp.c14
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/init_32.c69
-rw-r--r--arch/x86/mm/init_64.c74
-rw-r--r--arch/x86/mm/ioremap.c46
-rw-r--r--arch/x86/mm/numa_64.c42
-rw-r--r--arch/x86/mm/pageattr.c4
-rw-r--r--arch/x86/mm/pat.c207
-rw-r--r--arch/x86/mm/pgtable.c276
-rw-r--r--arch/x86/mm/pgtable_32.c204
-rw-r--r--arch/x86/vdso/vdso.S10
-rw-r--r--arch/x86/xen/Kconfig2
-rw-r--r--arch/x86/xen/Makefile4
-rw-r--r--arch/x86/xen/enlighten.c54
-rw-r--r--arch/x86/xen/events.c591
-rw-r--r--arch/x86/xen/features.c29
-rw-r--r--arch/x86/xen/grant-table.c91
-rw-r--r--arch/x86/xen/mmu.c147
-rw-r--r--arch/x86/xen/setup.c21
-rw-r--r--arch/x86/xen/smp.c22
-rw-r--r--arch/x86/xen/xen-asm.S42
-rw-r--r--arch/x86/xen/xen-ops.h8
436 files changed, 27666 insertions, 10166 deletions
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index f10d2eddd2c..b04f1feb1dd 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -994,7 +994,7 @@ marvel_agp_configure(alpha_agp_info *agp)
* rate, but warn the user.
*/
printk("%s: unknown PLL setting RNGB=%lx (PLL6_CTL=%016lx)\n",
- __FUNCTION__, IO7_PLL_RNGB(agp_pll), agp_pll);
+ __func__, IO7_PLL_RNGB(agp_pll), agp_pll);
break;
}
@@ -1044,13 +1044,13 @@ marvel_agp_translate(alpha_agp_info *agp, dma_addr_t addr)
if (addr < agp->aperture.bus_base ||
addr >= agp->aperture.bus_base + agp->aperture.size) {
- printk("%s: addr out of range\n", __FUNCTION__);
+ printk("%s: addr out of range\n", __func__);
return -EINVAL;
}
pte = aper->arena->ptes[baddr >> PAGE_SHIFT];
if (!(pte & 1)) {
- printk("%s: pte not valid\n", __FUNCTION__);
+ printk("%s: pte not valid\n", __func__);
return -EINVAL;
}
return (pte >> 1) << PAGE_SHIFT;
diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c
index f5ca5255eb0..c0750291b44 100644
--- a/arch/alpha/kernel/core_t2.c
+++ b/arch/alpha/kernel/core_t2.c
@@ -336,10 +336,7 @@ t2_direct_map_window1(unsigned long base, unsigned long length)
#if DEBUG_PRINT_FINAL_SETTINGS
printk("%s: setting WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n",
- __FUNCTION__,
- *(vulp)T2_WBASE1,
- *(vulp)T2_WMASK1,
- *(vulp)T2_TBASE1);
+ __func__, *(vulp)T2_WBASE1, *(vulp)T2_WMASK1, *(vulp)T2_TBASE1);
#endif
}
@@ -366,10 +363,7 @@ t2_sg_map_window2(struct pci_controller *hose,
#if DEBUG_PRINT_FINAL_SETTINGS
printk("%s: setting WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n",
- __FUNCTION__,
- *(vulp)T2_WBASE2,
- *(vulp)T2_WMASK2,
- *(vulp)T2_TBASE2);
+ __func__, *(vulp)T2_WBASE2, *(vulp)T2_WMASK2, *(vulp)T2_TBASE2);
#endif
}
@@ -377,15 +371,15 @@ static void __init
t2_save_configuration(void)
{
#if DEBUG_PRINT_INITIAL_SETTINGS
- printk("%s: HAE_1 was 0x%lx\n", __FUNCTION__, srm_hae); /* HW is 0 */
- printk("%s: HAE_2 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_2);
- printk("%s: HAE_3 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_3);
- printk("%s: HAE_4 was 0x%lx\n", __FUNCTION__, *(vulp)T2_HAE_4);
- printk("%s: HBASE was 0x%lx\n", __FUNCTION__, *(vulp)T2_HBASE);
+ printk("%s: HAE_1 was 0x%lx\n", __func__, srm_hae); /* HW is 0 */
+ printk("%s: HAE_2 was 0x%lx\n", __func__, *(vulp)T2_HAE_2);
+ printk("%s: HAE_3 was 0x%lx\n", __func__, *(vulp)T2_HAE_3);
+ printk("%s: HAE_4 was 0x%lx\n", __func__, *(vulp)T2_HAE_4);
+ printk("%s: HBASE was 0x%lx\n", __func__, *(vulp)T2_HBASE);
- printk("%s: WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n", __FUNCTION__,
+ printk("%s: WBASE1=0x%lx WMASK1=0x%lx TBASE1=0x%lx\n", __func__,
*(vulp)T2_WBASE1, *(vulp)T2_WMASK1, *(vulp)T2_TBASE1);
- printk("%s: WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n", __FUNCTION__,
+ printk("%s: WBASE2=0x%lx WMASK2=0x%lx TBASE2=0x%lx\n", __func__,
*(vulp)T2_WBASE2, *(vulp)T2_WMASK2, *(vulp)T2_TBASE2);
#endif
diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c
index 819326627b9..319fcb74611 100644
--- a/arch/alpha/kernel/core_titan.c
+++ b/arch/alpha/kernel/core_titan.c
@@ -365,21 +365,21 @@ void __init
titan_init_arch(void)
{
#if 0
- printk("%s: titan_init_arch()\n", __FUNCTION__);
- printk("%s: CChip registers:\n", __FUNCTION__);
- printk("%s: CSR_CSC 0x%lx\n", __FUNCTION__, TITAN_cchip->csc.csr);
- printk("%s: CSR_MTR 0x%lx\n", __FUNCTION__, TITAN_cchip->mtr.csr);
- printk("%s: CSR_MISC 0x%lx\n", __FUNCTION__, TITAN_cchip->misc.csr);
- printk("%s: CSR_DIM0 0x%lx\n", __FUNCTION__, TITAN_cchip->dim0.csr);
- printk("%s: CSR_DIM1 0x%lx\n", __FUNCTION__, TITAN_cchip->dim1.csr);
- printk("%s: CSR_DIR0 0x%lx\n", __FUNCTION__, TITAN_cchip->dir0.csr);
- printk("%s: CSR_DIR1 0x%lx\n", __FUNCTION__, TITAN_cchip->dir1.csr);
- printk("%s: CSR_DRIR 0x%lx\n", __FUNCTION__, TITAN_cchip->drir.csr);
-
- printk("%s: DChip registers:\n", __FUNCTION__);
- printk("%s: CSR_DSC 0x%lx\n", __FUNCTION__, TITAN_dchip->dsc.csr);
- printk("%s: CSR_STR 0x%lx\n", __FUNCTION__, TITAN_dchip->str.csr);
- printk("%s: CSR_DREV 0x%lx\n", __FUNCTION__, TITAN_dchip->drev.csr);
+ printk("%s: titan_init_arch()\n", __func__);
+ printk("%s: CChip registers:\n", __func__);
+ printk("%s: CSR_CSC 0x%lx\n", __func__, TITAN_cchip->csc.csr);
+ printk("%s: CSR_MTR 0x%lx\n", __func__, TITAN_cchip->mtr.csr);
+ printk("%s: CSR_MISC 0x%lx\n", __func__, TITAN_cchip->misc.csr);
+ printk("%s: CSR_DIM0 0x%lx\n", __func__, TITAN_cchip->dim0.csr);
+ printk("%s: CSR_DIM1 0x%lx\n", __func__, TITAN_cchip->dim1.csr);
+ printk("%s: CSR_DIR0 0x%lx\n", __func__, TITAN_cchip->dir0.csr);
+ printk("%s: CSR_DIR1 0x%lx\n", __func__, TITAN_cchip->dir1.csr);
+ printk("%s: CSR_DRIR 0x%lx\n", __func__, TITAN_cchip->drir.csr);
+
+ printk("%s: DChip registers:\n", __func__);
+ printk("%s: CSR_DSC 0x%lx\n", __func__, TITAN_dchip->dsc.csr);
+ printk("%s: CSR_STR 0x%lx\n", __func__, TITAN_dchip->str.csr);
+ printk("%s: CSR_DREV 0x%lx\n", __func__, TITAN_dchip->drev.csr);
#endif
boot_cpuid = __hard_smp_processor_id();
@@ -700,13 +700,13 @@ titan_agp_translate(alpha_agp_info *agp, dma_addr_t addr)
if (addr < agp->aperture.bus_base ||
addr >= agp->aperture.bus_base + agp->aperture.size) {
- printk("%s: addr out of range\n", __FUNCTION__);
+ printk("%s: addr out of range\n", __func__);
return -EINVAL;
}
pte = aper->arena->ptes[baddr >> PAGE_SHIFT];
if (!(pte & 1)) {
- printk("%s: pte not valid\n", __FUNCTION__);
+ printk("%s: pte not valid\n", __func__);
return -EINVAL;
}
diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c
index ef91e09590d..5e7c28f92f1 100644
--- a/arch/alpha/kernel/core_tsunami.c
+++ b/arch/alpha/kernel/core_tsunami.c
@@ -241,8 +241,6 @@ tsunami_probe_write(volatile unsigned long *vaddr)
#define tsunami_probe_read(ADDR) 1
#endif /* NXM_MACHINE_CHECKS_ON_TSUNAMI */
-#define FN __FUNCTION__
-
static void __init
tsunami_init_one_pchip(tsunami_pchip *pchip, int index)
{
@@ -383,27 +381,27 @@ tsunami_init_arch(void)
/* NXMs just don't matter to Tsunami--unless they make it
choke completely. */
tmp = (unsigned long)(TSUNAMI_cchip - 1);
- printk("%s: probing bogus address: 0x%016lx\n", FN, bogus_addr);
+ printk("%s: probing bogus address: 0x%016lx\n", __func__, bogus_addr);
printk("\tprobe %s\n",
tsunami_probe_write((unsigned long *)bogus_addr)
? "succeeded" : "failed");
#endif /* NXM_MACHINE_CHECKS_ON_TSUNAMI */
#if 0
- printk("%s: CChip registers:\n", FN);
- printk("%s: CSR_CSC 0x%lx\n", FN, TSUNAMI_cchip->csc.csr);
- printk("%s: CSR_MTR 0x%lx\n", FN, TSUNAMI_cchip.mtr.csr);
- printk("%s: CSR_MISC 0x%lx\n", FN, TSUNAMI_cchip->misc.csr);
- printk("%s: CSR_DIM0 0x%lx\n", FN, TSUNAMI_cchip->dim0.csr);
- printk("%s: CSR_DIM1 0x%lx\n", FN, TSUNAMI_cchip->dim1.csr);
- printk("%s: CSR_DIR0 0x%lx\n", FN, TSUNAMI_cchip->dir0.csr);
- printk("%s: CSR_DIR1 0x%lx\n", FN, TSUNAMI_cchip->dir1.csr);
- printk("%s: CSR_DRIR 0x%lx\n", FN, TSUNAMI_cchip->drir.csr);
+ printk("%s: CChip registers:\n", __func__);
+ printk("%s: CSR_CSC 0x%lx\n", __func__, TSUNAMI_cchip->csc.csr);
+ printk("%s: CSR_MTR 0x%lx\n", __func__, TSUNAMI_cchip.mtr.csr);
+ printk("%s: CSR_MISC 0x%lx\n", __func__, TSUNAMI_cchip->misc.csr);
+ printk("%s: CSR_DIM0 0x%lx\n", __func__, TSUNAMI_cchip->dim0.csr);
+ printk("%s: CSR_DIM1 0x%lx\n", __func__, TSUNAMI_cchip->dim1.csr);
+ printk("%s: CSR_DIR0 0x%lx\n", __func__, TSUNAMI_cchip->dir0.csr);
+ printk("%s: CSR_DIR1 0x%lx\n", __func__, TSUNAMI_cchip->dir1.csr);
+ printk("%s: CSR_DRIR 0x%lx\n", __func__, TSUNAMI_cchip->drir.csr);
printk("%s: DChip registers:\n");
- printk("%s: CSR_DSC 0x%lx\n", FN, TSUNAMI_dchip->dsc.csr);
- printk("%s: CSR_STR 0x%lx\n", FN, TSUNAMI_dchip->str.csr);
- printk("%s: CSR_DREV 0x%lx\n", FN, TSUNAMI_dchip->drev.csr);
+ printk("%s: CSR_DSC 0x%lx\n", __func__, TSUNAMI_dchip->dsc.csr);
+ printk("%s: CSR_STR 0x%lx\n", __func__, TSUNAMI_dchip->str.csr);
+ printk("%s: CSR_DREV 0x%lx\n", __func__, TSUNAMI_dchip->drev.csr);
#endif
/* With multiple PCI busses, we play with I/O as physical addrs. */
ioport_resource.end = ~0UL;
diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c
index 026ba9af6d6..ebc3c894b5a 100644
--- a/arch/alpha/kernel/module.c
+++ b/arch/alpha/kernel/module.c
@@ -120,6 +120,12 @@ module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs,
nsyms = symtab->sh_size / sizeof(Elf64_Sym);
chains = kcalloc(nsyms, sizeof(struct got_entry), GFP_KERNEL);
+ if (!chains) {
+ printk(KERN_ERR
+ "module %s: no memory for symbol chain buffer\n",
+ me->name);
+ return -ENOMEM;
+ }
got->sh_size = 0;
got->sh_addralign = 8;
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 78357798b6f..baf57563b14 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -208,7 +208,7 @@ pdev_save_srm_config(struct pci_dev *dev)
tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
if (!tmp) {
- printk(KERN_ERR "%s: kmalloc() failed!\n", __FUNCTION__);
+ printk(KERN_ERR "%s: kmalloc() failed!\n", __func__);
return;
}
tmp->next = srm_saved_configs;
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index dd6e334ab9e..2179c602032 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -79,25 +79,21 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base,
#ifdef CONFIG_DISCONTIGMEM
- if (!NODE_DATA(nid) ||
- (NULL == (arena = alloc_bootmem_node(NODE_DATA(nid),
- sizeof(*arena))))) {
- printk("%s: couldn't allocate arena from node %d\n"
- " falling back to system-wide allocation\n",
- __FUNCTION__, nid);
- arena = alloc_bootmem(sizeof(*arena));
- }
-
- if (!NODE_DATA(nid) ||
- (NULL == (arena->ptes = __alloc_bootmem_node(NODE_DATA(nid),
- mem_size,
- align,
- 0)))) {
- printk("%s: couldn't allocate arena ptes from node %d\n"
- " falling back to system-wide allocation\n",
- __FUNCTION__, nid);
- arena->ptes = __alloc_bootmem(mem_size, align, 0);
- }
+ arena = alloc_bootmem_node(NODE_DATA(nid), sizeof(*arena));
+ if (!NODE_DATA(nid) || !arena) {
+ printk("%s: couldn't allocate arena from node %d\n"
+ " falling back to system-wide allocation\n",
+ __func__, nid);
+ arena = alloc_bootmem(sizeof(*arena));
+ }
+
+ arena->ptes = __alloc_bootmem_node(NODE_DATA(nid), mem_size, align, 0);
+ if (!NODE_DATA(nid) || !arena->ptes) {
+ printk("%s: couldn't allocate arena ptes from node %d\n"
+ " falling back to system-wide allocation\n",
+ __func__, nid);
+ arena->ptes = __alloc_bootmem(mem_size, align, 0);
+ }
#else /* CONFIG_DISCONTIGMEM */
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 63c2073401e..2525692db0a 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -755,7 +755,7 @@ smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry,
if (atomic_read(&data.unstarted_count) > 0) {
long start_time = jiffies;
printk(KERN_ERR "%s: initial timeout -- trying long wait\n",
- __FUNCTION__);
+ __func__);
timeout = jiffies + 30 * HZ;
while (atomic_read(&data.unstarted_count) > 0
&& time_before(jiffies, timeout))
@@ -764,7 +764,7 @@ smp_call_function_on_cpu (void (*func) (void *info), void *info, int retry,
long delta = jiffies - start_time;
printk(KERN_ERR
"%s: response %ld.%ld seconds into long wait\n",
- __FUNCTION__, delta / HZ,
+ __func__, delta / HZ,
(100 * (delta - ((delta / HZ) * HZ))) / HZ);
}
}
diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c
index f7dd081d57f..78ad7cd1bbd 100644
--- a/arch/alpha/kernel/srm_env.c
+++ b/arch/alpha/kernel/srm_env.c
@@ -199,7 +199,7 @@ srm_env_init(void)
printk(KERN_INFO "%s: This Alpha system doesn't "
"know about SRM (or you've booted "
"SRM->MILO->Linux, which gets "
- "misdetected)...\n", __FUNCTION__);
+ "misdetected)...\n", __func__);
return -ENODEV;
}
diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c
index d187d01d2a1..e53a1e1c2f2 100644
--- a/arch/alpha/kernel/sys_alcor.c
+++ b/arch/alpha/kernel/sys_alcor.c
@@ -259,7 +259,7 @@ alcor_init_pci(void)
if (dev && dev->devfn == PCI_DEVFN(6,0)) {
alpha_mv.sys.cia.gru_int_req_bits = XLT_GRU_INT_REQ_BITS;
printk(KERN_INFO "%s: Detected AS500 or XLT motherboard.\n",
- __FUNCTION__);
+ __func__);
}
pci_dev_put(dev);
}
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index 922143ea1cd..828449cd263 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -80,7 +80,7 @@ io7_get_irq_ctl(unsigned int irq, struct io7 **pio7)
if (!(io7 = marvel_find_io7(pid))) {
printk(KERN_ERR
"%s for nonexistent io7 -- vec %x, pid %d\n",
- __FUNCTION__, irq, pid);
+ __func__, irq, pid);
return NULL;
}
@@ -90,7 +90,7 @@ io7_get_irq_ctl(unsigned int irq, struct io7 **pio7)
if (irq >= 0x180) {
printk(KERN_ERR
"%s for invalid irq -- pid %d adjusted irq %x\n",
- __FUNCTION__, pid, irq);
+ __func__, pid, irq);
return NULL;
}
@@ -110,8 +110,8 @@ io7_enable_irq(unsigned int irq)
ctl = io7_get_irq_ctl(irq, &io7);
if (!ctl || !io7) {
- printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
- __FUNCTION__, irq);
+ printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
+ __func__, irq);
return;
}
@@ -130,8 +130,8 @@ io7_disable_irq(unsigned int irq)
ctl = io7_get_irq_ctl(irq, &io7);
if (!ctl || !io7) {
- printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
- __FUNCTION__, irq);
+ printk(KERN_ERR "%s: get_ctl failed for irq %x\n",
+ __func__, irq);
return;
}
diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c
index 906019cfa68..99a7f19da13 100644
--- a/arch/alpha/kernel/sys_sable.c
+++ b/arch/alpha/kernel/sys_sable.c
@@ -454,7 +454,7 @@ sable_lynx_enable_irq(unsigned int irq)
spin_unlock(&sable_lynx_irq_lock);
#if 0
printk("%s: mask 0x%lx bit 0x%x irq 0x%x\n",
- __FUNCTION__, mask, bit, irq);
+ __func__, mask, bit, irq);
#endif
}
@@ -470,7 +470,7 @@ sable_lynx_disable_irq(unsigned int irq)
spin_unlock(&sable_lynx_irq_lock);
#if 0
printk("%s: mask 0x%lx bit 0x%x irq 0x%x\n",
- __FUNCTION__, mask, bit, irq);
+ __func__, mask, bit, irq);
#endif
}
@@ -524,7 +524,7 @@ sable_lynx_srm_device_interrupt(unsigned long vector)
irq = sable_lynx_irq_swizzle->mask_to_irq[bit];
#if 0
printk("%s: vector 0x%lx bit 0x%x irq 0x%x\n",
- __FUNCTION__, vector, bit, irq);
+ __func__, vector, bit, irq);
#endif
handle_irq(irq);
}
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index ee7b9009ebb..d4327e461c2 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -89,7 +89,7 @@ sio_pci_route(void)
/* First, ALWAYS read and print the original setting. */
pci_bus_read_config_dword(pci_isa_hose->bus, PCI_DEVFN(7, 0), 0x60,
&orig_route_tab);
- printk("%s: PIRQ original 0x%x new 0x%x\n", __FUNCTION__,
+ printk("%s: PIRQ original 0x%x new 0x%x\n", __func__,
orig_route_tab, alpha_mv.sys.sio.route_tab);
#if defined(ALPHA_RESTORE_SRM_SETUP)
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 2dc7f9fed21..dc57790250d 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -8,6 +8,7 @@
* This file initializes the trap entry points
*/
+#include <linux/jiffies.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/tty.h>
@@ -770,7 +771,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
unsigned long reg, struct pt_regs *regs)
{
static int cnt = 0;
- static long last_time = 0;
+ static unsigned long last_time;
unsigned long tmp1, tmp2, tmp3, tmp4;
unsigned long fake_reg, *reg_addr = &fake_reg;
@@ -781,7 +782,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
with the unaliged access. */
if (!test_thread_flag (TIF_UAC_NOPRINT)) {
- if (cnt >= 5 && jiffies - last_time > 5*HZ) {
+ if (cnt >= 5 && time_after(jiffies, last_time + 5 * HZ)) {
cnt = 0;
}
if (++cnt < 5) {
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 37cd547855b..728bb8f3944 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -539,6 +539,17 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
at91_set_B_periph(AT91_PIN_PB28, 0); /* LCDD23 */
#endif
+ if (ARRAY_SIZE(lcdc_resources) > 2) {
+ void __iomem *fb;
+ struct resource *fb_res = &lcdc_resources[2];
+ size_t fb_len = fb_res->end - fb_res->start + 1;
+
+ fb = ioremap_writecombine(fb_res->start, fb_len);
+ if (fb) {
+ memset(fb, 0, fb_len);
+ iounmap(fb, fb_len);
+ }
+ }
lcdc_data = *data;
platform_device_register(&at91_lcdc_device);
}
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index dbb9a5fc209..054689804e7 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -381,6 +381,20 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
at91_set_B_periph(AT91_PIN_PC24, 0); /* LCDD22 */
at91_set_B_periph(AT91_PIN_PC25, 0); /* LCDD23 */
+#ifdef CONFIG_FB_INTSRAM
+ {
+ void __iomem *fb;
+ struct resource *fb_res = &lcdc_resources[2];
+ size_t fb_len = fb_res->end - fb_res->start + 1;
+
+ fb = ioremap_writecombine(fb_res->start, fb_len);
+ if (fb) {
+ memset(fb, 0, fb_len);
+ iounmap(fb, fb_len);
+ }
+ }
+#endif
+
lcdc_data = *data;
platform_device_register(&at91_lcdc_device);
}
diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c
index 2687b730e2d..ce48c14f434 100644
--- a/arch/avr32/kernel/setup.c
+++ b/arch/avr32/kernel/setup.c
@@ -274,6 +274,8 @@ static int __init early_parse_fbmem(char *p)
printk(KERN_WARNING
"Failed to allocate framebuffer memory\n");
fbmem_size = 0;
+ } else {
+ memset(__va(fbmem_start), 0, fbmem_size);
}
}
diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c
index 4207a2b5275..5b06ffa15e3 100644
--- a/arch/cris/mm/init.c
+++ b/arch/cris/mm/init.c
@@ -27,7 +27,6 @@ show_mem(void)
printk("\nMem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
i = max_mapnr;
while (i-- > 0) {
total++;
diff --git a/arch/frv/kernel/traps.c b/arch/frv/kernel/traps.c
index 7089c2428b3..a40df80b2eb 100644
--- a/arch/frv/kernel/traps.c
+++ b/arch/frv/kernel/traps.c
@@ -49,7 +49,7 @@ asmlinkage void insn_access_error(unsigned long esfr1, unsigned long epcr0, unsi
info.si_signo = SIGSEGV;
info.si_code = SEGV_ACCERR;
info.si_errno = 0;
- info.si_addr = (void *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
+ info.si_addr = (void __user *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
force_sig_info(info.si_signo, &info, current);
} /* end insn_access_error() */
@@ -73,7 +73,7 @@ asmlinkage void illegal_instruction(unsigned long esfr1, unsigned long epcr0, un
epcr0, esr0, esfr1);
info.si_errno = 0;
- info.si_addr = (void *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
+ info.si_addr = (void __user *) ((epcr0 & EPCR0_V) ? (epcr0 & EPCR0_PC) : __frame->pc);
switch (__frame->tbr & TBR_TT) {
case TBR_TT_ILLEGAL_INSTR:
@@ -111,7 +111,8 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
unsigned long esr0)
{
static DEFINE_SPINLOCK(atomic_op_lock);
- unsigned long x, y, z, *p;
+ unsigned long x, y, z;
+ unsigned long __user *p;
mm_segment_t oldfs;
siginfo_t info;
int ret;
@@ -128,7 +129,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* u32 __atomic_user_cmpxchg32(u32 *ptr, u32 test, u32 new)
*/
case TBR_TT_ATOMIC_CMPXCHG32:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
y = __frame->gr10;
@@ -158,7 +159,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* u32 __atomic_kernel_xchg32(void *v, u32 new)
*/
case TBR_TT_ATOMIC_XCHG32:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
y = __frame->gr9;
for (;;) {
@@ -181,7 +182,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* ulong __atomic_kernel_XOR_return(ulong i, ulong *v)
*/
case TBR_TT_ATOMIC_XOR:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
for (;;) {
@@ -205,7 +206,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* ulong __atomic_kernel_OR_return(ulong i, ulong *v)
*/
case TBR_TT_ATOMIC_OR:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
for (;;) {
@@ -229,7 +230,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* ulong __atomic_kernel_AND_return(ulong i, ulong *v)
*/
case TBR_TT_ATOMIC_AND:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
for (;;) {
@@ -253,7 +254,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* int __atomic_user_sub_return(atomic_t *v, int i)
*/
case TBR_TT_ATOMIC_SUB:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
for (;;) {
@@ -277,7 +278,7 @@ asmlinkage void atomic_operation(unsigned long esfr1, unsigned long epcr0,
* int __atomic_user_add_return(atomic_t *v, int i)
*/
case TBR_TT_ATOMIC_ADD:
- p = (unsigned long *) __frame->gr8;
+ p = (unsigned long __user *) __frame->gr8;
x = __frame->gr9;
for (;;) {
@@ -322,7 +323,7 @@ error:
info.si_signo = SIGSEGV;
info.si_code = SEGV_ACCERR;
info.si_errno = 0;
- info.si_addr = (void *) __frame->pc;
+ info.si_addr = (void __user *) __frame->pc;
force_sig_info(info.si_signo, &info, current);
}
@@ -343,7 +344,7 @@ asmlinkage void media_exception(unsigned long msr0, unsigned long msr1)
info.si_signo = SIGFPE;
info.si_code = FPE_MDAOVF;
info.si_errno = 0;
- info.si_addr = (void *) __frame->pc;
+ info.si_addr = (void __user *) __frame->pc;
force_sig_info(info.si_signo, &info, current);
} /* end media_exception() */
@@ -383,7 +384,7 @@ asmlinkage void memory_access_exception(unsigned long esr0,
info.si_addr = NULL;
if ((esr0 & (ESRx_VALID | ESR0_EAV)) == (ESRx_VALID | ESR0_EAV))
- info.si_addr = (void *) ear0;
+ info.si_addr = (void __user *) ear0;
force_sig_info(info.si_signo, &info, current);
@@ -412,7 +413,7 @@ asmlinkage void data_access_error(unsigned long esfr1, unsigned long esr15, unsi
info.si_signo = SIGSEGV;
info.si_code = SEGV_ACCERR;
info.si_errno = 0;
- info.si_addr = (void *)
+ info.si_addr = (void __user *)
(((esr15 & (ESRx_VALID|ESR15_EAV)) == (ESRx_VALID|ESR15_EAV)) ? ear15 : 0);
force_sig_info(info.si_signo, &info, current);
@@ -446,7 +447,7 @@ asmlinkage void division_exception(unsigned long esfr1, unsigned long esr0, unsi
info.si_signo = SIGFPE;
info.si_code = FPE_INTDIV;
info.si_errno = 0;
- info.si_addr = (void *) __frame->pc;
+ info.si_addr = (void __user *) __frame->pc;
force_sig_info(info.si_signo, &info, current);
} /* end division_exception() */
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index cd13e138bd0..3aa6c821449 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -19,6 +19,7 @@ config IA64
select HAVE_OPROFILE
select HAVE_KPROBES
select HAVE_KRETPROBES
+ select HAVE_KVM
default y
help
The Itanium Processor Family is Intel's 64-bit successor to
@@ -589,6 +590,8 @@ config MSPEC
source "fs/Kconfig"
+source "arch/ia64/kvm/Kconfig"
+
source "lib/Kconfig"
#
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index f1645c4f703..ec4cca477f4 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -57,6 +57,7 @@ core-$(CONFIG_IA64_GENERIC) += arch/ia64/dig/
core-$(CONFIG_IA64_HP_ZX1) += arch/ia64/dig/
core-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += arch/ia64/dig/
core-$(CONFIG_IA64_SGI_SN2) += arch/ia64/sn/
+core-$(CONFIG_KVM) += arch/ia64/kvm/
drivers-$(CONFIG_PCI) += arch/ia64/pci/
drivers-$(CONFIG_IA64_HP_SIM) += arch/ia64/hp/sim/
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
new file mode 100644
index 00000000000..7914e482850
--- /dev/null
+++ b/arch/ia64/kvm/Kconfig
@@ -0,0 +1,49 @@
+#
+# KVM configuration
+#
+config HAVE_KVM
+ bool
+
+menuconfig VIRTUALIZATION
+ bool "Virtualization"
+ depends on HAVE_KVM || IA64
+ default y
+ ---help---
+ Say Y here to get to see options for using your Linux host to run other
+ operating systems inside virtual machines (guests).
+ This option alone does not add any kernel code.
+
+ If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRTUALIZATION
+
+config KVM
+ tristate "Kernel-based Virtual Machine (KVM) support"
+ depends on HAVE_KVM && EXPERIMENTAL
+ select PREEMPT_NOTIFIERS
+ select ANON_INODES
+ ---help---
+ Support hosting fully virtualized guest machines using hardware
+ virtualization extensions. You will need a fairly recent
+ processor equipped with virtualization extensions. You will also
+ need to select one or more of the processor modules below.
+
+ This module provides access to the hardware capabilities through
+ a character device node named /dev/kvm.
+
+ To compile this as a module, choose M here: the module
+ will be called kvm.
+
+ If unsure, say N.
+
+config KVM_INTEL
+ tristate "KVM for Intel Itanium 2 processors support"
+ depends on KVM && m
+ ---help---
+ Provides support for KVM on Itanium 2 processors equipped with the VT
+ extensions.
+
+config KVM_TRACE
+ bool
+
+endif # VIRTUALIZATION
diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile
new file mode 100644
index 00000000000..52353397a1a
--- /dev/null
+++ b/arch/ia64/kvm/Makefile
@@ -0,0 +1,58 @@
+#This Make file is to generate asm-offsets.h and build source.
+#
+
+#Generate asm-offsets.h for vmm module build
+offsets-file := asm-offsets.h
+
+always := $(offsets-file)
+targets := $(offsets-file)
+targets += arch/ia64/kvm/asm-offsets.s
+clean-files := $(addprefix $(objtree)/,$(targets) $(obj)/memcpy.S $(obj)/memset.S)
+
+# Default sed regexp - multiline due to syntax constraints
+define sed-y
+ "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
+endef
+
+quiet_cmd_offsets = GEN $@
+define cmd_offsets
+ (set -e; \
+ echo "#ifndef __ASM_KVM_OFFSETS_H__"; \
+ echo "#define __ASM_KVM_OFFSETS_H__"; \
+ echo "/*"; \
+ echo " * DO NOT MODIFY."; \
+ echo " *"; \
+ echo " * This file was generated by Makefile"; \
+ echo " *"; \
+ echo " */"; \
+ echo ""; \
+ sed -ne $(sed-y) $<; \
+ echo ""; \
+ echo "#endif" ) > $@
+endef
+# We use internal rules to avoid the "is up to date" message from make
+arch/ia64/kvm/asm-offsets.s: arch/ia64/kvm/asm-offsets.c
+ $(call if_changed_dep,cc_s_c)
+
+$(obj)/$(offsets-file): arch/ia64/kvm/asm-offsets.s
+ $(call cmd,offsets)
+
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
+EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+
+kvm-objs := $(common-objs) kvm-ia64.o kvm_fw.o
+obj-$(CONFIG_KVM) += kvm.o
+
+FORCE : $(obj)/$(offsets-file)
+EXTRA_CFLAGS_vcpu.o += -mfixed-range=f2-f5,f12-f127
+kvm-intel-objs = vmm.o vmm_ivt.o trampoline.o vcpu.o optvfault.o mmio.o \
+ vtlb.o process.o
+#Add link memcpy and memset to avoid possible structure assignment error
+kvm-intel-objs += ../lib/memset.o ../lib/memcpy.o
+obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/arch/ia64/kvm/asm-offsets.c b/arch/ia64/kvm/asm-offsets.c
new file mode 100644
index 00000000000..4e3dc13a619
--- /dev/null
+++ b/arch/ia64/kvm/asm-offsets.c
@@ -0,0 +1,251 @@
+/*
+ * asm-offsets.c Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed
+ * to extract and format the required data.
+ *
+ * Anthony Xu <anthony.xu@intel.com>
+ * Xiantao Zhang <xiantao.zhang@intel.com>
+ * Copyright (c) 2007 Intel Corporation KVM support.
+ *
+ * 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.
+ *
+ * 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/autoconf.h>
+#include <linux/kvm_host.h>
+
+#include "vcpu.h"
+
+#define task_struct kvm_vcpu
+
+#define DEFINE(sym, val) \
+ asm volatile("\n->" #sym " (%0) " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : :)
+
+#define OFFSET(_sym, _str, _mem) \
+ DEFINE(_sym, offsetof(_str, _mem));
+
+void foo(void)
+{
+ DEFINE(VMM_TASK_SIZE, sizeof(struct kvm_vcpu));
+ DEFINE(VMM_PT_REGS_SIZE, sizeof(struct kvm_pt_regs));
+
+ BLANK();
+
+ DEFINE(VMM_VCPU_META_RR0_OFFSET,
+ offsetof(struct kvm_vcpu, arch.metaphysical_rr0));
+ DEFINE(VMM_VCPU_META_SAVED_RR0_OFFSET,
+ offsetof(struct kvm_vcpu,
+ arch.metaphysical_saved_rr0));
+ DEFINE(VMM_VCPU_VRR0_OFFSET,
+ offsetof(struct kvm_vcpu, arch.vrr[0]));
+ DEFINE(VMM_VPD_IRR0_OFFSET,
+ offsetof(struct vpd, irr[0]));
+ DEFINE(VMM_VCPU_ITC_CHECK_OFFSET,
+ offsetof(struct kvm_vcpu, arch.itc_check));
+ DEFINE(VMM_VCPU_IRQ_CHECK_OFFSET,
+ offsetof(struct kvm_vcpu, arch.irq_check));
+ DEFINE(VMM_VPD_VHPI_OFFSET,
+ offsetof(struct vpd, vhpi));
+ DEFINE(VMM_VCPU_VSA_BASE_OFFSET,
+ offsetof(struct kvm_vcpu, arch.vsa_base));
+ DEFINE(VMM_VCPU_VPD_OFFSET,
+ offsetof(struct kvm_vcpu, arch.vpd));
+ DEFINE(VMM_VCPU_IRQ_CHECK,
+ offsetof(struct kvm_vcpu, arch.irq_check));
+ DEFINE(VMM_VCPU_TIMER_PENDING,
+ offsetof(struct kvm_vcpu, arch.timer_pending));
+ DEFINE(VMM_VCPU_META_SAVED_RR0_OFFSET,
+ offsetof(struct kvm_vcpu, arch.metaphysical_saved_rr0));
+ DEFINE(VMM_VCPU_MODE_FLAGS_OFFSET,
+ offsetof(struct kvm_vcpu, arch.mode_flags));
+ DEFINE(VMM_VCPU_ITC_OFS_OFFSET,
+ offsetof(struct kvm_vcpu, arch.itc_offset));
+ DEFINE(VMM_VCPU_LAST_ITC_OFFSET,
+ offsetof(struct kvm_vcpu, arch.last_itc));
+ DEFINE(VMM_VCPU_SAVED_GP_OFFSET,
+ offsetof(struct kvm_vcpu, arch.saved_gp));
+
+ BLANK();
+
+ DEFINE(VMM_PT_REGS_B6_OFFSET,
+ offsetof(struct kvm_pt_regs, b6));
+ DEFINE(VMM_PT_REGS_B7_OFFSET,
+ offsetof(struct kvm_pt_regs, b7));
+ DEFINE(VMM_PT_REGS_AR_CSD_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_csd));
+ DEFINE(VMM_PT_REGS_AR_SSD_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_ssd));
+ DEFINE(VMM_PT_REGS_R8_OFFSET,
+ offsetof(struct kvm_pt_regs, r8));
+ DEFINE(VMM_PT_REGS_R9_OFFSET,
+ offsetof(struct kvm_pt_regs, r9));
+ DEFINE(VMM_PT_REGS_R10_OFFSET,
+ offsetof(struct kvm_pt_regs, r10));
+ DEFINE(VMM_PT_REGS_R11_OFFSET,
+ offsetof(struct kvm_pt_regs, r11));
+ DEFINE(VMM_PT_REGS_CR_IPSR_OFFSET,
+ offsetof(struct kvm_pt_regs, cr_ipsr));
+ DEFINE(VMM_PT_REGS_CR_IIP_OFFSET,
+ offsetof(struct kvm_pt_regs, cr_iip));
+ DEFINE(VMM_PT_REGS_CR_IFS_OFFSET,
+ offsetof(struct kvm_pt_regs, cr_ifs));
+ DEFINE(VMM_PT_REGS_AR_UNAT_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_unat));
+ DEFINE(VMM_PT_REGS_AR_PFS_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_pfs));
+ DEFINE(VMM_PT_REGS_AR_RSC_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_rsc));
+ DEFINE(VMM_PT_REGS_AR_RNAT_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_rnat));
+
+ DEFINE(VMM_PT_REGS_AR_BSPSTORE_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_bspstore));
+ DEFINE(VMM_PT_REGS_PR_OFFSET,
+ offsetof(struct kvm_pt_regs, pr));
+ DEFINE(VMM_PT_REGS_B0_OFFSET,
+ offsetof(struct kvm_pt_regs, b0));
+ DEFINE(VMM_PT_REGS_LOADRS_OFFSET,
+ offsetof(struct kvm_pt_regs, loadrs));
+ DEFINE(VMM_PT_REGS_R1_OFFSET,
+ offsetof(struct kvm_pt_regs, r1));
+ DEFINE(VMM_PT_REGS_R12_OFFSET,
+ offsetof(struct kvm_pt_regs, r12));
+ DEFINE(VMM_PT_REGS_R13_OFFSET,
+ offsetof(struct kvm_pt_regs, r13));
+ DEFINE(VMM_PT_REGS_AR_FPSR_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_fpsr));
+ DEFINE(VMM_PT_REGS_R15_OFFSET,
+ offsetof(struct kvm_pt_regs, r15));
+ DEFINE(VMM_PT_REGS_R14_OFFSET,
+ offsetof(struct kvm_pt_regs, r14));
+ DEFINE(VMM_PT_REGS_R2_OFFSET,
+ offsetof(struct kvm_pt_regs, r2));
+ DEFINE(VMM_PT_REGS_R3_OFFSET,
+ offsetof(struct kvm_pt_regs, r3));
+ DEFINE(VMM_PT_REGS_R16_OFFSET,
+ offsetof(struct kvm_pt_regs, r16));
+ DEFINE(VMM_PT_REGS_R17_OFFSET,
+ offsetof(struct kvm_pt_regs, r17));
+ DEFINE(VMM_PT_REGS_R18_OFFSET,
+ offsetof(struct kvm_pt_regs, r18));
+ DEFINE(VMM_PT_REGS_R19_OFFSET,
+ offsetof(struct kvm_pt_regs, r19));
+ DEFINE(VMM_PT_REGS_R20_OFFSET,
+ offsetof(struct kvm_pt_regs, r20));
+ DEFINE(VMM_PT_REGS_R21_OFFSET,
+ offsetof(struct kvm_pt_regs, r21));
+ DEFINE(VMM_PT_REGS_R22_OFFSET,
+ offsetof(struct kvm_pt_regs, r22));
+ DEFINE(VMM_PT_REGS_R23_OFFSET,
+ offsetof(struct kvm_pt_regs, r23));
+ DEFINE(VMM_PT_REGS_R24_OFFSET,
+ offsetof(struct kvm_pt_regs, r24));
+ DEFINE(VMM_PT_REGS_R25_OFFSET,
+ offsetof(struct kvm_pt_regs, r25));
+ DEFINE(VMM_PT_REGS_R26_OFFSET,
+ offsetof(struct kvm_pt_regs, r26));
+ DEFINE(VMM_PT_REGS_R27_OFFSET,
+ offsetof(struct kvm_pt_regs, r27));
+ DEFINE(VMM_PT_REGS_R28_OFFSET,
+ offsetof(struct kvm_pt_regs, r28));
+ DEFINE(VMM_PT_REGS_R29_OFFSET,
+ offsetof(struct kvm_pt_regs, r29));
+ DEFINE(VMM_PT_REGS_R30_OFFSET,
+ offsetof(struct kvm_pt_regs, r30));
+ DEFINE(VMM_PT_REGS_R31_OFFSET,
+ offsetof(struct kvm_pt_regs, r31));
+ DEFINE(VMM_PT_REGS_AR_CCV_OFFSET,
+ offsetof(struct kvm_pt_regs, ar_ccv));
+ DEFINE(VMM_PT_REGS_F6_OFFSET,
+ offsetof(struct kvm_pt_regs, f6));
+ DEFINE(VMM_PT_REGS_F7_OFFSET,
+ offsetof(struct kvm_pt_regs, f7));
+ DEFINE(VMM_PT_REGS_F8_OFFSET,
+ offsetof(struct kvm_pt_regs, f8));
+ DEFINE(VMM_PT_REGS_F9_OFFSET,
+ offsetof(struct kvm_pt_regs, f9));
+ DEFINE(VMM_PT_REGS_F10_OFFSET,
+ offsetof(struct kvm_pt_regs, f10));
+ DEFINE(VMM_PT_REGS_F11_OFFSET,
+ offsetof(struct kvm_pt_regs, f11));
+ DEFINE(VMM_PT_REGS_R4_OFFSET,
+ offsetof(struct kvm_pt_regs, r4));
+ DEFINE(VMM_PT_REGS_R5_OFFSET,
+ offsetof(struct kvm_pt_regs, r5));
+ DEFINE(VMM_PT_REGS_R6_OFFSET,
+ offsetof(struct kvm_pt_regs, r6));
+ DEFINE(VMM_PT_REGS_R7_OFFSET,
+ offsetof(struct kvm_pt_regs, r7));
+ DEFINE(VMM_PT_REGS_EML_UNAT_OFFSET,
+ offsetof(struct kvm_pt_regs, eml_unat));
+ DEFINE(VMM_VCPU_IIPA_OFFSET,
+ offsetof(struct kvm_vcpu, arch.cr_iipa));
+ DEFINE(VMM_VCPU_OPCODE_OFFSET,
+ offsetof(struct kvm_vcpu, arch.opcode));
+ DEFINE(VMM_VCPU_CAUSE_OFFSET, offsetof(struct kvm_vcpu, arch.cause));
+ DEFINE(VMM_VCPU_ISR_OFFSET,
+ offsetof(struct kvm_vcpu, arch.cr_isr));
+ DEFINE(VMM_PT_REGS_R16_SLOT,
+ (((offsetof(struct kvm_pt_regs, r16)
+ - sizeof(struct kvm_pt_regs)) >> 3) & 0x3f));
+ DEFINE(VMM_VCPU_MODE_FLAGS_OFFSET,
+ offsetof(struct kvm_vcpu, arch.mode_flags));
+ DEFINE(VMM_VCPU_GP_OFFSET, offsetof(struct kvm_vcpu, arch.__gp));
+ BLANK();
+
+ DEFINE(VMM_VPD_BASE_OFFSET, offsetof(struct kvm_vcpu, arch.vpd));
+ DEFINE(VMM_VPD_VIFS_OFFSET, offsetof(struct vpd, ifs));
+ DEFINE(VMM_VLSAPIC_INSVC_BASE_OFFSET,
+ offsetof(struct kvm_vcpu, arch.insvc[0]));
+ DEFINE(VMM_VPD_VPTA_OFFSET, offsetof(struct vpd, pta));
+ DEFINE(VMM_VPD_VPSR_OFFSET, offsetof(struct vpd, vpsr));
+
+ DEFINE(VMM_CTX_R4_OFFSET, offsetof(union context, gr[4]));
+ DEFINE(VMM_CTX_R5_OFFSET, offsetof(union context, gr[5]));
+ DEFINE(VMM_CTX_R12_OFFSET, offsetof(union context, gr[12]));
+ DEFINE(VMM_CTX_R13_OFFSET, offsetof(union context, gr[13]));
+ DEFINE(VMM_CTX_KR0_OFFSET, offsetof(union context, ar[0]));
+ DEFINE(VMM_CTX_KR1_OFFSET, offsetof(union context, ar[1]));
+ DEFINE(VMM_CTX_B0_OFFSET, offsetof(union context, br[0]));
+ DEFINE(VMM_CTX_B1_OFFSET, offsetof(union context, br[1]));
+ DEFINE(VMM_CTX_B2_OFFSET, offsetof(union context, br[2]));
+ DEFINE(VMM_CTX_RR0_OFFSET, offsetof(union context, rr[0]));
+ DEFINE(VMM_CTX_RSC_OFFSET, offsetof(union context, ar[16]));
+ DEFINE(VMM_CTX_BSPSTORE_OFFSET, offsetof(union context, ar[18]));
+ DEFINE(VMM_CTX_RNAT_OFFSET, offsetof(union context, ar[19]));
+ DEFINE(VMM_CTX_FCR_OFFSET, offsetof(union context, ar[21]));
+ DEFINE(VMM_CTX_EFLAG_OFFSET, offsetof(union context, ar[24]));
+ DEFINE(VMM_CTX_CFLG_OFFSET, offsetof(union context, ar[27]));
+ DEFINE(VMM_CTX_FSR_OFFSET, offsetof(union context, ar[28]));
+ DEFINE(VMM_CTX_FIR_OFFSET, offsetof(union context, ar[29]));
+ DEFINE(VMM_CTX_FDR_OFFSET, offsetof(union context, ar[30]));
+ DEFINE(VMM_CTX_UNAT_OFFSET, offsetof(union context, ar[36]));
+ DEFINE(VMM_CTX_FPSR_OFFSET, offsetof(union context, ar[40]));
+ DEFINE(VMM_CTX_PFS_OFFSET, offsetof(union context, ar[64]));
+ DEFINE(VMM_CTX_LC_OFFSET, offsetof(union context, ar[65]));
+ DEFINE(VMM_CTX_DCR_OFFSET, offsetof(union context, cr[0]));
+ DEFINE(VMM_CTX_IVA_OFFSET, offsetof(union context, cr[2]));
+ DEFINE(VMM_CTX_PTA_OFFSET, offsetof(union context, cr[8]));
+ DEFINE(VMM_CTX_IBR0_OFFSET, offsetof(union context, ibr[0]));
+ DEFINE(VMM_CTX_DBR0_OFFSET, offsetof(union context, dbr[0]));
+ DEFINE(VMM_CTX_F2_OFFSET, offsetof(union context, fr[2]));
+ DEFINE(VMM_CTX_F3_OFFSET, offsetof(union context, fr[3]));
+ DEFINE(VMM_CTX_F32_OFFSET, offsetof(union context, fr[32]));
+ DEFINE(VMM_CTX_F33_OFFSET, offsetof(union context, fr[33]));
+ DEFINE(VMM_CTX_PKR0_OFFSET, offsetof(union context, pkr[0]));
+ DEFINE(VMM_CTX_PSR_OFFSET, offsetof(union context, psr));
+ BLANK();
+}
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
new file mode 100644
index 00000000000..6df07324013
--- /dev/null
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -0,0 +1,1806 @@
+
+/*
+ * kvm_ia64.c: Basic KVM suppport On Itanium series processors
+ *
+ *
+ * Copyright (C) 2007, Intel Corporation.
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/bitops.h>
+#include <linux/hrtimer.h>
+#include <linux/uaccess.h>
+
+#include <asm/pgtable.h>
+#include <asm/gcc_intrin.h>
+#include <asm/pal.h>
+#include <asm/cacheflush.h>
+#include <asm/div64.h>
+#include <asm/tlb.h>
+
+#include "misc.h"
+#include "vti.h"
+#include "iodev.h"
+#include "ioapic.h"
+#include "lapic.h"
+
+static unsigned long kvm_vmm_base;
+static unsigned long kvm_vsa_base;
+static unsigned long kvm_vm_buffer;
+static unsigned long kvm_vm_buffer_size;
+unsigned long kvm_vmm_gp;
+
+static long vp_env_info;
+
+static struct kvm_vmm_info *kvm_vmm_info;
+
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+ { NULL }
+};
+
+
+struct fdesc{
+ unsigned long ip;
+ unsigned long gp;
+};
+
+static void kvm_flush_icache(unsigned long start, unsigned long len)
+{
+ int l;
+
+ for (l = 0; l < (len + 32); l += 32)
+ ia64_fc(start + l);
+
+ ia64_sync_i();
+ ia64_srlz_i();
+}
+
+static void kvm_flush_tlb_all(void)
+{
+ unsigned long i, j, count0, count1, stride0, stride1, addr;
+ long flags;
+
+ addr = local_cpu_data->ptce_base;
+ count0 = local_cpu_data->ptce_count[0];
+ count1 = local_cpu_data->ptce_count[1];
+ stride0 = local_cpu_data->ptce_stride[0];
+ stride1 = local_cpu_data->ptce_stride[1];
+
+ local_irq_save(flags);
+ for (i = 0; i < count0; ++i) {
+ for (j = 0; j < count1; ++j) {
+ ia64_ptce(addr);
+ addr += stride1;
+ }
+ addr += stride0;
+ }
+ local_irq_restore(flags);
+ ia64_srlz_i(); /* srlz.i implies srlz.d */
+}
+
+long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
+{
+ struct ia64_pal_retval iprv;
+
+ PAL_CALL_STK(iprv, PAL_VP_CREATE, (u64)vpd, (u64)host_iva,
+ (u64)opt_handler);
+
+ return iprv.status;
+}
+
+static DEFINE_SPINLOCK(vp_lock);
+
+void kvm_arch_hardware_enable(void *garbage)
+{
+ long status;
+ long tmp_base;
+ unsigned long pte;
+ unsigned long saved_psr;
+ int slot;
+
+ pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
+ PAGE_KERNEL));
+ local_irq_save(saved_psr);
+ slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+ if (slot < 0)
+ return;
+ local_irq_restore(saved_psr);
+
+ spin_lock(&vp_lock);
+ status = ia64_pal_vp_init_env(kvm_vsa_base ?
+ VP_INIT_ENV : VP_INIT_ENV_INITALIZE,
+ __pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base);
+ if (status != 0) {
+ printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n");
+ return ;
+ }
+
+ if (!kvm_vsa_base) {
+ kvm_vsa_base = tmp_base;
+ printk(KERN_INFO"kvm: kvm_vsa_base:0x%lx\n", kvm_vsa_base);
+ }
+ spin_unlock(&vp_lock);
+ ia64_ptr_entry(0x3, slot);
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+
+ long status;
+ int slot;
+ unsigned long pte;
+ unsigned long saved_psr;
+ unsigned long host_iva = ia64_getreg(_IA64_REG_CR_IVA);
+
+ pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base),
+ PAGE_KERNEL));
+
+ local_irq_save(saved_psr);
+ slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+ if (slot < 0)
+ return;
+ local_irq_restore(saved_psr);
+
+ status = ia64_pal_vp_exit_env(host_iva);
+ if (status)
+ printk(KERN_DEBUG"kvm: Failed to disable VT support! :%ld\n",
+ status);
+ ia64_ptr_entry(0x3, slot);
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+ *(int *)rtn = 0;
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+
+ int r;
+
+ switch (ext) {
+ case KVM_CAP_IRQCHIP:
+ case KVM_CAP_USER_MEMORY:
+
+ r = 1;
+ break;
+ default:
+ r = 0;
+ }
+ return r;
+
+}
+
+static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
+ gpa_t addr)
+{
+ struct kvm_io_device *dev;
+
+ dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr);
+
+ return dev;
+}
+
+static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+ kvm_run->hw.hardware_exit_reason = 1;
+ return 0;
+}
+
+static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct kvm_mmio_req *p;
+ struct kvm_io_device *mmio_dev;
+
+ p = kvm_get_vcpu_ioreq(vcpu);
+
+ if ((p->addr & PAGE_MASK) == IOAPIC_DEFAULT_BASE_ADDRESS)
+ goto mmio;
+ vcpu->mmio_needed = 1;
+ vcpu->mmio_phys_addr = kvm_run->mmio.phys_addr = p->addr;
+ vcpu->mmio_size = kvm_run->mmio.len = p->size;
+ vcpu->mmio_is_write = kvm_run->mmio.is_write = !p->dir;
+
+ if (vcpu->mmio_is_write)
+ memcpy(vcpu->mmio_data, &p->data, p->size);
+ memcpy(kvm_run->mmio.data, &p->data, p->size);
+ kvm_run->exit_reason = KVM_EXIT_MMIO;
+ return 0;
+mmio:
+ mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr);
+ if (mmio_dev) {
+ if (!p->dir)
+ kvm_iodevice_write(mmio_dev, p->addr, p->size,
+ &p->data);
+ else
+ kvm_iodevice_read(mmio_dev, p->addr, p->size,
+ &p->data);
+
+ } else
+ printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
+ p->state = STATE_IORESP_READY;
+
+ return 1;
+}
+
+static int handle_pal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+
+ if (p->exit_reason == EXIT_REASON_PAL_CALL)
+ return kvm_pal_emul(vcpu, kvm_run);
+ else {
+ kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+ kvm_run->hw.hardware_exit_reason = 2;
+ return 0;
+ }
+}
+
+static int handle_sal_call(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+
+ if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+ kvm_sal_emul(vcpu);
+ return 1;
+ } else {
+ kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+ kvm_run->hw.hardware_exit_reason = 3;
+ return 0;
+ }
+
+}
+
+/*
+ * offset: address offset to IPI space.
+ * value: deliver value.
+ */
+static void vcpu_deliver_ipi(struct kvm_vcpu *vcpu, uint64_t dm,
+ uint64_t vector)
+{
+ switch (dm) {
+ case SAPIC_FIXED:
+ kvm_apic_set_irq(vcpu, vector, 0);
+ break;
+ case SAPIC_NMI:
+ kvm_apic_set_irq(vcpu, 2, 0);
+ break;
+ case SAPIC_EXTINT:
+ kvm_apic_set_irq(vcpu, 0, 0);
+ break;
+ case SAPIC_INIT:
+ case SAPIC_PMI:
+ default:
+ printk(KERN_ERR"kvm: Unimplemented Deliver reserved IPI!\n");
+ break;
+ }
+}
+
+static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
+ unsigned long eid)
+{
+ union ia64_lid lid;
+ int i;
+
+ for (i = 0; i < KVM_MAX_VCPUS; i++) {
+ if (kvm->vcpus[i]) {
+ lid.val = VCPU_LID(kvm->vcpus[i]);
+ if (lid.id == id && lid.eid == eid)
+ return kvm->vcpus[i];
+ }
+ }
+
+ return NULL;
+}
+
+static int handle_ipi(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct exit_ctl_data *p = kvm_get_exit_data(vcpu);
+ struct kvm_vcpu *target_vcpu;
+ struct kvm_pt_regs *regs;
+ union ia64_ipi_a addr = p->u.ipi_data.addr;
+ union ia64_ipi_d data = p->u.ipi_data.data;
+
+ target_vcpu = lid_to_vcpu(vcpu->kvm, addr.id, addr.eid);
+ if (!target_vcpu)
+ return handle_vm_error(vcpu, kvm_run);
+
+ if (!target_vcpu->arch.launched) {
+ regs = vcpu_regs(target_vcpu);
+
+ regs->cr_iip = vcpu->kvm->arch.rdv_sal_data.boot_ip;
+ regs->r1 = vcpu->kvm->arch.rdv_sal_data.boot_gp;
+
+ target_vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ if (waitqueue_active(&target_vcpu->wq))
+ wake_up_interruptible(&target_vcpu->wq);
+ } else {
+ vcpu_deliver_ipi(target_vcpu, data.dm, data.vector);
+ if (target_vcpu != vcpu)
+ kvm_vcpu_kick(target_vcpu);
+ }
+
+ return 1;
+}
+
+struct call_data {
+ struct kvm_ptc_g ptc_g_data;
+ struct kvm_vcpu *vcpu;
+};
+
+static void vcpu_global_purge(void *info)
+{
+ struct call_data *p = (struct call_data *)info;
+ struct kvm_vcpu *vcpu = p->vcpu;
+
+ if (test_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+ return;
+
+ set_bit(KVM_REQ_PTC_G, &vcpu->requests);
+ if (vcpu->arch.ptc_g_count < MAX_PTC_G_NUM) {
+ vcpu->arch.ptc_g_data[vcpu->arch.ptc_g_count++] =
+ p->ptc_g_data;
+ } else {
+ clear_bit(KVM_REQ_PTC_G, &vcpu->requests);
+ vcpu->arch.ptc_g_count = 0;
+ set_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests);
+ }
+}
+
+static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ struct exit_ctl_data *p = kvm_get_exit_data(vcpu);
+ struct kvm *kvm = vcpu->kvm;
+ struct call_data call_data;
+ int i;
+ call_data.ptc_g_data = p->u.ptc_g_data;
+
+ for (i = 0; i < KVM_MAX_VCPUS; i++) {
+ if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state ==
+ KVM_MP_STATE_UNINITIALIZED ||
+ vcpu == kvm->vcpus[i])
+ continue;
+
+ if (waitqueue_active(&kvm->vcpus[i]->wq))
+ wake_up_interruptible(&kvm->vcpus[i]->wq);
+
+ if (kvm->vcpus[i]->cpu != -1) {
+ call_data.vcpu = kvm->vcpus[i];
+ smp_call_function_single(kvm->vcpus[i]->cpu,
+ vcpu_global_purge, &call_data, 0, 1);
+ } else
+ printk(KERN_WARNING"kvm: Uninit vcpu received ipi!\n");
+
+ }
+ return 1;
+}
+
+static int handle_switch_rr6(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ return 1;
+}
+
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
+
+ ktime_t kt;
+ long itc_diff;
+ unsigned long vcpu_now_itc;
+
+ unsigned long expires;
+ struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
+ unsigned long cyc_per_usec = local_cpu_data->cyc_per_usec;
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+ vcpu_now_itc = ia64_getreg(_IA64_REG_AR_ITC) + vcpu->arch.itc_offset;
+
+ if (time_after(vcpu_now_itc, vpd->itm)) {
+ vcpu->arch.timer_check = 1;
+ return 1;
+ }
+ itc_diff = vpd->itm - vcpu_now_itc;
+ if (itc_diff < 0)
+ itc_diff = -itc_diff;
+
+ expires = div64_64(itc_diff, cyc_per_usec);
+ kt = ktime_set(0, 1000 * expires);
+ vcpu->arch.ht_active = 1;
+ hrtimer_start(p_ht, kt, HRTIMER_MODE_ABS);
+
+ if (irqchip_in_kernel(vcpu->kvm)) {
+ vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+ kvm_vcpu_block(vcpu);
+ hrtimer_cancel(p_ht);
+ vcpu->arch.ht_active = 0;
+
+ if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
+ return -EINTR;
+ return 1;
+ } else {
+ printk(KERN_ERR"kvm: Unsupported userspace halt!");
+ return 0;
+ }
+}
+
+static int handle_vm_shutdown(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
+{
+ kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+ return 0;
+}
+
+static int handle_external_interrupt(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
+{
+ return 1;
+}
+
+static int (*kvm_vti_exit_handlers[])(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run) = {
+ [EXIT_REASON_VM_PANIC] = handle_vm_error,
+ [EXIT_REASON_MMIO_INSTRUCTION] = handle_mmio,
+ [EXIT_REASON_PAL_CALL] = handle_pal_call,
+ [EXIT_REASON_SAL_CALL] = handle_sal_call,
+ [EXIT_REASON_SWITCH_RR6] = handle_switch_rr6,
+ [EXIT_REASON_VM_DESTROY] = handle_vm_shutdown,
+ [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
+ [EXIT_REASON_IPI] = handle_ipi,
+ [EXIT_REASON_PTC_G] = handle_global_purge,
+
+};
+
+static const int kvm_vti_max_exit_handlers =
+ sizeof(kvm_vti_exit_handlers)/sizeof(*kvm_vti_exit_handlers);
+
+static void kvm_prepare_guest_switch(struct kvm_vcpu *vcpu)
+{
+}
+
+static uint32_t kvm_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p_exit_data;
+
+ p_exit_data = kvm_get_exit_data(vcpu);
+ return p_exit_data->exit_reason;
+}
+
+/*
+ * The guest has exited. See if we can fix it or if we need userspace
+ * assistance.
+ */
+static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+ u32 exit_reason = kvm_get_exit_reason(vcpu);
+ vcpu->arch.last_exit = exit_reason;
+
+ if (exit_reason < kvm_vti_max_exit_handlers
+ && kvm_vti_exit_handlers[exit_reason])
+ return kvm_vti_exit_handlers[exit_reason](vcpu, kvm_run);
+ else {
+ kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+ kvm_run->hw.hardware_exit_reason = exit_reason;
+ }
+ return 0;
+}
+
+static inline void vti_set_rr6(unsigned long rr6)
+{
+ ia64_set_rr(RR6, rr6);
+ ia64_srlz_i();
+}
+
+static int kvm_insert_vmm_mapping(struct kvm_vcpu *vcpu)
+{
+ unsigned long pte;
+ struct kvm *kvm = vcpu->kvm;
+ int r;
+
+ /*Insert a pair of tr to map vmm*/
+ pte = pte_val(mk_pte_phys(__pa(kvm_vmm_base), PAGE_KERNEL));
+ r = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
+ if (r < 0)
+ goto out;
+ vcpu->arch.vmm_tr_slot = r;
+ /*Insert a pairt of tr to map data of vm*/
+ pte = pte_val(mk_pte_phys(__pa(kvm->arch.vm_base), PAGE_KERNEL));
+ r = ia64_itr_entry(0x3, KVM_VM_DATA_BASE,
+ pte, KVM_VM_DATA_SHIFT);
+ if (r < 0)
+ goto out;
+ vcpu->arch.vm_tr_slot = r;
+ r = 0;
+out:
+ return r;
+
+}
+
+static void kvm_purge_vmm_mapping(struct kvm_vcpu *vcpu)
+{
+
+ ia64_ptr_entry(0x3, vcpu->arch.vmm_tr_slot);
+ ia64_ptr_entry(0x3, vcpu->arch.vm_tr_slot);
+
+}
+
+static int kvm_vcpu_pre_transition(struct kvm_vcpu *vcpu)
+{
+ int cpu = smp_processor_id();
+
+ if (vcpu->arch.last_run_cpu != cpu ||
+ per_cpu(last_vcpu, cpu) != vcpu) {
+ per_cpu(last_vcpu, cpu) = vcpu;
+ vcpu->arch.last_run_cpu = cpu;
+ kvm_flush_tlb_all();
+ }
+
+ vcpu->arch.host_rr6 = ia64_get_rr(RR6);
+ vti_set_rr6(vcpu->arch.vmm_rr);
+ return kvm_insert_vmm_mapping(vcpu);
+}
+static void kvm_vcpu_post_transition(struct kvm_vcpu *vcpu)
+{
+ kvm_purge_vmm_mapping(vcpu);
+ vti_set_rr6(vcpu->arch.host_rr6);
+}
+
+static int vti_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ union context *host_ctx, *guest_ctx;
+ int r;
+
+ /*Get host and guest context with guest address space.*/
+ host_ctx = kvm_get_host_context(vcpu);
+ guest_ctx = kvm_get_guest_context(vcpu);
+
+ r = kvm_vcpu_pre_transition(vcpu);
+ if (r < 0)
+ goto out;
+ kvm_vmm_info->tramp_entry(host_ctx, guest_ctx);
+ kvm_vcpu_post_transition(vcpu);
+ r = 0;
+out:
+ return r;
+}
+
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ int r;
+
+again:
+ preempt_disable();
+
+ kvm_prepare_guest_switch(vcpu);
+ local_irq_disable();
+
+ if (signal_pending(current)) {
+ local_irq_enable();
+ preempt_enable();
+ r = -EINTR;
+ kvm_run->exit_reason = KVM_EXIT_INTR;
+ goto out;
+ }
+
+ vcpu->guest_mode = 1;
+ kvm_guest_enter();
+
+ r = vti_vcpu_run(vcpu, kvm_run);
+ if (r < 0) {
+ local_irq_enable();
+ preempt_enable();
+ kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ goto out;
+ }
+
+ vcpu->arch.launched = 1;
+ vcpu->guest_mode = 0;
+ local_irq_enable();
+
+ /*
+ * We must have an instruction between local_irq_enable() and
+ * kvm_guest_exit(), so the timer interrupt isn't delayed by
+ * the interrupt shadow. The stat.exits increment will do nicely.
+ * But we need to prevent reordering, hence this barrier():
+ */
+ barrier();
+
+ kvm_guest_exit();
+
+ preempt_enable();
+
+ r = kvm_handle_exit(kvm_run, vcpu);
+
+ if (r > 0) {
+ if (!need_resched())
+ goto again;
+ }
+
+out:
+ if (r > 0) {
+ kvm_resched(vcpu);
+ goto again;
+ }
+
+ return r;
+}
+
+static void kvm_set_mmio_data(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmio_req *p = kvm_get_vcpu_ioreq(vcpu);
+
+ if (!vcpu->mmio_is_write)
+ memcpy(&p->data, vcpu->mmio_data, 8);
+ p->state = STATE_IORESP_READY;
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ int r;
+ sigset_t sigsaved;
+
+ vcpu_load(vcpu);
+
+ if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
+ kvm_vcpu_block(vcpu);
+ vcpu_put(vcpu);
+ return -EAGAIN;
+ }
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+ if (vcpu->mmio_needed) {
+ memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+ kvm_set_mmio_data(vcpu);
+ vcpu->mmio_read_completed = 1;
+ vcpu->mmio_needed = 0;
+ }
+ r = __vcpu_run(vcpu, kvm_run);
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+ vcpu_put(vcpu);
+ return r;
+}
+
+/*
+ * Allocate 16M memory for every vm to hold its specific data.
+ * Its memory map is defined in kvm_host.h.
+ */
+static struct kvm *kvm_alloc_kvm(void)
+{
+
+ struct kvm *kvm;
+ uint64_t vm_base;
+
+ vm_base = __get_free_pages(GFP_KERNEL, get_order(KVM_VM_DATA_SIZE));
+
+ if (!vm_base)
+ return ERR_PTR(-ENOMEM);
+ printk(KERN_DEBUG"kvm: VM data's base Address:0x%lx\n", vm_base);
+
+ /* Zero all pages before use! */
+ memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
+
+ kvm = (struct kvm *)(vm_base + KVM_VM_OFS);
+ kvm->arch.vm_base = vm_base;
+
+ return kvm;
+}
+
+struct kvm_io_range {
+ unsigned long start;
+ unsigned long size;
+ unsigned long type;
+};
+
+static const struct kvm_io_range io_ranges[] = {
+ {VGA_IO_START, VGA_IO_SIZE, GPFN_FRAME_BUFFER},
+ {MMIO_START, MMIO_SIZE, GPFN_LOW_MMIO},
+ {LEGACY_IO_START, LEGACY_IO_SIZE, GPFN_LEGACY_IO},
+ {IO_SAPIC_START, IO_SAPIC_SIZE, GPFN_IOSAPIC},
+ {PIB_START, PIB_SIZE, GPFN_PIB},
+};
+
+static void kvm_build_io_pmt(struct kvm *kvm)
+{
+ unsigned long i, j;
+
+ /* Mark I/O ranges */
+ for (i = 0; i < (sizeof(io_ranges) / sizeof(struct kvm_io_range));
+ i++) {
+ for (j = io_ranges[i].start;
+ j < io_ranges[i].start + io_ranges[i].size;
+ j += PAGE_SIZE)
+ kvm_set_pmt_entry(kvm, j >> PAGE_SHIFT,
+ io_ranges[i].type, 0);
+ }
+
+}
+
+/*Use unused rids to virtualize guest rid.*/
+#define GUEST_PHYSICAL_RR0 0x1739
+#define GUEST_PHYSICAL_RR4 0x2739
+#define VMM_INIT_RR 0x1660
+
+static void kvm_init_vm(struct kvm *kvm)
+{
+ long vm_base;
+
+ BUG_ON(!kvm);
+
+ kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
+ kvm->arch.metaphysical_rr4 = GUEST_PHYSICAL_RR4;
+ kvm->arch.vmm_init_rr = VMM_INIT_RR;
+
+ vm_base = kvm->arch.vm_base;
+ if (vm_base) {
+ kvm->arch.vhpt_base = vm_base + KVM_VHPT_OFS;
+ kvm->arch.vtlb_base = vm_base + KVM_VTLB_OFS;
+ kvm->arch.vpd_base = vm_base + KVM_VPD_OFS;
+ }
+
+ /*
+ *Fill P2M entries for MMIO/IO ranges
+ */
+ kvm_build_io_pmt(kvm);
+
+}
+
+struct kvm *kvm_arch_create_vm(void)
+{
+ struct kvm *kvm = kvm_alloc_kvm();
+
+ if (IS_ERR(kvm))
+ return ERR_PTR(-ENOMEM);
+ kvm_init_vm(kvm);
+
+ return kvm;
+
+}
+
+static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm,
+ struct kvm_irqchip *chip)
+{
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_IOAPIC:
+ memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm),
+ sizeof(struct kvm_ioapic_state));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
+static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_IOAPIC:
+ memcpy(ioapic_irqchip(kvm),
+ &chip->chip.ioapic,
+ sizeof(struct kvm_ioapic_state));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
+#define RESTORE_REGS(_x) vcpu->arch._x = regs->_x
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ int i;
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+ int r;
+
+ vcpu_load(vcpu);
+
+ for (i = 0; i < 16; i++) {
+ vpd->vgr[i] = regs->vpd.vgr[i];
+ vpd->vbgr[i] = regs->vpd.vbgr[i];
+ }
+ for (i = 0; i < 128; i++)
+ vpd->vcr[i] = regs->vpd.vcr[i];
+ vpd->vhpi = regs->vpd.vhpi;
+ vpd->vnat = regs->vpd.vnat;
+ vpd->vbnat = regs->vpd.vbnat;
+ vpd->vpsr = regs->vpd.vpsr;
+
+ vpd->vpr = regs->vpd.vpr;
+
+ r = -EFAULT;
+ r = copy_from_user(&vcpu->arch.guest, regs->saved_guest,
+ sizeof(union context));
+ if (r)
+ goto out;
+ r = copy_from_user(vcpu + 1, regs->saved_stack +
+ sizeof(struct kvm_vcpu),
+ IA64_STK_OFFSET - sizeof(struct kvm_vcpu));
+ if (r)
+ goto out;
+ vcpu->arch.exit_data =
+ ((struct kvm_vcpu *)(regs->saved_stack))->arch.exit_data;
+
+ RESTORE_REGS(mp_state);
+ RESTORE_REGS(vmm_rr);
+ memcpy(vcpu->arch.itrs, regs->itrs, sizeof(struct thash_data) * NITRS);
+ memcpy(vcpu->arch.dtrs, regs->dtrs, sizeof(struct thash_data) * NDTRS);
+ RESTORE_REGS(itr_regions);
+ RESTORE_REGS(dtr_regions);
+ RESTORE_REGS(tc_regions);
+ RESTORE_REGS(irq_check);
+ RESTORE_REGS(itc_check);
+ RESTORE_REGS(timer_check);
+ RESTORE_REGS(timer_pending);
+ RESTORE_REGS(last_itc);
+ for (i = 0; i < 8; i++) {
+ vcpu->arch.vrr[i] = regs->vrr[i];
+ vcpu->arch.ibr[i] = regs->ibr[i];
+ vcpu->arch.dbr[i] = regs->dbr[i];
+ }
+ for (i = 0; i < 4; i++)
+ vcpu->arch.insvc[i] = regs->insvc[i];
+ RESTORE_REGS(xtp);
+ RESTORE_REGS(metaphysical_rr0);
+ RESTORE_REGS(metaphysical_rr4);
+ RESTORE_REGS(metaphysical_saved_rr0);
+ RESTORE_REGS(metaphysical_saved_rr4);
+ RESTORE_REGS(fp_psr);
+ RESTORE_REGS(saved_gp);
+
+ vcpu->arch.irq_new_pending = 1;
+ vcpu->arch.itc_offset = regs->saved_itc - ia64_getreg(_IA64_REG_AR_ITC);
+ set_bit(KVM_REQ_RESUME, &vcpu->requests);
+
+ vcpu_put(vcpu);
+ r = 0;
+out:
+ return r;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm *kvm = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int r = -EINVAL;
+
+ switch (ioctl) {
+ case KVM_SET_MEMORY_REGION: {
+ struct kvm_memory_region kvm_mem;
+ struct kvm_userspace_memory_region kvm_userspace_mem;
+
+ r = -EFAULT;
+ if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
+ goto out;
+ kvm_userspace_mem.slot = kvm_mem.slot;
+ kvm_userspace_mem.flags = kvm_mem.flags;
+ kvm_userspace_mem.guest_phys_addr =
+ kvm_mem.guest_phys_addr;
+ kvm_userspace_mem.memory_size = kvm_mem.memory_size;
+ r = kvm_vm_ioctl_set_memory_region(kvm,
+ &kvm_userspace_mem, 0);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_CREATE_IRQCHIP:
+ r = -EFAULT;
+ r = kvm_ioapic_init(kvm);
+ if (r)
+ goto out;
+ break;
+ case KVM_IRQ_LINE: {
+ struct kvm_irq_level irq_event;
+
+ r = -EFAULT;
+ if (copy_from_user(&irq_event, argp, sizeof irq_event))
+ goto out;
+ if (irqchip_in_kernel(kvm)) {
+ mutex_lock(&kvm->lock);
+ kvm_ioapic_set_irq(kvm->arch.vioapic,
+ irq_event.irq,
+ irq_event.level);
+ mutex_unlock(&kvm->lock);
+ r = 0;
+ }
+ break;
+ }
+ case KVM_GET_IRQCHIP: {
+ /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+ struct kvm_irqchip chip;
+
+ r = -EFAULT;
+ if (copy_from_user(&chip, argp, sizeof chip))
+ goto out;
+ r = -ENXIO;
+ if (!irqchip_in_kernel(kvm))
+ goto out;
+ r = kvm_vm_ioctl_get_irqchip(kvm, &chip);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &chip, sizeof chip))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_IRQCHIP: {
+ /* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+ struct kvm_irqchip chip;
+
+ r = -EFAULT;
+ if (copy_from_user(&chip, argp, sizeof chip))
+ goto out;
+ r = -ENXIO;
+ if (!irqchip_in_kernel(kvm))
+ goto out;
+ r = kvm_vm_ioctl_set_irqchip(kvm, &chip);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
+ default:
+ ;
+ }
+out:
+ return r;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -EINVAL;
+
+}
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
+{
+
+ return -EINVAL;
+}
+
+static int kvm_alloc_vmm_area(void)
+{
+ if (!kvm_vmm_base && (kvm_vm_buffer_size < KVM_VM_BUFFER_SIZE)) {
+ kvm_vmm_base = __get_free_pages(GFP_KERNEL,
+ get_order(KVM_VMM_SIZE));
+ if (!kvm_vmm_base)
+ return -ENOMEM;
+
+ memset((void *)kvm_vmm_base, 0, KVM_VMM_SIZE);
+ kvm_vm_buffer = kvm_vmm_base + VMM_SIZE;
+
+ printk(KERN_DEBUG"kvm:VMM's Base Addr:0x%lx, vm_buffer:0x%lx\n",
+ kvm_vmm_base, kvm_vm_buffer);
+ }
+
+ return 0;
+}
+
+static void kvm_free_vmm_area(void)
+{
+ if (kvm_vmm_base) {
+ /*Zero this area before free to avoid bits leak!!*/
+ memset((void *)kvm_vmm_base, 0, KVM_VMM_SIZE);
+ free_pages(kvm_vmm_base, get_order(KVM_VMM_SIZE));
+ kvm_vmm_base = 0;
+ kvm_vm_buffer = 0;
+ kvm_vsa_base = 0;
+ }
+}
+
+/*
+ * Make sure that a cpu that is being hot-unplugged does not have any vcpus
+ * cached on it. Leave it as blank for IA64.
+ */
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+static void vti_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
+static int vti_init_vpd(struct kvm_vcpu *vcpu)
+{
+ int i;
+ union cpuid3_t cpuid3;
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+ if (IS_ERR(vpd))
+ return PTR_ERR(vpd);
+
+ /* CPUID init */
+ for (i = 0; i < 5; i++)
+ vpd->vcpuid[i] = ia64_get_cpuid(i);
+
+ /* Limit the CPUID number to 5 */
+ cpuid3.value = vpd->vcpuid[3];
+ cpuid3.number = 4; /* 5 - 1 */
+ vpd->vcpuid[3] = cpuid3.value;
+
+ /*Set vac and vdc fields*/
+ vpd->vac.a_from_int_cr = 1;
+ vpd->vac.a_to_int_cr = 1;
+ vpd->vac.a_from_psr = 1;
+ vpd->vac.a_from_cpuid = 1;
+ vpd->vac.a_cover = 1;
+ vpd->vac.a_bsw = 1;
+ vpd->vac.a_int = 1;
+ vpd->vdc.d_vmsw = 1;
+
+ /*Set virtual buffer*/
+ vpd->virt_env_vaddr = KVM_VM_BUFFER_BASE;
+
+ return 0;
+}
+
+static int vti_create_vp(struct kvm_vcpu *vcpu)
+{
+ long ret;
+ struct vpd *vpd = vcpu->arch.vpd;
+ unsigned long vmm_ivt;
+
+ vmm_ivt = kvm_vmm_info->vmm_ivt;
+
+ printk(KERN_DEBUG "kvm: vcpu:%p,ivt: 0x%lx\n", vcpu, vmm_ivt);
+
+ ret = ia64_pal_vp_create((u64 *)vpd, (u64 *)vmm_ivt, 0);
+
+ if (ret) {
+ printk(KERN_ERR"kvm: ia64_pal_vp_create failed!\n");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static void init_ptce_info(struct kvm_vcpu *vcpu)
+{
+ ia64_ptce_info_t ptce = {0};
+
+ ia64_get_ptce(&ptce);
+ vcpu->arch.ptce_base = ptce.base;
+ vcpu->arch.ptce_count[0] = ptce.count[0];
+ vcpu->arch.ptce_count[1] = ptce.count[1];
+ vcpu->arch.ptce_stride[0] = ptce.stride[0];
+ vcpu->arch.ptce_stride[1] = ptce.stride[1];
+}
+
+static void kvm_migrate_hlt_timer(struct kvm_vcpu *vcpu)
+{
+ struct hrtimer *p_ht = &vcpu->arch.hlt_timer;
+
+ if (hrtimer_cancel(p_ht))
+ hrtimer_start(p_ht, p_ht->expires, HRTIMER_MODE_ABS);
+}
+
+static enum hrtimer_restart hlt_timer_fn(struct hrtimer *data)
+{
+ struct kvm_vcpu *vcpu;
+ wait_queue_head_t *q;
+
+ vcpu = container_of(data, struct kvm_vcpu, arch.hlt_timer);
+ if (vcpu->arch.mp_state != KVM_MP_STATE_HALTED)
+ goto out;
+
+ q = &vcpu->wq;
+ if (waitqueue_active(q)) {
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ wake_up_interruptible(q);
+ }
+out:
+ vcpu->arch.timer_check = 1;
+ return HRTIMER_NORESTART;
+}
+
+#define PALE_RESET_ENTRY 0x80000000ffffffb0UL
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu *v;
+ int r;
+ int i;
+ long itc_offset;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ union context *p_ctx = &vcpu->arch.guest;
+ struct kvm_vcpu *vmm_vcpu = to_guest(vcpu->kvm, vcpu);
+
+ /*Init vcpu context for first run.*/
+ if (IS_ERR(vmm_vcpu))
+ return PTR_ERR(vmm_vcpu);
+
+ if (vcpu->vcpu_id == 0) {
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ /*Set entry address for first run.*/
+ regs->cr_iip = PALE_RESET_ENTRY;
+
+ /*Initilize itc offset for vcpus*/
+ itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
+ for (i = 0; i < MAX_VCPU_NUM; i++) {
+ v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+ v->arch.itc_offset = itc_offset;
+ v->arch.last_itc = 0;
+ }
+ } else
+ vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
+
+ r = -ENOMEM;
+ vcpu->arch.apic = kzalloc(sizeof(struct kvm_lapic), GFP_KERNEL);
+ if (!vcpu->arch.apic)
+ goto out;
+ vcpu->arch.apic->vcpu = vcpu;
+
+ p_ctx->gr[1] = 0;
+ p_ctx->gr[12] = (unsigned long)((char *)vmm_vcpu + IA64_STK_OFFSET);
+ p_ctx->gr[13] = (unsigned long)vmm_vcpu;
+ p_ctx->psr = 0x1008522000UL;
+ p_ctx->ar[40] = FPSR_DEFAULT; /*fpsr*/
+ p_ctx->caller_unat = 0;
+ p_ctx->pr = 0x0;
+ p_ctx->ar[36] = 0x0; /*unat*/
+ p_ctx->ar[19] = 0x0; /*rnat*/
+ p_ctx->ar[18] = (unsigned long)vmm_vcpu +
+ ((sizeof(struct kvm_vcpu)+15) & ~15);
+ p_ctx->ar[64] = 0x0; /*pfs*/
+ p_ctx->cr[0] = 0x7e04UL;
+ p_ctx->cr[2] = (unsigned long)kvm_vmm_info->vmm_ivt;
+ p_ctx->cr[8] = 0x3c;
+
+ /*Initilize region register*/
+ p_ctx->rr[0] = 0x30;
+ p_ctx->rr[1] = 0x30;
+ p_ctx->rr[2] = 0x30;
+ p_ctx->rr[3] = 0x30;
+ p_ctx->rr[4] = 0x30;
+ p_ctx->rr[5] = 0x30;
+ p_ctx->rr[7] = 0x30;
+
+ /*Initilize branch register 0*/
+ p_ctx->br[0] = *(unsigned long *)kvm_vmm_info->vmm_entry;
+
+ vcpu->arch.vmm_rr = kvm->arch.vmm_init_rr;
+ vcpu->arch.metaphysical_rr0 = kvm->arch.metaphysical_rr0;
+ vcpu->arch.metaphysical_rr4 = kvm->arch.metaphysical_rr4;
+
+ hrtimer_init(&vcpu->arch.hlt_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ vcpu->arch.hlt_timer.function = hlt_timer_fn;
+
+ vcpu->arch.last_run_cpu = -1;
+ vcpu->arch.vpd = (struct vpd *)VPD_ADDR(vcpu->vcpu_id);
+ vcpu->arch.vsa_base = kvm_vsa_base;
+ vcpu->arch.__gp = kvm_vmm_gp;
+ vcpu->arch.dirty_log_lock_pa = __pa(&kvm->arch.dirty_log_lock);
+ vcpu->arch.vhpt.hash = (struct thash_data *)VHPT_ADDR(vcpu->vcpu_id);
+ vcpu->arch.vtlb.hash = (struct thash_data *)VTLB_ADDR(vcpu->vcpu_id);
+ init_ptce_info(vcpu);
+
+ r = 0;
+out:
+ return r;
+}
+
+static int vti_vcpu_setup(struct kvm_vcpu *vcpu, int id)
+{
+ unsigned long psr;
+ int r;
+
+ local_irq_save(psr);
+ r = kvm_insert_vmm_mapping(vcpu);
+ if (r)
+ goto fail;
+ r = kvm_vcpu_init(vcpu, vcpu->kvm, id);
+ if (r)
+ goto fail;
+
+ r = vti_init_vpd(vcpu);
+ if (r) {
+ printk(KERN_DEBUG"kvm: vpd init error!!\n");
+ goto uninit;
+ }
+
+ r = vti_create_vp(vcpu);
+ if (r)
+ goto uninit;
+
+ kvm_purge_vmm_mapping(vcpu);
+ local_irq_restore(psr);
+
+ return 0;
+uninit:
+ kvm_vcpu_uninit(vcpu);
+fail:
+ return r;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
+ unsigned int id)
+{
+ struct kvm_vcpu *vcpu;
+ unsigned long vm_base = kvm->arch.vm_base;
+ int r;
+ int cpu;
+
+ r = -ENOMEM;
+ if (!vm_base) {
+ printk(KERN_ERR"kvm: Create vcpu[%d] error!\n", id);
+ goto fail;
+ }
+ vcpu = (struct kvm_vcpu *)(vm_base + KVM_VCPU_OFS + VCPU_SIZE * id);
+ vcpu->kvm = kvm;
+
+ cpu = get_cpu();
+ vti_vcpu_load(vcpu, cpu);
+ r = vti_vcpu_setup(vcpu, id);
+ put_cpu();
+
+ if (r) {
+ printk(KERN_DEBUG"kvm: vcpu_setup error!!\n");
+ goto fail;
+ }
+
+ return vcpu;
+fail:
+ return ERR_PTR(r);
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+ struct kvm_debug_guest *dbg)
+{
+ return -EINVAL;
+}
+
+static void free_kvm(struct kvm *kvm)
+{
+ unsigned long vm_base = kvm->arch.vm_base;
+
+ if (vm_base) {
+ memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
+ free_pages(vm_base, get_order(KVM_VM_DATA_SIZE));
+ }
+
+}
+
+static void kvm_release_vm_pages(struct kvm *kvm)
+{
+ struct kvm_memory_slot *memslot;
+ int i, j;
+ unsigned long base_gfn;
+
+ for (i = 0; i < kvm->nmemslots; i++) {
+ memslot = &kvm->memslots[i];
+ base_gfn = memslot->base_gfn;
+
+ for (j = 0; j < memslot->npages; j++) {
+ if (memslot->rmap[j])
+ put_page((struct page *)memslot->rmap[j]);
+ }
+ }
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+ kfree(kvm->arch.vioapic);
+ kvm_release_vm_pages(kvm);
+ kvm_free_physmem(kvm);
+ free_kvm(kvm);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ if (cpu != vcpu->cpu) {
+ vcpu->cpu = cpu;
+ if (vcpu->arch.ht_active)
+ kvm_migrate_hlt_timer(vcpu);
+ }
+}
+
+#define SAVE_REGS(_x) regs->_x = vcpu->arch._x
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ int i;
+ int r;
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+ vcpu_load(vcpu);
+
+ for (i = 0; i < 16; i++) {
+ regs->vpd.vgr[i] = vpd->vgr[i];
+ regs->vpd.vbgr[i] = vpd->vbgr[i];
+ }
+ for (i = 0; i < 128; i++)
+ regs->vpd.vcr[i] = vpd->vcr[i];
+ regs->vpd.vhpi = vpd->vhpi;
+ regs->vpd.vnat = vpd->vnat;
+ regs->vpd.vbnat = vpd->vbnat;
+ regs->vpd.vpsr = vpd->vpsr;
+ regs->vpd.vpr = vpd->vpr;
+
+ r = -EFAULT;
+ r = copy_to_user(regs->saved_guest, &vcpu->arch.guest,
+ sizeof(union context));
+ if (r)
+ goto out;
+ r = copy_to_user(regs->saved_stack, (void *)vcpu, IA64_STK_OFFSET);
+ if (r)
+ goto out;
+ SAVE_REGS(mp_state);
+ SAVE_REGS(vmm_rr);
+ memcpy(regs->itrs, vcpu->arch.itrs, sizeof(struct thash_data) * NITRS);
+ memcpy(regs->dtrs, vcpu->arch.dtrs, sizeof(struct thash_data) * NDTRS);
+ SAVE_REGS(itr_regions);
+ SAVE_REGS(dtr_regions);
+ SAVE_REGS(tc_regions);
+ SAVE_REGS(irq_check);
+ SAVE_REGS(itc_check);
+ SAVE_REGS(timer_check);
+ SAVE_REGS(timer_pending);
+ SAVE_REGS(last_itc);
+ for (i = 0; i < 8; i++) {
+ regs->vrr[i] = vcpu->arch.vrr[i];
+ regs->ibr[i] = vcpu->arch.ibr[i];
+ regs->dbr[i] = vcpu->arch.dbr[i];
+ }
+ for (i = 0; i < 4; i++)
+ regs->insvc[i] = vcpu->arch.insvc[i];
+ regs->saved_itc = vcpu->arch.itc_offset + ia64_getreg(_IA64_REG_AR_ITC);
+ SAVE_REGS(xtp);
+ SAVE_REGS(metaphysical_rr0);
+ SAVE_REGS(metaphysical_rr4);
+ SAVE_REGS(metaphysical_saved_rr0);
+ SAVE_REGS(metaphysical_saved_rr4);
+ SAVE_REGS(fp_psr);
+ SAVE_REGS(saved_gp);
+ vcpu_put(vcpu);
+ r = 0;
+out:
+ return r;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+
+ hrtimer_cancel(&vcpu->arch.hlt_timer);
+ kfree(vcpu->arch.apic);
+}
+
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ unsigned long i;
+ struct page *page;
+ int npages = mem->memory_size >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+ unsigned long base_gfn = memslot->base_gfn;
+
+ for (i = 0; i < npages; i++) {
+ page = gfn_to_page(kvm, base_gfn + i);
+ kvm_set_pmt_entry(kvm, base_gfn + i,
+ page_to_pfn(page) << PAGE_SHIFT,
+ _PAGE_AR_RWX|_PAGE_MA_WB);
+ memslot->rmap[i] = (unsigned long)page;
+ }
+
+ return 0;
+}
+
+
+long kvm_arch_dev_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ return -EINVAL;
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_vcpu_uninit(vcpu);
+}
+
+static int vti_cpu_has_kvm_support(void)
+{
+ long avail = 1, status = 1, control = 1;
+ long ret;
+
+ ret = ia64_pal_proc_get_features(&avail, &status, &control, 0);
+ if (ret)
+ goto out;
+
+ if (!(avail & PAL_PROC_VM_BIT))
+ goto out;
+
+ printk(KERN_DEBUG"kvm: Hardware Supports VT\n");
+
+ ret = ia64_pal_vp_env_info(&kvm_vm_buffer_size, &vp_env_info);
+ if (ret)
+ goto out;
+ printk(KERN_DEBUG"kvm: VM Buffer Size:0x%lx\n", kvm_vm_buffer_size);
+
+ if (!(vp_env_info & VP_OPCODE)) {
+ printk(KERN_WARNING"kvm: No opcode ability on hardware, "
+ "vm_env_info:0x%lx\n", vp_env_info);
+ }
+
+ return 1;
+out:
+ return 0;
+}
+
+static int kvm_relocate_vmm(struct kvm_vmm_info *vmm_info,
+ struct module *module)
+{
+ unsigned long module_base;
+ unsigned long vmm_size;
+
+ unsigned long vmm_offset, func_offset, fdesc_offset;
+ struct fdesc *p_fdesc;
+
+ BUG_ON(!module);
+
+ if (!kvm_vmm_base) {
+ printk("kvm: kvm area hasn't been initilized yet!!\n");
+ return -EFAULT;
+ }
+
+ /*Calculate new position of relocated vmm module.*/
+ module_base = (unsigned long)module->module_core;
+ vmm_size = module->core_size;
+ if (unlikely(vmm_size > KVM_VMM_SIZE))
+ return -EFAULT;
+
+ memcpy((void *)kvm_vmm_base, (void *)module_base, vmm_size);
+ kvm_flush_icache(kvm_vmm_base, vmm_size);
+
+ /*Recalculate kvm_vmm_info based on new VMM*/
+ vmm_offset = vmm_info->vmm_ivt - module_base;
+ kvm_vmm_info->vmm_ivt = KVM_VMM_BASE + vmm_offset;
+ printk(KERN_DEBUG"kvm: Relocated VMM's IVT Base Addr:%lx\n",
+ kvm_vmm_info->vmm_ivt);
+
+ fdesc_offset = (unsigned long)vmm_info->vmm_entry - module_base;
+ kvm_vmm_info->vmm_entry = (kvm_vmm_entry *)(KVM_VMM_BASE +
+ fdesc_offset);
+ func_offset = *(unsigned long *)vmm_info->vmm_entry - module_base;
+ p_fdesc = (struct fdesc *)(kvm_vmm_base + fdesc_offset);
+ p_fdesc->ip = KVM_VMM_BASE + func_offset;
+ p_fdesc->gp = KVM_VMM_BASE+(p_fdesc->gp - module_base);
+
+ printk(KERN_DEBUG"kvm: Relocated VMM's Init Entry Addr:%lx\n",
+ KVM_VMM_BASE+func_offset);
+
+ fdesc_offset = (unsigned long)vmm_info->tramp_entry - module_base;
+ kvm_vmm_info->tramp_entry = (kvm_tramp_entry *)(KVM_VMM_BASE +
+ fdesc_offset);
+ func_offset = *(unsigned long *)vmm_info->tramp_entry - module_base;
+ p_fdesc = (struct fdesc *)(kvm_vmm_base + fdesc_offset);
+ p_fdesc->ip = KVM_VMM_BASE + func_offset;
+ p_fdesc->gp = KVM_VMM_BASE + (p_fdesc->gp - module_base);
+
+ kvm_vmm_gp = p_fdesc->gp;
+
+ printk(KERN_DEBUG"kvm: Relocated VMM's Entry IP:%p\n",
+ kvm_vmm_info->vmm_entry);
+ printk(KERN_DEBUG"kvm: Relocated VMM's Trampoline Entry IP:0x%lx\n",
+ KVM_VMM_BASE + func_offset);
+
+ return 0;
+}
+
+int kvm_arch_init(void *opaque)
+{
+ int r;
+ struct kvm_vmm_info *vmm_info = (struct kvm_vmm_info *)opaque;
+
+ if (!vti_cpu_has_kvm_support()) {
+ printk(KERN_ERR "kvm: No Hardware Virtualization Support!\n");
+ r = -EOPNOTSUPP;
+ goto out;
+ }
+
+ if (kvm_vmm_info) {
+ printk(KERN_ERR "kvm: Already loaded VMM module!\n");
+ r = -EEXIST;
+ goto out;
+ }
+
+ r = -ENOMEM;
+ kvm_vmm_info = kzalloc(sizeof(struct kvm_vmm_info), GFP_KERNEL);
+ if (!kvm_vmm_info)
+ goto out;
+
+ if (kvm_alloc_vmm_area())
+ goto out_free0;
+
+ r = kvm_relocate_vmm(vmm_info, vmm_info->module);
+ if (r)
+ goto out_free1;
+
+ return 0;
+
+out_free1:
+ kvm_free_vmm_area();
+out_free0:
+ kfree(kvm_vmm_info);
+out:
+ return r;
+}
+
+void kvm_arch_exit(void)
+{
+ kvm_free_vmm_area();
+ kfree(kvm_vmm_info);
+ kvm_vmm_info = NULL;
+}
+
+static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
+ struct kvm_dirty_log *log)
+{
+ struct kvm_memory_slot *memslot;
+ int r, i;
+ long n, base;
+ unsigned long *dirty_bitmap = (unsigned long *)((void *)kvm - KVM_VM_OFS
+ + KVM_MEM_DIRTY_LOG_OFS);
+
+ r = -EINVAL;
+ if (log->slot >= KVM_MEMORY_SLOTS)
+ goto out;
+
+ memslot = &kvm->memslots[log->slot];
+ r = -ENOENT;
+ if (!memslot->dirty_bitmap)
+ goto out;
+
+ n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+ base = memslot->base_gfn / BITS_PER_LONG;
+
+ for (i = 0; i < n/sizeof(long); ++i) {
+ memslot->dirty_bitmap[i] = dirty_bitmap[base + i];
+ dirty_bitmap[base + i] = 0;
+ }
+ r = 0;
+out:
+ return r;
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+ struct kvm_dirty_log *log)
+{
+ int r;
+ int n;
+ struct kvm_memory_slot *memslot;
+ int is_dirty = 0;
+
+ spin_lock(&kvm->arch.dirty_log_lock);
+
+ r = kvm_ia64_sync_dirty_log(kvm, log);
+ if (r)
+ goto out;
+
+ r = kvm_get_dirty_log(kvm, log, &is_dirty);
+ if (r)
+ goto out;
+
+ /* If nothing is dirty, don't bother messing with page tables. */
+ if (is_dirty) {
+ kvm_flush_remote_tlbs(kvm);
+ memslot = &kvm->memslots[log->slot];
+ n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+ memset(memslot->dirty_bitmap, 0, n);
+ }
+ r = 0;
+out:
+ spin_unlock(&kvm->arch.dirty_log_lock);
+ return r;
+}
+
+int kvm_arch_hardware_setup(void)
+{
+ return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+static void vcpu_kick_intr(void *info)
+{
+#ifdef DEBUG
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info;
+ printk(KERN_DEBUG"vcpu_kick_intr %p \n", vcpu);
+#endif
+}
+
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+ int ipi_pcpu = vcpu->cpu;
+
+ if (waitqueue_active(&vcpu->wq))
+ wake_up_interruptible(&vcpu->wq);
+
+ if (vcpu->guest_mode)
+ smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+}
+
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig)
+{
+
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+ if (!test_and_set_bit(vec, &vpd->irr[0])) {
+ vcpu->arch.irq_new_pending = 1;
+ if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
+ kvm_vcpu_kick(vcpu);
+ else if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) {
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ if (waitqueue_active(&vcpu->wq))
+ wake_up_interruptible(&vcpu->wq);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
+{
+ return apic->vcpu->vcpu_id == dest;
+}
+
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
+{
+ return 0;
+}
+
+struct kvm_vcpu *kvm_get_lowest_prio_vcpu(struct kvm *kvm, u8 vector,
+ unsigned long bitmap)
+{
+ struct kvm_vcpu *lvcpu = kvm->vcpus[0];
+ int i;
+
+ for (i = 1; i < KVM_MAX_VCPUS; i++) {
+ if (!kvm->vcpus[i])
+ continue;
+ if (lvcpu->arch.xtp > kvm->vcpus[i]->arch.xtp)
+ lvcpu = kvm->vcpus[i];
+ }
+
+ return lvcpu;
+}
+
+static int find_highest_bits(int *dat)
+{
+ u32 bits, bitnum;
+ int i;
+
+ /* loop for all 256 bits */
+ for (i = 7; i >= 0 ; i--) {
+ bits = dat[i];
+ if (bits) {
+ bitnum = fls(bits);
+ return i * 32 + bitnum - 1;
+ }
+ }
+
+ return -1;
+}
+
+int kvm_highest_pending_irq(struct kvm_vcpu *vcpu)
+{
+ struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+
+ if (vpd->irr[0] & (1UL << NMI_VECTOR))
+ return NMI_VECTOR;
+ if (vpd->irr[0] & (1UL << ExtINT_VECTOR))
+ return ExtINT_VECTOR;
+
+ return find_highest_bits((int *)&vpd->irr[0]);
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ if (kvm_highest_pending_irq(vcpu) != -1)
+ return 1;
+ return 0;
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn;
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE;
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL;
+}
diff --git a/arch/ia64/kvm/kvm_fw.c b/arch/ia64/kvm/kvm_fw.c
new file mode 100644
index 00000000000..091f936c448
--- /dev/null
+++ b/arch/ia64/kvm/kvm_fw.c
@@ -0,0 +1,500 @@
+/*
+ * PAL/SAL call delegation
+ *
+ * Copyright (c) 2004 Li Susie <susie.li@intel.com>
+ * Copyright (c) 2005 Yu Ke <ke.yu@intel.com>
+ * Copyright (c) 2007 Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * 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.
+ *
+ * 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/kvm_host.h>
+#include <linux/smp.h>
+
+#include "vti.h"
+#include "misc.h"
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/tlb.h>
+
+/*
+ * Handy macros to make sure that the PAL return values start out
+ * as something meaningful.
+ */
+#define INIT_PAL_STATUS_UNIMPLEMENTED(x) \
+ { \
+ x.status = PAL_STATUS_UNIMPLEMENTED; \
+ x.v0 = 0; \
+ x.v1 = 0; \
+ x.v2 = 0; \
+ }
+
+#define INIT_PAL_STATUS_SUCCESS(x) \
+ { \
+ x.status = PAL_STATUS_SUCCESS; \
+ x.v0 = 0; \
+ x.v1 = 0; \
+ x.v2 = 0; \
+ }
+
+static void kvm_get_pal_call_data(struct kvm_vcpu *vcpu,
+ u64 *gr28, u64 *gr29, u64 *gr30, u64 *gr31) {
+ struct exit_ctl_data *p;
+
+ if (vcpu) {
+ p = &vcpu->arch.exit_data;
+ if (p->exit_reason == EXIT_REASON_PAL_CALL) {
+ *gr28 = p->u.pal_data.gr28;
+ *gr29 = p->u.pal_data.gr29;
+ *gr30 = p->u.pal_data.gr30;
+ *gr31 = p->u.pal_data.gr31;
+ return ;
+ }
+ }
+ printk(KERN_DEBUG"Failed to get vcpu pal data!!!\n");
+}
+
+static void set_pal_result(struct kvm_vcpu *vcpu,
+ struct ia64_pal_retval result) {
+
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+ if (p && p->exit_reason == EXIT_REASON_PAL_CALL) {
+ p->u.pal_data.ret = result;
+ return ;
+ }
+ INIT_PAL_STATUS_UNIMPLEMENTED(p->u.pal_data.ret);
+}
+
+static void set_sal_result(struct kvm_vcpu *vcpu,
+ struct sal_ret_values result) {
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+ if (p && p->exit_reason == EXIT_REASON_SAL_CALL) {
+ p->u.sal_data.ret = result;
+ return ;
+ }
+ printk(KERN_WARNING"Failed to set sal result!!\n");
+}
+
+struct cache_flush_args {
+ u64 cache_type;
+ u64 operation;
+ u64 progress;
+ long status;
+};
+
+cpumask_t cpu_cache_coherent_map;
+
+static void remote_pal_cache_flush(void *data)
+{
+ struct cache_flush_args *args = data;
+ long status;
+ u64 progress = args->progress;
+
+ status = ia64_pal_cache_flush(args->cache_type, args->operation,
+ &progress, NULL);
+ if (status != 0)
+ args->status = status;
+}
+
+static struct ia64_pal_retval pal_cache_flush(struct kvm_vcpu *vcpu)
+{
+ u64 gr28, gr29, gr30, gr31;
+ struct ia64_pal_retval result = {0, 0, 0, 0};
+ struct cache_flush_args args = {0, 0, 0, 0};
+ long psr;
+
+ gr28 = gr29 = gr30 = gr31 = 0;
+ kvm_get_pal_call_data(vcpu, &gr28, &gr29, &gr30, &gr31);
+
+ if (gr31 != 0)
+ printk(KERN_ERR"vcpu:%p called cache_flush error!\n", vcpu);
+
+ /* Always call Host Pal in int=1 */
+ gr30 &= ~PAL_CACHE_FLUSH_CHK_INTRS;
+ args.cache_type = gr29;
+ args.operation = gr30;
+ smp_call_function(remote_pal_cache_flush,
+ (void *)&args, 1, 1);
+ if (args.status != 0)
+ printk(KERN_ERR"pal_cache_flush error!,"
+ "status:0x%lx\n", args.status);
+ /*
+ * Call Host PAL cache flush
+ * Clear psr.ic when call PAL_CACHE_FLUSH
+ */
+ local_irq_save(psr);
+ result.status = ia64_pal_cache_flush(gr29, gr30, &result.v1,
+ &result.v0);
+ local_irq_restore(psr);
+ if (result.status != 0)
+ printk(KERN_ERR"vcpu:%p crashed due to cache_flush err:%ld"
+ "in1:%lx,in2:%lx\n",
+ vcpu, result.status, gr29, gr30);
+
+#if 0
+ if (gr29 == PAL_CACHE_TYPE_COHERENT) {
+ cpus_setall(vcpu->arch.cache_coherent_map);
+ cpu_clear(vcpu->cpu, vcpu->arch.cache_coherent_map);
+ cpus_setall(cpu_cache_coherent_map);
+ cpu_clear(vcpu->cpu, cpu_cache_coherent_map);
+ }
+#endif
+ return result;
+}
+
+struct ia64_pal_retval pal_cache_summary(struct kvm_vcpu *vcpu)
+{
+
+ struct ia64_pal_retval result;
+
+ PAL_CALL(result, PAL_CACHE_SUMMARY, 0, 0, 0);
+ return result;
+}
+
+static struct ia64_pal_retval pal_freq_base(struct kvm_vcpu *vcpu)
+{
+
+ struct ia64_pal_retval result;
+
+ PAL_CALL(result, PAL_FREQ_BASE, 0, 0, 0);
+
+ /*
+ * PAL_FREQ_BASE may not be implemented in some platforms,
+ * call SAL instead.
+ */
+ if (result.v0 == 0) {
+ result.status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
+ &result.v0,
+ &result.v1);
+ result.v2 = 0;
+ }
+
+ return result;
+}
+
+static struct ia64_pal_retval pal_freq_ratios(struct kvm_vcpu *vcpu)
+{
+
+ struct ia64_pal_retval result;
+
+ PAL_CALL(result, PAL_FREQ_RATIOS, 0, 0, 0);
+ return result;
+}
+
+static struct ia64_pal_retval pal_logical_to_physica(struct kvm_vcpu *vcpu)
+{
+ struct ia64_pal_retval result;
+
+ INIT_PAL_STATUS_UNIMPLEMENTED(result);
+ return result;
+}
+
+static struct ia64_pal_retval pal_platform_addr(struct kvm_vcpu *vcpu)
+{
+
+ struct ia64_pal_retval result;
+
+ INIT_PAL_STATUS_SUCCESS(result);
+ return result;
+}
+
+static struct ia64_pal_retval pal_proc_get_features(struct kvm_vcpu *vcpu)
+{
+
+ struct ia64_pal_retval result = {0, 0, 0, 0};
+ long in0, in1, in2, in3;
+
+ kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+ result.status = ia64_pal_proc_get_features(&result.v0, &result.v1,
+ &result.v2, in2);
+
+ return result;
+}
+
+static struct ia64_pal_retval pal_cache_info(struct kvm_vcpu *vcpu)
+{
+
+ pal_cache_config_info_t ci;
+ long status;
+ unsigned long in0, in1, in2, in3, r9, r10;
+
+ kvm_get_pal_call_data(vcpu, &in0, &in1, &in2, &in3);
+ status = ia64_pal_cache_config_info(in1, in2, &ci);
+ r9 = ci.pcci_info_1.pcci1_data;
+ r10 = ci.pcci_info_2.pcci2_data;
+ return ((struct ia64_pal_retval){status, r9, r10, 0});
+}
+
+#define GUEST_IMPL_VA_MSB 59
+#define GUEST_RID_BITS 18
+
+static struct ia64_pal_retval pal_vm_summary(struct kvm_vcpu *vcpu)
+{
+
+ pal_vm_info_1_u_t vminfo1;
+ pal_vm_info_2_u_t vminfo2;
+ struct ia64_pal_retval result;
+
+ PAL_CALL(result, PAL_VM_SUMMARY, 0, 0, 0);
+ if (!result.status) {
+ vminfo1.pvi1_val = result.v0;
+ vminfo1.pal_vm_info_1_s.max_itr_entry = 8;
+ vminfo1.pal_vm_info_1_s.max_dtr_entry = 8;
+ result.v0 = vminfo1.pvi1_val;
+ vminfo2.pal_vm_info_2_s.impl_va_msb = GUEST_IMPL_VA_MSB;
+ vminfo2.pal_vm_info_2_s.rid_size = GUEST_RID_BITS;
+ result.v1 = vminfo2.pvi2_val;
+ }
+
+ return result;
+}
+
+static struct ia64_pal_retval pal_vm_info(struct kvm_vcpu *vcpu)
+{
+ struct ia64_pal_retval result;
+
+ INIT_PAL_STATUS_UNIMPLEMENTED(result);
+
+ return result;
+}
+
+static u64 kvm_get_pal_call_index(struct kvm_vcpu *vcpu)
+{
+ u64 index = 0;
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+ if (p && (p->exit_reason == EXIT_REASON_PAL_CALL))
+ index = p->u.pal_data.gr28;
+
+ return index;
+}
+
+int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+
+ u64 gr28;
+ struct ia64_pal_retval result;
+ int ret = 1;
+
+ gr28 = kvm_get_pal_call_index(vcpu);
+ /*printk("pal_call index:%lx\n",gr28);*/
+ switch (gr28) {
+ case PAL_CACHE_FLUSH:
+ result = pal_cache_flush(vcpu);
+ break;
+ case PAL_CACHE_SUMMARY:
+ result = pal_cache_summary(vcpu);
+ break;
+ case PAL_HALT_LIGHT:
+ {
+ vcpu->arch.timer_pending = 1;
+ INIT_PAL_STATUS_SUCCESS(result);
+ if (kvm_highest_pending_irq(vcpu) == -1)
+ ret = kvm_emulate_halt(vcpu);
+
+ }
+ break;
+
+ case PAL_FREQ_RATIOS:
+ result = pal_freq_ratios(vcpu);
+ break;
+
+ case PAL_FREQ_BASE:
+ result = pal_freq_base(vcpu);
+ break;
+
+ case PAL_LOGICAL_TO_PHYSICAL :
+ result = pal_logical_to_physica(vcpu);
+ break;
+
+ case PAL_VM_SUMMARY :
+ result = pal_vm_summary(vcpu);
+ break;
+
+ case PAL_VM_INFO :
+ result = pal_vm_info(vcpu);
+ break;
+ case PAL_PLATFORM_ADDR :
+ result = pal_platform_addr(vcpu);
+ break;
+ case PAL_CACHE_INFO:
+ result = pal_cache_info(vcpu);
+ break;
+ case PAL_PTCE_INFO:
+ INIT_PAL_STATUS_SUCCESS(result);
+ result.v1 = (1L << 32) | 1L;
+ break;
+ case PAL_VM_PAGE_SIZE:
+ result.status = ia64_pal_vm_page_size(&result.v0,
+ &result.v1);
+ break;
+ case PAL_RSE_INFO:
+ result.status = ia64_pal_rse_info(&result.v0,
+ (pal_hints_u_t *)&result.v1);
+ break;
+ case PAL_PROC_GET_FEATURES:
+ result = pal_proc_get_features(vcpu);
+ break;
+ case PAL_DEBUG_INFO:
+ result.status = ia64_pal_debug_info(&result.v0,
+ &result.v1);
+ break;
+ case PAL_VERSION:
+ result.status = ia64_pal_version(
+ (pal_version_u_t *)&result.v0,
+ (pal_version_u_t *)&result.v1);
+
+ break;
+ case PAL_FIXED_ADDR:
+ result.status = PAL_STATUS_SUCCESS;
+ result.v0 = vcpu->vcpu_id;
+ break;
+ default:
+ INIT_PAL_STATUS_UNIMPLEMENTED(result);
+ printk(KERN_WARNING"kvm: Unsupported pal call,"
+ " index:0x%lx\n", gr28);
+ }
+ set_pal_result(vcpu, result);
+ return ret;
+}
+
+static struct sal_ret_values sal_emulator(struct kvm *kvm,
+ long index, unsigned long in1,
+ unsigned long in2, unsigned long in3,
+ unsigned long in4, unsigned long in5,
+ unsigned long in6, unsigned long in7)
+{
+ unsigned long r9 = 0;
+ unsigned long r10 = 0;
+ long r11 = 0;
+ long status;
+
+ status = 0;
+ switch (index) {
+ case SAL_FREQ_BASE:
+ status = ia64_sal_freq_base(in1, &r9, &r10);
+ break;
+ case SAL_PCI_CONFIG_READ:
+ printk(KERN_WARNING"kvm: Not allowed to call here!"
+ " SAL_PCI_CONFIG_READ\n");
+ break;
+ case SAL_PCI_CONFIG_WRITE:
+ printk(KERN_WARNING"kvm: Not allowed to call here!"
+ " SAL_PCI_CONFIG_WRITE\n");
+ break;
+ case SAL_SET_VECTORS:
+ if (in1 == SAL_VECTOR_OS_BOOT_RENDEZ) {
+ if (in4 != 0 || in5 != 0 || in6 != 0 || in7 != 0) {
+ status = -2;
+ } else {
+ kvm->arch.rdv_sal_data.boot_ip = in2;
+ kvm->arch.rdv_sal_data.boot_gp = in3;
+ }
+ printk("Rendvous called! iip:%lx\n\n", in2);
+ } else
+ printk(KERN_WARNING"kvm: CALLED SAL_SET_VECTORS %lu."
+ "ignored...\n", in1);
+ break;
+ case SAL_GET_STATE_INFO:
+ /* No more info. */
+ status = -5;
+ r9 = 0;
+ break;
+ case SAL_GET_STATE_INFO_SIZE:
+ /* Return a dummy size. */
+ status = 0;
+ r9 = 128;
+ break;
+ case SAL_CLEAR_STATE_INFO:
+ /* Noop. */
+ break;
+ case SAL_MC_RENDEZ:
+ printk(KERN_WARNING
+ "kvm: called SAL_MC_RENDEZ. ignored...\n");
+ break;
+ case SAL_MC_SET_PARAMS:
+ printk(KERN_WARNING
+ "kvm: called SAL_MC_SET_PARAMS.ignored!\n");
+ break;
+ case SAL_CACHE_FLUSH:
+ if (1) {
+ /*Flush using SAL.
+ This method is faster but has a side
+ effect on other vcpu running on
+ this cpu. */
+ status = ia64_sal_cache_flush(in1);
+ } else {
+ /*Maybe need to implement the method
+ without side effect!*/
+ status = 0;
+ }
+ break;
+ case SAL_CACHE_INIT:
+ printk(KERN_WARNING
+ "kvm: called SAL_CACHE_INIT. ignored...\n");
+ break;
+ case SAL_UPDATE_PAL:
+ printk(KERN_WARNING
+ "kvm: CALLED SAL_UPDATE_PAL. ignored...\n");
+ break;
+ default:
+ printk(KERN_WARNING"kvm: called SAL_CALL with unknown index."
+ " index:%ld\n", index);
+ status = -1;
+ break;
+ }
+ return ((struct sal_ret_values) {status, r9, r10, r11});
+}
+
+static void kvm_get_sal_call_data(struct kvm_vcpu *vcpu, u64 *in0, u64 *in1,
+ u64 *in2, u64 *in3, u64 *in4, u64 *in5, u64 *in6, u64 *in7){
+
+ struct exit_ctl_data *p;
+
+ p = kvm_get_exit_data(vcpu);
+
+ if (p) {
+ if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+ *in0 = p->u.sal_data.in0;
+ *in1 = p->u.sal_data.in1;
+ *in2 = p->u.sal_data.in2;
+ *in3 = p->u.sal_data.in3;
+ *in4 = p->u.sal_data.in4;
+ *in5 = p->u.sal_data.in5;
+ *in6 = p->u.sal_data.in6;
+ *in7 = p->u.sal_data.in7;
+ return ;
+ }
+ }
+ *in0 = 0;
+}
+
+void kvm_sal_emul(struct kvm_vcpu *vcpu)
+{
+
+ struct sal_ret_values result;
+ u64 index, in1, in2, in3, in4, in5, in6, in7;
+
+ kvm_get_sal_call_data(vcpu, &index, &in1, &in2,
+ &in3, &in4, &in5, &in6, &in7);
+ result = sal_emulator(vcpu->kvm, index, in1, in2, in3,
+ in4, in5, in6, in7);
+ set_sal_result(vcpu, result);
+}
diff --git a/arch/ia64/kvm/kvm_minstate.h b/arch/ia64/kvm/kvm_minstate.h
new file mode 100644
index 00000000000..13980d9b8bc
--- /dev/null
+++ b/arch/ia64/kvm/kvm_minstate.h
@@ -0,0 +1,273 @@
+/*
+ * kvm_minstate.h: min save macros
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * 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/asmmacro.h>
+#include <asm/types.h>
+#include <asm/kregs.h>
+#include "asm-offsets.h"
+
+#define KVM_MINSTATE_START_SAVE_MIN \
+ mov ar.rsc = 0;/* set enforced lazy mode, pl 0, little-endian, loadrs=0 */\
+ ;; \
+ mov.m r28 = ar.rnat; \
+ addl r22 = VMM_RBS_OFFSET,r1; /* compute base of RBS */ \
+ ;; \
+ lfetch.fault.excl.nt1 [r22]; \
+ addl r1 = IA64_STK_OFFSET-VMM_PT_REGS_SIZE,r1; /* compute base of memory stack */ \
+ mov r23 = ar.bspstore; /* save ar.bspstore */ \
+ ;; \
+ mov ar.bspstore = r22; /* switch to kernel RBS */\
+ ;; \
+ mov r18 = ar.bsp; \
+ mov ar.rsc = 0x3; /* set eager mode, pl 0, little-endian, loadrs=0 */
+
+
+
+#define KVM_MINSTATE_END_SAVE_MIN \
+ bsw.1; /* switch back to bank 1 (must be last in insn group) */\
+ ;;
+
+
+#define PAL_VSA_SYNC_READ \
+ /* begin to call pal vps sync_read */ \
+ add r25 = VMM_VPD_BASE_OFFSET, r21; \
+ adds r20 = VMM_VCPU_VSA_BASE_OFFSET, r21; /* entry point */ \
+ ;; \
+ ld8 r25 = [r25]; /* read vpd base */ \
+ ld8 r20 = [r20]; \
+ ;; \
+ add r20 = PAL_VPS_SYNC_READ,r20; \
+ ;; \
+{ .mii; \
+ nop 0x0; \
+ mov r24 = ip; \
+ mov b0 = r20; \
+ ;; \
+}; \
+{ .mmb; \
+ add r24 = 0x20, r24; \
+ nop 0x0; \
+ br.cond.sptk b0; /* call the service */ \
+ ;; \
+};
+
+
+
+#define KVM_MINSTATE_GET_CURRENT(reg) mov reg=r21
+
+/*
+ * KVM_DO_SAVE_MIN switches to the kernel stacks (if necessary) and saves
+ * the minimum state necessary that allows us to turn psr.ic back
+ * on.
+ *
+ * Assumed state upon entry:
+ * psr.ic: off
+ * r31: contains saved predicates (pr)
+ *
+ * Upon exit, the state is as follows:
+ * psr.ic: off
+ * r2 = points to &pt_regs.r16
+ * r8 = contents of ar.ccv
+ * r9 = contents of ar.csd
+ * r10 = contents of ar.ssd
+ * r11 = FPSR_DEFAULT
+ * r12 = kernel sp (kernel virtual address)
+ * r13 = points to current task_struct (kernel virtual address)
+ * p15 = TRUE if psr.i is set in cr.ipsr
+ * predicate registers (other than p2, p3, and p15), b6, r3, r14, r15:
+ * preserved
+ *
+ * Note that psr.ic is NOT turned on by this macro. This is so that
+ * we can pass interruption state as arguments to a handler.
+ */
+
+
+#define PT(f) (VMM_PT_REGS_##f##_OFFSET)
+
+#define KVM_DO_SAVE_MIN(COVER,SAVE_IFS,EXTRA) \
+ KVM_MINSTATE_GET_CURRENT(r16); /* M (or M;;I) */ \
+ mov r27 = ar.rsc; /* M */ \
+ mov r20 = r1; /* A */ \
+ mov r25 = ar.unat; /* M */ \
+ mov r29 = cr.ipsr; /* M */ \
+ mov r26 = ar.pfs; /* I */ \
+ mov r18 = cr.isr; \
+ COVER; /* B;; (or nothing) */ \
+ ;; \
+ tbit.z p0,p15 = r29,IA64_PSR_I_BIT; \
+ mov r1 = r16; \
+/* mov r21=r16; */ \
+ /* switch from user to kernel RBS: */ \
+ ;; \
+ invala; /* M */ \
+ SAVE_IFS; \
+ ;; \
+ KVM_MINSTATE_START_SAVE_MIN \
+ adds r17 = 2*L1_CACHE_BYTES,r1;/* cache-line size */ \
+ adds r16 = PT(CR_IPSR),r1; \
+ ;; \
+ lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES; \
+ st8 [r16] = r29; /* save cr.ipsr */ \
+ ;; \
+ lfetch.fault.excl.nt1 [r17]; \
+ tbit.nz p15,p0 = r29,IA64_PSR_I_BIT; \
+ mov r29 = b0 \
+ ;; \
+ adds r16 = PT(R8),r1; /* initialize first base pointer */\
+ adds r17 = PT(R9),r1; /* initialize second base pointer */\
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r8,16; \
+.mem.offset 8,0; st8.spill [r17] = r9,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r10,24; \
+.mem.offset 8,0; st8.spill [r17] = r11,24; \
+ ;; \
+ mov r9 = cr.iip; /* M */ \
+ mov r10 = ar.fpsr; /* M */ \
+ ;; \
+ st8 [r16] = r9,16; /* save cr.iip */ \
+ st8 [r17] = r30,16; /* save cr.ifs */ \
+ sub r18 = r18,r22; /* r18=RSE.ndirty*8 */ \
+ ;; \
+ st8 [r16] = r25,16; /* save ar.unat */ \
+ st8 [r17] = r26,16; /* save ar.pfs */ \
+ shl r18 = r18,16; /* calu ar.rsc used for "loadrs" */\
+ ;; \
+ st8 [r16] = r27,16; /* save ar.rsc */ \
+ st8 [r17] = r28,16; /* save ar.rnat */ \
+ ;; /* avoid RAW on r16 & r17 */ \
+ st8 [r16] = r23,16; /* save ar.bspstore */ \
+ st8 [r17] = r31,16; /* save predicates */ \
+ ;; \
+ st8 [r16] = r29,16; /* save b0 */ \
+ st8 [r17] = r18,16; /* save ar.rsc value for "loadrs" */\
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r20,16;/* save original r1 */ \
+.mem.offset 8,0; st8.spill [r17] = r12,16; \
+ adds r12 = -16,r1; /* switch to kernel memory stack */ \
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r13,16; \
+.mem.offset 8,0; st8.spill [r17] = r10,16; /* save ar.fpsr */\
+ mov r13 = r21; /* establish `current' */ \
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r15,16; \
+.mem.offset 8,0; st8.spill [r17] = r14,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r16] = r2,16; \
+.mem.offset 8,0; st8.spill [r17] = r3,16; \
+ adds r2 = VMM_PT_REGS_R16_OFFSET,r1; \
+ ;; \
+ adds r16 = VMM_VCPU_IIPA_OFFSET,r13; \
+ adds r17 = VMM_VCPU_ISR_OFFSET,r13; \
+ mov r26 = cr.iipa; \
+ mov r27 = cr.isr; \
+ ;; \
+ st8 [r16] = r26; \
+ st8 [r17] = r27; \
+ ;; \
+ EXTRA; \
+ mov r8 = ar.ccv; \
+ mov r9 = ar.csd; \
+ mov r10 = ar.ssd; \
+ movl r11 = FPSR_DEFAULT; /* L-unit */ \
+ adds r17 = VMM_VCPU_GP_OFFSET,r13; \
+ ;; \
+ ld8 r1 = [r17];/* establish kernel global pointer */ \
+ ;; \
+ PAL_VSA_SYNC_READ \
+ KVM_MINSTATE_END_SAVE_MIN
+
+/*
+ * SAVE_REST saves the remainder of pt_regs (with psr.ic on).
+ *
+ * Assumed state upon entry:
+ * psr.ic: on
+ * r2: points to &pt_regs.f6
+ * r3: points to &pt_regs.f7
+ * r8: contents of ar.ccv
+ * r9: contents of ar.csd
+ * r10: contents of ar.ssd
+ * r11: FPSR_DEFAULT
+ *
+ * Registers r14 and r15 are guaranteed not to be touched by SAVE_REST.
+ */
+#define KVM_SAVE_REST \
+.mem.offset 0,0; st8.spill [r2] = r16,16; \
+.mem.offset 8,0; st8.spill [r3] = r17,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r18,16; \
+.mem.offset 8,0; st8.spill [r3] = r19,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r20,16; \
+.mem.offset 8,0; st8.spill [r3] = r21,16; \
+ mov r18=b6; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r22,16; \
+.mem.offset 8,0; st8.spill [r3] = r23,16; \
+ mov r19 = b7; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r24,16; \
+.mem.offset 8,0; st8.spill [r3] = r25,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r26,16; \
+.mem.offset 8,0; st8.spill [r3] = r27,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r28,16; \
+.mem.offset 8,0; st8.spill [r3] = r29,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r30,16; \
+.mem.offset 8,0; st8.spill [r3] = r31,32; \
+ ;; \
+ mov ar.fpsr = r11; \
+ st8 [r2] = r8,8; \
+ adds r24 = PT(B6)-PT(F7),r3; \
+ adds r25 = PT(B7)-PT(F7),r3; \
+ ;; \
+ st8 [r24] = r18,16; /* b6 */ \
+ st8 [r25] = r19,16; /* b7 */ \
+ adds r2 = PT(R4)-PT(F6),r2; \
+ adds r3 = PT(R5)-PT(F7),r3; \
+ ;; \
+ st8 [r24] = r9; /* ar.csd */ \
+ st8 [r25] = r10; /* ar.ssd */ \
+ ;; \
+ mov r18 = ar.unat; \
+ adds r19 = PT(EML_UNAT)-PT(R4),r2; \
+ ;; \
+ st8 [r19] = r18; /* eml_unat */ \
+
+
+#define KVM_SAVE_EXTRA \
+.mem.offset 0,0; st8.spill [r2] = r4,16; \
+.mem.offset 8,0; st8.spill [r3] = r5,16; \
+ ;; \
+.mem.offset 0,0; st8.spill [r2] = r6,16; \
+.mem.offset 8,0; st8.spill [r3] = r7; \
+ ;; \
+ mov r26 = ar.unat; \
+ ;; \
+ st8 [r2] = r26;/* eml_unat */ \
+
+#define KVM_SAVE_MIN_WITH_COVER KVM_DO_SAVE_MIN(cover, mov r30 = cr.ifs,)
+#define KVM_SAVE_MIN_WITH_COVER_R19 KVM_DO_SAVE_MIN(cover, mov r30 = cr.ifs, mov r15 = r19)
+#define KVM_SAVE_MIN KVM_DO_SAVE_MIN( , mov r30 = r0, )
diff --git a/arch/ia64/kvm/lapic.h b/arch/ia64/kvm/lapic.h
new file mode 100644
index 00000000000..6d6cbcb1489
--- /dev/null
+++ b/arch/ia64/kvm/lapic.h
@@ -0,0 +1,25 @@
+#ifndef __KVM_IA64_LAPIC_H
+#define __KVM_IA64_LAPIC_H
+
+#include <linux/kvm_host.h>
+
+/*
+ * vlsapic
+ */
+struct kvm_lapic{
+ struct kvm_vcpu *vcpu;
+ uint64_t insvc[4];
+ uint64_t vhpi;
+ uint8_t xtp;
+ uint8_t pal_init_pending;
+ uint8_t pad[2];
+};
+
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
+void kvm_free_lapic(struct kvm_vcpu *vcpu);
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
+int kvm_apic_set_irq(struct kvm_vcpu *vcpu, u8 vec, u8 trig);
+
+#endif
diff --git a/arch/ia64/kvm/misc.h b/arch/ia64/kvm/misc.h
new file mode 100644
index 00000000000..e585c460734
--- /dev/null
+++ b/arch/ia64/kvm/misc.h
@@ -0,0 +1,93 @@
+#ifndef __KVM_IA64_MISC_H
+#define __KVM_IA64_MISC_H
+
+#include <linux/kvm_host.h>
+/*
+ * misc.h
+ * Copyright (C) 2007, Intel Corporation.
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * 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.
+ *
+ */
+
+/*
+ *Return p2m base address at host side!
+ */
+static inline uint64_t *kvm_host_get_pmt(struct kvm *kvm)
+{
+ return (uint64_t *)(kvm->arch.vm_base + KVM_P2M_OFS);
+}
+
+static inline void kvm_set_pmt_entry(struct kvm *kvm, gfn_t gfn,
+ u64 paddr, u64 mem_flags)
+{
+ uint64_t *pmt_base = kvm_host_get_pmt(kvm);
+ unsigned long pte;
+
+ pte = PAGE_ALIGN(paddr) | mem_flags;
+ pmt_base[gfn] = pte;
+}
+
+/*Function for translating host address to guest address*/
+
+static inline void *to_guest(struct kvm *kvm, void *addr)
+{
+ return (void *)((unsigned long)(addr) - kvm->arch.vm_base +
+ KVM_VM_DATA_BASE);
+}
+
+/*Function for translating guest address to host address*/
+
+static inline void *to_host(struct kvm *kvm, void *addr)
+{
+ return (void *)((unsigned long)addr - KVM_VM_DATA_BASE
+ + kvm->arch.vm_base);
+}
+
+/* Get host context of the vcpu */
+static inline union context *kvm_get_host_context(struct kvm_vcpu *vcpu)
+{
+ union context *ctx = &vcpu->arch.host;
+ return to_guest(vcpu->kvm, ctx);
+}
+
+/* Get guest context of the vcpu */
+static inline union context *kvm_get_guest_context(struct kvm_vcpu *vcpu)
+{
+ union context *ctx = &vcpu->arch.guest;
+ return to_guest(vcpu->kvm, ctx);
+}
+
+/* kvm get exit data from gvmm! */
+static inline struct exit_ctl_data *kvm_get_exit_data(struct kvm_vcpu *vcpu)
+{
+ return &vcpu->arch.exit_data;
+}
+
+/*kvm get vcpu ioreq for kvm module!*/
+static inline struct kvm_mmio_req *kvm_get_vcpu_ioreq(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p_ctl_data;
+
+ if (vcpu) {
+ p_ctl_data = kvm_get_exit_data(vcpu);
+ if (p_ctl_data->exit_reason == EXIT_REASON_MMIO_INSTRUCTION)
+ return &p_ctl_data->u.ioreq;
+ }
+
+ return NULL;
+}
+
+#endif
diff --git a/arch/ia64/kvm/mmio.c b/arch/ia64/kvm/mmio.c
new file mode 100644
index 00000000000..351bf70da46
--- /dev/null
+++ b/arch/ia64/kvm/mmio.c
@@ -0,0 +1,341 @@
+/*
+ * mmio.c: MMIO emulation components.
+ * Copyright (c) 2004, Intel Corporation.
+ * Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ * Kun Tian (Kevin Tian) (Kevin.tian@intel.com)
+ *
+ * Copyright (c) 2007 Intel Corporation KVM support.
+ * Xuefei Xu (Anthony Xu) (anthony.xu@intel.com)
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * 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/kvm_host.h>
+
+#include "vcpu.h"
+
+static void vlsapic_write_xtp(struct kvm_vcpu *v, uint8_t val)
+{
+ VLSAPIC_XTP(v) = val;
+}
+
+/*
+ * LSAPIC OFFSET
+ */
+#define PIB_LOW_HALF(ofst) !(ofst & (1 << 20))
+#define PIB_OFST_INTA 0x1E0000
+#define PIB_OFST_XTP 0x1E0008
+
+/*
+ * execute write IPI op.
+ */
+static void vlsapic_write_ipi(struct kvm_vcpu *vcpu,
+ uint64_t addr, uint64_t data)
+{
+ struct exit_ctl_data *p = &current_vcpu->arch.exit_data;
+ unsigned long psr;
+
+ local_irq_save(psr);
+
+ p->exit_reason = EXIT_REASON_IPI;
+ p->u.ipi_data.addr.val = addr;
+ p->u.ipi_data.data.val = data;
+ vmm_transition(current_vcpu);
+
+ local_irq_restore(psr);
+
+}
+
+void lsapic_write(struct kvm_vcpu *v, unsigned long addr,
+ unsigned long length, unsigned long val)
+{
+ addr &= (PIB_SIZE - 1);
+
+ switch (addr) {
+ case PIB_OFST_INTA:
+ /*panic_domain(NULL, "Undefined write on PIB INTA\n");*/
+ panic_vm(v);
+ break;
+ case PIB_OFST_XTP:
+ if (length == 1) {
+ vlsapic_write_xtp(v, val);
+ } else {
+ /*panic_domain(NULL,
+ "Undefined write on PIB XTP\n");*/
+ panic_vm(v);
+ }
+ break;
+ default:
+ if (PIB_LOW_HALF(addr)) {
+ /*lower half */
+ if (length != 8)
+ /*panic_domain(NULL,
+ "Can't LHF write with size %ld!\n",
+ length);*/
+ panic_vm(v);
+ else
+ vlsapic_write_ipi(v, addr, val);
+ } else { /* upper half
+ printk("IPI-UHF write %lx\n",addr);*/
+ panic_vm(v);
+ }
+ break;
+ }
+}
+
+unsigned long lsapic_read(struct kvm_vcpu *v, unsigned long addr,
+ unsigned long length)
+{
+ uint64_t result = 0;
+
+ addr &= (PIB_SIZE - 1);
+
+ switch (addr) {
+ case PIB_OFST_INTA:
+ if (length == 1) /* 1 byte load */
+ ; /* There is no i8259, there is no INTA access*/
+ else
+ /*panic_domain(NULL,"Undefined read on PIB INTA\n"); */
+ panic_vm(v);
+
+ break;
+ case PIB_OFST_XTP:
+ if (length == 1) {
+ result = VLSAPIC_XTP(v);
+ /* printk("read xtp %lx\n", result); */
+ } else {
+ /*panic_domain(NULL,
+ "Undefined read on PIB XTP\n");*/
+ panic_vm(v);
+ }
+ break;
+ default:
+ panic_vm(v);
+ break;
+ }
+ return result;
+}
+
+static void mmio_access(struct kvm_vcpu *vcpu, u64 src_pa, u64 *dest,
+ u16 s, int ma, int dir)
+{
+ unsigned long iot;
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+ unsigned long psr;
+
+ iot = __gpfn_is_io(src_pa >> PAGE_SHIFT);
+
+ local_irq_save(psr);
+
+ /*Intercept the acces for PIB range*/
+ if (iot == GPFN_PIB) {
+ if (!dir)
+ lsapic_write(vcpu, src_pa, s, *dest);
+ else
+ *dest = lsapic_read(vcpu, src_pa, s);
+ goto out;
+ }
+ p->exit_reason = EXIT_REASON_MMIO_INSTRUCTION;
+ p->u.ioreq.addr = src_pa;
+ p->u.ioreq.size = s;
+ p->u.ioreq.dir = dir;
+ if (dir == IOREQ_WRITE)
+ p->u.ioreq.data = *dest;
+ p->u.ioreq.state = STATE_IOREQ_READY;
+ vmm_transition(vcpu);
+
+ if (p->u.ioreq.state == STATE_IORESP_READY) {
+ if (dir == IOREQ_READ)
+ *dest = p->u.ioreq.data;
+ } else
+ panic_vm(vcpu);
+out:
+ local_irq_restore(psr);
+ return ;
+}
+
+/*
+ dir 1: read 0:write
+ inst_type 0:integer 1:floating point
+ */
+#define SL_INTEGER 0 /* store/load interger*/
+#define SL_FLOATING 1 /* store/load floating*/
+
+void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
+{
+ struct kvm_pt_regs *regs;
+ IA64_BUNDLE bundle;
+ int slot, dir = 0;
+ int inst_type = -1;
+ u16 size = 0;
+ u64 data, slot1a, slot1b, temp, update_reg;
+ s32 imm;
+ INST64 inst;
+
+ regs = vcpu_regs(vcpu);
+
+ if (fetch_code(vcpu, regs->cr_iip, &bundle)) {
+ /* if fetch code fail, return and try again */
+ return;
+ }
+ slot = ((struct ia64_psr *)&(regs->cr_ipsr))->ri;
+ if (!slot)
+ inst.inst = bundle.slot0;
+ else if (slot == 1) {
+ slot1a = bundle.slot1a;
+ slot1b = bundle.slot1b;
+ inst.inst = slot1a + (slot1b << 18);
+ } else if (slot == 2)
+ inst.inst = bundle.slot2;
+
+ /* Integer Load/Store */
+ if (inst.M1.major == 4 && inst.M1.m == 0 && inst.M1.x == 0) {
+ inst_type = SL_INTEGER;
+ size = (inst.M1.x6 & 0x3);
+ if ((inst.M1.x6 >> 2) > 0xb) {
+ /*write*/
+ dir = IOREQ_WRITE;
+ data = vcpu_get_gr(vcpu, inst.M4.r2);
+ } else if ((inst.M1.x6 >> 2) < 0xb) {
+ /*read*/
+ dir = IOREQ_READ;
+ }
+ } else if (inst.M2.major == 4 && inst.M2.m == 1 && inst.M2.x == 0) {
+ /* Integer Load + Reg update */
+ inst_type = SL_INTEGER;
+ dir = IOREQ_READ;
+ size = (inst.M2.x6 & 0x3);
+ temp = vcpu_get_gr(vcpu, inst.M2.r3);
+ update_reg = vcpu_get_gr(vcpu, inst.M2.r2);
+ temp += update_reg;
+ vcpu_set_gr(vcpu, inst.M2.r3, temp, 0);
+ } else if (inst.M3.major == 5) {
+ /*Integer Load/Store + Imm update*/
+ inst_type = SL_INTEGER;
+ size = (inst.M3.x6&0x3);
+ if ((inst.M5.x6 >> 2) > 0xb) {
+ /*write*/
+ dir = IOREQ_WRITE;
+ data = vcpu_get_gr(vcpu, inst.M5.r2);
+ temp = vcpu_get_gr(vcpu, inst.M5.r3);
+ imm = (inst.M5.s << 31) | (inst.M5.i << 30) |
+ (inst.M5.imm7 << 23);
+ temp += imm >> 23;
+ vcpu_set_gr(vcpu, inst.M5.r3, temp, 0);
+
+ } else if ((inst.M3.x6 >> 2) < 0xb) {
+ /*read*/
+ dir = IOREQ_READ;
+ temp = vcpu_get_gr(vcpu, inst.M3.r3);
+ imm = (inst.M3.s << 31) | (inst.M3.i << 30) |
+ (inst.M3.imm7 << 23);
+ temp += imm >> 23;
+ vcpu_set_gr(vcpu, inst.M3.r3, temp, 0);
+
+ }
+ } else if (inst.M9.major == 6 && inst.M9.x6 == 0x3B
+ && inst.M9.m == 0 && inst.M9.x == 0) {
+ /* Floating-point spill*/
+ struct ia64_fpreg v;
+
+ inst_type = SL_FLOATING;
+ dir = IOREQ_WRITE;
+ vcpu_get_fpreg(vcpu, inst.M9.f2, &v);
+ /* Write high word. FIXME: this is a kludge! */
+ v.u.bits[1] &= 0x3ffff;
+ mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+ data = v.u.bits[0];
+ size = 3;
+ } else if (inst.M10.major == 7 && inst.M10.x6 == 0x3B) {
+ /* Floating-point spill + Imm update */
+ struct ia64_fpreg v;
+
+ inst_type = SL_FLOATING;
+ dir = IOREQ_WRITE;
+ vcpu_get_fpreg(vcpu, inst.M10.f2, &v);
+ temp = vcpu_get_gr(vcpu, inst.M10.r3);
+ imm = (inst.M10.s << 31) | (inst.M10.i << 30) |
+ (inst.M10.imm7 << 23);
+ temp += imm >> 23;
+ vcpu_set_gr(vcpu, inst.M10.r3, temp, 0);
+
+ /* Write high word.FIXME: this is a kludge! */
+ v.u.bits[1] &= 0x3ffff;
+ mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE);
+ data = v.u.bits[0];
+ size = 3;
+ } else if (inst.M10.major == 7 && inst.M10.x6 == 0x31) {
+ /* Floating-point stf8 + Imm update */
+ struct ia64_fpreg v;
+ inst_type = SL_FLOATING;
+ dir = IOREQ_WRITE;
+ size = 3;
+ vcpu_get_fpreg(vcpu, inst.M10.f2, &v);
+ data = v.u.bits[0]; /* Significand. */
+ temp = vcpu_get_gr(vcpu, inst.M10.r3);
+ imm = (inst.M10.s << 31) | (inst.M10.i << 30) |
+ (inst.M10.imm7 << 23);
+ temp += imm >> 23;
+ vcpu_set_gr(vcpu, inst.M10.r3, temp, 0);
+ } else if (inst.M15.major == 7 && inst.M15.x6 >= 0x2c
+ && inst.M15.x6 <= 0x2f) {
+ temp = vcpu_get_gr(vcpu, inst.M15.r3);
+ imm = (inst.M15.s << 31) | (inst.M15.i << 30) |
+ (inst.M15.imm7 << 23);
+ temp += imm >> 23;
+ vcpu_set_gr(vcpu, inst.M15.r3, temp, 0);
+
+ vcpu_increment_iip(vcpu);
+ return;
+ } else if (inst.M12.major == 6 && inst.M12.m == 1
+ && inst.M12.x == 1 && inst.M12.x6 == 1) {
+ /* Floating-point Load Pair + Imm ldfp8 M12*/
+ struct ia64_fpreg v;
+
+ inst_type = SL_FLOATING;
+ dir = IOREQ_READ;
+ size = 8; /*ldfd*/
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ v.u.bits[0] = data;
+ v.u.bits[1] = 0x1003E;
+ vcpu_set_fpreg(vcpu, inst.M12.f1, &v);
+ padr += 8;
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ v.u.bits[0] = data;
+ v.u.bits[1] = 0x1003E;
+ vcpu_set_fpreg(vcpu, inst.M12.f2, &v);
+ padr += 8;
+ vcpu_set_gr(vcpu, inst.M12.r3, padr, 0);
+ vcpu_increment_iip(vcpu);
+ return;
+ } else {
+ inst_type = -1;
+ panic_vm(vcpu);
+ }
+
+ size = 1 << size;
+ if (dir == IOREQ_WRITE) {
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ } else {
+ mmio_access(vcpu, padr, &data, size, ma, dir);
+ if (inst_type == SL_INTEGER)
+ vcpu_set_gr(vcpu, inst.M1.r1, data, 0);
+ else
+ panic_vm(vcpu);
+
+ }
+ vcpu_increment_iip(vcpu);
+}
diff --git a/arch/ia64/kvm/optvfault.S b/arch/ia64/kvm/optvfault.S
new file mode 100644
index 00000000000..e4f15d641b2
--- /dev/null
+++ b/arch/ia64/kvm/optvfault.S
@@ -0,0 +1,918 @@
+/*
+ * arch/ia64/vmx/optvfault.S
+ * optimize virtualization fault handler
+ *
+ * Copyright (C) 2006 Intel Co
+ * Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ */
+
+#include <asm/asmmacro.h>
+#include <asm/processor.h>
+
+#include "vti.h"
+#include "asm-offsets.h"
+
+#define ACCE_MOV_FROM_AR
+#define ACCE_MOV_FROM_RR
+#define ACCE_MOV_TO_RR
+#define ACCE_RSM
+#define ACCE_SSM
+#define ACCE_MOV_TO_PSR
+#define ACCE_THASH
+
+//mov r1=ar3
+GLOBAL_ENTRY(kvm_asm_mov_from_ar)
+#ifndef ACCE_MOV_FROM_AR
+ br.many kvm_virtualization_fault_back
+#endif
+ add r18=VMM_VCPU_ITC_OFS_OFFSET, r21
+ add r16=VMM_VCPU_LAST_ITC_OFFSET,r21
+ extr.u r17=r25,6,7
+ ;;
+ ld8 r18=[r18]
+ mov r19=ar.itc
+ mov r24=b0
+ ;;
+ add r19=r19,r18
+ addl r20=@gprel(asm_mov_to_reg),gp
+ ;;
+ st8 [r16] = r19
+ adds r30=kvm_resume_to_guest-asm_mov_to_reg,r20
+ shladd r17=r17,4,r20
+ ;;
+ mov b0=r17
+ br.sptk.few b0
+ ;;
+END(kvm_asm_mov_from_ar)
+
+
+// mov r1=rr[r3]
+GLOBAL_ENTRY(kvm_asm_mov_from_rr)
+#ifndef ACCE_MOV_FROM_RR
+ br.many kvm_virtualization_fault_back
+#endif
+ extr.u r16=r25,20,7
+ extr.u r17=r25,6,7
+ addl r20=@gprel(asm_mov_from_reg),gp
+ ;;
+ adds r30=kvm_asm_mov_from_rr_back_1-asm_mov_from_reg,r20
+ shladd r16=r16,4,r20
+ mov r24=b0
+ ;;
+ add r27=VMM_VCPU_VRR0_OFFSET,r21
+ mov b0=r16
+ br.many b0
+ ;;
+kvm_asm_mov_from_rr_back_1:
+ adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+ adds r22=asm_mov_to_reg-asm_mov_from_reg,r20
+ shr.u r26=r19,61
+ ;;
+ shladd r17=r17,4,r22
+ shladd r27=r26,3,r27
+ ;;
+ ld8 r19=[r27]
+ mov b0=r17
+ br.many b0
+END(kvm_asm_mov_from_rr)
+
+
+// mov rr[r3]=r2
+GLOBAL_ENTRY(kvm_asm_mov_to_rr)
+#ifndef ACCE_MOV_TO_RR
+ br.many kvm_virtualization_fault_back
+#endif
+ extr.u r16=r25,20,7
+ extr.u r17=r25,13,7
+ addl r20=@gprel(asm_mov_from_reg),gp
+ ;;
+ adds r30=kvm_asm_mov_to_rr_back_1-asm_mov_from_reg,r20
+ shladd r16=r16,4,r20
+ mov r22=b0
+ ;;
+ add r27=VMM_VCPU_VRR0_OFFSET,r21
+ mov b0=r16
+ br.many b0
+ ;;
+kvm_asm_mov_to_rr_back_1:
+ adds r30=kvm_asm_mov_to_rr_back_2-asm_mov_from_reg,r20
+ shr.u r23=r19,61
+ shladd r17=r17,4,r20
+ ;;
+ //if rr6, go back
+ cmp.eq p6,p0=6,r23
+ mov b0=r22
+ (p6) br.cond.dpnt.many kvm_virtualization_fault_back
+ ;;
+ mov r28=r19
+ mov b0=r17
+ br.many b0
+kvm_asm_mov_to_rr_back_2:
+ adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+ shladd r27=r23,3,r27
+ ;; // vrr.rid<<4 |0xe
+ st8 [r27]=r19
+ mov b0=r30
+ ;;
+ extr.u r16=r19,8,26
+ extr.u r18 =r19,2,6
+ mov r17 =0xe
+ ;;
+ shladd r16 = r16, 4, r17
+ extr.u r19 =r19,0,8
+ ;;
+ shl r16 = r16,8
+ ;;
+ add r19 = r19, r16
+ ;; //set ve 1
+ dep r19=-1,r19,0,1
+ cmp.lt p6,p0=14,r18
+ ;;
+ (p6) mov r18=14
+ ;;
+ (p6) dep r19=r18,r19,2,6
+ ;;
+ cmp.eq p6,p0=0,r23
+ ;;
+ cmp.eq.or p6,p0=4,r23
+ ;;
+ adds r16=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+ (p6) adds r17=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+ ;;
+ ld4 r16=[r16]
+ cmp.eq p7,p0=r0,r0
+ (p6) shladd r17=r23,1,r17
+ ;;
+ (p6) st8 [r17]=r19
+ (p6) tbit.nz p6,p7=r16,0
+ ;;
+ (p7) mov rr[r28]=r19
+ mov r24=r22
+ br.many b0
+END(kvm_asm_mov_to_rr)
+
+
+//rsm
+GLOBAL_ENTRY(kvm_asm_rsm)
+#ifndef ACCE_RSM
+ br.many kvm_virtualization_fault_back
+#endif
+ add r16=VMM_VPD_BASE_OFFSET,r21
+ extr.u r26=r25,6,21
+ extr.u r27=r25,31,2
+ ;;
+ ld8 r16=[r16]
+ extr.u r28=r25,36,1
+ dep r26=r27,r26,21,2
+ ;;
+ add r17=VPD_VPSR_START_OFFSET,r16
+ add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+ //r26 is imm24
+ dep r26=r28,r26,23,1
+ ;;
+ ld8 r18=[r17]
+ movl r28=IA64_PSR_IC+IA64_PSR_I+IA64_PSR_DT+IA64_PSR_SI
+ ld4 r23=[r22]
+ sub r27=-1,r26
+ mov r24=b0
+ ;;
+ mov r20=cr.ipsr
+ or r28=r27,r28
+ and r19=r18,r27
+ ;;
+ st8 [r17]=r19
+ and r20=r20,r28
+ /* Comment it out due to short of fp lazy alorgithm support
+ adds r27=IA64_VCPU_FP_PSR_OFFSET,r21
+ ;;
+ ld8 r27=[r27]
+ ;;
+ tbit.nz p8,p0= r27,IA64_PSR_DFH_BIT
+ ;;
+ (p8) dep r20=-1,r20,IA64_PSR_DFH_BIT,1
+ */
+ ;;
+ mov cr.ipsr=r20
+ tbit.nz p6,p0=r23,0
+ ;;
+ tbit.z.or p6,p0=r26,IA64_PSR_DT_BIT
+ (p6) br.dptk kvm_resume_to_guest
+ ;;
+ add r26=VMM_VCPU_META_RR0_OFFSET,r21
+ add r27=VMM_VCPU_META_RR0_OFFSET+8,r21
+ dep r23=-1,r23,0,1
+ ;;
+ ld8 r26=[r26]
+ ld8 r27=[r27]
+ st4 [r22]=r23
+ dep.z r28=4,61,3
+ ;;
+ mov rr[r0]=r26
+ ;;
+ mov rr[r28]=r27
+ ;;
+ srlz.d
+ br.many kvm_resume_to_guest
+END(kvm_asm_rsm)
+
+
+//ssm
+GLOBAL_ENTRY(kvm_asm_ssm)
+#ifndef ACCE_SSM
+ br.many kvm_virtualization_fault_back
+#endif
+ add r16=VMM_VPD_BASE_OFFSET,r21
+ extr.u r26=r25,6,21
+ extr.u r27=r25,31,2
+ ;;
+ ld8 r16=[r16]
+ extr.u r28=r25,36,1
+ dep r26=r27,r26,21,2
+ ;; //r26 is imm24
+ add r27=VPD_VPSR_START_OFFSET,r16
+ dep r26=r28,r26,23,1
+ ;; //r19 vpsr
+ ld8 r29=[r27]
+ mov r24=b0
+ ;;
+ add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+ mov r20=cr.ipsr
+ or r19=r29,r26
+ ;;
+ ld4 r23=[r22]
+ st8 [r27]=r19
+ or r20=r20,r26
+ ;;
+ mov cr.ipsr=r20
+ movl r28=IA64_PSR_DT+IA64_PSR_RT+IA64_PSR_IT
+ ;;
+ and r19=r28,r19
+ tbit.z p6,p0=r23,0
+ ;;
+ cmp.ne.or p6,p0=r28,r19
+ (p6) br.dptk kvm_asm_ssm_1
+ ;;
+ add r26=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+ add r27=VMM_VCPU_META_SAVED_RR0_OFFSET+8,r21
+ dep r23=0,r23,0,1
+ ;;
+ ld8 r26=[r26]
+ ld8 r27=[r27]
+ st4 [r22]=r23
+ dep.z r28=4,61,3
+ ;;
+ mov rr[r0]=r26
+ ;;
+ mov rr[r28]=r27
+ ;;
+ srlz.d
+ ;;
+kvm_asm_ssm_1:
+ tbit.nz p6,p0=r29,IA64_PSR_I_BIT
+ ;;
+ tbit.z.or p6,p0=r19,IA64_PSR_I_BIT
+ (p6) br.dptk kvm_resume_to_guest
+ ;;
+ add r29=VPD_VTPR_START_OFFSET,r16
+ add r30=VPD_VHPI_START_OFFSET,r16
+ ;;
+ ld8 r29=[r29]
+ ld8 r30=[r30]
+ ;;
+ extr.u r17=r29,4,4
+ extr.u r18=r29,16,1
+ ;;
+ dep r17=r18,r17,4,1
+ ;;
+ cmp.gt p6,p0=r30,r17
+ (p6) br.dpnt.few kvm_asm_dispatch_vexirq
+ br.many kvm_resume_to_guest
+END(kvm_asm_ssm)
+
+
+//mov psr.l=r2
+GLOBAL_ENTRY(kvm_asm_mov_to_psr)
+#ifndef ACCE_MOV_TO_PSR
+ br.many kvm_virtualization_fault_back
+#endif
+ add r16=VMM_VPD_BASE_OFFSET,r21
+ extr.u r26=r25,13,7 //r2
+ ;;
+ ld8 r16=[r16]
+ addl r20=@gprel(asm_mov_from_reg),gp
+ ;;
+ adds r30=kvm_asm_mov_to_psr_back-asm_mov_from_reg,r20
+ shladd r26=r26,4,r20
+ mov r24=b0
+ ;;
+ add r27=VPD_VPSR_START_OFFSET,r16
+ mov b0=r26
+ br.many b0
+ ;;
+kvm_asm_mov_to_psr_back:
+ ld8 r17=[r27]
+ add r22=VMM_VCPU_MODE_FLAGS_OFFSET,r21
+ dep r19=0,r19,32,32
+ ;;
+ ld4 r23=[r22]
+ dep r18=0,r17,0,32
+ ;;
+ add r30=r18,r19
+ movl r28=IA64_PSR_DT+IA64_PSR_RT+IA64_PSR_IT
+ ;;
+ st8 [r27]=r30
+ and r27=r28,r30
+ and r29=r28,r17
+ ;;
+ cmp.eq p5,p0=r29,r27
+ cmp.eq p6,p7=r28,r27
+ (p5) br.many kvm_asm_mov_to_psr_1
+ ;;
+ //virtual to physical
+ (p7) add r26=VMM_VCPU_META_RR0_OFFSET,r21
+ (p7) add r27=VMM_VCPU_META_RR0_OFFSET+8,r21
+ (p7) dep r23=-1,r23,0,1
+ ;;
+ //physical to virtual
+ (p6) add r26=VMM_VCPU_META_SAVED_RR0_OFFSET,r21
+ (p6) add r27=VMM_VCPU_META_SAVED_RR0_OFFSET+8,r21
+ (p6) dep r23=0,r23,0,1
+ ;;
+ ld8 r26=[r26]
+ ld8 r27=[r27]
+ st4 [r22]=r23
+ dep.z r28=4,61,3
+ ;;
+ mov rr[r0]=r26
+ ;;
+ mov rr[r28]=r27
+ ;;
+ srlz.d
+ ;;
+kvm_asm_mov_to_psr_1:
+ mov r20=cr.ipsr
+ movl r28=IA64_PSR_IC+IA64_PSR_I+IA64_PSR_DT+IA64_PSR_SI+IA64_PSR_RT
+ ;;
+ or r19=r19,r28
+ dep r20=0,r20,0,32
+ ;;
+ add r20=r19,r20
+ mov b0=r24
+ ;;
+ /* Comment it out due to short of fp lazy algorithm support
+ adds r27=IA64_VCPU_FP_PSR_OFFSET,r21
+ ;;
+ ld8 r27=[r27]
+ ;;
+ tbit.nz p8,p0=r27,IA64_PSR_DFH_BIT
+ ;;
+ (p8) dep r20=-1,r20,IA64_PSR_DFH_BIT,1
+ ;;
+ */
+ mov cr.ipsr=r20
+ cmp.ne p6,p0=r0,r0
+ ;;
+ tbit.nz.or p6,p0=r17,IA64_PSR_I_BIT
+ tbit.z.or p6,p0=r30,IA64_PSR_I_BIT
+ (p6) br.dpnt.few kvm_resume_to_guest
+ ;;
+ add r29=VPD_VTPR_START_OFFSET,r16
+ add r30=VPD_VHPI_START_OFFSET,r16
+ ;;
+ ld8 r29=[r29]
+ ld8 r30=[r30]
+ ;;
+ extr.u r17=r29,4,4
+ extr.u r18=r29,16,1
+ ;;
+ dep r17=r18,r17,4,1
+ ;;
+ cmp.gt p6,p0=r30,r17
+ (p6) br.dpnt.few kvm_asm_dispatch_vexirq
+ br.many kvm_resume_to_guest
+END(kvm_asm_mov_to_psr)
+
+
+ENTRY(kvm_asm_dispatch_vexirq)
+//increment iip
+ mov r16=cr.ipsr
+ ;;
+ extr.u r17=r16,IA64_PSR_RI_BIT,2
+ tbit.nz p6,p7=r16,IA64_PSR_RI_BIT+1
+ ;;
+ (p6) mov r18=cr.iip
+ (p6) mov r17=r0
+ (p7) add r17=1,r17
+ ;;
+ (p6) add r18=0x10,r18
+ dep r16=r17,r16,IA64_PSR_RI_BIT,2
+ ;;
+ (p6) mov cr.iip=r18
+ mov cr.ipsr=r16
+ mov r30 =1
+ br.many kvm_dispatch_vexirq
+END(kvm_asm_dispatch_vexirq)
+
+// thash
+// TODO: add support when pta.vf = 1
+GLOBAL_ENTRY(kvm_asm_thash)
+#ifndef ACCE_THASH
+ br.many kvm_virtualization_fault_back
+#endif
+ extr.u r17=r25,20,7 // get r3 from opcode in r25
+ extr.u r18=r25,6,7 // get r1 from opcode in r25
+ addl r20=@gprel(asm_mov_from_reg),gp
+ ;;
+ adds r30=kvm_asm_thash_back1-asm_mov_from_reg,r20
+ shladd r17=r17,4,r20 // get addr of MOVE_FROM_REG(r17)
+ adds r16=VMM_VPD_BASE_OFFSET,r21 // get vcpu.arch.priveregs
+ ;;
+ mov r24=b0
+ ;;
+ ld8 r16=[r16] // get VPD addr
+ mov b0=r17
+ br.many b0 // r19 return value
+ ;;
+kvm_asm_thash_back1:
+ shr.u r23=r19,61 // get RR number
+ adds r25=VMM_VCPU_VRR0_OFFSET,r21 // get vcpu->arch.vrr[0]'s addr
+ adds r16=VMM_VPD_VPTA_OFFSET,r16 // get vpta
+ ;;
+ shladd r27=r23,3,r25 // get vcpu->arch.vrr[r23]'s addr
+ ld8 r17=[r16] // get PTA
+ mov r26=1
+ ;;
+ extr.u r29=r17,2,6 // get pta.size
+ ld8 r25=[r27] // get vcpu->arch.vrr[r23]'s value
+ ;;
+ extr.u r25=r25,2,6 // get rr.ps
+ shl r22=r26,r29 // 1UL << pta.size
+ ;;
+ shr.u r23=r19,r25 // vaddr >> rr.ps
+ adds r26=3,r29 // pta.size + 3
+ shl r27=r17,3 // pta << 3
+ ;;
+ shl r23=r23,3 // (vaddr >> rr.ps) << 3
+ shr.u r27=r27,r26 // (pta << 3) >> (pta.size+3)
+ movl r16=7<<61
+ ;;
+ adds r22=-1,r22 // (1UL << pta.size) - 1
+ shl r27=r27,r29 // ((pta<<3)>>(pta.size+3))<<pta.size
+ and r19=r19,r16 // vaddr & VRN_MASK
+ ;;
+ and r22=r22,r23 // vhpt_offset
+ or r19=r19,r27 // (vadr&VRN_MASK)|(((pta<<3)>>(pta.size + 3))<<pta.size)
+ adds r26=asm_mov_to_reg-asm_mov_from_reg,r20
+ ;;
+ or r19=r19,r22 // calc pval
+ shladd r17=r18,4,r26
+ adds r30=kvm_resume_to_guest-asm_mov_from_reg,r20
+ ;;
+ mov b0=r17
+ br.many b0
+END(kvm_asm_thash)
+
+#define MOV_TO_REG0 \
+{; \
+ nop.b 0x0; \
+ nop.b 0x0; \
+ nop.b 0x0; \
+ ;; \
+};
+
+
+#define MOV_TO_REG(n) \
+{; \
+ mov r##n##=r19; \
+ mov b0=r30; \
+ br.sptk.many b0; \
+ ;; \
+};
+
+
+#define MOV_FROM_REG(n) \
+{; \
+ mov r19=r##n##; \
+ mov b0=r30; \
+ br.sptk.many b0; \
+ ;; \
+};
+
+
+#define MOV_TO_BANK0_REG(n) \
+ENTRY_MIN_ALIGN(asm_mov_to_bank0_reg##n##); \
+{; \
+ mov r26=r2; \
+ mov r2=r19; \
+ bsw.1; \
+ ;; \
+}; \
+{; \
+ mov r##n##=r2; \
+ nop.b 0x0; \
+ bsw.0; \
+ ;; \
+}; \
+{; \
+ mov r2=r26; \
+ mov b0=r30; \
+ br.sptk.many b0; \
+ ;; \
+}; \
+END(asm_mov_to_bank0_reg##n##)
+
+
+#define MOV_FROM_BANK0_REG(n) \
+ENTRY_MIN_ALIGN(asm_mov_from_bank0_reg##n##); \
+{; \
+ mov r26=r2; \
+ nop.b 0x0; \
+ bsw.1; \
+ ;; \
+}; \
+{; \
+ mov r2=r##n##; \
+ nop.b 0x0; \
+ bsw.0; \
+ ;; \
+}; \
+{; \
+ mov r19=r2; \
+ mov r2=r26; \
+ mov b0=r30; \
+}; \
+{; \
+ nop.b 0x0; \
+ nop.b 0x0; \
+ br.sptk.many b0; \
+ ;; \
+}; \
+END(asm_mov_from_bank0_reg##n##)
+
+
+#define JMP_TO_MOV_TO_BANK0_REG(n) \
+{; \
+ nop.b 0x0; \
+ nop.b 0x0; \
+ br.sptk.many asm_mov_to_bank0_reg##n##; \
+ ;; \
+}
+
+
+#define JMP_TO_MOV_FROM_BANK0_REG(n) \
+{; \
+ nop.b 0x0; \
+ nop.b 0x0; \
+ br.sptk.many asm_mov_from_bank0_reg##n##; \
+ ;; \
+}
+
+
+MOV_FROM_BANK0_REG(16)
+MOV_FROM_BANK0_REG(17)
+MOV_FROM_BANK0_REG(18)
+MOV_FROM_BANK0_REG(19)
+MOV_FROM_BANK0_REG(20)
+MOV_FROM_BANK0_REG(21)
+MOV_FROM_BANK0_REG(22)
+MOV_FROM_BANK0_REG(23)
+MOV_FROM_BANK0_REG(24)
+MOV_FROM_BANK0_REG(25)
+MOV_FROM_BANK0_REG(26)
+MOV_FROM_BANK0_REG(27)
+MOV_FROM_BANK0_REG(28)
+MOV_FROM_BANK0_REG(29)
+MOV_FROM_BANK0_REG(30)
+MOV_FROM_BANK0_REG(31)
+
+
+// mov from reg table
+ENTRY(asm_mov_from_reg)
+ MOV_FROM_REG(0)
+ MOV_FROM_REG(1)
+ MOV_FROM_REG(2)
+ MOV_FROM_REG(3)
+ MOV_FROM_REG(4)
+ MOV_FROM_REG(5)
+ MOV_FROM_REG(6)
+ MOV_FROM_REG(7)
+ MOV_FROM_REG(8)
+ MOV_FROM_REG(9)
+ MOV_FROM_REG(10)
+ MOV_FROM_REG(11)
+ MOV_FROM_REG(12)
+ MOV_FROM_REG(13)
+ MOV_FROM_REG(14)
+ MOV_FROM_REG(15)
+ JMP_TO_MOV_FROM_BANK0_REG(16)
+ JMP_TO_MOV_FROM_BANK0_REG(17)
+ JMP_TO_MOV_FROM_BANK0_REG(18)
+ JMP_TO_MOV_FROM_BANK0_REG(19)
+ JMP_TO_MOV_FROM_BANK0_REG(20)
+ JMP_TO_MOV_FROM_BANK0_REG(21)
+ JMP_TO_MOV_FROM_BANK0_REG(22)
+ JMP_TO_MOV_FROM_BANK0_REG(23)
+ JMP_TO_MOV_FROM_BANK0_REG(24)
+ JMP_TO_MOV_FROM_BANK0_REG(25)
+ JMP_TO_MOV_FROM_BANK0_REG(26)
+ JMP_TO_MOV_FROM_BANK0_REG(27)
+ JMP_TO_MOV_FROM_BANK0_REG(28)
+ JMP_TO_MOV_FROM_BANK0_REG(29)
+ JMP_TO_MOV_FROM_BANK0_REG(30)
+ JMP_TO_MOV_FROM_BANK0_REG(31)
+ MOV_FROM_REG(32)
+ MOV_FROM_REG(33)
+ MOV_FROM_REG(34)
+ MOV_FROM_REG(35)
+ MOV_FROM_REG(36)
+ MOV_FROM_REG(37)
+ MOV_FROM_REG(38)
+ MOV_FROM_REG(39)
+ MOV_FROM_REG(40)
+ MOV_FROM_REG(41)
+ MOV_FROM_REG(42)
+ MOV_FROM_REG(43)
+ MOV_FROM_REG(44)
+ MOV_FROM_REG(45)
+ MOV_FROM_REG(46)
+ MOV_FROM_REG(47)
+ MOV_FROM_REG(48)
+ MOV_FROM_REG(49)
+ MOV_FROM_REG(50)
+ MOV_FROM_REG(51)
+ MOV_FROM_REG(52)
+ MOV_FROM_REG(53)
+ MOV_FROM_REG(54)
+ MOV_FROM_REG(55)
+ MOV_FROM_REG(56)
+ MOV_FROM_REG(57)
+ MOV_FROM_REG(58)
+ MOV_FROM_REG(59)
+ MOV_FROM_REG(60)
+ MOV_FROM_REG(61)
+ MOV_FROM_REG(62)
+ MOV_FROM_REG(63)
+ MOV_FROM_REG(64)
+ MOV_FROM_REG(65)
+ MOV_FROM_REG(66)
+ MOV_FROM_REG(67)
+ MOV_FROM_REG(68)
+ MOV_FROM_REG(69)
+ MOV_FROM_REG(70)
+ MOV_FROM_REG(71)
+ MOV_FROM_REG(72)
+ MOV_FROM_REG(73)
+ MOV_FROM_REG(74)
+ MOV_FROM_REG(75)
+ MOV_FROM_REG(76)
+ MOV_FROM_REG(77)
+ MOV_FROM_REG(78)
+ MOV_FROM_REG(79)
+ MOV_FROM_REG(80)
+ MOV_FROM_REG(81)
+ MOV_FROM_REG(82)
+ MOV_FROM_REG(83)
+ MOV_FROM_REG(84)
+ MOV_FROM_REG(85)
+ MOV_FROM_REG(86)
+ MOV_FROM_REG(87)
+ MOV_FROM_REG(88)
+ MOV_FROM_REG(89)
+ MOV_FROM_REG(90)
+ MOV_FROM_REG(91)
+ MOV_FROM_REG(92)
+ MOV_FROM_REG(93)
+ MOV_FROM_REG(94)
+ MOV_FROM_REG(95)
+ MOV_FROM_REG(96)
+ MOV_FROM_REG(97)
+ MOV_FROM_REG(98)
+ MOV_FROM_REG(99)
+ MOV_FROM_REG(100)
+ MOV_FROM_REG(101)
+ MOV_FROM_REG(102)
+ MOV_FROM_REG(103)
+ MOV_FROM_REG(104)
+ MOV_FROM_REG(105)
+ MOV_FROM_REG(106)
+ MOV_FROM_REG(107)
+ MOV_FROM_REG(108)
+ MOV_FROM_REG(109)
+ MOV_FROM_REG(110)
+ MOV_FROM_REG(111)
+ MOV_FROM_REG(112)
+ MOV_FROM_REG(113)
+ MOV_FROM_REG(114)
+ MOV_FROM_REG(115)
+ MOV_FROM_REG(116)
+ MOV_FROM_REG(117)
+ MOV_FROM_REG(118)
+ MOV_FROM_REG(119)
+ MOV_FROM_REG(120)
+ MOV_FROM_REG(121)
+ MOV_FROM_REG(122)
+ MOV_FROM_REG(123)
+ MOV_FROM_REG(124)
+ MOV_FROM_REG(125)
+ MOV_FROM_REG(126)
+ MOV_FROM_REG(127)
+END(asm_mov_from_reg)
+
+
+/* must be in bank 0
+ * parameter:
+ * r31: pr
+ * r24: b0
+ */
+ENTRY(kvm_resume_to_guest)
+ adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+ ;;
+ ld8 r1 =[r16]
+ adds r20 = VMM_VCPU_VSA_BASE_OFFSET,r21
+ ;;
+ mov r16=cr.ipsr
+ ;;
+ ld8 r20 = [r20]
+ adds r19=VMM_VPD_BASE_OFFSET,r21
+ ;;
+ ld8 r25=[r19]
+ extr.u r17=r16,IA64_PSR_RI_BIT,2
+ tbit.nz p6,p7=r16,IA64_PSR_RI_BIT+1
+ ;;
+ (p6) mov r18=cr.iip
+ (p6) mov r17=r0
+ ;;
+ (p6) add r18=0x10,r18
+ (p7) add r17=1,r17
+ ;;
+ (p6) mov cr.iip=r18
+ dep r16=r17,r16,IA64_PSR_RI_BIT,2
+ ;;
+ mov cr.ipsr=r16
+ adds r19= VPD_VPSR_START_OFFSET,r25
+ add r28=PAL_VPS_RESUME_NORMAL,r20
+ add r29=PAL_VPS_RESUME_HANDLER,r20
+ ;;
+ ld8 r19=[r19]
+ mov b0=r29
+ cmp.ne p6,p7 = r0,r0
+ ;;
+ tbit.z p6,p7 = r19,IA64_PSR_IC_BIT // p1=vpsr.ic
+ ;;
+ (p6) ld8 r26=[r25]
+ (p7) mov b0=r28
+ mov pr=r31,-2
+ br.sptk.many b0 // call pal service
+ ;;
+END(kvm_resume_to_guest)
+
+
+MOV_TO_BANK0_REG(16)
+MOV_TO_BANK0_REG(17)
+MOV_TO_BANK0_REG(18)
+MOV_TO_BANK0_REG(19)
+MOV_TO_BANK0_REG(20)
+MOV_TO_BANK0_REG(21)
+MOV_TO_BANK0_REG(22)
+MOV_TO_BANK0_REG(23)
+MOV_TO_BANK0_REG(24)
+MOV_TO_BANK0_REG(25)
+MOV_TO_BANK0_REG(26)
+MOV_TO_BANK0_REG(27)
+MOV_TO_BANK0_REG(28)
+MOV_TO_BANK0_REG(29)
+MOV_TO_BANK0_REG(30)
+MOV_TO_BANK0_REG(31)
+
+
+// mov to reg table
+ENTRY(asm_mov_to_reg)
+ MOV_TO_REG0
+ MOV_TO_REG(1)
+ MOV_TO_REG(2)
+ MOV_TO_REG(3)
+ MOV_TO_REG(4)
+ MOV_TO_REG(5)
+ MOV_TO_REG(6)
+ MOV_TO_REG(7)
+ MOV_TO_REG(8)
+ MOV_TO_REG(9)
+ MOV_TO_REG(10)
+ MOV_TO_REG(11)
+ MOV_TO_REG(12)
+ MOV_TO_REG(13)
+ MOV_TO_REG(14)
+ MOV_TO_REG(15)
+ JMP_TO_MOV_TO_BANK0_REG(16)
+ JMP_TO_MOV_TO_BANK0_REG(17)
+ JMP_TO_MOV_TO_BANK0_REG(18)
+ JMP_TO_MOV_TO_BANK0_REG(19)
+ JMP_TO_MOV_TO_BANK0_REG(20)
+ JMP_TO_MOV_TO_BANK0_REG(21)
+ JMP_TO_MOV_TO_BANK0_REG(22)
+ JMP_TO_MOV_TO_BANK0_REG(23)
+ JMP_TO_MOV_TO_BANK0_REG(24)
+ JMP_TO_MOV_TO_BANK0_REG(25)
+ JMP_TO_MOV_TO_BANK0_REG(26)
+ JMP_TO_MOV_TO_BANK0_REG(27)
+ JMP_TO_MOV_TO_BANK0_REG(28)
+ JMP_TO_MOV_TO_BANK0_REG(29)
+ JMP_TO_MOV_TO_BANK0_REG(30)
+ JMP_TO_MOV_TO_BANK0_REG(31)
+ MOV_TO_REG(32)
+ MOV_TO_REG(33)
+ MOV_TO_REG(34)
+ MOV_TO_REG(35)
+ MOV_TO_REG(36)
+ MOV_TO_REG(37)
+ MOV_TO_REG(38)
+ MOV_TO_REG(39)
+ MOV_TO_REG(40)
+ MOV_TO_REG(41)
+ MOV_TO_REG(42)
+ MOV_TO_REG(43)
+ MOV_TO_REG(44)
+ MOV_TO_REG(45)
+ MOV_TO_REG(46)
+ MOV_TO_REG(47)
+ MOV_TO_REG(48)
+ MOV_TO_REG(49)
+ MOV_TO_REG(50)
+ MOV_TO_REG(51)
+ MOV_TO_REG(52)
+ MOV_TO_REG(53)
+ MOV_TO_REG(54)
+ MOV_TO_REG(55)
+ MOV_TO_REG(56)
+ MOV_TO_REG(57)
+ MOV_TO_REG(58)
+ MOV_TO_REG(59)
+ MOV_TO_REG(60)
+ MOV_TO_REG(61)
+ MOV_TO_REG(62)
+ MOV_TO_REG(63)
+ MOV_TO_REG(64)
+ MOV_TO_REG(65)
+ MOV_TO_REG(66)
+ MOV_TO_REG(67)
+ MOV_TO_REG(68)
+ MOV_TO_REG(69)
+ MOV_TO_REG(70)
+ MOV_TO_REG(71)
+ MOV_TO_REG(72)
+ MOV_TO_REG(73)
+ MOV_TO_REG(74)
+ MOV_TO_REG(75)
+ MOV_TO_REG(76)
+ MOV_TO_REG(77)
+ MOV_TO_REG(78)
+ MOV_TO_REG(79)
+ MOV_TO_REG(80)
+ MOV_TO_REG(81)
+ MOV_TO_REG(82)
+ MOV_TO_REG(83)
+ MOV_TO_REG(84)
+ MOV_TO_REG(85)
+ MOV_TO_REG(86)
+ MOV_TO_REG(87)
+ MOV_TO_REG(88)
+ MOV_TO_REG(89)
+ MOV_TO_REG(90)
+ MOV_TO_REG(91)
+ MOV_TO_REG(92)
+ MOV_TO_REG(93)
+ MOV_TO_REG(94)
+ MOV_TO_REG(95)
+ MOV_TO_REG(96)
+ MOV_TO_REG(97)
+ MOV_TO_REG(98)
+ MOV_TO_REG(99)
+ MOV_TO_REG(100)
+ MOV_TO_REG(101)
+ MOV_TO_REG(102)
+ MOV_TO_REG(103)
+ MOV_TO_REG(104)
+ MOV_TO_REG(105)
+ MOV_TO_REG(106)
+ MOV_TO_REG(107)
+ MOV_TO_REG(108)
+ MOV_TO_REG(109)
+ MOV_TO_REG(110)
+ MOV_TO_REG(111)
+ MOV_TO_REG(112)
+ MOV_TO_REG(113)
+ MOV_TO_REG(114)
+ MOV_TO_REG(115)
+ MOV_TO_REG(116)
+ MOV_TO_REG(117)
+ MOV_TO_REG(118)
+ MOV_TO_REG(119)
+ MOV_TO_REG(120)
+ MOV_TO_REG(121)
+ MOV_TO_REG(122)
+ MOV_TO_REG(123)
+ MOV_TO_REG(124)
+ MOV_TO_REG(125)
+ MOV_TO_REG(126)
+ MOV_TO_REG(127)
+END(asm_mov_to_reg)
diff --git a/arch/ia64/kvm/process.c b/arch/ia64/kvm/process.c
new file mode 100644
index 00000000000..5a33f7ed29a
--- /dev/null
+++ b/arch/ia64/kvm/process.c
@@ -0,0 +1,970 @@
+/*
+ * process.c: handle interruption inject for guests.
+ * Copyright (c) 2005, 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.
+ *
+ * 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.
+ *
+ * Shaofan Li (Susue Li) <susie.li@intel.com>
+ * Xiaoyan Feng (Fleming Feng) <fleming.feng@intel.com>
+ * Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ */
+#include "vcpu.h"
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/fpswa.h>
+#include <asm/kregs.h>
+#include <asm/tlb.h>
+
+fpswa_interface_t *vmm_fpswa_interface;
+
+#define IA64_VHPT_TRANS_VECTOR 0x0000
+#define IA64_INST_TLB_VECTOR 0x0400
+#define IA64_DATA_TLB_VECTOR 0x0800
+#define IA64_ALT_INST_TLB_VECTOR 0x0c00
+#define IA64_ALT_DATA_TLB_VECTOR 0x1000
+#define IA64_DATA_NESTED_TLB_VECTOR 0x1400
+#define IA64_INST_KEY_MISS_VECTOR 0x1800
+#define IA64_DATA_KEY_MISS_VECTOR 0x1c00
+#define IA64_DIRTY_BIT_VECTOR 0x2000
+#define IA64_INST_ACCESS_BIT_VECTOR 0x2400
+#define IA64_DATA_ACCESS_BIT_VECTOR 0x2800
+#define IA64_BREAK_VECTOR 0x2c00
+#define IA64_EXTINT_VECTOR 0x3000
+#define IA64_PAGE_NOT_PRESENT_VECTOR 0x5000
+#define IA64_KEY_PERMISSION_VECTOR 0x5100
+#define IA64_INST_ACCESS_RIGHTS_VECTOR 0x5200
+#define IA64_DATA_ACCESS_RIGHTS_VECTOR 0x5300
+#define IA64_GENEX_VECTOR 0x5400
+#define IA64_DISABLED_FPREG_VECTOR 0x5500
+#define IA64_NAT_CONSUMPTION_VECTOR 0x5600
+#define IA64_SPECULATION_VECTOR 0x5700 /* UNUSED */
+#define IA64_DEBUG_VECTOR 0x5900
+#define IA64_UNALIGNED_REF_VECTOR 0x5a00
+#define IA64_UNSUPPORTED_DATA_REF_VECTOR 0x5b00
+#define IA64_FP_FAULT_VECTOR 0x5c00
+#define IA64_FP_TRAP_VECTOR 0x5d00
+#define IA64_LOWERPRIV_TRANSFER_TRAP_VECTOR 0x5e00
+#define IA64_TAKEN_BRANCH_TRAP_VECTOR 0x5f00
+#define IA64_SINGLE_STEP_TRAP_VECTOR 0x6000
+
+/* SDM vol2 5.5 - IVA based interruption handling */
+#define INITIAL_PSR_VALUE_AT_INTERRUPTION (IA64_PSR_UP | IA64_PSR_MFL |\
+ IA64_PSR_MFH | IA64_PSR_PK | IA64_PSR_DT | \
+ IA64_PSR_RT | IA64_PSR_MC|IA64_PSR_IT)
+
+#define DOMN_PAL_REQUEST 0x110000
+#define DOMN_SAL_REQUEST 0x110001
+
+static u64 vec2off[68] = {0x0, 0x400, 0x800, 0xc00, 0x1000, 0x1400, 0x1800,
+ 0x1c00, 0x2000, 0x2400, 0x2800, 0x2c00, 0x3000, 0x3400, 0x3800, 0x3c00,
+ 0x4000, 0x4400, 0x4800, 0x4c00, 0x5000, 0x5100, 0x5200, 0x5300, 0x5400,
+ 0x5500, 0x5600, 0x5700, 0x5800, 0x5900, 0x5a00, 0x5b00, 0x5c00, 0x5d00,
+ 0x5e00, 0x5f00, 0x6000, 0x6100, 0x6200, 0x6300, 0x6400, 0x6500, 0x6600,
+ 0x6700, 0x6800, 0x6900, 0x6a00, 0x6b00, 0x6c00, 0x6d00, 0x6e00, 0x6f00,
+ 0x7000, 0x7100, 0x7200, 0x7300, 0x7400, 0x7500, 0x7600, 0x7700, 0x7800,
+ 0x7900, 0x7a00, 0x7b00, 0x7c00, 0x7d00, 0x7e00, 0x7f00
+};
+
+static void collect_interruption(struct kvm_vcpu *vcpu)
+{
+ u64 ipsr;
+ u64 vdcr;
+ u64 vifs;
+ unsigned long vpsr;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ vpsr = vcpu_get_psr(vcpu);
+ vcpu_bsw0(vcpu);
+ if (vpsr & IA64_PSR_IC) {
+
+ /* Sync mpsr id/da/dd/ss/ed bits to vipsr
+ * since after guest do rfi, we still want these bits on in
+ * mpsr
+ */
+
+ ipsr = regs->cr_ipsr;
+ vpsr = vpsr | (ipsr & (IA64_PSR_ID | IA64_PSR_DA
+ | IA64_PSR_DD | IA64_PSR_SS
+ | IA64_PSR_ED));
+ vcpu_set_ipsr(vcpu, vpsr);
+
+ /* Currently, for trap, we do not advance IIP to next
+ * instruction. That's because we assume caller already
+ * set up IIP correctly
+ */
+
+ vcpu_set_iip(vcpu , regs->cr_iip);
+
+ /* set vifs.v to zero */
+ vifs = VCPU(vcpu, ifs);
+ vifs &= ~IA64_IFS_V;
+ vcpu_set_ifs(vcpu, vifs);
+
+ vcpu_set_iipa(vcpu, VMX(vcpu, cr_iipa));
+ }
+
+ vdcr = VCPU(vcpu, dcr);
+
+ /* Set guest psr
+ * up/mfl/mfh/pk/dt/rt/mc/it keeps unchanged
+ * be: set to the value of dcr.be
+ * pp: set to the value of dcr.pp
+ */
+ vpsr &= INITIAL_PSR_VALUE_AT_INTERRUPTION;
+ vpsr |= (vdcr & IA64_DCR_BE);
+
+ /* VDCR pp bit position is different from VPSR pp bit */
+ if (vdcr & IA64_DCR_PP) {
+ vpsr |= IA64_PSR_PP;
+ } else {
+ vpsr &= ~IA64_PSR_PP;;
+ }
+
+ vcpu_set_psr(vcpu, vpsr);
+
+}
+
+void inject_guest_interruption(struct kvm_vcpu *vcpu, u64 vec)
+{
+ u64 viva;
+ struct kvm_pt_regs *regs;
+ union ia64_isr pt_isr;
+
+ regs = vcpu_regs(vcpu);
+
+ /* clear cr.isr.ir (incomplete register frame)*/
+ pt_isr.val = VMX(vcpu, cr_isr);
+ pt_isr.ir = 0;
+ VMX(vcpu, cr_isr) = pt_isr.val;
+
+ collect_interruption(vcpu);
+
+ viva = vcpu_get_iva(vcpu);
+ regs->cr_iip = viva + vec;
+}
+
+static u64 vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, u64 ifa)
+{
+ union ia64_rr rr, rr1;
+
+ rr.val = vcpu_get_rr(vcpu, ifa);
+ rr1.val = 0;
+ rr1.ps = rr.ps;
+ rr1.rid = rr.rid;
+ return (rr1.val);
+}
+
+
+/*
+ * Set vIFA & vITIR & vIHA, when vPSR.ic =1
+ * Parameter:
+ * set_ifa: if true, set vIFA
+ * set_itir: if true, set vITIR
+ * set_iha: if true, set vIHA
+ */
+void set_ifa_itir_iha(struct kvm_vcpu *vcpu, u64 vadr,
+ int set_ifa, int set_itir, int set_iha)
+{
+ long vpsr;
+ u64 value;
+
+ vpsr = VCPU(vcpu, vpsr);
+ /* Vol2, Table 8-1 */
+ if (vpsr & IA64_PSR_IC) {
+ if (set_ifa)
+ vcpu_set_ifa(vcpu, vadr);
+ if (set_itir) {
+ value = vcpu_get_itir_on_fault(vcpu, vadr);
+ vcpu_set_itir(vcpu, value);
+ }
+
+ if (set_iha) {
+ value = vcpu_thash(vcpu, vadr);
+ vcpu_set_iha(vcpu, value);
+ }
+ }
+}
+
+/*
+ * Data TLB Fault
+ * @ Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dtlb_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ /* If vPSR.ic, IFA, ITIR, IHA */
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+ inject_guest_interruption(vcpu, IA64_DATA_TLB_VECTOR);
+}
+
+/*
+ * Instruction TLB Fault
+ * @ Instruction TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void itlb_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ /* If vPSR.ic, IFA, ITIR, IHA */
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+ inject_guest_interruption(vcpu, IA64_INST_TLB_VECTOR);
+}
+
+
+
+/*
+ * Data Nested TLB Fault
+ * @ Data Nested TLB Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void nested_dtlb(struct kvm_vcpu *vcpu)
+{
+ inject_guest_interruption(vcpu, IA64_DATA_NESTED_TLB_VECTOR);
+}
+
+/*
+ * Alternate Data TLB Fault
+ * @ Alternate Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void alt_dtlb(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+ inject_guest_interruption(vcpu, IA64_ALT_DATA_TLB_VECTOR);
+}
+
+
+/*
+ * Data TLB Fault
+ * @ Data TLB vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void alt_itlb(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+ inject_guest_interruption(vcpu, IA64_ALT_INST_TLB_VECTOR);
+}
+
+/* Deal with:
+ * VHPT Translation Vector
+ */
+static void _vhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ /* If vPSR.ic, IFA, ITIR, IHA*/
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 1);
+ inject_guest_interruption(vcpu, IA64_VHPT_TRANS_VECTOR);
+
+
+}
+
+/*
+ * VHPT Instruction Fault
+ * @ VHPT Translation vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void ivhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ _vhpt_fault(vcpu, vadr);
+}
+
+
+/*
+ * VHPT Data Fault
+ * @ VHPT Translation vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dvhpt_fault(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ _vhpt_fault(vcpu, vadr);
+}
+
+
+
+/*
+ * Deal with:
+ * General Exception vector
+ */
+void _general_exception(struct kvm_vcpu *vcpu)
+{
+ inject_guest_interruption(vcpu, IA64_GENEX_VECTOR);
+}
+
+
+/*
+ * Illegal Operation Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void illegal_op(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+
+/*
+ * Illegal Dependency Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void illegal_dep(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+
+/*
+ * Reserved Register/Field Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void rsv_reg_field(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+/*
+ * Privileged Operation Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+
+void privilege_op(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+
+/*
+ * Unimplement Data Address Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void unimpl_daddr(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+
+/*
+ * Privileged Register Fault
+ * @ General Exception Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void privilege_reg(struct kvm_vcpu *vcpu)
+{
+ _general_exception(vcpu);
+}
+
+/* Deal with
+ * Nat consumption vector
+ * Parameter:
+ * vaddr: Optional, if t == REGISTER
+ */
+static void _nat_consumption_fault(struct kvm_vcpu *vcpu, u64 vadr,
+ enum tlb_miss_type t)
+{
+ /* If vPSR.ic && t == DATA/INST, IFA */
+ if (t == DATA || t == INSTRUCTION) {
+ /* IFA */
+ set_ifa_itir_iha(vcpu, vadr, 1, 0, 0);
+ }
+
+ inject_guest_interruption(vcpu, IA64_NAT_CONSUMPTION_VECTOR);
+}
+
+/*
+ * Instruction Nat Page Consumption Fault
+ * @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void inat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ _nat_consumption_fault(vcpu, vadr, INSTRUCTION);
+}
+
+/*
+ * Register Nat Consumption Fault
+ * @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void rnat_consumption(struct kvm_vcpu *vcpu)
+{
+ _nat_consumption_fault(vcpu, 0, REGISTER);
+}
+
+/*
+ * Data Nat Page Consumption Fault
+ * @ Nat Consumption Vector
+ * Refer to SDM Vol2 Table 5-6 & 8-1
+ */
+void dnat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ _nat_consumption_fault(vcpu, vadr, DATA);
+}
+
+/* Deal with
+ * Page not present vector
+ */
+static void __page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ /* If vPSR.ic, IFA, ITIR */
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+ inject_guest_interruption(vcpu, IA64_PAGE_NOT_PRESENT_VECTOR);
+}
+
+
+void data_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ __page_not_present(vcpu, vadr);
+}
+
+
+void inst_page_not_present(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ __page_not_present(vcpu, vadr);
+}
+
+
+/* Deal with
+ * Data access rights vector
+ */
+void data_access_rights(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ /* If vPSR.ic, IFA, ITIR */
+ set_ifa_itir_iha(vcpu, vadr, 1, 1, 0);
+ inject_guest_interruption(vcpu, IA64_DATA_ACCESS_RIGHTS_VECTOR);
+}
+
+fpswa_ret_t vmm_fp_emulate(int fp_fault, void *bundle, unsigned long *ipsr,
+ unsigned long *fpsr, unsigned long *isr, unsigned long *pr,
+ unsigned long *ifs, struct kvm_pt_regs *regs)
+{
+ fp_state_t fp_state;
+ fpswa_ret_t ret;
+ struct kvm_vcpu *vcpu = current_vcpu;
+
+ uint64_t old_rr7 = ia64_get_rr(7UL<<61);
+
+ if (!vmm_fpswa_interface)
+ return (fpswa_ret_t) {-1, 0, 0, 0};
+
+ /*
+ * Just let fpswa driver to use hardware fp registers.
+ * No fp register is valid in memory.
+ */
+ memset(&fp_state, 0, sizeof(fp_state_t));
+
+ /*
+ * unsigned long (*EFI_FPSWA) (
+ * unsigned long trap_type,
+ * void *Bundle,
+ * unsigned long *pipsr,
+ * unsigned long *pfsr,
+ * unsigned long *pisr,
+ * unsigned long *ppreds,
+ * unsigned long *pifs,
+ * void *fp_state);
+ */
+ /*Call host fpswa interface directly to virtualize
+ *guest fpswa request!
+ */
+ ia64_set_rr(7UL << 61, vcpu->arch.host.rr[7]);
+ ia64_srlz_d();
+
+ ret = (*vmm_fpswa_interface->fpswa) (fp_fault, bundle,
+ ipsr, fpsr, isr, pr, ifs, &fp_state);
+ ia64_set_rr(7UL << 61, old_rr7);
+ ia64_srlz_d();
+ return ret;
+}
+
+/*
+ * Handle floating-point assist faults and traps for domain.
+ */
+unsigned long vmm_handle_fpu_swa(int fp_fault, struct kvm_pt_regs *regs,
+ unsigned long isr)
+{
+ struct kvm_vcpu *v = current_vcpu;
+ IA64_BUNDLE bundle;
+ unsigned long fault_ip;
+ fpswa_ret_t ret;
+
+ fault_ip = regs->cr_iip;
+ /*
+ * When the FP trap occurs, the trapping instruction is completed.
+ * If ipsr.ri == 0, there is the trapping instruction in previous
+ * bundle.
+ */
+ if (!fp_fault && (ia64_psr(regs)->ri == 0))
+ fault_ip -= 16;
+
+ if (fetch_code(v, fault_ip, &bundle))
+ return -EAGAIN;
+
+ if (!bundle.i64[0] && !bundle.i64[1])
+ return -EACCES;
+
+ ret = vmm_fp_emulate(fp_fault, &bundle, &regs->cr_ipsr, &regs->ar_fpsr,
+ &isr, &regs->pr, &regs->cr_ifs, regs);
+ return ret.status;
+}
+
+void reflect_interruption(u64 ifa, u64 isr, u64 iim,
+ u64 vec, struct kvm_pt_regs *regs)
+{
+ u64 vector;
+ int status ;
+ struct kvm_vcpu *vcpu = current_vcpu;
+ u64 vpsr = VCPU(vcpu, vpsr);
+
+ vector = vec2off[vec];
+
+ if (!(vpsr & IA64_PSR_IC) && (vector != IA64_DATA_NESTED_TLB_VECTOR)) {
+ panic_vm(vcpu);
+ return;
+ }
+
+ switch (vec) {
+ case 32: /*IA64_FP_FAULT_VECTOR*/
+ status = vmm_handle_fpu_swa(1, regs, isr);
+ if (!status) {
+ vcpu_increment_iip(vcpu);
+ return;
+ } else if (-EAGAIN == status)
+ return;
+ break;
+ case 33: /*IA64_FP_TRAP_VECTOR*/
+ status = vmm_handle_fpu_swa(0, regs, isr);
+ if (!status)
+ return ;
+ else if (-EAGAIN == status) {
+ vcpu_decrement_iip(vcpu);
+ return ;
+ }
+ break;
+ }
+
+ VCPU(vcpu, isr) = isr;
+ VCPU(vcpu, iipa) = regs->cr_iip;
+ if (vector == IA64_BREAK_VECTOR || vector == IA64_SPECULATION_VECTOR)
+ VCPU(vcpu, iim) = iim;
+ else
+ set_ifa_itir_iha(vcpu, ifa, 1, 1, 1);
+
+ inject_guest_interruption(vcpu, vector);
+}
+
+static void set_pal_call_data(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+ /*FIXME:For static and stacked convention, firmware
+ * has put the parameters in gr28-gr31 before
+ * break to vmm !!*/
+
+ p->u.pal_data.gr28 = vcpu_get_gr(vcpu, 28);
+ p->u.pal_data.gr29 = vcpu_get_gr(vcpu, 29);
+ p->u.pal_data.gr30 = vcpu_get_gr(vcpu, 30);
+ p->u.pal_data.gr31 = vcpu_get_gr(vcpu, 31);
+ p->exit_reason = EXIT_REASON_PAL_CALL;
+}
+
+static void set_pal_call_result(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+ if (p->exit_reason == EXIT_REASON_PAL_CALL) {
+ vcpu_set_gr(vcpu, 8, p->u.pal_data.ret.status, 0);
+ vcpu_set_gr(vcpu, 9, p->u.pal_data.ret.v0, 0);
+ vcpu_set_gr(vcpu, 10, p->u.pal_data.ret.v1, 0);
+ vcpu_set_gr(vcpu, 11, p->u.pal_data.ret.v2, 0);
+ } else
+ panic_vm(vcpu);
+}
+
+static void set_sal_call_data(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+ p->u.sal_data.in0 = vcpu_get_gr(vcpu, 32);
+ p->u.sal_data.in1 = vcpu_get_gr(vcpu, 33);
+ p->u.sal_data.in2 = vcpu_get_gr(vcpu, 34);
+ p->u.sal_data.in3 = vcpu_get_gr(vcpu, 35);
+ p->u.sal_data.in4 = vcpu_get_gr(vcpu, 36);
+ p->u.sal_data.in5 = vcpu_get_gr(vcpu, 37);
+ p->u.sal_data.in6 = vcpu_get_gr(vcpu, 38);
+ p->u.sal_data.in7 = vcpu_get_gr(vcpu, 39);
+ p->exit_reason = EXIT_REASON_SAL_CALL;
+}
+
+static void set_sal_call_result(struct kvm_vcpu *vcpu)
+{
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+ if (p->exit_reason == EXIT_REASON_SAL_CALL) {
+ vcpu_set_gr(vcpu, 8, p->u.sal_data.ret.r8, 0);
+ vcpu_set_gr(vcpu, 9, p->u.sal_data.ret.r9, 0);
+ vcpu_set_gr(vcpu, 10, p->u.sal_data.ret.r10, 0);
+ vcpu_set_gr(vcpu, 11, p->u.sal_data.ret.r11, 0);
+ } else
+ panic_vm(vcpu);
+}
+
+void kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
+ unsigned long isr, unsigned long iim)
+{
+ struct kvm_vcpu *v = current_vcpu;
+
+ if (ia64_psr(regs)->cpl == 0) {
+ /* Allow hypercalls only when cpl = 0. */
+ if (iim == DOMN_PAL_REQUEST) {
+ set_pal_call_data(v);
+ vmm_transition(v);
+ set_pal_call_result(v);
+ vcpu_increment_iip(v);
+ return;
+ } else if (iim == DOMN_SAL_REQUEST) {
+ set_sal_call_data(v);
+ vmm_transition(v);
+ set_sal_call_result(v);
+ vcpu_increment_iip(v);
+ return;
+ }
+ }
+ reflect_interruption(ifa, isr, iim, 11, regs);
+}
+
+void check_pending_irq(struct kvm_vcpu *vcpu)
+{
+ int mask, h_pending, h_inservice;
+ u64 isr;
+ unsigned long vpsr;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ h_pending = highest_pending_irq(vcpu);
+ if (h_pending == NULL_VECTOR) {
+ update_vhpi(vcpu, NULL_VECTOR);
+ return;
+ }
+ h_inservice = highest_inservice_irq(vcpu);
+
+ vpsr = VCPU(vcpu, vpsr);
+ mask = irq_masked(vcpu, h_pending, h_inservice);
+ if ((vpsr & IA64_PSR_I) && IRQ_NO_MASKED == mask) {
+ isr = vpsr & IA64_PSR_RI;
+ update_vhpi(vcpu, h_pending);
+ reflect_interruption(0, isr, 0, 12, regs); /* EXT IRQ */
+ } else if (mask == IRQ_MASKED_BY_INSVC) {
+ if (VCPU(vcpu, vhpi))
+ update_vhpi(vcpu, NULL_VECTOR);
+ } else {
+ /* masked by vpsr.i or vtpr.*/
+ update_vhpi(vcpu, h_pending);
+ }
+}
+
+static void generate_exirq(struct kvm_vcpu *vcpu)
+{
+ unsigned vpsr;
+ uint64_t isr;
+
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ vpsr = VCPU(vcpu, vpsr);
+ isr = vpsr & IA64_PSR_RI;
+ if (!(vpsr & IA64_PSR_IC))
+ panic_vm(vcpu);
+ reflect_interruption(0, isr, 0, 12, regs); /* EXT IRQ */
+}
+
+void vhpi_detection(struct kvm_vcpu *vcpu)
+{
+ uint64_t threshold, vhpi;
+ union ia64_tpr vtpr;
+ struct ia64_psr vpsr;
+
+ vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+ vtpr.val = VCPU(vcpu, tpr);
+
+ threshold = ((!vpsr.i) << 5) | (vtpr.mmi << 4) | vtpr.mic;
+ vhpi = VCPU(vcpu, vhpi);
+ if (vhpi > threshold) {
+ /* interrupt actived*/
+ generate_exirq(vcpu);
+ }
+}
+
+
+void leave_hypervisor_tail(void)
+{
+ struct kvm_vcpu *v = current_vcpu;
+
+ if (VMX(v, timer_check)) {
+ VMX(v, timer_check) = 0;
+ if (VMX(v, itc_check)) {
+ if (vcpu_get_itc(v) > VCPU(v, itm)) {
+ if (!(VCPU(v, itv) & (1 << 16))) {
+ vcpu_pend_interrupt(v, VCPU(v, itv)
+ & 0xff);
+ VMX(v, itc_check) = 0;
+ } else {
+ v->arch.timer_pending = 1;
+ }
+ VMX(v, last_itc) = VCPU(v, itm) + 1;
+ }
+ }
+ }
+
+ rmb();
+ if (v->arch.irq_new_pending) {
+ v->arch.irq_new_pending = 0;
+ VMX(v, irq_check) = 0;
+ check_pending_irq(v);
+ return;
+ }
+ if (VMX(v, irq_check)) {
+ VMX(v, irq_check) = 0;
+ vhpi_detection(v);
+ }
+}
+
+
+static inline void handle_lds(struct kvm_pt_regs *regs)
+{
+ regs->cr_ipsr |= IA64_PSR_ED;
+}
+
+void physical_tlb_miss(struct kvm_vcpu *vcpu, unsigned long vadr, int type)
+{
+ unsigned long pte;
+ union ia64_rr rr;
+
+ rr.val = ia64_get_rr(vadr);
+ pte = vadr & _PAGE_PPN_MASK;
+ pte = pte | PHY_PAGE_WB;
+ thash_vhpt_insert(vcpu, pte, (u64)(rr.ps << 2), vadr, type);
+ return;
+}
+
+void kvm_page_fault(u64 vadr , u64 vec, struct kvm_pt_regs *regs)
+{
+ unsigned long vpsr;
+ int type;
+
+ u64 vhpt_adr, gppa, pteval, rr, itir;
+ union ia64_isr misr;
+ union ia64_pta vpta;
+ struct thash_data *data;
+ struct kvm_vcpu *v = current_vcpu;
+
+ vpsr = VCPU(v, vpsr);
+ misr.val = VMX(v, cr_isr);
+
+ type = vec;
+
+ if (is_physical_mode(v) && (!(vadr << 1 >> 62))) {
+ if (vec == 2) {
+ if (__gpfn_is_io((vadr << 1) >> (PAGE_SHIFT + 1))) {
+ emulate_io_inst(v, ((vadr << 1) >> 1), 4);
+ return;
+ }
+ }
+ physical_tlb_miss(v, vadr, type);
+ return;
+ }
+ data = vtlb_lookup(v, vadr, type);
+ if (data != 0) {
+ if (type == D_TLB) {
+ gppa = (vadr & ((1UL << data->ps) - 1))
+ + (data->ppn >> (data->ps - 12) << data->ps);
+ if (__gpfn_is_io(gppa >> PAGE_SHIFT)) {
+ if (data->pl >= ((regs->cr_ipsr >>
+ IA64_PSR_CPL0_BIT) & 3))
+ emulate_io_inst(v, gppa, data->ma);
+ else {
+ vcpu_set_isr(v, misr.val);
+ data_access_rights(v, vadr);
+ }
+ return ;
+ }
+ }
+ thash_vhpt_insert(v, data->page_flags, data->itir, vadr, type);
+
+ } else if (type == D_TLB) {
+ if (misr.sp) {
+ handle_lds(regs);
+ return;
+ }
+
+ rr = vcpu_get_rr(v, vadr);
+ itir = rr & (RR_RID_MASK | RR_PS_MASK);
+
+ if (!vhpt_enabled(v, vadr, misr.rs ? RSE_REF : DATA_REF)) {
+ if (vpsr & IA64_PSR_IC) {
+ vcpu_set_isr(v, misr.val);
+ alt_dtlb(v, vadr);
+ } else {
+ nested_dtlb(v);
+ }
+ return ;
+ }
+
+ vpta.val = vcpu_get_pta(v);
+ /* avoid recursively walking (short format) VHPT */
+
+ vhpt_adr = vcpu_thash(v, vadr);
+ if (!guest_vhpt_lookup(vhpt_adr, &pteval)) {
+ /* VHPT successfully read. */
+ if (!(pteval & _PAGE_P)) {
+ if (vpsr & IA64_PSR_IC) {
+ vcpu_set_isr(v, misr.val);
+ dtlb_fault(v, vadr);
+ } else {
+ nested_dtlb(v);
+ }
+ } else if ((pteval & _PAGE_MA_MASK) != _PAGE_MA_ST) {
+ thash_purge_and_insert(v, pteval, itir,
+ vadr, D_TLB);
+ } else if (vpsr & IA64_PSR_IC) {
+ vcpu_set_isr(v, misr.val);
+ dtlb_fault(v, vadr);
+ } else {
+ nested_dtlb(v);
+ }
+ } else {
+ /* Can't read VHPT. */
+ if (vpsr & IA64_PSR_IC) {
+ vcpu_set_isr(v, misr.val);
+ dvhpt_fault(v, vadr);
+ } else {
+ nested_dtlb(v);
+ }
+ }
+ } else if (type == I_TLB) {
+ if (!(vpsr & IA64_PSR_IC))
+ misr.ni = 1;
+ if (!vhpt_enabled(v, vadr, INST_REF)) {
+ vcpu_set_isr(v, misr.val);
+ alt_itlb(v, vadr);
+ return;
+ }
+
+ vpta.val = vcpu_get_pta(v);
+
+ vhpt_adr = vcpu_thash(v, vadr);
+ if (!guest_vhpt_lookup(vhpt_adr, &pteval)) {
+ /* VHPT successfully read. */
+ if (pteval & _PAGE_P) {
+ if ((pteval & _PAGE_MA_MASK) == _PAGE_MA_ST) {
+ vcpu_set_isr(v, misr.val);
+ itlb_fault(v, vadr);
+ return ;
+ }
+ rr = vcpu_get_rr(v, vadr);
+ itir = rr & (RR_RID_MASK | RR_PS_MASK);
+ thash_purge_and_insert(v, pteval, itir,
+ vadr, I_TLB);
+ } else {
+ vcpu_set_isr(v, misr.val);
+ inst_page_not_present(v, vadr);
+ }
+ } else {
+ vcpu_set_isr(v, misr.val);
+ ivhpt_fault(v, vadr);
+ }
+ }
+}
+
+void kvm_vexirq(struct kvm_vcpu *vcpu)
+{
+ u64 vpsr, isr;
+ struct kvm_pt_regs *regs;
+
+ regs = vcpu_regs(vcpu);
+ vpsr = VCPU(vcpu, vpsr);
+ isr = vpsr & IA64_PSR_RI;
+ reflect_interruption(0, isr, 0, 12, regs); /*EXT IRQ*/
+}
+
+void kvm_ia64_handle_irq(struct kvm_vcpu *v)
+{
+ struct exit_ctl_data *p = &v->arch.exit_data;
+ long psr;
+
+ local_irq_save(psr);
+ p->exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT;
+ vmm_transition(v);
+ local_irq_restore(psr);
+
+ VMX(v, timer_check) = 1;
+
+}
+
+static void ptc_ga_remote_func(struct kvm_vcpu *v, int pos)
+{
+ u64 oldrid, moldrid, oldpsbits, vaddr;
+ struct kvm_ptc_g *p = &v->arch.ptc_g_data[pos];
+ vaddr = p->vaddr;
+
+ oldrid = VMX(v, vrr[0]);
+ VMX(v, vrr[0]) = p->rr;
+ oldpsbits = VMX(v, psbits[0]);
+ VMX(v, psbits[0]) = VMX(v, psbits[REGION_NUMBER(vaddr)]);
+ moldrid = ia64_get_rr(0x0);
+ ia64_set_rr(0x0, vrrtomrr(p->rr));
+ ia64_srlz_d();
+
+ vaddr = PAGEALIGN(vaddr, p->ps);
+ thash_purge_entries_remote(v, vaddr, p->ps);
+
+ VMX(v, vrr[0]) = oldrid;
+ VMX(v, psbits[0]) = oldpsbits;
+ ia64_set_rr(0x0, moldrid);
+ ia64_dv_serialize_data();
+}
+
+static void vcpu_do_resume(struct kvm_vcpu *vcpu)
+{
+ /*Re-init VHPT and VTLB once from resume*/
+ vcpu->arch.vhpt.num = VHPT_NUM_ENTRIES;
+ thash_init(&vcpu->arch.vhpt, VHPT_SHIFT);
+ vcpu->arch.vtlb.num = VTLB_NUM_ENTRIES;
+ thash_init(&vcpu->arch.vtlb, VTLB_SHIFT);
+
+ ia64_set_pta(vcpu->arch.vhpt.pta.val);
+}
+
+static void kvm_do_resume_op(struct kvm_vcpu *vcpu)
+{
+ if (test_and_clear_bit(KVM_REQ_RESUME, &vcpu->requests)) {
+ vcpu_do_resume(vcpu);
+ return;
+ }
+
+ if (unlikely(test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))) {
+ thash_purge_all(vcpu);
+ return;
+ }
+
+ if (test_and_clear_bit(KVM_REQ_PTC_G, &vcpu->requests)) {
+ while (vcpu->arch.ptc_g_count > 0)
+ ptc_ga_remote_func(vcpu, --vcpu->arch.ptc_g_count);
+ }
+}
+
+void vmm_transition(struct kvm_vcpu *vcpu)
+{
+ ia64_call_vsa(PAL_VPS_SAVE, (unsigned long)vcpu->arch.vpd,
+ 0, 0, 0, 0, 0, 0);
+ vmm_trampoline(&vcpu->arch.guest, &vcpu->arch.host);
+ ia64_call_vsa(PAL_VPS_RESTORE, (unsigned long)vcpu->arch.vpd,
+ 0, 0, 0, 0, 0, 0);
+ kvm_do_resume_op(vcpu);
+}
diff --git a/arch/ia64/kvm/trampoline.S b/arch/ia64/kvm/trampoline.S
new file mode 100644
index 00000000000..30897d44d61
--- /dev/null
+++ b/arch/ia64/kvm/trampoline.S
@@ -0,0 +1,1038 @@
+/* Save all processor states
+ *
+ * Copyright (c) 2007 Fleming Feng <fleming.feng@intel.com>
+ * Copyright (c) 2007 Anthony Xu <anthony.xu@intel.com>
+ */
+
+#include <asm/asmmacro.h>
+#include "asm-offsets.h"
+
+
+#define CTX(name) VMM_CTX_##name##_OFFSET
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_BRANCH_REGS \
+ add r2 = CTX(B0),r32; \
+ add r3 = CTX(B1),r32; \
+ mov r16 = b0; \
+ mov r17 = b1; \
+ ;; \
+ st8 [r2]=r16,16; \
+ st8 [r3]=r17,16; \
+ ;; \
+ mov r16 = b2; \
+ mov r17 = b3; \
+ ;; \
+ st8 [r2]=r16,16; \
+ st8 [r3]=r17,16; \
+ ;; \
+ mov r16 = b4; \
+ mov r17 = b5; \
+ ;; \
+ st8 [r2]=r16; \
+ st8 [r3]=r17; \
+ ;;
+
+ /*
+ * r33: context_t base address
+ */
+#define RESTORE_BRANCH_REGS \
+ add r2 = CTX(B0),r33; \
+ add r3 = CTX(B1),r33; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov b0 = r16; \
+ mov b1 = r17; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov b2 = r16; \
+ mov b3 = r17; \
+ ;; \
+ ld8 r16=[r2]; \
+ ld8 r17=[r3]; \
+ ;; \
+ mov b4=r16; \
+ mov b5=r17; \
+ ;;
+
+
+ /*
+ * r32: context_t base address
+ * bsw == 1
+ * Save all bank1 general registers, r4 ~ r7
+ */
+#define SAVE_GENERAL_REGS \
+ add r2=CTX(R4),r32; \
+ add r3=CTX(R5),r32; \
+ ;; \
+.mem.offset 0,0; \
+ st8.spill [r2]=r4,16; \
+.mem.offset 8,0; \
+ st8.spill [r3]=r5,16; \
+ ;; \
+.mem.offset 0,0; \
+ st8.spill [r2]=r6,48; \
+.mem.offset 8,0; \
+ st8.spill [r3]=r7,48; \
+ ;; \
+.mem.offset 0,0; \
+ st8.spill [r2]=r12; \
+.mem.offset 8,0; \
+ st8.spill [r3]=r13; \
+ ;;
+
+ /*
+ * r33: context_t base address
+ * bsw == 1
+ */
+#define RESTORE_GENERAL_REGS \
+ add r2=CTX(R4),r33; \
+ add r3=CTX(R5),r33; \
+ ;; \
+ ld8.fill r4=[r2],16; \
+ ld8.fill r5=[r3],16; \
+ ;; \
+ ld8.fill r6=[r2],48; \
+ ld8.fill r7=[r3],48; \
+ ;; \
+ ld8.fill r12=[r2]; \
+ ld8.fill r13 =[r3]; \
+ ;;
+
+
+
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_KERNEL_REGS \
+ add r2 = CTX(KR0),r32; \
+ add r3 = CTX(KR1),r32; \
+ mov r16 = ar.k0; \
+ mov r17 = ar.k1; \
+ ;; \
+ st8 [r2] = r16,16; \
+ st8 [r3] = r17,16; \
+ ;; \
+ mov r16 = ar.k2; \
+ mov r17 = ar.k3; \
+ ;; \
+ st8 [r2] = r16,16; \
+ st8 [r3] = r17,16; \
+ ;; \
+ mov r16 = ar.k4; \
+ mov r17 = ar.k5; \
+ ;; \
+ st8 [r2] = r16,16; \
+ st8 [r3] = r17,16; \
+ ;; \
+ mov r16 = ar.k6; \
+ mov r17 = ar.k7; \
+ ;; \
+ st8 [r2] = r16; \
+ st8 [r3] = r17; \
+ ;;
+
+
+
+ /*
+ * r33: context_t base address
+ */
+#define RESTORE_KERNEL_REGS \
+ add r2 = CTX(KR0),r33; \
+ add r3 = CTX(KR1),r33; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov ar.k0=r16; \
+ mov ar.k1=r17; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov ar.k2=r16; \
+ mov ar.k3=r17; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov ar.k4=r16; \
+ mov ar.k5=r17; \
+ ;; \
+ ld8 r16=[r2],16; \
+ ld8 r17=[r3],16; \
+ ;; \
+ mov ar.k6=r16; \
+ mov ar.k7=r17; \
+ ;;
+
+
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_APP_REGS \
+ add r2 = CTX(BSPSTORE),r32; \
+ mov r16 = ar.bspstore; \
+ ;; \
+ st8 [r2] = r16,CTX(RNAT)-CTX(BSPSTORE);\
+ mov r16 = ar.rnat; \
+ ;; \
+ st8 [r2] = r16,CTX(FCR)-CTX(RNAT); \
+ mov r16 = ar.fcr; \
+ ;; \
+ st8 [r2] = r16,CTX(EFLAG)-CTX(FCR); \
+ mov r16 = ar.eflag; \
+ ;; \
+ st8 [r2] = r16,CTX(CFLG)-CTX(EFLAG); \
+ mov r16 = ar.cflg; \
+ ;; \
+ st8 [r2] = r16,CTX(FSR)-CTX(CFLG); \
+ mov r16 = ar.fsr; \
+ ;; \
+ st8 [r2] = r16,CTX(FIR)-CTX(FSR); \
+ mov r16 = ar.fir; \
+ ;; \
+ st8 [r2] = r16,CTX(FDR)-CTX(FIR); \
+ mov r16 = ar.fdr; \
+ ;; \
+ st8 [r2] = r16,CTX(UNAT)-CTX(FDR); \
+ mov r16 = ar.unat; \
+ ;; \
+ st8 [r2] = r16,CTX(FPSR)-CTX(UNAT); \
+ mov r16 = ar.fpsr; \
+ ;; \
+ st8 [r2] = r16,CTX(PFS)-CTX(FPSR); \
+ mov r16 = ar.pfs; \
+ ;; \
+ st8 [r2] = r16,CTX(LC)-CTX(PFS); \
+ mov r16 = ar.lc; \
+ ;; \
+ st8 [r2] = r16; \
+ ;;
+
+ /*
+ * r33: context_t base address
+ */
+#define RESTORE_APP_REGS \
+ add r2=CTX(BSPSTORE),r33; \
+ ;; \
+ ld8 r16=[r2],CTX(RNAT)-CTX(BSPSTORE); \
+ ;; \
+ mov ar.bspstore=r16; \
+ ld8 r16=[r2],CTX(FCR)-CTX(RNAT); \
+ ;; \
+ mov ar.rnat=r16; \
+ ld8 r16=[r2],CTX(EFLAG)-CTX(FCR); \
+ ;; \
+ mov ar.fcr=r16; \
+ ld8 r16=[r2],CTX(CFLG)-CTX(EFLAG); \
+ ;; \
+ mov ar.eflag=r16; \
+ ld8 r16=[r2],CTX(FSR)-CTX(CFLG); \
+ ;; \
+ mov ar.cflg=r16; \
+ ld8 r16=[r2],CTX(FIR)-CTX(FSR); \
+ ;; \
+ mov ar.fsr=r16; \
+ ld8 r16=[r2],CTX(FDR)-CTX(FIR); \
+ ;; \
+ mov ar.fir=r16; \
+ ld8 r16=[r2],CTX(UNAT)-CTX(FDR); \
+ ;; \
+ mov ar.fdr=r16; \
+ ld8 r16=[r2],CTX(FPSR)-CTX(UNAT); \
+ ;; \
+ mov ar.unat=r16; \
+ ld8 r16=[r2],CTX(PFS)-CTX(FPSR); \
+ ;; \
+ mov ar.fpsr=r16; \
+ ld8 r16=[r2],CTX(LC)-CTX(PFS); \
+ ;; \
+ mov ar.pfs=r16; \
+ ld8 r16=[r2]; \
+ ;; \
+ mov ar.lc=r16; \
+ ;;
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_CTL_REGS \
+ add r2 = CTX(DCR),r32; \
+ mov r16 = cr.dcr; \
+ ;; \
+ st8 [r2] = r16,CTX(IVA)-CTX(DCR); \
+ ;; \
+ mov r16 = cr.iva; \
+ ;; \
+ st8 [r2] = r16,CTX(PTA)-CTX(IVA); \
+ ;; \
+ mov r16 = cr.pta; \
+ ;; \
+ st8 [r2] = r16 ; \
+ ;;
+
+ /*
+ * r33: context_t base address
+ */
+#define RESTORE_CTL_REGS \
+ add r2 = CTX(DCR),r33; \
+ ;; \
+ ld8 r16 = [r2],CTX(IVA)-CTX(DCR); \
+ ;; \
+ mov cr.dcr = r16; \
+ dv_serialize_data; \
+ ;; \
+ ld8 r16 = [r2],CTX(PTA)-CTX(IVA); \
+ ;; \
+ mov cr.iva = r16; \
+ dv_serialize_data; \
+ ;; \
+ ld8 r16 = [r2]; \
+ ;; \
+ mov cr.pta = r16; \
+ dv_serialize_data; \
+ ;;
+
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_REGION_REGS \
+ add r2=CTX(RR0),r32; \
+ mov r16=rr[r0]; \
+ dep.z r18=1,61,3; \
+ ;; \
+ st8 [r2]=r16,8; \
+ mov r17=rr[r18]; \
+ dep.z r18=2,61,3; \
+ ;; \
+ st8 [r2]=r17,8; \
+ mov r16=rr[r18]; \
+ dep.z r18=3,61,3; \
+ ;; \
+ st8 [r2]=r16,8; \
+ mov r17=rr[r18]; \
+ dep.z r18=4,61,3; \
+ ;; \
+ st8 [r2]=r17,8; \
+ mov r16=rr[r18]; \
+ dep.z r18=5,61,3; \
+ ;; \
+ st8 [r2]=r16,8; \
+ mov r17=rr[r18]; \
+ dep.z r18=7,61,3; \
+ ;; \
+ st8 [r2]=r17,16; \
+ mov r16=rr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ ;;
+
+ /*
+ * r33:context_t base address
+ */
+#define RESTORE_REGION_REGS \
+ add r2=CTX(RR0),r33;\
+ mov r18=r0; \
+ ;; \
+ ld8 r20=[r2],8; \
+ ;; /* rr0 */ \
+ ld8 r21=[r2],8; \
+ ;; /* rr1 */ \
+ ld8 r22=[r2],8; \
+ ;; /* rr2 */ \
+ ld8 r23=[r2],8; \
+ ;; /* rr3 */ \
+ ld8 r24=[r2],8; \
+ ;; /* rr4 */ \
+ ld8 r25=[r2],16; \
+ ;; /* rr5 */ \
+ ld8 r27=[r2]; \
+ ;; /* rr7 */ \
+ mov rr[r18]=r20; \
+ dep.z r18=1,61,3; \
+ ;; /* rr1 */ \
+ mov rr[r18]=r21; \
+ dep.z r18=2,61,3; \
+ ;; /* rr2 */ \
+ mov rr[r18]=r22; \
+ dep.z r18=3,61,3; \
+ ;; /* rr3 */ \
+ mov rr[r18]=r23; \
+ dep.z r18=4,61,3; \
+ ;; /* rr4 */ \
+ mov rr[r18]=r24; \
+ dep.z r18=5,61,3; \
+ ;; /* rr5 */ \
+ mov rr[r18]=r25; \
+ dep.z r18=7,61,3; \
+ ;; /* rr7 */ \
+ mov rr[r18]=r27; \
+ ;; \
+ srlz.i; \
+ ;;
+
+
+
+ /*
+ * r32: context_t base address
+ * r36~r39:scratch registers
+ */
+#define SAVE_DEBUG_REGS \
+ add r2=CTX(IBR0),r32; \
+ add r3=CTX(DBR0),r32; \
+ mov r16=ibr[r0]; \
+ mov r17=dbr[r0]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=1,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=2,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=2,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=3,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=4,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=5,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=6,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ add r18=7,r0; \
+ ;; \
+ mov r16=ibr[r18]; \
+ mov r17=dbr[r18]; \
+ ;; \
+ st8 [r2]=r16,8; \
+ st8 [r3]=r17,8; \
+ ;;
+
+
+/*
+ * r33: point to context_t structure
+ * ar.lc are corrupted.
+ */
+#define RESTORE_DEBUG_REGS \
+ add r2=CTX(IBR0),r33; \
+ add r3=CTX(DBR0),r33; \
+ mov r16=7; \
+ mov r17=r0; \
+ ;; \
+ mov ar.lc = r16; \
+ ;; \
+1: \
+ ld8 r18=[r2],8; \
+ ld8 r19=[r3],8; \
+ ;; \
+ mov ibr[r17]=r18; \
+ mov dbr[r17]=r19; \
+ ;; \
+ srlz.i; \
+ ;; \
+ add r17=1,r17; \
+ br.cloop.sptk 1b; \
+ ;;
+
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_FPU_LOW \
+ add r2=CTX(F2),r32; \
+ add r3=CTX(F3),r32; \
+ ;; \
+ stf.spill.nta [r2]=f2,32; \
+ stf.spill.nta [r3]=f3,32; \
+ ;; \
+ stf.spill.nta [r2]=f4,32; \
+ stf.spill.nta [r3]=f5,32; \
+ ;; \
+ stf.spill.nta [r2]=f6,32; \
+ stf.spill.nta [r3]=f7,32; \
+ ;; \
+ stf.spill.nta [r2]=f8,32; \
+ stf.spill.nta [r3]=f9,32; \
+ ;; \
+ stf.spill.nta [r2]=f10,32; \
+ stf.spill.nta [r3]=f11,32; \
+ ;; \
+ stf.spill.nta [r2]=f12,32; \
+ stf.spill.nta [r3]=f13,32; \
+ ;; \
+ stf.spill.nta [r2]=f14,32; \
+ stf.spill.nta [r3]=f15,32; \
+ ;; \
+ stf.spill.nta [r2]=f16,32; \
+ stf.spill.nta [r3]=f17,32; \
+ ;; \
+ stf.spill.nta [r2]=f18,32; \
+ stf.spill.nta [r3]=f19,32; \
+ ;; \
+ stf.spill.nta [r2]=f20,32; \
+ stf.spill.nta [r3]=f21,32; \
+ ;; \
+ stf.spill.nta [r2]=f22,32; \
+ stf.spill.nta [r3]=f23,32; \
+ ;; \
+ stf.spill.nta [r2]=f24,32; \
+ stf.spill.nta [r3]=f25,32; \
+ ;; \
+ stf.spill.nta [r2]=f26,32; \
+ stf.spill.nta [r3]=f27,32; \
+ ;; \
+ stf.spill.nta [r2]=f28,32; \
+ stf.spill.nta [r3]=f29,32; \
+ ;; \
+ stf.spill.nta [r2]=f30; \
+ stf.spill.nta [r3]=f31; \
+ ;;
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_FPU_HIGH \
+ add r2=CTX(F32),r32; \
+ add r3=CTX(F33),r32; \
+ ;; \
+ stf.spill.nta [r2]=f32,32; \
+ stf.spill.nta [r3]=f33,32; \
+ ;; \
+ stf.spill.nta [r2]=f34,32; \
+ stf.spill.nta [r3]=f35,32; \
+ ;; \
+ stf.spill.nta [r2]=f36,32; \
+ stf.spill.nta [r3]=f37,32; \
+ ;; \
+ stf.spill.nta [r2]=f38,32; \
+ stf.spill.nta [r3]=f39,32; \
+ ;; \
+ stf.spill.nta [r2]=f40,32; \
+ stf.spill.nta [r3]=f41,32; \
+ ;; \
+ stf.spill.nta [r2]=f42,32; \
+ stf.spill.nta [r3]=f43,32; \
+ ;; \
+ stf.spill.nta [r2]=f44,32; \
+ stf.spill.nta [r3]=f45,32; \
+ ;; \
+ stf.spill.nta [r2]=f46,32; \
+ stf.spill.nta [r3]=f47,32; \
+ ;; \
+ stf.spill.nta [r2]=f48,32; \
+ stf.spill.nta [r3]=f49,32; \
+ ;; \
+ stf.spill.nta [r2]=f50,32; \
+ stf.spill.nta [r3]=f51,32; \
+ ;; \
+ stf.spill.nta [r2]=f52,32; \
+ stf.spill.nta [r3]=f53,32; \
+ ;; \
+ stf.spill.nta [r2]=f54,32; \
+ stf.spill.nta [r3]=f55,32; \
+ ;; \
+ stf.spill.nta [r2]=f56,32; \
+ stf.spill.nta [r3]=f57,32; \
+ ;; \
+ stf.spill.nta [r2]=f58,32; \
+ stf.spill.nta [r3]=f59,32; \
+ ;; \
+ stf.spill.nta [r2]=f60,32; \
+ stf.spill.nta [r3]=f61,32; \
+ ;; \
+ stf.spill.nta [r2]=f62,32; \
+ stf.spill.nta [r3]=f63,32; \
+ ;; \
+ stf.spill.nta [r2]=f64,32; \
+ stf.spill.nta [r3]=f65,32; \
+ ;; \
+ stf.spill.nta [r2]=f66,32; \
+ stf.spill.nta [r3]=f67,32; \
+ ;; \
+ stf.spill.nta [r2]=f68,32; \
+ stf.spill.nta [r3]=f69,32; \
+ ;; \
+ stf.spill.nta [r2]=f70,32; \
+ stf.spill.nta [r3]=f71,32; \
+ ;; \
+ stf.spill.nta [r2]=f72,32; \
+ stf.spill.nta [r3]=f73,32; \
+ ;; \
+ stf.spill.nta [r2]=f74,32; \
+ stf.spill.nta [r3]=f75,32; \
+ ;; \
+ stf.spill.nta [r2]=f76,32; \
+ stf.spill.nta [r3]=f77,32; \
+ ;; \
+ stf.spill.nta [r2]=f78,32; \
+ stf.spill.nta [r3]=f79,32; \
+ ;; \
+ stf.spill.nta [r2]=f80,32; \
+ stf.spill.nta [r3]=f81,32; \
+ ;; \
+ stf.spill.nta [r2]=f82,32; \
+ stf.spill.nta [r3]=f83,32; \
+ ;; \
+ stf.spill.nta [r2]=f84,32; \
+ stf.spill.nta [r3]=f85,32; \
+ ;; \
+ stf.spill.nta [r2]=f86,32; \
+ stf.spill.nta [r3]=f87,32; \
+ ;; \
+ stf.spill.nta [r2]=f88,32; \
+ stf.spill.nta [r3]=f89,32; \
+ ;; \
+ stf.spill.nta [r2]=f90,32; \
+ stf.spill.nta [r3]=f91,32; \
+ ;; \
+ stf.spill.nta [r2]=f92,32; \
+ stf.spill.nta [r3]=f93,32; \
+ ;; \
+ stf.spill.nta [r2]=f94,32; \
+ stf.spill.nta [r3]=f95,32; \
+ ;; \
+ stf.spill.nta [r2]=f96,32; \
+ stf.spill.nta [r3]=f97,32; \
+ ;; \
+ stf.spill.nta [r2]=f98,32; \
+ stf.spill.nta [r3]=f99,32; \
+ ;; \
+ stf.spill.nta [r2]=f100,32; \
+ stf.spill.nta [r3]=f101,32; \
+ ;; \
+ stf.spill.nta [r2]=f102,32; \
+ stf.spill.nta [r3]=f103,32; \
+ ;; \
+ stf.spill.nta [r2]=f104,32; \
+ stf.spill.nta [r3]=f105,32; \
+ ;; \
+ stf.spill.nta [r2]=f106,32; \
+ stf.spill.nta [r3]=f107,32; \
+ ;; \
+ stf.spill.nta [r2]=f108,32; \
+ stf.spill.nta [r3]=f109,32; \
+ ;; \
+ stf.spill.nta [r2]=f110,32; \
+ stf.spill.nta [r3]=f111,32; \
+ ;; \
+ stf.spill.nta [r2]=f112,32; \
+ stf.spill.nta [r3]=f113,32; \
+ ;; \
+ stf.spill.nta [r2]=f114,32; \
+ stf.spill.nta [r3]=f115,32; \
+ ;; \
+ stf.spill.nta [r2]=f116,32; \
+ stf.spill.nta [r3]=f117,32; \
+ ;; \
+ stf.spill.nta [r2]=f118,32; \
+ stf.spill.nta [r3]=f119,32; \
+ ;; \
+ stf.spill.nta [r2]=f120,32; \
+ stf.spill.nta [r3]=f121,32; \
+ ;; \
+ stf.spill.nta [r2]=f122,32; \
+ stf.spill.nta [r3]=f123,32; \
+ ;; \
+ stf.spill.nta [r2]=f124,32; \
+ stf.spill.nta [r3]=f125,32; \
+ ;; \
+ stf.spill.nta [r2]=f126; \
+ stf.spill.nta [r3]=f127; \
+ ;;
+
+ /*
+ * r33: point to context_t structure
+ */
+#define RESTORE_FPU_LOW \
+ add r2 = CTX(F2), r33; \
+ add r3 = CTX(F3), r33; \
+ ;; \
+ ldf.fill.nta f2 = [r2], 32; \
+ ldf.fill.nta f3 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f4 = [r2], 32; \
+ ldf.fill.nta f5 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f6 = [r2], 32; \
+ ldf.fill.nta f7 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f8 = [r2], 32; \
+ ldf.fill.nta f9 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f10 = [r2], 32; \
+ ldf.fill.nta f11 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f12 = [r2], 32; \
+ ldf.fill.nta f13 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f14 = [r2], 32; \
+ ldf.fill.nta f15 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f16 = [r2], 32; \
+ ldf.fill.nta f17 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f18 = [r2], 32; \
+ ldf.fill.nta f19 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f20 = [r2], 32; \
+ ldf.fill.nta f21 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f22 = [r2], 32; \
+ ldf.fill.nta f23 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f24 = [r2], 32; \
+ ldf.fill.nta f25 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f26 = [r2], 32; \
+ ldf.fill.nta f27 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f28 = [r2], 32; \
+ ldf.fill.nta f29 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f30 = [r2], 32; \
+ ldf.fill.nta f31 = [r3], 32; \
+ ;;
+
+
+
+ /*
+ * r33: point to context_t structure
+ */
+#define RESTORE_FPU_HIGH \
+ add r2 = CTX(F32), r33; \
+ add r3 = CTX(F33), r33; \
+ ;; \
+ ldf.fill.nta f32 = [r2], 32; \
+ ldf.fill.nta f33 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f34 = [r2], 32; \
+ ldf.fill.nta f35 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f36 = [r2], 32; \
+ ldf.fill.nta f37 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f38 = [r2], 32; \
+ ldf.fill.nta f39 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f40 = [r2], 32; \
+ ldf.fill.nta f41 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f42 = [r2], 32; \
+ ldf.fill.nta f43 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f44 = [r2], 32; \
+ ldf.fill.nta f45 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f46 = [r2], 32; \
+ ldf.fill.nta f47 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f48 = [r2], 32; \
+ ldf.fill.nta f49 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f50 = [r2], 32; \
+ ldf.fill.nta f51 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f52 = [r2], 32; \
+ ldf.fill.nta f53 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f54 = [r2], 32; \
+ ldf.fill.nta f55 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f56 = [r2], 32; \
+ ldf.fill.nta f57 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f58 = [r2], 32; \
+ ldf.fill.nta f59 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f60 = [r2], 32; \
+ ldf.fill.nta f61 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f62 = [r2], 32; \
+ ldf.fill.nta f63 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f64 = [r2], 32; \
+ ldf.fill.nta f65 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f66 = [r2], 32; \
+ ldf.fill.nta f67 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f68 = [r2], 32; \
+ ldf.fill.nta f69 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f70 = [r2], 32; \
+ ldf.fill.nta f71 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f72 = [r2], 32; \
+ ldf.fill.nta f73 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f74 = [r2], 32; \
+ ldf.fill.nta f75 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f76 = [r2], 32; \
+ ldf.fill.nta f77 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f78 = [r2], 32; \
+ ldf.fill.nta f79 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f80 = [r2], 32; \
+ ldf.fill.nta f81 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f82 = [r2], 32; \
+ ldf.fill.nta f83 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f84 = [r2], 32; \
+ ldf.fill.nta f85 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f86 = [r2], 32; \
+ ldf.fill.nta f87 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f88 = [r2], 32; \
+ ldf.fill.nta f89 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f90 = [r2], 32; \
+ ldf.fill.nta f91 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f92 = [r2], 32; \
+ ldf.fill.nta f93 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f94 = [r2], 32; \
+ ldf.fill.nta f95 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f96 = [r2], 32; \
+ ldf.fill.nta f97 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f98 = [r2], 32; \
+ ldf.fill.nta f99 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f100 = [r2], 32; \
+ ldf.fill.nta f101 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f102 = [r2], 32; \
+ ldf.fill.nta f103 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f104 = [r2], 32; \
+ ldf.fill.nta f105 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f106 = [r2], 32; \
+ ldf.fill.nta f107 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f108 = [r2], 32; \
+ ldf.fill.nta f109 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f110 = [r2], 32; \
+ ldf.fill.nta f111 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f112 = [r2], 32; \
+ ldf.fill.nta f113 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f114 = [r2], 32; \
+ ldf.fill.nta f115 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f116 = [r2], 32; \
+ ldf.fill.nta f117 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f118 = [r2], 32; \
+ ldf.fill.nta f119 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f120 = [r2], 32; \
+ ldf.fill.nta f121 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f122 = [r2], 32; \
+ ldf.fill.nta f123 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f124 = [r2], 32; \
+ ldf.fill.nta f125 = [r3], 32; \
+ ;; \
+ ldf.fill.nta f126 = [r2], 32; \
+ ldf.fill.nta f127 = [r3], 32; \
+ ;;
+
+ /*
+ * r32: context_t base address
+ */
+#define SAVE_PTK_REGS \
+ add r2=CTX(PKR0), r32; \
+ mov r16=7; \
+ ;; \
+ mov ar.lc=r16; \
+ mov r17=r0; \
+ ;; \
+1: \
+ mov r18=pkr[r17]; \
+ ;; \
+ srlz.i; \
+ ;; \
+ st8 [r2]=r18, 8; \
+ ;; \
+ add r17 =1,r17; \
+ ;; \
+ br.cloop.sptk 1b; \
+ ;;
+
+/*
+ * r33: point to context_t structure
+ * ar.lc are corrupted.
+ */
+#define RESTORE_PTK_REGS \
+ add r2=CTX(PKR0), r33; \
+ mov r16=7; \
+ ;; \
+ mov ar.lc=r16; \
+ mov r17=r0; \
+ ;; \
+1: \
+ ld8 r18=[r2], 8; \
+ ;; \
+ mov pkr[r17]=r18; \
+ ;; \
+ srlz.i; \
+ ;; \
+ add r17 =1,r17; \
+ ;; \
+ br.cloop.sptk 1b; \
+ ;;
+
+
+/*
+ * void vmm_trampoline( context_t * from,
+ * context_t * to)
+ *
+ * from: r32
+ * to: r33
+ * note: interrupt disabled before call this function.
+ */
+GLOBAL_ENTRY(vmm_trampoline)
+ mov r16 = psr
+ adds r2 = CTX(PSR), r32
+ ;;
+ st8 [r2] = r16, 8 // psr
+ mov r17 = pr
+ ;;
+ st8 [r2] = r17, 8 // pr
+ mov r18 = ar.unat
+ ;;
+ st8 [r2] = r18
+ mov r17 = ar.rsc
+ ;;
+ adds r2 = CTX(RSC),r32
+ ;;
+ st8 [r2]= r17
+ mov ar.rsc =0
+ flushrs
+ ;;
+ SAVE_GENERAL_REGS
+ ;;
+ SAVE_KERNEL_REGS
+ ;;
+ SAVE_APP_REGS
+ ;;
+ SAVE_BRANCH_REGS
+ ;;
+ SAVE_CTL_REGS
+ ;;
+ SAVE_REGION_REGS
+ ;;
+ //SAVE_DEBUG_REGS
+ ;;
+ rsm psr.dfl
+ ;;
+ srlz.d
+ ;;
+ SAVE_FPU_LOW
+ ;;
+ rsm psr.dfh
+ ;;
+ srlz.d
+ ;;
+ SAVE_FPU_HIGH
+ ;;
+ SAVE_PTK_REGS
+ ;;
+ RESTORE_PTK_REGS
+ ;;
+ RESTORE_FPU_HIGH
+ ;;
+ RESTORE_FPU_LOW
+ ;;
+ //RESTORE_DEBUG_REGS
+ ;;
+ RESTORE_REGION_REGS
+ ;;
+ RESTORE_CTL_REGS
+ ;;
+ RESTORE_BRANCH_REGS
+ ;;
+ RESTORE_APP_REGS
+ ;;
+ RESTORE_KERNEL_REGS
+ ;;
+ RESTORE_GENERAL_REGS
+ ;;
+ adds r2=CTX(PSR), r33
+ ;;
+ ld8 r16=[r2], 8 // psr
+ ;;
+ mov psr.l=r16
+ ;;
+ srlz.d
+ ;;
+ ld8 r16=[r2], 8 // pr
+ ;;
+ mov pr =r16,-1
+ ld8 r16=[r2] // unat
+ ;;
+ mov ar.unat=r16
+ ;;
+ adds r2=CTX(RSC),r33
+ ;;
+ ld8 r16 =[r2]
+ ;;
+ mov ar.rsc = r16
+ ;;
+ br.ret.sptk.few b0
+END(vmm_trampoline)
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
new file mode 100644
index 00000000000..e44027ce566
--- /dev/null
+++ b/arch/ia64/kvm/vcpu.c
@@ -0,0 +1,2163 @@
+/*
+ * kvm_vcpu.c: handling all virtual cpu related thing.
+ * Copyright (c) 2005, 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.
+ *
+ * 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.
+ *
+ * Shaofan Li (Susue Li) <susie.li@intel.com>
+ * Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ * Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ * Xiantao Zhang <xiantao.zhang@intel.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+
+#include <asm/processor.h>
+#include <asm/ia64regs.h>
+#include <asm/gcc_intrin.h>
+#include <asm/kregs.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+#include "asm-offsets.h"
+#include "vcpu.h"
+
+/*
+ * Special notes:
+ * - Index by it/dt/rt sequence
+ * - Only existing mode transitions are allowed in this table
+ * - RSE is placed at lazy mode when emulating guest partial mode
+ * - If gva happens to be rr0 and rr4, only allowed case is identity
+ * mapping (gva=gpa), or panic! (How?)
+ */
+int mm_switch_table[8][8] = {
+ /* 2004/09/12(Kevin): Allow switch to self */
+ /*
+ * (it,dt,rt): (0,0,0) -> (1,1,1)
+ * This kind of transition usually occurs in the very early
+ * stage of Linux boot up procedure. Another case is in efi
+ * and pal calls. (see "arch/ia64/kernel/head.S")
+ *
+ * (it,dt,rt): (0,0,0) -> (0,1,1)
+ * This kind of transition is found when OSYa exits efi boot
+ * service. Due to gva = gpa in this case (Same region),
+ * data access can be satisfied though itlb entry for physical
+ * emulation is hit.
+ */
+ {SW_SELF, 0, 0, SW_NOP, 0, 0, 0, SW_P2V},
+ {0, 0, 0, 0, 0, 0, 0, 0},
+ {0, 0, 0, 0, 0, 0, 0, 0},
+ /*
+ * (it,dt,rt): (0,1,1) -> (1,1,1)
+ * This kind of transition is found in OSYa.
+ *
+ * (it,dt,rt): (0,1,1) -> (0,0,0)
+ * This kind of transition is found in OSYa
+ */
+ {SW_NOP, 0, 0, SW_SELF, 0, 0, 0, SW_P2V},
+ /* (1,0,0)->(1,1,1) */
+ {0, 0, 0, 0, 0, 0, 0, SW_P2V},
+ /*
+ * (it,dt,rt): (1,0,1) -> (1,1,1)
+ * This kind of transition usually occurs when Linux returns
+ * from the low level TLB miss handlers.
+ * (see "arch/ia64/kernel/ivt.S")
+ */
+ {0, 0, 0, 0, 0, SW_SELF, 0, SW_P2V},
+ {0, 0, 0, 0, 0, 0, 0, 0},
+ /*
+ * (it,dt,rt): (1,1,1) -> (1,0,1)
+ * This kind of transition usually occurs in Linux low level
+ * TLB miss handler. (see "arch/ia64/kernel/ivt.S")
+ *
+ * (it,dt,rt): (1,1,1) -> (0,0,0)
+ * This kind of transition usually occurs in pal and efi calls,
+ * which requires running in physical mode.
+ * (see "arch/ia64/kernel/head.S")
+ * (1,1,1)->(1,0,0)
+ */
+
+ {SW_V2P, 0, 0, 0, SW_V2P, SW_V2P, 0, SW_SELF},
+};
+
+void physical_mode_init(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.mode_flags = GUEST_IN_PHY;
+}
+
+void switch_to_physical_rid(struct kvm_vcpu *vcpu)
+{
+ unsigned long psr;
+
+ /* Save original virtual mode rr[0] and rr[4] */
+ psr = ia64_clear_ic();
+ ia64_set_rr(VRN0<<VRN_SHIFT, vcpu->arch.metaphysical_rr0);
+ ia64_srlz_d();
+ ia64_set_rr(VRN4<<VRN_SHIFT, vcpu->arch.metaphysical_rr4);
+ ia64_srlz_d();
+
+ ia64_set_psr(psr);
+ return;
+}
+
+
+void switch_to_virtual_rid(struct kvm_vcpu *vcpu)
+{
+ unsigned long psr;
+
+ psr = ia64_clear_ic();
+ ia64_set_rr(VRN0 << VRN_SHIFT, vcpu->arch.metaphysical_saved_rr0);
+ ia64_srlz_d();
+ ia64_set_rr(VRN4 << VRN_SHIFT, vcpu->arch.metaphysical_saved_rr4);
+ ia64_srlz_d();
+ ia64_set_psr(psr);
+ return;
+}
+
+static int mm_switch_action(struct ia64_psr opsr, struct ia64_psr npsr)
+{
+ return mm_switch_table[MODE_IND(opsr)][MODE_IND(npsr)];
+}
+
+void switch_mm_mode(struct kvm_vcpu *vcpu, struct ia64_psr old_psr,
+ struct ia64_psr new_psr)
+{
+ int act;
+ act = mm_switch_action(old_psr, new_psr);
+ switch (act) {
+ case SW_V2P:
+ /*printk("V -> P mode transition: (0x%lx -> 0x%lx)\n",
+ old_psr.val, new_psr.val);*/
+ switch_to_physical_rid(vcpu);
+ /*
+ * Set rse to enforced lazy, to prevent active rse
+ *save/restor when guest physical mode.
+ */
+ vcpu->arch.mode_flags |= GUEST_IN_PHY;
+ break;
+ case SW_P2V:
+ switch_to_virtual_rid(vcpu);
+ /*
+ * recover old mode which is saved when entering
+ * guest physical mode
+ */
+ vcpu->arch.mode_flags &= ~GUEST_IN_PHY;
+ break;
+ case SW_SELF:
+ break;
+ case SW_NOP:
+ break;
+ default:
+ /* Sanity check */
+ break;
+ }
+ return;
+}
+
+
+
+/*
+ * In physical mode, insert tc/tr for region 0 and 4 uses
+ * RID[0] and RID[4] which is for physical mode emulation.
+ * However what those inserted tc/tr wants is rid for
+ * virtual mode. So original virtual rid needs to be restored
+ * before insert.
+ *
+ * Operations which required such switch include:
+ * - insertions (itc.*, itr.*)
+ * - purges (ptc.* and ptr.*)
+ * - tpa
+ * - tak
+ * - thash?, ttag?
+ * All above needs actual virtual rid for destination entry.
+ */
+
+void check_mm_mode_switch(struct kvm_vcpu *vcpu, struct ia64_psr old_psr,
+ struct ia64_psr new_psr)
+{
+
+ if ((old_psr.dt != new_psr.dt)
+ || (old_psr.it != new_psr.it)
+ || (old_psr.rt != new_psr.rt))
+ switch_mm_mode(vcpu, old_psr, new_psr);
+
+ return;
+}
+
+
+/*
+ * In physical mode, insert tc/tr for region 0 and 4 uses
+ * RID[0] and RID[4] which is for physical mode emulation.
+ * However what those inserted tc/tr wants is rid for
+ * virtual mode. So original virtual rid needs to be restored
+ * before insert.
+ *
+ * Operations which required such switch include:
+ * - insertions (itc.*, itr.*)
+ * - purges (ptc.* and ptr.*)
+ * - tpa
+ * - tak
+ * - thash?, ttag?
+ * All above needs actual virtual rid for destination entry.
+ */
+
+void prepare_if_physical_mode(struct kvm_vcpu *vcpu)
+{
+ if (is_physical_mode(vcpu)) {
+ vcpu->arch.mode_flags |= GUEST_PHY_EMUL;
+ switch_to_virtual_rid(vcpu);
+ }
+ return;
+}
+
+/* Recover always follows prepare */
+void recover_if_physical_mode(struct kvm_vcpu *vcpu)
+{
+ if (is_physical_mode(vcpu))
+ switch_to_physical_rid(vcpu);
+ vcpu->arch.mode_flags &= ~GUEST_PHY_EMUL;
+ return;
+}
+
+#define RPT(x) ((u16) &((struct kvm_pt_regs *)0)->x)
+
+static u16 gr_info[32] = {
+ 0, /* r0 is read-only : WE SHOULD NEVER GET THIS */
+ RPT(r1), RPT(r2), RPT(r3),
+ RPT(r4), RPT(r5), RPT(r6), RPT(r7),
+ RPT(r8), RPT(r9), RPT(r10), RPT(r11),
+ RPT(r12), RPT(r13), RPT(r14), RPT(r15),
+ RPT(r16), RPT(r17), RPT(r18), RPT(r19),
+ RPT(r20), RPT(r21), RPT(r22), RPT(r23),
+ RPT(r24), RPT(r25), RPT(r26), RPT(r27),
+ RPT(r28), RPT(r29), RPT(r30), RPT(r31)
+};
+
+#define IA64_FIRST_STACKED_GR 32
+#define IA64_FIRST_ROTATING_FR 32
+
+static inline unsigned long
+rotate_reg(unsigned long sor, unsigned long rrb, unsigned long reg)
+{
+ reg += rrb;
+ if (reg >= sor)
+ reg -= sor;
+ return reg;
+}
+
+/*
+ * Return the (rotated) index for floating point register
+ * be in the REGNUM (REGNUM must range from 32-127,
+ * result is in the range from 0-95.
+ */
+static inline unsigned long fph_index(struct kvm_pt_regs *regs,
+ long regnum)
+{
+ unsigned long rrb_fr = (regs->cr_ifs >> 25) & 0x7f;
+ return rotate_reg(96, rrb_fr, (regnum - IA64_FIRST_ROTATING_FR));
+}
+
+
+/*
+ * The inverse of the above: given bspstore and the number of
+ * registers, calculate ar.bsp.
+ */
+static inline unsigned long *kvm_rse_skip_regs(unsigned long *addr,
+ long num_regs)
+{
+ long delta = ia64_rse_slot_num(addr) + num_regs;
+ int i = 0;
+
+ if (num_regs < 0)
+ delta -= 0x3e;
+ if (delta < 0) {
+ while (delta <= -0x3f) {
+ i--;
+ delta += 0x3f;
+ }
+ } else {
+ while (delta >= 0x3f) {
+ i++;
+ delta -= 0x3f;
+ }
+ }
+
+ return addr + num_regs + i;
+}
+
+static void get_rse_reg(struct kvm_pt_regs *regs, unsigned long r1,
+ unsigned long *val, int *nat)
+{
+ unsigned long *bsp, *addr, *rnat_addr, *bspstore;
+ unsigned long *kbs = (void *) current_vcpu + VMM_RBS_OFFSET;
+ unsigned long nat_mask;
+ unsigned long old_rsc, new_rsc;
+ long sof = (regs->cr_ifs) & 0x7f;
+ long sor = (((regs->cr_ifs >> 14) & 0xf) << 3);
+ long rrb_gr = (regs->cr_ifs >> 18) & 0x7f;
+ long ridx = r1 - 32;
+
+ if (ridx < sor)
+ ridx = rotate_reg(sor, rrb_gr, ridx);
+
+ old_rsc = ia64_getreg(_IA64_REG_AR_RSC);
+ new_rsc = old_rsc&(~(0x3));
+ ia64_setreg(_IA64_REG_AR_RSC, new_rsc);
+
+ bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+ bsp = kbs + (regs->loadrs >> 19);
+
+ addr = kvm_rse_skip_regs(bsp, -sof + ridx);
+ nat_mask = 1UL << ia64_rse_slot_num(addr);
+ rnat_addr = ia64_rse_rnat_addr(addr);
+
+ if (addr >= bspstore) {
+ ia64_flushrs();
+ ia64_mf();
+ bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+ }
+ *val = *addr;
+ if (nat) {
+ if (bspstore < rnat_addr)
+ *nat = (int)!!(ia64_getreg(_IA64_REG_AR_RNAT)
+ & nat_mask);
+ else
+ *nat = (int)!!((*rnat_addr) & nat_mask);
+ ia64_setreg(_IA64_REG_AR_RSC, old_rsc);
+ }
+}
+
+void set_rse_reg(struct kvm_pt_regs *regs, unsigned long r1,
+ unsigned long val, unsigned long nat)
+{
+ unsigned long *bsp, *bspstore, *addr, *rnat_addr;
+ unsigned long *kbs = (void *) current_vcpu + VMM_RBS_OFFSET;
+ unsigned long nat_mask;
+ unsigned long old_rsc, new_rsc, psr;
+ unsigned long rnat;
+ long sof = (regs->cr_ifs) & 0x7f;
+ long sor = (((regs->cr_ifs >> 14) & 0xf) << 3);
+ long rrb_gr = (regs->cr_ifs >> 18) & 0x7f;
+ long ridx = r1 - 32;
+
+ if (ridx < sor)
+ ridx = rotate_reg(sor, rrb_gr, ridx);
+
+ old_rsc = ia64_getreg(_IA64_REG_AR_RSC);
+ /* put RSC to lazy mode, and set loadrs 0 */
+ new_rsc = old_rsc & (~0x3fff0003);
+ ia64_setreg(_IA64_REG_AR_RSC, new_rsc);
+ bsp = kbs + (regs->loadrs >> 19); /* 16 + 3 */
+
+ addr = kvm_rse_skip_regs(bsp, -sof + ridx);
+ nat_mask = 1UL << ia64_rse_slot_num(addr);
+ rnat_addr = ia64_rse_rnat_addr(addr);
+
+ local_irq_save(psr);
+ bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+ if (addr >= bspstore) {
+
+ ia64_flushrs();
+ ia64_mf();
+ *addr = val;
+ bspstore = (unsigned long *)ia64_getreg(_IA64_REG_AR_BSPSTORE);
+ rnat = ia64_getreg(_IA64_REG_AR_RNAT);
+ if (bspstore < rnat_addr)
+ rnat = rnat & (~nat_mask);
+ else
+ *rnat_addr = (*rnat_addr)&(~nat_mask);
+
+ ia64_mf();
+ ia64_loadrs();
+ ia64_setreg(_IA64_REG_AR_RNAT, rnat);
+ } else {
+ rnat = ia64_getreg(_IA64_REG_AR_RNAT);
+ *addr = val;
+ if (bspstore < rnat_addr)
+ rnat = rnat&(~nat_mask);
+ else
+ *rnat_addr = (*rnat_addr) & (~nat_mask);
+
+ ia64_setreg(_IA64_REG_AR_BSPSTORE, bspstore);
+ ia64_setreg(_IA64_REG_AR_RNAT, rnat);
+ }
+ local_irq_restore(psr);
+ ia64_setreg(_IA64_REG_AR_RSC, old_rsc);
+}
+
+void getreg(unsigned long regnum, unsigned long *val,
+ int *nat, struct kvm_pt_regs *regs)
+{
+ unsigned long addr, *unat;
+ if (regnum >= IA64_FIRST_STACKED_GR) {
+ get_rse_reg(regs, regnum, val, nat);
+ return;
+ }
+
+ /*
+ * Now look at registers in [0-31] range and init correct UNAT
+ */
+ addr = (unsigned long)regs;
+ unat = &regs->eml_unat;;
+
+ addr += gr_info[regnum];
+
+ *val = *(unsigned long *)addr;
+ /*
+ * do it only when requested
+ */
+ if (nat)
+ *nat = (*unat >> ((addr >> 3) & 0x3f)) & 0x1UL;
+}
+
+void setreg(unsigned long regnum, unsigned long val,
+ int nat, struct kvm_pt_regs *regs)
+{
+ unsigned long addr;
+ unsigned long bitmask;
+ unsigned long *unat;
+
+ /*
+ * First takes care of stacked registers
+ */
+ if (regnum >= IA64_FIRST_STACKED_GR) {
+ set_rse_reg(regs, regnum, val, nat);
+ return;
+ }
+
+ /*
+ * Now look at registers in [0-31] range and init correct UNAT
+ */
+ addr = (unsigned long)regs;
+ unat = &regs->eml_unat;
+ /*
+ * add offset from base of struct
+ * and do it !
+ */
+ addr += gr_info[regnum];
+
+ *(unsigned long *)addr = val;
+
+ /*
+ * We need to clear the corresponding UNAT bit to fully emulate the load
+ * UNAT bit_pos = GR[r3]{8:3} form EAS-2.4
+ */
+ bitmask = 1UL << ((addr >> 3) & 0x3f);
+ if (nat)
+ *unat |= bitmask;
+ else
+ *unat &= ~bitmask;
+
+}
+
+u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ u64 val;
+
+ if (!reg)
+ return 0;
+ getreg(reg, &val, 0, regs);
+ return val;
+}
+
+void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 value, int nat)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ long sof = (regs->cr_ifs) & 0x7f;
+
+ if (!reg)
+ return;
+ if (reg >= sof + 32)
+ return;
+ setreg(reg, value, nat, regs); /* FIXME: handle NATs later*/
+}
+
+void getfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
+ struct kvm_pt_regs *regs)
+{
+ /* Take floating register rotation into consideration*/
+ if (regnum >= IA64_FIRST_ROTATING_FR)
+ regnum = IA64_FIRST_ROTATING_FR + fph_index(regs, regnum);
+#define CASE_FIXED_FP(reg) \
+ case (reg) : \
+ ia64_stf_spill(fpval, reg); \
+ break
+
+ switch (regnum) {
+ CASE_FIXED_FP(0);
+ CASE_FIXED_FP(1);
+ CASE_FIXED_FP(2);
+ CASE_FIXED_FP(3);
+ CASE_FIXED_FP(4);
+ CASE_FIXED_FP(5);
+
+ CASE_FIXED_FP(6);
+ CASE_FIXED_FP(7);
+ CASE_FIXED_FP(8);
+ CASE_FIXED_FP(9);
+ CASE_FIXED_FP(10);
+ CASE_FIXED_FP(11);
+
+ CASE_FIXED_FP(12);
+ CASE_FIXED_FP(13);
+ CASE_FIXED_FP(14);
+ CASE_FIXED_FP(15);
+ CASE_FIXED_FP(16);
+ CASE_FIXED_FP(17);
+ CASE_FIXED_FP(18);
+ CASE_FIXED_FP(19);
+ CASE_FIXED_FP(20);
+ CASE_FIXED_FP(21);
+ CASE_FIXED_FP(22);
+ CASE_FIXED_FP(23);
+ CASE_FIXED_FP(24);
+ CASE_FIXED_FP(25);
+ CASE_FIXED_FP(26);
+ CASE_FIXED_FP(27);
+ CASE_FIXED_FP(28);
+ CASE_FIXED_FP(29);
+ CASE_FIXED_FP(30);
+ CASE_FIXED_FP(31);
+ CASE_FIXED_FP(32);
+ CASE_FIXED_FP(33);
+ CASE_FIXED_FP(34);
+ CASE_FIXED_FP(35);
+ CASE_FIXED_FP(36);
+ CASE_FIXED_FP(37);
+ CASE_FIXED_FP(38);
+ CASE_FIXED_FP(39);
+ CASE_FIXED_FP(40);
+ CASE_FIXED_FP(41);
+ CASE_FIXED_FP(42);
+ CASE_FIXED_FP(43);
+ CASE_FIXED_FP(44);
+ CASE_FIXED_FP(45);
+ CASE_FIXED_FP(46);
+ CASE_FIXED_FP(47);
+ CASE_FIXED_FP(48);
+ CASE_FIXED_FP(49);
+ CASE_FIXED_FP(50);
+ CASE_FIXED_FP(51);
+ CASE_FIXED_FP(52);
+ CASE_FIXED_FP(53);
+ CASE_FIXED_FP(54);
+ CASE_FIXED_FP(55);
+ CASE_FIXED_FP(56);
+ CASE_FIXED_FP(57);
+ CASE_FIXED_FP(58);
+ CASE_FIXED_FP(59);
+ CASE_FIXED_FP(60);
+ CASE_FIXED_FP(61);
+ CASE_FIXED_FP(62);
+ CASE_FIXED_FP(63);
+ CASE_FIXED_FP(64);
+ CASE_FIXED_FP(65);
+ CASE_FIXED_FP(66);
+ CASE_FIXED_FP(67);
+ CASE_FIXED_FP(68);
+ CASE_FIXED_FP(69);
+ CASE_FIXED_FP(70);
+ CASE_FIXED_FP(71);
+ CASE_FIXED_FP(72);
+ CASE_FIXED_FP(73);
+ CASE_FIXED_FP(74);
+ CASE_FIXED_FP(75);
+ CASE_FIXED_FP(76);
+ CASE_FIXED_FP(77);
+ CASE_FIXED_FP(78);
+ CASE_FIXED_FP(79);
+ CASE_FIXED_FP(80);
+ CASE_FIXED_FP(81);
+ CASE_FIXED_FP(82);
+ CASE_FIXED_FP(83);
+ CASE_FIXED_FP(84);
+ CASE_FIXED_FP(85);
+ CASE_FIXED_FP(86);
+ CASE_FIXED_FP(87);
+ CASE_FIXED_FP(88);
+ CASE_FIXED_FP(89);
+ CASE_FIXED_FP(90);
+ CASE_FIXED_FP(91);
+ CASE_FIXED_FP(92);
+ CASE_FIXED_FP(93);
+ CASE_FIXED_FP(94);
+ CASE_FIXED_FP(95);
+ CASE_FIXED_FP(96);
+ CASE_FIXED_FP(97);
+ CASE_FIXED_FP(98);
+ CASE_FIXED_FP(99);
+ CASE_FIXED_FP(100);
+ CASE_FIXED_FP(101);
+ CASE_FIXED_FP(102);
+ CASE_FIXED_FP(103);
+ CASE_FIXED_FP(104);
+ CASE_FIXED_FP(105);
+ CASE_FIXED_FP(106);
+ CASE_FIXED_FP(107);
+ CASE_FIXED_FP(108);
+ CASE_FIXED_FP(109);
+ CASE_FIXED_FP(110);
+ CASE_FIXED_FP(111);
+ CASE_FIXED_FP(112);
+ CASE_FIXED_FP(113);
+ CASE_FIXED_FP(114);
+ CASE_FIXED_FP(115);
+ CASE_FIXED_FP(116);
+ CASE_FIXED_FP(117);
+ CASE_FIXED_FP(118);
+ CASE_FIXED_FP(119);
+ CASE_FIXED_FP(120);
+ CASE_FIXED_FP(121);
+ CASE_FIXED_FP(122);
+ CASE_FIXED_FP(123);
+ CASE_FIXED_FP(124);
+ CASE_FIXED_FP(125);
+ CASE_FIXED_FP(126);
+ CASE_FIXED_FP(127);
+ }
+#undef CASE_FIXED_FP
+}
+
+void setfpreg(unsigned long regnum, struct ia64_fpreg *fpval,
+ struct kvm_pt_regs *regs)
+{
+ /* Take floating register rotation into consideration*/
+ if (regnum >= IA64_FIRST_ROTATING_FR)
+ regnum = IA64_FIRST_ROTATING_FR + fph_index(regs, regnum);
+
+#define CASE_FIXED_FP(reg) \
+ case (reg) : \
+ ia64_ldf_fill(reg, fpval); \
+ break
+
+ switch (regnum) {
+ CASE_FIXED_FP(2);
+ CASE_FIXED_FP(3);
+ CASE_FIXED_FP(4);
+ CASE_FIXED_FP(5);
+
+ CASE_FIXED_FP(6);
+ CASE_FIXED_FP(7);
+ CASE_FIXED_FP(8);
+ CASE_FIXED_FP(9);
+ CASE_FIXED_FP(10);
+ CASE_FIXED_FP(11);
+
+ CASE_FIXED_FP(12);
+ CASE_FIXED_FP(13);
+ CASE_FIXED_FP(14);
+ CASE_FIXED_FP(15);
+ CASE_FIXED_FP(16);
+ CASE_FIXED_FP(17);
+ CASE_FIXED_FP(18);
+ CASE_FIXED_FP(19);
+ CASE_FIXED_FP(20);
+ CASE_FIXED_FP(21);
+ CASE_FIXED_FP(22);
+ CASE_FIXED_FP(23);
+ CASE_FIXED_FP(24);
+ CASE_FIXED_FP(25);
+ CASE_FIXED_FP(26);
+ CASE_FIXED_FP(27);
+ CASE_FIXED_FP(28);
+ CASE_FIXED_FP(29);
+ CASE_FIXED_FP(30);
+ CASE_FIXED_FP(31);
+ CASE_FIXED_FP(32);
+ CASE_FIXED_FP(33);
+ CASE_FIXED_FP(34);
+ CASE_FIXED_FP(35);
+ CASE_FIXED_FP(36);
+ CASE_FIXED_FP(37);
+ CASE_FIXED_FP(38);
+ CASE_FIXED_FP(39);
+ CASE_FIXED_FP(40);
+ CASE_FIXED_FP(41);
+ CASE_FIXED_FP(42);
+ CASE_FIXED_FP(43);
+ CASE_FIXED_FP(44);
+ CASE_FIXED_FP(45);
+ CASE_FIXED_FP(46);
+ CASE_FIXED_FP(47);
+ CASE_FIXED_FP(48);
+ CASE_FIXED_FP(49);
+ CASE_FIXED_FP(50);
+ CASE_FIXED_FP(51);
+ CASE_FIXED_FP(52);
+ CASE_FIXED_FP(53);
+ CASE_FIXED_FP(54);
+ CASE_FIXED_FP(55);
+ CASE_FIXED_FP(56);
+ CASE_FIXED_FP(57);
+ CASE_FIXED_FP(58);
+ CASE_FIXED_FP(59);
+ CASE_FIXED_FP(60);
+ CASE_FIXED_FP(61);
+ CASE_FIXED_FP(62);
+ CASE_FIXED_FP(63);
+ CASE_FIXED_FP(64);
+ CASE_FIXED_FP(65);
+ CASE_FIXED_FP(66);
+ CASE_FIXED_FP(67);
+ CASE_FIXED_FP(68);
+ CASE_FIXED_FP(69);
+ CASE_FIXED_FP(70);
+ CASE_FIXED_FP(71);
+ CASE_FIXED_FP(72);
+ CASE_FIXED_FP(73);
+ CASE_FIXED_FP(74);
+ CASE_FIXED_FP(75);
+ CASE_FIXED_FP(76);
+ CASE_FIXED_FP(77);
+ CASE_FIXED_FP(78);
+ CASE_FIXED_FP(79);
+ CASE_FIXED_FP(80);
+ CASE_FIXED_FP(81);
+ CASE_FIXED_FP(82);
+ CASE_FIXED_FP(83);
+ CASE_FIXED_FP(84);
+ CASE_FIXED_FP(85);
+ CASE_FIXED_FP(86);
+ CASE_FIXED_FP(87);
+ CASE_FIXED_FP(88);
+ CASE_FIXED_FP(89);
+ CASE_FIXED_FP(90);
+ CASE_FIXED_FP(91);
+ CASE_FIXED_FP(92);
+ CASE_FIXED_FP(93);
+ CASE_FIXED_FP(94);
+ CASE_FIXED_FP(95);
+ CASE_FIXED_FP(96);
+ CASE_FIXED_FP(97);
+ CASE_FIXED_FP(98);
+ CASE_FIXED_FP(99);
+ CASE_FIXED_FP(100);
+ CASE_FIXED_FP(101);
+ CASE_FIXED_FP(102);
+ CASE_FIXED_FP(103);
+ CASE_FIXED_FP(104);
+ CASE_FIXED_FP(105);
+ CASE_FIXED_FP(106);
+ CASE_FIXED_FP(107);
+ CASE_FIXED_FP(108);
+ CASE_FIXED_FP(109);
+ CASE_FIXED_FP(110);
+ CASE_FIXED_FP(111);
+ CASE_FIXED_FP(112);
+ CASE_FIXED_FP(113);
+ CASE_FIXED_FP(114);
+ CASE_FIXED_FP(115);
+ CASE_FIXED_FP(116);
+ CASE_FIXED_FP(117);
+ CASE_FIXED_FP(118);
+ CASE_FIXED_FP(119);
+ CASE_FIXED_FP(120);
+ CASE_FIXED_FP(121);
+ CASE_FIXED_FP(122);
+ CASE_FIXED_FP(123);
+ CASE_FIXED_FP(124);
+ CASE_FIXED_FP(125);
+ CASE_FIXED_FP(126);
+ CASE_FIXED_FP(127);
+ }
+}
+
+void vcpu_get_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
+ struct ia64_fpreg *val)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ getfpreg(reg, val, regs); /* FIXME: handle NATs later*/
+}
+
+void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg,
+ struct ia64_fpreg *val)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ if (reg > 1)
+ setfpreg(reg, val, regs); /* FIXME: handle NATs later*/
+}
+
+/************************************************************************
+ * lsapic timer
+ ***********************************************************************/
+u64 vcpu_get_itc(struct kvm_vcpu *vcpu)
+{
+ unsigned long guest_itc;
+ guest_itc = VMX(vcpu, itc_offset) + ia64_getreg(_IA64_REG_AR_ITC);
+
+ if (guest_itc >= VMX(vcpu, last_itc)) {
+ VMX(vcpu, last_itc) = guest_itc;
+ return guest_itc;
+ } else
+ return VMX(vcpu, last_itc);
+}
+
+static inline void vcpu_set_itm(struct kvm_vcpu *vcpu, u64 val);
+static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
+{
+ struct kvm_vcpu *v;
+ int i;
+ long itc_offset = val - ia64_getreg(_IA64_REG_AR_ITC);
+ unsigned long vitv = VCPU(vcpu, itv);
+
+ if (vcpu->vcpu_id == 0) {
+ for (i = 0; i < MAX_VCPU_NUM; i++) {
+ v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+ VMX(v, itc_offset) = itc_offset;
+ VMX(v, last_itc) = 0;
+ }
+ }
+ VMX(vcpu, last_itc) = 0;
+ if (VCPU(vcpu, itm) <= val) {
+ VMX(vcpu, itc_check) = 0;
+ vcpu_unpend_interrupt(vcpu, vitv);
+ } else {
+ VMX(vcpu, itc_check) = 1;
+ vcpu_set_itm(vcpu, VCPU(vcpu, itm));
+ }
+
+}
+
+static inline u64 vcpu_get_itm(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, itm));
+}
+
+static inline void vcpu_set_itm(struct kvm_vcpu *vcpu, u64 val)
+{
+ unsigned long vitv = VCPU(vcpu, itv);
+ VCPU(vcpu, itm) = val;
+
+ if (val > vcpu_get_itc(vcpu)) {
+ VMX(vcpu, itc_check) = 1;
+ vcpu_unpend_interrupt(vcpu, vitv);
+ VMX(vcpu, timer_pending) = 0;
+ } else
+ VMX(vcpu, itc_check) = 0;
+}
+
+#define ITV_VECTOR(itv) (itv&0xff)
+#define ITV_IRQ_MASK(itv) (itv&(1<<16))
+
+static inline void vcpu_set_itv(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, itv) = val;
+ if (!ITV_IRQ_MASK(val) && vcpu->arch.timer_pending) {
+ vcpu_pend_interrupt(vcpu, ITV_VECTOR(val));
+ vcpu->arch.timer_pending = 0;
+ }
+}
+
+static inline void vcpu_set_eoi(struct kvm_vcpu *vcpu, u64 val)
+{
+ int vec;
+
+ vec = highest_inservice_irq(vcpu);
+ if (vec == NULL_VECTOR)
+ return;
+ VMX(vcpu, insvc[vec >> 6]) &= ~(1UL << (vec & 63));
+ VCPU(vcpu, eoi) = 0;
+ vcpu->arch.irq_new_pending = 1;
+
+}
+
+/* See Table 5-8 in SDM vol2 for the definition */
+int irq_masked(struct kvm_vcpu *vcpu, int h_pending, int h_inservice)
+{
+ union ia64_tpr vtpr;
+
+ vtpr.val = VCPU(vcpu, tpr);
+
+ if (h_inservice == NMI_VECTOR)
+ return IRQ_MASKED_BY_INSVC;
+
+ if (h_pending == NMI_VECTOR) {
+ /* Non Maskable Interrupt */
+ return IRQ_NO_MASKED;
+ }
+
+ if (h_inservice == ExtINT_VECTOR)
+ return IRQ_MASKED_BY_INSVC;
+
+ if (h_pending == ExtINT_VECTOR) {
+ if (vtpr.mmi) {
+ /* mask all external IRQ */
+ return IRQ_MASKED_BY_VTPR;
+ } else
+ return IRQ_NO_MASKED;
+ }
+
+ if (is_higher_irq(h_pending, h_inservice)) {
+ if (is_higher_class(h_pending, vtpr.mic + (vtpr.mmi << 4)))
+ return IRQ_NO_MASKED;
+ else
+ return IRQ_MASKED_BY_VTPR;
+ } else {
+ return IRQ_MASKED_BY_INSVC;
+ }
+}
+
+void vcpu_pend_interrupt(struct kvm_vcpu *vcpu, u8 vec)
+{
+ long spsr;
+ int ret;
+
+ local_irq_save(spsr);
+ ret = test_and_set_bit(vec, &VCPU(vcpu, irr[0]));
+ local_irq_restore(spsr);
+
+ vcpu->arch.irq_new_pending = 1;
+}
+
+void vcpu_unpend_interrupt(struct kvm_vcpu *vcpu, u8 vec)
+{
+ long spsr;
+ int ret;
+
+ local_irq_save(spsr);
+ ret = test_and_clear_bit(vec, &VCPU(vcpu, irr[0]));
+ local_irq_restore(spsr);
+ if (ret) {
+ vcpu->arch.irq_new_pending = 1;
+ wmb();
+ }
+}
+
+void update_vhpi(struct kvm_vcpu *vcpu, int vec)
+{
+ u64 vhpi;
+
+ if (vec == NULL_VECTOR)
+ vhpi = 0;
+ else if (vec == NMI_VECTOR)
+ vhpi = 32;
+ else if (vec == ExtINT_VECTOR)
+ vhpi = 16;
+ else
+ vhpi = vec >> 4;
+
+ VCPU(vcpu, vhpi) = vhpi;
+ if (VCPU(vcpu, vac).a_int)
+ ia64_call_vsa(PAL_VPS_SET_PENDING_INTERRUPT,
+ (u64)vcpu->arch.vpd, 0, 0, 0, 0, 0, 0);
+}
+
+u64 vcpu_get_ivr(struct kvm_vcpu *vcpu)
+{
+ int vec, h_inservice, mask;
+
+ vec = highest_pending_irq(vcpu);
+ h_inservice = highest_inservice_irq(vcpu);
+ mask = irq_masked(vcpu, vec, h_inservice);
+ if (vec == NULL_VECTOR || mask == IRQ_MASKED_BY_INSVC) {
+ if (VCPU(vcpu, vhpi))
+ update_vhpi(vcpu, NULL_VECTOR);
+ return IA64_SPURIOUS_INT_VECTOR;
+ }
+ if (mask == IRQ_MASKED_BY_VTPR) {
+ update_vhpi(vcpu, vec);
+ return IA64_SPURIOUS_INT_VECTOR;
+ }
+ VMX(vcpu, insvc[vec >> 6]) |= (1UL << (vec & 63));
+ vcpu_unpend_interrupt(vcpu, vec);
+ return (u64)vec;
+}
+
+/**************************************************************************
+ Privileged operation emulation routines
+ **************************************************************************/
+u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ union ia64_pta vpta;
+ union ia64_rr vrr;
+ u64 pval;
+ u64 vhpt_offset;
+
+ vpta.val = vcpu_get_pta(vcpu);
+ vrr.val = vcpu_get_rr(vcpu, vadr);
+ vhpt_offset = ((vadr >> vrr.ps) << 3) & ((1UL << (vpta.size)) - 1);
+ if (vpta.vf) {
+ pval = ia64_call_vsa(PAL_VPS_THASH, vadr, vrr.val,
+ vpta.val, 0, 0, 0, 0);
+ } else {
+ pval = (vadr & VRN_MASK) | vhpt_offset |
+ (vpta.val << 3 >> (vpta.size + 3) << (vpta.size));
+ }
+ return pval;
+}
+
+u64 vcpu_ttag(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ union ia64_rr vrr;
+ union ia64_pta vpta;
+ u64 pval;
+
+ vpta.val = vcpu_get_pta(vcpu);
+ vrr.val = vcpu_get_rr(vcpu, vadr);
+ if (vpta.vf) {
+ pval = ia64_call_vsa(PAL_VPS_TTAG, vadr, vrr.val,
+ 0, 0, 0, 0, 0);
+ } else
+ pval = 1;
+
+ return pval;
+}
+
+u64 vcpu_tak(struct kvm_vcpu *vcpu, u64 vadr)
+{
+ struct thash_data *data;
+ union ia64_pta vpta;
+ u64 key;
+
+ vpta.val = vcpu_get_pta(vcpu);
+ if (vpta.vf == 0) {
+ key = 1;
+ return key;
+ }
+ data = vtlb_lookup(vcpu, vadr, D_TLB);
+ if (!data || !data->p)
+ key = 1;
+ else
+ key = data->key;
+
+ return key;
+}
+
+
+
+void kvm_thash(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long thash, vadr;
+
+ vadr = vcpu_get_gr(vcpu, inst.M46.r3);
+ thash = vcpu_thash(vcpu, vadr);
+ vcpu_set_gr(vcpu, inst.M46.r1, thash, 0);
+}
+
+
+void kvm_ttag(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long tag, vadr;
+
+ vadr = vcpu_get_gr(vcpu, inst.M46.r3);
+ tag = vcpu_ttag(vcpu, vadr);
+ vcpu_set_gr(vcpu, inst.M46.r1, tag, 0);
+}
+
+int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, u64 *padr)
+{
+ struct thash_data *data;
+ union ia64_isr visr, pt_isr;
+ struct kvm_pt_regs *regs;
+ struct ia64_psr vpsr;
+
+ regs = vcpu_regs(vcpu);
+ pt_isr.val = VMX(vcpu, cr_isr);
+ visr.val = 0;
+ visr.ei = pt_isr.ei;
+ visr.ir = pt_isr.ir;
+ vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+ visr.na = 1;
+
+ data = vhpt_lookup(vadr);
+ if (data) {
+ if (data->p == 0) {
+ vcpu_set_isr(vcpu, visr.val);
+ data_page_not_present(vcpu, vadr);
+ return IA64_FAULT;
+ } else if (data->ma == VA_MATTR_NATPAGE) {
+ vcpu_set_isr(vcpu, visr.val);
+ dnat_page_consumption(vcpu, vadr);
+ return IA64_FAULT;
+ } else {
+ *padr = (data->gpaddr >> data->ps << data->ps) |
+ (vadr & (PSIZE(data->ps) - 1));
+ return IA64_NO_FAULT;
+ }
+ }
+
+ data = vtlb_lookup(vcpu, vadr, D_TLB);
+ if (data) {
+ if (data->p == 0) {
+ vcpu_set_isr(vcpu, visr.val);
+ data_page_not_present(vcpu, vadr);
+ return IA64_FAULT;
+ } else if (data->ma == VA_MATTR_NATPAGE) {
+ vcpu_set_isr(vcpu, visr.val);
+ dnat_page_consumption(vcpu, vadr);
+ return IA64_FAULT;
+ } else{
+ *padr = ((data->ppn >> (data->ps - 12)) << data->ps)
+ | (vadr & (PSIZE(data->ps) - 1));
+ return IA64_NO_FAULT;
+ }
+ }
+ if (!vhpt_enabled(vcpu, vadr, NA_REF)) {
+ if (vpsr.ic) {
+ vcpu_set_isr(vcpu, visr.val);
+ alt_dtlb(vcpu, vadr);
+ return IA64_FAULT;
+ } else {
+ nested_dtlb(vcpu);
+ return IA64_FAULT;
+ }
+ } else {
+ if (vpsr.ic) {
+ vcpu_set_isr(vcpu, visr.val);
+ dvhpt_fault(vcpu, vadr);
+ return IA64_FAULT;
+ } else{
+ nested_dtlb(vcpu);
+ return IA64_FAULT;
+ }
+ }
+
+ return IA64_NO_FAULT;
+}
+
+
+int kvm_tpa(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r1, r3;
+
+ r3 = vcpu_get_gr(vcpu, inst.M46.r3);
+
+ if (vcpu_tpa(vcpu, r3, &r1))
+ return IA64_FAULT;
+
+ vcpu_set_gr(vcpu, inst.M46.r1, r1, 0);
+ return(IA64_NO_FAULT);
+}
+
+void kvm_tak(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r1, r3;
+
+ r3 = vcpu_get_gr(vcpu, inst.M46.r3);
+ r1 = vcpu_tak(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M46.r1, r1, 0);
+}
+
+
+/************************************
+ * Insert/Purge translation register/cache
+ ************************************/
+void vcpu_itc_i(struct kvm_vcpu *vcpu, u64 pte, u64 itir, u64 ifa)
+{
+ thash_purge_and_insert(vcpu, pte, itir, ifa, I_TLB);
+}
+
+void vcpu_itc_d(struct kvm_vcpu *vcpu, u64 pte, u64 itir, u64 ifa)
+{
+ thash_purge_and_insert(vcpu, pte, itir, ifa, D_TLB);
+}
+
+void vcpu_itr_i(struct kvm_vcpu *vcpu, u64 slot, u64 pte, u64 itir, u64 ifa)
+{
+ u64 ps, va, rid;
+ struct thash_data *p_itr;
+
+ ps = itir_ps(itir);
+ va = PAGEALIGN(ifa, ps);
+ pte &= ~PAGE_FLAGS_RV_MASK;
+ rid = vcpu_get_rr(vcpu, ifa);
+ rid = rid & RR_RID_MASK;
+ p_itr = (struct thash_data *)&vcpu->arch.itrs[slot];
+ vcpu_set_tr(p_itr, pte, itir, va, rid);
+ vcpu_quick_region_set(VMX(vcpu, itr_regions), va);
+}
+
+
+void vcpu_itr_d(struct kvm_vcpu *vcpu, u64 slot, u64 pte, u64 itir, u64 ifa)
+{
+ u64 gpfn;
+ u64 ps, va, rid;
+ struct thash_data *p_dtr;
+
+ ps = itir_ps(itir);
+ va = PAGEALIGN(ifa, ps);
+ pte &= ~PAGE_FLAGS_RV_MASK;
+
+ if (ps != _PAGE_SIZE_16M)
+ thash_purge_entries(vcpu, va, ps);
+ gpfn = (pte & _PAGE_PPN_MASK) >> PAGE_SHIFT;
+ if (__gpfn_is_io(gpfn))
+ pte |= VTLB_PTE_IO;
+ rid = vcpu_get_rr(vcpu, va);
+ rid = rid & RR_RID_MASK;
+ p_dtr = (struct thash_data *)&vcpu->arch.dtrs[slot];
+ vcpu_set_tr((struct thash_data *)&vcpu->arch.dtrs[slot],
+ pte, itir, va, rid);
+ vcpu_quick_region_set(VMX(vcpu, dtr_regions), va);
+}
+
+void vcpu_ptr_d(struct kvm_vcpu *vcpu, u64 ifa, u64 ps)
+{
+ int index;
+ u64 va;
+
+ va = PAGEALIGN(ifa, ps);
+ while ((index = vtr_find_overlap(vcpu, va, ps, D_TLB)) >= 0)
+ vcpu->arch.dtrs[index].page_flags = 0;
+
+ thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptr_i(struct kvm_vcpu *vcpu, u64 ifa, u64 ps)
+{
+ int index;
+ u64 va;
+
+ va = PAGEALIGN(ifa, ps);
+ while ((index = vtr_find_overlap(vcpu, va, ps, I_TLB)) >= 0)
+ vcpu->arch.itrs[index].page_flags = 0;
+
+ thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptc_l(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+ va = PAGEALIGN(va, ps);
+ thash_purge_entries(vcpu, va, ps);
+}
+
+void vcpu_ptc_e(struct kvm_vcpu *vcpu, u64 va)
+{
+ thash_purge_all(vcpu);
+}
+
+void vcpu_ptc_ga(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+ long psr;
+ local_irq_save(psr);
+ p->exit_reason = EXIT_REASON_PTC_G;
+
+ p->u.ptc_g_data.rr = vcpu_get_rr(vcpu, va);
+ p->u.ptc_g_data.vaddr = va;
+ p->u.ptc_g_data.ps = ps;
+ vmm_transition(vcpu);
+ /* Do Local Purge Here*/
+ vcpu_ptc_l(vcpu, va, ps);
+ local_irq_restore(psr);
+}
+
+
+void vcpu_ptc_g(struct kvm_vcpu *vcpu, u64 va, u64 ps)
+{
+ vcpu_ptc_ga(vcpu, va, ps);
+}
+
+void kvm_ptc_e(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ vcpu_ptc_e(vcpu, ifa);
+}
+
+void kvm_ptc_g(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa, itir;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ itir = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_ptc_g(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptc_ga(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa, itir;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ itir = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_ptc_ga(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptc_l(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa, itir;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ itir = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_ptc_l(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptr_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa, itir;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ itir = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_ptr_d(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_ptr_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long ifa, itir;
+
+ ifa = vcpu_get_gr(vcpu, inst.M45.r3);
+ itir = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_ptr_i(vcpu, ifa, itir_ps(itir));
+}
+
+void kvm_itr_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long itir, ifa, pte, slot;
+
+ slot = vcpu_get_gr(vcpu, inst.M45.r3);
+ pte = vcpu_get_gr(vcpu, inst.M45.r2);
+ itir = vcpu_get_itir(vcpu);
+ ifa = vcpu_get_ifa(vcpu);
+ vcpu_itr_d(vcpu, slot, pte, itir, ifa);
+}
+
+
+
+void kvm_itr_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long itir, ifa, pte, slot;
+
+ slot = vcpu_get_gr(vcpu, inst.M45.r3);
+ pte = vcpu_get_gr(vcpu, inst.M45.r2);
+ itir = vcpu_get_itir(vcpu);
+ ifa = vcpu_get_ifa(vcpu);
+ vcpu_itr_i(vcpu, slot, pte, itir, ifa);
+}
+
+void kvm_itc_d(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long itir, ifa, pte;
+
+ itir = vcpu_get_itir(vcpu);
+ ifa = vcpu_get_ifa(vcpu);
+ pte = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_itc_d(vcpu, pte, itir, ifa);
+}
+
+void kvm_itc_i(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long itir, ifa, pte;
+
+ itir = vcpu_get_itir(vcpu);
+ ifa = vcpu_get_ifa(vcpu);
+ pte = vcpu_get_gr(vcpu, inst.M45.r2);
+ vcpu_itc_i(vcpu, pte, itir, ifa);
+}
+
+/*************************************
+ * Moves to semi-privileged registers
+ *************************************/
+
+void kvm_mov_to_ar_imm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long imm;
+
+ if (inst.M30.s)
+ imm = -inst.M30.imm;
+ else
+ imm = inst.M30.imm;
+
+ vcpu_set_itc(vcpu, imm);
+}
+
+void kvm_mov_to_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r2;
+
+ r2 = vcpu_get_gr(vcpu, inst.M29.r2);
+ vcpu_set_itc(vcpu, r2);
+}
+
+
+void kvm_mov_from_ar_reg(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r1;
+
+ r1 = vcpu_get_itc(vcpu);
+ vcpu_set_gr(vcpu, inst.M31.r1, r1, 0);
+}
+/**************************************************************************
+ struct kvm_vcpu*protection key register access routines
+ **************************************************************************/
+
+unsigned long vcpu_get_pkr(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+ return ((unsigned long)ia64_get_pkr(reg));
+}
+
+void vcpu_set_pkr(struct kvm_vcpu *vcpu, unsigned long reg, unsigned long val)
+{
+ ia64_set_pkr(reg, val);
+}
+
+
+unsigned long vcpu_get_itir_on_fault(struct kvm_vcpu *vcpu, unsigned long ifa)
+{
+ union ia64_rr rr, rr1;
+
+ rr.val = vcpu_get_rr(vcpu, ifa);
+ rr1.val = 0;
+ rr1.ps = rr.ps;
+ rr1.rid = rr.rid;
+ return (rr1.val);
+}
+
+
+
+/********************************
+ * Moves to privileged registers
+ ********************************/
+unsigned long vcpu_set_rr(struct kvm_vcpu *vcpu, unsigned long reg,
+ unsigned long val)
+{
+ union ia64_rr oldrr, newrr;
+ unsigned long rrval;
+ struct exit_ctl_data *p = &vcpu->arch.exit_data;
+ unsigned long psr;
+
+ oldrr.val = vcpu_get_rr(vcpu, reg);
+ newrr.val = val;
+ vcpu->arch.vrr[reg >> VRN_SHIFT] = val;
+
+ switch ((unsigned long)(reg >> VRN_SHIFT)) {
+ case VRN6:
+ vcpu->arch.vmm_rr = vrrtomrr(val);
+ local_irq_save(psr);
+ p->exit_reason = EXIT_REASON_SWITCH_RR6;
+ vmm_transition(vcpu);
+ local_irq_restore(psr);
+ break;
+ case VRN4:
+ rrval = vrrtomrr(val);
+ vcpu->arch.metaphysical_saved_rr4 = rrval;
+ if (!is_physical_mode(vcpu))
+ ia64_set_rr(reg, rrval);
+ break;
+ case VRN0:
+ rrval = vrrtomrr(val);
+ vcpu->arch.metaphysical_saved_rr0 = rrval;
+ if (!is_physical_mode(vcpu))
+ ia64_set_rr(reg, rrval);
+ break;
+ default:
+ ia64_set_rr(reg, vrrtomrr(val));
+ break;
+ }
+
+ return (IA64_NO_FAULT);
+}
+
+
+
+void kvm_mov_to_rr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r2;
+
+ r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+ r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+ vcpu_set_rr(vcpu, r3, r2);
+}
+
+void kvm_mov_to_dbr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+}
+
+void kvm_mov_to_ibr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+}
+
+void kvm_mov_to_pmc(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r2;
+
+ r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+ r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+ vcpu_set_pmc(vcpu, r3, r2);
+}
+
+void kvm_mov_to_pmd(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r2;
+
+ r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+ r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+ vcpu_set_pmd(vcpu, r3, r2);
+}
+
+void kvm_mov_to_pkr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ u64 r3, r2;
+
+ r3 = vcpu_get_gr(vcpu, inst.M42.r3);
+ r2 = vcpu_get_gr(vcpu, inst.M42.r2);
+ vcpu_set_pkr(vcpu, r3, r2);
+}
+
+
+
+void kvm_mov_from_rr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_rr(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_pkr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_pkr(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_dbr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_dbr(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_ibr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_ibr(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void kvm_mov_from_pmc(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_pmc(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+
+unsigned long vcpu_get_cpuid(struct kvm_vcpu *vcpu, unsigned long reg)
+{
+ /* FIXME: This could get called as a result of a rsvd-reg fault */
+ if (reg > (ia64_get_cpuid(3) & 0xff))
+ return 0;
+ else
+ return ia64_get_cpuid(reg);
+}
+
+void kvm_mov_from_cpuid(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r3, r1;
+
+ r3 = vcpu_get_gr(vcpu, inst.M43.r3);
+ r1 = vcpu_get_cpuid(vcpu, r3);
+ vcpu_set_gr(vcpu, inst.M43.r1, r1, 0);
+}
+
+void vcpu_set_tpr(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ VCPU(vcpu, tpr) = val;
+ vcpu->arch.irq_check = 1;
+}
+
+unsigned long kvm_mov_to_cr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long r2;
+
+ r2 = vcpu_get_gr(vcpu, inst.M32.r2);
+ VCPU(vcpu, vcr[inst.M32.cr3]) = r2;
+
+ switch (inst.M32.cr3) {
+ case 0:
+ vcpu_set_dcr(vcpu, r2);
+ break;
+ case 1:
+ vcpu_set_itm(vcpu, r2);
+ break;
+ case 66:
+ vcpu_set_tpr(vcpu, r2);
+ break;
+ case 67:
+ vcpu_set_eoi(vcpu, r2);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+
+unsigned long kvm_mov_from_cr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long tgt = inst.M33.r1;
+ unsigned long val;
+
+ switch (inst.M33.cr3) {
+ case 65:
+ val = vcpu_get_ivr(vcpu);
+ vcpu_set_gr(vcpu, tgt, val, 0);
+ break;
+
+ case 67:
+ vcpu_set_gr(vcpu, tgt, 0L, 0);
+ break;
+ default:
+ val = VCPU(vcpu, vcr[inst.M33.cr3]);
+ vcpu_set_gr(vcpu, tgt, val, 0);
+ break;
+ }
+
+ return 0;
+}
+
+
+
+void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
+{
+
+ unsigned long mask;
+ struct kvm_pt_regs *regs;
+ struct ia64_psr old_psr, new_psr;
+
+ old_psr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+ regs = vcpu_regs(vcpu);
+ /* We only support guest as:
+ * vpsr.pk = 0
+ * vpsr.is = 0
+ * Otherwise panic
+ */
+ if (val & (IA64_PSR_PK | IA64_PSR_IS | IA64_PSR_VM))
+ panic_vm(vcpu);
+
+ /*
+ * For those IA64_PSR bits: id/da/dd/ss/ed/ia
+ * Since these bits will become 0, after success execution of each
+ * instruction, we will change set them to mIA64_PSR
+ */
+ VCPU(vcpu, vpsr) = val
+ & (~(IA64_PSR_ID | IA64_PSR_DA | IA64_PSR_DD |
+ IA64_PSR_SS | IA64_PSR_ED | IA64_PSR_IA));
+
+ if (!old_psr.i && (val & IA64_PSR_I)) {
+ /* vpsr.i 0->1 */
+ vcpu->arch.irq_check = 1;
+ }
+ new_psr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+ /*
+ * All vIA64_PSR bits shall go to mPSR (v->tf->tf_special.psr)
+ * , except for the following bits:
+ * ic/i/dt/si/rt/mc/it/bn/vm
+ */
+ mask = IA64_PSR_IC + IA64_PSR_I + IA64_PSR_DT + IA64_PSR_SI +
+ IA64_PSR_RT + IA64_PSR_MC + IA64_PSR_IT + IA64_PSR_BN +
+ IA64_PSR_VM;
+
+ regs->cr_ipsr = (regs->cr_ipsr & mask) | (val & (~mask));
+
+ check_mm_mode_switch(vcpu, old_psr, new_psr);
+
+ return ;
+}
+
+unsigned long vcpu_cover(struct kvm_vcpu *vcpu)
+{
+ struct ia64_psr vpsr;
+
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+
+ if (!vpsr.ic)
+ VCPU(vcpu, ifs) = regs->cr_ifs;
+ regs->cr_ifs = IA64_IFS_V;
+ return (IA64_NO_FAULT);
+}
+
+
+
+/**************************************************************************
+ VCPU banked general register access routines
+ **************************************************************************/
+#define vcpu_bsw0_unat(i, b0unat, b1unat, runat, VMM_PT_REGS_R16_SLOT) \
+ do { \
+ __asm__ __volatile__ ( \
+ ";;extr.u %0 = %3,%6,16;;\n" \
+ "dep %1 = %0, %1, 0, 16;;\n" \
+ "st8 [%4] = %1\n" \
+ "extr.u %0 = %2, 16, 16;;\n" \
+ "dep %3 = %0, %3, %6, 16;;\n" \
+ "st8 [%5] = %3\n" \
+ ::"r"(i), "r"(*b1unat), "r"(*b0unat), \
+ "r"(*runat), "r"(b1unat), "r"(runat), \
+ "i"(VMM_PT_REGS_R16_SLOT) : "memory"); \
+ } while (0)
+
+void vcpu_bsw0(struct kvm_vcpu *vcpu)
+{
+ unsigned long i;
+
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ unsigned long *r = &regs->r16;
+ unsigned long *b0 = &VCPU(vcpu, vbgr[0]);
+ unsigned long *b1 = &VCPU(vcpu, vgr[0]);
+ unsigned long *runat = &regs->eml_unat;
+ unsigned long *b0unat = &VCPU(vcpu, vbnat);
+ unsigned long *b1unat = &VCPU(vcpu, vnat);
+
+
+ if (VCPU(vcpu, vpsr) & IA64_PSR_BN) {
+ for (i = 0; i < 16; i++) {
+ *b1++ = *r;
+ *r++ = *b0++;
+ }
+ vcpu_bsw0_unat(i, b0unat, b1unat, runat,
+ VMM_PT_REGS_R16_SLOT);
+ VCPU(vcpu, vpsr) &= ~IA64_PSR_BN;
+ }
+}
+
+#define vcpu_bsw1_unat(i, b0unat, b1unat, runat, VMM_PT_REGS_R16_SLOT) \
+ do { \
+ __asm__ __volatile__ (";;extr.u %0 = %3, %6, 16;;\n" \
+ "dep %1 = %0, %1, 16, 16;;\n" \
+ "st8 [%4] = %1\n" \
+ "extr.u %0 = %2, 0, 16;;\n" \
+ "dep %3 = %0, %3, %6, 16;;\n" \
+ "st8 [%5] = %3\n" \
+ ::"r"(i), "r"(*b0unat), "r"(*b1unat), \
+ "r"(*runat), "r"(b0unat), "r"(runat), \
+ "i"(VMM_PT_REGS_R16_SLOT) : "memory"); \
+ } while (0)
+
+void vcpu_bsw1(struct kvm_vcpu *vcpu)
+{
+ unsigned long i;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ unsigned long *r = &regs->r16;
+ unsigned long *b0 = &VCPU(vcpu, vbgr[0]);
+ unsigned long *b1 = &VCPU(vcpu, vgr[0]);
+ unsigned long *runat = &regs->eml_unat;
+ unsigned long *b0unat = &VCPU(vcpu, vbnat);
+ unsigned long *b1unat = &VCPU(vcpu, vnat);
+
+ if (!(VCPU(vcpu, vpsr) & IA64_PSR_BN)) {
+ for (i = 0; i < 16; i++) {
+ *b0++ = *r;
+ *r++ = *b1++;
+ }
+ vcpu_bsw1_unat(i, b0unat, b1unat, runat,
+ VMM_PT_REGS_R16_SLOT);
+ VCPU(vcpu, vpsr) |= IA64_PSR_BN;
+ }
+}
+
+
+
+
+void vcpu_rfi(struct kvm_vcpu *vcpu)
+{
+ unsigned long ifs, psr;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ psr = VCPU(vcpu, ipsr);
+ if (psr & IA64_PSR_BN)
+ vcpu_bsw1(vcpu);
+ else
+ vcpu_bsw0(vcpu);
+ vcpu_set_psr(vcpu, psr);
+ ifs = VCPU(vcpu, ifs);
+ if (ifs >> 63)
+ regs->cr_ifs = ifs;
+ regs->cr_iip = VCPU(vcpu, iip);
+}
+
+
+/*
+ VPSR can't keep track of below bits of guest PSR
+ This function gets guest PSR
+ */
+
+unsigned long vcpu_get_psr(struct kvm_vcpu *vcpu)
+{
+ unsigned long mask;
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+
+ mask = IA64_PSR_BE | IA64_PSR_UP | IA64_PSR_AC | IA64_PSR_MFL |
+ IA64_PSR_MFH | IA64_PSR_CPL | IA64_PSR_RI;
+ return (VCPU(vcpu, vpsr) & ~mask) | (regs->cr_ipsr & mask);
+}
+
+void kvm_rsm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long vpsr;
+ unsigned long imm24 = (inst.M44.i<<23) | (inst.M44.i2<<21)
+ | inst.M44.imm;
+
+ vpsr = vcpu_get_psr(vcpu);
+ vpsr &= (~imm24);
+ vcpu_set_psr(vcpu, vpsr);
+}
+
+void kvm_ssm(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long vpsr;
+ unsigned long imm24 = (inst.M44.i << 23) | (inst.M44.i2 << 21)
+ | inst.M44.imm;
+
+ vpsr = vcpu_get_psr(vcpu);
+ vpsr |= imm24;
+ vcpu_set_psr(vcpu, vpsr);
+}
+
+/* Generate Mask
+ * Parameter:
+ * bit -- starting bit
+ * len -- how many bits
+ */
+#define MASK(bit,len) \
+({ \
+ __u64 ret; \
+ \
+ __asm __volatile("dep %0=-1, r0, %1, %2"\
+ : "=r" (ret): \
+ "M" (bit), \
+ "M" (len)); \
+ ret; \
+})
+
+void vcpu_set_psr_l(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ val = (val & MASK(0, 32)) | (vcpu_get_psr(vcpu) & MASK(32, 32));
+ vcpu_set_psr(vcpu, val);
+}
+
+void kvm_mov_to_psr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long val;
+
+ val = vcpu_get_gr(vcpu, inst.M35.r2);
+ vcpu_set_psr_l(vcpu, val);
+}
+
+void kvm_mov_from_psr(struct kvm_vcpu *vcpu, INST64 inst)
+{
+ unsigned long val;
+
+ val = vcpu_get_psr(vcpu);
+ val = (val & MASK(0, 32)) | (val & MASK(35, 2));
+ vcpu_set_gr(vcpu, inst.M33.r1, val, 0);
+}
+
+void vcpu_increment_iip(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ struct ia64_psr *ipsr = (struct ia64_psr *)&regs->cr_ipsr;
+ if (ipsr->ri == 2) {
+ ipsr->ri = 0;
+ regs->cr_iip += 16;
+ } else
+ ipsr->ri++;
+}
+
+void vcpu_decrement_iip(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pt_regs *regs = vcpu_regs(vcpu);
+ struct ia64_psr *ipsr = (struct ia64_psr *)&regs->cr_ipsr;
+
+ if (ipsr->ri == 0) {
+ ipsr->ri = 2;
+ regs->cr_iip -= 16;
+ } else
+ ipsr->ri--;
+}
+
+/** Emulate a privileged operation.
+ *
+ *
+ * @param vcpu virtual cpu
+ * @cause the reason cause virtualization fault
+ * @opcode the instruction code which cause virtualization fault
+ */
+
+void kvm_emulate(struct kvm_vcpu *vcpu, struct kvm_pt_regs *regs)
+{
+ unsigned long status, cause, opcode ;
+ INST64 inst;
+
+ status = IA64_NO_FAULT;
+ cause = VMX(vcpu, cause);
+ opcode = VMX(vcpu, opcode);
+ inst.inst = opcode;
+ /*
+ * Switch to actual virtual rid in rr0 and rr4,
+ * which is required by some tlb related instructions.
+ */
+ prepare_if_physical_mode(vcpu);
+
+ switch (cause) {
+ case EVENT_RSM:
+ kvm_rsm(vcpu, inst);
+ break;
+ case EVENT_SSM:
+ kvm_ssm(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_PSR:
+ kvm_mov_to_psr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_PSR:
+ kvm_mov_from_psr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_CR:
+ kvm_mov_from_cr(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_CR:
+ kvm_mov_to_cr(vcpu, inst);
+ break;
+ case EVENT_BSW_0:
+ vcpu_bsw0(vcpu);
+ break;
+ case EVENT_BSW_1:
+ vcpu_bsw1(vcpu);
+ break;
+ case EVENT_COVER:
+ vcpu_cover(vcpu);
+ break;
+ case EVENT_RFI:
+ vcpu_rfi(vcpu);
+ break;
+ case EVENT_ITR_D:
+ kvm_itr_d(vcpu, inst);
+ break;
+ case EVENT_ITR_I:
+ kvm_itr_i(vcpu, inst);
+ break;
+ case EVENT_PTR_D:
+ kvm_ptr_d(vcpu, inst);
+ break;
+ case EVENT_PTR_I:
+ kvm_ptr_i(vcpu, inst);
+ break;
+ case EVENT_ITC_D:
+ kvm_itc_d(vcpu, inst);
+ break;
+ case EVENT_ITC_I:
+ kvm_itc_i(vcpu, inst);
+ break;
+ case EVENT_PTC_L:
+ kvm_ptc_l(vcpu, inst);
+ break;
+ case EVENT_PTC_G:
+ kvm_ptc_g(vcpu, inst);
+ break;
+ case EVENT_PTC_GA:
+ kvm_ptc_ga(vcpu, inst);
+ break;
+ case EVENT_PTC_E:
+ kvm_ptc_e(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_RR:
+ kvm_mov_to_rr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_RR:
+ kvm_mov_from_rr(vcpu, inst);
+ break;
+ case EVENT_THASH:
+ kvm_thash(vcpu, inst);
+ break;
+ case EVENT_TTAG:
+ kvm_ttag(vcpu, inst);
+ break;
+ case EVENT_TPA:
+ status = kvm_tpa(vcpu, inst);
+ break;
+ case EVENT_TAK:
+ kvm_tak(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_AR_IMM:
+ kvm_mov_to_ar_imm(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_AR:
+ kvm_mov_to_ar_reg(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_AR:
+ kvm_mov_from_ar_reg(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_DBR:
+ kvm_mov_to_dbr(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_IBR:
+ kvm_mov_to_ibr(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_PMC:
+ kvm_mov_to_pmc(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_PMD:
+ kvm_mov_to_pmd(vcpu, inst);
+ break;
+ case EVENT_MOV_TO_PKR:
+ kvm_mov_to_pkr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_DBR:
+ kvm_mov_from_dbr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_IBR:
+ kvm_mov_from_ibr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_PMC:
+ kvm_mov_from_pmc(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_PKR:
+ kvm_mov_from_pkr(vcpu, inst);
+ break;
+ case EVENT_MOV_FROM_CPUID:
+ kvm_mov_from_cpuid(vcpu, inst);
+ break;
+ case EVENT_VMSW:
+ status = IA64_FAULT;
+ break;
+ default:
+ break;
+ };
+ /*Assume all status is NO_FAULT ?*/
+ if (status == IA64_NO_FAULT && cause != EVENT_RFI)
+ vcpu_increment_iip(vcpu);
+
+ recover_if_physical_mode(vcpu);
+}
+
+void init_vcpu(struct kvm_vcpu *vcpu)
+{
+ int i;
+
+ vcpu->arch.mode_flags = GUEST_IN_PHY;
+ VMX(vcpu, vrr[0]) = 0x38;
+ VMX(vcpu, vrr[1]) = 0x38;
+ VMX(vcpu, vrr[2]) = 0x38;
+ VMX(vcpu, vrr[3]) = 0x38;
+ VMX(vcpu, vrr[4]) = 0x38;
+ VMX(vcpu, vrr[5]) = 0x38;
+ VMX(vcpu, vrr[6]) = 0x38;
+ VMX(vcpu, vrr[7]) = 0x38;
+ VCPU(vcpu, vpsr) = IA64_PSR_BN;
+ VCPU(vcpu, dcr) = 0;
+ /* pta.size must not be 0. The minimum is 15 (32k) */
+ VCPU(vcpu, pta) = 15 << 2;
+ VCPU(vcpu, itv) = 0x10000;
+ VCPU(vcpu, itm) = 0;
+ VMX(vcpu, last_itc) = 0;
+
+ VCPU(vcpu, lid) = VCPU_LID(vcpu);
+ VCPU(vcpu, ivr) = 0;
+ VCPU(vcpu, tpr) = 0x10000;
+ VCPU(vcpu, eoi) = 0;
+ VCPU(vcpu, irr[0]) = 0;
+ VCPU(vcpu, irr[1]) = 0;
+ VCPU(vcpu, irr[2]) = 0;
+ VCPU(vcpu, irr[3]) = 0;
+ VCPU(vcpu, pmv) = 0x10000;
+ VCPU(vcpu, cmcv) = 0x10000;
+ VCPU(vcpu, lrr0) = 0x10000; /* default reset value? */
+ VCPU(vcpu, lrr1) = 0x10000; /* default reset value? */
+ update_vhpi(vcpu, NULL_VECTOR);
+ VLSAPIC_XTP(vcpu) = 0x80; /* disabled */
+
+ for (i = 0; i < 4; i++)
+ VLSAPIC_INSVC(vcpu, i) = 0;
+}
+
+void kvm_init_all_rr(struct kvm_vcpu *vcpu)
+{
+ unsigned long psr;
+
+ local_irq_save(psr);
+
+ /* WARNING: not allow co-exist of both virtual mode and physical
+ * mode in same region
+ */
+
+ vcpu->arch.metaphysical_saved_rr0 = vrrtomrr(VMX(vcpu, vrr[VRN0]));
+ vcpu->arch.metaphysical_saved_rr4 = vrrtomrr(VMX(vcpu, vrr[VRN4]));
+
+ if (is_physical_mode(vcpu)) {
+ if (vcpu->arch.mode_flags & GUEST_PHY_EMUL)
+ panic_vm(vcpu);
+
+ ia64_set_rr((VRN0 << VRN_SHIFT), vcpu->arch.metaphysical_rr0);
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN4 << VRN_SHIFT), vcpu->arch.metaphysical_rr4);
+ ia64_dv_serialize_data();
+ } else {
+ ia64_set_rr((VRN0 << VRN_SHIFT),
+ vcpu->arch.metaphysical_saved_rr0);
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN4 << VRN_SHIFT),
+ vcpu->arch.metaphysical_saved_rr4);
+ ia64_dv_serialize_data();
+ }
+ ia64_set_rr((VRN1 << VRN_SHIFT),
+ vrrtomrr(VMX(vcpu, vrr[VRN1])));
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN2 << VRN_SHIFT),
+ vrrtomrr(VMX(vcpu, vrr[VRN2])));
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN3 << VRN_SHIFT),
+ vrrtomrr(VMX(vcpu, vrr[VRN3])));
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN5 << VRN_SHIFT),
+ vrrtomrr(VMX(vcpu, vrr[VRN5])));
+ ia64_dv_serialize_data();
+ ia64_set_rr((VRN7 << VRN_SHIFT),
+ vrrtomrr(VMX(vcpu, vrr[VRN7])));
+ ia64_dv_serialize_data();
+ ia64_srlz_d();
+ ia64_set_psr(psr);
+}
+
+int vmm_entry(void)
+{
+ struct kvm_vcpu *v;
+ v = current_vcpu;
+
+ ia64_call_vsa(PAL_VPS_RESTORE, (unsigned long)v->arch.vpd,
+ 0, 0, 0, 0, 0, 0);
+ kvm_init_vtlb(v);
+ kvm_init_vhpt(v);
+ init_vcpu(v);
+ kvm_init_all_rr(v);
+ vmm_reset_entry();
+
+ return 0;
+}
+
+void panic_vm(struct kvm_vcpu *v)
+{
+ struct exit_ctl_data *p = &v->arch.exit_data;
+
+ p->exit_reason = EXIT_REASON_VM_PANIC;
+ vmm_transition(v);
+ /*Never to return*/
+ while (1);
+}
diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h
new file mode 100644
index 00000000000..b0fcfb62c49
--- /dev/null
+++ b/arch/ia64/kvm/vcpu.h
@@ -0,0 +1,740 @@
+/*
+ * vcpu.h: vcpu routines
+ * Copyright (c) 2005, Intel Corporation.
+ * Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ * Yaozu Dong (Eddie Dong) (Eddie.dong@intel.com)
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ * Xuefei Xu (Anthony Xu) (Anthony.xu@intel.com)
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * 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 __KVM_VCPU_H__
+#define __KVM_VCPU_H__
+
+#include <asm/types.h>
+#include <asm/fpu.h>
+#include <asm/processor.h>
+
+#ifndef __ASSEMBLY__
+#include "vti.h"
+
+#include <linux/kvm_host.h>
+#include <linux/spinlock.h>
+
+typedef unsigned long IA64_INST;
+
+typedef union U_IA64_BUNDLE {
+ unsigned long i64[2];
+ struct { unsigned long template:5, slot0:41, slot1a:18,
+ slot1b:23, slot2:41; };
+ /* NOTE: following doesn't work because bitfields can't cross natural
+ size boundaries
+ struct { unsigned long template:5, slot0:41, slot1:41, slot2:41; }; */
+} IA64_BUNDLE;
+
+typedef union U_INST64_A5 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, imm7b:7, r3:2, imm5c:5,
+ imm9d:9, s:1, major:4; };
+} INST64_A5;
+
+typedef union U_INST64_B4 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, btype:3, un3:3, p:1, b2:3, un11:11, x6:6,
+ wh:2, d:1, un1:1, major:4; };
+} INST64_B4;
+
+typedef union U_INST64_B8 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, un21:21, x6:6, un4:4, major:4; };
+} INST64_B8;
+
+typedef union U_INST64_B9 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm20:20, :1, x6:6, :3, i:1, major:4; };
+} INST64_B9;
+
+typedef union U_INST64_I19 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm20:20, :1, x6:6, x3:3, i:1, major:4; };
+} INST64_I19;
+
+typedef union U_INST64_I26 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_I26;
+
+typedef union U_INST64_I27 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, imm:7, ar3:7, x6:6, x3:3, s:1, major:4; };
+} INST64_I27;
+
+typedef union U_INST64_I28 { /* not privileged (mov from AR) */
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, :7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_I28;
+
+typedef union U_INST64_M28 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :14, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M28;
+
+typedef union U_INST64_M29 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M29;
+
+typedef union U_INST64_M30 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, imm:7, ar3:7, x4:4, x2:2,
+ x3:3, s:1, major:4; };
+} INST64_M30;
+
+typedef union U_INST64_M31 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, :7, ar3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M31;
+
+typedef union U_INST64_M32 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, cr3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M32;
+
+typedef union U_INST64_M33 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, :7, cr3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M33;
+
+typedef union U_INST64_M35 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, :7, x6:6, x3:3, :1, major:4; };
+
+} INST64_M35;
+
+typedef union U_INST64_M36 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, :14, x6:6, x3:3, :1, major:4; };
+} INST64_M36;
+
+typedef union U_INST64_M37 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm20a:20, :1, x4:4, x2:2, x3:3,
+ i:1, major:4; };
+} INST64_M37;
+
+typedef union U_INST64_M41 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, :7, x6:6, x3:3, :1, major:4; };
+} INST64_M41;
+
+typedef union U_INST64_M42 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M42;
+
+typedef union U_INST64_M43 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, :7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M43;
+
+typedef union U_INST64_M44 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm:21, x4:4, i2:2, x3:3, i:1, major:4; };
+} INST64_M44;
+
+typedef union U_INST64_M45 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, r2:7, r3:7, x6:6, x3:3, :1, major:4; };
+} INST64_M45;
+
+typedef union U_INST64_M46 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, un7:7, r3:7, x6:6,
+ x3:3, un1:1, major:4; };
+} INST64_M46;
+
+typedef union U_INST64_M47 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, un14:14, r3:7, x6:6, x3:3, un1:1, major:4; };
+} INST64_M47;
+
+typedef union U_INST64_M1{
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, un7:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M1;
+
+typedef union U_INST64_M2{
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, r2:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M2;
+
+typedef union U_INST64_M3{
+ IA64_INST inst;
+ struct { unsigned long qp:6, r1:7, imm7:7, r3:7, i:1, hint:2,
+ x6:6, s:1, major:4; };
+} INST64_M3;
+
+typedef union U_INST64_M4 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, un7:7, r2:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M4;
+
+typedef union U_INST64_M5 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm7:7, r2:7, r3:7, i:1, hint:2,
+ x6:6, s:1, major:4; };
+} INST64_M5;
+
+typedef union U_INST64_M6 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, f1:7, un7:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M6;
+
+typedef union U_INST64_M9 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, f2:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M9;
+
+typedef union U_INST64_M10 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, imm7:7, f2:7, r3:7, i:1, hint:2,
+ x6:6, s:1, major:4; };
+} INST64_M10;
+
+typedef union U_INST64_M12 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, f1:7, f2:7, r3:7, x:1, hint:2,
+ x6:6, m:1, major:4; };
+} INST64_M12;
+
+typedef union U_INST64_M15 {
+ IA64_INST inst;
+ struct { unsigned long qp:6, :7, imm7:7, r3:7, i:1, hint:2,
+ x6:6, s:1, major:4; };
+} INST64_M15;
+
+typedef union U_INST64 {
+ IA64_INST inst;
+ struct { unsigned long :37, major:4; } generic;
+ INST64_A5 A5; /* used in build_hypercall_bundle only */
+ INST64_B4 B4; /* used in build_hypercall_bundle only */
+ INST64_B8 B8; /* rfi, bsw.[01] */
+ INST64_B9 B9; /* break.b */
+ INST64_I19 I19; /* used in build_hypercall_bundle only */
+ INST64_I26 I26; /* mov register to ar (I unit) */
+ INST64_I27 I27; /* mov immediate to ar (I unit) */
+ INST64_I28 I28; /* mov from ar (I unit) */
+ INST64_M1 M1; /* ld integer */
+ INST64_M2 M2;
+ INST64_M3 M3;
+ INST64_M4 M4; /* st integer */
+ INST64_M5 M5;
+ INST64_M6 M6; /* ldfd floating pointer */
+ INST64_M9 M9; /* stfd floating pointer */
+ INST64_M10 M10; /* stfd floating pointer */
+ INST64_M12 M12; /* ldfd pair floating pointer */
+ INST64_M15 M15; /* lfetch + imm update */
+ INST64_M28 M28; /* purge translation cache entry */
+ INST64_M29 M29; /* mov register to ar (M unit) */
+ INST64_M30 M30; /* mov immediate to ar (M unit) */
+ INST64_M31 M31; /* mov from ar (M unit) */
+ INST64_M32 M32; /* mov reg to cr */
+ INST64_M33 M33; /* mov from cr */
+ INST64_M35 M35; /* mov to psr */
+ INST64_M36 M36; /* mov from psr */
+ INST64_M37 M37; /* break.m */
+ INST64_M41 M41; /* translation cache insert */
+ INST64_M42 M42; /* mov to indirect reg/translation reg insert*/
+ INST64_M43 M43; /* mov from indirect reg */
+ INST64_M44 M44; /* set/reset system mask */
+ INST64_M45 M45; /* translation purge */
+ INST64_M46 M46; /* translation access (tpa,tak) */
+ INST64_M47 M47; /* purge translation entry */
+} INST64;
+
+#define MASK_41 ((unsigned long)0x1ffffffffff)
+
+/* Virtual address memory attributes encoding */
+#define VA_MATTR_WB 0x0
+#define VA_MATTR_UC 0x4
+#define VA_MATTR_UCE 0x5
+#define VA_MATTR_WC 0x6
+#define VA_MATTR_NATPAGE 0x7
+
+#define PMASK(size) (~((size) - 1))
+#define PSIZE(size) (1UL<<(size))
+#define CLEARLSB(ppn, nbits) (((ppn) >> (nbits)) << (nbits))
+#define PAGEALIGN(va, ps) CLEARLSB(va, ps)
+#define PAGE_FLAGS_RV_MASK (0x2|(0x3UL<<50)|(((1UL<<11)-1)<<53))
+#define _PAGE_MA_ST (0x1 << 2) /* is reserved for software use */
+
+#define ARCH_PAGE_SHIFT 12
+
+#define INVALID_TI_TAG (1UL << 63)
+
+#define VTLB_PTE_P_BIT 0
+#define VTLB_PTE_IO_BIT 60
+#define VTLB_PTE_IO (1UL<<VTLB_PTE_IO_BIT)
+#define VTLB_PTE_P (1UL<<VTLB_PTE_P_BIT)
+
+#define vcpu_quick_region_check(_tr_regions,_ifa) \
+ (_tr_regions & (1 << ((unsigned long)_ifa >> 61)))
+
+#define vcpu_quick_region_set(_tr_regions,_ifa) \
+ do {_tr_regions |= (1 << ((unsigned long)_ifa >> 61)); } while (0)
+
+static inline void vcpu_set_tr(struct thash_data *trp, u64 pte, u64 itir,
+ u64 va, u64 rid)
+{
+ trp->page_flags = pte;
+ trp->itir = itir;
+ trp->vadr = va;
+ trp->rid = rid;
+}
+
+extern u64 kvm_lookup_mpa(u64 gpfn);
+extern u64 kvm_gpa_to_mpa(u64 gpa);
+
+/* Return I/O type if trye */
+#define __gpfn_is_io(gpfn) \
+ ({ \
+ u64 pte, ret = 0; \
+ pte = kvm_lookup_mpa(gpfn); \
+ if (!(pte & GPFN_INV_MASK)) \
+ ret = pte & GPFN_IO_MASK; \
+ ret; \
+ })
+
+#endif
+
+#define IA64_NO_FAULT 0
+#define IA64_FAULT 1
+
+#define VMM_RBS_OFFSET ((VMM_TASK_SIZE + 15) & ~15)
+
+#define SW_BAD 0 /* Bad mode transitition */
+#define SW_V2P 1 /* Physical emulatino is activated */
+#define SW_P2V 2 /* Exit physical mode emulation */
+#define SW_SELF 3 /* No mode transition */
+#define SW_NOP 4 /* Mode transition, but without action required */
+
+#define GUEST_IN_PHY 0x1
+#define GUEST_PHY_EMUL 0x2
+
+#define current_vcpu ((struct kvm_vcpu *) ia64_getreg(_IA64_REG_TP))
+
+#define VRN_SHIFT 61
+#define VRN_MASK 0xe000000000000000
+#define VRN0 0x0UL
+#define VRN1 0x1UL
+#define VRN2 0x2UL
+#define VRN3 0x3UL
+#define VRN4 0x4UL
+#define VRN5 0x5UL
+#define VRN6 0x6UL
+#define VRN7 0x7UL
+
+#define IRQ_NO_MASKED 0
+#define IRQ_MASKED_BY_VTPR 1
+#define IRQ_MASKED_BY_INSVC 2 /* masked by inservice IRQ */
+
+#define PTA_BASE_SHIFT 15
+
+#define IA64_PSR_VM_BIT 46
+#define IA64_PSR_VM (__IA64_UL(1) << IA64_PSR_VM_BIT)
+
+/* Interruption Function State */
+#define IA64_IFS_V_BIT 63
+#define IA64_IFS_V (__IA64_UL(1) << IA64_IFS_V_BIT)
+
+#define PHY_PAGE_UC (_PAGE_A|_PAGE_D|_PAGE_P|_PAGE_MA_UC|_PAGE_AR_RWX)
+#define PHY_PAGE_WB (_PAGE_A|_PAGE_D|_PAGE_P|_PAGE_MA_WB|_PAGE_AR_RWX)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/gcc_intrin.h>
+
+#define is_physical_mode(v) \
+ ((v->arch.mode_flags) & GUEST_IN_PHY)
+
+#define is_virtual_mode(v) \
+ (!is_physical_mode(v))
+
+#define MODE_IND(psr) \
+ (((psr).it << 2) + ((psr).dt << 1) + (psr).rt)
+
+#define _vmm_raw_spin_lock(x) \
+ do { \
+ __u32 *ia64_spinlock_ptr = (__u32 *) (x); \
+ __u64 ia64_spinlock_val; \
+ ia64_spinlock_val = ia64_cmpxchg4_acq(ia64_spinlock_ptr, 1, 0);\
+ if (unlikely(ia64_spinlock_val)) { \
+ do { \
+ while (*ia64_spinlock_ptr) \
+ ia64_barrier(); \
+ ia64_spinlock_val = \
+ ia64_cmpxchg4_acq(ia64_spinlock_ptr, 1, 0);\
+ } while (ia64_spinlock_val); \
+ } \
+ } while (0)
+
+#define _vmm_raw_spin_unlock(x) \
+ do { barrier(); \
+ ((spinlock_t *)x)->raw_lock.lock = 0; } \
+while (0)
+
+void vmm_spin_lock(spinlock_t *lock);
+void vmm_spin_unlock(spinlock_t *lock);
+enum {
+ I_TLB = 1,
+ D_TLB = 2
+};
+
+union kvm_va {
+ struct {
+ unsigned long off : 60; /* intra-region offset */
+ unsigned long reg : 4; /* region number */
+ } f;
+ unsigned long l;
+ void *p;
+};
+
+#define __kvm_pa(x) ({union kvm_va _v; _v.l = (long) (x); \
+ _v.f.reg = 0; _v.l; })
+#define __kvm_va(x) ({union kvm_va _v; _v.l = (long) (x); \
+ _v.f.reg = -1; _v.p; })
+
+#define _REGION_ID(x) ({union ia64_rr _v; _v.val = (long)(x); \
+ _v.rid; })
+#define _REGION_PAGE_SIZE(x) ({union ia64_rr _v; _v.val = (long)(x); \
+ _v.ps; })
+#define _REGION_HW_WALKER(x) ({union ia64_rr _v; _v.val = (long)(x); \
+ _v.ve; })
+
+enum vhpt_ref{ DATA_REF, NA_REF, INST_REF, RSE_REF };
+enum tlb_miss_type { INSTRUCTION, DATA, REGISTER };
+
+#define VCPU(_v, _x) ((_v)->arch.vpd->_x)
+#define VMX(_v, _x) ((_v)->arch._x)
+
+#define VLSAPIC_INSVC(vcpu, i) ((vcpu)->arch.insvc[i])
+#define VLSAPIC_XTP(_v) VMX(_v, xtp)
+
+static inline unsigned long itir_ps(unsigned long itir)
+{
+ return ((itir >> 2) & 0x3f);
+}
+
+
+/**************************************************************************
+ VCPU control register access routines
+ **************************************************************************/
+
+static inline u64 vcpu_get_itir(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, itir));
+}
+
+static inline void vcpu_set_itir(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, itir) = val;
+}
+
+static inline u64 vcpu_get_ifa(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, ifa));
+}
+
+static inline void vcpu_set_ifa(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, ifa) = val;
+}
+
+static inline u64 vcpu_get_iva(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, iva));
+}
+
+static inline u64 vcpu_get_pta(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, pta));
+}
+
+static inline u64 vcpu_get_lid(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, lid));
+}
+
+static inline u64 vcpu_get_tpr(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, tpr));
+}
+
+static inline u64 vcpu_get_eoi(struct kvm_vcpu *vcpu)
+{
+ return (0UL); /*reads of eoi always return 0 */
+}
+
+static inline u64 vcpu_get_irr0(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, irr[0]));
+}
+
+static inline u64 vcpu_get_irr1(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, irr[1]));
+}
+
+static inline u64 vcpu_get_irr2(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, irr[2]));
+}
+
+static inline u64 vcpu_get_irr3(struct kvm_vcpu *vcpu)
+{
+ return ((u64)VCPU(vcpu, irr[3]));
+}
+
+static inline void vcpu_set_dcr(struct kvm_vcpu *vcpu, u64 val)
+{
+ ia64_setreg(_IA64_REG_CR_DCR, val);
+}
+
+static inline void vcpu_set_isr(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, isr) = val;
+}
+
+static inline void vcpu_set_lid(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, lid) = val;
+}
+
+static inline void vcpu_set_ipsr(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, ipsr) = val;
+}
+
+static inline void vcpu_set_iip(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, iip) = val;
+}
+
+static inline void vcpu_set_ifs(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, ifs) = val;
+}
+
+static inline void vcpu_set_iipa(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, iipa) = val;
+}
+
+static inline void vcpu_set_iha(struct kvm_vcpu *vcpu, u64 val)
+{
+ VCPU(vcpu, iha) = val;
+}
+
+
+static inline u64 vcpu_get_rr(struct kvm_vcpu *vcpu, u64 reg)
+{
+ return vcpu->arch.vrr[reg>>61];
+}
+
+/**************************************************************************
+ VCPU debug breakpoint register access routines
+ **************************************************************************/
+
+static inline void vcpu_set_dbr(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+ __ia64_set_dbr(reg, val);
+}
+
+static inline void vcpu_set_ibr(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+ ia64_set_ibr(reg, val);
+}
+
+static inline u64 vcpu_get_dbr(struct kvm_vcpu *vcpu, u64 reg)
+{
+ return ((u64)__ia64_get_dbr(reg));
+}
+
+static inline u64 vcpu_get_ibr(struct kvm_vcpu *vcpu, u64 reg)
+{
+ return ((u64)ia64_get_ibr(reg));
+}
+
+/**************************************************************************
+ VCPU performance monitor register access routines
+ **************************************************************************/
+static inline void vcpu_set_pmc(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+ /* NOTE: Writes to unimplemented PMC registers are discarded */
+ ia64_set_pmc(reg, val);
+}
+
+static inline void vcpu_set_pmd(struct kvm_vcpu *vcpu, u64 reg, u64 val)
+{
+ /* NOTE: Writes to unimplemented PMD registers are discarded */
+ ia64_set_pmd(reg, val);
+}
+
+static inline u64 vcpu_get_pmc(struct kvm_vcpu *vcpu, u64 reg)
+{
+ /* NOTE: Reads from unimplemented PMC registers return zero */
+ return ((u64)ia64_get_pmc(reg));
+}
+
+static inline u64 vcpu_get_pmd(struct kvm_vcpu *vcpu, u64 reg)
+{
+ /* NOTE: Reads from unimplemented PMD registers return zero */
+ return ((u64)ia64_get_pmd(reg));
+}
+
+static inline unsigned long vrrtomrr(unsigned long val)
+{
+ union ia64_rr rr;
+ rr.val = val;
+ rr.rid = (rr.rid << 4) | 0xe;
+ if (rr.ps > PAGE_SHIFT)
+ rr.ps = PAGE_SHIFT;
+ rr.ve = 1;
+ return rr.val;
+}
+
+
+static inline int highest_bits(int *dat)
+{
+ u32 bits, bitnum;
+ int i;
+
+ /* loop for all 256 bits */
+ for (i = 7; i >= 0 ; i--) {
+ bits = dat[i];
+ if (bits) {
+ bitnum = fls(bits);
+ return i * 32 + bitnum - 1;
+ }
+ }
+ return NULL_VECTOR;
+}
+
+/*
+ * The pending irq is higher than the inservice one.
+ *
+ */
+static inline int is_higher_irq(int pending, int inservice)
+{
+ return ((pending > inservice)
+ || ((pending != NULL_VECTOR)
+ && (inservice == NULL_VECTOR)));
+}
+
+static inline int is_higher_class(int pending, int mic)
+{
+ return ((pending >> 4) > mic);
+}
+
+/*
+ * Return 0-255 for pending irq.
+ * NULL_VECTOR: when no pending.
+ */
+static inline int highest_pending_irq(struct kvm_vcpu *vcpu)
+{
+ if (VCPU(vcpu, irr[0]) & (1UL<<NMI_VECTOR))
+ return NMI_VECTOR;
+ if (VCPU(vcpu, irr[0]) & (1UL<<ExtINT_VECTOR))
+ return ExtINT_VECTOR;
+
+ return highest_bits((int *)&VCPU(vcpu, irr[0]));
+}
+
+static inline int highest_inservice_irq(struct kvm_vcpu *vcpu)
+{
+ if (VMX(vcpu, insvc[0]) & (1UL<<NMI_VECTOR))
+ return NMI_VECTOR;
+ if (VMX(vcpu, insvc[0]) & (1UL<<ExtINT_VECTOR))
+ return ExtINT_VECTOR;
+
+ return highest_bits((int *)&(VMX(vcpu, insvc[0])));
+}
+
+extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+ struct ia64_fpreg *val);
+extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, u64 reg,
+ struct ia64_fpreg *val);
+extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, u64 reg);
+extern void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 val, int nat);
+extern u64 vcpu_get_psr(struct kvm_vcpu *vcpu);
+extern void vcpu_set_psr(struct kvm_vcpu *vcpu, u64 val);
+extern u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr);
+extern void vcpu_bsw0(struct kvm_vcpu *vcpu);
+extern void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte,
+ u64 itir, u64 va, int type);
+extern struct thash_data *vhpt_lookup(u64 va);
+extern u64 guest_vhpt_lookup(u64 iha, u64 *pte);
+extern void thash_purge_entries(struct kvm_vcpu *v, u64 va, u64 ps);
+extern void thash_purge_entries_remote(struct kvm_vcpu *v, u64 va, u64 ps);
+extern u64 translate_phy_pte(u64 *pte, u64 itir, u64 va);
+extern int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte,
+ u64 itir, u64 ifa, int type);
+extern void thash_purge_all(struct kvm_vcpu *v);
+extern struct thash_data *vtlb_lookup(struct kvm_vcpu *v,
+ u64 va, int is_data);
+extern int vtr_find_overlap(struct kvm_vcpu *vcpu, u64 va,
+ u64 ps, int is_data);
+
+extern void vcpu_increment_iip(struct kvm_vcpu *v);
+extern void vcpu_decrement_iip(struct kvm_vcpu *vcpu);
+extern void vcpu_pend_interrupt(struct kvm_vcpu *vcpu, u8 vec);
+extern void vcpu_unpend_interrupt(struct kvm_vcpu *vcpu, u8 vec);
+extern void data_page_not_present(struct kvm_vcpu *vcpu, u64 vadr);
+extern void dnat_page_consumption(struct kvm_vcpu *vcpu, u64 vadr);
+extern void alt_dtlb(struct kvm_vcpu *vcpu, u64 vadr);
+extern void nested_dtlb(struct kvm_vcpu *vcpu);
+extern void dvhpt_fault(struct kvm_vcpu *vcpu, u64 vadr);
+extern int vhpt_enabled(struct kvm_vcpu *vcpu, u64 vadr, enum vhpt_ref ref);
+
+extern void update_vhpi(struct kvm_vcpu *vcpu, int vec);
+extern int irq_masked(struct kvm_vcpu *vcpu, int h_pending, int h_inservice);
+
+extern int fetch_code(struct kvm_vcpu *vcpu, u64 gip, IA64_BUNDLE *pbundle);
+extern void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma);
+extern void vmm_transition(struct kvm_vcpu *vcpu);
+extern void vmm_trampoline(union context *from, union context *to);
+extern int vmm_entry(void);
+extern u64 vcpu_get_itc(struct kvm_vcpu *vcpu);
+
+extern void vmm_reset_entry(void);
+void kvm_init_vtlb(struct kvm_vcpu *v);
+void kvm_init_vhpt(struct kvm_vcpu *v);
+void thash_init(struct thash_cb *hcb, u64 sz);
+
+void panic_vm(struct kvm_vcpu *v);
+
+extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2, u64 arg3,
+ u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+#endif
+#endif /* __VCPU_H__ */
diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c
new file mode 100644
index 00000000000..2275bf4e681
--- /dev/null
+++ b/arch/ia64/kvm/vmm.c
@@ -0,0 +1,66 @@
+/*
+ * vmm.c: vmm module interface with kvm module
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * Xiantao Zhang (xiantao.zhang@intel.com)
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+
+#include<linux/module.h>
+#include<asm/fpswa.h>
+
+#include "vcpu.h"
+
+MODULE_AUTHOR("Intel");
+MODULE_LICENSE("GPL");
+
+extern char kvm_ia64_ivt;
+extern fpswa_interface_t *vmm_fpswa_interface;
+
+struct kvm_vmm_info vmm_info = {
+ .module = THIS_MODULE,
+ .vmm_entry = vmm_entry,
+ .tramp_entry = vmm_trampoline,
+ .vmm_ivt = (unsigned long)&kvm_ia64_ivt,
+};
+
+static int __init kvm_vmm_init(void)
+{
+
+ vmm_fpswa_interface = fpswa_interface;
+
+ /*Register vmm data to kvm side*/
+ return kvm_init(&vmm_info, 1024, THIS_MODULE);
+}
+
+static void __exit kvm_vmm_exit(void)
+{
+ kvm_exit();
+ return ;
+}
+
+void vmm_spin_lock(spinlock_t *lock)
+{
+ _vmm_raw_spin_lock(lock);
+}
+
+void vmm_spin_unlock(spinlock_t *lock)
+{
+ _vmm_raw_spin_unlock(lock);
+}
+module_init(kvm_vmm_init)
+module_exit(kvm_vmm_exit)
diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S
new file mode 100644
index 00000000000..3ee5f481c06
--- /dev/null
+++ b/arch/ia64/kvm/vmm_ivt.S
@@ -0,0 +1,1424 @@
+/*
+ * /ia64/kvm_ivt.S
+ *
+ * Copyright (C) 1998-2001, 2003 Hewlett-Packard Co
+ * Stephane Eranian <eranian@hpl.hp.com>
+ * David Mosberger <davidm@hpl.hp.com>
+ * Copyright (C) 2000, 2002-2003 Intel Co
+ * Asit Mallick <asit.k.mallick@intel.com>
+ * Suresh Siddha <suresh.b.siddha@intel.com>
+ * Kenneth Chen <kenneth.w.chen@intel.com>
+ * Fenghua Yu <fenghua.yu@intel.com>
+ *
+ *
+ * 00/08/23 Asit Mallick <asit.k.mallick@intel.com> TLB handling
+ * for SMP
+ * 00/12/20 David Mosberger-Tang <davidm@hpl.hp.com> DTLB/ITLB
+ * handler now uses virtual PT.
+ *
+ * 07/6/20 Xuefei Xu (Anthony Xu) (anthony.xu@intel.com)
+ * Supporting Intel virtualization architecture
+ *
+ */
+
+/*
+ * This file defines the interruption vector table used by the CPU.
+ * It does not include one entry per possible cause of interruption.
+ *
+ * The first 20 entries of the table contain 64 bundles each while the
+ * remaining 48 entries contain only 16 bundles each.
+ *
+ * The 64 bundles are used to allow inlining the whole handler for
+ * critical
+ * interruptions like TLB misses.
+ *
+ * For each entry, the comment is as follows:
+ *
+ * // 0x1c00 Entry 7 (size 64 bundles) Data Key Miss
+ * (12,51)
+ * entry offset ----/ / / /
+ * /
+ * entry number ---------/ / /
+ * /
+ * size of the entry -------------/ /
+ * /
+ * vector name -------------------------------------/
+ * /
+ * interruptions triggering this vector
+ * ----------------------/
+ *
+ * The table is 32KB in size and must be aligned on 32KB
+ * boundary.
+ * (The CPU ignores the 15 lower bits of the address)
+ *
+ * Table is based upon EAS2.6 (Oct 1999)
+ */
+
+
+#include <asm/asmmacro.h>
+#include <asm/cache.h>
+#include <asm/pgtable.h>
+
+#include "asm-offsets.h"
+#include "vcpu.h"
+#include "kvm_minstate.h"
+#include "vti.h"
+
+#if 1
+# define PSR_DEFAULT_BITS psr.ac
+#else
+# define PSR_DEFAULT_BITS 0
+#endif
+
+
+#define KVM_FAULT(n) \
+ kvm_fault_##n:; \
+ mov r19=n;; \
+ br.sptk.many kvm_fault_##n; \
+ ;; \
+
+
+#define KVM_REFLECT(n) \
+ mov r31=pr; \
+ mov r19=n; /* prepare to save predicates */ \
+ mov r29=cr.ipsr; \
+ ;; \
+ tbit.z p6,p7=r29,IA64_PSR_VM_BIT; \
+(p7)br.sptk.many kvm_dispatch_reflection; \
+ br.sptk.many kvm_panic; \
+
+
+GLOBAL_ENTRY(kvm_panic)
+ br.sptk.many kvm_panic
+ ;;
+END(kvm_panic)
+
+
+
+
+
+ .section .text.ivt,"ax"
+
+ .align 32768 // align on 32KB boundary
+ .global kvm_ia64_ivt
+kvm_ia64_ivt:
+///////////////////////////////////////////////////////////////
+// 0x0000 Entry 0 (size 64 bundles) VHPT Translation (8,20,47)
+ENTRY(kvm_vhpt_miss)
+ KVM_FAULT(0)
+END(kvm_vhpt_miss)
+
+
+ .org kvm_ia64_ivt+0x400
+////////////////////////////////////////////////////////////////
+// 0x0400 Entry 1 (size 64 bundles) ITLB (21)
+ENTRY(kvm_itlb_miss)
+ mov r31 = pr
+ mov r29=cr.ipsr;
+ ;;
+ tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+ (p6) br.sptk kvm_alt_itlb_miss
+ mov r19 = 1
+ br.sptk kvm_itlb_miss_dispatch
+ KVM_FAULT(1);
+END(kvm_itlb_miss)
+
+ .org kvm_ia64_ivt+0x0800
+//////////////////////////////////////////////////////////////////
+// 0x0800 Entry 2 (size 64 bundles) DTLB (9,48)
+ENTRY(kvm_dtlb_miss)
+ mov r31 = pr
+ mov r29=cr.ipsr;
+ ;;
+ tbit.z p6,p7=r29,IA64_PSR_VM_BIT;
+(p6)br.sptk kvm_alt_dtlb_miss
+ br.sptk kvm_dtlb_miss_dispatch
+END(kvm_dtlb_miss)
+
+ .org kvm_ia64_ivt+0x0c00
+////////////////////////////////////////////////////////////////////
+// 0x0c00 Entry 3 (size 64 bundles) Alt ITLB (19)
+ENTRY(kvm_alt_itlb_miss)
+ mov r16=cr.ifa // get address that caused the TLB miss
+ ;;
+ movl r17=PAGE_KERNEL
+ mov r24=cr.ipsr
+ movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+ ;;
+ and r19=r19,r16 // clear ed, reserved bits, and PTE control bits
+ ;;
+ or r19=r17,r19 // insert PTE control bits into r19
+ ;;
+ movl r20=IA64_GRANULE_SHIFT<<2
+ ;;
+ mov cr.itir=r20
+ ;;
+ itc.i r19 // insert the TLB entry
+ mov pr=r31,-1
+ rfi
+END(kvm_alt_itlb_miss)
+
+ .org kvm_ia64_ivt+0x1000
+/////////////////////////////////////////////////////////////////////
+// 0x1000 Entry 4 (size 64 bundles) Alt DTLB (7,46)
+ENTRY(kvm_alt_dtlb_miss)
+ mov r16=cr.ifa // get address that caused the TLB miss
+ ;;
+ movl r17=PAGE_KERNEL
+ movl r19=(((1 << IA64_MAX_PHYS_BITS) - 1) & ~0xfff)
+ mov r24=cr.ipsr
+ ;;
+ and r19=r19,r16 // clear ed, reserved bits, and PTE control bits
+ ;;
+ or r19=r19,r17 // insert PTE control bits into r19
+ ;;
+ movl r20=IA64_GRANULE_SHIFT<<2
+ ;;
+ mov cr.itir=r20
+ ;;
+ itc.d r19 // insert the TLB entry
+ mov pr=r31,-1
+ rfi
+END(kvm_alt_dtlb_miss)
+
+ .org kvm_ia64_ivt+0x1400
+//////////////////////////////////////////////////////////////////////
+// 0x1400 Entry 5 (size 64 bundles) Data nested TLB (6,45)
+ENTRY(kvm_nested_dtlb_miss)
+ KVM_FAULT(5)
+END(kvm_nested_dtlb_miss)
+
+ .org kvm_ia64_ivt+0x1800
+/////////////////////////////////////////////////////////////////////
+// 0x1800 Entry 6 (size 64 bundles) Instruction Key Miss (24)
+ENTRY(kvm_ikey_miss)
+ KVM_REFLECT(6)
+END(kvm_ikey_miss)
+
+ .org kvm_ia64_ivt+0x1c00
+/////////////////////////////////////////////////////////////////////
+// 0x1c00 Entry 7 (size 64 bundles) Data Key Miss (12,51)
+ENTRY(kvm_dkey_miss)
+ KVM_REFLECT(7)
+END(kvm_dkey_miss)
+
+ .org kvm_ia64_ivt+0x2000
+////////////////////////////////////////////////////////////////////
+// 0x2000 Entry 8 (size 64 bundles) Dirty-bit (54)
+ENTRY(kvm_dirty_bit)
+ KVM_REFLECT(8)
+END(kvm_dirty_bit)
+
+ .org kvm_ia64_ivt+0x2400
+////////////////////////////////////////////////////////////////////
+// 0x2400 Entry 9 (size 64 bundles) Instruction Access-bit (27)
+ENTRY(kvm_iaccess_bit)
+ KVM_REFLECT(9)
+END(kvm_iaccess_bit)
+
+ .org kvm_ia64_ivt+0x2800
+///////////////////////////////////////////////////////////////////
+// 0x2800 Entry 10 (size 64 bundles) Data Access-bit (15,55)
+ENTRY(kvm_daccess_bit)
+ KVM_REFLECT(10)
+END(kvm_daccess_bit)
+
+ .org kvm_ia64_ivt+0x2c00
+/////////////////////////////////////////////////////////////////
+// 0x2c00 Entry 11 (size 64 bundles) Break instruction (33)
+ENTRY(kvm_break_fault)
+ mov r31=pr
+ mov r19=11
+ mov r29=cr.ipsr
+ ;;
+ KVM_SAVE_MIN_WITH_COVER_R19
+ ;;
+ alloc r14=ar.pfs,0,0,4,0 // now it's safe (must be first in insn group!)
+ mov out0=cr.ifa
+ mov out2=cr.isr // FIXME: pity to make this slow access twice
+ mov out3=cr.iim // FIXME: pity to make this slow access twice
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15)ssm psr.i // restore psr.i
+ addl r14=@gprel(ia64_leave_hypervisor),gp
+ ;;
+ KVM_SAVE_REST
+ mov rp=r14
+ ;;
+ adds out1=16,sp
+ br.call.sptk.many b6=kvm_ia64_handle_break
+ ;;
+END(kvm_break_fault)
+
+ .org kvm_ia64_ivt+0x3000
+/////////////////////////////////////////////////////////////////
+// 0x3000 Entry 12 (size 64 bundles) External Interrupt (4)
+ENTRY(kvm_interrupt)
+ mov r31=pr // prepare to save predicates
+ mov r19=12
+ mov r29=cr.ipsr
+ ;;
+ tbit.z p6,p7=r29,IA64_PSR_VM_BIT
+ tbit.z p0,p15=r29,IA64_PSR_I_BIT
+ ;;
+(p7) br.sptk kvm_dispatch_interrupt
+ ;;
+ mov r27=ar.rsc /* M */
+ mov r20=r1 /* A */
+ mov r25=ar.unat /* M */
+ mov r26=ar.pfs /* I */
+ mov r28=cr.iip /* M */
+ cover /* B (or nothing) */
+ ;;
+ mov r1=sp
+ ;;
+ invala /* M */
+ mov r30=cr.ifs
+ ;;
+ addl r1=-VMM_PT_REGS_SIZE,r1
+ ;;
+ adds r17=2*L1_CACHE_BYTES,r1 /* really: biggest cache-line size */
+ adds r16=PT(CR_IPSR),r1
+ ;;
+ lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES
+ st8 [r16]=r29 /* save cr.ipsr */
+ ;;
+ lfetch.fault.excl.nt1 [r17]
+ mov r29=b0
+ ;;
+ adds r16=PT(R8),r1 /* initialize first base pointer */
+ adds r17=PT(R9),r1 /* initialize second base pointer */
+ mov r18=r0 /* make sure r18 isn't NaT */
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r8,16
+.mem.offset 8,0; st8.spill [r17]=r9,16
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r10,24
+.mem.offset 8,0; st8.spill [r17]=r11,24
+ ;;
+ st8 [r16]=r28,16 /* save cr.iip */
+ st8 [r17]=r30,16 /* save cr.ifs */
+ mov r8=ar.fpsr /* M */
+ mov r9=ar.csd
+ mov r10=ar.ssd
+ movl r11=FPSR_DEFAULT /* L-unit */
+ ;;
+ st8 [r16]=r25,16 /* save ar.unat */
+ st8 [r17]=r26,16 /* save ar.pfs */
+ shl r18=r18,16 /* compute ar.rsc to be used for "loadrs" */
+ ;;
+ st8 [r16]=r27,16 /* save ar.rsc */
+ adds r17=16,r17 /* skip over ar_rnat field */
+ ;;
+ st8 [r17]=r31,16 /* save predicates */
+ adds r16=16,r16 /* skip over ar_bspstore field */
+ ;;
+ st8 [r16]=r29,16 /* save b0 */
+ st8 [r17]=r18,16 /* save ar.rsc value for "loadrs" */
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r20,16 /* save original r1 */
+.mem.offset 8,0; st8.spill [r17]=r12,16
+ adds r12=-16,r1
+ /* switch to kernel memory stack (with 16 bytes of scratch) */
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r13,16
+.mem.offset 8,0; st8.spill [r17]=r8,16 /* save ar.fpsr */
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r15,16
+.mem.offset 8,0; st8.spill [r17]=r14,16
+ dep r14=-1,r0,60,4
+ ;;
+.mem.offset 0,0; st8.spill [r16]=r2,16
+.mem.offset 8,0; st8.spill [r17]=r3,16
+ adds r2=VMM_PT_REGS_R16_OFFSET,r1
+ adds r14 = VMM_VCPU_GP_OFFSET,r13
+ ;;
+ mov r8=ar.ccv
+ ld8 r14 = [r14]
+ ;;
+ mov r1=r14 /* establish kernel global pointer */
+ ;; \
+ bsw.1
+ ;;
+ alloc r14=ar.pfs,0,0,1,0 // must be first in an insn group
+ mov out0=r13
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i
+ ;;
+ //(p15) ssm psr.i
+ adds r3=8,r2 // set up second base pointer for SAVE_REST
+ srlz.i // ensure everybody knows psr.ic is back on
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r16,16
+.mem.offset 8,0; st8.spill [r3]=r17,16
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r18,16
+.mem.offset 8,0; st8.spill [r3]=r19,16
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r20,16
+.mem.offset 8,0; st8.spill [r3]=r21,16
+ mov r18=b6
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r22,16
+.mem.offset 8,0; st8.spill [r3]=r23,16
+ mov r19=b7
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r24,16
+.mem.offset 8,0; st8.spill [r3]=r25,16
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r26,16
+.mem.offset 8,0; st8.spill [r3]=r27,16
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r28,16
+.mem.offset 8,0; st8.spill [r3]=r29,16
+ ;;
+.mem.offset 0,0; st8.spill [r2]=r30,16
+.mem.offset 8,0; st8.spill [r3]=r31,32
+ ;;
+ mov ar.fpsr=r11 /* M-unit */
+ st8 [r2]=r8,8 /* ar.ccv */
+ adds r24=PT(B6)-PT(F7),r3
+ ;;
+ stf.spill [r2]=f6,32
+ stf.spill [r3]=f7,32
+ ;;
+ stf.spill [r2]=f8,32
+ stf.spill [r3]=f9,32
+ ;;
+ stf.spill [r2]=f10
+ stf.spill [r3]=f11
+ adds r25=PT(B7)-PT(F11),r3
+ ;;
+ st8 [r24]=r18,16 /* b6 */
+ st8 [r25]=r19,16 /* b7 */
+ ;;
+ st8 [r24]=r9 /* ar.csd */
+ st8 [r25]=r10 /* ar.ssd */
+ ;;
+ srlz.d // make sure we see the effect of cr.ivr
+ addl r14=@gprel(ia64_leave_nested),gp
+ ;;
+ mov rp=r14
+ br.call.sptk.many b6=kvm_ia64_handle_irq
+ ;;
+END(kvm_interrupt)
+
+ .global kvm_dispatch_vexirq
+ .org kvm_ia64_ivt+0x3400
+//////////////////////////////////////////////////////////////////////
+// 0x3400 Entry 13 (size 64 bundles) Reserved
+ENTRY(kvm_virtual_exirq)
+ mov r31=pr
+ mov r19=13
+ mov r30 =r0
+ ;;
+kvm_dispatch_vexirq:
+ cmp.eq p6,p0 = 1,r30
+ ;;
+(p6)add r29 = VMM_VCPU_SAVED_GP_OFFSET,r21
+ ;;
+(p6)ld8 r1 = [r29]
+ ;;
+ KVM_SAVE_MIN_WITH_COVER_R19
+ alloc r14=ar.pfs,0,0,1,0
+ mov out0=r13
+
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15) ssm psr.i // restore psr.i
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ KVM_SAVE_REST
+ addl r14=@gprel(ia64_leave_hypervisor),gp
+ ;;
+ mov rp=r14
+ br.call.sptk.many b6=kvm_vexirq
+END(kvm_virtual_exirq)
+
+ .org kvm_ia64_ivt+0x3800
+/////////////////////////////////////////////////////////////////////
+// 0x3800 Entry 14 (size 64 bundles) Reserved
+ KVM_FAULT(14)
+ // this code segment is from 2.6.16.13
+
+
+ .org kvm_ia64_ivt+0x3c00
+///////////////////////////////////////////////////////////////////////
+// 0x3c00 Entry 15 (size 64 bundles) Reserved
+ KVM_FAULT(15)
+
+
+ .org kvm_ia64_ivt+0x4000
+///////////////////////////////////////////////////////////////////////
+// 0x4000 Entry 16 (size 64 bundles) Reserved
+ KVM_FAULT(16)
+
+ .org kvm_ia64_ivt+0x4400
+//////////////////////////////////////////////////////////////////////
+// 0x4400 Entry 17 (size 64 bundles) Reserved
+ KVM_FAULT(17)
+
+ .org kvm_ia64_ivt+0x4800
+//////////////////////////////////////////////////////////////////////
+// 0x4800 Entry 18 (size 64 bundles) Reserved
+ KVM_FAULT(18)
+
+ .org kvm_ia64_ivt+0x4c00
+//////////////////////////////////////////////////////////////////////
+// 0x4c00 Entry 19 (size 64 bundles) Reserved
+ KVM_FAULT(19)
+
+ .org kvm_ia64_ivt+0x5000
+//////////////////////////////////////////////////////////////////////
+// 0x5000 Entry 20 (size 16 bundles) Page Not Present
+ENTRY(kvm_page_not_present)
+ KVM_REFLECT(20)
+END(kvm_page_not_present)
+
+ .org kvm_ia64_ivt+0x5100
+///////////////////////////////////////////////////////////////////////
+// 0x5100 Entry 21 (size 16 bundles) Key Permission vector
+ENTRY(kvm_key_permission)
+ KVM_REFLECT(21)
+END(kvm_key_permission)
+
+ .org kvm_ia64_ivt+0x5200
+//////////////////////////////////////////////////////////////////////
+// 0x5200 Entry 22 (size 16 bundles) Instruction Access Rights (26)
+ENTRY(kvm_iaccess_rights)
+ KVM_REFLECT(22)
+END(kvm_iaccess_rights)
+
+ .org kvm_ia64_ivt+0x5300
+//////////////////////////////////////////////////////////////////////
+// 0x5300 Entry 23 (size 16 bundles) Data Access Rights (14,53)
+ENTRY(kvm_daccess_rights)
+ KVM_REFLECT(23)
+END(kvm_daccess_rights)
+
+ .org kvm_ia64_ivt+0x5400
+/////////////////////////////////////////////////////////////////////
+// 0x5400 Entry 24 (size 16 bundles) General Exception (5,32,34,36,38,39)
+ENTRY(kvm_general_exception)
+ KVM_REFLECT(24)
+ KVM_FAULT(24)
+END(kvm_general_exception)
+
+ .org kvm_ia64_ivt+0x5500
+//////////////////////////////////////////////////////////////////////
+// 0x5500 Entry 25 (size 16 bundles) Disabled FP-Register (35)
+ENTRY(kvm_disabled_fp_reg)
+ KVM_REFLECT(25)
+END(kvm_disabled_fp_reg)
+
+ .org kvm_ia64_ivt+0x5600
+////////////////////////////////////////////////////////////////////
+// 0x5600 Entry 26 (size 16 bundles) Nat Consumption (11,23,37,50)
+ENTRY(kvm_nat_consumption)
+ KVM_REFLECT(26)
+END(kvm_nat_consumption)
+
+ .org kvm_ia64_ivt+0x5700
+/////////////////////////////////////////////////////////////////////
+// 0x5700 Entry 27 (size 16 bundles) Speculation (40)
+ENTRY(kvm_speculation_vector)
+ KVM_REFLECT(27)
+END(kvm_speculation_vector)
+
+ .org kvm_ia64_ivt+0x5800
+/////////////////////////////////////////////////////////////////////
+// 0x5800 Entry 28 (size 16 bundles) Reserved
+ KVM_FAULT(28)
+
+ .org kvm_ia64_ivt+0x5900
+///////////////////////////////////////////////////////////////////
+// 0x5900 Entry 29 (size 16 bundles) Debug (16,28,56)
+ENTRY(kvm_debug_vector)
+ KVM_FAULT(29)
+END(kvm_debug_vector)
+
+ .org kvm_ia64_ivt+0x5a00
+///////////////////////////////////////////////////////////////
+// 0x5a00 Entry 30 (size 16 bundles) Unaligned Reference (57)
+ENTRY(kvm_unaligned_access)
+ KVM_REFLECT(30)
+END(kvm_unaligned_access)
+
+ .org kvm_ia64_ivt+0x5b00
+//////////////////////////////////////////////////////////////////////
+// 0x5b00 Entry 31 (size 16 bundles) Unsupported Data Reference (57)
+ENTRY(kvm_unsupported_data_reference)
+ KVM_REFLECT(31)
+END(kvm_unsupported_data_reference)
+
+ .org kvm_ia64_ivt+0x5c00
+////////////////////////////////////////////////////////////////////
+// 0x5c00 Entry 32 (size 16 bundles) Floating Point FAULT (65)
+ENTRY(kvm_floating_point_fault)
+ KVM_REFLECT(32)
+END(kvm_floating_point_fault)
+
+ .org kvm_ia64_ivt+0x5d00
+/////////////////////////////////////////////////////////////////////
+// 0x5d00 Entry 33 (size 16 bundles) Floating Point Trap (66)
+ENTRY(kvm_floating_point_trap)
+ KVM_REFLECT(33)
+END(kvm_floating_point_trap)
+
+ .org kvm_ia64_ivt+0x5e00
+//////////////////////////////////////////////////////////////////////
+// 0x5e00 Entry 34 (size 16 bundles) Lower Privilege Transfer Trap (66)
+ENTRY(kvm_lower_privilege_trap)
+ KVM_REFLECT(34)
+END(kvm_lower_privilege_trap)
+
+ .org kvm_ia64_ivt+0x5f00
+//////////////////////////////////////////////////////////////////////
+// 0x5f00 Entry 35 (size 16 bundles) Taken Branch Trap (68)
+ENTRY(kvm_taken_branch_trap)
+ KVM_REFLECT(35)
+END(kvm_taken_branch_trap)
+
+ .org kvm_ia64_ivt+0x6000
+////////////////////////////////////////////////////////////////////
+// 0x6000 Entry 36 (size 16 bundles) Single Step Trap (69)
+ENTRY(kvm_single_step_trap)
+ KVM_REFLECT(36)
+END(kvm_single_step_trap)
+ .global kvm_virtualization_fault_back
+ .org kvm_ia64_ivt+0x6100
+/////////////////////////////////////////////////////////////////////
+// 0x6100 Entry 37 (size 16 bundles) Virtualization Fault
+ENTRY(kvm_virtualization_fault)
+ mov r31=pr
+ adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+ ;;
+ st8 [r16] = r1
+ adds r17 = VMM_VCPU_GP_OFFSET, r21
+ ;;
+ ld8 r1 = [r17]
+ cmp.eq p6,p0=EVENT_MOV_FROM_AR,r24
+ cmp.eq p7,p0=EVENT_MOV_FROM_RR,r24
+ cmp.eq p8,p0=EVENT_MOV_TO_RR,r24
+ cmp.eq p9,p0=EVENT_RSM,r24
+ cmp.eq p10,p0=EVENT_SSM,r24
+ cmp.eq p11,p0=EVENT_MOV_TO_PSR,r24
+ cmp.eq p12,p0=EVENT_THASH,r24
+ (p6) br.dptk.many kvm_asm_mov_from_ar
+ (p7) br.dptk.many kvm_asm_mov_from_rr
+ (p8) br.dptk.many kvm_asm_mov_to_rr
+ (p9) br.dptk.many kvm_asm_rsm
+ (p10) br.dptk.many kvm_asm_ssm
+ (p11) br.dptk.many kvm_asm_mov_to_psr
+ (p12) br.dptk.many kvm_asm_thash
+ ;;
+kvm_virtualization_fault_back:
+ adds r16 = VMM_VCPU_SAVED_GP_OFFSET,r21
+ ;;
+ ld8 r1 = [r16]
+ ;;
+ mov r19=37
+ adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+ adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+ ;;
+ st8 [r16] = r24
+ st8 [r17] = r25
+ ;;
+ cmp.ne p6,p0=EVENT_RFI, r24
+ (p6) br.sptk kvm_dispatch_virtualization_fault
+ ;;
+ adds r18=VMM_VPD_BASE_OFFSET,r21
+ ;;
+ ld8 r18=[r18]
+ ;;
+ adds r18=VMM_VPD_VIFS_OFFSET,r18
+ ;;
+ ld8 r18=[r18]
+ ;;
+ tbit.z p6,p0=r18,63
+ (p6) br.sptk kvm_dispatch_virtualization_fault
+ ;;
+ //if vifs.v=1 desert current register frame
+ alloc r18=ar.pfs,0,0,0,0
+ br.sptk kvm_dispatch_virtualization_fault
+END(kvm_virtualization_fault)
+
+ .org kvm_ia64_ivt+0x6200
+//////////////////////////////////////////////////////////////
+// 0x6200 Entry 38 (size 16 bundles) Reserved
+ KVM_FAULT(38)
+
+ .org kvm_ia64_ivt+0x6300
+/////////////////////////////////////////////////////////////////
+// 0x6300 Entry 39 (size 16 bundles) Reserved
+ KVM_FAULT(39)
+
+ .org kvm_ia64_ivt+0x6400
+/////////////////////////////////////////////////////////////////
+// 0x6400 Entry 40 (size 16 bundles) Reserved
+ KVM_FAULT(40)
+
+ .org kvm_ia64_ivt+0x6500
+//////////////////////////////////////////////////////////////////
+// 0x6500 Entry 41 (size 16 bundles) Reserved
+ KVM_FAULT(41)
+
+ .org kvm_ia64_ivt+0x6600
+//////////////////////////////////////////////////////////////////
+// 0x6600 Entry 42 (size 16 bundles) Reserved
+ KVM_FAULT(42)
+
+ .org kvm_ia64_ivt+0x6700
+//////////////////////////////////////////////////////////////////
+// 0x6700 Entry 43 (size 16 bundles) Reserved
+ KVM_FAULT(43)
+
+ .org kvm_ia64_ivt+0x6800
+//////////////////////////////////////////////////////////////////
+// 0x6800 Entry 44 (size 16 bundles) Reserved
+ KVM_FAULT(44)
+
+ .org kvm_ia64_ivt+0x6900
+///////////////////////////////////////////////////////////////////
+// 0x6900 Entry 45 (size 16 bundles) IA-32 Exeception
+//(17,18,29,41,42,43,44,58,60,61,62,72,73,75,76,77)
+ENTRY(kvm_ia32_exception)
+ KVM_FAULT(45)
+END(kvm_ia32_exception)
+
+ .org kvm_ia64_ivt+0x6a00
+////////////////////////////////////////////////////////////////////
+// 0x6a00 Entry 46 (size 16 bundles) IA-32 Intercept (30,31,59,70,71)
+ENTRY(kvm_ia32_intercept)
+ KVM_FAULT(47)
+END(kvm_ia32_intercept)
+
+ .org kvm_ia64_ivt+0x6c00
+/////////////////////////////////////////////////////////////////////
+// 0x6c00 Entry 48 (size 16 bundles) Reserved
+ KVM_FAULT(48)
+
+ .org kvm_ia64_ivt+0x6d00
+//////////////////////////////////////////////////////////////////////
+// 0x6d00 Entry 49 (size 16 bundles) Reserved
+ KVM_FAULT(49)
+
+ .org kvm_ia64_ivt+0x6e00
+//////////////////////////////////////////////////////////////////////
+// 0x6e00 Entry 50 (size 16 bundles) Reserved
+ KVM_FAULT(50)
+
+ .org kvm_ia64_ivt+0x6f00
+/////////////////////////////////////////////////////////////////////
+// 0x6f00 Entry 51 (size 16 bundles) Reserved
+ KVM_FAULT(52)
+
+ .org kvm_ia64_ivt+0x7100
+////////////////////////////////////////////////////////////////////
+// 0x7100 Entry 53 (size 16 bundles) Reserved
+ KVM_FAULT(53)
+
+ .org kvm_ia64_ivt+0x7200
+/////////////////////////////////////////////////////////////////////
+// 0x7200 Entry 54 (size 16 bundles) Reserved
+ KVM_FAULT(54)
+
+ .org kvm_ia64_ivt+0x7300
+////////////////////////////////////////////////////////////////////
+// 0x7300 Entry 55 (size 16 bundles) Reserved
+ KVM_FAULT(55)
+
+ .org kvm_ia64_ivt+0x7400
+////////////////////////////////////////////////////////////////////
+// 0x7400 Entry 56 (size 16 bundles) Reserved
+ KVM_FAULT(56)
+
+ .org kvm_ia64_ivt+0x7500
+/////////////////////////////////////////////////////////////////////
+// 0x7500 Entry 57 (size 16 bundles) Reserved
+ KVM_FAULT(57)
+
+ .org kvm_ia64_ivt+0x7600
+/////////////////////////////////////////////////////////////////////
+// 0x7600 Entry 58 (size 16 bundles) Reserved
+ KVM_FAULT(58)
+
+ .org kvm_ia64_ivt+0x7700
+////////////////////////////////////////////////////////////////////
+// 0x7700 Entry 59 (size 16 bundles) Reserved
+ KVM_FAULT(59)
+
+ .org kvm_ia64_ivt+0x7800
+////////////////////////////////////////////////////////////////////
+// 0x7800 Entry 60 (size 16 bundles) Reserved
+ KVM_FAULT(60)
+
+ .org kvm_ia64_ivt+0x7900
+/////////////////////////////////////////////////////////////////////
+// 0x7900 Entry 61 (size 16 bundles) Reserved
+ KVM_FAULT(61)
+
+ .org kvm_ia64_ivt+0x7a00
+/////////////////////////////////////////////////////////////////////
+// 0x7a00 Entry 62 (size 16 bundles) Reserved
+ KVM_FAULT(62)
+
+ .org kvm_ia64_ivt+0x7b00
+/////////////////////////////////////////////////////////////////////
+// 0x7b00 Entry 63 (size 16 bundles) Reserved
+ KVM_FAULT(63)
+
+ .org kvm_ia64_ivt+0x7c00
+////////////////////////////////////////////////////////////////////
+// 0x7c00 Entry 64 (size 16 bundles) Reserved
+ KVM_FAULT(64)
+
+ .org kvm_ia64_ivt+0x7d00
+/////////////////////////////////////////////////////////////////////
+// 0x7d00 Entry 65 (size 16 bundles) Reserved
+ KVM_FAULT(65)
+
+ .org kvm_ia64_ivt+0x7e00
+/////////////////////////////////////////////////////////////////////
+// 0x7e00 Entry 66 (size 16 bundles) Reserved
+ KVM_FAULT(66)
+
+ .org kvm_ia64_ivt+0x7f00
+////////////////////////////////////////////////////////////////////
+// 0x7f00 Entry 67 (size 16 bundles) Reserved
+ KVM_FAULT(67)
+
+ .org kvm_ia64_ivt+0x8000
+// 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. If this
+// fault ever gets "unreserved", simply moved the following code to a more
+// suitable spot...
+
+
+ENTRY(kvm_dtlb_miss_dispatch)
+ mov r19 = 2
+ KVM_SAVE_MIN_WITH_COVER_R19
+ alloc r14=ar.pfs,0,0,3,0
+ mov out0=cr.ifa
+ mov out1=r15
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15) ssm psr.i // restore psr.i
+ addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+ ;;
+ KVM_SAVE_REST
+ KVM_SAVE_EXTRA
+ mov rp=r14
+ ;;
+ adds out2=16,r12
+ br.call.sptk.many b6=kvm_page_fault
+END(kvm_dtlb_miss_dispatch)
+
+ENTRY(kvm_itlb_miss_dispatch)
+
+ KVM_SAVE_MIN_WITH_COVER_R19
+ alloc r14=ar.pfs,0,0,3,0
+ mov out0=cr.ifa
+ mov out1=r15
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15) ssm psr.i // restore psr.i
+ addl r14=@gprel(ia64_leave_hypervisor),gp
+ ;;
+ KVM_SAVE_REST
+ mov rp=r14
+ ;;
+ adds out2=16,r12
+ br.call.sptk.many b6=kvm_page_fault
+END(kvm_itlb_miss_dispatch)
+
+ENTRY(kvm_dispatch_reflection)
+ /*
+ * Input:
+ * psr.ic: off
+ * r19: intr type (offset into ivt, see ia64_int.h)
+ * r31: contains saved predicates (pr)
+ */
+ KVM_SAVE_MIN_WITH_COVER_R19
+ alloc r14=ar.pfs,0,0,5,0
+ mov out0=cr.ifa
+ mov out1=cr.isr
+ mov out2=cr.iim
+ mov out3=r15
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15) ssm psr.i // restore psr.i
+ addl r14=@gprel(ia64_leave_hypervisor),gp
+ ;;
+ KVM_SAVE_REST
+ mov rp=r14
+ ;;
+ adds out4=16,r12
+ br.call.sptk.many b6=reflect_interruption
+END(kvm_dispatch_reflection)
+
+ENTRY(kvm_dispatch_virtualization_fault)
+ adds r16 = VMM_VCPU_CAUSE_OFFSET,r21
+ adds r17 = VMM_VCPU_OPCODE_OFFSET,r21
+ ;;
+ st8 [r16] = r24
+ st8 [r17] = r25
+ ;;
+ KVM_SAVE_MIN_WITH_COVER_R19
+ ;;
+ alloc r14=ar.pfs,0,0,2,0 // now it's safe (must be first in insn group!)
+ mov out0=r13 //vcpu
+ adds r3=8,r2 // set up second base pointer
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i // guarantee that interruption collection is on
+ ;;
+ //(p15) ssm psr.i // restore psr.i
+ addl r14=@gprel(ia64_leave_hypervisor_prepare),gp
+ ;;
+ KVM_SAVE_REST
+ KVM_SAVE_EXTRA
+ mov rp=r14
+ ;;
+ adds out1=16,sp //regs
+ br.call.sptk.many b6=kvm_emulate
+END(kvm_dispatch_virtualization_fault)
+
+
+ENTRY(kvm_dispatch_interrupt)
+ KVM_SAVE_MIN_WITH_COVER_R19 // uses r31; defines r2 and r3
+ ;;
+ alloc r14=ar.pfs,0,0,1,0 // must be first in an insn group
+ //mov out0=cr.ivr // pass cr.ivr as first arg
+ adds r3=8,r2 // set up second base pointer for SAVE_REST
+ ;;
+ ssm psr.ic
+ ;;
+ srlz.i
+ ;;
+ //(p15) ssm psr.i
+ addl r14=@gprel(ia64_leave_hypervisor),gp
+ ;;
+ KVM_SAVE_REST
+ mov rp=r14
+ ;;
+ mov out0=r13 // pass pointer to pt_regs as second arg
+ br.call.sptk.many b6=kvm_ia64_handle_irq
+END(kvm_dispatch_interrupt)
+
+
+
+
+GLOBAL_ENTRY(ia64_leave_nested)
+ rsm psr.i
+ ;;
+ adds r21=PT(PR)+16,r12
+ ;;
+ lfetch [r21],PT(CR_IPSR)-PT(PR)
+ adds r2=PT(B6)+16,r12
+ adds r3=PT(R16)+16,r12
+ ;;
+ lfetch [r21]
+ ld8 r28=[r2],8 // load b6
+ adds r29=PT(R24)+16,r12
+
+ ld8.fill r16=[r3]
+ adds r3=PT(AR_CSD)-PT(R16),r3
+ adds r30=PT(AR_CCV)+16,r12
+ ;;
+ ld8.fill r24=[r29]
+ ld8 r15=[r30] // load ar.ccv
+ ;;
+ ld8 r29=[r2],16 // load b7
+ ld8 r30=[r3],16 // load ar.csd
+ ;;
+ ld8 r31=[r2],16 // load ar.ssd
+ ld8.fill r8=[r3],16
+ ;;
+ ld8.fill r9=[r2],16
+ ld8.fill r10=[r3],PT(R17)-PT(R10)
+ ;;
+ ld8.fill r11=[r2],PT(R18)-PT(R11)
+ ld8.fill r17=[r3],16
+ ;;
+ ld8.fill r18=[r2],16
+ ld8.fill r19=[r3],16
+ ;;
+ ld8.fill r20=[r2],16
+ ld8.fill r21=[r3],16
+ mov ar.csd=r30
+ mov ar.ssd=r31
+ ;;
+ rsm psr.i | psr.ic
+ // initiate turning off of interrupt and interruption collection
+ invala // invalidate ALAT
+ ;;
+ srlz.i
+ ;;
+ ld8.fill r22=[r2],24
+ ld8.fill r23=[r3],24
+ mov b6=r28
+ ;;
+ ld8.fill r25=[r2],16
+ ld8.fill r26=[r3],16
+ mov b7=r29
+ ;;
+ ld8.fill r27=[r2],16
+ ld8.fill r28=[r3],16
+ ;;
+ ld8.fill r29=[r2],16
+ ld8.fill r30=[r3],24
+ ;;
+ ld8.fill r31=[r2],PT(F9)-PT(R31)
+ adds r3=PT(F10)-PT(F6),r3
+ ;;
+ ldf.fill f9=[r2],PT(F6)-PT(F9)
+ ldf.fill f10=[r3],PT(F8)-PT(F10)
+ ;;
+ ldf.fill f6=[r2],PT(F7)-PT(F6)
+ ;;
+ ldf.fill f7=[r2],PT(F11)-PT(F7)
+ ldf.fill f8=[r3],32
+ ;;
+ srlz.i // ensure interruption collection is off
+ mov ar.ccv=r15
+ ;;
+ bsw.0 // switch back to bank 0 (no stop bit required beforehand...)
+ ;;
+ ldf.fill f11=[r2]
+// mov r18=r13
+// mov r21=r13
+ adds r16=PT(CR_IPSR)+16,r12
+ adds r17=PT(CR_IIP)+16,r12
+ ;;
+ ld8 r29=[r16],16 // load cr.ipsr
+ ld8 r28=[r17],16 // load cr.iip
+ ;;
+ ld8 r30=[r16],16 // load cr.ifs
+ ld8 r25=[r17],16 // load ar.unat
+ ;;
+ ld8 r26=[r16],16 // load ar.pfs
+ ld8 r27=[r17],16 // load ar.rsc
+ cmp.eq p9,p0=r0,r0
+ // set p9 to indicate that we should restore cr.ifs
+ ;;
+ ld8 r24=[r16],16 // load ar.rnat (may be garbage)
+ ld8 r23=[r17],16// load ar.bspstore (may be garbage)
+ ;;
+ ld8 r31=[r16],16 // load predicates
+ ld8 r22=[r17],16 // load b0
+ ;;
+ ld8 r19=[r16],16 // load ar.rsc value for "loadrs"
+ ld8.fill r1=[r17],16 // load r1
+ ;;
+ ld8.fill r12=[r16],16
+ ld8.fill r13=[r17],16
+ ;;
+ ld8 r20=[r16],16 // ar.fpsr
+ ld8.fill r15=[r17],16
+ ;;
+ ld8.fill r14=[r16],16
+ ld8.fill r2=[r17]
+ ;;
+ ld8.fill r3=[r16]
+ ;;
+ mov r16=ar.bsp // get existing backing store pointer
+ ;;
+ mov b0=r22
+ mov ar.pfs=r26
+ mov cr.ifs=r30
+ mov cr.ipsr=r29
+ mov ar.fpsr=r20
+ mov cr.iip=r28
+ ;;
+ mov ar.rsc=r27
+ mov ar.unat=r25
+ mov pr=r31,-1
+ rfi
+END(ia64_leave_nested)
+
+
+
+GLOBAL_ENTRY(ia64_leave_hypervisor_prepare)
+ /*
+ * work.need_resched etc. mustn't get changed
+ *by this CPU before it returns to
+ ;;
+ * user- or fsys-mode, hence we disable interrupts early on:
+ */
+ adds r2 = PT(R4)+16,r12
+ adds r3 = PT(R5)+16,r12
+ adds r8 = PT(EML_UNAT)+16,r12
+ ;;
+ ld8 r8 = [r8]
+ ;;
+ mov ar.unat=r8
+ ;;
+ ld8.fill r4=[r2],16 //load r4
+ ld8.fill r5=[r3],16 //load r5
+ ;;
+ ld8.fill r6=[r2] //load r6
+ ld8.fill r7=[r3] //load r7
+ ;;
+END(ia64_leave_hypervisor_prepare)
+//fall through
+GLOBAL_ENTRY(ia64_leave_hypervisor)
+ rsm psr.i
+ ;;
+ br.call.sptk.many b0=leave_hypervisor_tail
+ ;;
+ adds r20=PT(PR)+16,r12
+ adds r8=PT(EML_UNAT)+16,r12
+ ;;
+ ld8 r8=[r8]
+ ;;
+ mov ar.unat=r8
+ ;;
+ lfetch [r20],PT(CR_IPSR)-PT(PR)
+ adds r2 = PT(B6)+16,r12
+ adds r3 = PT(B7)+16,r12
+ ;;
+ lfetch [r20]
+ ;;
+ ld8 r24=[r2],16 /* B6 */
+ ld8 r25=[r3],16 /* B7 */
+ ;;
+ ld8 r26=[r2],16 /* ar_csd */
+ ld8 r27=[r3],16 /* ar_ssd */
+ mov b6 = r24
+ ;;
+ ld8.fill r8=[r2],16
+ ld8.fill r9=[r3],16
+ mov b7 = r25
+ ;;
+ mov ar.csd = r26
+ mov ar.ssd = r27
+ ;;
+ ld8.fill r10=[r2],PT(R15)-PT(R10)
+ ld8.fill r11=[r3],PT(R14)-PT(R11)
+ ;;
+ ld8.fill r15=[r2],PT(R16)-PT(R15)
+ ld8.fill r14=[r3],PT(R17)-PT(R14)
+ ;;
+ ld8.fill r16=[r2],16
+ ld8.fill r17=[r3],16
+ ;;
+ ld8.fill r18=[r2],16
+ ld8.fill r19=[r3],16
+ ;;
+ ld8.fill r20=[r2],16
+ ld8.fill r21=[r3],16
+ ;;
+ ld8.fill r22=[r2],16
+ ld8.fill r23=[r3],16
+ ;;
+ ld8.fill r24=[r2],16
+ ld8.fill r25=[r3],16
+ ;;
+ ld8.fill r26=[r2],16
+ ld8.fill r27=[r3],16
+ ;;
+ ld8.fill r28=[r2],16
+ ld8.fill r29=[r3],16
+ ;;
+ ld8.fill r30=[r2],PT(F6)-PT(R30)
+ ld8.fill r31=[r3],PT(F7)-PT(R31)
+ ;;
+ rsm psr.i | psr.ic
+ // initiate turning off of interrupt and interruption collection
+ invala // invalidate ALAT
+ ;;
+ srlz.i // ensure interruption collection is off
+ ;;
+ bsw.0
+ ;;
+ adds r16 = PT(CR_IPSR)+16,r12
+ adds r17 = PT(CR_IIP)+16,r12
+ mov r21=r13 // get current
+ ;;
+ ld8 r31=[r16],16 // load cr.ipsr
+ ld8 r30=[r17],16 // load cr.iip
+ ;;
+ ld8 r29=[r16],16 // load cr.ifs
+ ld8 r28=[r17],16 // load ar.unat
+ ;;
+ ld8 r27=[r16],16 // load ar.pfs
+ ld8 r26=[r17],16 // load ar.rsc
+ ;;
+ ld8 r25=[r16],16 // load ar.rnat
+ ld8 r24=[r17],16 // load ar.bspstore
+ ;;
+ ld8 r23=[r16],16 // load predicates
+ ld8 r22=[r17],16 // load b0
+ ;;
+ ld8 r20=[r16],16 // load ar.rsc value for "loadrs"
+ ld8.fill r1=[r17],16 //load r1
+ ;;
+ ld8.fill r12=[r16],16 //load r12
+ ld8.fill r13=[r17],PT(R2)-PT(R13) //load r13
+ ;;
+ ld8 r19=[r16],PT(R3)-PT(AR_FPSR) //load ar_fpsr
+ ld8.fill r2=[r17],PT(AR_CCV)-PT(R2) //load r2
+ ;;
+ ld8.fill r3=[r16] //load r3
+ ld8 r18=[r17] //load ar_ccv
+ ;;
+ mov ar.fpsr=r19
+ mov ar.ccv=r18
+ shr.u r18=r20,16
+ ;;
+kvm_rbs_switch:
+ mov r19=96
+
+kvm_dont_preserve_current_frame:
+/*
+ * To prevent leaking bits between the hypervisor and guest domain,
+ * we must clear the stacked registers in the "invalid" partition here.
+ * 5 registers/cycle on McKinley).
+ */
+# define pRecurse p6
+# define pReturn p7
+# define Nregs 14
+
+ alloc loc0=ar.pfs,2,Nregs-2,2,0
+ shr.u loc1=r18,9 // RNaTslots <= floor(dirtySize / (64*8))
+ sub r19=r19,r18 // r19 = (physStackedSize + 8) - dirtySize
+ ;;
+ mov ar.rsc=r20 // load ar.rsc to be used for "loadrs"
+ shladd in0=loc1,3,r19
+ mov in1=0
+ ;;
+ TEXT_ALIGN(32)
+kvm_rse_clear_invalid:
+ alloc loc0=ar.pfs,2,Nregs-2,2,0
+ cmp.lt pRecurse,p0=Nregs*8,in0
+ // if more than Nregs regs left to clear, (re)curse
+ add out0=-Nregs*8,in0
+ add out1=1,in1 // increment recursion count
+ mov loc1=0
+ mov loc2=0
+ ;;
+ mov loc3=0
+ mov loc4=0
+ mov loc5=0
+ mov loc6=0
+ mov loc7=0
+(pRecurse) br.call.dptk.few b0=kvm_rse_clear_invalid
+ ;;
+ mov loc8=0
+ mov loc9=0
+ cmp.ne pReturn,p0=r0,in1
+ // if recursion count != 0, we need to do a br.ret
+ mov loc10=0
+ mov loc11=0
+(pReturn) br.ret.dptk.many b0
+
+# undef pRecurse
+# undef pReturn
+
+// loadrs has already been shifted
+ alloc r16=ar.pfs,0,0,0,0 // drop current register frame
+ ;;
+ loadrs
+ ;;
+ mov ar.bspstore=r24
+ ;;
+ mov ar.unat=r28
+ mov ar.rnat=r25
+ mov ar.rsc=r26
+ ;;
+ mov cr.ipsr=r31
+ mov cr.iip=r30
+ mov cr.ifs=r29
+ mov ar.pfs=r27
+ adds r18=VMM_VPD_BASE_OFFSET,r21
+ ;;
+ ld8 r18=[r18] //vpd
+ adds r17=VMM_VCPU_ISR_OFFSET,r21
+ ;;
+ ld8 r17=[r17]
+ adds r19=VMM_VPD_VPSR_OFFSET,r18
+ ;;
+ ld8 r19=[r19] //vpsr
+ adds r20=VMM_VCPU_VSA_BASE_OFFSET,r21
+ ;;
+ ld8 r20=[r20]
+ ;;
+//vsa_sync_write_start
+ mov r25=r18
+ adds r16= VMM_VCPU_GP_OFFSET,r21
+ ;;
+ ld8 r16= [r16] // Put gp in r24
+ movl r24=@gprel(ia64_vmm_entry) // calculate return address
+ ;;
+ add r24=r24,r16
+ ;;
+ add r16=PAL_VPS_SYNC_WRITE,r20
+ ;;
+ mov b0=r16
+ br.cond.sptk b0 // call the service
+ ;;
+END(ia64_leave_hypervisor)
+// fall through
+GLOBAL_ENTRY(ia64_vmm_entry)
+/*
+ * must be at bank 0
+ * parameter:
+ * r17:cr.isr
+ * r18:vpd
+ * r19:vpsr
+ * r20:__vsa_base
+ * r22:b0
+ * r23:predicate
+ */
+ mov r24=r22
+ mov r25=r18
+ tbit.nz p1,p2 = r19,IA64_PSR_IC_BIT // p1=vpsr.ic
+ ;;
+ (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+ (p1) br.sptk.many ia64_vmm_entry_out
+ ;;
+ tbit.nz p1,p2 = r17,IA64_ISR_IR_BIT //p1=cr.isr.ir
+ ;;
+ (p1) add r29=PAL_VPS_RESUME_NORMAL,r20
+ (p2) add r29=PAL_VPS_RESUME_HANDLER,r20
+ (p2) ld8 r26=[r25]
+ ;;
+ia64_vmm_entry_out:
+ mov pr=r23,-2
+ mov b0=r29
+ ;;
+ br.cond.sptk b0 // call pal service
+END(ia64_vmm_entry)
+
+
+
+/*
+ * extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2,
+ * u64 arg3, u64 arg4, u64 arg5,
+ * u64 arg6, u64 arg7);
+ *
+ * XXX: The currently defined services use only 4 args at the max. The
+ * rest are not consumed.
+ */
+GLOBAL_ENTRY(ia64_call_vsa)
+ .regstk 4,4,0,0
+
+rpsave = loc0
+pfssave = loc1
+psrsave = loc2
+entry = loc3
+hostret = r24
+
+ alloc pfssave=ar.pfs,4,4,0,0
+ mov rpsave=rp
+ adds entry=VMM_VCPU_VSA_BASE_OFFSET, r13
+ ;;
+ ld8 entry=[entry]
+1: mov hostret=ip
+ mov r25=in1 // copy arguments
+ mov r26=in2
+ mov r27=in3
+ mov psrsave=psr
+ ;;
+ tbit.nz p6,p0=psrsave,14 // IA64_PSR_I
+ tbit.nz p7,p0=psrsave,13 // IA64_PSR_IC
+ ;;
+ add hostret=2f-1b,hostret // calculate return address
+ add entry=entry,in0
+ ;;
+ rsm psr.i | psr.ic
+ ;;
+ srlz.i
+ mov b6=entry
+ br.cond.sptk b6 // call the service
+2:
+ // Architectural sequence for enabling interrupts if necessary
+(p7) ssm psr.ic
+ ;;
+(p7) srlz.i
+ ;;
+//(p6) ssm psr.i
+ ;;
+ mov rp=rpsave
+ mov ar.pfs=pfssave
+ mov r8=r31
+ ;;
+ srlz.d
+ br.ret.sptk rp
+
+END(ia64_call_vsa)
+
+#define INIT_BSPSTORE ((4<<30)-(12<<20)-0x100)
+
+GLOBAL_ENTRY(vmm_reset_entry)
+ //set up ipsr, iip, vpd.vpsr, dcr
+ // For IPSR: it/dt/rt=1, i/ic=1, si=1, vm/bn=1
+ // For DCR: all bits 0
+ adds r14=-VMM_PT_REGS_SIZE, r12
+ ;;
+ movl r6=0x501008826000 // IPSR dt/rt/it:1;i/ic:1, si:1, vm/bn:1
+ movl r10=0x8000000000000000
+ adds r16=PT(CR_IIP), r14
+ adds r20=PT(R1), r14
+ ;;
+ rsm psr.ic | psr.i
+ ;;
+ srlz.i
+ ;;
+ bsw.0
+ ;;
+ mov r21 =r13
+ ;;
+ bsw.1
+ ;;
+ mov ar.rsc = 0
+ ;;
+ flushrs
+ ;;
+ mov ar.bspstore = 0
+ // clear BSPSTORE
+ ;;
+ mov cr.ipsr=r6
+ mov cr.ifs=r10
+ ld8 r4 = [r16] // Set init iip for first run.
+ ld8 r1 = [r20]
+ ;;
+ mov cr.iip=r4
+ ;;
+ adds r16=VMM_VPD_BASE_OFFSET,r13
+ adds r20=VMM_VCPU_VSA_BASE_OFFSET,r13
+ ;;
+ ld8 r18=[r16]
+ ld8 r20=[r20]
+ ;;
+ adds r19=VMM_VPD_VPSR_OFFSET,r18
+ ;;
+ ld8 r19=[r19]
+ mov r17=r0
+ mov r22=r0
+ mov r23=r0
+ br.cond.sptk ia64_vmm_entry
+ br.ret.sptk b0
+END(vmm_reset_entry)
diff --git a/arch/ia64/kvm/vti.h b/arch/ia64/kvm/vti.h
new file mode 100644
index 00000000000..f6c5617e16a
--- /dev/null
+++ b/arch/ia64/kvm/vti.h
@@ -0,0 +1,290 @@
+/*
+ * vti.h: prototype for generial vt related interface
+ * Copyright (c) 2004, Intel Corporation.
+ *
+ * Xuefei Xu (Anthony Xu) (anthony.xu@intel.com)
+ * Fred Yang (fred.yang@intel.com)
+ * Kun Tian (Kevin Tian) (kevin.tian@intel.com)
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ * Zhang xiantao <xiantao.zhang@intel.com>
+ *
+ * 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.
+ *
+ * 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 _KVM_VT_I_H
+#define _KVM_VT_I_H
+
+#ifndef __ASSEMBLY__
+#include <asm/page.h>
+
+#include <linux/kvm_host.h>
+
+/* define itr.i and itr.d in ia64_itr function */
+#define ITR 0x01
+#define DTR 0x02
+#define IaDTR 0x03
+
+#define IA64_TR_VMM 6 /*itr6, dtr6 : maps vmm code, vmbuffer*/
+#define IA64_TR_VM_DATA 7 /*dtr7 : maps current vm data*/
+
+#define RR6 (6UL<<61)
+#define RR7 (7UL<<61)
+
+
+/* config_options in pal_vp_init_env */
+#define VP_INITIALIZE 1UL
+#define VP_FR_PMC 1UL<<1
+#define VP_OPCODE 1UL<<8
+#define VP_CAUSE 1UL<<9
+#define VP_FW_ACC 1UL<<63
+
+/* init vp env with initializing vm_buffer */
+#define VP_INIT_ENV_INITALIZE (VP_INITIALIZE | VP_FR_PMC |\
+ VP_OPCODE | VP_CAUSE | VP_FW_ACC)
+/* init vp env without initializing vm_buffer */
+#define VP_INIT_ENV VP_FR_PMC | VP_OPCODE | VP_CAUSE | VP_FW_ACC
+
+#define PAL_VP_CREATE 265
+/* Stacked Virt. Initializes a new VPD for the operation of
+ * a new virtual processor in the virtual environment.
+ */
+#define PAL_VP_ENV_INFO 266
+/*Stacked Virt. Returns the parameters needed to enter a virtual environment.*/
+#define PAL_VP_EXIT_ENV 267
+/*Stacked Virt. Allows a logical processor to exit a virtual environment.*/
+#define PAL_VP_INIT_ENV 268
+/*Stacked Virt. Allows a logical processor to enter a virtual environment.*/
+#define PAL_VP_REGISTER 269
+/*Stacked Virt. Register a different host IVT for the virtual processor.*/
+#define PAL_VP_RESUME 270
+/* Renamed from PAL_VP_RESUME */
+#define PAL_VP_RESTORE 270
+/*Stacked Virt. Resumes virtual processor operation on the logical processor.*/
+#define PAL_VP_SUSPEND 271
+/* Renamed from PAL_VP_SUSPEND */
+#define PAL_VP_SAVE 271
+/* Stacked Virt. Suspends operation for the specified virtual processor on
+ * the logical processor.
+ */
+#define PAL_VP_TERMINATE 272
+/* Stacked Virt. Terminates operation for the specified virtual processor.*/
+
+union vac {
+ unsigned long value;
+ struct {
+ int a_int:1;
+ int a_from_int_cr:1;
+ int a_to_int_cr:1;
+ int a_from_psr:1;
+ int a_from_cpuid:1;
+ int a_cover:1;
+ int a_bsw:1;
+ long reserved:57;
+ };
+};
+
+union vdc {
+ unsigned long value;
+ struct {
+ int d_vmsw:1;
+ int d_extint:1;
+ int d_ibr_dbr:1;
+ int d_pmc:1;
+ int d_to_pmd:1;
+ int d_itm:1;
+ long reserved:58;
+ };
+};
+
+struct vpd {
+ union vac vac;
+ union vdc vdc;
+ unsigned long virt_env_vaddr;
+ unsigned long reserved1[29];
+ unsigned long vhpi;
+ unsigned long reserved2[95];
+ unsigned long vgr[16];
+ unsigned long vbgr[16];
+ unsigned long vnat;
+ unsigned long vbnat;
+ unsigned long vcpuid[5];
+ unsigned long reserved3[11];
+ unsigned long vpsr;
+ unsigned long vpr;
+ unsigned long reserved4[76];
+ union {
+ unsigned long vcr[128];
+ struct {
+ unsigned long dcr;
+ unsigned long itm;
+ unsigned long iva;
+ unsigned long rsv1[5];
+ unsigned long pta;
+ unsigned long rsv2[7];
+ unsigned long ipsr;
+ unsigned long isr;
+ unsigned long rsv3;
+ unsigned long iip;
+ unsigned long ifa;
+ unsigned long itir;
+ unsigned long iipa;
+ unsigned long ifs;
+ unsigned long iim;
+ unsigned long iha;
+ unsigned long rsv4[38];
+ unsigned long lid;
+ unsigned long ivr;
+ unsigned long tpr;
+ unsigned long eoi;
+ unsigned long irr[4];
+ unsigned long itv;
+ unsigned long pmv;
+ unsigned long cmcv;
+ unsigned long rsv5[5];
+ unsigned long lrr0;
+ unsigned long lrr1;
+ unsigned long rsv6[46];
+ };
+ };
+ unsigned long reserved5[128];
+ unsigned long reserved6[3456];
+ unsigned long vmm_avail[128];
+ unsigned long reserved7[4096];
+};
+
+#define PAL_PROC_VM_BIT (1UL << 40)
+#define PAL_PROC_VMSW_BIT (1UL << 54)
+
+static inline s64 ia64_pal_vp_env_info(u64 *buffer_size,
+ u64 *vp_env_info)
+{
+ struct ia64_pal_retval iprv;
+ PAL_CALL_STK(iprv, PAL_VP_ENV_INFO, 0, 0, 0);
+ *buffer_size = iprv.v0;
+ *vp_env_info = iprv.v1;
+ return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_exit_env(u64 iva)
+{
+ struct ia64_pal_retval iprv;
+
+ PAL_CALL_STK(iprv, PAL_VP_EXIT_ENV, (u64)iva, 0, 0);
+ return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_init_env(u64 config_options, u64 pbase_addr,
+ u64 vbase_addr, u64 *vsa_base)
+{
+ struct ia64_pal_retval iprv;
+
+ PAL_CALL_STK(iprv, PAL_VP_INIT_ENV, config_options, pbase_addr,
+ vbase_addr);
+ *vsa_base = iprv.v0;
+
+ return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_restore(u64 *vpd, u64 pal_proc_vector)
+{
+ struct ia64_pal_retval iprv;
+
+ PAL_CALL_STK(iprv, PAL_VP_RESTORE, (u64)vpd, pal_proc_vector, 0);
+
+ return iprv.status;
+}
+
+static inline s64 ia64_pal_vp_save(u64 *vpd, u64 pal_proc_vector)
+{
+ struct ia64_pal_retval iprv;
+
+ PAL_CALL_STK(iprv, PAL_VP_SAVE, (u64)vpd, pal_proc_vector, 0);
+
+ return iprv.status;
+}
+
+#endif
+
+/*VPD field offset*/
+#define VPD_VAC_START_OFFSET 0
+#define VPD_VDC_START_OFFSET 8
+#define VPD_VHPI_START_OFFSET 256
+#define VPD_VGR_START_OFFSET 1024
+#define VPD_VBGR_START_OFFSET 1152
+#define VPD_VNAT_START_OFFSET 1280
+#define VPD_VBNAT_START_OFFSET 1288
+#define VPD_VCPUID_START_OFFSET 1296
+#define VPD_VPSR_START_OFFSET 1424
+#define VPD_VPR_START_OFFSET 1432
+#define VPD_VRSE_CFLE_START_OFFSET 1440
+#define VPD_VCR_START_OFFSET 2048
+#define VPD_VTPR_START_OFFSET 2576
+#define VPD_VRR_START_OFFSET 3072
+#define VPD_VMM_VAIL_START_OFFSET 31744
+
+/*Virtualization faults*/
+
+#define EVENT_MOV_TO_AR 1
+#define EVENT_MOV_TO_AR_IMM 2
+#define EVENT_MOV_FROM_AR 3
+#define EVENT_MOV_TO_CR 4
+#define EVENT_MOV_FROM_CR 5
+#define EVENT_MOV_TO_PSR 6
+#define EVENT_MOV_FROM_PSR 7
+#define EVENT_ITC_D 8
+#define EVENT_ITC_I 9
+#define EVENT_MOV_TO_RR 10
+#define EVENT_MOV_TO_DBR 11
+#define EVENT_MOV_TO_IBR 12
+#define EVENT_MOV_TO_PKR 13
+#define EVENT_MOV_TO_PMC 14
+#define EVENT_MOV_TO_PMD 15
+#define EVENT_ITR_D 16
+#define EVENT_ITR_I 17
+#define EVENT_MOV_FROM_RR 18
+#define EVENT_MOV_FROM_DBR 19
+#define EVENT_MOV_FROM_IBR 20
+#define EVENT_MOV_FROM_PKR 21
+#define EVENT_MOV_FROM_PMC 22
+#define EVENT_MOV_FROM_CPUID 23
+#define EVENT_SSM 24
+#define EVENT_RSM 25
+#define EVENT_PTC_L 26
+#define EVENT_PTC_G 27
+#define EVENT_PTC_GA 28
+#define EVENT_PTR_D 29
+#define EVENT_PTR_I 30
+#define EVENT_THASH 31
+#define EVENT_TTAG 32
+#define EVENT_TPA 33
+#define EVENT_TAK 34
+#define EVENT_PTC_E 35
+#define EVENT_COVER 36
+#define EVENT_RFI 37
+#define EVENT_BSW_0 38
+#define EVENT_BSW_1 39
+#define EVENT_VMSW 40
+
+/**PAL virtual services offsets */
+#define PAL_VPS_RESUME_NORMAL 0x0000
+#define PAL_VPS_RESUME_HANDLER 0x0400
+#define PAL_VPS_SYNC_READ 0x0800
+#define PAL_VPS_SYNC_WRITE 0x0c00
+#define PAL_VPS_SET_PENDING_INTERRUPT 0x1000
+#define PAL_VPS_THASH 0x1400
+#define PAL_VPS_TTAG 0x1800
+#define PAL_VPS_RESTORE 0x1c00
+#define PAL_VPS_SAVE 0x2000
+
+#endif/* _VT_I_H*/
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
new file mode 100644
index 00000000000..def4576d22b
--- /dev/null
+++ b/arch/ia64/kvm/vtlb.c
@@ -0,0 +1,636 @@
+/*
+ * vtlb.c: guest virtual tlb handling module.
+ * Copyright (c) 2004, Intel Corporation.
+ * Yaozu Dong (Eddie Dong) <Eddie.dong@intel.com>
+ * Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ *
+ * Copyright (c) 2007, Intel Corporation.
+ * Xuefei Xu (Anthony Xu) <anthony.xu@intel.com>
+ * Xiantao Zhang <xiantao.zhang@intel.com>
+ *
+ * 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.
+ *
+ * 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 "vcpu.h"
+
+#include <linux/rwsem.h>
+
+#include <asm/tlb.h>
+
+/*
+ * Check to see if the address rid:va is translated by the TLB
+ */
+
+static int __is_tr_translated(struct thash_data *trp, u64 rid, u64 va)
+{
+ return ((trp->p) && (trp->rid == rid)
+ && ((va-trp->vadr) < PSIZE(trp->ps)));
+}
+
+/*
+ * Only for GUEST TR format.
+ */
+static int __is_tr_overlap(struct thash_data *trp, u64 rid, u64 sva, u64 eva)
+{
+ u64 sa1, ea1;
+
+ if (!trp->p || trp->rid != rid)
+ return 0;
+
+ sa1 = trp->vadr;
+ ea1 = sa1 + PSIZE(trp->ps) - 1;
+ eva -= 1;
+ if ((sva > ea1) || (sa1 > eva))
+ return 0;
+ else
+ return 1;
+
+}
+
+void machine_tlb_purge(u64 va, u64 ps)
+{
+ ia64_ptcl(va, ps << 2);
+}
+
+void local_flush_tlb_all(void)
+{
+ int i, j;
+ unsigned long flags, count0, count1;
+ unsigned long stride0, stride1, addr;
+
+ addr = current_vcpu->arch.ptce_base;
+ count0 = current_vcpu->arch.ptce_count[0];
+ count1 = current_vcpu->arch.ptce_count[1];
+ stride0 = current_vcpu->arch.ptce_stride[0];
+ stride1 = current_vcpu->arch.ptce_stride[1];
+
+ local_irq_save(flags);
+ for (i = 0; i < count0; ++i) {
+ for (j = 0; j < count1; ++j) {
+ ia64_ptce(addr);
+ addr += stride1;
+ }
+ addr += stride0;
+ }
+ local_irq_restore(flags);
+ ia64_srlz_i(); /* srlz.i implies srlz.d */
+}
+
+int vhpt_enabled(struct kvm_vcpu *vcpu, u64 vadr, enum vhpt_ref ref)
+{
+ union ia64_rr vrr;
+ union ia64_pta vpta;
+ struct ia64_psr vpsr;
+
+ vpsr = *(struct ia64_psr *)&VCPU(vcpu, vpsr);
+ vrr.val = vcpu_get_rr(vcpu, vadr);
+ vpta.val = vcpu_get_pta(vcpu);
+
+ if (vrr.ve & vpta.ve) {
+ switch (ref) {
+ case DATA_REF:
+ case NA_REF:
+ return vpsr.dt;
+ case INST_REF:
+ return vpsr.dt && vpsr.it && vpsr.ic;
+ case RSE_REF:
+ return vpsr.dt && vpsr.rt;
+
+ }
+ }
+ return 0;
+}
+
+struct thash_data *vsa_thash(union ia64_pta vpta, u64 va, u64 vrr, u64 *tag)
+{
+ u64 index, pfn, rid, pfn_bits;
+
+ pfn_bits = vpta.size - 5 - 8;
+ pfn = REGION_OFFSET(va) >> _REGION_PAGE_SIZE(vrr);
+ rid = _REGION_ID(vrr);
+ index = ((rid & 0xff) << pfn_bits)|(pfn & ((1UL << pfn_bits) - 1));
+ *tag = ((rid >> 8) & 0xffff) | ((pfn >> pfn_bits) << 16);
+
+ return (struct thash_data *)((vpta.base << PTA_BASE_SHIFT) +
+ (index << 5));
+}
+
+struct thash_data *__vtr_lookup(struct kvm_vcpu *vcpu, u64 va, int type)
+{
+
+ struct thash_data *trp;
+ int i;
+ u64 rid;
+
+ rid = vcpu_get_rr(vcpu, va);
+ rid = rid & RR_RID_MASK;;
+ if (type == D_TLB) {
+ if (vcpu_quick_region_check(vcpu->arch.dtr_regions, va)) {
+ for (trp = (struct thash_data *)&vcpu->arch.dtrs, i = 0;
+ i < NDTRS; i++, trp++) {
+ if (__is_tr_translated(trp, rid, va))
+ return trp;
+ }
+ }
+ } else {
+ if (vcpu_quick_region_check(vcpu->arch.itr_regions, va)) {
+ for (trp = (struct thash_data *)&vcpu->arch.itrs, i = 0;
+ i < NITRS; i++, trp++) {
+ if (__is_tr_translated(trp, rid, va))
+ return trp;
+ }
+ }
+ }
+
+ return NULL;
+}
+
+static void vhpt_insert(u64 pte, u64 itir, u64 ifa, u64 gpte)
+{
+ union ia64_rr rr;
+ struct thash_data *head;
+ unsigned long ps, gpaddr;
+
+ ps = itir_ps(itir);
+
+ gpaddr = ((gpte & _PAGE_PPN_MASK) >> ps << ps) |
+ (ifa & ((1UL << ps) - 1));
+
+ rr.val = ia64_get_rr(ifa);
+ head = (struct thash_data *)ia64_thash(ifa);
+ head->etag = INVALID_TI_TAG;
+ ia64_mf();
+ head->page_flags = pte & ~PAGE_FLAGS_RV_MASK;
+ head->itir = rr.ps << 2;
+ head->etag = ia64_ttag(ifa);
+ head->gpaddr = gpaddr;
+}
+
+void mark_pages_dirty(struct kvm_vcpu *v, u64 pte, u64 ps)
+{
+ u64 i, dirty_pages = 1;
+ u64 base_gfn = (pte&_PAGE_PPN_MASK) >> PAGE_SHIFT;
+ spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
+ void *dirty_bitmap = (void *)v - (KVM_VCPU_OFS + v->vcpu_id * VCPU_SIZE)
+ + KVM_MEM_DIRTY_LOG_OFS;
+ dirty_pages <<= ps <= PAGE_SHIFT ? 0 : ps - PAGE_SHIFT;
+
+ vmm_spin_lock(lock);
+ for (i = 0; i < dirty_pages; i++) {
+ /* avoid RMW */
+ if (!test_bit(base_gfn + i, dirty_bitmap))
+ set_bit(base_gfn + i , dirty_bitmap);
+ }
+ vmm_spin_unlock(lock);
+}
+
+void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte, u64 itir, u64 va, int type)
+{
+ u64 phy_pte, psr;
+ union ia64_rr mrr;
+
+ mrr.val = ia64_get_rr(va);
+ phy_pte = translate_phy_pte(&pte, itir, va);
+
+ if (itir_ps(itir) >= mrr.ps) {
+ vhpt_insert(phy_pte, itir, va, pte);
+ } else {
+ phy_pte &= ~PAGE_FLAGS_RV_MASK;
+ psr = ia64_clear_ic();
+ ia64_itc(type, va, phy_pte, itir_ps(itir));
+ ia64_set_psr(psr);
+ }
+
+ if (!(pte&VTLB_PTE_IO))
+ mark_pages_dirty(v, pte, itir_ps(itir));
+}
+
+/*
+ * vhpt lookup
+ */
+struct thash_data *vhpt_lookup(u64 va)
+{
+ struct thash_data *head;
+ u64 tag;
+
+ head = (struct thash_data *)ia64_thash(va);
+ tag = ia64_ttag(va);
+ if (head->etag == tag)
+ return head;
+ return NULL;
+}
+
+u64 guest_vhpt_lookup(u64 iha, u64 *pte)
+{
+ u64 ret;
+ struct thash_data *data;
+
+ data = __vtr_lookup(current_vcpu, iha, D_TLB);
+ if (data != NULL)
+ thash_vhpt_insert(current_vcpu, data->page_flags,
+ data->itir, iha, D_TLB);
+
+ asm volatile ("rsm psr.ic|psr.i;;"
+ "srlz.d;;"
+ "ld8.s r9=[%1];;"
+ "tnat.nz p6,p7=r9;;"
+ "(p6) mov %0=1;"
+ "(p6) mov r9=r0;"
+ "(p7) extr.u r9=r9,0,53;;"
+ "(p7) mov %0=r0;"
+ "(p7) st8 [%2]=r9;;"
+ "ssm psr.ic;;"
+ "srlz.d;;"
+ /* "ssm psr.i;;" Once interrupts in vmm open, need fix*/
+ : "=r"(ret) : "r"(iha), "r"(pte):"memory");
+
+ return ret;
+}
+
+/*
+ * purge software guest tlb
+ */
+
+static void vtlb_purge(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+ struct thash_data *cur;
+ u64 start, curadr, size, psbits, tag, rr_ps, num;
+ union ia64_rr vrr;
+ struct thash_cb *hcb = &v->arch.vtlb;
+
+ vrr.val = vcpu_get_rr(v, va);
+ psbits = VMX(v, psbits[(va >> 61)]);
+ start = va & ~((1UL << ps) - 1);
+ while (psbits) {
+ curadr = start;
+ rr_ps = __ffs(psbits);
+ psbits &= ~(1UL << rr_ps);
+ num = 1UL << ((ps < rr_ps) ? 0 : (ps - rr_ps));
+ size = PSIZE(rr_ps);
+ vrr.ps = rr_ps;
+ while (num) {
+ cur = vsa_thash(hcb->pta, curadr, vrr.val, &tag);
+ if (cur->etag == tag && cur->ps == rr_ps)
+ cur->etag = INVALID_TI_TAG;
+ curadr += size;
+ num--;
+ }
+ }
+}
+
+
+/*
+ * purge VHPT and machine TLB
+ */
+static void vhpt_purge(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+ struct thash_data *cur;
+ u64 start, size, tag, num;
+ union ia64_rr rr;
+
+ start = va & ~((1UL << ps) - 1);
+ rr.val = ia64_get_rr(va);
+ size = PSIZE(rr.ps);
+ num = 1UL << ((ps < rr.ps) ? 0 : (ps - rr.ps));
+ while (num) {
+ cur = (struct thash_data *)ia64_thash(start);
+ tag = ia64_ttag(start);
+ if (cur->etag == tag)
+ cur->etag = INVALID_TI_TAG;
+ start += size;
+ num--;
+ }
+ machine_tlb_purge(va, ps);
+}
+
+/*
+ * Insert an entry into hash TLB or VHPT.
+ * NOTES:
+ * 1: When inserting VHPT to thash, "va" is a must covered
+ * address by the inserted machine VHPT entry.
+ * 2: The format of entry is always in TLB.
+ * 3: The caller need to make sure the new entry will not overlap
+ * with any existed entry.
+ */
+void vtlb_insert(struct kvm_vcpu *v, u64 pte, u64 itir, u64 va)
+{
+ struct thash_data *head;
+ union ia64_rr vrr;
+ u64 tag;
+ struct thash_cb *hcb = &v->arch.vtlb;
+
+ vrr.val = vcpu_get_rr(v, va);
+ vrr.ps = itir_ps(itir);
+ VMX(v, psbits[va >> 61]) |= (1UL << vrr.ps);
+ head = vsa_thash(hcb->pta, va, vrr.val, &tag);
+ head->page_flags = pte;
+ head->itir = itir;
+ head->etag = tag;
+}
+
+int vtr_find_overlap(struct kvm_vcpu *vcpu, u64 va, u64 ps, int type)
+{
+ struct thash_data *trp;
+ int i;
+ u64 end, rid;
+
+ rid = vcpu_get_rr(vcpu, va);
+ rid = rid & RR_RID_MASK;
+ end = va + PSIZE(ps);
+ if (type == D_TLB) {
+ if (vcpu_quick_region_check(vcpu->arch.dtr_regions, va)) {
+ for (trp = (struct thash_data *)&vcpu->arch.dtrs, i = 0;
+ i < NDTRS; i++, trp++) {
+ if (__is_tr_overlap(trp, rid, va, end))
+ return i;
+ }
+ }
+ } else {
+ if (vcpu_quick_region_check(vcpu->arch.itr_regions, va)) {
+ for (trp = (struct thash_data *)&vcpu->arch.itrs, i = 0;
+ i < NITRS; i++, trp++) {
+ if (__is_tr_overlap(trp, rid, va, end))
+ return i;
+ }
+ }
+ }
+ return -1;
+}
+
+/*
+ * Purge entries in VTLB and VHPT
+ */
+void thash_purge_entries(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+ if (vcpu_quick_region_check(v->arch.tc_regions, va))
+ vtlb_purge(v, va, ps);
+ vhpt_purge(v, va, ps);
+}
+
+void thash_purge_entries_remote(struct kvm_vcpu *v, u64 va, u64 ps)
+{
+ u64 old_va = va;
+ va = REGION_OFFSET(va);
+ if (vcpu_quick_region_check(v->arch.tc_regions, old_va))
+ vtlb_purge(v, va, ps);
+ vhpt_purge(v, va, ps);
+}
+
+u64 translate_phy_pte(u64 *pte, u64 itir, u64 va)
+{
+ u64 ps, ps_mask, paddr, maddr;
+ union pte_flags phy_pte;
+
+ ps = itir_ps(itir);
+ ps_mask = ~((1UL << ps) - 1);
+ phy_pte.val = *pte;
+ paddr = *pte;
+ paddr = ((paddr & _PAGE_PPN_MASK) & ps_mask) | (va & ~ps_mask);
+ maddr = kvm_lookup_mpa(paddr >> PAGE_SHIFT);
+ if (maddr & GPFN_IO_MASK) {
+ *pte |= VTLB_PTE_IO;
+ return -1;
+ }
+ maddr = ((maddr & _PAGE_PPN_MASK) & PAGE_MASK) |
+ (paddr & ~PAGE_MASK);
+ phy_pte.ppn = maddr >> ARCH_PAGE_SHIFT;
+ return phy_pte.val;
+}
+
+/*
+ * Purge overlap TCs and then insert the new entry to emulate itc ops.
+ * Notes: Only TC entry can purge and insert.
+ * 1 indicates this is MMIO
+ */
+int thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
+ u64 ifa, int type)
+{
+ u64 ps;
+ u64 phy_pte;
+ union ia64_rr vrr, mrr;
+ int ret = 0;
+
+ ps = itir_ps(itir);
+ vrr.val = vcpu_get_rr(v, ifa);
+ mrr.val = ia64_get_rr(ifa);
+
+ phy_pte = translate_phy_pte(&pte, itir, ifa);
+
+ /* Ensure WB attribute if pte is related to a normal mem page,
+ * which is required by vga acceleration since qemu maps shared
+ * vram buffer with WB.
+ */
+ if (!(pte & VTLB_PTE_IO) && ((pte & _PAGE_MA_MASK) != _PAGE_MA_NAT)) {
+ pte &= ~_PAGE_MA_MASK;
+ phy_pte &= ~_PAGE_MA_MASK;
+ }
+
+ if (pte & VTLB_PTE_IO)
+ ret = 1;
+
+ vtlb_purge(v, ifa, ps);
+ vhpt_purge(v, ifa, ps);
+
+ if (ps == mrr.ps) {
+ if (!(pte&VTLB_PTE_IO)) {
+ vhpt_insert(phy_pte, itir, ifa, pte);
+ } else {
+ vtlb_insert(v, pte, itir, ifa);
+ vcpu_quick_region_set(VMX(v, tc_regions), ifa);
+ }
+ } else if (ps > mrr.ps) {
+ vtlb_insert(v, pte, itir, ifa);
+ vcpu_quick_region_set(VMX(v, tc_regions), ifa);
+ if (!(pte&VTLB_PTE_IO))
+ vhpt_insert(phy_pte, itir, ifa, pte);
+ } else {
+ u64 psr;
+ phy_pte &= ~PAGE_FLAGS_RV_MASK;
+ psr = ia64_clear_ic();
+ ia64_itc(type, ifa, phy_pte, ps);
+ ia64_set_psr(psr);
+ }
+ if (!(pte&VTLB_PTE_IO))
+ mark_pages_dirty(v, pte, ps);
+
+ return ret;
+}
+
+/*
+ * Purge all TCs or VHPT entries including those in Hash table.
+ *
+ */
+
+void thash_purge_all(struct kvm_vcpu *v)
+{
+ int i;
+ struct thash_data *head;
+ struct thash_cb *vtlb, *vhpt;
+ vtlb = &v->arch.vtlb;
+ vhpt = &v->arch.vhpt;
+
+ for (i = 0; i < 8; i++)
+ VMX(v, psbits[i]) = 0;
+
+ head = vtlb->hash;
+ for (i = 0; i < vtlb->num; i++) {
+ head->page_flags = 0;
+ head->etag = INVALID_TI_TAG;
+ head->itir = 0;
+ head->next = 0;
+ head++;
+ };
+
+ head = vhpt->hash;
+ for (i = 0; i < vhpt->num; i++) {
+ head->page_flags = 0;
+ head->etag = INVALID_TI_TAG;
+ head->itir = 0;
+ head->next = 0;
+ head++;
+ };
+
+ local_flush_tlb_all();
+}
+
+
+/*
+ * Lookup the hash table and its collision chain to find an entry
+ * covering this address rid:va or the entry.
+ *
+ * INPUT:
+ * in: TLB format for both VHPT & TLB.
+ */
+
+struct thash_data *vtlb_lookup(struct kvm_vcpu *v, u64 va, int is_data)
+{
+ struct thash_data *cch;
+ u64 psbits, ps, tag;
+ union ia64_rr vrr;
+
+ struct thash_cb *hcb = &v->arch.vtlb;
+
+ cch = __vtr_lookup(v, va, is_data);;
+ if (cch)
+ return cch;
+
+ if (vcpu_quick_region_check(v->arch.tc_regions, va) == 0)
+ return NULL;
+
+ psbits = VMX(v, psbits[(va >> 61)]);
+ vrr.val = vcpu_get_rr(v, va);
+ while (psbits) {
+ ps = __ffs(psbits);
+ psbits &= ~(1UL << ps);
+ vrr.ps = ps;
+ cch = vsa_thash(hcb->pta, va, vrr.val, &tag);
+ if (cch->etag == tag && cch->ps == ps)
+ return cch;
+ }
+
+ return NULL;
+}
+
+
+/*
+ * Initialize internal control data before service.
+ */
+void thash_init(struct thash_cb *hcb, u64 sz)
+{
+ int i;
+ struct thash_data *head;
+
+ hcb->pta.val = (unsigned long)hcb->hash;
+ hcb->pta.vf = 1;
+ hcb->pta.ve = 1;
+ hcb->pta.size = sz;
+ head = hcb->hash;
+ for (i = 0; i < hcb->num; i++) {
+ head->page_flags = 0;
+ head->itir = 0;
+ head->etag = INVALID_TI_TAG;
+ head->next = 0;
+ head++;
+ }
+}
+
+u64 kvm_lookup_mpa(u64 gpfn)
+{
+ u64 *base = (u64 *) KVM_P2M_BASE;
+ return *(base + gpfn);
+}
+
+u64 kvm_gpa_to_mpa(u64 gpa)
+{
+ u64 pte = kvm_lookup_mpa(gpa >> PAGE_SHIFT);
+ return (pte >> PAGE_SHIFT << PAGE_SHIFT) | (gpa & ~PAGE_MASK);
+}
+
+
+/*
+ * Fetch guest bundle code.
+ * INPUT:
+ * gip: guest ip
+ * pbundle: used to return fetched bundle.
+ */
+int fetch_code(struct kvm_vcpu *vcpu, u64 gip, IA64_BUNDLE *pbundle)
+{
+ u64 gpip = 0; /* guest physical IP*/
+ u64 *vpa;
+ struct thash_data *tlb;
+ u64 maddr;
+
+ if (!(VCPU(vcpu, vpsr) & IA64_PSR_IT)) {
+ /* I-side physical mode */
+ gpip = gip;
+ } else {
+ tlb = vtlb_lookup(vcpu, gip, I_TLB);
+ if (tlb)
+ gpip = (tlb->ppn >> (tlb->ps - 12) << tlb->ps) |
+ (gip & (PSIZE(tlb->ps) - 1));
+ }
+ if (gpip) {
+ maddr = kvm_gpa_to_mpa(gpip);
+ } else {
+ tlb = vhpt_lookup(gip);
+ if (tlb == NULL) {
+ ia64_ptcl(gip, ARCH_PAGE_SHIFT << 2);
+ return IA64_FAULT;
+ }
+ maddr = (tlb->ppn >> (tlb->ps - 12) << tlb->ps)
+ | (gip & (PSIZE(tlb->ps) - 1));
+ }
+ vpa = (u64 *)__kvm_va(maddr);
+
+ pbundle->i64[0] = *vpa++;
+ pbundle->i64[1] = *vpa;
+
+ return IA64_NO_FAULT;
+}
+
+
+void kvm_init_vhpt(struct kvm_vcpu *v)
+{
+ v->arch.vhpt.num = VHPT_NUM_ENTRIES;
+ thash_init(&v->arch.vhpt, VHPT_SHIFT);
+ ia64_set_pta(v->arch.vhpt.pta.val);
+ /*Enable VHPT here?*/
+}
+
+void kvm_init_vtlb(struct kvm_vcpu *v)
+{
+ v->arch.vtlb.num = VTLB_NUM_ENTRIES;
+ thash_init(&v->arch.vtlb, VTLB_SHIFT);
+}
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 5c1de53c8c1..fc6c6636ffd 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -682,15 +682,6 @@ mem_init (void)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- init_page_count(page);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
int arch_add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat;
diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 2b412454cb4..ded7dd2f67b 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -186,7 +186,7 @@ int setup_irq(unsigned int irq, struct irq_node *node)
if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
printk("%s: Incorrect IRQ %d from %s\n",
- __FUNCTION__, irq, node->devname);
+ __func__, irq, node->devname);
return -ENXIO;
}
@@ -249,7 +249,7 @@ void free_irq(unsigned int irq, void *dev_id)
unsigned long flags;
if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
- printk("%s: Incorrect IRQ %d\n", __FUNCTION__, irq);
+ printk("%s: Incorrect IRQ %d\n", __func__, irq);
return;
}
@@ -267,7 +267,7 @@ void free_irq(unsigned int irq, void *dev_id)
node->handler = NULL;
} else
printk("%s: Removing probably wrong IRQ %d\n",
- __FUNCTION__, irq);
+ __func__, irq);
if (!irq_list[irq]) {
if (contr->shutdown)
@@ -288,7 +288,7 @@ void enable_irq(unsigned int irq)
if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
printk("%s: Incorrect IRQ %d\n",
- __FUNCTION__, irq);
+ __func__, irq);
return;
}
@@ -312,7 +312,7 @@ void disable_irq(unsigned int irq)
if (irq >= NR_IRQS || !(contr = irq_controller[irq])) {
printk("%s: Incorrect IRQ %d\n",
- __FUNCTION__, irq);
+ __func__, irq);
return;
}
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 50603d3dce8..3c943d2ec57 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -190,7 +190,7 @@ void oss_irq_enable(int irq) {
break;
#ifdef DEBUG_IRQUSE
default:
- printk("%s unknown irq %d\n",__FUNCTION__, irq);
+ printk("%s unknown irq %d\n", __func__, irq);
break;
#endif
}
@@ -230,7 +230,7 @@ void oss_irq_disable(int irq) {
break;
#ifdef DEBUG_IRQUSE
default:
- printk("%s unknown irq %d\n", __FUNCTION__, irq);
+ printk("%s unknown irq %d\n", __func__, irq);
break;
#endif
}
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index f42caa79e4e..a2bb01f5964 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -79,7 +79,6 @@ void show_mem(void)
printk("\nMem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
for_each_online_pgdat(pgdat) {
for (i = 0; i < pgdat->node_spanned_pages; i++) {
struct page *page = pgdat->node_mem_map + i;
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 46161cef08b..9f0e3d59bf9 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -47,7 +47,7 @@ static int q40_irq_startup(unsigned int irq)
switch (irq) {
case 1: case 2: case 8: case 9:
case 11: case 12: case 13:
- printk("%s: ISA IRQ %d not implemented by HW\n", __FUNCTION__, irq);
+ printk("%s: ISA IRQ %d not implemented by HW\n", __func__, irq);
return -ENXIO;
}
return 0;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8724ed3298d..e5a7c5d9636 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -81,7 +81,9 @@ config MIPS_COBALT
config MACH_DECSTATION
bool "DECstations"
select BOOT_ELF32
+ select CEVT_DS1287
select CEVT_R4K
+ select CSRC_IOASIC
select CSRC_R4K
select CPU_DADDI_WORKAROUNDS if 64BIT
select CPU_R4000_WORKAROUNDS if 64BIT
@@ -221,6 +223,7 @@ config MIPS_MALTA
select DMA_NONCOHERENT
select GENERIC_ISA_DMA
select IRQ_CPU
+ select IRQ_GIC
select HW_HAS_PCI
select I8253
select I8259
@@ -309,12 +312,12 @@ config MACH_VR41XX
select GENERIC_HARDIRQS_NO__DO_IRQ
config PNX8550_JBS
- bool "Philips PNX8550 based JBS board"
+ bool "NXP PNX8550 based JBS board"
select PNX8550
select SYS_SUPPORTS_LITTLE_ENDIAN
config PNX8550_STB810
- bool "Philips PNX8550 based STB810 board"
+ bool "NXP PNX8550 based STB810 board"
select PNX8550
select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -612,6 +615,7 @@ config TOSHIBA_JMR3927
select SYS_SUPPORTS_LITTLE_ENDIAN
select SYS_SUPPORTS_BIG_ENDIAN
select GENERIC_HARDIRQS_NO__DO_IRQ
+ select GPIO_TXX9
config TOSHIBA_RBTX4927
bool "Toshiba RBTX49[23]7 board"
@@ -653,7 +657,7 @@ config TOSHIBA_RBTX4938
select SYS_SUPPORTS_BIG_ENDIAN
select SYS_SUPPORTS_KGDB
select GENERIC_HARDIRQS_NO__DO_IRQ
- select GENERIC_GPIO
+ select GPIO_TXX9
help
This Toshiba board is based on the TX4938 processor. Say Y here to
support this machine type
@@ -767,6 +771,9 @@ config BOOT_RAW
config CEVT_BCM1480
bool
+config CEVT_DS1287
+ bool
+
config CEVT_GT641XX
bool
@@ -782,12 +789,20 @@ config CEVT_TXX9
config CSRC_BCM1480
bool
+config CSRC_IOASIC
+ bool
+
config CSRC_R4K
bool
config CSRC_SB1250
bool
+config GPIO_TXX9
+ select GENERIC_GPIO
+ select HAVE_GPIO_LIB
+ bool
+
config CFE
bool
@@ -840,6 +855,9 @@ config MIPS_NILE4
config MIPS_DISABLE_OBSOLETE_IDE
bool
+config SYNC_R4K
+ bool
+
config NO_IOPORT
def_bool n
@@ -909,6 +927,9 @@ config IRQ_TXX9
config IRQ_GT641XX
bool
+config IRQ_GIC
+ bool
+
config MIPS_BOARDS_GEN
bool
@@ -1811,6 +1832,17 @@ config NR_CPUS
performance should round up your number of processors to the next
power of two.
+config MIPS_CMP
+ bool "MIPS CMP framework support"
+ depends on SMP
+ select SYNC_R4K
+ select SYS_SUPPORTS_SCHED_SMT
+ select WEAK_ORDERING
+ default n
+ help
+ This is a placeholder option for the GCMP work. It will need to
+ be handled differently...
+
source "kernel/time/Kconfig"
#
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index fd7124c1b75..f18cf92650e 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -73,14 +73,4 @@ config RUNTIME_DEBUG
include/asm-mips/debug.h for debuging macros.
If unsure, say N.
-config MIPS_UNCACHED
- bool "Run uncached"
- depends on DEBUG_KERNEL && !SMP && !SGI_IP27
- help
- If you say Y here there kernel will disable all CPU caches. This will
- reduce the system's performance dramatically but can help finding
- otherwise hard to track bugs. It can also useful if you're doing
- hardware debugging with a logic analyzer and need to see all traffic
- on the bus.
-
endmenu
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 1c62381f5c2..69648d01acc 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -410,21 +410,21 @@ load-$(CONFIG_CASIO_E55) += 0xffffffff80004000
load-$(CONFIG_TANBAC_TB022X) += 0xffffffff80000000
#
-# Common Philips PNX8550
+# Common NXP PNX8550
#
-core-$(CONFIG_SOC_PNX8550) += arch/mips/philips/pnx8550/common/
+core-$(CONFIG_SOC_PNX8550) += arch/mips/nxp/pnx8550/common/
cflags-$(CONFIG_SOC_PNX8550) += -Iinclude/asm-mips/mach-pnx8550
#
-# Philips PNX8550 JBS board
+# NXP PNX8550 JBS board
#
-libs-$(CONFIG_PNX8550_JBS) += arch/mips/philips/pnx8550/jbs/
+libs-$(CONFIG_PNX8550_JBS) += arch/mips/nxp/pnx8550/jbs/
#cflags-$(CONFIG_PNX8550_JBS) += -Iinclude/asm-mips/mach-pnx8550
load-$(CONFIG_PNX8550_JBS) += 0xffffffff80060000
-# Philips PNX8550 STB810 board
+# NXP PNX8550 STB810 board
#
-libs-$(CONFIG_PNX8550_STB810) += arch/mips/philips/pnx8550/stb810/
+libs-$(CONFIG_PNX8550_STB810) += arch/mips/nxp/pnx8550/stb810/
load-$(CONFIG_PNX8550_STB810) += 0xffffffff80060000
# NEC EMMA2RH boards
diff --git a/arch/mips/au1000/common/cputable.c b/arch/mips/au1000/common/cputable.c
index 5c0d35d6e22..8c93a05d738 100644
--- a/arch/mips/au1000/common/cputable.c
+++ b/arch/mips/au1000/common/cputable.c
@@ -11,10 +11,7 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/string.h>
-#include <linux/sched.h>
-#include <linux/threads.h>
-#include <linux/init.h>
+
#include <asm/mach-au1x00/au1000.h>
struct cpu_spec* cur_cpu_spec[NR_CPUS];
diff --git a/arch/mips/au1000/common/dbdma.c b/arch/mips/au1000/common/dbdma.c
index 57f17b41098..53377dfc064 100644
--- a/arch/mips/au1000/common/dbdma.c
+++ b/arch/mips/au1000/common/dbdma.c
@@ -31,18 +31,12 @@
*/
#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1xxx_dbdma.h>
-#include <asm/system.h>
-
#if defined(CONFIG_SOC_AU1550) || defined(CONFIG_SOC_AU1200)
diff --git a/arch/mips/au1000/common/dbg_io.c b/arch/mips/au1000/common/dbg_io.c
index 79e0b0a51ac..eae1bb2ca26 100644
--- a/arch/mips/au1000/common/dbg_io.c
+++ b/arch/mips/au1000/common/dbg_io.c
@@ -1,5 +1,4 @@
-#include <asm/io.h>
#include <asm/mach-au1x00/au1000.h>
#ifdef CONFIG_KGDB
@@ -55,8 +54,7 @@ typedef unsigned int uint32;
#define UART16550_READ(y) (au_readl(DEBUG_BASE + y) & 0xff)
#define UART16550_WRITE(y, z) (au_writel(z&0xff, DEBUG_BASE + y))
-extern unsigned long get_au1x00_uart_baud_base(void);
-extern unsigned long cal_r4koff(void);
+extern unsigned long calc_clock(void);
void debugInit(uint32 baud, uint8 data, uint8 parity, uint8 stop)
{
@@ -64,7 +62,7 @@ void debugInit(uint32 baud, uint8 data, uint8 parity, uint8 stop)
if (UART16550_READ(UART_MOD_CNTRL) != 0x3) {
UART16550_WRITE(UART_MOD_CNTRL, 3);
}
- cal_r4koff();
+ calc_clock();
/* disable interrupts */
UART16550_WRITE(UART_IER, 0);
diff --git a/arch/mips/au1000/common/dma.c b/arch/mips/au1000/common/dma.c
index c78260d4e83..95f69ea146e 100644
--- a/arch/mips/au1000/common/dma.c
+++ b/arch/mips/au1000/common/dma.c
@@ -33,12 +33,9 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/errno.h>
-#include <linux/sched.h>
#include <linux/spinlock.h>
-#include <linux/string.h>
-#include <linux/delay.h>
#include <linux/interrupt.h>
-#include <asm/system.h>
+
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-au1x00/au1000_dma.h>
diff --git a/arch/mips/au1000/common/gpio.c b/arch/mips/au1000/common/gpio.c
index 0b658f1db4c..52545258997 100644
--- a/arch/mips/au1000/common/gpio.c
+++ b/arch/mips/au1000/common/gpio.c
@@ -27,13 +27,8 @@
* others have a second one : GPIO2
*/
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/types.h>
#include <linux/module.h>
-#include <asm/addrspace.h>
-
#include <asm/mach-au1x00/au1000.h>
#include <asm/gpio.h>
diff --git a/arch/mips/au1000/common/irq.c b/arch/mips/au1000/common/irq.c
index 3c7714f057a..f0626992fd7 100644
--- a/arch/mips/au1000/common/irq.c
+++ b/arch/mips/au1000/common/irq.c
@@ -1,7 +1,6 @@
/*
- * Copyright 2001 MontaVista Software Inc.
- * Author: MontaVista Software, Inc.
- * ppopov@mvista.com or source@mvista.com
+ * Copyright 2001, 2007-2008 MontaVista Software Inc.
+ * Author: MontaVista Software, Inc. <source@mvista.com>
*
* Copyright (C) 2007 Ralf Baechle (ralf@linux-mips.org)
*
@@ -27,7 +26,6 @@
*/
#include <linux/bitops.h>
#include <linux/init.h>
-#include <linux/io.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
@@ -591,7 +589,7 @@ void __init arch_init_irq(void)
imp++;
}
- set_c0_status(ALLINTS);
+ set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | IE_IRQ3 | IE_IRQ4);
/* Board specific IRQ initialization.
*/
diff --git a/arch/mips/au1000/common/pci.c b/arch/mips/au1000/common/pci.c
index ce771487567..7e966b31e3e 100644
--- a/arch/mips/au1000/common/pci.c
+++ b/arch/mips/au1000/common/pci.c
@@ -30,7 +30,7 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/types.h>
+
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/arch/mips/au1000/common/platform.c b/arch/mips/au1000/common/platform.c
index 39d68126529..31d2a227087 100644
--- a/arch/mips/au1000/common/platform.c
+++ b/arch/mips/au1000/common/platform.c
@@ -3,18 +3,65 @@
*
* Copyright 2004, Matt Porter <mporter@kernel.crashing.org>
*
+ * (C) Copyright Embedded Alley Solutions, Inc 2005
+ * Author: Pantelis Antoniou <pantelis@embeddedalley.com>
+ *
* This file is licensed under the terms of the GNU General Public
* License version 2. This program is licensed "as is" without any
* warranty of any kind, whether express or implied.
*/
-#include <linux/device.h>
+
#include <linux/platform_device.h>
-#include <linux/kernel.h>
+#include <linux/serial_8250.h>
#include <linux/init.h>
-#include <linux/resource.h>
#include <asm/mach-au1x00/au1xxx.h>
+#define PORT(_base, _irq) \
+ { \
+ .iobase = _base, \
+ .membase = (void __iomem *)_base,\
+ .mapbase = CPHYSADDR(_base), \
+ .irq = _irq, \
+ .regshift = 2, \
+ .iotype = UPIO_AU, \
+ .flags = UPF_SKIP_TEST \
+ }
+
+static struct plat_serial8250_port au1x00_uart_data[] = {
+#if defined(CONFIG_SERIAL_8250_AU1X00)
+#if defined(CONFIG_SOC_AU1000)
+ PORT(UART0_ADDR, AU1000_UART0_INT),
+ PORT(UART1_ADDR, AU1000_UART1_INT),
+ PORT(UART2_ADDR, AU1000_UART2_INT),
+ PORT(UART3_ADDR, AU1000_UART3_INT),
+#elif defined(CONFIG_SOC_AU1500)
+ PORT(UART0_ADDR, AU1500_UART0_INT),
+ PORT(UART3_ADDR, AU1500_UART3_INT),
+#elif defined(CONFIG_SOC_AU1100)
+ PORT(UART0_ADDR, AU1100_UART0_INT),
+ PORT(UART1_ADDR, AU1100_UART1_INT),
+ PORT(UART3_ADDR, AU1100_UART3_INT),
+#elif defined(CONFIG_SOC_AU1550)
+ PORT(UART0_ADDR, AU1550_UART0_INT),
+ PORT(UART1_ADDR, AU1550_UART1_INT),
+ PORT(UART3_ADDR, AU1550_UART3_INT),
+#elif defined(CONFIG_SOC_AU1200)
+ PORT(UART0_ADDR, AU1200_UART0_INT),
+ PORT(UART1_ADDR, AU1200_UART1_INT),
+#endif
+#endif /* CONFIG_SERIAL_8250_AU1X00 */
+ { },
+};
+
+static struct platform_device au1xx0_uart_device = {
+ .name = "serial8250",
+ .id = PLAT8250_DEV_AU1X00,
+ .dev = {
+ .platform_data = au1x00_uart_data,
+ },
+};
+
/* OHCI (USB full speed host controller) */
static struct resource au1xxx_usb_ohci_resources[] = {
[0] = {
@@ -186,19 +233,6 @@ static struct resource au1200_lcd_resources[] = {
}
};
-static struct resource au1200_ide0_resources[] = {
- [0] = {
- .start = AU1XXX_ATA_PHYS_ADDR,
- .end = AU1XXX_ATA_PHYS_ADDR + AU1XXX_ATA_PHYS_LEN - 1,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1XXX_ATA_INT,
- .end = AU1XXX_ATA_INT,
- .flags = IORESOURCE_IRQ,
- }
-};
-
static u64 au1200_lcd_dmamask = ~(u32)0;
static struct platform_device au1200_lcd_device = {
@@ -212,20 +246,6 @@ static struct platform_device au1200_lcd_device = {
.resource = au1200_lcd_resources,
};
-
-static u64 ide0_dmamask = ~(u32)0;
-
-static struct platform_device au1200_ide0_device = {
- .name = "au1200-ide",
- .id = 0,
- .dev = {
- .dma_mask = &ide0_dmamask,
- .coherent_dma_mask = 0xffffffff,
- },
- .num_resources = ARRAY_SIZE(au1200_ide0_resources),
- .resource = au1200_ide0_resources,
-};
-
static u64 au1xxx_mmc_dmamask = ~(u32)0;
static struct platform_device au1xxx_mmc_device = {
@@ -245,31 +265,6 @@ static struct platform_device au1x00_pcmcia_device = {
.id = 0,
};
-#ifdef CONFIG_MIPS_DB1200
-
-static struct resource smc91x_resources[] = {
- [0] = {
- .name = "smc91x-regs",
- .start = AU1XXX_SMC91111_PHYS_ADDR,
- .end = AU1XXX_SMC91111_PHYS_ADDR + 0xfffff,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = AU1XXX_SMC91111_IRQ,
- .end = AU1XXX_SMC91111_IRQ,
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device smc91x_device = {
- .name = "smc91x",
- .id = -1,
- .num_resources = ARRAY_SIZE(smc91x_resources),
- .resource = smc91x_resources,
-};
-
-#endif
-
/* All Alchemy demoboards with I2C have this #define in their headers */
#ifdef SMBUS_PSC_BASE
static struct resource pbdb_smbus_resources[] = {
@@ -289,6 +284,7 @@ static struct platform_device pbdb_smbus_device = {
#endif
static struct platform_device *au1xxx_platform_devices[] __initdata = {
+ &au1xx0_uart_device,
&au1xxx_usb_ohci_device,
&au1x00_pcmcia_device,
#ifdef CONFIG_FB_AU1100
@@ -299,12 +295,8 @@ static struct platform_device *au1xxx_platform_devices[] __initdata = {
&au1xxx_usb_gdt_device,
&au1xxx_usb_otg_device,
&au1200_lcd_device,
- &au1200_ide0_device,
&au1xxx_mmc_device,
#endif
-#ifdef CONFIG_MIPS_DB1200
- &smc91x_device,
-#endif
#ifdef SMBUS_PSC_BASE
&pbdb_smbus_device,
#endif
@@ -312,6 +304,13 @@ static struct platform_device *au1xxx_platform_devices[] __initdata = {
int __init au1xxx_platform_init(void)
{
+ unsigned int uartclk = get_au1x00_uart_baud_base() * 16;
+ int i;
+
+ /* Fill up uartclk. */
+ for (i = 0; au1x00_uart_data[i].flags ; i++)
+ au1x00_uart_data[i].uartclk = uartclk;
+
return platform_add_devices(au1xxx_platform_devices, ARRAY_SIZE(au1xxx_platform_devices));
}
diff --git a/arch/mips/au1000/common/power.c b/arch/mips/au1000/common/power.c
index 54047d69b82..812a5f8b7d2 100644
--- a/arch/mips/au1000/common/power.c
+++ b/arch/mips/au1000/common/power.c
@@ -29,17 +29,14 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
#include <linux/pm.h>
#include <linux/pm_legacy.h>
-#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/jiffies.h>
-#include <asm/string.h>
#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/system.h>
#include <asm/cacheflush.h>
#include <asm/mach-au1x00/au1000.h>
@@ -47,17 +44,13 @@
#define DEBUG 1
#ifdef DEBUG
-# define DPRINTK(fmt, args...) printk("%s: " fmt, __FUNCTION__ , ## args)
+# define DPRINTK(fmt, args...) printk("%s: " fmt, __func__, ## args)
#else
# define DPRINTK(fmt, args...)
#endif
static void au1000_calibrate_delay(void);
-extern void set_au1x00_speed(unsigned int new_freq);
-extern unsigned int get_au1x00_speed(void);
-extern unsigned long get_au1x00_uart_baud_base(void);
-extern void set_au1x00_uart_baud_base(unsigned long new_baud_base);
extern unsigned long save_local_and_disable(int controller);
extern void restore_local_and_enable(int controller, unsigned long mask);
extern void local_enable_irq(unsigned int irq_nr);
diff --git a/arch/mips/au1000/common/prom.c b/arch/mips/au1000/common/prom.c
index 90d70695aa6..f10af829e4e 100644
--- a/arch/mips/au1000/common/prom.c
+++ b/arch/mips/au1000/common/prom.c
@@ -33,8 +33,8 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/module.h>
-#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/string.h>
diff --git a/arch/mips/au1000/common/puts.c b/arch/mips/au1000/common/puts.c
index 2705829cd46..e34c67e8929 100644
--- a/arch/mips/au1000/common/puts.c
+++ b/arch/mips/au1000/common/puts.c
@@ -28,7 +28,6 @@
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/types.h>
#include <asm/mach-au1x00/au1000.h>
#define SERIAL_BASE UART_BASE
diff --git a/arch/mips/au1000/common/reset.c b/arch/mips/au1000/common/reset.c
index b8638d293cf..60cec537c74 100644
--- a/arch/mips/au1000/common/reset.c
+++ b/arch/mips/au1000/common/reset.c
@@ -27,13 +27,7 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <asm/io.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/reboot.h>
-#include <asm/system.h>
+
#include <asm/mach-au1x00/au1000.h>
extern int au_sleep(void);
diff --git a/arch/mips/au1000/common/setup.c b/arch/mips/au1000/common/setup.c
index 9e4ab80caab..0e86f7a6b4a 100644
--- a/arch/mips/au1000/common/setup.c
+++ b/arch/mips/au1000/common/setup.c
@@ -25,21 +25,14 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pm.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
#include <asm/mipsregs.h>
#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/time.h>
#include <au1000.h>
@@ -49,8 +42,6 @@ extern void __init board_setup(void);
extern void au1000_restart(char *);
extern void au1000_halt(void);
extern void au1000_power_off(void);
-extern void au1x_time_init(void);
-extern void au1x_timer_setup(struct irqaction *irq);
extern void set_cpuspec(void);
void __init plat_mem_setup(void)
diff --git a/arch/mips/au1000/common/sleeper.S b/arch/mips/au1000/common/sleeper.S
index 683d9da84b6..4b3cf021a45 100644
--- a/arch/mips/au1000/common/sleeper.S
+++ b/arch/mips/au1000/common/sleeper.S
@@ -9,9 +9,9 @@
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*/
+
#include <asm/asm.h>
#include <asm/mipsregs.h>
-#include <asm/addrspace.h>
#include <asm/regdef.h>
#include <asm/stackframe.h>
diff --git a/arch/mips/au1000/common/time.c b/arch/mips/au1000/common/time.c
index e122bbc6cd8..bdb6d73b26f 100644
--- a/arch/mips/au1000/common/time.c
+++ b/arch/mips/au1000/common/time.c
@@ -1,6 +1,6 @@
/*
*
- * Copyright (C) 2001 MontaVista Software, ppopov@mvista.com
+ * Copyright (C) 2001, 2006, 2008 MontaVista Software, <source@mvista.com>
* Copied and modified Carsten Langgaard's time.c
*
* Carsten Langgaard, carstenl@mips.com
@@ -34,23 +34,13 @@
#include <linux/types.h>
#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sched.h>
#include <linux/spinlock.h>
-#include <linux/hardirq.h>
-#include <asm/compiler.h>
#include <asm/mipsregs.h>
#include <asm/time.h>
-#include <asm/div64.h>
#include <asm/mach-au1x00/au1000.h>
-#include <linux/mc146818rtc.h>
-#include <linux/timex.h>
-
-static unsigned long r4k_offset; /* Amount to increment compare reg each time */
-static unsigned long r4k_cur; /* What counter should be at next timer irq */
-int no_au1xxx_32khz;
+static int no_au1xxx_32khz;
extern int allow_au1k_wait; /* default off for CP0 Counter */
#ifdef CONFIG_PM
@@ -184,7 +174,7 @@ wakeup_counter0_set(int ticks)
* "wait" is enabled, and we need to detect if the 32KHz isn't present
* but requested......got it? :-) -- Dan
*/
-unsigned long cal_r4koff(void)
+unsigned long calc_clock(void)
{
unsigned long cpu_speed;
unsigned long flags;
@@ -229,19 +219,13 @@ unsigned long cal_r4koff(void)
// Equation: Baudrate = CPU / (SD * 2 * CLKDIV * 16)
set_au1x00_uart_baud_base(cpu_speed / (2 * ((int)(au_readl(SYS_POWERCTRL)&0x03) + 2) * 16));
spin_unlock_irqrestore(&time_lock, flags);
- return (cpu_speed / HZ);
+ return cpu_speed;
}
void __init plat_time_init(void)
{
- unsigned int est_freq;
-
- printk("calculating r4koff... ");
- r4k_offset = cal_r4koff();
- printk("%08lx(%d)\n", r4k_offset, (int) r4k_offset);
+ unsigned int est_freq = calc_clock();
- //est_freq = 2*r4k_offset*HZ;
- est_freq = r4k_offset*HZ;
est_freq += 5000; /* round */
est_freq -= est_freq%10000;
printk("CPU frequency %d.%02d MHz\n", est_freq/1000000,
@@ -249,9 +233,6 @@ void __init plat_time_init(void)
set_au1x00_speed(est_freq);
set_au1x00_lcd_clock(); // program the LCD clock
- r4k_cur = (read_c0_count() + r4k_offset);
- write_c0_compare(r4k_cur);
-
#ifdef CONFIG_PM
/*
* setup counter 0, since it keeps ticking after a
@@ -265,12 +246,8 @@ void __init plat_time_init(void)
* Check to ensure we really have a 32KHz oscillator before
* we do this.
*/
- if (no_au1xxx_32khz) {
+ if (no_au1xxx_32khz)
printk("WARNING: no 32KHz clock found.\n");
-
- /* Ensure we get CPO_COUNTER interrupts. */
- set_c0_status(IE_IRQ5);
- }
else {
while (au_readl(SYS_COUNTER_CNTRL) & SYS_CNTRL_C0S);
au_writel(0, SYS_TOYWRITE);
diff --git a/arch/mips/au1000/db1x00/board_setup.c b/arch/mips/au1000/db1x00/board_setup.c
index 99eafeada51..b7dcbad5c58 100644
--- a/arch/mips/au1000/db1x00/board_setup.c
+++ b/arch/mips/au1000/db1x00/board_setup.c
@@ -27,20 +27,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
+
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-db1x00/db1x00.h>
diff --git a/arch/mips/au1000/db1x00/init.c b/arch/mips/au1000/db1x00/init.c
index e822c123eab..d3b967caf70 100644
--- a/arch/mips/au1000/db1x00/init.c
+++ b/arch/mips/au1000/db1x00/init.c
@@ -28,13 +28,8 @@
*/
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/db1x00/irqmap.c b/arch/mips/au1000/db1x00/irqmap.c
index 09cea03411b..eaa50c7b634 100644
--- a/arch/mips/au1000/db1x00/irqmap.c
+++ b/arch/mips/au1000/db1x00/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
#ifdef CONFIG_MIPS_DB1500
diff --git a/arch/mips/au1000/mtx-1/board_setup.c b/arch/mips/au1000/mtx-1/board_setup.c
index 310d5dff89f..5736354829c 100644
--- a/arch/mips/au1000/mtx-1/board_setup.c
+++ b/arch/mips/au1000/mtx-1/board_setup.c
@@ -28,19 +28,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
extern int (*board_pci_idsel)(unsigned int devsel, int assert);
diff --git a/arch/mips/au1000/mtx-1/init.c b/arch/mips/au1000/mtx-1/init.c
index e700fd312a2..c015cbce1cc 100644
--- a/arch/mips/au1000/mtx-1/init.c
+++ b/arch/mips/au1000/mtx-1/init.c
@@ -28,14 +28,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/string.h>
+
#include <linux/kernel.h>
-#include <linux/sched.h>
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/bootmem.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/mtx-1/irqmap.c b/arch/mips/au1000/mtx-1/irqmap.c
index 49c612aeddc..78d70c42c9d 100644
--- a/arch/mips/au1000/mtx-1/irqmap.c
+++ b/arch/mips/au1000/mtx-1/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
char irq_tab_alchemy[][5] __initdata = {
diff --git a/arch/mips/au1000/mtx-1/platform.c b/arch/mips/au1000/mtx-1/platform.c
index ce8637b3afa..a7edbf0829a 100644
--- a/arch/mips/au1000/mtx-1/platform.c
+++ b/arch/mips/au1000/mtx-1/platform.c
@@ -19,7 +19,6 @@
*/
#include <linux/init.h>
-#include <linux/types.h>
#include <linux/platform_device.h>
#include <linux/leds.h>
#include <linux/gpio_keys.h>
diff --git a/arch/mips/au1000/pb1000/board_setup.c b/arch/mips/au1000/pb1000/board_setup.c
index 5198c4f98b4..33f15acc1b1 100644
--- a/arch/mips/au1000/pb1000/board_setup.c
+++ b/arch/mips/au1000/pb1000/board_setup.c
@@ -23,19 +23,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-pb1x00/pb1000.h>
diff --git a/arch/mips/au1000/pb1000/init.c b/arch/mips/au1000/pb1000/init.c
index 2515b9fb24a..549447df71d 100644
--- a/arch/mips/au1000/pb1000/init.c
+++ b/arch/mips/au1000/pb1000/init.c
@@ -26,14 +26,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/pb1000/irqmap.c b/arch/mips/au1000/pb1000/irqmap.c
index 88e35450820..b3d56b0af32 100644
--- a/arch/mips/au1000/pb1000/irqmap.c
+++ b/arch/mips/au1000/pb1000/irqmap.c
@@ -25,26 +25,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/arch/mips/au1000/pb1100/board_setup.c b/arch/mips/au1000/pb1100/board_setup.c
index 42874a6b31d..656164c8e9c 100644
--- a/arch/mips/au1000/pb1100/board_setup.c
+++ b/arch/mips/au1000/pb1100/board_setup.c
@@ -23,19 +23,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-pb1x00/pb1100.h>
diff --git a/arch/mips/au1000/pb1100/init.c b/arch/mips/au1000/pb1100/init.c
index 490c3801c27..c91344648ed 100644
--- a/arch/mips/au1000/pb1100/init.c
+++ b/arch/mips/au1000/pb1100/init.c
@@ -27,14 +27,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/pb1100/irqmap.c b/arch/mips/au1000/pb1100/irqmap.c
index 880456bf8c1..b5021e3d477 100644
--- a/arch/mips/au1000/pb1100/irqmap.c
+++ b/arch/mips/au1000/pb1100/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/arch/mips/au1000/pb1200/Makefile b/arch/mips/au1000/pb1200/Makefile
index 970b1b1d5cd..4fe02ea65a6 100644
--- a/arch/mips/au1000/pb1200/Makefile
+++ b/arch/mips/au1000/pb1200/Makefile
@@ -3,5 +3,6 @@
#
lib-y := init.o board_setup.o irqmap.o
+obj-y += platform.o
EXTRA_CFLAGS += -Werror
diff --git a/arch/mips/au1000/pb1200/board_setup.c b/arch/mips/au1000/pb1200/board_setup.c
index b98bebfa87c..4493a792cc4 100644
--- a/arch/mips/au1000/pb1200/board_setup.c
+++ b/arch/mips/au1000/pb1200/board_setup.c
@@ -23,27 +23,11 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
-
-#if defined(CONFIG_BLK_DEV_IDE_AU1XXX)
-#include <linux/ide.h>
-#endif
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <au1000.h>
-#include <au1xxx_dbdma.h>
#include <prom.h>
#ifdef CONFIG_MIPS_PB1200
@@ -52,8 +36,6 @@
#ifdef CONFIG_MIPS_DB1200
#include <asm/mach-db1x00/db1200.h>
-#define PB1200_ETH_INT DB1200_ETH_INT
-#define PB1200_IDE_INT DB1200_IDE_INT
#endif
extern void _board_init_irq(void);
diff --git a/arch/mips/au1000/pb1200/init.c b/arch/mips/au1000/pb1200/init.c
index 069ed45f04f..72af5500660 100644
--- a/arch/mips/au1000/pb1200/init.c
+++ b/arch/mips/au1000/pb1200/init.c
@@ -27,14 +27,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/pb1200/irqmap.c b/arch/mips/au1000/pb1200/irqmap.c
index 8fcd0df86f9..e61eb8e0b76 100644
--- a/arch/mips/au1000/pb1200/irqmap.c
+++ b/arch/mips/au1000/pb1200/irqmap.c
@@ -22,26 +22,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
+
#include <asm/mach-au1x00/au1000.h>
#ifdef CONFIG_MIPS_PB1200
diff --git a/arch/mips/au1000/pb1200/platform.c b/arch/mips/au1000/pb1200/platform.c
new file mode 100644
index 00000000000..5930110b9b6
--- /dev/null
+++ b/arch/mips/au1000/pb1200/platform.c
@@ -0,0 +1,84 @@
+/*
+ * Pb1200/DBAu1200 board platform device registration
+ *
+ * Copyright (C) 2008 MontaVista Software Inc. <source@mvista.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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach-au1x00/au1xxx.h>
+
+static struct resource ide_resources[] = {
+ [0] = {
+ .start = IDE_PHYS_ADDR,
+ .end = IDE_PHYS_ADDR + IDE_PHYS_LEN - 1,
+ .flags = IORESOURCE_MEM
+ },
+ [1] = {
+ .start = IDE_INT,
+ .end = IDE_INT,
+ .flags = IORESOURCE_IRQ
+ }
+};
+
+static u64 ide_dmamask = ~(u32)0;
+
+static struct platform_device ide_device = {
+ .name = "au1200-ide",
+ .id = 0,
+ .dev = {
+ .dma_mask = &ide_dmamask,
+ .coherent_dma_mask = 0xffffffff,
+ },
+ .num_resources = ARRAY_SIZE(ide_resources),
+ .resource = ide_resources
+};
+
+static struct resource smc91c111_resources[] = {
+ [0] = {
+ .name = "smc91x-regs",
+ .start = SMC91C111_PHYS_ADDR,
+ .end = SMC91C111_PHYS_ADDR + 0xf,
+ .flags = IORESOURCE_MEM
+ },
+ [1] = {
+ .start = SMC91C111_INT,
+ .end = SMC91C111_INT,
+ .flags = IORESOURCE_IRQ
+ },
+};
+
+static struct platform_device smc91c111_device = {
+ .name = "smc91x",
+ .id = -1,
+ .num_resources = ARRAY_SIZE(smc91c111_resources),
+ .resource = smc91c111_resources
+};
+
+static struct platform_device *board_platform_devices[] __initdata = {
+ &ide_device,
+ &smc91c111_device
+};
+
+static int __init board_register_devices(void)
+{
+ return platform_add_devices(board_platform_devices,
+ ARRAY_SIZE(board_platform_devices));
+}
+
+arch_initcall(board_register_devices);
diff --git a/arch/mips/au1000/pb1500/board_setup.c b/arch/mips/au1000/pb1500/board_setup.c
index 5446836869d..24c652e8ec4 100644
--- a/arch/mips/au1000/pb1500/board_setup.c
+++ b/arch/mips/au1000/pb1500/board_setup.c
@@ -23,19 +23,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-pb1x00/pb1500.h>
diff --git a/arch/mips/au1000/pb1500/init.c b/arch/mips/au1000/pb1500/init.c
index db558c96704..488507c07db 100644
--- a/arch/mips/au1000/pb1500/init.c
+++ b/arch/mips/au1000/pb1500/init.c
@@ -27,14 +27,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/pb1500/irqmap.c b/arch/mips/au1000/pb1500/irqmap.c
index 810f695e24b..4817ab44d07 100644
--- a/arch/mips/au1000/pb1500/irqmap.c
+++ b/arch/mips/au1000/pb1500/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
char irq_tab_alchemy[][5] __initdata = {
diff --git a/arch/mips/au1000/pb1550/board_setup.c b/arch/mips/au1000/pb1550/board_setup.c
index e3cfb0d7318..45d60872b56 100644
--- a/arch/mips/au1000/pb1550/board_setup.c
+++ b/arch/mips/au1000/pb1550/board_setup.c
@@ -27,20 +27,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
-#include <linux/mc146818rtc.h>
-#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
#include <asm/mach-pb1x00/pb1550.h>
diff --git a/arch/mips/au1000/pb1550/init.c b/arch/mips/au1000/pb1550/init.c
index b716363ea56..f6b2fc58798 100644
--- a/arch/mips/au1000/pb1550/init.c
+++ b/arch/mips/au1000/pb1550/init.c
@@ -27,14 +27,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/pb1550/irqmap.c b/arch/mips/au1000/pb1550/irqmap.c
index 56becab28e5..e1dac37af08 100644
--- a/arch/mips/au1000/pb1550/irqmap.c
+++ b/arch/mips/au1000/pb1550/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
char irq_tab_alchemy[][5] __initdata = {
diff --git a/arch/mips/au1000/xxs1500/board_setup.c b/arch/mips/au1000/xxs1500/board_setup.c
index b2e413e597a..79d1798621b 100644
--- a/arch/mips/au1000/xxs1500/board_setup.c
+++ b/arch/mips/au1000/xxs1500/board_setup.c
@@ -23,19 +23,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/console.h>
#include <linux/delay.h>
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
#include <asm/mach-au1x00/au1000.h>
void board_reset(void)
diff --git a/arch/mips/au1000/xxs1500/init.c b/arch/mips/au1000/xxs1500/init.c
index 7e6878c1b0a..24fc6e132dc 100644
--- a/arch/mips/au1000/xxs1500/init.c
+++ b/arch/mips/au1000/xxs1500/init.c
@@ -26,14 +26,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
+
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/string.h>
#include <linux/kernel.h>
-#include <asm/addrspace.h>
#include <asm/bootinfo.h>
#include <prom.h>
diff --git a/arch/mips/au1000/xxs1500/irqmap.c b/arch/mips/au1000/xxs1500/irqmap.c
index a343da13433..dd6e3d1eb4d 100644
--- a/arch/mips/au1000/xxs1500/irqmap.c
+++ b/arch/mips/au1000/xxs1500/irqmap.c
@@ -25,26 +25,9 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/errno.h>
+
#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/ioport.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/delay.h>
-#include <linux/bitops.h>
-#include <asm/bootinfo.h>
-#include <asm/io.h>
-#include <asm/mipsregs.h>
-#include <asm/system.h>
#include <asm/mach-au1x00/au1000.h>
struct au1xxx_irqmap __initdata au1xxx_irq_map[] = {
diff --git a/arch/mips/configs/mipssim_defconfig b/arch/mips/configs/mipssim_defconfig
index 6db0bdaefb2..4f6bce99d5c 100644
--- a/arch/mips/configs/mipssim_defconfig
+++ b/arch/mips/configs/mipssim_defconfig
@@ -641,7 +641,6 @@ CONFIG_CROSSCOMPILE=y
CONFIG_CMDLINE="nfsroot=192.168.192.169:/u1/mipsel,timeo=20 ip=dhcp"
# CONFIG_DEBUG_STACK_USAGE is not set
# CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
#
# Security options
diff --git a/arch/mips/configs/pnx8550-jbs_defconfig b/arch/mips/configs/pnx8550-jbs_defconfig
index 518a60892b7..780c7fc24b8 100644
--- a/arch/mips/configs/pnx8550-jbs_defconfig
+++ b/arch/mips/configs/pnx8550-jbs_defconfig
@@ -1223,7 +1223,6 @@ CONFIG_CMDLINE="console=ttyS1,38400n8 kgdb=ttyS0 root=/dev/nfs ip=bootp"
# CONFIG_KGDB is not set
CONFIG_SYS_SUPPORTS_KGDB=y
# CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
#
# Security options
diff --git a/arch/mips/configs/pnx8550-stb810_defconfig b/arch/mips/configs/pnx8550-stb810_defconfig
index 68351eb81bc..267f21ed1d0 100644
--- a/arch/mips/configs/pnx8550-stb810_defconfig
+++ b/arch/mips/configs/pnx8550-stb810_defconfig
@@ -1213,7 +1213,6 @@ CONFIG_CMDLINE="console=ttyS1,38400n8 kgdb=ttyS0 root=/dev/nfs ip=bootp"
# CONFIG_KGDB is not set
CONFIG_SYS_SUPPORTS_KGDB=y
# CONFIG_RUNTIME_DEBUG is not set
-# CONFIG_MIPS_UNCACHED is not set
#
# Security options
diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c
index 60349062595..3965fda94a8 100644
--- a/arch/mips/dec/time.c
+++ b/arch/mips/dec/time.c
@@ -9,30 +9,15 @@
*
*/
#include <linux/bcd.h>
-#include <linux/errno.h>
#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
#include <linux/mc146818rtc.h>
-#include <linux/mm.h>
-#include <linux/module.h>
#include <linux/param.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/types.h>
-
-#include <asm/bootinfo.h>
-#include <asm/cpu.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/sections.h>
-#include <asm/time.h>
+#include <asm/cpu-features.h>
+#include <asm/ds1287.h>
+#include <asm/time.h>
#include <asm/dec/interrupts.h>
#include <asm/dec/ioasic.h>
-#include <asm/dec/ioasic_addrs.h>
#include <asm/dec/machtype.h>
unsigned long read_persistent_clock(void)
@@ -139,42 +124,32 @@ int rtc_mips_set_mmss(unsigned long nowtime)
return retval;
}
-static int dec_timer_state(void)
+void __init plat_time_init(void)
{
- return (CMOS_READ(RTC_REG_C) & RTC_PF) != 0;
-}
+ u32 start, end;
+ int i = HZ / 10;
-static void dec_timer_ack(void)
-{
- CMOS_READ(RTC_REG_C); /* Ack the RTC interrupt. */
-}
-
-static cycle_t dec_ioasic_hpt_read(void)
-{
- /*
- * The free-running counter is 32-bit which is good for about
- * 2 minutes, 50 seconds at possible count rates of up to 25MHz.
- */
- return ioasic_read(IO_REG_FCTR);
-}
+ /* Set up the rate of periodic DS1287 interrupts. */
+ ds1287_set_base_clock(HZ);
+ if (cpu_has_counter) {
+ while (!ds1287_timer_state())
+ ;
-void __init plat_time_init(void)
-{
- mips_timer_ack = dec_timer_ack;
+ start = read_c0_count();
- if (!cpu_has_counter && IOASIC)
- /* For pre-R4k systems we use the I/O ASIC's counter. */
- clocksource_mips.read = dec_ioasic_hpt_read;
+ while (i--)
+ while (!ds1287_timer_state())
+ ;
- /* Set up the rate of periodic DS1287 interrupts. */
- CMOS_WRITE(RTC_REF_CLCK_32KHZ | (16 - __ffs(HZ)), RTC_REG_A);
-}
+ end = read_c0_count();
-void __init plat_timer_setup(struct irqaction *irq)
-{
- setup_irq(dec_interrupt[DEC_IRQ_RTC], irq);
+ mips_hpt_frequency = (end - start) * 10;
+ printk(KERN_INFO "MIPS counter frequency %dHz\n",
+ mips_hpt_frequency);
+ } else if (IOASIC)
+ /* For pre-R4k systems we use the I/O ASIC's counter. */
+ dec_ioasic_clocksource_init();
- /* Enable periodic DS1287 interrupts. */
- CMOS_WRITE(CMOS_READ(RTC_REG_B) | RTC_PIE, RTC_REG_B);
+ ds1287_clockevent_init(dec_interrupt[DEC_IRQ_RTC]);
}
diff --git a/arch/mips/jmr3927/rbhma3100/setup.c b/arch/mips/jmr3927/rbhma3100/setup.c
index c886d804d30..f39c444e42d 100644
--- a/arch/mips/jmr3927/rbhma3100/setup.c
+++ b/arch/mips/jmr3927/rbhma3100/setup.c
@@ -36,11 +36,13 @@
#include <linux/pm.h>
#include <linux/platform_device.h>
#include <linux/clk.h>
+#include <linux/gpio.h>
#ifdef CONFIG_SERIAL_TXX9
#include <linux/serial_core.h>
#endif
#include <asm/txx9tmr.h>
+#include <asm/txx9pio.h>
#include <asm/reboot.h>
#include <asm/jmr3927/jmr3927.h>
#include <asm/mipsregs.h>
@@ -340,9 +342,12 @@ static void __init tx3927_setup(void)
/* PIO */
/* PIO[15:12] connected to LEDs */
- tx3927_pioptr->dir = 0x0000f000;
- tx3927_pioptr->maskcpu = 0;
- tx3927_pioptr->maskext = 0;
+ __raw_writel(0x0000f000, &tx3927_pioptr->dir);
+ __raw_writel(0, &tx3927_pioptr->maskcpu);
+ __raw_writel(0, &tx3927_pioptr->maskext);
+ txx9_gpio_init(TX3927_PIO_REG, 0, 16);
+ gpio_request(11, "dipsw1");
+ gpio_request(10, "dipsw2");
{
unsigned int conf;
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 6fcdb6fda2e..45545be3eb8 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -10,12 +10,15 @@ obj-y += cpu-probe.o branch.o entry.o genex.o irq.o process.o \
obj-$(CONFIG_CEVT_BCM1480) += cevt-bcm1480.o
obj-$(CONFIG_CEVT_R4K) += cevt-r4k.o
+obj-$(CONFIG_CEVT_DS1287) += cevt-ds1287.o
obj-$(CONFIG_CEVT_GT641XX) += cevt-gt641xx.o
obj-$(CONFIG_CEVT_SB1250) += cevt-sb1250.o
obj-$(CONFIG_CEVT_TXX9) += cevt-txx9.o
obj-$(CONFIG_CSRC_BCM1480) += csrc-bcm1480.o
+obj-$(CONFIG_CSRC_IOASIC) += csrc-ioasic.o
obj-$(CONFIG_CSRC_R4K) += csrc-r4k.o
obj-$(CONFIG_CSRC_SB1250) += csrc-sb1250.o
+obj-$(CONFIG_SYNC_R4K) += sync-r4k.o
binfmt_irix-objs := irixelf.o irixinv.o irixioctl.o irixsig.o \
irix5sys.o sysirix.o
@@ -50,6 +53,8 @@ obj-$(CONFIG_MIPS_MT) += mips-mt.o
obj-$(CONFIG_MIPS_MT_FPAFF) += mips-mt-fpaff.o
obj-$(CONFIG_MIPS_MT_SMTC) += smtc.o smtc-asm.o smtc-proc.o
obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o
+obj-$(CONFIG_MIPS_CMP) += smp-cmp.o
+obj-$(CONFIG_CPU_MIPSR2) += spram.o
obj-$(CONFIG_MIPS_APSP_KSPD) += kspd.o
obj-$(CONFIG_MIPS_VPE_LOADER) += vpe.o
@@ -62,6 +67,7 @@ obj-$(CONFIG_IRQ_CPU_RM9K) += irq-rm9000.o
obj-$(CONFIG_MIPS_BOARDS_GEN) += irq-msc01.o
obj-$(CONFIG_IRQ_TXX9) += irq_txx9.o
obj-$(CONFIG_IRQ_GT641XX) += irq-gt641xx.o
+obj-$(CONFIG_IRQ_GIC) += irq-gic.o
obj-$(CONFIG_32BIT) += scall32-o32.o
obj-$(CONFIG_64BIT) += scall64-64.o
@@ -77,6 +83,8 @@ obj-$(CONFIG_64BIT) += cpu-bugs64.o
obj-$(CONFIG_I8253) += i8253.o
+obj-$(CONFIG_GPIO_TXX9) += gpio_txx9.o
+
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index ca136298acd..5bf03b3c415 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -17,252 +17,252 @@
#include <asm/ptrace.h>
#include <asm/processor.h>
-#define text(t) __asm__("\n@@@" t)
+#define text(t) __asm__("\n->#" t)
#define _offset(type, member) (&(((type *)NULL)->member))
#define offset(string, ptr, member) \
- __asm__("\n@@@" string "%0" : : "i" (_offset(ptr, member)))
+ __asm__("\n->" string " %0" : : "i" (_offset(ptr, member)))
#define constant(string, member) \
- __asm__("\n@@@" string "%X0" : : "ri" (member))
+ __asm__("\n->" string " %0" : : "ri" (member))
#define size(string, size) \
- __asm__("\n@@@" string "%0" : : "i" (sizeof(size)))
+ __asm__("\n->" string " %0" : : "i" (sizeof(size)))
#define linefeed text("")
void output_ptreg_defines(void)
{
- text("/* MIPS pt_regs offsets. */");
- offset("#define PT_R0 ", struct pt_regs, regs[0]);
- offset("#define PT_R1 ", struct pt_regs, regs[1]);
- offset("#define PT_R2 ", struct pt_regs, regs[2]);
- offset("#define PT_R3 ", struct pt_regs, regs[3]);
- offset("#define PT_R4 ", struct pt_regs, regs[4]);
- offset("#define PT_R5 ", struct pt_regs, regs[5]);
- offset("#define PT_R6 ", struct pt_regs, regs[6]);
- offset("#define PT_R7 ", struct pt_regs, regs[7]);
- offset("#define PT_R8 ", struct pt_regs, regs[8]);
- offset("#define PT_R9 ", struct pt_regs, regs[9]);
- offset("#define PT_R10 ", struct pt_regs, regs[10]);
- offset("#define PT_R11 ", struct pt_regs, regs[11]);
- offset("#define PT_R12 ", struct pt_regs, regs[12]);
- offset("#define PT_R13 ", struct pt_regs, regs[13]);
- offset("#define PT_R14 ", struct pt_regs, regs[14]);
- offset("#define PT_R15 ", struct pt_regs, regs[15]);
- offset("#define PT_R16 ", struct pt_regs, regs[16]);
- offset("#define PT_R17 ", struct pt_regs, regs[17]);
- offset("#define PT_R18 ", struct pt_regs, regs[18]);
- offset("#define PT_R19 ", struct pt_regs, regs[19]);
- offset("#define PT_R20 ", struct pt_regs, regs[20]);
- offset("#define PT_R21 ", struct pt_regs, regs[21]);
- offset("#define PT_R22 ", struct pt_regs, regs[22]);
- offset("#define PT_R23 ", struct pt_regs, regs[23]);
- offset("#define PT_R24 ", struct pt_regs, regs[24]);
- offset("#define PT_R25 ", struct pt_regs, regs[25]);
- offset("#define PT_R26 ", struct pt_regs, regs[26]);
- offset("#define PT_R27 ", struct pt_regs, regs[27]);
- offset("#define PT_R28 ", struct pt_regs, regs[28]);
- offset("#define PT_R29 ", struct pt_regs, regs[29]);
- offset("#define PT_R30 ", struct pt_regs, regs[30]);
- offset("#define PT_R31 ", struct pt_regs, regs[31]);
- offset("#define PT_LO ", struct pt_regs, lo);
- offset("#define PT_HI ", struct pt_regs, hi);
+ text("MIPS pt_regs offsets.");
+ offset("PT_R0", struct pt_regs, regs[0]);
+ offset("PT_R1", struct pt_regs, regs[1]);
+ offset("PT_R2", struct pt_regs, regs[2]);
+ offset("PT_R3", struct pt_regs, regs[3]);
+ offset("PT_R4", struct pt_regs, regs[4]);
+ offset("PT_R5", struct pt_regs, regs[5]);
+ offset("PT_R6", struct pt_regs, regs[6]);
+ offset("PT_R7", struct pt_regs, regs[7]);
+ offset("PT_R8", struct pt_regs, regs[8]);
+ offset("PT_R9", struct pt_regs, regs[9]);
+ offset("PT_R10", struct pt_regs, regs[10]);
+ offset("PT_R11", struct pt_regs, regs[11]);
+ offset("PT_R12", struct pt_regs, regs[12]);
+ offset("PT_R13", struct pt_regs, regs[13]);
+ offset("PT_R14", struct pt_regs, regs[14]);
+ offset("PT_R15", struct pt_regs, regs[15]);
+ offset("PT_R16", struct pt_regs, regs[16]);
+ offset("PT_R17", struct pt_regs, regs[17]);
+ offset("PT_R18", struct pt_regs, regs[18]);
+ offset("PT_R19", struct pt_regs, regs[19]);
+ offset("PT_R20", struct pt_regs, regs[20]);
+ offset("PT_R21", struct pt_regs, regs[21]);
+ offset("PT_R22", struct pt_regs, regs[22]);
+ offset("PT_R23", struct pt_regs, regs[23]);
+ offset("PT_R24", struct pt_regs, regs[24]);
+ offset("PT_R25", struct pt_regs, regs[25]);
+ offset("PT_R26", struct pt_regs, regs[26]);
+ offset("PT_R27", struct pt_regs, regs[27]);
+ offset("PT_R28", struct pt_regs, regs[28]);
+ offset("PT_R29", struct pt_regs, regs[29]);
+ offset("PT_R30", struct pt_regs, regs[30]);
+ offset("PT_R31", struct pt_regs, regs[31]);
+ offset("PT_LO", struct pt_regs, lo);
+ offset("PT_HI", struct pt_regs, hi);
#ifdef CONFIG_CPU_HAS_SMARTMIPS
- offset("#define PT_ACX ", struct pt_regs, acx);
+ offset("PT_ACX", struct pt_regs, acx);
#endif
- offset("#define PT_EPC ", struct pt_regs, cp0_epc);
- offset("#define PT_BVADDR ", struct pt_regs, cp0_badvaddr);
- offset("#define PT_STATUS ", struct pt_regs, cp0_status);
- offset("#define PT_CAUSE ", struct pt_regs, cp0_cause);
+ offset("PT_EPC", struct pt_regs, cp0_epc);
+ offset("PT_BVADDR", struct pt_regs, cp0_badvaddr);
+ offset("PT_STATUS", struct pt_regs, cp0_status);
+ offset("PT_CAUSE", struct pt_regs, cp0_cause);
#ifdef CONFIG_MIPS_MT_SMTC
- offset("#define PT_TCSTATUS ", struct pt_regs, cp0_tcstatus);
+ offset("PT_TCSTATUS", struct pt_regs, cp0_tcstatus);
#endif /* CONFIG_MIPS_MT_SMTC */
- size("#define PT_SIZE ", struct pt_regs);
+ size("PT_SIZE", struct pt_regs);
linefeed;
}
void output_task_defines(void)
{
- text("/* MIPS task_struct offsets. */");
- offset("#define TASK_STATE ", struct task_struct, state);
- offset("#define TASK_THREAD_INFO ", struct task_struct, stack);
- offset("#define TASK_FLAGS ", struct task_struct, flags);
- offset("#define TASK_MM ", struct task_struct, mm);
- offset("#define TASK_PID ", struct task_struct, pid);
- size( "#define TASK_STRUCT_SIZE ", struct task_struct);
+ text("MIPS task_struct offsets.");
+ offset("TASK_STATE", struct task_struct, state);
+ offset("TASK_THREAD_INFO", struct task_struct, stack);
+ offset("TASK_FLAGS", struct task_struct, flags);
+ offset("TASK_MM", struct task_struct, mm);
+ offset("TASK_PID", struct task_struct, pid);
+ size( "TASK_STRUCT_SIZE", struct task_struct);
linefeed;
}
void output_thread_info_defines(void)
{
- text("/* MIPS thread_info offsets. */");
- offset("#define TI_TASK ", struct thread_info, task);
- offset("#define TI_EXEC_DOMAIN ", struct thread_info, exec_domain);
- offset("#define TI_FLAGS ", struct thread_info, flags);
- offset("#define TI_TP_VALUE ", struct thread_info, tp_value);
- offset("#define TI_CPU ", struct thread_info, cpu);
- offset("#define TI_PRE_COUNT ", struct thread_info, preempt_count);
- offset("#define TI_ADDR_LIMIT ", struct thread_info, addr_limit);
- offset("#define TI_RESTART_BLOCK ", struct thread_info, restart_block);
- offset("#define TI_REGS ", struct thread_info, regs);
- constant("#define _THREAD_SIZE ", THREAD_SIZE);
- constant("#define _THREAD_MASK ", THREAD_MASK);
+ text("MIPS thread_info offsets.");
+ offset("TI_TASK", struct thread_info, task);
+ offset("TI_EXEC_DOMAIN", struct thread_info, exec_domain);
+ offset("TI_FLAGS", struct thread_info, flags);
+ offset("TI_TP_VALUE", struct thread_info, tp_value);
+ offset("TI_CPU", struct thread_info, cpu);
+ offset("TI_PRE_COUNT", struct thread_info, preempt_count);
+ offset("TI_ADDR_LIMIT", struct thread_info, addr_limit);
+ offset("TI_RESTART_BLOCK", struct thread_info, restart_block);
+ offset("TI_REGS", struct thread_info, regs);
+ constant("_THREAD_SIZE", THREAD_SIZE);
+ constant("_THREAD_MASK", THREAD_MASK);
linefeed;
}
void output_thread_defines(void)
{
- text("/* MIPS specific thread_struct offsets. */");
- offset("#define THREAD_REG16 ", struct task_struct, thread.reg16);
- offset("#define THREAD_REG17 ", struct task_struct, thread.reg17);
- offset("#define THREAD_REG18 ", struct task_struct, thread.reg18);
- offset("#define THREAD_REG19 ", struct task_struct, thread.reg19);
- offset("#define THREAD_REG20 ", struct task_struct, thread.reg20);
- offset("#define THREAD_REG21 ", struct task_struct, thread.reg21);
- offset("#define THREAD_REG22 ", struct task_struct, thread.reg22);
- offset("#define THREAD_REG23 ", struct task_struct, thread.reg23);
- offset("#define THREAD_REG29 ", struct task_struct, thread.reg29);
- offset("#define THREAD_REG30 ", struct task_struct, thread.reg30);
- offset("#define THREAD_REG31 ", struct task_struct, thread.reg31);
- offset("#define THREAD_STATUS ", struct task_struct,
+ text("MIPS specific thread_struct offsets.");
+ offset("THREAD_REG16", struct task_struct, thread.reg16);
+ offset("THREAD_REG17", struct task_struct, thread.reg17);
+ offset("THREAD_REG18", struct task_struct, thread.reg18);
+ offset("THREAD_REG19", struct task_struct, thread.reg19);
+ offset("THREAD_REG20", struct task_struct, thread.reg20);
+ offset("THREAD_REG21", struct task_struct, thread.reg21);
+ offset("THREAD_REG22", struct task_struct, thread.reg22);
+ offset("THREAD_REG23", struct task_struct, thread.reg23);
+ offset("THREAD_REG29", struct task_struct, thread.reg29);
+ offset("THREAD_REG30", struct task_struct, thread.reg30);
+ offset("THREAD_REG31", struct task_struct, thread.reg31);
+ offset("THREAD_STATUS", struct task_struct,
thread.cp0_status);
- offset("#define THREAD_FPU ", struct task_struct, thread.fpu);
+ offset("THREAD_FPU", struct task_struct, thread.fpu);
- offset("#define THREAD_BVADDR ", struct task_struct, \
+ offset("THREAD_BVADDR", struct task_struct, \
thread.cp0_badvaddr);
- offset("#define THREAD_BUADDR ", struct task_struct, \
+ offset("THREAD_BUADDR", struct task_struct, \
thread.cp0_baduaddr);
- offset("#define THREAD_ECODE ", struct task_struct, \
+ offset("THREAD_ECODE", struct task_struct, \
thread.error_code);
- offset("#define THREAD_TRAPNO ", struct task_struct, thread.trap_no);
- offset("#define THREAD_TRAMP ", struct task_struct, \
+ offset("THREAD_TRAPNO", struct task_struct, thread.trap_no);
+ offset("THREAD_TRAMP", struct task_struct, \
thread.irix_trampoline);
- offset("#define THREAD_OLDCTX ", struct task_struct, \
+ offset("THREAD_OLDCTX", struct task_struct, \
thread.irix_oldctx);
linefeed;
}
void output_thread_fpu_defines(void)
{
- offset("#define THREAD_FPR0 ",
+ offset("THREAD_FPR0",
struct task_struct, thread.fpu.fpr[0]);
- offset("#define THREAD_FPR1 ",
+ offset("THREAD_FPR1",
struct task_struct, thread.fpu.fpr[1]);
- offset("#define THREAD_FPR2 ",
+ offset("THREAD_FPR2",
struct task_struct, thread.fpu.fpr[2]);
- offset("#define THREAD_FPR3 ",
+ offset("THREAD_FPR3",
struct task_struct, thread.fpu.fpr[3]);
- offset("#define THREAD_FPR4 ",
+ offset("THREAD_FPR4",
struct task_struct, thread.fpu.fpr[4]);
- offset("#define THREAD_FPR5 ",
+ offset("THREAD_FPR5",
struct task_struct, thread.fpu.fpr[5]);
- offset("#define THREAD_FPR6 ",
+ offset("THREAD_FPR6",
struct task_struct, thread.fpu.fpr[6]);
- offset("#define THREAD_FPR7 ",
+ offset("THREAD_FPR7",
struct task_struct, thread.fpu.fpr[7]);
- offset("#define THREAD_FPR8 ",
+ offset("THREAD_FPR8",
struct task_struct, thread.fpu.fpr[8]);
- offset("#define THREAD_FPR9 ",
+ offset("THREAD_FPR9",
struct task_struct, thread.fpu.fpr[9]);
- offset("#define THREAD_FPR10 ",
+ offset("THREAD_FPR10",
struct task_struct, thread.fpu.fpr[10]);
- offset("#define THREAD_FPR11 ",
+ offset("THREAD_FPR11",
struct task_struct, thread.fpu.fpr[11]);
- offset("#define THREAD_FPR12 ",
+ offset("THREAD_FPR12",
struct task_struct, thread.fpu.fpr[12]);
- offset("#define THREAD_FPR13 ",
+ offset("THREAD_FPR13",
struct task_struct, thread.fpu.fpr[13]);
- offset("#define THREAD_FPR14 ",
+ offset("THREAD_FPR14",
struct task_struct, thread.fpu.fpr[14]);
- offset("#define THREAD_FPR15 ",
+ offset("THREAD_FPR15",
struct task_struct, thread.fpu.fpr[15]);
- offset("#define THREAD_FPR16 ",
+ offset("THREAD_FPR16",
struct task_struct, thread.fpu.fpr[16]);
- offset("#define THREAD_FPR17 ",
+ offset("THREAD_FPR17",
struct task_struct, thread.fpu.fpr[17]);
- offset("#define THREAD_FPR18 ",
+ offset("THREAD_FPR18",
struct task_struct, thread.fpu.fpr[18]);
- offset("#define THREAD_FPR19 ",
+ offset("THREAD_FPR19",
struct task_struct, thread.fpu.fpr[19]);
- offset("#define THREAD_FPR20 ",
+ offset("THREAD_FPR20",
struct task_struct, thread.fpu.fpr[20]);
- offset("#define THREAD_FPR21 ",
+ offset("THREAD_FPR21",
struct task_struct, thread.fpu.fpr[21]);
- offset("#define THREAD_FPR22 ",
+ offset("THREAD_FPR22",
struct task_struct, thread.fpu.fpr[22]);
- offset("#define THREAD_FPR23 ",
+ offset("THREAD_FPR23",
struct task_struct, thread.fpu.fpr[23]);
- offset("#define THREAD_FPR24 ",
+ offset("THREAD_FPR24",
struct task_struct, thread.fpu.fpr[24]);
- offset("#define THREAD_FPR25 ",
+ offset("THREAD_FPR25",
struct task_struct, thread.fpu.fpr[25]);
- offset("#define THREAD_FPR26 ",
+ offset("THREAD_FPR26",
struct task_struct, thread.fpu.fpr[26]);
- offset("#define THREAD_FPR27 ",
+ offset("THREAD_FPR27",
struct task_struct, thread.fpu.fpr[27]);
- offset("#define THREAD_FPR28 ",
+ offset("THREAD_FPR28",
struct task_struct, thread.fpu.fpr[28]);
- offset("#define THREAD_FPR29 ",
+ offset("THREAD_FPR29",
struct task_struct, thread.fpu.fpr[29]);
- offset("#define THREAD_FPR30 ",
+ offset("THREAD_FPR30",
struct task_struct, thread.fpu.fpr[30]);
- offset("#define THREAD_FPR31 ",
+ offset("THREAD_FPR31",
struct task_struct, thread.fpu.fpr[31]);
- offset("#define THREAD_FCR31 ",
+ offset("THREAD_FCR31",
struct task_struct, thread.fpu.fcr31);
linefeed;
}
void output_mm_defines(void)
{
- text("/* Size of struct page */");
- size("#define STRUCT_PAGE_SIZE ", struct page);
+ text("Size of struct page");
+ size("STRUCT_PAGE_SIZE", struct page);
linefeed;
- text("/* Linux mm_struct offsets. */");
- offset("#define MM_USERS ", struct mm_struct, mm_users);
- offset("#define MM_PGD ", struct mm_struct, pgd);
- offset("#define MM_CONTEXT ", struct mm_struct, context);
+ text("Linux mm_struct offsets.");
+ offset("MM_USERS", struct mm_struct, mm_users);
+ offset("MM_PGD", struct mm_struct, pgd);
+ offset("MM_CONTEXT", struct mm_struct, context);
linefeed;
- constant("#define _PAGE_SIZE ", PAGE_SIZE);
- constant("#define _PAGE_SHIFT ", PAGE_SHIFT);
+ constant("_PAGE_SIZE", PAGE_SIZE);
+ constant("_PAGE_SHIFT", PAGE_SHIFT);
linefeed;
- constant("#define _PGD_T_SIZE ", sizeof(pgd_t));
- constant("#define _PMD_T_SIZE ", sizeof(pmd_t));
- constant("#define _PTE_T_SIZE ", sizeof(pte_t));
+ constant("_PGD_T_SIZE", sizeof(pgd_t));
+ constant("_PMD_T_SIZE", sizeof(pmd_t));
+ constant("_PTE_T_SIZE", sizeof(pte_t));
linefeed;
- constant("#define _PGD_T_LOG2 ", PGD_T_LOG2);
- constant("#define _PMD_T_LOG2 ", PMD_T_LOG2);
- constant("#define _PTE_T_LOG2 ", PTE_T_LOG2);
+ constant("_PGD_T_LOG2", PGD_T_LOG2);
+ constant("_PMD_T_LOG2", PMD_T_LOG2);
+ constant("_PTE_T_LOG2", PTE_T_LOG2);
linefeed;
- constant("#define _PGD_ORDER ", PGD_ORDER);
- constant("#define _PMD_ORDER ", PMD_ORDER);
- constant("#define _PTE_ORDER ", PTE_ORDER);
+ constant("_PGD_ORDER", PGD_ORDER);
+ constant("_PMD_ORDER", PMD_ORDER);
+ constant("_PTE_ORDER", PTE_ORDER);
linefeed;
- constant("#define _PMD_SHIFT ", PMD_SHIFT);
- constant("#define _PGDIR_SHIFT ", PGDIR_SHIFT);
+ constant("_PMD_SHIFT", PMD_SHIFT);
+ constant("_PGDIR_SHIFT", PGDIR_SHIFT);
linefeed;
- constant("#define _PTRS_PER_PGD ", PTRS_PER_PGD);
- constant("#define _PTRS_PER_PMD ", PTRS_PER_PMD);
- constant("#define _PTRS_PER_PTE ", PTRS_PER_PTE);
+ constant("_PTRS_PER_PGD", PTRS_PER_PGD);
+ constant("_PTRS_PER_PMD", PTRS_PER_PMD);
+ constant("_PTRS_PER_PTE", PTRS_PER_PTE);
linefeed;
}
#ifdef CONFIG_32BIT
void output_sc_defines(void)
{
- text("/* Linux sigcontext offsets. */");
- offset("#define SC_REGS ", struct sigcontext, sc_regs);
- offset("#define SC_FPREGS ", struct sigcontext, sc_fpregs);
- offset("#define SC_ACX ", struct sigcontext, sc_acx);
- offset("#define SC_MDHI ", struct sigcontext, sc_mdhi);
- offset("#define SC_MDLO ", struct sigcontext, sc_mdlo);
- offset("#define SC_PC ", struct sigcontext, sc_pc);
- offset("#define SC_FPC_CSR ", struct sigcontext, sc_fpc_csr);
- offset("#define SC_FPC_EIR ", struct sigcontext, sc_fpc_eir);
- offset("#define SC_HI1 ", struct sigcontext, sc_hi1);
- offset("#define SC_LO1 ", struct sigcontext, sc_lo1);
- offset("#define SC_HI2 ", struct sigcontext, sc_hi2);
- offset("#define SC_LO2 ", struct sigcontext, sc_lo2);
- offset("#define SC_HI3 ", struct sigcontext, sc_hi3);
- offset("#define SC_LO3 ", struct sigcontext, sc_lo3);
+ text("Linux sigcontext offsets.");
+ offset("SC_REGS", struct sigcontext, sc_regs);
+ offset("SC_FPREGS", struct sigcontext, sc_fpregs);
+ offset("SC_ACX", struct sigcontext, sc_acx);
+ offset("SC_MDHI", struct sigcontext, sc_mdhi);
+ offset("SC_MDLO", struct sigcontext, sc_mdlo);
+ offset("SC_PC", struct sigcontext, sc_pc);
+ offset("SC_FPC_CSR", struct sigcontext, sc_fpc_csr);
+ offset("SC_FPC_EIR", struct sigcontext, sc_fpc_eir);
+ offset("SC_HI1", struct sigcontext, sc_hi1);
+ offset("SC_LO1", struct sigcontext, sc_lo1);
+ offset("SC_HI2", struct sigcontext, sc_hi2);
+ offset("SC_LO2", struct sigcontext, sc_lo2);
+ offset("SC_HI3", struct sigcontext, sc_hi3);
+ offset("SC_LO3", struct sigcontext, sc_lo3);
linefeed;
}
#endif
@@ -270,13 +270,13 @@ void output_sc_defines(void)
#ifdef CONFIG_64BIT
void output_sc_defines(void)
{
- text("/* Linux sigcontext offsets. */");
- offset("#define SC_REGS ", struct sigcontext, sc_regs);
- offset("#define SC_FPREGS ", struct sigcontext, sc_fpregs);
- offset("#define SC_MDHI ", struct sigcontext, sc_mdhi);
- offset("#define SC_MDLO ", struct sigcontext, sc_mdlo);
- offset("#define SC_PC ", struct sigcontext, sc_pc);
- offset("#define SC_FPC_CSR ", struct sigcontext, sc_fpc_csr);
+ text("Linux sigcontext offsets.");
+ offset("SC_REGS", struct sigcontext, sc_regs);
+ offset("SC_FPREGS", struct sigcontext, sc_fpregs);
+ offset("SC_MDHI", struct sigcontext, sc_mdhi);
+ offset("SC_MDLO", struct sigcontext, sc_mdlo);
+ offset("SC_PC", struct sigcontext, sc_pc);
+ offset("SC_FPC_CSR", struct sigcontext, sc_fpc_csr);
linefeed;
}
#endif
@@ -284,56 +284,56 @@ void output_sc_defines(void)
#ifdef CONFIG_MIPS32_COMPAT
void output_sc32_defines(void)
{
- text("/* Linux 32-bit sigcontext offsets. */");
- offset("#define SC32_FPREGS ", struct sigcontext32, sc_fpregs);
- offset("#define SC32_FPC_CSR ", struct sigcontext32, sc_fpc_csr);
- offset("#define SC32_FPC_EIR ", struct sigcontext32, sc_fpc_eir);
+ text("Linux 32-bit sigcontext offsets.");
+ offset("SC32_FPREGS", struct sigcontext32, sc_fpregs);
+ offset("SC32_FPC_CSR", struct sigcontext32, sc_fpc_csr);
+ offset("SC32_FPC_EIR", struct sigcontext32, sc_fpc_eir);
linefeed;
}
#endif
void output_signal_defined(void)
{
- text("/* Linux signal numbers. */");
- constant("#define _SIGHUP ", SIGHUP);
- constant("#define _SIGINT ", SIGINT);
- constant("#define _SIGQUIT ", SIGQUIT);
- constant("#define _SIGILL ", SIGILL);
- constant("#define _SIGTRAP ", SIGTRAP);
- constant("#define _SIGIOT ", SIGIOT);
- constant("#define _SIGABRT ", SIGABRT);
- constant("#define _SIGEMT ", SIGEMT);
- constant("#define _SIGFPE ", SIGFPE);
- constant("#define _SIGKILL ", SIGKILL);
- constant("#define _SIGBUS ", SIGBUS);
- constant("#define _SIGSEGV ", SIGSEGV);
- constant("#define _SIGSYS ", SIGSYS);
- constant("#define _SIGPIPE ", SIGPIPE);
- constant("#define _SIGALRM ", SIGALRM);
- constant("#define _SIGTERM ", SIGTERM);
- constant("#define _SIGUSR1 ", SIGUSR1);
- constant("#define _SIGUSR2 ", SIGUSR2);
- constant("#define _SIGCHLD ", SIGCHLD);
- constant("#define _SIGPWR ", SIGPWR);
- constant("#define _SIGWINCH ", SIGWINCH);
- constant("#define _SIGURG ", SIGURG);
- constant("#define _SIGIO ", SIGIO);
- constant("#define _SIGSTOP ", SIGSTOP);
- constant("#define _SIGTSTP ", SIGTSTP);
- constant("#define _SIGCONT ", SIGCONT);
- constant("#define _SIGTTIN ", SIGTTIN);
- constant("#define _SIGTTOU ", SIGTTOU);
- constant("#define _SIGVTALRM ", SIGVTALRM);
- constant("#define _SIGPROF ", SIGPROF);
- constant("#define _SIGXCPU ", SIGXCPU);
- constant("#define _SIGXFSZ ", SIGXFSZ);
+ text("Linux signal numbers.");
+ constant("_SIGHUP", SIGHUP);
+ constant("_SIGINT", SIGINT);
+ constant("_SIGQUIT", SIGQUIT);
+ constant("_SIGILL", SIGILL);
+ constant("_SIGTRAP", SIGTRAP);
+ constant("_SIGIOT", SIGIOT);
+ constant("_SIGABRT", SIGABRT);
+ constant("_SIGEMT", SIGEMT);
+ constant("_SIGFPE", SIGFPE);
+ constant("_SIGKILL", SIGKILL);
+ constant("_SIGBUS", SIGBUS);
+ constant("_SIGSEGV", SIGSEGV);
+ constant("_SIGSYS", SIGSYS);
+ constant("_SIGPIPE", SIGPIPE);
+ constant("_SIGALRM", SIGALRM);
+ constant("_SIGTERM", SIGTERM);
+ constant("_SIGUSR1", SIGUSR1);
+ constant("_SIGUSR2", SIGUSR2);
+ constant("_SIGCHLD", SIGCHLD);
+ constant("_SIGPWR", SIGPWR);
+ constant("_SIGWINCH", SIGWINCH);
+ constant("_SIGURG", SIGURG);
+ constant("_SIGIO", SIGIO);
+ constant("_SIGSTOP", SIGSTOP);
+ constant("_SIGTSTP", SIGTSTP);
+ constant("_SIGCONT", SIGCONT);
+ constant("_SIGTTIN", SIGTTIN);
+ constant("_SIGTTOU", SIGTTOU);
+ constant("_SIGVTALRM", SIGVTALRM);
+ constant("_SIGPROF", SIGPROF);
+ constant("_SIGXCPU", SIGXCPU);
+ constant("_SIGXFSZ", SIGXFSZ);
linefeed;
}
void output_irq_cpustat_t_defines(void)
{
- text("/* Linux irq_cpustat_t offsets. */");
- offset("#define IC_SOFTIRQ_PENDING ", irq_cpustat_t, __softirq_pending);
- size("#define IC_IRQ_CPUSTAT_T ", irq_cpustat_t);
+ text("Linux irq_cpustat_t offsets.");
+ offset("IC_SOFTIRQ_PENDING", irq_cpustat_t, __softirq_pending);
+ size("IC_IRQ_CPUSTAT_T", irq_cpustat_t);
linefeed;
}
diff --git a/arch/mips/kernel/cevt-ds1287.c b/arch/mips/kernel/cevt-ds1287.c
new file mode 100644
index 00000000000..df4acb68bfb
--- /dev/null
+++ b/arch/mips/kernel/cevt-ds1287.c
@@ -0,0 +1,129 @@
+/*
+ * DS1287 clockevent driver
+ *
+ * Copyright (C) 2008 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/clockchips.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/mc146818rtc.h>
+
+#include <asm/time.h>
+
+int ds1287_timer_state(void)
+{
+ return (CMOS_READ(RTC_REG_C) & RTC_PF) != 0;
+}
+
+int ds1287_set_base_clock(unsigned int hz)
+{
+ u8 rate;
+
+ switch (hz) {
+ case 128:
+ rate = 0x9;
+ break;
+ case 256:
+ rate = 0x8;
+ break;
+ case 1024:
+ rate = 0x6;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ CMOS_WRITE(RTC_REF_CLCK_32KHZ | rate, RTC_REG_A);
+
+ return 0;
+}
+
+static int ds1287_set_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ return -EINVAL;
+}
+
+static void ds1287_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *evt)
+{
+ u8 val;
+
+ spin_lock(&rtc_lock);
+
+ val = CMOS_READ(RTC_REG_B);
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
+ val |= RTC_PIE;
+ break;
+ default:
+ val &= ~RTC_PIE;
+ break;
+ }
+
+ CMOS_WRITE(val, RTC_REG_B);
+
+ spin_unlock(&rtc_lock);
+}
+
+static void ds1287_event_handler(struct clock_event_device *dev)
+{
+}
+
+static struct clock_event_device ds1287_clockevent = {
+ .name = "ds1287",
+ .features = CLOCK_EVT_FEAT_PERIODIC,
+ .cpumask = CPU_MASK_CPU0,
+ .set_next_event = ds1287_set_next_event,
+ .set_mode = ds1287_set_mode,
+ .event_handler = ds1287_event_handler,
+};
+
+static irqreturn_t ds1287_interrupt(int irq, void *dev_id)
+{
+ struct clock_event_device *cd = &ds1287_clockevent;
+
+ /* Ack the RTC interrupt. */
+ CMOS_READ(RTC_REG_C);
+
+ cd->event_handler(cd);
+
+ return IRQ_HANDLED;
+}
+
+static struct irqaction ds1287_irqaction = {
+ .handler = ds1287_interrupt,
+ .flags = IRQF_DISABLED | IRQF_PERCPU,
+ .name = "ds1287",
+};
+
+int __init ds1287_clockevent_init(int irq)
+{
+ struct clock_event_device *cd;
+
+ cd = &ds1287_clockevent;
+ cd->rating = 100;
+ cd->irq = irq;
+ clockevent_set_clock(cd, 32768);
+ cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+ cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+
+ clockevents_register_device(&ds1287_clockevent);
+
+ return setup_irq(irq, &ds1287_irqaction);
+}
diff --git a/arch/mips/kernel/cevt-gt641xx.c b/arch/mips/kernel/cevt-gt641xx.c
index c36772631fe..6e2f58520af 100644
--- a/arch/mips/kernel/cevt-gt641xx.c
+++ b/arch/mips/kernel/cevt-gt641xx.c
@@ -25,8 +25,6 @@
#include <asm/gt64120.h>
#include <asm/time.h>
-#include <irq.h>
-
static DEFINE_SPINLOCK(gt641xx_timer_lock);
static unsigned int gt641xx_base_clock;
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 89c3304cb93..335a6ae3d59 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -169,6 +169,7 @@ static inline void check_wait(void)
case CPU_24K:
case CPU_34K:
+ case CPU_1004K:
cpu_wait = r4k_wait;
if (read_c0_config7() & MIPS_CONF7_WII)
cpu_wait = r4k_wait_irqoff;
@@ -675,6 +676,12 @@ static void __cpuinit decode_configs(struct cpuinfo_mips *c)
return;
}
+#ifdef CONFIG_CPU_MIPSR2
+extern void spram_config(void);
+#else
+static inline void spram_config(void) {}
+#endif
+
static inline void cpu_probe_mips(struct cpuinfo_mips *c)
{
decode_configs(c);
@@ -711,7 +718,12 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c)
case PRID_IMP_74K:
c->cputype = CPU_74K;
break;
+ case PRID_IMP_1004K:
+ c->cputype = CPU_1004K;
+ break;
}
+
+ spram_config();
}
static inline void cpu_probe_alchemy(struct cpuinfo_mips *c)
@@ -778,7 +790,7 @@ static inline void cpu_probe_sandcraft(struct cpuinfo_mips *c)
}
}
-static inline void cpu_probe_philips(struct cpuinfo_mips *c)
+static inline void cpu_probe_nxp(struct cpuinfo_mips *c)
{
decode_configs(c);
switch (c->processor_id & 0xff00) {
@@ -787,7 +799,7 @@ static inline void cpu_probe_philips(struct cpuinfo_mips *c)
c->isa_level = MIPS_CPU_ISA_M32R1;
break;
default:
- panic("Unknown Philips Core!"); /* REVISIT: die? */
+ panic("Unknown NXP Core!"); /* REVISIT: die? */
break;
}
}
@@ -876,6 +888,7 @@ static __cpuinit const char *cpu_to_name(struct cpuinfo_mips *c)
case CPU_24K: name = "MIPS 24K"; break;
case CPU_25KF: name = "MIPS 25Kf"; break;
case CPU_34K: name = "MIPS 34K"; break;
+ case CPU_1004K: name = "MIPS 1004K"; break;
case CPU_74K: name = "MIPS 74K"; break;
case CPU_VR4111: name = "NEC VR4111"; break;
case CPU_VR4121: name = "NEC VR4121"; break;
@@ -925,8 +938,8 @@ __cpuinit void cpu_probe(void)
case PRID_COMP_SANDCRAFT:
cpu_probe_sandcraft(c);
break;
- case PRID_COMP_PHILIPS:
- cpu_probe_philips(c);
+ case PRID_COMP_NXP:
+ cpu_probe_nxp(c);
break;
default:
c->cputype = CPU_UNKNOWN;
diff --git a/arch/mips/kernel/csrc-ioasic.c b/arch/mips/kernel/csrc-ioasic.c
new file mode 100644
index 00000000000..1d5f63cf899
--- /dev/null
+++ b/arch/mips/kernel/csrc-ioasic.c
@@ -0,0 +1,65 @@
+/*
+ * DEC I/O ASIC's counter clocksource
+ *
+ * Copyright (C) 2008 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/clocksource.h>
+#include <linux/init.h>
+
+#include <asm/ds1287.h>
+#include <asm/time.h>
+#include <asm/dec/ioasic.h>
+#include <asm/dec/ioasic_addrs.h>
+
+static cycle_t dec_ioasic_hpt_read(void)
+{
+ return ioasic_read(IO_REG_FCTR);
+}
+
+static struct clocksource clocksource_dec = {
+ .name = "dec-ioasic",
+ .read = dec_ioasic_hpt_read,
+ .mask = CLOCKSOURCE_MASK(32),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+void __init dec_ioasic_clocksource_init(void)
+{
+ unsigned int freq;
+ u32 start, end;
+ int i = HZ / 10;
+
+
+ while (!ds1287_timer_state())
+ ;
+
+ start = dec_ioasic_hpt_read();
+
+ while (i--)
+ while (!ds1287_timer_state())
+ ;
+
+ end = dec_ioasic_hpt_read();
+
+ freq = (end - start) * 10;
+ printk(KERN_INFO "I/O ASIC clock frequency %dHz\n", freq);
+
+ clocksource_dec.rating = 200 + freq / 10000000;
+ clocksource_set_clock(&clocksource_dec, freq);
+
+ clocksource_register(&clocksource_dec);
+}
diff --git a/arch/mips/kernel/gpio_txx9.c b/arch/mips/kernel/gpio_txx9.c
new file mode 100644
index 00000000000..b1436a85799
--- /dev/null
+++ b/arch/mips/kernel/gpio_txx9.c
@@ -0,0 +1,87 @@
+/*
+ * A gpio chip driver for TXx9 SoCs
+ *
+ * Copyright (C) 2008 Atsushi Nemoto <anemo@mba.ocn.ne.jp>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/gpio.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <asm/txx9pio.h>
+
+static DEFINE_SPINLOCK(txx9_gpio_lock);
+
+static struct txx9_pio_reg __iomem *txx9_pioptr;
+
+static int txx9_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+ return __raw_readl(&txx9_pioptr->din) & (1 << offset);
+}
+
+static void txx9_gpio_set_raw(unsigned int offset, int value)
+{
+ u32 val;
+ val = __raw_readl(&txx9_pioptr->dout);
+ if (value)
+ val |= 1 << offset;
+ else
+ val &= ~(1 << offset);
+ __raw_writel(val, &txx9_pioptr->dout);
+}
+
+static void txx9_gpio_set(struct gpio_chip *chip, unsigned int offset,
+ int value)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&txx9_gpio_lock, flags);
+ txx9_gpio_set_raw(offset, value);
+ mmiowb();
+ spin_unlock_irqrestore(&txx9_gpio_lock, flags);
+}
+
+static int txx9_gpio_dir_in(struct gpio_chip *chip, unsigned int offset)
+{
+ spin_lock_irq(&txx9_gpio_lock);
+ __raw_writel(__raw_readl(&txx9_pioptr->dir) & ~(1 << offset),
+ &txx9_pioptr->dir);
+ mmiowb();
+ spin_unlock_irq(&txx9_gpio_lock);
+ return 0;
+}
+
+static int txx9_gpio_dir_out(struct gpio_chip *chip, unsigned int offset,
+ int value)
+{
+ spin_lock_irq(&txx9_gpio_lock);
+ txx9_gpio_set_raw(offset, value);
+ __raw_writel(__raw_readl(&txx9_pioptr->dir) | (1 << offset),
+ &txx9_pioptr->dir);
+ mmiowb();
+ spin_unlock_irq(&txx9_gpio_lock);
+ return 0;
+}
+
+static struct gpio_chip txx9_gpio_chip = {
+ .get = txx9_gpio_get,
+ .set = txx9_gpio_set,
+ .direction_input = txx9_gpio_dir_in,
+ .direction_output = txx9_gpio_dir_out,
+ .label = "TXx9",
+};
+
+int __init txx9_gpio_init(unsigned long baseaddr,
+ unsigned int base, unsigned int num)
+{
+ txx9_pioptr = ioremap(baseaddr, sizeof(struct txx9_pio_reg));
+ if (!txx9_pioptr)
+ return -ENODEV;
+ txx9_gpio_chip.base = base;
+ txx9_gpio_chip.ngpio = num;
+ return gpiochip_add(&txx9_gpio_chip);
+}
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
new file mode 100644
index 00000000000..f0a4bb19e09
--- /dev/null
+++ b/arch/mips/kernel/irq-gic.c
@@ -0,0 +1,295 @@
+#undef DEBUG
+
+#include <linux/bitmap.h>
+#include <linux/init.h>
+
+#include <asm/io.h>
+#include <asm/gic.h>
+#include <asm/gcmpregs.h>
+#include <asm/mips-boards/maltaint.h>
+#include <asm/irq.h>
+#include <linux/hardirq.h>
+#include <asm-generic/bitops/find.h>
+
+
+static unsigned long _gic_base;
+static unsigned int _irqbase, _mapsize, numvpes, numintrs;
+static struct gic_intr_map *_intrmap;
+
+static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
+static struct gic_pending_regs pending_regs[NR_CPUS];
+static struct gic_intrmask_regs intrmask_regs[NR_CPUS];
+
+#define gic_wedgeb2bok 0 /*
+ * Can GIC handle b2b writes to wedge register?
+ */
+#if gic_wedgeb2bok == 0
+static DEFINE_SPINLOCK(gic_wedgeb2b_lock);
+#endif
+
+void gic_send_ipi(unsigned int intr)
+{
+#if gic_wedgeb2bok == 0
+ unsigned long flags;
+#endif
+ pr_debug("CPU%d: %s status %08x\n", smp_processor_id(), __func__,
+ read_c0_status());
+ if (!gic_wedgeb2bok)
+ spin_lock_irqsave(&gic_wedgeb2b_lock, flags);
+ GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), 0x80000000 | intr);
+ if (!gic_wedgeb2bok) {
+ (void) GIC_REG(SHARED, GIC_SH_CONFIG);
+ spin_unlock_irqrestore(&gic_wedgeb2b_lock, flags);
+ }
+}
+
+/* This is Malta specific and needs to be exported */
+static void vpe_local_setup(unsigned int numvpes)
+{
+ int i;
+ unsigned long timer_interrupt = 5, perf_interrupt = 5;
+ unsigned int vpe_ctl;
+
+ /*
+ * Setup the default performance counter timer interrupts
+ * for all VPEs
+ */
+ for (i = 0; i < numvpes; i++) {
+ GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_OTHER_ADDR), i);
+
+ /* Are Interrupts locally routable? */
+ GICREAD(GIC_REG(VPE_OTHER, GIC_VPE_CTL), vpe_ctl);
+ if (vpe_ctl & GIC_VPE_CTL_TIMER_RTBL_MSK)
+ GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_TIMER_MAP),
+ GIC_MAP_TO_PIN_MSK | timer_interrupt);
+
+ if (vpe_ctl & GIC_VPE_CTL_PERFCNT_RTBL_MSK)
+ GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_PERFCTR_MAP),
+ GIC_MAP_TO_PIN_MSK | perf_interrupt);
+ }
+}
+
+unsigned int gic_get_int(void)
+{
+ unsigned int i;
+ unsigned long *pending, *intrmask, *pcpu_mask;
+ unsigned long *pending_abs, *intrmask_abs;
+
+ /* Get per-cpu bitmaps */
+ pending = pending_regs[smp_processor_id()].pending;
+ intrmask = intrmask_regs[smp_processor_id()].intrmask;
+ pcpu_mask = pcpu_masks[smp_processor_id()].pcpu_mask;
+
+ pending_abs = (unsigned long *) GIC_REG_ABS_ADDR(SHARED,
+ GIC_SH_PEND_31_0_OFS);
+ intrmask_abs = (unsigned long *) GIC_REG_ABS_ADDR(SHARED,
+ GIC_SH_MASK_31_0_OFS);
+
+ for (i = 0; i < BITS_TO_LONGS(GIC_NUM_INTRS); i++) {
+ GICREAD(*pending_abs, pending[i]);
+ GICREAD(*intrmask_abs, intrmask[i]);
+ pending_abs++;
+ intrmask_abs++;
+ }
+
+ bitmap_and(pending, pending, intrmask, GIC_NUM_INTRS);
+ bitmap_and(pending, pending, pcpu_mask, GIC_NUM_INTRS);
+
+ i = find_first_bit(pending, GIC_NUM_INTRS);
+
+ pr_debug("CPU%d: %s pend=%d\n", smp_processor_id(), __func__, i);
+
+ return i;
+}
+
+static unsigned int gic_irq_startup(unsigned int irq)
+{
+ pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+ irq -= _irqbase;
+ /* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+ GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_SMASK_31_0_OFS + (irq / 32))),
+ 1 << (irq % 32));
+ return 0;
+}
+
+static void gic_irq_ack(unsigned int irq)
+{
+#if gic_wedgeb2bok == 0
+ unsigned long flags;
+#endif
+ pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+ irq -= _irqbase;
+ GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_RMASK_31_0_OFS + (irq / 32))),
+ 1 << (irq % 32));
+
+ if (_intrmap[irq].trigtype == GIC_TRIG_EDGE) {
+ if (!gic_wedgeb2bok)
+ spin_lock_irqsave(&gic_wedgeb2b_lock, flags);
+ GICWRITE(GIC_REG(SHARED, GIC_SH_WEDGE), irq);
+ if (!gic_wedgeb2bok) {
+ (void) GIC_REG(SHARED, GIC_SH_CONFIG);
+ spin_unlock_irqrestore(&gic_wedgeb2b_lock, flags);
+ }
+ }
+}
+
+static void gic_mask_irq(unsigned int irq)
+{
+ pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+ irq -= _irqbase;
+ /* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+ GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_RMASK_31_0_OFS + (irq / 32))),
+ 1 << (irq % 32));
+}
+
+static void gic_unmask_irq(unsigned int irq)
+{
+ pr_debug("CPU%d: %s: irq%d\n", smp_processor_id(), __func__, irq);
+ irq -= _irqbase;
+ /* FIXME: this is wrong for !GICISWORDLITTLEENDIAN */
+ GICWRITE(GIC_REG_ADDR(SHARED, (GIC_SH_SMASK_31_0_OFS + (irq / 32))),
+ 1 << (irq % 32));
+}
+
+#ifdef CONFIG_SMP
+
+static DEFINE_SPINLOCK(gic_lock);
+
+static void gic_set_affinity(unsigned int irq, cpumask_t cpumask)
+{
+ cpumask_t tmp = CPU_MASK_NONE;
+ unsigned long flags;
+ int i;
+
+ pr_debug(KERN_DEBUG "%s called\n", __func__);
+ irq -= _irqbase;
+
+ cpus_and(tmp, cpumask, cpu_online_map);
+ if (cpus_empty(tmp))
+ return;
+
+ /* Assumption : cpumask refers to a single CPU */
+ spin_lock_irqsave(&gic_lock, flags);
+ for (;;) {
+ /* Re-route this IRQ */
+ GIC_SH_MAP_TO_VPE_SMASK(irq, first_cpu(tmp));
+
+ /*
+ * FIXME: assumption that _intrmap is ordered and has no holes
+ */
+
+ /* Update the intr_map */
+ _intrmap[irq].cpunum = first_cpu(tmp);
+
+ /* Update the pcpu_masks */
+ for (i = 0; i < NR_CPUS; i++)
+ clear_bit(irq, pcpu_masks[i].pcpu_mask);
+ set_bit(irq, pcpu_masks[first_cpu(tmp)].pcpu_mask);
+
+ }
+ irq_desc[irq].affinity = cpumask;
+ spin_unlock_irqrestore(&gic_lock, flags);
+
+}
+#endif
+
+static struct irq_chip gic_irq_controller = {
+ .name = "MIPS GIC",
+ .startup = gic_irq_startup,
+ .ack = gic_irq_ack,
+ .mask = gic_mask_irq,
+ .mask_ack = gic_mask_irq,
+ .unmask = gic_unmask_irq,
+ .eoi = gic_unmask_irq,
+#ifdef CONFIG_SMP
+ .set_affinity = gic_set_affinity,
+#endif
+};
+
+static void __init setup_intr(unsigned int intr, unsigned int cpu,
+ unsigned int pin, unsigned int polarity, unsigned int trigtype)
+{
+ /* Setup Intr to Pin mapping */
+ if (pin & GIC_MAP_TO_NMI_MSK) {
+ GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
+ /* FIXME: hack to route NMI to all cpu's */
+ for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+ GICWRITE(GIC_REG_ADDR(SHARED,
+ GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+ 0xffffffff);
+ }
+ } else {
+ GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)),
+ GIC_MAP_TO_PIN_MSK | pin);
+ /* Setup Intr to CPU mapping */
+ GIC_SH_MAP_TO_VPE_SMASK(intr, cpu);
+ }
+
+ /* Setup Intr Polarity */
+ GIC_SET_POLARITY(intr, polarity);
+
+ /* Setup Intr Trigger Type */
+ GIC_SET_TRIGGER(intr, trigtype);
+
+ /* Init Intr Masks */
+ GIC_SET_INTR_MASK(intr, 0);
+}
+
+static void __init gic_basic_init(void)
+{
+ unsigned int i, cpu;
+
+ /* Setup defaults */
+ for (i = 0; i < GIC_NUM_INTRS; i++) {
+ GIC_SET_POLARITY(i, GIC_POL_POS);
+ GIC_SET_TRIGGER(i, GIC_TRIG_LEVEL);
+ GIC_SET_INTR_MASK(i, 0);
+ }
+
+ /* Setup specifics */
+ for (i = 0; i < _mapsize; i++) {
+ cpu = _intrmap[i].cpunum;
+ if (cpu == X)
+ continue;
+
+ setup_intr(_intrmap[i].intrnum,
+ _intrmap[i].cpunum,
+ _intrmap[i].pin,
+ _intrmap[i].polarity,
+ _intrmap[i].trigtype);
+ /* Initialise per-cpu Interrupt software masks */
+ if (_intrmap[i].ipiflag)
+ set_bit(_intrmap[i].intrnum, pcpu_masks[cpu].pcpu_mask);
+ }
+
+ vpe_local_setup(numvpes);
+
+ for (i = _irqbase; i < (_irqbase + numintrs); i++)
+ set_irq_chip(i, &gic_irq_controller);
+}
+
+void __init gic_init(unsigned long gic_base_addr,
+ unsigned long gic_addrspace_size,
+ struct gic_intr_map *intr_map, unsigned int intr_map_size,
+ unsigned int irqbase)
+{
+ unsigned int gicconfig;
+
+ _gic_base = (unsigned long) ioremap_nocache(gic_base_addr,
+ gic_addrspace_size);
+ _irqbase = irqbase;
+ _intrmap = intr_map;
+ _mapsize = intr_map_size;
+
+ GICREAD(GIC_REG(SHARED, GIC_SH_CONFIG), gicconfig);
+ numintrs = (gicconfig & GIC_SH_CONFIG_NUMINTRS_MSK) >>
+ GIC_SH_CONFIG_NUMINTRS_SHF;
+ numintrs = ((numintrs + 1) * 8);
+
+ numvpes = (gicconfig & GIC_SH_CONFIG_NUMVPES_MSK) >>
+ GIC_SH_CONFIG_NUMVPES_SHF;
+
+ pr_debug("%s called\n", __func__);
+
+ gic_basic_init();
+}
diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index 4edc7e451d9..963c16d266a 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -17,6 +17,7 @@
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/msc01_ic.h>
+#include <asm/traps.h>
static unsigned long _icctrl_msc;
#define MSC01_IC_REG_BASE _icctrl_msc
@@ -98,14 +99,13 @@ void ll_msc_irq(void)
}
}
-void
-msc_bind_eic_interrupt(unsigned int irq, unsigned int set)
+static void msc_bind_eic_interrupt(int irq, int set)
{
MSCIC_WRITE(MSC01_IC_RAMW,
(irq<<MSC01_IC_RAMW_ADDR_SHF) | (set<<MSC01_IC_RAMW_DATA_SHF));
}
-struct irq_chip msc_levelirq_type = {
+static struct irq_chip msc_levelirq_type = {
.name = "SOC-it-Level",
.ack = level_mask_and_ack_msc_irq,
.mask = mask_msc_irq,
@@ -115,7 +115,7 @@ struct irq_chip msc_levelirq_type = {
.end = end_msc_irq,
};
-struct irq_chip msc_edgeirq_type = {
+static struct irq_chip msc_edgeirq_type = {
.name = "SOC-it-Edge",
.ack = edge_mask_and_ack_msc_irq,
.mask = mask_msc_irq,
@@ -128,8 +128,6 @@ struct irq_chip msc_edgeirq_type = {
void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqmap_t *imp, int nirq)
{
- extern void (*board_bind_eic_interrupt)(unsigned int irq, unsigned int regset);
-
_icctrl_msc = (unsigned long) ioremap(icubase, 0x40000);
/* Reset interrupt controller - initialises all registers to 0 */
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index c0faabd5201..6c8e8c4246f 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -14,7 +14,7 @@
/* #define DEBUG_SIG */
#ifdef DEBUG_SIG
-# define DEBUGP(fmt, args...) printk("%s: " fmt, __FUNCTION__ , ##args)
+# define DEBUGP(fmt, args...) printk("%s: " fmt, __func__, ##args)
#else
# define DEBUGP(fmt, args...)
#endif
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
new file mode 100644
index 00000000000..ca476c4f62a
--- /dev/null
+++ b/arch/mips/kernel/smp-cmp.c
@@ -0,0 +1,265 @@
+/*
+ * This program is free software; you can distribute 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 it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *
+ * Copyright (C) 2007 MIPS Technologies, Inc.
+ * Chris Dearman (chris@mips.com)
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/compiler.h>
+
+#include <asm/atomic.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/hardirq.h>
+#include <asm/mmu_context.h>
+#include <asm/smp.h>
+#include <asm/time.h>
+#include <asm/mipsregs.h>
+#include <asm/mipsmtregs.h>
+#include <asm/mips_mt.h>
+
+/*
+ * Crude manipulation of the CPU masks to control which
+ * which CPU's are brought online during initialisation
+ *
+ * Beware... this needs to be called after CPU discovery
+ * but before CPU bringup
+ */
+static int __init allowcpus(char *str)
+{
+ cpumask_t cpu_allow_map;
+ char buf[256];
+ int len;
+
+ cpus_clear(cpu_allow_map);
+ if (cpulist_parse(str, cpu_allow_map) == 0) {
+ cpu_set(0, cpu_allow_map);
+ cpus_and(cpu_possible_map, cpu_possible_map, cpu_allow_map);
+ len = cpulist_scnprintf(buf, sizeof(buf)-1, cpu_possible_map);
+ buf[len] = '\0';
+ pr_debug("Allowable CPUs: %s\n", buf);
+ return 1;
+ } else
+ return 0;
+}
+__setup("allowcpus=", allowcpus);
+
+static void ipi_call_function(unsigned int cpu)
+{
+ unsigned int action = 0;
+
+ pr_debug("CPU%d: %s cpu %d status %08x\n",
+ smp_processor_id(), __func__, cpu, read_c0_status());
+
+ switch (cpu) {
+ case 0:
+ action = GIC_IPI_EXT_INTR_CALLFNC_VPE0;
+ break;
+ case 1:
+ action = GIC_IPI_EXT_INTR_CALLFNC_VPE1;
+ break;
+ case 2:
+ action = GIC_IPI_EXT_INTR_CALLFNC_VPE2;
+ break;
+ case 3:
+ action = GIC_IPI_EXT_INTR_CALLFNC_VPE3;
+ break;
+ }
+ gic_send_ipi(action);
+}
+
+
+static void ipi_resched(unsigned int cpu)
+{
+ unsigned int action = 0;
+
+ pr_debug("CPU%d: %s cpu %d status %08x\n",
+ smp_processor_id(), __func__, cpu, read_c0_status());
+
+ switch (cpu) {
+ case 0:
+ action = GIC_IPI_EXT_INTR_RESCHED_VPE0;
+ break;
+ case 1:
+ action = GIC_IPI_EXT_INTR_RESCHED_VPE1;
+ break;
+ case 2:
+ action = GIC_IPI_EXT_INTR_RESCHED_VPE2;
+ break;
+ case 3:
+ action = GIC_IPI_EXT_INTR_RESCHED_VPE3;
+ break;
+ }
+ gic_send_ipi(action);
+}
+
+/*
+ * FIXME: This isn't restricted to CMP
+ * The SMVP kernel could use GIC interrupts if available
+ */
+void cmp_send_ipi_single(int cpu, unsigned int action)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ switch (action) {
+ case SMP_CALL_FUNCTION:
+ ipi_call_function(cpu);
+ break;
+
+ case SMP_RESCHEDULE_YOURSELF:
+ ipi_resched(cpu);
+ break;
+ }
+
+ local_irq_restore(flags);
+}
+
+static void cmp_send_ipi_mask(cpumask_t mask, unsigned int action)
+{
+ unsigned int i;
+
+ for_each_cpu_mask(i, mask)
+ cmp_send_ipi_single(i, action);
+}
+
+static void cmp_init_secondary(void)
+{
+ struct cpuinfo_mips *c = &current_cpu_data;
+
+ /* Assume GIC is present */
+ change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 |
+ STATUSF_IP7);
+
+ /* Enable per-cpu interrupts: platform specific */
+
+ c->core = (read_c0_ebase() >> 1) & 0xff;
+#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+ c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & TCBIND_CURVPE;
+#endif
+#ifdef CONFIG_MIPS_MT_SMTC
+ c->tc_id = (read_c0_tcbind() >> TCBIND_CURTC_SHIFT) & TCBIND_CURTC;
+#endif
+}
+
+static void cmp_smp_finish(void)
+{
+ pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+
+ /* CDFIXME: remove this? */
+ write_c0_compare(read_c0_count() + (8 * mips_hpt_frequency / HZ));
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+ /* If we have an FPU, enroll ourselves in the FPU-full mask */
+ if (cpu_has_fpu)
+ cpu_set(smp_processor_id(), mt_fpu_cpumask);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
+ local_irq_enable();
+}
+
+static void cmp_cpus_done(void)
+{
+ pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+}
+
+/*
+ * Setup the PC, SP, and GP of a secondary processor and start it running
+ * smp_bootstrap is the place to resume from
+ * __KSTK_TOS(idle) is apparently the stack pointer
+ * (unsigned long)idle->thread_info the gp
+ */
+static void cmp_boot_secondary(int cpu, struct task_struct *idle)
+{
+ struct thread_info *gp = task_thread_info(idle);
+ unsigned long sp = __KSTK_TOS(idle);
+ unsigned long pc = (unsigned long)&smp_bootstrap;
+ unsigned long a0 = 0;
+
+ pr_debug("SMPCMP: CPU%d: %s cpu %d\n", smp_processor_id(),
+ __func__, cpu);
+
+#if 0
+ /* Needed? */
+ flush_icache_range((unsigned long)gp,
+ (unsigned long)(gp + sizeof(struct thread_info)));
+#endif
+
+ amon_cpu_start(cpu, pc, sp, gp, a0);
+}
+
+/*
+ * Common setup before any secondaries are started
+ */
+void __init cmp_smp_setup(void)
+{
+ int i;
+ int ncpu = 0;
+
+ pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+ /* If we have an FPU, enroll ourselves in the FPU-full mask */
+ if (cpu_has_fpu)
+ cpu_set(0, mt_fpu_cpumask);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
+ for (i = 1; i < NR_CPUS; i++) {
+ if (amon_cpu_avail(i)) {
+ cpu_set(i, phys_cpu_present_map);
+ __cpu_number_map[i] = ++ncpu;
+ __cpu_logical_map[ncpu] = i;
+ }
+ }
+
+ if (cpu_has_mipsmt) {
+ unsigned int nvpe, mvpconf0 = read_c0_mvpconf0();
+
+ nvpe = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
+ smp_num_siblings = nvpe;
+ }
+ pr_info("Detected %i available secondary CPU(s)\n", ncpu);
+}
+
+void __init cmp_prepare_cpus(unsigned int max_cpus)
+{
+ pr_debug("SMPCMP: CPU%d: %s max_cpus=%d\n",
+ smp_processor_id(), __func__, max_cpus);
+
+ /*
+ * FIXME: some of these options are per-system, some per-core and
+ * some per-cpu
+ */
+ mips_mt_set_cpuoptions();
+}
+
+struct plat_smp_ops cmp_smp_ops = {
+ .send_ipi_single = cmp_send_ipi_single,
+ .send_ipi_mask = cmp_send_ipi_mask,
+ .init_secondary = cmp_init_secondary,
+ .smp_finish = cmp_smp_finish,
+ .cpus_done = cmp_cpus_done,
+ .boot_secondary = cmp_boot_secondary,
+ .smp_setup = cmp_smp_setup,
+ .prepare_cpus = cmp_prepare_cpus,
+};
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 89e6f6aa516..87a1816c1f4 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -36,110 +36,7 @@
#include <asm/mipsmtregs.h>
#include <asm/mips_mt.h>
-#define MIPS_CPU_IPI_RESCHED_IRQ 0
-#define MIPS_CPU_IPI_CALL_IRQ 1
-
-static int cpu_ipi_resched_irq, cpu_ipi_call_irq;
-
-#if 0
-static void dump_mtregisters(int vpe, int tc)
-{
- printk("vpe %d tc %d\n", vpe, tc);
-
- settc(tc);
-
- printk(" c0 status 0x%lx\n", read_vpe_c0_status());
- printk(" vpecontrol 0x%lx\n", read_vpe_c0_vpecontrol());
- printk(" vpeconf0 0x%lx\n", read_vpe_c0_vpeconf0());
- printk(" tcstatus 0x%lx\n", read_tc_c0_tcstatus());
- printk(" tcrestart 0x%lx\n", read_tc_c0_tcrestart());
- printk(" tcbind 0x%lx\n", read_tc_c0_tcbind());
- printk(" tchalt 0x%lx\n", read_tc_c0_tchalt());
-}
-#endif
-
-void __init sanitize_tlb_entries(void)
-{
- int i, tlbsiz;
- unsigned long mvpconf0, ncpu;
-
- if (!cpu_has_mipsmt)
- return;
-
- /* Enable VPC */
- set_c0_mvpcontrol(MVPCONTROL_VPC);
-
- back_to_back_c0_hazard();
-
- /* Disable TLB sharing */
- clear_c0_mvpcontrol(MVPCONTROL_STLB);
-
- mvpconf0 = read_c0_mvpconf0();
-
- printk(KERN_INFO "MVPConf0 0x%lx TLBS %lx PTLBE %ld\n", mvpconf0,
- (mvpconf0 & MVPCONF0_TLBS) >> MVPCONF0_TLBS_SHIFT,
- (mvpconf0 & MVPCONF0_PTLBE) >> MVPCONF0_PTLBE_SHIFT);
-
- tlbsiz = (mvpconf0 & MVPCONF0_PTLBE) >> MVPCONF0_PTLBE_SHIFT;
- ncpu = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
-
- printk(" tlbsiz %d ncpu %ld\n", tlbsiz, ncpu);
-
- if (tlbsiz > 0) {
- /* share them out across the vpe's */
- tlbsiz /= ncpu;
-
- printk(KERN_INFO "setting Config1.MMU_size to %d\n", tlbsiz);
-
- for (i = 0; i < ncpu; i++) {
- settc(i);
-
- if (i == 0)
- write_c0_config1((read_c0_config1() & ~(0x3f << 25)) | (tlbsiz << 25));
- else
- write_vpe_c0_config1((read_vpe_c0_config1() & ~(0x3f << 25)) |
- (tlbsiz << 25));
- }
- }
-
- clear_c0_mvpcontrol(MVPCONTROL_VPC);
-}
-
-static void ipi_resched_dispatch(void)
-{
- do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ);
-}
-
-static void ipi_call_dispatch(void)
-{
- do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ);
-}
-
-static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
-{
- return IRQ_HANDLED;
-}
-
-static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
-{
- smp_call_function_interrupt();
-
- return IRQ_HANDLED;
-}
-
-static struct irqaction irq_resched = {
- .handler = ipi_resched_interrupt,
- .flags = IRQF_DISABLED|IRQF_PERCPU,
- .name = "IPI_resched"
-};
-
-static struct irqaction irq_call = {
- .handler = ipi_call_interrupt,
- .flags = IRQF_DISABLED|IRQF_PERCPU,
- .name = "IPI_call"
-};
-
-static void __init smp_copy_vpe_config(void)
+static void __init smvp_copy_vpe_config(void)
{
write_vpe_c0_status(
(read_c0_status() & ~(ST0_IM | ST0_IE | ST0_KSU)) | ST0_CU0);
@@ -156,7 +53,7 @@ static void __init smp_copy_vpe_config(void)
write_vpe_c0_count(read_c0_count());
}
-static unsigned int __init smp_vpe_init(unsigned int tc, unsigned int mvpconf0,
+static unsigned int __init smvp_vpe_init(unsigned int tc, unsigned int mvpconf0,
unsigned int ncpu)
{
if (tc > ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT))
@@ -182,12 +79,12 @@ static unsigned int __init smp_vpe_init(unsigned int tc, unsigned int mvpconf0,
write_vpe_c0_vpecontrol(read_vpe_c0_vpecontrol() & ~VPECONTROL_TE);
if (tc != 0)
- smp_copy_vpe_config();
+ smvp_copy_vpe_config();
return ncpu;
}
-static void __init smp_tc_init(unsigned int tc, unsigned int mvpconf0)
+static void __init smvp_tc_init(unsigned int tc, unsigned int mvpconf0)
{
unsigned long tmp;
@@ -254,15 +151,20 @@ static void vsmp_send_ipi_mask(cpumask_t mask, unsigned int action)
static void __cpuinit vsmp_init_secondary(void)
{
- /* Enable per-cpu interrupts */
+ extern int gic_present;
/* This is Malta specific: IPI,performance and timer inetrrupts */
- write_c0_status((read_c0_status() & ~ST0_IM ) |
- (STATUSF_IP0 | STATUSF_IP1 | STATUSF_IP6 | STATUSF_IP7));
+ if (gic_present)
+ change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
+ STATUSF_IP6 | STATUSF_IP7);
+ else
+ change_c0_status(ST0_IM, STATUSF_IP0 | STATUSF_IP1 |
+ STATUSF_IP6 | STATUSF_IP7);
}
static void __cpuinit vsmp_smp_finish(void)
{
+ /* CDFIXME: remove this? */
write_c0_compare(read_c0_count() + (8* mips_hpt_frequency/HZ));
#ifdef CONFIG_MIPS_MT_FPAFF
@@ -323,7 +225,7 @@ static void __cpuinit vsmp_boot_secondary(int cpu, struct task_struct *idle)
/*
* Common setup before any secondaries are started
* Make sure all CPU's are in a sensible state before we boot any of the
- * secondarys
+ * secondaries
*/
static void __init vsmp_smp_setup(void)
{
@@ -356,8 +258,8 @@ static void __init vsmp_smp_setup(void)
for (tc = 0; tc <= ntc; tc++) {
settc(tc);
- smp_tc_init(tc, mvpconf0);
- ncpu = smp_vpe_init(tc, mvpconf0, ncpu);
+ smvp_tc_init(tc, mvpconf0);
+ ncpu = smvp_vpe_init(tc, mvpconf0, ncpu);
}
/* Release config state */
@@ -371,21 +273,6 @@ static void __init vsmp_smp_setup(void)
static void __init vsmp_prepare_cpus(unsigned int max_cpus)
{
mips_mt_set_cpuoptions();
-
- /* set up ipi interrupts */
- if (cpu_has_vint) {
- set_vi_handler(MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch);
- set_vi_handler(MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch);
- }
-
- cpu_ipi_resched_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ;
- cpu_ipi_call_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ;
-
- setup_irq(cpu_ipi_resched_irq, &irq_resched);
- setup_irq(cpu_ipi_call_irq, &irq_call);
-
- set_irq_handler(cpu_ipi_resched_irq, handle_percpu_irq);
- set_irq_handler(cpu_ipi_call_irq, handle_percpu_irq);
}
struct plat_smp_ops vsmp_smp_ops = {
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 9d41dab90a8..33780cc61ce 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -35,6 +35,7 @@
#include <asm/atomic.h>
#include <asm/cpu.h>
#include <asm/processor.h>
+#include <asm/r4k-timer.h>
#include <asm/system.h>
#include <asm/mmu_context.h>
#include <asm/time.h>
@@ -125,6 +126,8 @@ asmlinkage __cpuinit void start_secondary(void)
cpu_set(cpu, cpu_callin_map);
+ synchronise_count_slave();
+
cpu_idle();
}
@@ -287,6 +290,7 @@ void smp_send_stop(void)
void __init smp_cpus_done(unsigned int max_cpus)
{
mp_ops->cpus_done();
+ synchronise_count_master();
}
/* called from main before smp_init() */
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index b42e71c7111..3e863186cd2 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -174,14 +174,6 @@ static int clock_hang_reported[NR_CPUS];
#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
-/* Initialize shared TLB - the should probably migrate to smtc_setup_cpus() */
-
-void __init sanitize_tlb_entries(void)
-{
- printk("Deprecated sanitize_tlb_entries() invoked\n");
-}
-
-
/*
* Configure shared TLB - VPC configuration bit must be set by caller
*/
@@ -339,7 +331,8 @@ static void smtc_tc_setup(int vpe, int tc, int cpu)
/* In general, all TCs should have the same cpu_data indications */
memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips));
/* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */
- if (cpu_data[0].cputype == CPU_34K)
+ if (cpu_data[0].cputype == CPU_34K ||
+ cpu_data[0].cputype == CPU_1004K)
cpu_data[cpu].options &= ~MIPS_CPU_FPU;
cpu_data[cpu].vpe_id = vpe;
cpu_data[cpu].tc_id = tc;
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
new file mode 100644
index 00000000000..6ddb507a87e
--- /dev/null
+++ b/arch/mips/kernel/spram.c
@@ -0,0 +1,221 @@
+/*
+ * MIPS SPRAM support
+ *
+ * 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.
+ *
+ * Copyright (C) 2007, 2008 MIPS Technologies, Inc.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/stddef.h>
+
+#include <asm/cpu.h>
+#include <asm/fpu.h>
+#include <asm/mipsregs.h>
+#include <asm/system.h>
+#include <asm/r4kcache.h>
+#include <asm/hazards.h>
+
+/*
+ * These definitions are correct for the 24K/34K/74K SPRAM sample
+ * implementation. The 4KS interpreted the tags differently...
+ */
+#define SPRAM_TAG0_ENABLE 0x00000080
+#define SPRAM_TAG0_PA_MASK 0xfffff000
+#define SPRAM_TAG1_SIZE_MASK 0xfffff000
+
+#define SPRAM_TAG_STRIDE 8
+
+#define ERRCTL_SPRAM (1 << 28)
+
+/* errctl access */
+#define read_c0_errctl(x) read_c0_ecc(x)
+#define write_c0_errctl(x) write_c0_ecc(x)
+
+/*
+ * Different semantics to the set_c0_* function built by __BUILD_SET_C0
+ */
+static __cpuinit unsigned int bis_c0_errctl(unsigned int set)
+{
+ unsigned int res;
+ res = read_c0_errctl();
+ write_c0_errctl(res | set);
+ return res;
+}
+
+static __cpuinit void ispram_store_tag(unsigned int offset, unsigned int data)
+{
+ unsigned int errctl;
+
+ /* enable SPRAM tag access */
+ errctl = bis_c0_errctl(ERRCTL_SPRAM);
+ ehb();
+
+ write_c0_taglo(data);
+ ehb();
+
+ cache_op(Index_Store_Tag_I, CKSEG0|offset);
+ ehb();
+
+ write_c0_errctl(errctl);
+ ehb();
+}
+
+
+static __cpuinit unsigned int ispram_load_tag(unsigned int offset)
+{
+ unsigned int data;
+ unsigned int errctl;
+
+ /* enable SPRAM tag access */
+ errctl = bis_c0_errctl(ERRCTL_SPRAM);
+ ehb();
+ cache_op(Index_Load_Tag_I, CKSEG0 | offset);
+ ehb();
+ data = read_c0_taglo();
+ ehb();
+ write_c0_errctl(errctl);
+ ehb();
+
+ return data;
+}
+
+static __cpuinit void dspram_store_tag(unsigned int offset, unsigned int data)
+{
+ unsigned int errctl;
+
+ /* enable SPRAM tag access */
+ errctl = bis_c0_errctl(ERRCTL_SPRAM);
+ ehb();
+ write_c0_dtaglo(data);
+ ehb();
+ cache_op(Index_Store_Tag_D, CKSEG0 | offset);
+ ehb();
+ write_c0_errctl(errctl);
+ ehb();
+}
+
+
+static __cpuinit unsigned int dspram_load_tag(unsigned int offset)
+{
+ unsigned int data;
+ unsigned int errctl;
+
+ errctl = bis_c0_errctl(ERRCTL_SPRAM);
+ ehb();
+ cache_op(Index_Load_Tag_D, CKSEG0 | offset);
+ ehb();
+ data = read_c0_dtaglo();
+ ehb();
+ write_c0_errctl(errctl);
+ ehb();
+
+ return data;
+}
+
+static __cpuinit void probe_spram(char *type,
+ unsigned int base,
+ unsigned int (*read)(unsigned int),
+ void (*write)(unsigned int, unsigned int))
+{
+ unsigned int firstsize = 0, lastsize = 0;
+ unsigned int firstpa = 0, lastpa = 0, pa = 0;
+ unsigned int offset = 0;
+ unsigned int size, tag0, tag1;
+ unsigned int enabled;
+ int i;
+
+ /*
+ * The limit is arbitrary but avoids the loop running away if
+ * the SPRAM tags are implemented differently
+ */
+
+ for (i = 0; i < 8; i++) {
+ tag0 = read(offset);
+ tag1 = read(offset+SPRAM_TAG_STRIDE);
+ pr_debug("DBG %s%d: tag0=%08x tag1=%08x\n",
+ type, i, tag0, tag1);
+
+ size = tag1 & SPRAM_TAG1_SIZE_MASK;
+
+ if (size == 0)
+ break;
+
+ if (i != 0) {
+ /* tags may repeat... */
+ if ((pa == firstpa && size == firstsize) ||
+ (pa == lastpa && size == lastsize))
+ break;
+ }
+
+ /* Align base with size */
+ base = (base + size - 1) & ~(size-1);
+
+ /* reprogram the base address base address and enable */
+ tag0 = (base & SPRAM_TAG0_PA_MASK) | SPRAM_TAG0_ENABLE;
+ write(offset, tag0);
+
+ base += size;
+
+ /* reread the tag */
+ tag0 = read(offset);
+ pa = tag0 & SPRAM_TAG0_PA_MASK;
+ enabled = tag0 & SPRAM_TAG0_ENABLE;
+
+ if (i == 0) {
+ firstpa = pa;
+ firstsize = size;
+ }
+
+ lastpa = pa;
+ lastsize = size;
+
+ if (strcmp(type, "DSPRAM") == 0) {
+ unsigned int *vp = (unsigned int *)(CKSEG1 | pa);
+ unsigned int v;
+#define TDAT 0x5a5aa5a5
+ vp[0] = TDAT;
+ vp[1] = ~TDAT;
+
+ mb();
+
+ v = vp[0];
+ if (v != TDAT)
+ printk(KERN_ERR "vp=%p wrote=%08x got=%08x\n",
+ vp, TDAT, v);
+ v = vp[1];
+ if (v != ~TDAT)
+ printk(KERN_ERR "vp=%p wrote=%08x got=%08x\n",
+ vp+1, ~TDAT, v);
+ }
+
+ pr_info("%s%d: PA=%08x,Size=%08x%s\n",
+ type, i, pa, size, enabled ? ",enabled" : "");
+ offset += 2 * SPRAM_TAG_STRIDE;
+ }
+}
+
+__cpuinit void spram_config(void)
+{
+ struct cpuinfo_mips *c = &current_cpu_data;
+ unsigned int config0;
+
+ switch (c->cputype) {
+ case CPU_24K:
+ case CPU_34K:
+ case CPU_74K:
+ config0 = read_c0_config();
+ /* FIXME: addresses are Malta specific */
+ if (config0 & (1<<24)) {
+ probe_spram("ISPRAM", 0x1c000000,
+ &ispram_load_tag, &ispram_store_tag);
+ }
+ if (config0 & (1<<23))
+ probe_spram("DSPRAM", 0x1c100000,
+ &dspram_load_tag, &dspram_store_tag);
+ }
+}
diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c
new file mode 100644
index 00000000000..9021108eb9c
--- /dev/null
+++ b/arch/mips/kernel/sync-r4k.c
@@ -0,0 +1,159 @@
+/*
+ * Count register synchronisation.
+ *
+ * All CPUs will have their count registers synchronised to the CPU0 expirelo
+ * value. This can cause a small timewarp for CPU0. All other CPU's should
+ * not have done anything significant (but they may have had interrupts
+ * enabled briefly - prom_smp_finish() should not be responsible for enabling
+ * interrupts...)
+ *
+ * FIXME: broken for SMTC
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/irqflags.h>
+#include <linux/r4k-timer.h>
+
+#include <asm/atomic.h>
+#include <asm/barrier.h>
+#include <asm/cpumask.h>
+#include <asm/mipsregs.h>
+
+static atomic_t __initdata count_start_flag = ATOMIC_INIT(0);
+static atomic_t __initdata count_count_start = ATOMIC_INIT(0);
+static atomic_t __initdata count_count_stop = ATOMIC_INIT(0);
+
+#define COUNTON 100
+#define NR_LOOPS 5
+
+void __init synchronise_count_master(void)
+{
+ int i;
+ unsigned long flags;
+ unsigned int initcount;
+ int nslaves;
+
+#ifdef CONFIG_MIPS_MT_SMTC
+ /*
+ * SMTC needs to synchronise per VPE, not per CPU
+ * ignore for now
+ */
+ return;
+#endif
+
+ pr_info("Checking COUNT synchronization across %u CPUs: ",
+ num_online_cpus());
+
+ local_irq_save(flags);
+
+ /*
+ * Notify the slaves that it's time to start
+ */
+ atomic_set(&count_start_flag, 1);
+ smp_wmb();
+
+ /* Count will be initialised to expirelo for all CPU's */
+ initcount = expirelo;
+
+ /*
+ * We loop a few times to get a primed instruction cache,
+ * then the last pass is more or less synchronised and
+ * the master and slaves each set their cycle counters to a known
+ * value all at once. This reduces the chance of having random offsets
+ * between the processors, and guarantees that the maximum
+ * delay between the cycle counters is never bigger than
+ * the latency of information-passing (cachelines) between
+ * two CPUs.
+ */
+
+ nslaves = num_online_cpus()-1;
+ for (i = 0; i < NR_LOOPS; i++) {
+ /* slaves loop on '!= ncpus' */
+ while (atomic_read(&count_count_start) != nslaves)
+ mb();
+ atomic_set(&count_count_stop, 0);
+ smp_wmb();
+
+ /* this lets the slaves write their count register */
+ atomic_inc(&count_count_start);
+
+ /*
+ * Everyone initialises count in the last loop:
+ */
+ if (i == NR_LOOPS-1)
+ write_c0_count(initcount);
+
+ /*
+ * Wait for all slaves to leave the synchronization point:
+ */
+ while (atomic_read(&count_count_stop) != nslaves)
+ mb();
+ atomic_set(&count_count_start, 0);
+ smp_wmb();
+ atomic_inc(&count_count_stop);
+ }
+ /* Arrange for an interrupt in a short while */
+ write_c0_compare(read_c0_count() + COUNTON);
+
+ local_irq_restore(flags);
+
+ /*
+ * i386 code reported the skew here, but the
+ * count registers were almost certainly out of sync
+ * so no point in alarming people
+ */
+ printk("done.\n");
+}
+
+void __init synchronise_count_slave(void)
+{
+ int i;
+ unsigned long flags;
+ unsigned int initcount;
+ int ncpus;
+
+#ifdef CONFIG_MIPS_MT_SMTC
+ /*
+ * SMTC needs to synchronise per VPE, not per CPU
+ * ignore for now
+ */
+ return;
+#endif
+
+ local_irq_save(flags);
+
+ /*
+ * Not every cpu is online at the time this gets called,
+ * so we first wait for the master to say everyone is ready
+ */
+
+ while (!atomic_read(&count_start_flag))
+ mb();
+
+ /* Count will be initialised to expirelo for all CPU's */
+ initcount = expirelo;
+
+ ncpus = num_online_cpus();
+ for (i = 0; i < NR_LOOPS; i++) {
+ atomic_inc(&count_count_start);
+ while (atomic_read(&count_count_start) != ncpus)
+ mb();
+
+ /*
+ * Everyone initialises count in the last loop:
+ */
+ if (i == NR_LOOPS-1)
+ write_c0_count(initcount);
+
+ atomic_inc(&count_count_stop);
+ while (atomic_read(&count_count_stop) != ncpus)
+ mb();
+ }
+ /* Arrange for an interrupt in a short while */
+ write_c0_compare(read_c0_count() + COUNTON);
+
+ local_irq_restore(flags);
+}
+#undef NR_LOOPS
+#endif
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index b45a7093ca2..1f467d53464 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -38,7 +38,6 @@ int __weak rtc_mips_set_time(unsigned long sec)
{
return 0;
}
-EXPORT_SYMBOL(rtc_mips_set_time);
int __weak rtc_mips_set_mmss(unsigned long nowtime)
{
@@ -50,13 +49,11 @@ int update_persistent_clock(struct timespec now)
return rtc_mips_set_mmss(now.tv_sec);
}
-int null_perf_irq(void)
+static int null_perf_irq(void)
{
return 0;
}
-EXPORT_SYMBOL(null_perf_irq);
-
int (*perf_irq)(void) = null_perf_irq;
EXPORT_SYMBOL(perf_irq);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 984c0d0a7b4..cb8b0e2c795 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -22,6 +22,7 @@
#include <linux/kallsyms.h>
#include <linux/bootmem.h>
#include <linux/interrupt.h>
+#include <linux/ptrace.h>
#include <asm/bootinfo.h>
#include <asm/branch.h>
@@ -80,19 +81,22 @@ void (*board_bind_eic_interrupt)(int irq, int regset);
static void show_raw_backtrace(unsigned long reg29)
{
- unsigned long *sp = (unsigned long *)reg29;
+ unsigned long *sp = (unsigned long *)(reg29 & ~3);
unsigned long addr;
printk("Call Trace:");
#ifdef CONFIG_KALLSYMS
printk("\n");
#endif
- while (!kstack_end(sp)) {
- addr = *sp++;
- if (__kernel_text_address(addr))
- print_ip_sym(addr);
+#define IS_KVA01(a) ((((unsigned int)a) & 0xc0000000) == 0x80000000)
+ if (IS_KVA01(sp)) {
+ while (!kstack_end(sp)) {
+ addr = *sp++;
+ if (__kernel_text_address(addr))
+ print_ip_sym(addr);
+ }
+ printk("\n");
}
- printk("\n");
}
#ifdef CONFIG_KALLSYMS
@@ -192,16 +196,19 @@ EXPORT_SYMBOL(dump_stack);
static void show_code(unsigned int __user *pc)
{
long i;
+ unsigned short __user *pc16 = NULL;
printk("\nCode:");
+ if ((unsigned long)pc & 1)
+ pc16 = (unsigned short __user *)((unsigned long)pc & ~1);
for(i = -3 ; i < 6 ; i++) {
unsigned int insn;
- if (__get_user(insn, pc + i)) {
+ if (pc16 ? __get_user(insn, pc16 + i) : __get_user(insn, pc + i)) {
printk(" (Bad address in epc)\n");
break;
}
- printk("%c%08x%c", (i?' ':'<'), insn, (i?' ':'>'));
+ printk("%c%0*x%c", (i?' ':'<'), pc16 ? 4 : 8, insn, (i?' ':'>'));
}
}
@@ -311,10 +318,21 @@ void show_regs(struct pt_regs *regs)
void show_registers(const struct pt_regs *regs)
{
+ const int field = 2 * sizeof(unsigned long);
+
__show_regs(regs);
print_modules();
- printk("Process %s (pid: %d, threadinfo=%p, task=%p)\n",
- current->comm, task_pid_nr(current), current_thread_info(), current);
+ printk("Process %s (pid: %d, threadinfo=%p, task=%p, tls=%0*lx)\n",
+ current->comm, current->pid, current_thread_info(), current,
+ field, current_thread_info()->tp_value);
+ if (cpu_has_userlocal) {
+ unsigned long tls;
+
+ tls = read_c0_userlocal();
+ if (tls != current_thread_info()->tp_value)
+ printk("*HwTLS: %0*lx\n", field, tls);
+ }
+
show_stacktrace(current, regs);
show_code((unsigned int __user *) regs->cp0_epc);
printk("\n");
@@ -657,35 +675,24 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
force_sig_info(SIGFPE, &info, current);
}
-asmlinkage void do_bp(struct pt_regs *regs)
+static void do_trap_or_bp(struct pt_regs *regs, unsigned int code,
+ const char *str)
{
- unsigned int opcode, bcode;
siginfo_t info;
-
- if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
- goto out_sigsegv;
-
- /*
- * There is the ancient bug in the MIPS assemblers that the break
- * code starts left to bit 16 instead to bit 6 in the opcode.
- * Gas is bug-compatible, but not always, grrr...
- * We handle both cases with a simple heuristics. --macro
- */
- bcode = ((opcode >> 6) & ((1 << 20) - 1));
- if (bcode < (1 << 10))
- bcode <<= 10;
+ char b[40];
/*
- * (A short test says that IRIX 5.3 sends SIGTRAP for all break
- * insns, even for break codes that indicate arithmetic failures.
- * Weird ...)
+ * A short test says that IRIX 5.3 sends SIGTRAP for all trap
+ * insns, even for trap and break codes that indicate arithmetic
+ * failures. Weird ...
* But should we continue the brokenness??? --macro
*/
- switch (bcode) {
- case BRK_OVERFLOW << 10:
- case BRK_DIVZERO << 10:
- die_if_kernel("Break instruction in kernel code", regs);
- if (bcode == (BRK_DIVZERO << 10))
+ switch (code) {
+ case BRK_OVERFLOW:
+ case BRK_DIVZERO:
+ scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
+ die_if_kernel(b, regs);
+ if (code == BRK_DIVZERO)
info.si_code = FPE_INTDIV;
else
info.si_code = FPE_INTOVF;
@@ -695,12 +702,34 @@ asmlinkage void do_bp(struct pt_regs *regs)
force_sig_info(SIGFPE, &info, current);
break;
case BRK_BUG:
- die("Kernel bug detected", regs);
+ die_if_kernel("Kernel bug detected", regs);
+ force_sig(SIGTRAP, current);
break;
default:
- die_if_kernel("Break instruction in kernel code", regs);
+ scnprintf(b, sizeof(b), "%s instruction in kernel code", str);
+ die_if_kernel(b, regs);
force_sig(SIGTRAP, current);
}
+}
+
+asmlinkage void do_bp(struct pt_regs *regs)
+{
+ unsigned int opcode, bcode;
+
+ if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
+ goto out_sigsegv;
+
+ /*
+ * There is the ancient bug in the MIPS assemblers that the break
+ * code starts left to bit 16 instead to bit 6 in the opcode.
+ * Gas is bug-compatible, but not always, grrr...
+ * We handle both cases with a simple heuristics. --macro
+ */
+ bcode = ((opcode >> 6) & ((1 << 20) - 1));
+ if (bcode >= (1 << 10))
+ bcode >>= 10;
+
+ do_trap_or_bp(regs, bcode, "Break");
return;
out_sigsegv:
@@ -710,7 +739,6 @@ out_sigsegv:
asmlinkage void do_tr(struct pt_regs *regs)
{
unsigned int opcode, tcode = 0;
- siginfo_t info;
if (__get_user(opcode, (unsigned int __user *) exception_epc(regs)))
goto out_sigsegv;
@@ -719,32 +747,7 @@ asmlinkage void do_tr(struct pt_regs *regs)
if (!(opcode & OPCODE))
tcode = ((opcode >> 6) & ((1 << 10) - 1));
- /*
- * (A short test says that IRIX 5.3 sends SIGTRAP for all trap
- * insns, even for trap codes that indicate arithmetic failures.
- * Weird ...)
- * But should we continue the brokenness??? --macro
- */
- switch (tcode) {
- case BRK_OVERFLOW:
- case BRK_DIVZERO:
- die_if_kernel("Trap instruction in kernel code", regs);
- if (tcode == BRK_DIVZERO)
- info.si_code = FPE_INTDIV;
- else
- info.si_code = FPE_INTOVF;
- info.si_signo = SIGFPE;
- info.si_errno = 0;
- info.si_addr = (void __user *) regs->cp0_epc;
- force_sig_info(SIGFPE, &info, current);
- break;
- case BRK_BUG:
- die("Kernel bug detected", regs);
- break;
- default:
- die_if_kernel("Trap instruction in kernel code", regs);
- force_sig(SIGTRAP, current);
- }
+ do_trap_or_bp(regs, tcode, "Trap");
return;
out_sigsegv:
@@ -985,6 +988,21 @@ asmlinkage void do_reserved(struct pt_regs *regs)
(regs->cp0_cause & 0x7f) >> 2);
}
+static int __initdata l1parity = 1;
+static int __init nol1parity(char *s)
+{
+ l1parity = 0;
+ return 1;
+}
+__setup("nol1par", nol1parity);
+static int __initdata l2parity = 1;
+static int __init nol2parity(char *s)
+{
+ l2parity = 0;
+ return 1;
+}
+__setup("nol2par", nol2parity);
+
/*
* Some MIPS CPUs can enable/disable for cache parity detection, but do
* it different ways.
@@ -994,6 +1012,62 @@ static inline void parity_protection_init(void)
switch (current_cpu_type()) {
case CPU_24K:
case CPU_34K:
+ case CPU_74K:
+ case CPU_1004K:
+ {
+#define ERRCTL_PE 0x80000000
+#define ERRCTL_L2P 0x00800000
+ unsigned long errctl;
+ unsigned int l1parity_present, l2parity_present;
+
+ errctl = read_c0_ecc();
+ errctl &= ~(ERRCTL_PE|ERRCTL_L2P);
+
+ /* probe L1 parity support */
+ write_c0_ecc(errctl | ERRCTL_PE);
+ back_to_back_c0_hazard();
+ l1parity_present = (read_c0_ecc() & ERRCTL_PE);
+
+ /* probe L2 parity support */
+ write_c0_ecc(errctl|ERRCTL_L2P);
+ back_to_back_c0_hazard();
+ l2parity_present = (read_c0_ecc() & ERRCTL_L2P);
+
+ if (l1parity_present && l2parity_present) {
+ if (l1parity)
+ errctl |= ERRCTL_PE;
+ if (l1parity ^ l2parity)
+ errctl |= ERRCTL_L2P;
+ } else if (l1parity_present) {
+ if (l1parity)
+ errctl |= ERRCTL_PE;
+ } else if (l2parity_present) {
+ if (l2parity)
+ errctl |= ERRCTL_L2P;
+ } else {
+ /* No parity available */
+ }
+
+ printk(KERN_INFO "Writing ErrCtl register=%08lx\n", errctl);
+
+ write_c0_ecc(errctl);
+ back_to_back_c0_hazard();
+ errctl = read_c0_ecc();
+ printk(KERN_INFO "Readback ErrCtl register=%08lx\n", errctl);
+
+ if (l1parity_present)
+ printk(KERN_INFO "Cache parity protection %sabled\n",
+ (errctl & ERRCTL_PE) ? "en" : "dis");
+
+ if (l2parity_present) {
+ if (l1parity_present && l1parity)
+ errctl ^= ERRCTL_L2P;
+ printk(KERN_INFO "L2 cache parity protection %sabled\n",
+ (errctl & ERRCTL_L2P) ? "en" : "dis");
+ }
+ }
+ break;
+
case CPU_5KC:
write_c0_ecc(0x80000000);
back_to_back_c0_hazard();
@@ -1306,6 +1380,17 @@ int cp0_compare_irq;
int cp0_perfcount_irq;
EXPORT_SYMBOL_GPL(cp0_perfcount_irq);
+static int __cpuinitdata noulri;
+
+static int __init ulri_disable(char *s)
+{
+ pr_info("Disabling ulri\n");
+ noulri = 1;
+
+ return 1;
+}
+__setup("noulri", ulri_disable);
+
void __cpuinit per_cpu_trap_init(void)
{
unsigned int cpu = smp_processor_id();
@@ -1342,16 +1427,14 @@ void __cpuinit per_cpu_trap_init(void)
change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
status_set);
-#ifdef CONFIG_CPU_MIPSR2
if (cpu_has_mips_r2) {
unsigned int enable = 0x0000000f;
- if (cpu_has_userlocal)
+ if (!noulri && cpu_has_userlocal)
enable |= (1 << 29);
write_c0_hwrena(enable);
}
-#endif
#ifdef CONFIG_MIPS_MT_SMTC
if (!secondaryTC) {
diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h
index 8977eb585a3..76278653844 100644
--- a/arch/mips/math-emu/ieee754dp.h
+++ b/arch/mips/math-emu/ieee754dp.h
@@ -46,7 +46,7 @@
#define DPDNORMX DPDNORMx(xm, xe)
#define DPDNORMY DPDNORMx(ym, ye)
-static __inline ieee754dp builddp(int s, int bx, u64 m)
+static inline ieee754dp builddp(int s, int bx, u64 m)
{
ieee754dp r;
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index 9917c1e4d94..d9e3586b5bc 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -51,7 +51,7 @@
#define SPDNORMX SPDNORMx(xm, xe)
#define SPDNORMY SPDNORMx(ym, ye)
-static __inline ieee754sp buildsp(int s, int bx, unsigned m)
+static inline ieee754sp buildsp(int s, int bx, unsigned m)
{
ieee754sp r;
diff --git a/arch/mips/mips-boards/generic/Makefile b/arch/mips/mips-boards/generic/Makefile
index b31d8dfed1b..f7f87fc09d1 100644
--- a/arch/mips/mips-boards/generic/Makefile
+++ b/arch/mips/mips-boards/generic/Makefile
@@ -20,6 +20,7 @@
obj-y := reset.o display.o init.o memory.o \
cmdline.o time.o
+obj-y += amon.o
obj-$(CONFIG_EARLY_PRINTK) += console.o
obj-$(CONFIG_PCI) += pci.o
diff --git a/arch/mips/mips-boards/generic/amon.c b/arch/mips/mips-boards/generic/amon.c
new file mode 100644
index 00000000000..b7633fda418
--- /dev/null
+++ b/arch/mips/mips-boards/generic/amon.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 2007 MIPS Technologies, Inc.
+ * All rights reserved.
+
+ * This program is free software; you can distribute 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 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.
+ *
+ * Arbitrary Monitor interface
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm-mips/addrspace.h>
+#include <asm-mips/mips-boards/launch.h>
+#include <asm-mips/mipsmtregs.h>
+
+int amon_cpu_avail(int cpu)
+{
+ struct cpulaunch *launch = (struct cpulaunch *)KSEG0ADDR(CPULAUNCH);
+
+ if (cpu < 0 || cpu >= NCPULAUNCH) {
+ pr_debug("avail: cpu%d is out of range\n", cpu);
+ return 0;
+ }
+
+ launch += cpu;
+ if (!(launch->flags & LAUNCH_FREADY)) {
+ pr_debug("avail: cpu%d is not ready\n", cpu);
+ return 0;
+ }
+ if (launch->flags & (LAUNCH_FGO|LAUNCH_FGONE)) {
+ pr_debug("avail: too late.. cpu%d is already gone\n", cpu);
+ return 0;
+ }
+
+ return 1;
+}
+
+void amon_cpu_start(int cpu,
+ unsigned long pc, unsigned long sp,
+ unsigned long gp, unsigned long a0)
+{
+ volatile struct cpulaunch *launch =
+ (struct cpulaunch *)KSEG0ADDR(CPULAUNCH);
+
+ if (!amon_cpu_avail(cpu))
+ return;
+ if (cpu == smp_processor_id()) {
+ pr_debug("launch: I am cpu%d!\n", cpu);
+ return;
+ }
+ launch += cpu;
+
+ pr_debug("launch: starting cpu%d\n", cpu);
+
+ launch->pc = pc;
+ launch->gp = gp;
+ launch->sp = sp;
+ launch->a0 = a0;
+
+ /* Make sure target sees parameters before the go bit */
+ smp_mb();
+
+ launch->flags |= LAUNCH_FGO;
+ while ((launch->flags & LAUNCH_FGONE) == 0)
+ ;
+ pr_debug("launch: cpu%d gone!\n", cpu);
+}
diff --git a/arch/mips/mips-boards/generic/init.c b/arch/mips/mips-boards/generic/init.c
index 1695dca5506..83b9dc73920 100644
--- a/arch/mips/mips-boards/generic/init.c
+++ b/arch/mips/mips-boards/generic/init.c
@@ -226,7 +226,7 @@ void __init kgdb_config(void)
}
#endif
-void __init mips_nmi_setup(void)
+static void __init mips_nmi_setup(void)
{
void *base;
extern char except_vec_nmi;
@@ -238,7 +238,7 @@ void __init mips_nmi_setup(void)
flush_icache_range((unsigned long)base, (unsigned long)base + 0x80);
}
-void __init mips_ejtag_setup(void)
+static void __init mips_ejtag_setup(void)
{
void *base;
extern char except_vec_ejtag_debug;
@@ -295,15 +295,21 @@ void __init prom_init(void)
break;
case MIPS_REVISION_CORID_CORE_MSC:
case MIPS_REVISION_CORID_CORE_FPGA2:
- case MIPS_REVISION_CORID_CORE_FPGA3:
- case MIPS_REVISION_CORID_CORE_FPGA4:
case MIPS_REVISION_CORID_CORE_24K:
- case MIPS_REVISION_CORID_CORE_EMUL_MSC:
+ /*
+ * SOCit/ROCit support is essentially identical
+ * but make an attempt to distinguish them
+ */
mips_revision_sconid = MIPS_REVISION_SCON_SOCIT;
break;
+ case MIPS_REVISION_CORID_CORE_FPGA3:
+ case MIPS_REVISION_CORID_CORE_FPGA4:
+ case MIPS_REVISION_CORID_CORE_FPGA5:
+ case MIPS_REVISION_CORID_CORE_EMUL_MSC:
default:
- mips_display_message("CC Error");
- while (1); /* We die here... */
+ /* See above */
+ mips_revision_sconid = MIPS_REVISION_SCON_ROCIT;
+ break;
}
}
@@ -418,6 +424,9 @@ void __init prom_init(void)
#ifdef CONFIG_SERIAL_8250_CONSOLE
console_config();
#endif
+#ifdef CONFIG_MIPS_CMP
+ register_smp_ops(&cmp_smp_ops);
+#endif
#ifdef CONFIG_MIPS_MT_SMP
register_smp_ops(&vsmp_smp_ops);
#endif
diff --git a/arch/mips/mips-boards/generic/memory.c b/arch/mips/mips-boards/generic/memory.c
index dc272c18823..5e443bba566 100644
--- a/arch/mips/mips-boards/generic/memory.c
+++ b/arch/mips/mips-boards/generic/memory.c
@@ -37,7 +37,7 @@ enum yamon_memtypes {
yamon_prom,
yamon_free,
};
-struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
+static struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
#ifdef DEBUG
static char *mtypes[3] = {
@@ -50,7 +50,7 @@ static char *mtypes[3] = {
/* determined physical memory size, not overridden by command line args */
unsigned long physical_memsize = 0L;
-struct prom_pmemblock * __init prom_getmdesc(void)
+static struct prom_pmemblock * __init prom_getmdesc(void)
{
char *memsize_str;
unsigned int memsize;
diff --git a/arch/mips/mips-boards/generic/time.c b/arch/mips/mips-boards/generic/time.c
index b50e0fc406a..008fd82b584 100644
--- a/arch/mips/mips-boards/generic/time.c
+++ b/arch/mips/mips-boards/generic/time.c
@@ -55,16 +55,36 @@
unsigned long cpu_khz;
static int mips_cpu_timer_irq;
+static int mips_cpu_perf_irq;
extern int cp0_perfcount_irq;
+DEFINE_PER_CPU(unsigned int, tickcount);
+#define tickcount_this_cpu __get_cpu_var(tickcount)
+static unsigned long ledbitmask;
+
static void mips_timer_dispatch(void)
{
+#if defined(CONFIG_MIPS_MALTA) || defined(CONFIG_MIPS_ATLAS)
+ /*
+ * Yes, this is very tacky, won't work as expected with SMTC and
+ * dyntick will break it,
+ * but it gives me a nice warm feeling during debug
+ */
+#define LEDBAR 0xbf000408
+ if (tickcount_this_cpu++ >= HZ) {
+ tickcount_this_cpu = 0;
+ change_bit(smp_processor_id(), &ledbitmask);
+ smp_wmb(); /* Make sure every one else sees the change */
+ /* This will pick up any recent changes made by other CPU's */
+ *(unsigned int *)LEDBAR = ledbitmask;
+ }
+#endif
do_IRQ(mips_cpu_timer_irq);
}
static void mips_perf_dispatch(void)
{
- do_IRQ(cp0_perfcount_irq);
+ do_IRQ(mips_cpu_perf_irq);
}
/*
@@ -127,21 +147,20 @@ unsigned long read_persistent_clock(void)
return mc146818_get_cmos_time();
}
-void __init plat_perf_setup(void)
+static void __init plat_perf_setup(void)
{
- cp0_perfcount_irq = -1;
-
#ifdef MSC01E_INT_BASE
if (cpu_has_veic) {
set_vi_handler(MSC01E_INT_PERFCTR, mips_perf_dispatch);
- cp0_perfcount_irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR;
+ mips_cpu_perf_irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR;
} else
#endif
if (cp0_perfcount_irq >= 0) {
if (cpu_has_vint)
set_vi_handler(cp0_perfcount_irq, mips_perf_dispatch);
+ mips_cpu_perf_irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
#ifdef CONFIG_SMP
- set_irq_handler(cp0_perfcount_irq, handle_percpu_irq);
+ set_irq_handler(mips_cpu_perf_irq, handle_percpu_irq);
#endif
}
}
diff --git a/arch/mips/mips-boards/malta/Makefile b/arch/mips/mips-boards/malta/Makefile
index 931ca4600a6..8dc6e2ac4c0 100644
--- a/arch/mips/mips-boards/malta/Makefile
+++ b/arch/mips/mips-boards/malta/Makefile
@@ -22,6 +22,7 @@
obj-y := malta_int.o malta_platform.o malta_setup.o
obj-$(CONFIG_MTD) += malta_mtd.o
+# FIXME FIXME FIXME
obj-$(CONFIG_MIPS_MT_SMTC) += malta_smtc.o
EXTRA_CFLAGS += -Werror
diff --git a/arch/mips/mips-boards/malta/malta_int.c b/arch/mips/mips-boards/malta/malta_int.c
index dbe60eb55e2..8c495104b32 100644
--- a/arch/mips/mips-boards/malta/malta_int.c
+++ b/arch/mips/mips-boards/malta/malta_int.c
@@ -31,6 +31,7 @@
#include <linux/kernel.h>
#include <linux/random.h>
+#include <asm/traps.h>
#include <asm/i8259.h>
#include <asm/irq_cpu.h>
#include <asm/irq_regs.h>
@@ -41,6 +42,14 @@
#include <asm/mips-boards/generic.h>
#include <asm/mips-boards/msc01_pci.h>
#include <asm/msc01_ic.h>
+#include <asm/gic.h>
+#include <asm/gcmpregs.h>
+
+int gcmp_present = -1;
+int gic_present;
+static unsigned long _msc01_biu_base;
+static unsigned long _gcmp_base;
+static unsigned int ipi_map[NR_CPUS];
static DEFINE_SPINLOCK(mips_irq_lock);
@@ -121,6 +130,17 @@ static void malta_hw0_irqdispatch(void)
do_IRQ(MALTA_INT_BASE + irq);
}
+static void malta_ipi_irqdispatch(void)
+{
+ int irq;
+
+ irq = gic_get_int();
+ if (irq < 0)
+ return; /* interrupt has already been cleared */
+
+ do_IRQ(MIPS_GIC_IRQ_BASE + irq);
+}
+
static void corehi_irqdispatch(void)
{
unsigned int intedge, intsteer, pcicmd, pcibadaddr;
@@ -257,12 +277,61 @@ asmlinkage void plat_irq_dispatch(void)
if (irq == MIPSCPU_INT_I8259A)
malta_hw0_irqdispatch();
+ else if (gic_present && ((1 << irq) & ipi_map[smp_processor_id()]))
+ malta_ipi_irqdispatch();
else if (irq >= 0)
do_IRQ(MIPS_CPU_IRQ_BASE + irq);
else
spurious_interrupt();
}
+#ifdef CONFIG_MIPS_MT_SMP
+
+
+#define GIC_MIPS_CPU_IPI_RESCHED_IRQ 3
+#define GIC_MIPS_CPU_IPI_CALL_IRQ 4
+
+#define MIPS_CPU_IPI_RESCHED_IRQ 0 /* SW int 0 for resched */
+#define C_RESCHED C_SW0
+#define MIPS_CPU_IPI_CALL_IRQ 1 /* SW int 1 for resched */
+#define C_CALL C_SW1
+static int cpu_ipi_resched_irq, cpu_ipi_call_irq;
+
+static void ipi_resched_dispatch(void)
+{
+ do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ);
+}
+
+static void ipi_call_dispatch(void)
+{
+ do_IRQ(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ);
+}
+
+static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
+{
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
+{
+ smp_call_function_interrupt();
+
+ return IRQ_HANDLED;
+}
+
+static struct irqaction irq_resched = {
+ .handler = ipi_resched_interrupt,
+ .flags = IRQF_DISABLED|IRQF_PERCPU,
+ .name = "IPI_resched"
+};
+
+static struct irqaction irq_call = {
+ .handler = ipi_call_interrupt,
+ .flags = IRQF_DISABLED|IRQF_PERCPU,
+ .name = "IPI_call"
+};
+#endif /* CONFIG_MIPS_MT_SMP */
+
static struct irqaction i8259irq = {
.handler = no_action,
.name = "XT-PIC cascade"
@@ -273,13 +342,13 @@ static struct irqaction corehi_irqaction = {
.name = "CoreHi"
};
-msc_irqmap_t __initdata msc_irqmap[] = {
+static msc_irqmap_t __initdata msc_irqmap[] = {
{MSC01C_INT_TMR, MSC01_IRQ_EDGE, 0},
{MSC01C_INT_PCI, MSC01_IRQ_LEVEL, 0},
};
-int __initdata msc_nr_irqs = ARRAY_SIZE(msc_irqmap);
+static int __initdata msc_nr_irqs = ARRAY_SIZE(msc_irqmap);
-msc_irqmap_t __initdata msc_eicirqmap[] = {
+static msc_irqmap_t __initdata msc_eicirqmap[] = {
{MSC01E_INT_SW0, MSC01_IRQ_LEVEL, 0},
{MSC01E_INT_SW1, MSC01_IRQ_LEVEL, 0},
{MSC01E_INT_I8259A, MSC01_IRQ_LEVEL, 0},
@@ -291,15 +360,90 @@ msc_irqmap_t __initdata msc_eicirqmap[] = {
{MSC01E_INT_PERFCTR, MSC01_IRQ_LEVEL, 0},
{MSC01E_INT_CPUCTR, MSC01_IRQ_LEVEL, 0}
};
-int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap);
+
+static int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap);
+
+/*
+ * This GIC specific tabular array defines the association between External
+ * Interrupts and CPUs/Core Interrupts. The nature of the External
+ * Interrupts is also defined here - polarity/trigger.
+ */
+static struct gic_intr_map gic_intr_map[] = {
+ { GIC_EXT_INTR(0), X, X, X, X, 0 },
+ { GIC_EXT_INTR(1), X, X, X, X, 0 },
+ { GIC_EXT_INTR(2), X, X, X, X, 0 },
+ { GIC_EXT_INTR(3), 0, GIC_CPU_INT0, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(4), 0, GIC_CPU_INT1, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(5), 0, GIC_CPU_INT2, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(6), 0, GIC_CPU_INT3, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(7), 0, GIC_CPU_INT4, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(8), 0, GIC_CPU_INT3, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(9), 0, GIC_CPU_INT3, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(10), X, X, X, X, 0 },
+ { GIC_EXT_INTR(11), X, X, X, X, 0 },
+ { GIC_EXT_INTR(12), 0, GIC_CPU_INT3, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(13), 0, GIC_MAP_TO_NMI_MSK, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(14), 0, GIC_MAP_TO_NMI_MSK, GIC_POL_POS, GIC_TRIG_LEVEL, 0 },
+ { GIC_EXT_INTR(15), X, X, X, X, 0 },
+ { GIC_EXT_INTR(16), 0, GIC_CPU_INT1, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(17), 0, GIC_CPU_INT2, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(18), 1, GIC_CPU_INT1, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(19), 1, GIC_CPU_INT2, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(20), 2, GIC_CPU_INT1, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(21), 2, GIC_CPU_INT2, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(22), 3, GIC_CPU_INT1, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+ { GIC_EXT_INTR(23), 3, GIC_CPU_INT2, GIC_POL_POS, GIC_TRIG_EDGE, 1 },
+};
+
+/*
+ * GCMP needs to be detected before any SMP initialisation
+ */
+int __init gcmp_probe(unsigned long addr, unsigned long size)
+{
+ if (gcmp_present >= 0)
+ return gcmp_present;
+
+ _gcmp_base = (unsigned long) ioremap_nocache(GCMP_BASE_ADDR, GCMP_ADDRSPACE_SZ);
+ _msc01_biu_base = (unsigned long) ioremap_nocache(MSC01_BIU_REG_BASE, MSC01_BIU_ADDRSPACE_SZ);
+ gcmp_present = (GCMPGCB(GCMPB) & GCMP_GCB_GCMPB_GCMPBASE_MSK) == GCMP_BASE_ADDR;
+
+ if (gcmp_present)
+ printk(KERN_DEBUG "GCMP present\n");
+ return gcmp_present;
+}
+
+void __init fill_ipi_map(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(gic_intr_map); i++) {
+ if (gic_intr_map[i].ipiflag && (gic_intr_map[i].cpunum != X))
+ ipi_map[gic_intr_map[i].cpunum] |=
+ (1 << (gic_intr_map[i].pin + 2));
+ }
+}
void __init arch_init_irq(void)
{
+ int gic_present, gcmp_present;
+
init_i8259_irqs();
if (!cpu_has_veic)
mips_cpu_irq_init();
+ gcmp_present = gcmp_probe(GCMP_BASE_ADDR, GCMP_ADDRSPACE_SZ);
+ if (gcmp_present) {
+ GCMPGCB(GICBA) = GIC_BASE_ADDR | GCMP_GCB_GICBA_EN_MSK;
+ gic_present = 1;
+ } else {
+ _msc01_biu_base = (unsigned long) ioremap_nocache(MSC01_BIU_REG_BASE, MSC01_BIU_ADDRSPACE_SZ);
+ gic_present = (REG(_msc01_biu_base, MSC01_SC_CFG) &
+ MSC01_SC_CFG_GICPRES_MSK) >> MSC01_SC_CFG_GICPRES_SHF;
+ }
+ if (gic_present)
+ printk(KERN_DEBUG "GIC present\n");
+
switch (mips_revision_sconid) {
case MIPS_REVISION_SCON_SOCIT:
case MIPS_REVISION_SCON_ROCIT:
@@ -360,4 +504,206 @@ void __init arch_init_irq(void)
setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI,
&corehi_irqaction);
}
+
+#if defined(CONFIG_MIPS_MT_SMP)
+ if (gic_present) {
+ /* FIXME */
+ int i;
+ struct {
+ unsigned int resched;
+ unsigned int call;
+ } ipiirq[] = {
+ {
+ .resched = GIC_IPI_EXT_INTR_RESCHED_VPE0,
+ .call = GIC_IPI_EXT_INTR_CALLFNC_VPE0},
+ {
+ .resched = GIC_IPI_EXT_INTR_RESCHED_VPE1,
+ .call = GIC_IPI_EXT_INTR_CALLFNC_VPE1
+ }, {
+ .resched = GIC_IPI_EXT_INTR_RESCHED_VPE2,
+ .call = GIC_IPI_EXT_INTR_CALLFNC_VPE2
+ }, {
+ .resched = GIC_IPI_EXT_INTR_RESCHED_VPE3,
+ .call = GIC_IPI_EXT_INTR_CALLFNC_VPE3
+ }
+ };
+#define NIPI (sizeof(ipiirq)/sizeof(ipiirq[0]))
+ fill_ipi_map();
+ gic_init(GIC_BASE_ADDR, GIC_ADDRSPACE_SZ, gic_intr_map, ARRAY_SIZE(gic_intr_map), MIPS_GIC_IRQ_BASE);
+ if (!gcmp_present) {
+ /* Enable the GIC */
+ i = REG(_msc01_biu_base, MSC01_SC_CFG);
+ REG(_msc01_biu_base, MSC01_SC_CFG) =
+ (i | (0x1 << MSC01_SC_CFG_GICENA_SHF));
+ pr_debug("GIC Enabled\n");
+ }
+
+ /* set up ipi interrupts */
+ if (cpu_has_vint) {
+ set_vi_handler(MIPSCPU_INT_IPI0, malta_ipi_irqdispatch);
+ set_vi_handler(MIPSCPU_INT_IPI1, malta_ipi_irqdispatch);
+ }
+ /* Argh.. this really needs sorting out.. */
+ printk("CPU%d: status register was %08x\n", smp_processor_id(), read_c0_status());
+ write_c0_status(read_c0_status() | STATUSF_IP3 | STATUSF_IP4);
+ printk("CPU%d: status register now %08x\n", smp_processor_id(), read_c0_status());
+ write_c0_status(0x1100dc00);
+ printk("CPU%d: status register frc %08x\n", smp_processor_id(), read_c0_status());
+ for (i = 0; i < NIPI; i++) {
+ setup_irq(MIPS_GIC_IRQ_BASE + ipiirq[i].resched, &irq_resched);
+ setup_irq(MIPS_GIC_IRQ_BASE + ipiirq[i].call, &irq_call);
+
+ set_irq_handler(MIPS_GIC_IRQ_BASE + ipiirq[i].resched, handle_percpu_irq);
+ set_irq_handler(MIPS_GIC_IRQ_BASE + ipiirq[i].call, handle_percpu_irq);
+ }
+ } else {
+ /* set up ipi interrupts */
+ if (cpu_has_veic) {
+ set_vi_handler (MSC01E_INT_SW0, ipi_resched_dispatch);
+ set_vi_handler (MSC01E_INT_SW1, ipi_call_dispatch);
+ cpu_ipi_resched_irq = MSC01E_INT_SW0;
+ cpu_ipi_call_irq = MSC01E_INT_SW1;
+ } else {
+ if (cpu_has_vint) {
+ set_vi_handler (MIPS_CPU_IPI_RESCHED_IRQ, ipi_resched_dispatch);
+ set_vi_handler (MIPS_CPU_IPI_CALL_IRQ, ipi_call_dispatch);
+ }
+ cpu_ipi_resched_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_RESCHED_IRQ;
+ cpu_ipi_call_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ;
+ }
+
+ setup_irq(cpu_ipi_resched_irq, &irq_resched);
+ setup_irq(cpu_ipi_call_irq, &irq_call);
+
+ set_irq_handler(cpu_ipi_resched_irq, handle_percpu_irq);
+ set_irq_handler(cpu_ipi_call_irq, handle_percpu_irq);
+ }
+#endif
+}
+
+void malta_be_init(void)
+{
+ if (gcmp_present) {
+ /* Could change CM error mask register */
+ }
+}
+
+
+static char *tr[8] = {
+ "mem", "gcr", "gic", "mmio",
+ "0x04", "0x05", "0x06", "0x07"
+};
+
+static char *mcmd[32] = {
+ [0x00] = "0x00",
+ [0x01] = "Legacy Write",
+ [0x02] = "Legacy Read",
+ [0x03] = "0x03",
+ [0x04] = "0x04",
+ [0x05] = "0x05",
+ [0x06] = "0x06",
+ [0x07] = "0x07",
+ [0x08] = "Coherent Read Own",
+ [0x09] = "Coherent Read Share",
+ [0x0a] = "Coherent Read Discard",
+ [0x0b] = "Coherent Ready Share Always",
+ [0x0c] = "Coherent Upgrade",
+ [0x0d] = "Coherent Writeback",
+ [0x0e] = "0x0e",
+ [0x0f] = "0x0f",
+ [0x10] = "Coherent Copyback",
+ [0x11] = "Coherent Copyback Invalidate",
+ [0x12] = "Coherent Invalidate",
+ [0x13] = "Coherent Write Invalidate",
+ [0x14] = "Coherent Completion Sync",
+ [0x15] = "0x15",
+ [0x16] = "0x16",
+ [0x17] = "0x17",
+ [0x18] = "0x18",
+ [0x19] = "0x19",
+ [0x1a] = "0x1a",
+ [0x1b] = "0x1b",
+ [0x1c] = "0x1c",
+ [0x1d] = "0x1d",
+ [0x1e] = "0x1e",
+ [0x1f] = "0x1f"
+};
+
+static char *core[8] = {
+ "Invalid/OK", "Invalid/Data",
+ "Shared/OK", "Shared/Data",
+ "Modified/OK", "Modified/Data",
+ "Exclusive/OK", "Exclusive/Data"
+};
+
+static char *causes[32] = {
+ "None", "GC_WR_ERR", "GC_RD_ERR", "COH_WR_ERR",
+ "COH_RD_ERR", "MMIO_WR_ERR", "MMIO_RD_ERR", "0x07",
+ "0x08", "0x09", "0x0a", "0x0b",
+ "0x0c", "0x0d", "0x0e", "0x0f",
+ "0x10", "0x11", "0x12", "0x13",
+ "0x14", "0x15", "0x16", "INTVN_WR_ERR",
+ "INTVN_RD_ERR", "0x19", "0x1a", "0x1b",
+ "0x1c", "0x1d", "0x1e", "0x1f"
+};
+
+int malta_be_handler(struct pt_regs *regs, int is_fixup)
+{
+ /* This duplicates the handling in do_be which seems wrong */
+ int retval = is_fixup ? MIPS_BE_FIXUP : MIPS_BE_FATAL;
+
+ if (gcmp_present) {
+ unsigned long cm_error = GCMPGCB(GCMEC);
+ unsigned long cm_addr = GCMPGCB(GCMEA);
+ unsigned long cm_other = GCMPGCB(GCMEO);
+ unsigned long cause, ocause;
+ char buf[256];
+
+ cause = (cm_error & GCMP_GCB_GMEC_ERROR_TYPE_MSK);
+ if (cause != 0) {
+ cause >>= GCMP_GCB_GMEC_ERROR_TYPE_SHF;
+ if (cause < 16) {
+ unsigned long cca_bits = (cm_error >> 15) & 7;
+ unsigned long tr_bits = (cm_error >> 12) & 7;
+ unsigned long mcmd_bits = (cm_error >> 7) & 0x1f;
+ unsigned long stag_bits = (cm_error >> 3) & 15;
+ unsigned long sport_bits = (cm_error >> 0) & 7;
+
+ snprintf(buf, sizeof(buf),
+ "CCA=%lu TR=%s MCmd=%s STag=%lu "
+ "SPort=%lu\n",
+ cca_bits, tr[tr_bits], mcmd[mcmd_bits],
+ stag_bits, sport_bits);
+ } else {
+ /* glob state & sresp together */
+ unsigned long c3_bits = (cm_error >> 18) & 7;
+ unsigned long c2_bits = (cm_error >> 15) & 7;
+ unsigned long c1_bits = (cm_error >> 12) & 7;
+ unsigned long c0_bits = (cm_error >> 9) & 7;
+ unsigned long sc_bit = (cm_error >> 8) & 1;
+ unsigned long mcmd_bits = (cm_error >> 3) & 0x1f;
+ unsigned long sport_bits = (cm_error >> 0) & 7;
+ snprintf(buf, sizeof(buf),
+ "C3=%s C2=%s C1=%s C0=%s SC=%s "
+ "MCmd=%s SPort=%lu\n",
+ core[c3_bits], core[c2_bits],
+ core[c1_bits], core[c0_bits],
+ sc_bit ? "True" : "False",
+ mcmd[mcmd_bits], sport_bits);
+ }
+
+ ocause = (cm_other & GCMP_GCB_GMEO_ERROR_2ND_MSK) >>
+ GCMP_GCB_GMEO_ERROR_2ND_SHF;
+
+ printk("CM_ERROR=%08lx %s <%s>\n", cm_error,
+ causes[cause], buf);
+ printk("CM_ADDR =%08lx\n", cm_addr);
+ printk("CM_OTHER=%08lx %s\n", cm_other, causes[ocause]);
+
+ /* reprime cause register */
+ GCMPGCB(GCMEC) = 0;
+ }
+ }
+
+ return retval;
}
diff --git a/arch/mips/mips-boards/malta/malta_setup.c b/arch/mips/mips-boards/malta/malta_setup.c
index 2cd8f5734b3..e7cad54936c 100644
--- a/arch/mips/mips-boards/malta/malta_setup.c
+++ b/arch/mips/mips-boards/malta/malta_setup.c
@@ -1,7 +1,7 @@
/*
* Carsten Langgaard, carstenl@mips.com
* Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved.
- * Copyright (C) Dmitri Vorobiev
+ * Copyright (C) 2008 Dmitri Vorobiev
*
* This program is free software; you can distribute it and/or modify it
* under the terms of the GNU General Public License (Version 2) as
@@ -36,7 +36,10 @@
#include <linux/console.h>
#endif
-struct resource standard_io_resources[] = {
+extern void malta_be_init(void);
+extern int malta_be_handler(struct pt_regs *regs, int is_fixup);
+
+static struct resource standard_io_resources[] = {
{
.name = "dma1",
.start = 0x00,
@@ -220,4 +223,7 @@ void __init plat_mem_setup(void)
screen_info_setup();
#endif
mips_reboot_setup();
+
+ board_be_init = malta_be_init;
+ board_be_handler = malta_be_handler;
}
diff --git a/arch/mips/mipssim/sim_setup.c b/arch/mips/mipssim/sim_setup.c
index d49fe73426b..7c7148ef264 100644
--- a/arch/mips/mipssim/sim_setup.c
+++ b/arch/mips/mipssim/sim_setup.c
@@ -39,9 +39,6 @@
static void __init serial_init(void);
unsigned int _isbonito = 0;
-extern void __init sanitize_tlb_entries(void);
-
-
const char *get_system_type(void)
{
return "MIPSsim";
@@ -55,9 +52,6 @@ void __init plat_mem_setup(void)
pr_info("Linux started...\n");
-#ifdef CONFIG_MIPS_MT_SMP
- sanitize_tlb_entries();
-#endif
}
extern struct plat_smp_ops ssmtc_smp_ops;
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c6f832e0f41..48731020ca0 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -4,30 +4,29 @@
obj-y += cache.o dma-default.o extable.o fault.o \
init.o pgtable.o tlbex.o tlbex-fault.o \
- uasm.o
+ uasm.o page.o
obj-$(CONFIG_32BIT) += ioremap.o pgtable-32.o
obj-$(CONFIG_64BIT) += pgtable-64.o
obj-$(CONFIG_HIGHMEM) += highmem.o
-obj-$(CONFIG_CPU_LOONGSON2) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_MIPS32) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_MIPS64) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_NEVADA) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R10000) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R3000) += c-r3k.o tlb-r3k.o pg-r4k.o
-obj-$(CONFIG_CPU_R4300) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R4X00) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R5000) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R5432) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_R8000) += c-r4k.o cex-gen.o pg-r4k.o tlb-r8k.o
-obj-$(CONFIG_CPU_RM7000) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_RM9000) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_SB1) += c-r4k.o cerr-sb1.o cex-sb1.o pg-sb1.o \
- tlb-r4k.o
-obj-$(CONFIG_CPU_TX39XX) += c-tx39.o pg-r4k.o tlb-r3k.o
-obj-$(CONFIG_CPU_TX49XX) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
-obj-$(CONFIG_CPU_VR41XX) += c-r4k.o cex-gen.o pg-r4k.o tlb-r4k.o
+obj-$(CONFIG_CPU_LOONGSON2) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_MIPS32) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_MIPS64) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_NEVADA) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R10000) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R3000) += c-r3k.o tlb-r3k.o
+obj-$(CONFIG_CPU_R4300) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R4X00) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R5000) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R5432) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_R8000) += c-r4k.o cex-gen.o tlb-r8k.o
+obj-$(CONFIG_CPU_RM7000) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_RM9000) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_SB1) += c-r4k.o cerr-sb1.o cex-sb1.o tlb-r4k.o
+obj-$(CONFIG_CPU_TX39XX) += c-tx39.o tlb-r3k.o
+obj-$(CONFIG_CPU_TX49XX) += c-r4k.o cex-gen.o tlb-r4k.o
+obj-$(CONFIG_CPU_VR41XX) += c-r4k.o cex-gen.o tlb-r4k.o
obj-$(CONFIG_IP22_CPU_SCACHE) += sc-ip22.o
obj-$(CONFIG_R5000_CPU_SCACHE) += sc-r5k.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 77aefb4ebed..643c8bcffff 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -14,6 +14,7 @@
#include <linux/linkage.h>
#include <linux/sched.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/bitops.h>
#include <asm/bcache.h>
@@ -53,6 +54,12 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info,
preempt_enable();
}
+#if defined(CONFIG_MIPS_CMP)
+#define cpu_has_safe_index_cacheops 0
+#else
+#define cpu_has_safe_index_cacheops 1
+#endif
+
/*
* Must die.
*/
@@ -481,6 +488,8 @@ static inline void local_r4k_flush_cache_page(void *args)
if (cpu_has_dc_aliases || (exec && !cpu_has_ic_fills_f_dc)) {
r4k_blast_dcache_page(addr);
+ if (exec && !cpu_icache_snoops_remote_store)
+ r4k_blast_scache_page(addr);
}
if (exec) {
if (vaddr && cpu_has_vtag_icache && mm == current->active_mm) {
@@ -583,7 +592,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
* subset property so we have to flush the primary caches
* explicitly
*/
- if (size >= dcache_size) {
+ if (cpu_has_safe_index_cacheops && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
@@ -606,7 +615,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
return;
}
- if (size >= dcache_size) {
+ if (cpu_has_safe_index_cacheops && size >= dcache_size) {
r4k_blast_dcache();
} else {
R4600_HIT_CACHEOP_WAR_IMPL;
@@ -968,6 +977,7 @@ static void __cpuinit probe_pcache(void)
case CPU_24K:
case CPU_34K:
case CPU_74K:
+ case CPU_1004K:
if ((read_c0_config7() & (1 << 16))) {
/* effectively physically indexed dcache,
thus no virtual aliases. */
@@ -1216,9 +1226,25 @@ void au1x00_fixup_config_od(void)
}
}
+static int __cpuinitdata cca = -1;
+
+static int __init cca_setup(char *str)
+{
+ get_option(&str, &cca);
+
+ return 1;
+}
+
+__setup("cca=", cca_setup);
+
static void __cpuinit coherency_setup(void)
{
- change_c0_config(CONF_CM_CMASK, CONF_CM_DEFAULT);
+ if (cca < 0 || cca > 7)
+ cca = read_c0_config() & CONF_CM_CMASK;
+ _page_cachable_default = cca << _CACHE_SHIFT;
+
+ pr_debug("Using cache attribute %d\n", cca);
+ change_c0_config(CONF_CM_CMASK, cca);
/*
* c0_status.cu=0 specifies that updates by the sc instruction use
@@ -1248,6 +1274,20 @@ static void __cpuinit coherency_setup(void)
}
}
+#if defined(CONFIG_DMA_NONCOHERENT)
+
+static int __cpuinitdata coherentio;
+
+static int __init setcoherentio(char *str)
+{
+ coherentio = 1;
+
+ return 1;
+}
+
+__setup("coherentio", setcoherentio);
+#endif
+
void __cpuinit r4k_cache_init(void)
{
extern void build_clear_page(void);
@@ -1307,14 +1347,22 @@ void __cpuinit r4k_cache_init(void)
flush_data_cache_page = r4k_flush_data_cache_page;
flush_icache_range = r4k_flush_icache_range;
-#ifdef CONFIG_DMA_NONCOHERENT
- _dma_cache_wback_inv = r4k_dma_cache_wback_inv;
- _dma_cache_wback = r4k_dma_cache_wback_inv;
- _dma_cache_inv = r4k_dma_cache_inv;
+#if defined(CONFIG_DMA_NONCOHERENT)
+ if (coherentio) {
+ _dma_cache_wback_inv = (void *)cache_noop;
+ _dma_cache_wback = (void *)cache_noop;
+ _dma_cache_inv = (void *)cache_noop;
+ } else {
+ _dma_cache_wback_inv = r4k_dma_cache_wback_inv;
+ _dma_cache_wback = r4k_dma_cache_wback_inv;
+ _dma_cache_inv = r4k_dma_cache_inv;
+ }
#endif
build_clear_page();
build_copy_page();
+#if !defined(CONFIG_MIPS_CMP)
local_r4k___flush_cache_all(NULL);
+#endif
coherency_setup();
}
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index f5903679ee6..034e8506f6e 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -130,8 +130,28 @@ void __update_cache(struct vm_area_struct *vma, unsigned long address,
}
}
-static char cache_panic[] __cpuinitdata =
- "Yeee, unsupported cache architecture.";
+unsigned long _page_cachable_default;
+EXPORT_SYMBOL_GPL(_page_cachable_default);
+
+static inline void setup_protection_map(void)
+{
+ protection_map[0] = PAGE_NONE;
+ protection_map[1] = PAGE_READONLY;
+ protection_map[2] = PAGE_COPY;
+ protection_map[3] = PAGE_COPY;
+ protection_map[4] = PAGE_READONLY;
+ protection_map[5] = PAGE_READONLY;
+ protection_map[6] = PAGE_COPY;
+ protection_map[7] = PAGE_COPY;
+ protection_map[8] = PAGE_NONE;
+ protection_map[9] = PAGE_READONLY;
+ protection_map[10] = PAGE_SHARED;
+ protection_map[11] = PAGE_SHARED;
+ protection_map[12] = PAGE_READONLY;
+ protection_map[13] = PAGE_READONLY;
+ protection_map[14] = PAGE_SHARED;
+ protection_map[15] = PAGE_SHARED;
+}
void __devinit cpu_cache_init(void)
{
@@ -139,34 +159,29 @@ void __devinit cpu_cache_init(void)
extern void __weak r3k_cache_init(void);
r3k_cache_init();
- return;
}
if (cpu_has_6k_cache) {
extern void __weak r6k_cache_init(void);
r6k_cache_init();
- return;
}
if (cpu_has_4k_cache) {
extern void __weak r4k_cache_init(void);
r4k_cache_init();
- return;
}
if (cpu_has_8k_cache) {
extern void __weak r8k_cache_init(void);
r8k_cache_init();
- return;
}
if (cpu_has_tx39_cache) {
extern void __weak tx39_cache_init(void);
tx39_cache_init();
- return;
}
- panic(cache_panic);
+ setup_protection_map();
}
int __weak __uncached_access(struct file *file, unsigned long addr)
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index c7aed133d11..ecd562d2c34 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -142,7 +142,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
#endif
vaddr = __fix_to_virt(FIX_CMAP_END - idx);
pte = mk_pte(page, PAGE_KERNEL);
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
entrylo = pte.pte_high;
#else
entrylo = pte_val(pte) >> 6;
@@ -221,7 +221,7 @@ void copy_user_highpage(struct page *to, struct page *from,
copy_page(vto, vfrom);
kunmap_atomic(vfrom, KM_USER0);
}
- if (((vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc) ||
+ if ((!cpu_has_ic_fills_f_dc) ||
pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK))
flush_data_cache_page((unsigned long)vto);
kunmap_atomic(vto, KM_USER1);
@@ -229,8 +229,6 @@ void copy_user_highpage(struct page *to, struct page *from,
smp_wmb();
}
-EXPORT_SYMBOL(copy_user_highpage);
-
void copy_to_user_page(struct vm_area_struct *vma,
struct page *page, unsigned long vaddr, void *dst, const void *src,
unsigned long len)
@@ -249,8 +247,6 @@ void copy_to_user_page(struct vm_area_struct *vma,
flush_cache_page(vma, vaddr, page_to_pfn(page));
}
-EXPORT_SYMBOL(copy_to_user_page);
-
void copy_from_user_page(struct vm_area_struct *vma,
struct page *page, unsigned long vaddr, void *dst, const void *src,
unsigned long len)
@@ -267,9 +263,6 @@ void copy_from_user_page(struct vm_area_struct *vma,
}
}
-EXPORT_SYMBOL(copy_from_user_page);
-
-
#ifdef CONFIG_HIGHMEM
unsigned long highstart_pfn, highend_pfn;
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
new file mode 100644
index 00000000000..d827d614436
--- /dev/null
+++ b/arch/mips/mm/page.c
@@ -0,0 +1,684 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2007 Maciej W. Rozycki
+ * Copyright (C) 2008 Thiemo Seufer
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+
+#include <asm/bugs.h>
+#include <asm/cacheops.h>
+#include <asm/inst.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/prefetch.h>
+#include <asm/system.h>
+#include <asm/bootinfo.h>
+#include <asm/mipsregs.h>
+#include <asm/mmu_context.h>
+#include <asm/cpu.h>
+#include <asm/war.h>
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+#include <asm/sibyte/sb1250.h>
+#include <asm/sibyte/sb1250_regs.h>
+#include <asm/sibyte/sb1250_dma.h>
+#endif
+
+#include "uasm.h"
+
+/* Registers used in the assembled routines. */
+#define ZERO 0
+#define AT 2
+#define A0 4
+#define A1 5
+#define A2 6
+#define T0 8
+#define T1 9
+#define T2 10
+#define T3 11
+#define T9 25
+#define RA 31
+
+/* Handle labels (which must be positive integers). */
+enum label_id {
+ label_clear_nopref = 1,
+ label_clear_pref,
+ label_copy_nopref,
+ label_copy_pref_both,
+ label_copy_pref_store,
+};
+
+UASM_L_LA(_clear_nopref)
+UASM_L_LA(_clear_pref)
+UASM_L_LA(_copy_nopref)
+UASM_L_LA(_copy_pref_both)
+UASM_L_LA(_copy_pref_store)
+
+/* We need one branch and therefore one relocation per target label. */
+static struct uasm_label __cpuinitdata labels[5];
+static struct uasm_reloc __cpuinitdata relocs[5];
+
+#define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010)
+#define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020)
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache: 0x058 bytes
+ * R4600 v1.7: 0x05c bytes
+ * R4600 v2.0: 0x060 bytes
+ * With prefetching, 16 word strides 0x120 bytes
+ */
+
+static u32 clear_page_array[0x120 / 4];
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+void clear_page_cpu(void *page) __attribute__((alias("clear_page_array")));
+#else
+void clear_page(void *page) __attribute__((alias("clear_page_array")));
+#endif
+
+EXPORT_SYMBOL(clear_page);
+
+/*
+ * Maximum sizes:
+ *
+ * R4000 128 bytes S-cache: 0x11c bytes
+ * R4600 v1.7: 0x080 bytes
+ * R4600 v2.0: 0x07c bytes
+ * With prefetching, 16 word strides 0x540 bytes
+ */
+static u32 copy_page_array[0x540 / 4];
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+void
+copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array")));
+#else
+void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
+#endif
+
+EXPORT_SYMBOL(copy_page);
+
+
+static int pref_bias_clear_store __cpuinitdata;
+static int pref_bias_copy_load __cpuinitdata;
+static int pref_bias_copy_store __cpuinitdata;
+
+static u32 pref_src_mode __cpuinitdata;
+static u32 pref_dst_mode __cpuinitdata;
+
+static int clear_word_size __cpuinitdata;
+static int copy_word_size __cpuinitdata;
+
+static int half_clear_loop_size __cpuinitdata;
+static int half_copy_loop_size __cpuinitdata;
+
+static int cache_line_size __cpuinitdata;
+#define cache_line_mask() (cache_line_size - 1)
+
+static inline void __cpuinit
+pg_addiu(u32 **buf, unsigned int reg1, unsigned int reg2, unsigned int off)
+{
+ if (cpu_has_64bit_gp_regs && DADDI_WAR && r4k_daddiu_bug()) {
+ if (off > 0x7fff) {
+ uasm_i_lui(buf, T9, uasm_rel_hi(off));
+ uasm_i_addiu(buf, T9, T9, uasm_rel_lo(off));
+ } else
+ uasm_i_addiu(buf, T9, ZERO, off);
+ uasm_i_daddu(buf, reg1, reg2, T9);
+ } else {
+ if (off > 0x7fff) {
+ uasm_i_lui(buf, T9, uasm_rel_hi(off));
+ uasm_i_addiu(buf, T9, T9, uasm_rel_lo(off));
+ UASM_i_ADDU(buf, reg1, reg2, T9);
+ } else
+ UASM_i_ADDIU(buf, reg1, reg2, off);
+ }
+}
+
+static void __cpuinit set_prefetch_parameters(void)
+{
+ if (cpu_has_64bit_gp_regs || cpu_has_64bit_zero_reg)
+ clear_word_size = 8;
+ else
+ clear_word_size = 4;
+
+ if (cpu_has_64bit_gp_regs)
+ copy_word_size = 8;
+ else
+ copy_word_size = 4;
+
+ /*
+ * The pref's used here are using "streaming" hints, which cause the
+ * copied data to be kicked out of the cache sooner. A page copy often
+ * ends up copying a lot more data than is commonly used, so this seems
+ * to make sense in terms of reducing cache pollution, but I've no real
+ * performance data to back this up.
+ */
+ if (cpu_has_prefetch) {
+ /*
+ * XXX: Most prefetch bias values in here are based on
+ * guesswork.
+ */
+ cache_line_size = cpu_dcache_line_size();
+ switch (current_cpu_type()) {
+ case CPU_TX49XX:
+ /* TX49 supports only Pref_Load */
+ pref_bias_copy_load = 256;
+ break;
+
+ case CPU_RM9000:
+ /*
+ * As a workaround for erratum G105 which make the
+ * PrepareForStore hint unusable we fall back to
+ * StoreRetained on the RM9000. Once it is known which
+ * versions of the RM9000 we'll be able to condition-
+ * alize this.
+ */
+
+ case CPU_R10000:
+ case CPU_R12000:
+ case CPU_R14000:
+ /*
+ * Those values have been experimentally tuned for an
+ * Origin 200.
+ */
+ pref_bias_clear_store = 512;
+ pref_bias_copy_load = 256;
+ pref_bias_copy_store = 256;
+ pref_src_mode = Pref_LoadStreamed;
+ pref_dst_mode = Pref_StoreStreamed;
+ break;
+
+ case CPU_SB1:
+ case CPU_SB1A:
+ pref_bias_clear_store = 128;
+ pref_bias_copy_load = 128;
+ pref_bias_copy_store = 128;
+ /*
+ * SB1 pass1 Pref_LoadStreamed/Pref_StoreStreamed
+ * hints are broken.
+ */
+ if (current_cpu_type() == CPU_SB1 &&
+ (current_cpu_data.processor_id & 0xff) < 0x02) {
+ pref_src_mode = Pref_Load;
+ pref_dst_mode = Pref_Store;
+ } else {
+ pref_src_mode = Pref_LoadStreamed;
+ pref_dst_mode = Pref_StoreStreamed;
+ }
+ break;
+
+ default:
+ pref_bias_clear_store = 128;
+ pref_bias_copy_load = 256;
+ pref_bias_copy_store = 128;
+ pref_src_mode = Pref_LoadStreamed;
+ pref_dst_mode = Pref_PrepareForStore;
+ break;
+ }
+ } else {
+ if (cpu_has_cache_cdex_s)
+ cache_line_size = cpu_scache_line_size();
+ else if (cpu_has_cache_cdex_p)
+ cache_line_size = cpu_dcache_line_size();
+ }
+ /*
+ * Too much unrolling will overflow the available space in
+ * clear_space_array / copy_page_array. 8 words sounds generous,
+ * but a R4000 with 128 byte L2 line length can exceed even that.
+ */
+ half_clear_loop_size = min(8 * clear_word_size,
+ max(cache_line_size >> 1,
+ 4 * clear_word_size));
+ half_copy_loop_size = min(8 * copy_word_size,
+ max(cache_line_size >> 1,
+ 4 * copy_word_size));
+}
+
+static void __cpuinit build_clear_store(u32 **buf, int off)
+{
+ if (cpu_has_64bit_gp_regs || cpu_has_64bit_zero_reg) {
+ uasm_i_sd(buf, ZERO, off, A0);
+ } else {
+ uasm_i_sw(buf, ZERO, off, A0);
+ }
+}
+
+static inline void __cpuinit build_clear_pref(u32 **buf, int off)
+{
+ if (off & cache_line_mask())
+ return;
+
+ if (pref_bias_clear_store) {
+ uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off,
+ A0);
+ } else if (cpu_has_cache_cdex_s) {
+ uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+ } else if (cpu_has_cache_cdex_p) {
+ if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ }
+
+ if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+ uasm_i_lw(buf, ZERO, ZERO, AT);
+
+ uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
+ }
+}
+
+void __cpuinit build_clear_page(void)
+{
+ int off;
+ u32 *buf = (u32 *)&clear_page_array;
+ struct uasm_label *l = labels;
+ struct uasm_reloc *r = relocs;
+ int i;
+
+ memset(labels, 0, sizeof(labels));
+ memset(relocs, 0, sizeof(relocs));
+
+ set_prefetch_parameters();
+
+ /*
+ * This algorithm makes the following assumptions:
+ * - The prefetch bias is a multiple of 2 words.
+ * - The prefetch bias is less than one page.
+ */
+ BUG_ON(pref_bias_clear_store % (2 * clear_word_size));
+ BUG_ON(PAGE_SIZE < pref_bias_clear_store);
+
+ off = PAGE_SIZE - pref_bias_clear_store;
+ if (off > 0xffff || !pref_bias_clear_store)
+ pg_addiu(&buf, A2, A0, off);
+ else
+ uasm_i_ori(&buf, A2, A0, off);
+
+ if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+ uasm_i_lui(&buf, AT, 0xa000);
+
+ off = min(8, pref_bias_clear_store / cache_line_size) *
+ cache_line_size;
+ while (off) {
+ build_clear_pref(&buf, -off);
+ off -= cache_line_size;
+ }
+ uasm_l_clear_pref(&l, buf);
+ do {
+ build_clear_pref(&buf, off);
+ build_clear_store(&buf, off);
+ off += clear_word_size;
+ } while (off < half_clear_loop_size);
+ pg_addiu(&buf, A0, A0, 2 * off);
+ off = -off;
+ do {
+ build_clear_pref(&buf, off);
+ if (off == -clear_word_size)
+ uasm_il_bne(&buf, &r, A0, A2, label_clear_pref);
+ build_clear_store(&buf, off);
+ off += clear_word_size;
+ } while (off < 0);
+
+ if (pref_bias_clear_store) {
+ pg_addiu(&buf, A2, A0, pref_bias_clear_store);
+ uasm_l_clear_nopref(&l, buf);
+ off = 0;
+ do {
+ build_clear_store(&buf, off);
+ off += clear_word_size;
+ } while (off < half_clear_loop_size);
+ pg_addiu(&buf, A0, A0, 2 * off);
+ off = -off;
+ do {
+ if (off == -clear_word_size)
+ uasm_il_bne(&buf, &r, A0, A2,
+ label_clear_nopref);
+ build_clear_store(&buf, off);
+ off += clear_word_size;
+ } while (off < 0);
+ }
+
+ uasm_i_jr(&buf, RA);
+ uasm_i_nop(&buf);
+
+ BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array));
+
+ uasm_resolve_relocs(relocs, labels);
+
+ pr_debug("Synthesized clear page handler (%u instructions).\n",
+ (u32)(buf - clear_page_array));
+
+ pr_debug("\t.set push\n");
+ pr_debug("\t.set noreorder\n");
+ for (i = 0; i < (buf - clear_page_array); i++)
+ pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
+ pr_debug("\t.set pop\n");
+}
+
+static void __cpuinit build_copy_load(u32 **buf, int reg, int off)
+{
+ if (cpu_has_64bit_gp_regs) {
+ uasm_i_ld(buf, reg, off, A1);
+ } else {
+ uasm_i_lw(buf, reg, off, A1);
+ }
+}
+
+static void __cpuinit build_copy_store(u32 **buf, int reg, int off)
+{
+ if (cpu_has_64bit_gp_regs) {
+ uasm_i_sd(buf, reg, off, A0);
+ } else {
+ uasm_i_sw(buf, reg, off, A0);
+ }
+}
+
+static inline void build_copy_load_pref(u32 **buf, int off)
+{
+ if (off & cache_line_mask())
+ return;
+
+ if (pref_bias_copy_load)
+ uasm_i_pref(buf, pref_src_mode, pref_bias_copy_load + off, A1);
+}
+
+static inline void build_copy_store_pref(u32 **buf, int off)
+{
+ if (off & cache_line_mask())
+ return;
+
+ if (pref_bias_copy_store) {
+ uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off,
+ A0);
+ } else if (cpu_has_cache_cdex_s) {
+ uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+ } else if (cpu_has_cache_cdex_p) {
+ if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ uasm_i_nop(buf);
+ }
+
+ if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+ uasm_i_lw(buf, ZERO, ZERO, AT);
+
+ uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
+ }
+}
+
+void __cpuinit build_copy_page(void)
+{
+ int off;
+ u32 *buf = (u32 *)&copy_page_array;
+ struct uasm_label *l = labels;
+ struct uasm_reloc *r = relocs;
+ int i;
+
+ memset(labels, 0, sizeof(labels));
+ memset(relocs, 0, sizeof(relocs));
+
+ set_prefetch_parameters();
+
+ /*
+ * This algorithm makes the following assumptions:
+ * - All prefetch biases are multiples of 8 words.
+ * - The prefetch biases are less than one page.
+ * - The store prefetch bias isn't greater than the load
+ * prefetch bias.
+ */
+ BUG_ON(pref_bias_copy_load % (8 * copy_word_size));
+ BUG_ON(pref_bias_copy_store % (8 * copy_word_size));
+ BUG_ON(PAGE_SIZE < pref_bias_copy_load);
+ BUG_ON(pref_bias_copy_store > pref_bias_copy_load);
+
+ off = PAGE_SIZE - pref_bias_copy_load;
+ if (off > 0xffff || !pref_bias_copy_load)
+ pg_addiu(&buf, A2, A0, off);
+ else
+ uasm_i_ori(&buf, A2, A0, off);
+
+ if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+ uasm_i_lui(&buf, AT, 0xa000);
+
+ off = min(8, pref_bias_copy_load / cache_line_size) * cache_line_size;
+ while (off) {
+ build_copy_load_pref(&buf, -off);
+ off -= cache_line_size;
+ }
+ off = min(8, pref_bias_copy_store / cache_line_size) * cache_line_size;
+ while (off) {
+ build_copy_store_pref(&buf, -off);
+ off -= cache_line_size;
+ }
+ uasm_l_copy_pref_both(&l, buf);
+ do {
+ build_copy_load_pref(&buf, off);
+ build_copy_load(&buf, T0, off);
+ build_copy_load_pref(&buf, off + copy_word_size);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load_pref(&buf, off + 2 * copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load_pref(&buf, off + 3 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store_pref(&buf, off);
+ build_copy_store(&buf, T0, off);
+ build_copy_store_pref(&buf, off + copy_word_size);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store_pref(&buf, off + 2 * copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ build_copy_store_pref(&buf, off + 3 * copy_word_size);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < half_copy_loop_size);
+ pg_addiu(&buf, A1, A1, 2 * off);
+ pg_addiu(&buf, A0, A0, 2 * off);
+ off = -off;
+ do {
+ build_copy_load_pref(&buf, off);
+ build_copy_load(&buf, T0, off);
+ build_copy_load_pref(&buf, off + copy_word_size);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load_pref(&buf, off + 2 * copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load_pref(&buf, off + 3 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store_pref(&buf, off);
+ build_copy_store(&buf, T0, off);
+ build_copy_store_pref(&buf, off + copy_word_size);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store_pref(&buf, off + 2 * copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ build_copy_store_pref(&buf, off + 3 * copy_word_size);
+ if (off == -(4 * copy_word_size))
+ uasm_il_bne(&buf, &r, A2, A0, label_copy_pref_both);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < 0);
+
+ if (pref_bias_copy_load - pref_bias_copy_store) {
+ pg_addiu(&buf, A2, A0,
+ pref_bias_copy_load - pref_bias_copy_store);
+ uasm_l_copy_pref_store(&l, buf);
+ off = 0;
+ do {
+ build_copy_load(&buf, T0, off);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store_pref(&buf, off);
+ build_copy_store(&buf, T0, off);
+ build_copy_store_pref(&buf, off + copy_word_size);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store_pref(&buf, off + 2 * copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ build_copy_store_pref(&buf, off + 3 * copy_word_size);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < half_copy_loop_size);
+ pg_addiu(&buf, A1, A1, 2 * off);
+ pg_addiu(&buf, A0, A0, 2 * off);
+ off = -off;
+ do {
+ build_copy_load(&buf, T0, off);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store_pref(&buf, off);
+ build_copy_store(&buf, T0, off);
+ build_copy_store_pref(&buf, off + copy_word_size);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store_pref(&buf, off + 2 * copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ build_copy_store_pref(&buf, off + 3 * copy_word_size);
+ if (off == -(4 * copy_word_size))
+ uasm_il_bne(&buf, &r, A2, A0,
+ label_copy_pref_store);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < 0);
+ }
+
+ if (pref_bias_copy_store) {
+ pg_addiu(&buf, A2, A0, pref_bias_copy_store);
+ uasm_l_copy_nopref(&l, buf);
+ off = 0;
+ do {
+ build_copy_load(&buf, T0, off);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store(&buf, T0, off);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < half_copy_loop_size);
+ pg_addiu(&buf, A1, A1, 2 * off);
+ pg_addiu(&buf, A0, A0, 2 * off);
+ off = -off;
+ do {
+ build_copy_load(&buf, T0, off);
+ build_copy_load(&buf, T1, off + copy_word_size);
+ build_copy_load(&buf, T2, off + 2 * copy_word_size);
+ build_copy_load(&buf, T3, off + 3 * copy_word_size);
+ build_copy_store(&buf, T0, off);
+ build_copy_store(&buf, T1, off + copy_word_size);
+ build_copy_store(&buf, T2, off + 2 * copy_word_size);
+ if (off == -(4 * copy_word_size))
+ uasm_il_bne(&buf, &r, A2, A0,
+ label_copy_nopref);
+ build_copy_store(&buf, T3, off + 3 * copy_word_size);
+ off += 4 * copy_word_size;
+ } while (off < 0);
+ }
+
+ uasm_i_jr(&buf, RA);
+ uasm_i_nop(&buf);
+
+ BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array));
+
+ uasm_resolve_relocs(relocs, labels);
+
+ pr_debug("Synthesized copy page handler (%u instructions).\n",
+ (u32)(buf - copy_page_array));
+
+ pr_debug("\t.set push\n");
+ pr_debug("\t.set noreorder\n");
+ for (i = 0; i < (buf - copy_page_array); i++)
+ pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
+ pr_debug("\t.set pop\n");
+}
+
+#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
+
+/*
+ * Pad descriptors to cacheline, since each is exclusively owned by a
+ * particular CPU.
+ */
+struct dmadscr {
+ u64 dscr_a;
+ u64 dscr_b;
+ u64 pad_a;
+ u64 pad_b;
+} ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
+
+void sb1_dma_init(void)
+{
+ int i;
+
+ for (i = 0; i < DM_NUM_CHANNELS; i++) {
+ const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
+ V_DM_DSCR_BASE_RINGSZ(1);
+ void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
+
+ __raw_writeq(base_val, base_reg);
+ __raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
+ __raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
+ }
+}
+
+void clear_page(void *page)
+{
+ u64 to_phys = CPHYSADDR((unsigned long)page);
+ unsigned int cpu = smp_processor_id();
+
+ /* if the page is not in KSEG0, use old way */
+ if ((long)KSEGX((unsigned long)page) != (long)CKSEG0)
+ return clear_page_cpu(page);
+
+ page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_ZERO_MEM |
+ M_DM_DSCRA_L2C_DEST | M_DM_DSCRA_INTERRUPT;
+ page_descr[cpu].dscr_b = V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
+ __raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
+
+ /*
+ * Don't really want to do it this way, but there's no
+ * reliable way to delay completion detection.
+ */
+ while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
+ & M_DM_DSCR_BASE_INTERRUPT))
+ ;
+ __raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
+}
+
+void copy_page(void *to, void *from)
+{
+ u64 from_phys = CPHYSADDR((unsigned long)from);
+ u64 to_phys = CPHYSADDR((unsigned long)to);
+ unsigned int cpu = smp_processor_id();
+
+ /* if any page is not in KSEG0, use old way */
+ if ((long)KSEGX((unsigned long)to) != (long)CKSEG0
+ || (long)KSEGX((unsigned long)from) != (long)CKSEG0)
+ return copy_page_cpu(to, from);
+
+ page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_L2C_DEST |
+ M_DM_DSCRA_INTERRUPT;
+ page_descr[cpu].dscr_b = from_phys | V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
+ __raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
+
+ /*
+ * Don't really want to do it this way, but there's no
+ * reliable way to delay completion detection.
+ */
+ while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
+ & M_DM_DSCR_BASE_INTERRUPT))
+ ;
+ __raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
+}
+
+#endif /* CONFIG_SIBYTE_DMA_PAGEOPS */
diff --git a/arch/mips/mm/pg-r4k.c b/arch/mips/mm/pg-r4k.c
deleted file mode 100644
index 455dedb5b39..00000000000
--- a/arch/mips/mm/pg-r4k.c
+++ /dev/null
@@ -1,534 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org)
- * Copyright (C) 2007 Maciej W. Rozycki
- */
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/proc_fs.h>
-
-#include <asm/bugs.h>
-#include <asm/cacheops.h>
-#include <asm/inst.h>
-#include <asm/io.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/prefetch.h>
-#include <asm/system.h>
-#include <asm/bootinfo.h>
-#include <asm/mipsregs.h>
-#include <asm/mmu_context.h>
-#include <asm/cpu.h>
-#include <asm/war.h>
-
-#define half_scache_line_size() (cpu_scache_line_size() >> 1)
-#define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010)
-#define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020)
-
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache: 0x58 bytes
- * R4600 v1.7: 0x5c bytes
- * R4600 v2.0: 0x60 bytes
- * With prefetching, 16 byte strides 0xa0 bytes
- */
-
-static unsigned int clear_page_array[0x130 / 4];
-
-void clear_page(void * page) __attribute__((alias("clear_page_array")));
-
-EXPORT_SYMBOL(clear_page);
-
-/*
- * Maximum sizes:
- *
- * R4000 128 bytes S-cache: 0x11c bytes
- * R4600 v1.7: 0x080 bytes
- * R4600 v2.0: 0x07c bytes
- * With prefetching, 16 byte strides 0x0b8 bytes
- */
-static unsigned int copy_page_array[0x148 / 4];
-
-void copy_page(void *to, void *from) __attribute__((alias("copy_page_array")));
-
-EXPORT_SYMBOL(copy_page);
-
-/*
- * This is suboptimal for 32-bit kernels; we assume that R10000 is only used
- * with 64-bit kernels. The prefetch offsets have been experimentally tuned
- * an Origin 200.
- */
-static int pref_offset_clear __cpuinitdata = 512;
-static int pref_offset_copy __cpuinitdata = 256;
-
-static unsigned int pref_src_mode __cpuinitdata;
-static unsigned int pref_dst_mode __cpuinitdata;
-
-static int load_offset __cpuinitdata;
-static int store_offset __cpuinitdata;
-
-static unsigned int __cpuinitdata *dest, *epc;
-
-static unsigned int instruction_pending;
-static union mips_instruction delayed_mi;
-
-static void __cpuinit emit_instruction(union mips_instruction mi)
-{
- if (instruction_pending)
- *epc++ = delayed_mi.word;
-
- instruction_pending = 1;
- delayed_mi = mi;
-}
-
-static inline void flush_delay_slot_or_nop(void)
-{
- if (instruction_pending) {
- *epc++ = delayed_mi.word;
- instruction_pending = 0;
- return;
- }
-
- *epc++ = 0;
-}
-
-static inline unsigned int *label(void)
-{
- if (instruction_pending) {
- *epc++ = delayed_mi.word;
- instruction_pending = 0;
- }
-
- return epc;
-}
-
-static inline void build_insn_word(unsigned int word)
-{
- union mips_instruction mi;
-
- mi.word = word;
-
- emit_instruction(mi);
-}
-
-static inline void build_nop(void)
-{
- build_insn_word(0); /* nop */
-}
-
-static inline void build_src_pref(int advance)
-{
- if (!(load_offset & (cpu_dcache_line_size() - 1)) && advance) {
- union mips_instruction mi;
-
- mi.i_format.opcode = pref_op;
- mi.i_format.rs = 5; /* $a1 */
- mi.i_format.rt = pref_src_mode;
- mi.i_format.simmediate = load_offset + advance;
-
- emit_instruction(mi);
- }
-}
-
-static inline void __build_load_reg(int reg)
-{
- union mips_instruction mi;
- unsigned int width;
-
- if (cpu_has_64bit_gp_regs) {
- mi.i_format.opcode = ld_op;
- width = 8;
- } else {
- mi.i_format.opcode = lw_op;
- width = 4;
- }
- mi.i_format.rs = 5; /* $a1 */
- mi.i_format.rt = reg; /* $reg */
- mi.i_format.simmediate = load_offset;
-
- load_offset += width;
- emit_instruction(mi);
-}
-
-static inline void build_load_reg(int reg)
-{
- if (cpu_has_prefetch)
- build_src_pref(pref_offset_copy);
-
- __build_load_reg(reg);
-}
-
-static inline void build_dst_pref(int advance)
-{
- if (!(store_offset & (cpu_dcache_line_size() - 1)) && advance) {
- union mips_instruction mi;
-
- mi.i_format.opcode = pref_op;
- mi.i_format.rs = 4; /* $a0 */
- mi.i_format.rt = pref_dst_mode;
- mi.i_format.simmediate = store_offset + advance;
-
- emit_instruction(mi);
- }
-}
-
-static inline void build_cdex_s(void)
-{
- union mips_instruction mi;
-
- if ((store_offset & (cpu_scache_line_size() - 1)))
- return;
-
- mi.c_format.opcode = cache_op;
- mi.c_format.rs = 4; /* $a0 */
- mi.c_format.c_op = 3; /* Create Dirty Exclusive */
- mi.c_format.cache = 3; /* Secondary Data Cache */
- mi.c_format.simmediate = store_offset;
-
- emit_instruction(mi);
-}
-
-static inline void build_cdex_p(void)
-{
- union mips_instruction mi;
-
- if (store_offset & (cpu_dcache_line_size() - 1))
- return;
-
- if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
- build_nop();
- build_nop();
- build_nop();
- build_nop();
- }
-
- if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
- build_insn_word(0x8c200000); /* lw $zero, ($at) */
-
- mi.c_format.opcode = cache_op;
- mi.c_format.rs = 4; /* $a0 */
- mi.c_format.c_op = 3; /* Create Dirty Exclusive */
- mi.c_format.cache = 1; /* Data Cache */
- mi.c_format.simmediate = store_offset;
-
- emit_instruction(mi);
-}
-
-static void __cpuinit __build_store_reg(int reg)
-{
- union mips_instruction mi;
- unsigned int width;
-
- if (cpu_has_64bit_gp_regs ||
- (cpu_has_64bit_zero_reg && reg == 0)) {
- mi.i_format.opcode = sd_op;
- width = 8;
- } else {
- mi.i_format.opcode = sw_op;
- width = 4;
- }
- mi.i_format.rs = 4; /* $a0 */
- mi.i_format.rt = reg; /* $reg */
- mi.i_format.simmediate = store_offset;
-
- store_offset += width;
- emit_instruction(mi);
-}
-
-static inline void build_store_reg(int reg)
-{
- int pref_off = cpu_has_prefetch ?
- (reg ? pref_offset_copy : pref_offset_clear) : 0;
- if (pref_off)
- build_dst_pref(pref_off);
- else if (cpu_has_cache_cdex_s)
- build_cdex_s();
- else if (cpu_has_cache_cdex_p)
- build_cdex_p();
-
- __build_store_reg(reg);
-}
-
-static inline void build_addiu_rt_rs(unsigned int rt, unsigned int rs,
- unsigned long offset)
-{
- union mips_instruction mi;
-
- BUG_ON(offset > 0x7fff);
-
- if (cpu_has_64bit_gp_regs && DADDI_WAR && r4k_daddiu_bug()) {
- mi.i_format.opcode = addiu_op;
- mi.i_format.rs = 0; /* $zero */
- mi.i_format.rt = 25; /* $t9 */
- mi.i_format.simmediate = offset;
- emit_instruction(mi);
-
- mi.r_format.opcode = spec_op;
- mi.r_format.rs = rs;
- mi.r_format.rt = 25; /* $t9 */
- mi.r_format.rd = rt;
- mi.r_format.re = 0;
- mi.r_format.func = daddu_op;
- } else {
- mi.i_format.opcode = cpu_has_64bit_gp_regs ?
- daddiu_op : addiu_op;
- mi.i_format.rs = rs;
- mi.i_format.rt = rt;
- mi.i_format.simmediate = offset;
- }
- emit_instruction(mi);
-}
-
-static inline void build_addiu_a2_a0(unsigned long offset)
-{
- build_addiu_rt_rs(6, 4, offset); /* $a2, $a0, offset */
-}
-
-static inline void build_addiu_a2(unsigned long offset)
-{
- build_addiu_rt_rs(6, 6, offset); /* $a2, $a2, offset */
-}
-
-static inline void build_addiu_a1(unsigned long offset)
-{
- build_addiu_rt_rs(5, 5, offset); /* $a1, $a1, offset */
-
- load_offset -= offset;
-}
-
-static inline void build_addiu_a0(unsigned long offset)
-{
- build_addiu_rt_rs(4, 4, offset); /* $a0, $a0, offset */
-
- store_offset -= offset;
-}
-
-static inline void build_bne(unsigned int *dest)
-{
- union mips_instruction mi;
-
- mi.i_format.opcode = bne_op;
- mi.i_format.rs = 6; /* $a2 */
- mi.i_format.rt = 4; /* $a0 */
- mi.i_format.simmediate = dest - epc - 1;
-
- *epc++ = mi.word;
- flush_delay_slot_or_nop();
-}
-
-static inline void build_jr_ra(void)
-{
- union mips_instruction mi;
-
- mi.r_format.opcode = spec_op;
- mi.r_format.rs = 31;
- mi.r_format.rt = 0;
- mi.r_format.rd = 0;
- mi.r_format.re = 0;
- mi.r_format.func = jr_op;
-
- *epc++ = mi.word;
- flush_delay_slot_or_nop();
-}
-
-void __cpuinit build_clear_page(void)
-{
- unsigned int loop_start;
- unsigned long off;
- int i;
-
- epc = (unsigned int *) &clear_page_array;
- instruction_pending = 0;
- store_offset = 0;
-
- if (cpu_has_prefetch) {
- switch (current_cpu_type()) {
- case CPU_TX49XX:
- /* TX49 supports only Pref_Load */
- pref_offset_clear = 0;
- pref_offset_copy = 0;
- break;
-
- case CPU_RM9000:
- /*
- * As a workaround for erratum G105 which make the
- * PrepareForStore hint unusable we fall back to
- * StoreRetained on the RM9000. Once it is known which
- * versions of the RM9000 we'll be able to condition-
- * alize this.
- */
-
- case CPU_R10000:
- case CPU_R12000:
- case CPU_R14000:
- pref_src_mode = Pref_LoadStreamed;
- pref_dst_mode = Pref_StoreStreamed;
- break;
-
- default:
- pref_src_mode = Pref_LoadStreamed;
- pref_dst_mode = Pref_PrepareForStore;
- break;
- }
- }
-
- off = PAGE_SIZE - (cpu_has_prefetch ? pref_offset_clear : 0);
- if (off > 0x7fff) {
- build_addiu_a2_a0(off >> 1);
- build_addiu_a2(off >> 1);
- } else
- build_addiu_a2_a0(off);
-
- if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
- build_insn_word(0x3c01a000); /* lui $at, 0xa000 */
-
-dest = label();
- do {
- build_store_reg(0);
- build_store_reg(0);
- build_store_reg(0);
- build_store_reg(0);
- } while (store_offset < half_scache_line_size());
- build_addiu_a0(2 * store_offset);
- loop_start = store_offset;
- do {
- build_store_reg(0);
- build_store_reg(0);
- build_store_reg(0);
- build_store_reg(0);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_bne(dest);
-
- if (cpu_has_prefetch && pref_offset_clear) {
- build_addiu_a2_a0(pref_offset_clear);
- dest = label();
- loop_start = store_offset;
- do {
- __build_store_reg(0);
- __build_store_reg(0);
- __build_store_reg(0);
- __build_store_reg(0);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_addiu_a0(2 * store_offset);
- loop_start = store_offset;
- do {
- __build_store_reg(0);
- __build_store_reg(0);
- __build_store_reg(0);
- __build_store_reg(0);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_bne(dest);
- }
-
- build_jr_ra();
-
- BUG_ON(epc > clear_page_array + ARRAY_SIZE(clear_page_array));
-
- pr_info("Synthesized clear page handler (%u instructions).\n",
- (unsigned int)(epc - clear_page_array));
-
- pr_debug("\t.set push\n");
- pr_debug("\t.set noreorder\n");
- for (i = 0; i < (epc - clear_page_array); i++)
- pr_debug("\t.word 0x%08x\n", clear_page_array[i]);
- pr_debug("\t.set pop\n");
-}
-
-void __cpuinit build_copy_page(void)
-{
- unsigned int loop_start;
- unsigned long off;
- int i;
-
- epc = (unsigned int *) &copy_page_array;
- store_offset = load_offset = 0;
- instruction_pending = 0;
-
- off = PAGE_SIZE - (cpu_has_prefetch ? pref_offset_copy : 0);
- if (off > 0x7fff) {
- build_addiu_a2_a0(off >> 1);
- build_addiu_a2(off >> 1);
- } else
- build_addiu_a2_a0(off);
-
- if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
- build_insn_word(0x3c01a000); /* lui $at, 0xa000 */
-
-dest = label();
- loop_start = store_offset;
- do {
- build_load_reg( 8);
- build_load_reg( 9);
- build_load_reg(10);
- build_load_reg(11);
- build_store_reg( 8);
- build_store_reg( 9);
- build_store_reg(10);
- build_store_reg(11);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_addiu_a0(2 * store_offset);
- build_addiu_a1(2 * load_offset);
- loop_start = store_offset;
- do {
- build_load_reg( 8);
- build_load_reg( 9);
- build_load_reg(10);
- build_load_reg(11);
- build_store_reg( 8);
- build_store_reg( 9);
- build_store_reg(10);
- build_store_reg(11);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_bne(dest);
-
- if (cpu_has_prefetch && pref_offset_copy) {
- build_addiu_a2_a0(pref_offset_copy);
- dest = label();
- loop_start = store_offset;
- do {
- __build_load_reg( 8);
- __build_load_reg( 9);
- __build_load_reg(10);
- __build_load_reg(11);
- __build_store_reg( 8);
- __build_store_reg( 9);
- __build_store_reg(10);
- __build_store_reg(11);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_addiu_a0(2 * store_offset);
- build_addiu_a1(2 * load_offset);
- loop_start = store_offset;
- do {
- __build_load_reg( 8);
- __build_load_reg( 9);
- __build_load_reg(10);
- __build_load_reg(11);
- __build_store_reg( 8);
- __build_store_reg( 9);
- __build_store_reg(10);
- __build_store_reg(11);
- } while ((store_offset - loop_start) < half_scache_line_size());
- build_bne(dest);
- }
-
- build_jr_ra();
-
- BUG_ON(epc > copy_page_array + ARRAY_SIZE(copy_page_array));
-
- pr_info("Synthesized copy page handler (%u instructions).\n",
- (unsigned int)(epc - copy_page_array));
-
- pr_debug("\t.set push\n");
- pr_debug("\t.set noreorder\n");
- for (i = 0; i < (epc - copy_page_array); i++)
- pr_debug("\t.word 0x%08x\n", copy_page_array[i]);
- pr_debug("\t.set pop\n");
-}
diff --git a/arch/mips/mm/pg-sb1.c b/arch/mips/mm/pg-sb1.c
deleted file mode 100644
index 49e289d0541..00000000000
--- a/arch/mips/mm/pg-sb1.c
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Copyright (C) 1996 David S. Miller (dm@engr.sgi.com)
- * Copyright (C) 1997, 2001 Ralf Baechle (ralf@gnu.org)
- * Copyright (C) 2000 SiByte, Inc.
- * Copyright (C) 2005 Thiemo Seufer
- *
- * Written by Justin Carlson of SiByte, Inc.
- * and Kip Walker of Broadcom 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 program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- */
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-
-#include <asm/io.h>
-#include <asm/sibyte/sb1250.h>
-#include <asm/sibyte/sb1250_regs.h>
-#include <asm/sibyte/sb1250_dma.h>
-
-#ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-#define SB1_PREF_LOAD_STREAMED_HINT "0"
-#define SB1_PREF_STORE_STREAMED_HINT "1"
-#else
-#define SB1_PREF_LOAD_STREAMED_HINT "4"
-#define SB1_PREF_STORE_STREAMED_HINT "5"
-#endif
-
-static inline void clear_page_cpu(void *page)
-{
- unsigned char *addr = (unsigned char *) page;
- unsigned char *end = addr + PAGE_SIZE;
-
- /*
- * JDCXXX - This should be bottlenecked by the write buffer, but these
- * things tend to be mildly unpredictable...should check this on the
- * performance model
- *
- * We prefetch 4 lines ahead. We're also "cheating" slightly here...
- * since we know we're on an SB1, we force the assembler to take
- * 64-bit operands to speed things up
- */
- __asm__ __volatile__(
- " .set push \n"
- " .set mips4 \n"
- " .set noreorder \n"
-#ifdef CONFIG_CPU_HAS_PREFETCH
- " daddiu %0, %0, 128 \n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -128(%0) \n"
- /* Prefetch the first 4 lines */
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -96(%0) \n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -64(%0) \n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -32(%0) \n"
- "1: sd $0, -128(%0) \n" /* Throw out a cacheline of 0's */
- " sd $0, -120(%0) \n"
- " sd $0, -112(%0) \n"
- " sd $0, -104(%0) \n"
- " daddiu %0, %0, 32 \n"
- " bnel %0, %1, 1b \n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -32(%0) \n"
- " daddiu %0, %0, -128 \n"
-#endif
- " sd $0, 0(%0) \n" /* Throw out a cacheline of 0's */
- "1: sd $0, 8(%0) \n"
- " sd $0, 16(%0) \n"
- " sd $0, 24(%0) \n"
- " daddiu %0, %0, 32 \n"
- " bnel %0, %1, 1b \n"
- " sd $0, 0(%0) \n"
- " .set pop \n"
- : "+r" (addr)
- : "r" (end)
- : "memory");
-}
-
-static inline void copy_page_cpu(void *to, void *from)
-{
- unsigned char *src = (unsigned char *)from;
- unsigned char *dst = (unsigned char *)to;
- unsigned char *end = src + PAGE_SIZE;
-
- /*
- * The pref's used here are using "streaming" hints, which cause the
- * copied data to be kicked out of the cache sooner. A page copy often
- * ends up copying a lot more data than is commonly used, so this seems
- * to make sense in terms of reducing cache pollution, but I've no real
- * performance data to back this up
- */
- __asm__ __volatile__(
- " .set push \n"
- " .set mips4 \n"
- " .set noreorder \n"
-#ifdef CONFIG_CPU_HAS_PREFETCH
- " daddiu %0, %0, 128 \n"
- " daddiu %1, %1, 128 \n"
- " pref " SB1_PREF_LOAD_STREAMED_HINT ", -128(%0)\n"
- /* Prefetch the first 4 lines */
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -128(%1)\n"
- " pref " SB1_PREF_LOAD_STREAMED_HINT ", -96(%0)\n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -96(%1)\n"
- " pref " SB1_PREF_LOAD_STREAMED_HINT ", -64(%0)\n"
- " pref " SB1_PREF_STORE_STREAMED_HINT ", -64(%1)\n"
- " pref " SB1_PREF_LOAD_STREAMED_HINT ", -32(%0)\n"
- "1: pref " SB1_PREF_STORE_STREAMED_HINT ", -32(%1)\n"
-# ifdef CONFIG_64BIT
- " ld $8, -128(%0) \n" /* Block copy a cacheline */
- " ld $9, -120(%0) \n"
- " ld $10, -112(%0) \n"
- " ld $11, -104(%0) \n"
- " sd $8, -128(%1) \n"
- " sd $9, -120(%1) \n"
- " sd $10, -112(%1) \n"
- " sd $11, -104(%1) \n"
-# else
- " lw $2, -128(%0) \n" /* Block copy a cacheline */
- " lw $3, -124(%0) \n"
- " lw $6, -120(%0) \n"
- " lw $7, -116(%0) \n"
- " lw $8, -112(%0) \n"
- " lw $9, -108(%0) \n"
- " lw $10, -104(%0) \n"
- " lw $11, -100(%0) \n"
- " sw $2, -128(%1) \n"
- " sw $3, -124(%1) \n"
- " sw $6, -120(%1) \n"
- " sw $7, -116(%1) \n"
- " sw $8, -112(%1) \n"
- " sw $9, -108(%1) \n"
- " sw $10, -104(%1) \n"
- " sw $11, -100(%1) \n"
-# endif
- " daddiu %0, %0, 32 \n"
- " daddiu %1, %1, 32 \n"
- " bnel %0, %2, 1b \n"
- " pref " SB1_PREF_LOAD_STREAMED_HINT ", -32(%0)\n"
- " daddiu %0, %0, -128 \n"
- " daddiu %1, %1, -128 \n"
-#endif
-#ifdef CONFIG_64BIT
- " ld $8, 0(%0) \n" /* Block copy a cacheline */
- "1: ld $9, 8(%0) \n"
- " ld $10, 16(%0) \n"
- " ld $11, 24(%0) \n"
- " sd $8, 0(%1) \n"
- " sd $9, 8(%1) \n"
- " sd $10, 16(%1) \n"
- " sd $11, 24(%1) \n"
-#else
- " lw $2, 0(%0) \n" /* Block copy a cacheline */
- "1: lw $3, 4(%0) \n"
- " lw $6, 8(%0) \n"
- " lw $7, 12(%0) \n"
- " lw $8, 16(%0) \n"
- " lw $9, 20(%0) \n"
- " lw $10, 24(%0) \n"
- " lw $11, 28(%0) \n"
- " sw $2, 0(%1) \n"
- " sw $3, 4(%1) \n"
- " sw $6, 8(%1) \n"
- " sw $7, 12(%1) \n"
- " sw $8, 16(%1) \n"
- " sw $9, 20(%1) \n"
- " sw $10, 24(%1) \n"
- " sw $11, 28(%1) \n"
-#endif
- " daddiu %0, %0, 32 \n"
- " daddiu %1, %1, 32 \n"
- " bnel %0, %2, 1b \n"
-#ifdef CONFIG_64BIT
- " ld $8, 0(%0) \n"
-#else
- " lw $2, 0(%0) \n"
-#endif
- " .set pop \n"
- : "+r" (src), "+r" (dst)
- : "r" (end)
-#ifdef CONFIG_64BIT
- : "$8", "$9", "$10", "$11", "memory");
-#else
- : "$2", "$3", "$6", "$7", "$8", "$9", "$10", "$11", "memory");
-#endif
-}
-
-
-#ifdef CONFIG_SIBYTE_DMA_PAGEOPS
-
-/*
- * Pad descriptors to cacheline, since each is exclusively owned by a
- * particular CPU.
- */
-typedef struct dmadscr_s {
- u64 dscr_a;
- u64 dscr_b;
- u64 pad_a;
- u64 pad_b;
-} dmadscr_t;
-
-static dmadscr_t page_descr[DM_NUM_CHANNELS]
- __attribute__((aligned(SMP_CACHE_BYTES)));
-
-void sb1_dma_init(void)
-{
- int i;
-
- for (i = 0; i < DM_NUM_CHANNELS; i++) {
- const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
- V_DM_DSCR_BASE_RINGSZ(1);
- void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
- __raw_writeq(base_val, base_reg);
- __raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
- __raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
- }
-}
-
-void clear_page(void *page)
-{
- u64 to_phys = CPHYSADDR((unsigned long)page);
- unsigned int cpu = smp_processor_id();
-
- /* if the page is not in KSEG0, use old way */
- if ((long)KSEGX((unsigned long)page) != (long)CKSEG0)
- return clear_page_cpu(page);
-
- page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_ZERO_MEM |
- M_DM_DSCRA_L2C_DEST | M_DM_DSCRA_INTERRUPT;
- page_descr[cpu].dscr_b = V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
- __raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
-
- /*
- * Don't really want to do it this way, but there's no
- * reliable way to delay completion detection.
- */
- while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
- & M_DM_DSCR_BASE_INTERRUPT))
- ;
- __raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
-}
-
-void copy_page(void *to, void *from)
-{
- u64 from_phys = CPHYSADDR((unsigned long)from);
- u64 to_phys = CPHYSADDR((unsigned long)to);
- unsigned int cpu = smp_processor_id();
-
- /* if any page is not in KSEG0, use old way */
- if ((long)KSEGX((unsigned long)to) != (long)CKSEG0
- || (long)KSEGX((unsigned long)from) != (long)CKSEG0)
- return copy_page_cpu(to, from);
-
- page_descr[cpu].dscr_a = to_phys | M_DM_DSCRA_L2C_DEST |
- M_DM_DSCRA_INTERRUPT;
- page_descr[cpu].dscr_b = from_phys | V_DM_DSCRB_SRC_LENGTH(PAGE_SIZE);
- __raw_writeq(1, IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_COUNT)));
-
- /*
- * Don't really want to do it this way, but there's no
- * reliable way to delay completion detection.
- */
- while (!(__raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE_DEBUG)))
- & M_DM_DSCR_BASE_INTERRUPT))
- ;
- __raw_readq(IOADDR(A_DM_REGISTER(cpu, R_DM_DSCR_BASE)));
-}
-
-#else /* !CONFIG_SIBYTE_DMA_PAGEOPS */
-
-void clear_page(void *page)
-{
- return clear_page_cpu(page);
-}
-
-void copy_page(void *to, void *from)
-{
- return copy_page_cpu(to, from);
-}
-
-#endif /* !CONFIG_SIBYTE_DMA_PAGEOPS */
-
-EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(copy_page);
-
-void __cpuinit build_clear_page(void)
-{
-}
-
-void __cpuinit build_copy_page(void)
-{
-}
diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c
index 57df1c38e30..7dfa579ab24 100644
--- a/arch/mips/mm/pgtable.c
+++ b/arch/mips/mm/pgtable.c
@@ -12,7 +12,6 @@ void show_mem(void)
printk("Mem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
pfn = max_mapnr;
while (pfn-- > 0) {
if (!pfn_valid(pfn))
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 63065d6e806..5ce2fa74562 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -299,7 +299,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
idx = read_c0_index();
ptep = pte_offset_map(pmdp, address);
-#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32_R1)
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
write_c0_entrylo0(ptep->pte_high);
ptep++;
write_c0_entrylo1(ptep->pte_high);
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index 1a6f7704cc8..1655aa69e13 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -58,13 +58,13 @@ enum opcode {
insn_invalid,
insn_addu, insn_addiu, insn_and, insn_andi, insn_beq,
insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
- insn_bne, insn_daddu, insn_daddiu, insn_dmfc0, insn_dmtc0,
- insn_dsll, insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32,
- insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr, insn_ld,
- insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0, insn_mtc0,
- insn_ori, insn_rfe, insn_sc, insn_scd, insn_sd, insn_sll,
- insn_sra, insn_srl, insn_subu, insn_sw, insn_tlbp, insn_tlbwi,
- insn_tlbwr, insn_xor, insn_xori
+ insn_bne, insn_cache, insn_daddu, insn_daddiu, insn_dmfc0,
+ insn_dmtc0, insn_dsll, insn_dsll32, insn_dsra, insn_dsrl,
+ insn_dsrl32, insn_dsubu, insn_eret, insn_j, insn_jal, insn_jr,
+ insn_ld, insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0,
+ insn_mtc0, insn_ori, insn_pref, insn_rfe, insn_sc, insn_scd,
+ insn_sd, insn_sll, insn_sra, insn_srl, insn_subu, insn_sw,
+ insn_tlbp, insn_tlbwi, insn_tlbwr, insn_xor, insn_xori
};
struct insn {
@@ -94,6 +94,7 @@ static struct insn insn_table[] __cpuinitdata = {
{ insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM },
{ insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM },
{ insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
+ { insn_cache, M(cache_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
@@ -116,6 +117,7 @@ static struct insn insn_table[] __cpuinitdata = {
{ insn_mfc0, M(cop0_op, mfc_op, 0, 0, 0, 0), RT | RD | SET},
{ insn_mtc0, M(cop0_op, mtc_op, 0, 0, 0, 0), RT | RD | SET},
{ insn_ori, M(ori_op, 0, 0, 0, 0, 0), RS | RT | UIMM },
+ { insn_pref, M(pref_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
{ insn_rfe, M(cop0_op, cop_op, 0, 0, 0, rfe_op), 0 },
{ insn_sc, M(sc_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
{ insn_scd, M(scd_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
@@ -337,6 +339,7 @@ I_u1s2(_bgezl)
I_u1s2(_bltz)
I_u1s2(_bltzl)
I_u1u2s3(_bne)
+I_u2s3u1(_cache)
I_u1u2u3(_dmfc0)
I_u1u2u3(_dmtc0)
I_u2u1s3(_daddiu)
@@ -359,6 +362,7 @@ I_u2s3u1(_lw)
I_u1u2u3(_mfc0)
I_u1u2u3(_mtc0)
I_u2u1u3(_ori)
+I_u2s3u1(_pref)
I_0(_rfe)
I_u2s3u1(_sc)
I_u2s3u1(_scd)
@@ -555,6 +559,14 @@ uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid)
}
void __cpuinit
+uasm_il_bne(u32 **p, struct uasm_reloc **r, unsigned int reg1,
+ unsigned int reg2, int lid)
+{
+ uasm_r_mips_pc16(r, *p, lid);
+ uasm_i_bne(p, reg1, reg2, 0);
+}
+
+void __cpuinit
uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid)
{
uasm_r_mips_pc16(r, *p, lid);
diff --git a/arch/mips/mm/uasm.h b/arch/mips/mm/uasm.h
index fe0574f6e77..0d6a66f3203 100644
--- a/arch/mips/mm/uasm.h
+++ b/arch/mips/mm/uasm.h
@@ -55,6 +55,7 @@ Ip_u1s2(_bgezl);
Ip_u1s2(_bltz);
Ip_u1s2(_bltzl);
Ip_u1u2s3(_bne);
+Ip_u2s3u1(_cache);
Ip_u1u2u3(_dmfc0);
Ip_u1u2u3(_dmtc0);
Ip_u2u1s3(_daddiu);
@@ -77,6 +78,7 @@ Ip_u2s3u1(_lw);
Ip_u1u2u3(_mfc0);
Ip_u1u2u3(_mtc0);
Ip_u2u1u3(_ori);
+Ip_u2s3u1(_pref);
Ip_0(_rfe);
Ip_u2s3u1(_sc);
Ip_u2s3u1(_scd);
@@ -177,6 +179,8 @@ void uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
void uasm_il_b(u32 **p, struct uasm_reloc **r, int lid);
void uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
void uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
+void uasm_il_bne(u32 **p, struct uasm_reloc **r, unsigned int reg1,
+ unsigned int reg2, int lid);
void uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
void uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
diff --git a/arch/mips/philips/pnx8550/common/Makefile b/arch/mips/nxp/pnx8550/common/Makefile
index 31cc1a5cec3..31cc1a5cec3 100644
--- a/arch/mips/philips/pnx8550/common/Makefile
+++ b/arch/mips/nxp/pnx8550/common/Makefile
diff --git a/arch/mips/philips/pnx8550/common/gdb_hook.c b/arch/mips/nxp/pnx8550/common/gdb_hook.c
index ad4624f6d9b..ad4624f6d9b 100644
--- a/arch/mips/philips/pnx8550/common/gdb_hook.c
+++ b/arch/mips/nxp/pnx8550/common/gdb_hook.c
diff --git a/arch/mips/philips/pnx8550/common/int.c b/arch/mips/nxp/pnx8550/common/int.c
index aad03429a5e..aad03429a5e 100644
--- a/arch/mips/philips/pnx8550/common/int.c
+++ b/arch/mips/nxp/pnx8550/common/int.c
diff --git a/arch/mips/philips/pnx8550/common/pci.c b/arch/mips/nxp/pnx8550/common/pci.c
index eee4f3dfc41..eee4f3dfc41 100644
--- a/arch/mips/philips/pnx8550/common/pci.c
+++ b/arch/mips/nxp/pnx8550/common/pci.c
diff --git a/arch/mips/philips/pnx8550/common/platform.c b/arch/mips/nxp/pnx8550/common/platform.c
index c839436bd01..c7c763dbe58 100644
--- a/arch/mips/philips/pnx8550/common/platform.c
+++ b/arch/mips/nxp/pnx8550/common/platform.c
@@ -1,5 +1,5 @@
/*
- * Platform device support for Philips PNX8550 SoCs
+ * Platform device support for NXP PNX8550 SoCs
*
* Copyright 2005, Embedded Alley Solutions, Inc
*
diff --git a/arch/mips/philips/pnx8550/common/proc.c b/arch/mips/nxp/pnx8550/common/proc.c
index 18b125e3b65..18b125e3b65 100644
--- a/arch/mips/philips/pnx8550/common/proc.c
+++ b/arch/mips/nxp/pnx8550/common/proc.c
diff --git a/arch/mips/philips/pnx8550/common/prom.c b/arch/mips/nxp/pnx8550/common/prom.c
index 2f567452e7a..2f567452e7a 100644
--- a/arch/mips/philips/pnx8550/common/prom.c
+++ b/arch/mips/nxp/pnx8550/common/prom.c
diff --git a/arch/mips/philips/pnx8550/common/reset.c b/arch/mips/nxp/pnx8550/common/reset.c
index 7b2cbc5b2c7..7b2cbc5b2c7 100644
--- a/arch/mips/philips/pnx8550/common/reset.c
+++ b/arch/mips/nxp/pnx8550/common/reset.c
diff --git a/arch/mips/philips/pnx8550/common/setup.c b/arch/mips/nxp/pnx8550/common/setup.c
index 92d764c9770..92d764c9770 100644
--- a/arch/mips/philips/pnx8550/common/setup.c
+++ b/arch/mips/nxp/pnx8550/common/setup.c
diff --git a/arch/mips/philips/pnx8550/common/time.c b/arch/mips/nxp/pnx8550/common/time.c
index 62f495b57f9..62f495b57f9 100644
--- a/arch/mips/philips/pnx8550/common/time.c
+++ b/arch/mips/nxp/pnx8550/common/time.c
diff --git a/arch/mips/philips/pnx8550/jbs/Makefile b/arch/mips/nxp/pnx8550/jbs/Makefile
index e8228dbca8f..ad6a8ca7d8c 100644
--- a/arch/mips/philips/pnx8550/jbs/Makefile
+++ b/arch/mips/nxp/pnx8550/jbs/Makefile
@@ -1,4 +1,4 @@
-# Makefile for the Philips JBS Board.
+# Makefile for the NXP JBS Board.
lib-y := init.o board_setup.o irqmap.o
diff --git a/arch/mips/philips/pnx8550/jbs/board_setup.c b/arch/mips/nxp/pnx8550/jbs/board_setup.c
index f92826e0096..f92826e0096 100644
--- a/arch/mips/philips/pnx8550/jbs/board_setup.c
+++ b/arch/mips/nxp/pnx8550/jbs/board_setup.c
diff --git a/arch/mips/philips/pnx8550/jbs/init.c b/arch/mips/nxp/pnx8550/jbs/init.c
index 90b4d35f3ec..d59b4a4e5e8 100644
--- a/arch/mips/philips/pnx8550/jbs/init.c
+++ b/arch/mips/nxp/pnx8550/jbs/init.c
@@ -40,7 +40,7 @@ extern char *prom_getenv(char *envname);
const char *get_system_type(void)
{
- return "Philips PNX8550/JBS";
+ return "NXP PNX8550/JBS";
}
void __init prom_init(void)
diff --git a/arch/mips/philips/pnx8550/jbs/irqmap.c b/arch/mips/nxp/pnx8550/jbs/irqmap.c
index 98c3429e6e5..7fc89842002 100644
--- a/arch/mips/philips/pnx8550/jbs/irqmap.c
+++ b/arch/mips/nxp/pnx8550/jbs/irqmap.c
@@ -1,5 +1,5 @@
/*
- * Philips JBS board irqmap.
+ * NXP JBS board irqmap.
*
* Copyright 2005 Embedded Alley Solutions, Inc
* source@embeddealley.com
@@ -33,4 +33,3 @@ char pnx8550_irq_tab[][5] __initdata = {
[9] = { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
[17] = { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
};
-
diff --git a/arch/mips/philips/pnx8550/stb810/Makefile b/arch/mips/nxp/pnx8550/stb810/Makefile
index f14b592af39..ab91d72c566 100644
--- a/arch/mips/philips/pnx8550/stb810/Makefile
+++ b/arch/mips/nxp/pnx8550/stb810/Makefile
@@ -1,4 +1,4 @@
-# Makefile for the Philips STB810 Board.
+# Makefile for the NXP STB810 Board.
lib-y := prom_init.o board_setup.o irqmap.o
diff --git a/arch/mips/philips/pnx8550/stb810/board_setup.c b/arch/mips/nxp/pnx8550/stb810/board_setup.c
index 345d71e53cf..1282c27cfcb 100644
--- a/arch/mips/philips/pnx8550/stb810/board_setup.c
+++ b/arch/mips/nxp/pnx8550/stb810/board_setup.c
@@ -1,7 +1,7 @@
/*
* STB810 specific board startup routines.
*
- * Based on the arch/mips/philips/pnx8550/jbs/board_setup.c
+ * Based on the arch/mips/nxp/pnx8550/jbs/board_setup.c
*
* Author: MontaVista Software, Inc.
* source@mvista.com
diff --git a/arch/mips/philips/pnx8550/stb810/irqmap.c b/arch/mips/nxp/pnx8550/stb810/irqmap.c
index 5ee11e19975..8c034963ddc 100644
--- a/arch/mips/philips/pnx8550/stb810/irqmap.c
+++ b/arch/mips/nxp/pnx8550/stb810/irqmap.c
@@ -1,5 +1,5 @@
/*
- * Philips STB810 board irqmap.
+ * NXP STB810 board irqmap.
*
* Author: MontaVista Software, Inc.
* source@mvista.com
@@ -20,4 +20,3 @@ char pnx8550_irq_tab[][5] __initdata = {
[9] = { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
[10] = { -1, PNX8550_INT_PCI_INTA, 0xff, 0xff, 0xff},
};
-
diff --git a/arch/mips/philips/pnx8550/stb810/prom_init.c b/arch/mips/nxp/pnx8550/stb810/prom_init.c
index 832dd60b0a7..ca7f4ada064 100644
--- a/arch/mips/philips/pnx8550/stb810/prom_init.c
+++ b/arch/mips/nxp/pnx8550/stb810/prom_init.c
@@ -28,7 +28,7 @@ extern char *prom_getenv(char *envname);
const char *get_system_type(void)
{
- return "Philips PNX8550/STB810";
+ return "NXP PNX8950/STB810";
}
void __init prom_init(void)
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index aa52aa146ce..b5f6f71b27b 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -80,6 +80,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
case CPU_24K:
case CPU_25KF:
case CPU_34K:
+ case CPU_1004K:
case CPU_74K:
case CPU_SB1:
case CPU_SB1A:
diff --git a/arch/mips/oprofile/op_impl.h b/arch/mips/oprofile/op_impl.h
index fa6b4aae752..2bfc17c3010 100644
--- a/arch/mips/oprofile/op_impl.h
+++ b/arch/mips/oprofile/op_impl.h
@@ -10,7 +10,6 @@
#ifndef OP_IMPL_H
#define OP_IMPL_H 1
-extern int null_perf_irq(void);
extern int (*perf_irq)(void);
/* Per-counter configuration as set via oprofilefs. */
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index ccbea229a0e..da8cbb6899d 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -31,9 +31,14 @@
#define M_COUNTER_OVERFLOW (1UL << 31)
+static int (*save_perf_irq)(void);
+
#ifdef CONFIG_MIPS_MT_SMP
-#define WHAT (M_TC_EN_VPE | M_PERFCTL_VPEID(smp_processor_id()))
-#define vpe_id() smp_processor_id()
+static int cpu_has_mipsmt_pertccounters;
+#define WHAT (M_TC_EN_VPE | \
+ M_PERFCTL_VPEID(cpu_data[smp_processor_id()].vpe_id))
+#define vpe_id() (cpu_has_mipsmt_pertccounters ? \
+ 0 : cpu_data[smp_processor_id()].vpe_id)
/*
* The number of bits to shift to convert between counters per core and
@@ -243,11 +248,11 @@ static inline int __n_counters(void)
{
if (!(read_c0_config1() & M_CONFIG1_PC))
return 0;
- if (!(r_c0_perfctrl0() & M_PERFCTL_MORE))
+ if (!(read_c0_perfctrl0() & M_PERFCTL_MORE))
return 1;
- if (!(r_c0_perfctrl1() & M_PERFCTL_MORE))
+ if (!(read_c0_perfctrl1() & M_PERFCTL_MORE))
return 2;
- if (!(r_c0_perfctrl2() & M_PERFCTL_MORE))
+ if (!(read_c0_perfctrl2() & M_PERFCTL_MORE))
return 3;
return 4;
@@ -274,8 +279,9 @@ static inline int n_counters(void)
return counters;
}
-static inline void reset_counters(int counters)
+static void reset_counters(void *arg)
{
+ int counters = (int)arg;
switch (counters) {
case 4:
w_c0_perfctrl3(0);
@@ -302,9 +308,12 @@ static int __init mipsxx_init(void)
return -ENODEV;
}
- reset_counters(counters);
-
- counters = counters_total_to_per_cpu(counters);
+#ifdef CONFIG_MIPS_MT_SMP
+ cpu_has_mipsmt_pertccounters = read_c0_config7() & (1<<19);
+ if (!cpu_has_mipsmt_pertccounters)
+ counters = counters_total_to_per_cpu(counters);
+#endif
+ on_each_cpu(reset_counters, (void *)counters, 0, 1);
op_model_mipsxx_ops.num_counters = counters;
switch (current_cpu_type()) {
@@ -320,6 +329,13 @@ static int __init mipsxx_init(void)
op_model_mipsxx_ops.cpu_type = "mips/25K";
break;
+ case CPU_1004K:
+#if 0
+ /* FIXME: report as 34K for now */
+ op_model_mipsxx_ops.cpu_type = "mips/1004K";
+ break;
+#endif
+
case CPU_34K:
op_model_mipsxx_ops.cpu_type = "mips/34K";
break;
@@ -355,6 +371,7 @@ static int __init mipsxx_init(void)
return -ENODEV;
}
+ save_perf_irq = perf_irq;
perf_irq = mipsxx_perfcount_handler;
return 0;
@@ -365,9 +382,9 @@ static void mipsxx_exit(void)
int counters = op_model_mipsxx_ops.num_counters;
counters = counters_per_cpu_to_total(counters);
- reset_counters(counters);
+ on_each_cpu(reset_counters, (void *)counters, 0, 1);
- perf_irq = null_perf_irq;
+ perf_irq = save_perf_irq;
}
struct op_mips_model op_model_mipsxx_ops = {
diff --git a/arch/mips/pci/fixup-au1000.c b/arch/mips/pci/fixup-au1000.c
index ca0276c8070..00c36c9dbe0 100644
--- a/arch/mips/pci/fixup-au1000.c
+++ b/arch/mips/pci/fixup-au1000.c
@@ -26,13 +26,10 @@
* with this program; if not, write to the Free Software Foundation, Inc.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/types.h>
+
#include <linux/pci.h>
-#include <linux/kernel.h>
#include <linux/init.h>
-#include <asm/mach-au1x00/au1000.h>
-
extern char irq_tab_alchemy[][5];
int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
diff --git a/arch/mips/pci/ops-pnx8550.c b/arch/mips/pci/ops-pnx8550.c
index d6106465249..0e160d9f07c 100644
--- a/arch/mips/pci/ops-pnx8550.c
+++ b/arch/mips/pci/ops-pnx8550.c
@@ -90,14 +90,14 @@ config_access(unsigned int pci_cmd, struct pci_bus *bus, unsigned int devfn, int
loops--;
if (loops == 0) {
- printk("%s : Arbiter Locked.\n", __FUNCTION__);
+ printk("%s : Arbiter Locked.\n", __func__);
}
}
clear_status();
if ((pci_cmd == PCI_CMD_IOR) || (pci_cmd == PCI_CMD_IOW)) {
printk("%s timeout (GPPM_CTRL=%X) ioaddr %lX pci_cmd %X\n",
- __FUNCTION__, inl(PCI_BASE | PCI_GPPM_CTRL), ioaddr,
+ __func__, inl(PCI_BASE | PCI_GPPM_CTRL), ioaddr,
pci_cmd);
}
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 624bbdbff2a..b6cab089561 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -142,7 +142,7 @@ static irqreturn_t ip32_rtc_int(int irq, void *dev_id)
reg_c = CMOS_READ(RTC_INTR_FLAGS);
if (!(reg_c & RTC_IRQF)) {
printk(KERN_WARNING
- "%s: RTC IRQ without RTC_IRQF\n", __FUNCTION__);
+ "%s: RTC IRQ without RTC_IRQF\n", __func__);
}
/* Wait until interrupt goes away */
disable_irq(MACEISA_RTC_IRQ);
diff --git a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
index 3f808b62924..6d31f2a98ab 100644
--- a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
+++ b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_irq.c
@@ -173,7 +173,7 @@ static const u32 toshiba_rbtx4927_irq_debug_flag =
{ \
char tmp[100]; \
sprintf( tmp, str ); \
- printk( "%s(%s:%u)::%s", __FUNCTION__, __FILE__, __LINE__, tmp ); \
+ printk( "%s(%s:%u)::%s", __func__, __FILE__, __LINE__, tmp ); \
}
#else
#define TOSHIBA_RBTX4927_IRQ_DPRINTK(flag, str...)
diff --git a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
index e466e5e711d..2203c77b2ce 100644
--- a/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
+++ b/arch/mips/tx4927/toshiba_rbtx4927/toshiba_rbtx4927_setup.c
@@ -93,7 +93,7 @@ static const u32 toshiba_rbtx4927_setup_debug_flag =
{ \
char tmp[100]; \
sprintf( tmp, str ); \
- printk( "%s(%s:%u)::%s", __FUNCTION__, __FILE__, __LINE__, tmp ); \
+ printk( "%s(%s:%u)::%s", __func__, __FILE__, __LINE__, tmp ); \
}
#else
#define TOSHIBA_RBTX4927_SETUP_DPRINTK(flag, str...)
diff --git a/arch/mips/tx4938/common/dbgio.c b/arch/mips/tx4938/common/dbgio.c
index bea59ff1842..33b9c672a32 100644
--- a/arch/mips/tx4938/common/dbgio.c
+++ b/arch/mips/tx4938/common/dbgio.c
@@ -31,9 +31,7 @@
* Support for TX4938 in 2.6 - Hiroshi DOYU <Hiroshi_DOYU@montavista.co.jp>
*/
-#include <asm/mipsregs.h>
-#include <asm/system.h>
-#include <asm/tx4938/tx4938_mips.h>
+#include <linux/types>
extern u8 txx9_sio_kdbg_rd(void);
extern int txx9_sio_kdbg_wr( u8 ch );
diff --git a/arch/mips/tx4938/common/prom.c b/arch/mips/tx4938/common/prom.c
index 3189a65f7d7..20baeaeba4c 100644
--- a/arch/mips/tx4938/common/prom.c
+++ b/arch/mips/tx4938/common/prom.c
@@ -13,13 +13,8 @@
*/
#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-
-#include <asm/addrspace.h>
-#include <asm/bootinfo.h>
-#include <asm/tx4938/tx4938.h>
+#include <linux/types.h>
+#include <linux/io.h>
static unsigned int __init
tx4938_process_sdccr(u64 * addr)
@@ -35,7 +30,7 @@ tx4938_process_sdccr(u64 * addr)
unsigned int bc = 4;
unsigned int msize = 0;
- val = (*((vu64 *) (addr)));
+ val = ____raw_readq((void __iomem *)addr);
/* MVMCP -- need #defs for these bits masks */
sdccr_ce = ((val & (1 << 10)) >> 10);
diff --git a/arch/mips/tx4938/toshiba_rbtx4938/irq.c b/arch/mips/tx4938/toshiba_rbtx4938/irq.c
index f00185017e8..4d6a8dc46c7 100644
--- a/arch/mips/tx4938/toshiba_rbtx4938/irq.c
+++ b/arch/mips/tx4938/toshiba_rbtx4938/irq.c
@@ -67,24 +67,7 @@ IRQ Device
63 RBTX4938-IOC/07 SWINT
*/
#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/ioport.h>
-#include <linux/sched.h>
#include <linux/interrupt.h>
-#include <linux/pci.h>
-#include <linux/timex.h>
-#include <asm/bootinfo.h>
-#include <asm/page.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/processor.h>
-#include <asm/reboot.h>
-#include <asm/time.h>
-#include <asm/wbflush.h>
-#include <linux/bootmem.h>
#include <asm/tx4938/rbtx4938.h>
static void toshiba_rbtx4938_irq_ioc_enable(unsigned int irq);
@@ -99,21 +82,16 @@ static struct irq_chip toshiba_rbtx4938_irq_ioc_type = {
.unmask = toshiba_rbtx4938_irq_ioc_enable,
};
-#define TOSHIBA_RBTX4938_IOC_INTR_ENAB 0xb7f02000
-#define TOSHIBA_RBTX4938_IOC_INTR_STAT 0xb7f0200a
-
int
toshiba_rbtx4938_irq_nested(int sw_irq)
{
u8 level3;
- level3 = reg_rd08(TOSHIBA_RBTX4938_IOC_INTR_STAT) & 0xff;
- if (level3) {
+ level3 = readb(rbtx4938_imstat_addr);
+ if (level3)
/* must use fls so onboard ATA has priority */
sw_irq = TOSHIBA_RBTX4938_IRQ_IOC_BEG + fls(level3) - 1;
- }
- wbflush();
return sw_irq;
}
@@ -144,25 +122,23 @@ toshiba_rbtx4938_irq_ioc_init(void)
static void
toshiba_rbtx4938_irq_ioc_enable(unsigned int irq)
{
- volatile unsigned char v;
+ unsigned char v;
- v = TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
+ v = readb(rbtx4938_imask_addr);
v |= (1 << (irq - TOSHIBA_RBTX4938_IRQ_IOC_BEG));
- TX4938_WR08(TOSHIBA_RBTX4938_IOC_INTR_ENAB, v);
+ writeb(v, rbtx4938_imask_addr);
mmiowb();
- TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
}
static void
toshiba_rbtx4938_irq_ioc_disable(unsigned int irq)
{
- volatile unsigned char v;
+ unsigned char v;
- v = TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
+ v = readb(rbtx4938_imask_addr);
v &= ~(1 << (irq - TOSHIBA_RBTX4938_IRQ_IOC_BEG));
- TX4938_WR08(TOSHIBA_RBTX4938_IOC_INTR_ENAB, v);
+ writeb(v, rbtx4938_imask_addr);
mmiowb();
- TX4938_RD08(TOSHIBA_RBTX4938_IOC_INTR_ENAB);
}
void __init arch_init_irq(void)
@@ -174,14 +150,12 @@ void __init arch_init_irq(void)
/* all IRC interrupt mode are Low Active. */
/* mask all IOC interrupts */
- *rbtx4938_imask_ptr = 0;
+ writeb(0, rbtx4938_imask_addr);
/* clear SoftInt interrupts */
- *rbtx4938_softint_ptr = 0;
+ writeb(0, rbtx4938_softint_addr);
tx4938_irq_init();
toshiba_rbtx4938_irq_ioc_init();
/* Onboard 10M Ether: High Active */
set_irq_type(RBTX4938_IRQ_ETHER, IRQF_TRIGGER_HIGH);
-
- wbflush();
}
diff --git a/arch/mips/tx4938/toshiba_rbtx4938/setup.c b/arch/mips/tx4938/toshiba_rbtx4938/setup.c
index 61249f049cd..3a3659e8633 100644
--- a/arch/mips/tx4938/toshiba_rbtx4938/setup.c
+++ b/arch/mips/tx4938/toshiba_rbtx4938/setup.c
@@ -21,8 +21,8 @@
#include <linux/pm.h>
#include <linux/platform_device.h>
#include <linux/clk.h>
+#include <linux/gpio.h>
-#include <asm/wbflush.h>
#include <asm/reboot.h>
#include <asm/time.h>
#include <asm/txx9tmr.h>
@@ -34,7 +34,7 @@
#endif
#include <linux/spi/spi.h>
#include <asm/tx4938/spi.h>
-#include <asm/gpio.h>
+#include <asm/txx9pio.h>
extern char * __init prom_getcmdline(void);
static inline void tx4938_report_pcic_status1(struct tx4938_pcic_reg *pcicptr);
@@ -90,12 +90,11 @@ void rbtx4938_machine_restart(char *command)
local_irq_disable();
printk("Rebooting...");
- *rbtx4938_softresetlock_ptr = 1;
- *rbtx4938_sfvol_ptr = 1;
- *rbtx4938_softreset_ptr = 1;
- wbflush();
-
- while(1);
+ writeb(1, rbtx4938_softresetlock_addr);
+ writeb(1, rbtx4938_sfvol_addr);
+ writeb(1, rbtx4938_softreset_addr);
+ while(1)
+ ;
}
void __init
@@ -487,7 +486,7 @@ static int __init tx4938_pcibios_init(void)
}
/* Reset PCI Bus */
- *rbtx4938_pcireset_ptr = 0;
+ writeb(0, rbtx4938_pcireset_addr);
/* Reset PCIC */
tx4938_ccfgptr->clkctr |= TX4938_CLKCTR_PCIRST;
if (txboard_pci66_mode > 0)
@@ -495,8 +494,8 @@ static int __init tx4938_pcibios_init(void)
mdelay(10);
/* clear PCIC reset */
tx4938_ccfgptr->clkctr &= ~TX4938_CLKCTR_PCIRST;
- *rbtx4938_pcireset_ptr = 1;
- wbflush();
+ writeb(1, rbtx4938_pcireset_addr);
+ mmiowb();
tx4938_report_pcic_status1(tx4938_pcicptr);
tx4938_report_pciclk();
@@ -504,15 +503,15 @@ static int __init tx4938_pcibios_init(void)
if (txboard_pci66_mode == 0 &&
txboard_pci66_check(&tx4938_pci_controller[0], 0, 0)) {
/* Reset PCI Bus */
- *rbtx4938_pcireset_ptr = 0;
+ writeb(0, rbtx4938_pcireset_addr);
/* Reset PCIC */
tx4938_ccfgptr->clkctr |= TX4938_CLKCTR_PCIRST;
tx4938_pciclk66_setup();
mdelay(10);
/* clear PCIC reset */
tx4938_ccfgptr->clkctr &= ~TX4938_CLKCTR_PCIRST;
- *rbtx4938_pcireset_ptr = 1;
- wbflush();
+ writeb(1, rbtx4938_pcireset_addr);
+ mmiowb();
/* Reinitialize PCIC */
tx4938_report_pciclk();
tx4938_pcic_setup(tx4938_pcicptr, &tx4938_pci_controller[0], io_base[0], extarb);
@@ -615,9 +614,6 @@ static void __init rbtx4938_spi_setup(void)
{
/* set SPI_SEL */
tx4938_ccfgptr->pcfg |= TX4938_PCFG_SPI_SEL;
- /* chip selects for SPI devices */
- tx4938_pioptr->dout |= (1 << SEEPROM1_CS);
- tx4938_pioptr->dir |= (1 << SEEPROM1_CS);
}
static struct resource rbtx4938_fpga_resource;
@@ -776,12 +772,13 @@ void __init tx4938_board_setup(void)
txx9_tmr_init(TX4938_TMR_REG(i) & 0xfffffffffULL);
/* enable DMA */
- TX4938_WR64(0xff1fb150, TX4938_DMA_MCR_MSTEN);
- TX4938_WR64(0xff1fb950, TX4938_DMA_MCR_MSTEN);
+ for (i = 0; i < 2; i++)
+ ____raw_writeq(TX4938_DMA_MCR_MSTEN,
+ (void __iomem *)(TX4938_DMA_REG(i) + 0x50));
/* PIO */
- tx4938_pioptr->maskcpu = 0;
- tx4938_pioptr->maskext = 0;
+ __raw_writel(0, &tx4938_pioptr->maskcpu);
+ __raw_writel(0, &tx4938_pioptr->maskext);
/* TX4938 internal registers */
if (request_resource(&iomem_resource, &tx4938_reg_resource))
@@ -863,10 +860,6 @@ void __init plat_mem_setup(void)
if (txx9_master_clock == 0)
txx9_master_clock = 25000000; /* 25MHz */
tx4938_board_setup();
- /* setup serial stuff */
- TX4938_WR(0xff1ff314, 0x00000000); /* h/w flow control off */
- TX4938_WR(0xff1ff414, 0x00000000); /* h/w flow control off */
-
#ifndef CONFIG_PCI
set_io_port_base(RBTX4938_ETHER_BASE);
#endif
@@ -932,16 +925,16 @@ void __init plat_mem_setup(void)
pcfg = tx4938_ccfgptr->pcfg; /* updated */
/* fixup piosel */
if ((pcfg & (TX4938_PCFG_ATA_SEL | TX4938_PCFG_NDF_SEL)) ==
- TX4938_PCFG_ATA_SEL) {
- *rbtx4938_piosel_ptr = (*rbtx4938_piosel_ptr & 0x03) | 0x04;
- }
+ TX4938_PCFG_ATA_SEL)
+ writeb((readb(rbtx4938_piosel_addr) & 0x03) | 0x04,
+ rbtx4938_piosel_addr);
else if ((pcfg & (TX4938_PCFG_ATA_SEL | TX4938_PCFG_NDF_SEL)) ==
- TX4938_PCFG_NDF_SEL) {
- *rbtx4938_piosel_ptr = (*rbtx4938_piosel_ptr & 0x03) | 0x08;
- }
- else {
- *rbtx4938_piosel_ptr &= ~(0x08 | 0x04);
- }
+ TX4938_PCFG_NDF_SEL)
+ writeb((readb(rbtx4938_piosel_addr) & 0x03) | 0x08,
+ rbtx4938_piosel_addr);
+ else
+ writeb(readb(rbtx4938_piosel_addr) & ~(0x08 | 0x04),
+ rbtx4938_piosel_addr);
rbtx4938_fpga_resource.name = "FPGA Registers";
rbtx4938_fpga_resource.start = CPHYSADDR(RBTX4938_FPGA_REG_ADDR);
@@ -950,17 +943,14 @@ void __init plat_mem_setup(void)
if (request_resource(&iomem_resource, &rbtx4938_fpga_resource))
printk("request resource for fpga failed\n");
- /* disable all OnBoard I/O interrupts */
- *rbtx4938_imask_ptr = 0;
-
_machine_restart = rbtx4938_machine_restart;
_machine_halt = rbtx4938_machine_halt;
pm_power_off = rbtx4938_machine_power_off;
- *rbtx4938_led_ptr = 0xff;
- printk("RBTX4938 --- FPGA(Rev %02x)", *rbtx4938_fpga_rev_ptr);
- printk(" DIPSW:%02x,%02x\n",
- *rbtx4938_dipsw_ptr, *rbtx4938_bdipsw_ptr);
+ writeb(0xff, rbtx4938_led_addr);
+ printk(KERN_INFO "RBTX4938 --- FPGA(Rev %02x) DIPSW:%02x,%02x\n",
+ readb(rbtx4938_fpga_rev_addr),
+ readb(rbtx4938_dipsw_addr), readb(rbtx4938_bdipsw_addr));
}
static int __init rbtx4938_ne_init(void)
@@ -984,106 +974,48 @@ device_initcall(rbtx4938_ne_init);
/* GPIO support */
-static DEFINE_SPINLOCK(rbtx4938_spi_gpio_lock);
-
-static void rbtx4938_spi_gpio_set(unsigned gpio, int value)
+int gpio_to_irq(unsigned gpio)
{
- u8 val;
- unsigned long flags;
- gpio -= 16;
- spin_lock_irqsave(&rbtx4938_spi_gpio_lock, flags);
- val = *rbtx4938_spics_ptr;
- if (value)
- val |= 1 << gpio;
- else
- val &= ~(1 << gpio);
- *rbtx4938_spics_ptr = val;
- mmiowb();
- spin_unlock_irqrestore(&rbtx4938_spi_gpio_lock, flags);
+ return -EINVAL;
}
-static int rbtx4938_spi_gpio_dir_out(unsigned gpio, int value)
+int irq_to_gpio(unsigned irq)
{
- rbtx4938_spi_gpio_set(gpio, value);
- return 0;
+ return -EINVAL;
}
-static DEFINE_SPINLOCK(tx4938_gpio_lock);
-
-static int tx4938_gpio_get(unsigned gpio)
-{
- return tx4938_pioptr->din & (1 << gpio);
-}
+static DEFINE_SPINLOCK(rbtx4938_spi_gpio_lock);
-static void tx4938_gpio_set_raw(unsigned gpio, int value)
+static void rbtx4938_spi_gpio_set(struct gpio_chip *chip, unsigned int offset,
+ int value)
{
- u32 val;
- val = tx4938_pioptr->dout;
+ u8 val;
+ unsigned long flags;
+ spin_lock_irqsave(&rbtx4938_spi_gpio_lock, flags);
+ val = readb(rbtx4938_spics_addr);
if (value)
- val |= 1 << gpio;
+ val |= 1 << offset;
else
- val &= ~(1 << gpio);
- tx4938_pioptr->dout = val;
-}
-
-static void tx4938_gpio_set(unsigned gpio, int value)
-{
- unsigned long flags;
- spin_lock_irqsave(&tx4938_gpio_lock, flags);
- tx4938_gpio_set_raw(gpio, value);
- mmiowb();
- spin_unlock_irqrestore(&tx4938_gpio_lock, flags);
-}
-
-static int tx4938_gpio_dir_in(unsigned gpio)
-{
- spin_lock_irq(&tx4938_gpio_lock);
- tx4938_pioptr->dir &= ~(1 << gpio);
+ val &= ~(1 << offset);
+ writeb(val, rbtx4938_spics_addr);
mmiowb();
- spin_unlock_irq(&tx4938_gpio_lock);
- return 0;
-}
-
-static int tx4938_gpio_dir_out(unsigned int gpio, int value)
-{
- spin_lock_irq(&tx4938_gpio_lock);
- tx4938_gpio_set_raw(gpio, value);
- tx4938_pioptr->dir |= 1 << gpio;
- mmiowb();
- spin_unlock_irq(&tx4938_gpio_lock);
- return 0;
-}
-
-int gpio_direction_input(unsigned gpio)
-{
- if (gpio < 16)
- return tx4938_gpio_dir_in(gpio);
- return -EINVAL;
-}
-
-int gpio_direction_output(unsigned gpio, int value)
-{
- if (gpio < 16)
- return tx4938_gpio_dir_out(gpio, value);
- if (gpio < 16 + 3)
- return rbtx4938_spi_gpio_dir_out(gpio, value);
- return -EINVAL;
+ spin_unlock_irqrestore(&rbtx4938_spi_gpio_lock, flags);
}
-int gpio_get_value(unsigned gpio)
+static int rbtx4938_spi_gpio_dir_out(struct gpio_chip *chip,
+ unsigned int offset, int value)
{
- if (gpio < 16)
- return tx4938_gpio_get(gpio);
+ rbtx4938_spi_gpio_set(chip, offset, value);
return 0;
}
-void gpio_set_value(unsigned gpio, int value)
-{
- if (gpio < 16)
- tx4938_gpio_set(gpio, value);
- else
- rbtx4938_spi_gpio_set(gpio, value);
-}
+static struct gpio_chip rbtx4938_spi_gpio_chip = {
+ .set = rbtx4938_spi_gpio_set,
+ .direction_output = rbtx4938_spi_gpio_dir_out,
+ .label = "RBTX4938-SPICS",
+ .base = 16,
+ .ngpio = 3,
+};
/* SPI support */
@@ -1094,7 +1026,6 @@ static void __init txx9_spi_init(unsigned long base, int irq)
.start = base,
.end = base + 0x20 - 1,
.flags = IORESOURCE_MEM,
- .parent = &tx4938_reg_resource,
}, {
.start = irq,
.flags = IORESOURCE_IRQ,
@@ -1118,10 +1049,25 @@ static int __init rbtx4938_spi_init(void)
spi_eeprom_register(SEEPROM1_CS);
spi_eeprom_register(16 + SEEPROM2_CS);
spi_eeprom_register(16 + SEEPROM3_CS);
+ gpio_request(16 + SRTC_CS, "rtc-rs5c348");
+ gpio_direction_output(16 + SRTC_CS, 0);
+ gpio_request(SEEPROM1_CS, "seeprom1");
+ gpio_direction_output(SEEPROM1_CS, 1);
+ gpio_request(16 + SEEPROM2_CS, "seeprom2");
+ gpio_direction_output(16 + SEEPROM2_CS, 1);
+ gpio_request(16 + SEEPROM3_CS, "seeprom3");
+ gpio_direction_output(16 + SEEPROM3_CS, 1);
txx9_spi_init(TX4938_SPI_REG & 0xfffffffffULL, RBTX4938_IRQ_IRC_SPI);
return 0;
}
-arch_initcall(rbtx4938_spi_init);
+
+static int __init rbtx4938_arch_init(void)
+{
+ txx9_gpio_init(TX4938_PIO_REG & 0xfffffffffULL, 0, 16);
+ gpiochip_add(&rbtx4938_spi_gpio_chip);
+ return rbtx4938_spi_init();
+}
+arch_initcall(rbtx4938_arch_init);
/* Watchdog support */
@@ -1131,7 +1077,6 @@ static int __init txx9_wdt_init(unsigned long base)
.start = base,
.end = base + 0x100 - 1,
.flags = IORESOURCE_MEM,
- .parent = &tx4938_reg_resource,
};
struct platform_device *dev =
platform_device_register_simple("txx9wdt", -1, &res, 1);
diff --git a/arch/mips/vr41xx/common/init.c b/arch/mips/vr41xx/common/init.c
index 76d4b5ed3fc..c64995342ba 100644
--- a/arch/mips/vr41xx/common/init.c
+++ b/arch/mips/vr41xx/common/init.c
@@ -1,7 +1,7 @@
/*
* init.c, Common initialization routines for NEC VR4100 series.
*
- * Copyright (C) 2003-2005 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ * Copyright (C) 2003-2008 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
*
* 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
@@ -53,6 +53,8 @@ void __init plat_time_init(void)
void __init plat_mem_setup(void)
{
iomem_resource_init();
+
+ vr41xx_siu_setup();
}
void __init prom_init(void)
diff --git a/arch/mips/vr41xx/common/siu.c b/arch/mips/vr41xx/common/siu.c
index b735f45b25f..654dee6208b 100644
--- a/arch/mips/vr41xx/common/siu.c
+++ b/arch/mips/vr41xx/common/siu.c
@@ -1,7 +1,7 @@
/*
* NEC VR4100 series SIU platform device.
*
- * Copyright (C) 2007 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
+ * Copyright (C) 2007-2008 Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
*
* 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
@@ -118,3 +118,37 @@ err_free_device:
return retval;
}
device_initcall(vr41xx_siu_add);
+
+void __init vr41xx_siu_setup(void)
+{
+ struct uart_port port;
+ struct resource *res;
+ unsigned int *type;
+ int i;
+
+ switch (current_cpu_type()) {
+ case CPU_VR4111:
+ case CPU_VR4121:
+ type = siu_type1_ports;
+ res = siu_type1_resource;
+ break;
+ case CPU_VR4122:
+ case CPU_VR4131:
+ case CPU_VR4133:
+ type = siu_type2_ports;
+ res = siu_type2_resource;
+ break;
+ default:
+ return;
+ }
+
+ for (i = 0; i < SIU_PORTS_MAX; i++) {
+ port.line = i;
+ port.type = type[i];
+ if (port.type == PORT_UNKNOWN)
+ break;
+ port.mapbase = res[i].start;
+ port.membase = (unsigned char __iomem *)KSEG1ADDR(res[i].start);
+ vr41xx_siu_early_setup(&port);
+ }
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index eb80f5e33d7..1f012843150 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -603,15 +603,18 @@ void show_mem(void)
#ifdef CONFIG_DISCONTIGMEM
{
struct zonelist *zl;
- int i, j, k;
+ int i, j;
for (i = 0; i < npmem_ranges; i++) {
+ zl = node_zonelist(i);
for (j = 0; j < MAX_NR_ZONES; j++) {
- zl = NODE_DATA(i)->node_zonelists + j;
+ struct zoneref *z;
+ struct zone *zone;
printk("Zone list for zone %d on node %d: ", j, i);
- for (k = 0; zl->zones[k] != NULL; k++)
- printk("[%d/%s] ", zone_to_nid(zl->zones[k]), zl->zones[k]->name);
+ for_each_zone_zonelist(zone, z, zl, j)
+ printk("[%d/%s] ", zone_to_nid(zone),
+ zone->name);
printk("\n");
}
}
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4bb2e9310a5..4e40c122bf2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -626,20 +626,6 @@ config ADVANCED_OPTIONS
comment "Default settings for advanced configuration options are used"
depends on !ADVANCED_OPTIONS
-config HIGHMEM_START_BOOL
- bool "Set high memory pool address"
- depends on ADVANCED_OPTIONS && HIGHMEM
- help
- This option allows you to set the base address of the kernel virtual
- area used to map high memory pages. This can be useful in
- optimizing the layout of kernel virtual memory.
-
- Say N here unless you know what you are doing.
-
-config HIGHMEM_START
- hex "Virtual start address of high memory pool" if HIGHMEM_START_BOOL
- default "0xfe000000"
-
config LOWMEM_SIZE_BOOL
bool "Set maximum low memory"
depends on ADVANCED_OPTIONS
@@ -656,21 +642,76 @@ config LOWMEM_SIZE
hex "Maximum low memory size (in bytes)" if LOWMEM_SIZE_BOOL
default "0x30000000"
+config RELOCATABLE
+ bool "Build a relocatable kernel (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && ADVANCED_OPTIONS && FLATMEM && FSL_BOOKE
+ help
+ This builds a kernel image that is capable of running at the
+ location the kernel is loaded at (some alignment restrictions may
+ exist).
+
+ One use is for the kexec on panic case where the recovery kernel
+ must live at a different physical address than the primary
+ kernel.
+
+ Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
+ it has been loaded at and the compile time physical addresses
+ CONFIG_PHYSICAL_START is ignored. However CONFIG_PHYSICAL_START
+ setting can still be useful to bootwrappers that need to know the
+ load location of the kernel (eg. u-boot/mkimage).
+
+config PAGE_OFFSET_BOOL
+ bool "Set custom page offset address"
+ depends on ADVANCED_OPTIONS
+ help
+ This option allows you to set the kernel virtual address at which
+ the kernel will map low memory. This can be useful in optimizing
+ the virtual memory layout of the system.
+
+ Say N here unless you know what you are doing.
+
+config PAGE_OFFSET
+ hex "Virtual address of memory base" if PAGE_OFFSET_BOOL
+ default "0xc0000000"
+
config KERNEL_START_BOOL
bool "Set custom kernel base address"
depends on ADVANCED_OPTIONS
help
This option allows you to set the kernel virtual address at which
- the kernel will map low memory (the kernel image will be linked at
- this address). This can be useful in optimizing the virtual memory
- layout of the system.
+ the kernel will be loaded. Normally this should match PAGE_OFFSET
+ however there are times (like kdump) that one might not want them
+ to be the same.
Say N here unless you know what you are doing.
config KERNEL_START
hex "Virtual address of kernel base" if KERNEL_START_BOOL
+ default PAGE_OFFSET if PAGE_OFFSET_BOOL
+ default "0xc2000000" if CRASH_DUMP
default "0xc0000000"
+config PHYSICAL_START_BOOL
+ bool "Set physical address where the kernel is loaded"
+ depends on ADVANCED_OPTIONS && FLATMEM && FSL_BOOKE
+ help
+ This gives the physical address where the kernel is loaded.
+
+ Say N here unless you know what you are doing.
+
+config PHYSICAL_START
+ hex "Physical address where the kernel is loaded" if PHYSICAL_START_BOOL
+ default "0x02000000" if PPC_STD_MMU && CRASH_DUMP
+ default "0x00000000"
+
+config PHYSICAL_ALIGN
+ hex
+ default "0x10000000" if FSL_BOOKE
+ help
+ This value puts the alignment restrictions on physical address
+ where kernel is loaded and run from. Kernel is compiled for an
+ address which meets above alignment restriction.
+
config TASK_SIZE_BOOL
bool "Set custom user task size"
depends on ADVANCED_OPTIONS
@@ -717,9 +758,17 @@ config PIN_TLB
endmenu
if PPC64
+config PAGE_OFFSET
+ hex
+ default "0xc000000000000000"
config KERNEL_START
hex
+ default "0xc000000002000000" if CRASH_DUMP
default "0xc000000000000000"
+config PHYSICAL_START
+ hex
+ default "0x02000000" if CRASH_DUMP
+ default "0x00000000"
endif
source "net/Kconfig"
@@ -754,3 +803,4 @@ config PPC_CLOCK
config PPC_LIB_RHEAP
bool
+source "arch/powerpc/kvm/Kconfig"
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index a86d8d85321..807a2dce626 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -151,6 +151,9 @@ config BOOTX_TEXT
config PPC_EARLY_DEBUG
bool "Early debugging (dangerous)"
+ # PPC_EARLY_DEBUG on 440 leaves AS=1 mappings above the TLB high water
+ # mark, which doesn't work with current 440 KVM.
+ depends on !KVM
help
Say Y to enable some early debugging facilities that may be available
for your processor/board combination. Those facilities are hacks
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index e2ec4a91cce..9dcdc036cdf 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -145,6 +145,7 @@ core-y += arch/powerpc/kernel/ \
arch/powerpc/platforms/
core-$(CONFIG_MATH_EMULATION) += arch/powerpc/math-emu/
core-$(CONFIG_XMON) += arch/powerpc/xmon/
+core-$(CONFIG_KVM) += arch/powerpc/kvm/
drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 5ef2bdf8d18..2347294ff35 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -27,6 +27,7 @@ zImage.chrp
zImage.coff
zImage.coff.lds
zImage.ep*
+zImage.iseries
zImage.*lds
zImage.miboot
zImage.pmac
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 5ba50c67339..7822d25c9d3 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -40,7 +40,7 @@ $(obj)/ebony.o: BOOTCFLAGS += -mcpu=405
$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405
$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405
$(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405
-$(obj)/virtex405-head.o: BOOTCFLAGS += -mcpu=405
+$(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405
zlib := inffast.c inflate.c inftrees.c
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 6f3d38a1554..39634124929 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -142,8 +142,45 @@
#address-cells = <2>;
#size-cells = <1>;
clock-frequency = <0>; /* Filled in by U-Boot */
+ /* ranges property is supplied by U-Boot */
interrupts = <6 4>;
interrupt-parent = <&UIC1>;
+
+ nor_flash@0,0 {
+ compatible = "amd,s29gl512n", "cfi-flash";
+ bank-width = <2>;
+ reg = <0 000000 4000000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ partition@0 {
+ label = "kernel";
+ reg = <0 1e0000>;
+ };
+ partition@1e0000 {
+ label = "dtb";
+ reg = <1e0000 20000>;
+ };
+ partition@200000 {
+ label = "ramdisk";
+ reg = <200000 1400000>;
+ };
+ partition@1600000 {
+ label = "jffs2";
+ reg = <1600000 400000>;
+ };
+ partition@1a00000 {
+ label = "user";
+ reg = <1a00000 2560000>;
+ };
+ partition@3f60000 {
+ label = "env";
+ reg = <3f60000 40000>;
+ };
+ partition@3fa0000 {
+ label = "u-boot";
+ reg = <3fa0000 60000>;
+ };
+ };
};
UART0: serial@ef600300 {
diff --git a/arch/powerpc/boot/dts/glacier.dts b/arch/powerpc/boot/dts/glacier.dts
index 958a5ca53d3..0f2fc077d8d 100644
--- a/arch/powerpc/boot/dts/glacier.dts
+++ b/arch/powerpc/boot/dts/glacier.dts
@@ -145,8 +145,45 @@
#address-cells = <2>;
#size-cells = <1>;
clock-frequency = <0>; /* Filled in by U-Boot */
+ /* ranges property is supplied by U-Boot */
interrupts = <6 4>;
interrupt-parent = <&UIC1>;
+
+ nor_flash@0,0 {
+ compatible = "amd,s29gl512n", "cfi-flash";
+ bank-width = <2>;
+ reg = <0 000000 4000000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ partition@0 {
+ label = "kernel";
+ reg = <0 1e0000>;
+ };
+ partition@1e0000 {
+ label = "dtb";
+ reg = <1e0000 20000>;
+ };
+ partition@200000 {
+ label = "ramdisk";
+ reg = <200000 1400000>;
+ };
+ partition@1600000 {
+ label = "jffs2";
+ reg = <1600000 400000>;
+ };
+ partition@1a00000 {
+ label = "user";
+ reg = <1a00000 2560000>;
+ };
+ partition@3f60000 {
+ label = "env";
+ reg = <3f60000 40000>;
+ };
+ partition@3fa0000 {
+ label = "u-boot";
+ reg = <3fa0000 60000>;
+ };
+ };
};
UART0: serial@ef600300 {
diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
index 16c947b8a72..1f2f1e0a557 100644
--- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts
+++ b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
@@ -45,6 +45,11 @@
reg = <0x00000000 0x20000000>; // 512M at 0x0
};
+ board-control@e8000000 {
+ compatible = "fsl,fpga-pixis";
+ reg = <0xe8000000 32>; // pixis at 0xe8000000
+ };
+
soc@e0000000 {
#address-cells = <1>;
#size-cells = <1>;
@@ -104,6 +109,13 @@
interrupt-parent = <&mpic>;
};
+ display@2c000 {
+ compatible = "fsl,diu";
+ reg = <0x2c000 100>;
+ interrupts = <72 2>;
+ interrupt-parent = <&mpic>;
+ };
+
mpic: interrupt-controller@40000 {
clock-frequency = <0>;
interrupt-controller;
diff --git a/arch/powerpc/boot/ns16550.c b/arch/powerpc/boot/ns16550.c
index aef3bdc8916..8c9ead94be0 100644
--- a/arch/powerpc/boot/ns16550.c
+++ b/arch/powerpc/boot/ns16550.c
@@ -55,10 +55,15 @@ static u8 ns16550_tstc(void)
int ns16550_console_init(void *devp, struct serial_console_data *scdp)
{
int n;
+ u32 reg_offset;
if (dt_get_virtual_reg(devp, (void **)&reg_base, 1) < 1)
return -1;
+ n = getprop(devp, "reg-offset", &reg_offset, sizeof(reg_offset));
+ if (n == sizeof(reg_offset))
+ reg_base += reg_offset;
+
n = getprop(devp, "reg-shift", &reg_shift, sizeof(reg_shift));
if (n != sizeof(reg_shift))
reg_shift = 0;
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ce1e8d24e74..9177b21b1a9 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -106,4 +106,13 @@ PHONY += systbl_chk
systbl_chk: $(src)/systbl_chk.sh $(obj)/systbl_chk.i
$(call cmd,systbl_chk)
+$(obj)/built-in.o: prom_init_check
+
+quiet_cmd_prom_init_check = CALL $<
+ cmd_prom_init_check = $(CONFIG_SHELL) $< "$(NM)" "$(obj)/prom_init.o"
+
+PHONY += prom_init_check
+prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o
+ $(call cmd,prom_init_check)
+
clean-files := vmlinux.lds
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 292c6d8db0e..62134845af0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -23,6 +23,9 @@
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/hrtimer.h>
+#ifdef CONFIG_KVM
+#include <linux/kvm_host.h>
+#endif
#ifdef CONFIG_PPC64
#include <linux/time.h>
#include <linux/hardirq.h>
@@ -93,10 +96,7 @@ int main(void)
DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
DEFINE(TI_TASK, offsetof(struct thread_info, task));
-#ifdef CONFIG_PPC32
- DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain));
DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
-#endif /* CONFIG_PPC32 */
#ifdef CONFIG_PPC64
DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size));
@@ -165,13 +165,9 @@ int main(void)
/* Interrupt register frame */
DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
-#ifndef CONFIG_PPC64
- DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
-#else /* CONFIG_PPC64 */
+ DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
+#ifdef CONFIG_PPC64
DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
- /* 288 = # of volatile regs, int & fp, for leaf routines */
- /* which do not stack a frame. See the PPC64 ABI. */
- DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 288);
/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
@@ -331,5 +327,30 @@ int main(void)
DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
+#ifdef CONFIG_KVM
+ DEFINE(TLBE_BYTES, sizeof(struct tlbe));
+
+ DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
+ DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
+ DEFINE(VCPU_HOST_TLB, offsetof(struct kvm_vcpu, arch.host_tlb));
+ DEFINE(VCPU_SHADOW_TLB, offsetof(struct kvm_vcpu, arch.shadow_tlb));
+ DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
+ DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+ DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
+ DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+ DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+ DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+ DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
+ DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
+ DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
+ DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
+ DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
+ DEFINE(VCPU_PID, offsetof(struct kvm_vcpu, arch.pid));
+
+ DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+ DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
+ DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+#endif
+
return 0;
}
diff --git a/arch/powerpc/kernel/cpu_setup_44x.S b/arch/powerpc/kernel/cpu_setup_44x.S
index 5465e8de0e6..e3623e3e345 100644
--- a/arch/powerpc/kernel/cpu_setup_44x.S
+++ b/arch/powerpc/kernel/cpu_setup_44x.S
@@ -33,7 +33,6 @@ _GLOBAL(__setup_cpu_440grx)
mtlr r4
blr
_GLOBAL(__setup_cpu_460ex)
-_GLOBAL(__setup_cpu_460gt)
b __init_fpu_44x
_GLOBAL(__setup_cpu_440gx)
_GLOBAL(__setup_cpu_440spe)
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f1ee0b3f78f..72d1d739525 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -17,7 +17,13 @@
#include <asm/cache.h>
_GLOBAL(__setup_cpu_603)
- b setup_common_caches
+ mflr r4
+BEGIN_FTR_SECTION
+ bl __init_fpu_registers
+END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
+ bl setup_common_caches
+ mtlr r4
+ blr
_GLOBAL(__setup_cpu_604)
mflr r4
bl setup_common_caches
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 26ffb44e270..36080d4d192 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -37,7 +37,6 @@ extern void __setup_cpu_440gx(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_440grx(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_440spe(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_460ex(unsigned long offset, struct cpu_spec* spec);
-extern void __setup_cpu_460gt(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_603(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_604(unsigned long offset, struct cpu_spec* spec);
extern void __setup_cpu_750(unsigned long offset, struct cpu_spec* spec);
@@ -1416,10 +1415,9 @@ static struct cpu_spec __initdata cpu_specs[] = {
.pvr_value = 0x13020000,
.cpu_name = "460GT",
.cpu_features = CPU_FTRS_44X,
- .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+ .cpu_user_features = COMMON_USER_BOOKE,
.icache_bsize = 32,
.dcache_bsize = 32,
- .cpu_setup = __setup_cpu_460gt,
.machine_check = machine_check_440A,
.platform = "ppc440",
},
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 4ff74414356..e581524d85b 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -371,6 +371,17 @@ skpinv: addi r6,r6,1 /* Increment */
bl early_init
+#ifdef CONFIG_RELOCATABLE
+ lis r3,kernstart_addr@ha
+ la r3,kernstart_addr@l(r3)
+#ifdef CONFIG_PHYS_64BIT
+ stw r23,0(r3)
+ stw r25,4(r3)
+#else
+ stw r25,0(r3)
+#endif
+#endif
+
mfspr r3,SPRN_TLB1CFG
andi. r3,r3,0xfff
lis r4,num_tlbcam_entries@ha
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 9d2c56621f1..92ccc6fcc5b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -152,7 +152,7 @@ _GLOBAL(low_choose_750fx_pll)
mtspr SPRN_HID1,r4
/* Store new HID1 image */
- rlwinm r6,r1,0,0,18
+ rlwinm r6,r1,0,0,(31-THREAD_SHIFT)
lwz r6,TI_CPU(r6)
slwi r6,r6,2
addis r6,r6,nap_save_hid1@ha
@@ -281,7 +281,7 @@ _GLOBAL(_tlbia)
#endif /* CONFIG_SMP */
#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
#if defined(CONFIG_SMP)
- rlwinm r8,r1,0,0,18
+ rlwinm r8,r1,0,0,(31-THREAD_SHIFT)
lwz r8,TI_CPU(r8)
oris r8,r8,10
mfmsr r10
@@ -377,7 +377,7 @@ _GLOBAL(_tlbie)
#endif /* CONFIG_SMP */
#else /* !(CONFIG_40x || CONFIG_44x || CONFIG_FSL_BOOKE) */
#if defined(CONFIG_SMP)
- rlwinm r8,r1,0,0,18
+ rlwinm r8,r1,0,0,(31-THREAD_SHIFT)
lwz r8,TI_CPU(r8)
oris r8,r8,11
mfmsr r10
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index a3c491e88a7..942951e7658 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -27,23 +27,11 @@
.text
-_GLOBAL(get_msr)
- mfmsr r3
- blr
-
-_GLOBAL(get_srr0)
- mfsrr0 r3
- blr
-
-_GLOBAL(get_srr1)
- mfsrr1 r3
- blr
-
#ifdef CONFIG_IRQSTACKS
_GLOBAL(call_do_softirq)
mflr r0
std r0,16(r1)
- stdu r1,THREAD_SIZE-112(r3)
+ stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
bl .__do_softirq
ld r1,0(r1)
@@ -56,7 +44,7 @@ _GLOBAL(call_handle_irq)
mflr r0
std r0,16(r1)
mtctr r8
- stdu r1,THREAD_SIZE-112(r5)
+ stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5)
mr r1,r5
bctrl
ld r1,0(r1)
@@ -599,7 +587,7 @@ _GLOBAL(kexec_sequence)
std r0,16(r1)
/* switch stacks to newstack -- &kexec_stack.stack */
- stdu r1,THREAD_SIZE-112(r3)
+ stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
mr r1,r3
li r0,0
@@ -616,7 +604,7 @@ _GLOBAL(kexec_sequence)
std r26,-48(r1)
std r25,-56(r1)
- stdu r1,-112-64(r1)
+ stdu r1,-STACK_FRAME_OVERHEAD-64(r1)
/* save args into preserved regs */
mr r31,r3 /* newstack (both) */
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index fb698d47082..e79ad8afda0 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -275,6 +275,8 @@ static int __devinit of_pci_phb_probe(struct of_device *dev,
/* Scan the bus */
scan_phb(phb);
+ if (phb->bus == NULL)
+ return -ENXIO;
/* Claim resources. This might need some rework as well depending
* wether we are doing probe-only or not, like assigning unassigned
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index ac163bd46cf..c9bf17eec31 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -7,17 +7,11 @@
* 2 of the License, or (at your option) any later version.
*/
-#include <linux/types.h>
#include <linux/threads.h>
#include <linux/module.h>
-#include <asm/processor.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
#include <asm/lppaca.h>
#include <asm/paca.h>
-#include <asm/mmu.h>
-
/* This symbol is provided by the linker - let it fill in the paca
* field correctly */
@@ -65,60 +59,29 @@ struct slb_shadow slb_shadow[] __cacheline_aligned = {
* processors. The processor VPD array needs one entry per physical
* processor (not thread).
*/
-#define PACA_INIT(number) \
-{ \
- .lppaca_ptr = &lppaca[number], \
- .lock_token = 0x8000, \
- .paca_index = (number), /* Paca Index */ \
- .kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL, \
- .hw_cpu_id = 0xffff, \
- .slb_shadow_ptr = &slb_shadow[number], \
- .__current = &init_task, \
-}
-
-struct paca_struct paca[] = {
- PACA_INIT(0),
-#if NR_CPUS > 1
- PACA_INIT( 1), PACA_INIT( 2), PACA_INIT( 3),
-#if NR_CPUS > 4
- PACA_INIT( 4), PACA_INIT( 5), PACA_INIT( 6), PACA_INIT( 7),
-#if NR_CPUS > 8
- PACA_INIT( 8), PACA_INIT( 9), PACA_INIT( 10), PACA_INIT( 11),
- PACA_INIT( 12), PACA_INIT( 13), PACA_INIT( 14), PACA_INIT( 15),
- PACA_INIT( 16), PACA_INIT( 17), PACA_INIT( 18), PACA_INIT( 19),
- PACA_INIT( 20), PACA_INIT( 21), PACA_INIT( 22), PACA_INIT( 23),
- PACA_INIT( 24), PACA_INIT( 25), PACA_INIT( 26), PACA_INIT( 27),
- PACA_INIT( 28), PACA_INIT( 29), PACA_INIT( 30), PACA_INIT( 31),
-#if NR_CPUS > 32
- PACA_INIT( 32), PACA_INIT( 33), PACA_INIT( 34), PACA_INIT( 35),
- PACA_INIT( 36), PACA_INIT( 37), PACA_INIT( 38), PACA_INIT( 39),
- PACA_INIT( 40), PACA_INIT( 41), PACA_INIT( 42), PACA_INIT( 43),
- PACA_INIT( 44), PACA_INIT( 45), PACA_INIT( 46), PACA_INIT( 47),
- PACA_INIT( 48), PACA_INIT( 49), PACA_INIT( 50), PACA_INIT( 51),
- PACA_INIT( 52), PACA_INIT( 53), PACA_INIT( 54), PACA_INIT( 55),
- PACA_INIT( 56), PACA_INIT( 57), PACA_INIT( 58), PACA_INIT( 59),
- PACA_INIT( 60), PACA_INIT( 61), PACA_INIT( 62), PACA_INIT( 63),
-#if NR_CPUS > 64
- PACA_INIT( 64), PACA_INIT( 65), PACA_INIT( 66), PACA_INIT( 67),
- PACA_INIT( 68), PACA_INIT( 69), PACA_INIT( 70), PACA_INIT( 71),
- PACA_INIT( 72), PACA_INIT( 73), PACA_INIT( 74), PACA_INIT( 75),
- PACA_INIT( 76), PACA_INIT( 77), PACA_INIT( 78), PACA_INIT( 79),
- PACA_INIT( 80), PACA_INIT( 81), PACA_INIT( 82), PACA_INIT( 83),
- PACA_INIT( 84), PACA_INIT( 85), PACA_INIT( 86), PACA_INIT( 87),
- PACA_INIT( 88), PACA_INIT( 89), PACA_INIT( 90), PACA_INIT( 91),
- PACA_INIT( 92), PACA_INIT( 93), PACA_INIT( 94), PACA_INIT( 95),
- PACA_INIT( 96), PACA_INIT( 97), PACA_INIT( 98), PACA_INIT( 99),
- PACA_INIT(100), PACA_INIT(101), PACA_INIT(102), PACA_INIT(103),
- PACA_INIT(104), PACA_INIT(105), PACA_INIT(106), PACA_INIT(107),
- PACA_INIT(108), PACA_INIT(109), PACA_INIT(110), PACA_INIT(111),
- PACA_INIT(112), PACA_INIT(113), PACA_INIT(114), PACA_INIT(115),
- PACA_INIT(116), PACA_INIT(117), PACA_INIT(118), PACA_INIT(119),
- PACA_INIT(120), PACA_INIT(121), PACA_INIT(122), PACA_INIT(123),
- PACA_INIT(124), PACA_INIT(125), PACA_INIT(126), PACA_INIT(127),
-#endif
-#endif
-#endif
-#endif
-#endif
-};
+struct paca_struct paca[NR_CPUS];
EXPORT_SYMBOL(paca);
+
+void __init initialise_pacas(void)
+{
+ int cpu;
+
+ /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB
+ * of the TOC can be addressed using a single machine instruction.
+ */
+ unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
+
+ /* Can't use for_each_*_cpu, as they aren't functional yet */
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ struct paca_struct *new_paca = &paca[cpu];
+
+ new_paca->lppaca_ptr = &lppaca[cpu];
+ new_paca->lock_token = 0x8000;
+ new_paca->paca_index = cpu;
+ new_paca->kernel_toc = kernel_toc;
+ new_paca->hw_cpu_id = 0xffff;
+ new_paca->slb_shadow_ptr = &slb_shadow[cpu];
+ new_paca->__current = &init_task;
+
+ }
+}
diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h
index fda05e2211d..90e56277179 100644
--- a/arch/powerpc/kernel/ppc32.h
+++ b/arch/powerpc/kernel/ppc32.h
@@ -135,6 +135,4 @@ struct ucontext32 {
struct mcontext32 uc_mcontext;
};
-extern int copy_siginfo_to_user32(struct compat_siginfo __user *d, siginfo_t *s);
-
#endif /* _PPC64_PPC32_H */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 703100d5e45..6caad17ea72 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1033,3 +1033,34 @@ void ppc64_runlatch_off(void)
}
}
#endif
+
+#if THREAD_SHIFT < PAGE_SHIFT
+
+static struct kmem_cache *thread_info_cache;
+
+struct thread_info *alloc_thread_info(struct task_struct *tsk)
+{
+ struct thread_info *ti;
+
+ ti = kmem_cache_alloc(thread_info_cache, GFP_KERNEL);
+ if (unlikely(ti == NULL))
+ return NULL;
+#ifdef CONFIG_DEBUG_STACK_USAGE
+ memset(ti, 0, THREAD_SIZE);
+#endif
+ return ti;
+}
+
+void free_thread_info(struct thread_info *ti)
+{
+ kmem_cache_free(thread_info_cache, ti);
+}
+
+void thread_info_cache_init(void)
+{
+ thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ THREAD_SIZE, 0, NULL);
+ BUG_ON(thread_info_cache == NULL);
+}
+
+#endif /* THREAD_SHIFT < PAGE_SHIFT */
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 3bfe7837e82..2aefe2a4129 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -53,6 +53,7 @@
#include <asm/pci-bridge.h>
#include <asm/phyp_dump.h>
#include <asm/kexec.h>
+#include <mm/mmu_decl.h>
#ifdef DEBUG
#define DBG(fmt...) printk(KERN_ERR fmt)
@@ -978,7 +979,10 @@ static int __init early_init_dt_scan_memory(unsigned long node,
}
#endif
lmb_add(base, size);
+
+ memstart_addr = min((u64)memstart_addr, base);
}
+
return 0;
}
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
new file mode 100644
index 00000000000..8e24fc1821e
--- /dev/null
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -0,0 +1,58 @@
+#!/bin/sh
+#
+# Copyright © 2008 IBM Corporation
+#
+# 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 script checks prom_init.o to see what external symbols it
+# is using, if it finds symbols not in the whitelist it returns
+# an error. The point of this is to discourage people from
+# intentionally or accidentally adding new code to prom_init.c
+# which has side effects on other parts of the kernel.
+
+# If you really need to reference something from prom_init.o add
+# it to the list below:
+
+WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
+_end enter_prom memcpy memset reloc_offset __secondary_hold
+__secondary_hold_acknowledge __secondary_hold_spinloop __start
+strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
+reloc_got2"
+
+NM="$1"
+OBJ="$2"
+
+ERROR=0
+
+for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+do
+ # On 64-bit nm gives us the function descriptors, which have
+ # a leading . on the name, so strip it off here.
+ UNDEF="${UNDEF#.}"
+
+ if [ $KBUILD_VERBOSE ]; then
+ if [ $KBUILD_VERBOSE -ne 0 ]; then
+ echo "Checking prom_init.o symbol '$UNDEF'"
+ fi
+ fi
+
+ OK=0
+ for WHITE in $WHITELIST
+ do
+ if [ "$UNDEF" = "$WHITE" ]; then
+ OK=1
+ break
+ fi
+ done
+
+ if [ $OK -eq 0 ]; then
+ ERROR=1
+ echo "Error: External symbol '$UNDEF' referenced" \
+ "from prom_init.c" >&2
+ fi
+done
+
+exit $ERROR
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 9d30e10970a..4c1de6af4c0 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -29,15 +29,12 @@
#include <linux/security.h>
#include <linux/signal.h>
#include <linux/compat.h>
-#include <linux/elf.h>
#include <asm/uaccess.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/system.h>
-#include "ppc32.h"
-
/*
* does not yet catch signals sent when the child dies.
* in exit.c or in signal.c.
@@ -67,27 +64,6 @@ static long compat_ptrace_old(struct task_struct *child, long request,
return -EPERM;
}
-static int compat_ptrace_getsiginfo(struct task_struct *child, compat_siginfo_t __user *data)
-{
- siginfo_t lastinfo;
- int error = -ESRCH;
-
- read_lock(&tasklist_lock);
- if (likely(child->sighand != NULL)) {
- error = -EINVAL;
- spin_lock_irq(&child->sighand->siglock);
- if (likely(child->last_siginfo != NULL)) {
- lastinfo = *child->last_siginfo;
- error = 0;
- }
- spin_unlock_irq(&child->sighand->siglock);
- }
- read_unlock(&tasklist_lock);
- if (!error)
- return copy_siginfo_to_user32(data, &lastinfo);
- return error;
-}
-
long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
compat_ulong_t caddr, compat_ulong_t cdata)
{
@@ -306,9 +282,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
0, PT_REGS_COUNT * sizeof(compat_long_t),
compat_ptr(data));
- case PTRACE_GETSIGINFO:
- return compat_ptrace_getsiginfo(child, compat_ptr(data));
-
case PTRACE_GETFPREGS:
case PTRACE_SETFPREGS:
case PTRACE_GETVRREGS:
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 31ada9fdfc5..dff6308d1b5 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
void __init early_setup(unsigned long dt_ptr)
{
+ /* Fill in any unititialised pacas */
+ initialise_pacas();
+
/* Identify CPU type */
identify_cpu(0, mfspr(SPRN_PVR));
@@ -435,7 +438,7 @@ void __init setup_system(void)
printk("htab_address = 0x%p\n", htab_address);
printk("htab_hash_mask = 0x%lx\n", htab_hash_mask);
#if PHYSICAL_START > 0
- printk("physical_start = 0x%x\n", PHYSICAL_START);
+ printk("physical_start = 0x%lx\n", PHYSICAL_START);
#endif
printk("-----------------------------------------------------\n");
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index e3638eeaaae..96294403843 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -13,7 +13,6 @@
#include <linux/sched.h>
#include <linux/stacktrace.h>
#include <asm/ptrace.h>
-#include <asm/asm-offsets.h>
/*
* Save stack-backtrace addresses into a stack_trace buffer.
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 7aad6203e41..7d6c9bb8c77 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -154,8 +154,8 @@ static void udbg_console_write(struct console *con, const char *s,
static struct console udbg_console = {
.name = "udbg",
.write = udbg_console_write,
- .flags = CON_PRINTBUFFER | CON_ENABLED | CON_BOOT,
- .index = -1,
+ .flags = CON_PRINTBUFFER | CON_ENABLED | CON_BOOT | CON_ANYTIME,
+ .index = 0,
};
static int early_console_initialized;
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
new file mode 100644
index 00000000000..f5d7a5eab96
--- /dev/null
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -0,0 +1,224 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <asm/mmu-44x.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+#define PPC44x_TLB_USER_PERM_MASK (PPC44x_TLB_UX|PPC44x_TLB_UR|PPC44x_TLB_UW)
+#define PPC44x_TLB_SUPER_PERM_MASK (PPC44x_TLB_SX|PPC44x_TLB_SR|PPC44x_TLB_SW)
+
+static unsigned int kvmppc_tlb_44x_pos;
+
+static u32 kvmppc_44x_tlb_shadow_attrib(u32 attrib, int usermode)
+{
+ /* Mask off reserved bits. */
+ attrib &= PPC44x_TLB_PERM_MASK|PPC44x_TLB_ATTR_MASK;
+
+ if (!usermode) {
+ /* Guest is in supervisor mode, so we need to translate guest
+ * supervisor permissions into user permissions. */
+ attrib &= ~PPC44x_TLB_USER_PERM_MASK;
+ attrib |= (attrib & PPC44x_TLB_SUPER_PERM_MASK) << 3;
+ }
+
+ /* Make sure host can always access this memory. */
+ attrib |= PPC44x_TLB_SX|PPC44x_TLB_SR|PPC44x_TLB_SW;
+
+ return attrib;
+}
+
+/* Search the guest TLB for a matching entry. */
+int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned int pid,
+ unsigned int as)
+{
+ int i;
+
+ /* XXX Replace loop with fancy data structures. */
+ for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+ struct tlbe *tlbe = &vcpu->arch.guest_tlb[i];
+ unsigned int tid;
+
+ if (eaddr < get_tlb_eaddr(tlbe))
+ continue;
+
+ if (eaddr > get_tlb_end(tlbe))
+ continue;
+
+ tid = get_tlb_tid(tlbe);
+ if (tid && (tid != pid))
+ continue;
+
+ if (!get_tlb_v(tlbe))
+ continue;
+
+ if (get_tlb_ts(tlbe) != as)
+ continue;
+
+ return i;
+ }
+
+ return -1;
+}
+
+struct tlbe *kvmppc_44x_itlb_search(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+ unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+ unsigned int index;
+
+ index = kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
+ if (index == -1)
+ return NULL;
+ return &vcpu->arch.guest_tlb[index];
+}
+
+struct tlbe *kvmppc_44x_dtlb_search(struct kvm_vcpu *vcpu, gva_t eaddr)
+{
+ unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+ unsigned int index;
+
+ index = kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
+ if (index == -1)
+ return NULL;
+ return &vcpu->arch.guest_tlb[index];
+}
+
+static int kvmppc_44x_tlbe_is_writable(struct tlbe *tlbe)
+{
+ return tlbe->word2 & (PPC44x_TLB_SW|PPC44x_TLB_UW);
+}
+
+/* Must be called with mmap_sem locked for writing. */
+static void kvmppc_44x_shadow_release(struct kvm_vcpu *vcpu,
+ unsigned int index)
+{
+ struct tlbe *stlbe = &vcpu->arch.shadow_tlb[index];
+ struct page *page = vcpu->arch.shadow_pages[index];
+
+ kunmap(vcpu->arch.shadow_pages[index]);
+
+ if (get_tlb_v(stlbe)) {
+ if (kvmppc_44x_tlbe_is_writable(stlbe))
+ kvm_release_page_dirty(page);
+ else
+ kvm_release_page_clean(page);
+ }
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gfn_t gfn, u64 asid,
+ u32 flags)
+{
+ struct page *new_page;
+ struct tlbe *stlbe;
+ hpa_t hpaddr;
+ unsigned int victim;
+
+ /* Future optimization: don't overwrite the TLB entry containing the
+ * current PC (or stack?). */
+ victim = kvmppc_tlb_44x_pos++;
+ if (kvmppc_tlb_44x_pos > tlb_44x_hwater)
+ kvmppc_tlb_44x_pos = 0;
+ stlbe = &vcpu->arch.shadow_tlb[victim];
+
+ /* Get reference to new page. */
+ down_write(&current->mm->mmap_sem);
+ new_page = gfn_to_page(vcpu->kvm, gfn);
+ if (is_error_page(new_page)) {
+ printk(KERN_ERR "Couldn't get guest page!\n");
+ kvm_release_page_clean(new_page);
+ return;
+ }
+ hpaddr = page_to_phys(new_page);
+
+ /* Drop reference to old page. */
+ kvmppc_44x_shadow_release(vcpu, victim);
+ up_write(&current->mm->mmap_sem);
+
+ vcpu->arch.shadow_pages[victim] = new_page;
+
+ /* XXX Make sure (va, size) doesn't overlap any other
+ * entries. 440x6 user manual says the result would be
+ * "undefined." */
+
+ /* XXX what about AS? */
+
+ stlbe->tid = asid & 0xff;
+
+ /* Force TS=1 for all guest mappings. */
+ /* For now we hardcode 4KB mappings, but it will be important to
+ * use host large pages in the future. */
+ stlbe->word0 = (gvaddr & PAGE_MASK) | PPC44x_TLB_VALID | PPC44x_TLB_TS
+ | PPC44x_TLB_4K;
+
+ stlbe->word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf);
+ stlbe->word2 = kvmppc_44x_tlb_shadow_attrib(flags,
+ vcpu->arch.msr & MSR_PR);
+}
+
+void kvmppc_mmu_invalidate(struct kvm_vcpu *vcpu, u64 eaddr, u64 asid)
+{
+ unsigned int pid = asid & 0xff;
+ int i;
+
+ /* XXX Replace loop with fancy data structures. */
+ down_write(&current->mm->mmap_sem);
+ for (i = 0; i <= tlb_44x_hwater; i++) {
+ struct tlbe *stlbe = &vcpu->arch.shadow_tlb[i];
+ unsigned int tid;
+
+ if (!get_tlb_v(stlbe))
+ continue;
+
+ if (eaddr < get_tlb_eaddr(stlbe))
+ continue;
+
+ if (eaddr > get_tlb_end(stlbe))
+ continue;
+
+ tid = get_tlb_tid(stlbe);
+ if (tid && (tid != pid))
+ continue;
+
+ kvmppc_44x_shadow_release(vcpu, i);
+ stlbe->word0 = 0;
+ }
+ up_write(&current->mm->mmap_sem);
+}
+
+/* Invalidate all mappings, so that when they fault back in they will get the
+ * proper permission bits. */
+void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
+{
+ int i;
+
+ /* XXX Replace loop with fancy data structures. */
+ down_write(&current->mm->mmap_sem);
+ for (i = 0; i <= tlb_44x_hwater; i++) {
+ kvmppc_44x_shadow_release(vcpu, i);
+ vcpu->arch.shadow_tlb[i].word0 = 0;
+ }
+ up_write(&current->mm->mmap_sem);
+}
diff --git a/arch/powerpc/kvm/44x_tlb.h b/arch/powerpc/kvm/44x_tlb.h
new file mode 100644
index 00000000000..2ccd46b6f6b
--- /dev/null
+++ b/arch/powerpc/kvm/44x_tlb.h
@@ -0,0 +1,91 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __KVM_POWERPC_TLB_H__
+#define __KVM_POWERPC_TLB_H__
+
+#include <linux/kvm_host.h>
+#include <asm/mmu-44x.h>
+
+extern int kvmppc_44x_tlb_index(struct kvm_vcpu *vcpu, gva_t eaddr,
+ unsigned int pid, unsigned int as);
+extern struct tlbe *kvmppc_44x_dtlb_search(struct kvm_vcpu *vcpu, gva_t eaddr);
+extern struct tlbe *kvmppc_44x_itlb_search(struct kvm_vcpu *vcpu, gva_t eaddr);
+
+/* TLB helper functions */
+static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+{
+ return (tlbe->word0 >> 4) & 0xf;
+}
+
+static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+{
+ return tlbe->word0 & 0xfffffc00;
+}
+
+static inline gva_t get_tlb_bytes(const struct tlbe *tlbe)
+{
+ unsigned int pgsize = get_tlb_size(tlbe);
+ return 1 << 10 << (pgsize << 1);
+}
+
+static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+{
+ return get_tlb_eaddr(tlbe) + get_tlb_bytes(tlbe) - 1;
+}
+
+static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+{
+ u64 word1 = tlbe->word1;
+ return ((word1 & 0xf) << 32) | (word1 & 0xfffffc00);
+}
+
+static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+{
+ return tlbe->tid & 0xff;
+}
+
+static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+{
+ return (tlbe->word0 >> 8) & 0x1;
+}
+
+static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+{
+ return (tlbe->word0 >> 9) & 0x1;
+}
+
+static inline unsigned int get_mmucr_stid(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mmucr & 0xff;
+}
+
+static inline unsigned int get_mmucr_sts(const struct kvm_vcpu *vcpu)
+{
+ return (vcpu->arch.mmucr >> 16) & 0x1;
+}
+
+static inline gpa_t tlb_xlate(struct tlbe *tlbe, gva_t eaddr)
+{
+ unsigned int pgmask = get_tlb_bytes(tlbe) - 1;
+
+ return get_tlb_raddr(tlbe) | (eaddr & pgmask);
+}
+
+#endif /* __KVM_POWERPC_TLB_H__ */
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
new file mode 100644
index 00000000000..6b076010213
--- /dev/null
+++ b/arch/powerpc/kvm/Kconfig
@@ -0,0 +1,42 @@
+#
+# KVM configuration
+#
+
+menuconfig VIRTUALIZATION
+ bool "Virtualization"
+ ---help---
+ Say Y here to get to see options for using your Linux host to run
+ other operating systems inside virtual machines (guests).
+ This option alone does not add any kernel code.
+
+ If you say N, all options in this submenu will be skipped and
+ disabled.
+
+if VIRTUALIZATION
+
+config KVM
+ bool "Kernel-based Virtual Machine (KVM) support"
+ depends on 44x && EXPERIMENTAL
+ select PREEMPT_NOTIFIERS
+ select ANON_INODES
+ # We can only run on Book E hosts so far
+ select KVM_BOOKE_HOST
+ ---help---
+ Support hosting virtualized guest machines. You will also
+ need to select one or more of the processor modules below.
+
+ This module provides access to the hardware capabilities through
+ a character device node named /dev/kvm.
+
+ If unsure, say N.
+
+config KVM_BOOKE_HOST
+ bool "KVM host support for Book E PowerPC processors"
+ depends on KVM && 44x
+ ---help---
+ Provides host support for KVM on Book E PowerPC processors. Currently
+ this works on 440 processors only.
+
+source drivers/virtio/Kconfig
+
+endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
new file mode 100644
index 00000000000..d0d358d367e
--- /dev/null
+++ b/arch/powerpc/kvm/Makefile
@@ -0,0 +1,15 @@
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
+
+kvm-objs := $(common-objs) powerpc.o emulate.o booke_guest.o
+obj-$(CONFIG_KVM) += kvm.o
+
+AFLAGS_booke_interrupts.o := -I$(obj)
+
+kvm-booke-host-objs := booke_host.o booke_interrupts.o 44x_tlb.o
+obj-$(CONFIG_KVM_BOOKE_HOST) += kvm-booke-host.o
diff --git a/arch/powerpc/kvm/booke_guest.c b/arch/powerpc/kvm/booke_guest.c
new file mode 100644
index 00000000000..6d9884a6884
--- /dev/null
+++ b/arch/powerpc/kvm/booke_guest.c
@@ -0,0 +1,615 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ * Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputable.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+ { "exits", VCPU_STAT(sum_exits) },
+ { "mmio", VCPU_STAT(mmio_exits) },
+ { "dcr", VCPU_STAT(dcr_exits) },
+ { "sig", VCPU_STAT(signal_exits) },
+ { "light", VCPU_STAT(light_exits) },
+ { "itlb_r", VCPU_STAT(itlb_real_miss_exits) },
+ { "itlb_v", VCPU_STAT(itlb_virt_miss_exits) },
+ { "dtlb_r", VCPU_STAT(dtlb_real_miss_exits) },
+ { "dtlb_v", VCPU_STAT(dtlb_virt_miss_exits) },
+ { "sysc", VCPU_STAT(syscall_exits) },
+ { "isi", VCPU_STAT(isi_exits) },
+ { "dsi", VCPU_STAT(dsi_exits) },
+ { "inst_emu", VCPU_STAT(emulated_inst_exits) },
+ { "dec", VCPU_STAT(dec_exits) },
+ { "ext_intr", VCPU_STAT(ext_intr_exits) },
+ { NULL }
+};
+
+static const u32 interrupt_msr_mask[16] = {
+ [BOOKE_INTERRUPT_CRITICAL] = MSR_ME,
+ [BOOKE_INTERRUPT_MACHINE_CHECK] = 0,
+ [BOOKE_INTERRUPT_DATA_STORAGE] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_INST_STORAGE] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_EXTERNAL] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_ALIGNMENT] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_PROGRAM] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_FP_UNAVAIL] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_SYSCALL] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_AP_UNAVAIL] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_DECREMENTER] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_FIT] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_WATCHDOG] = MSR_ME,
+ [BOOKE_INTERRUPT_DTLB_MISS] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_ITLB_MISS] = MSR_CE|MSR_ME|MSR_DE,
+ [BOOKE_INTERRUPT_DEBUG] = MSR_ME,
+};
+
+const unsigned char exception_priority[] = {
+ [BOOKE_INTERRUPT_DATA_STORAGE] = 0,
+ [BOOKE_INTERRUPT_INST_STORAGE] = 1,
+ [BOOKE_INTERRUPT_ALIGNMENT] = 2,
+ [BOOKE_INTERRUPT_PROGRAM] = 3,
+ [BOOKE_INTERRUPT_FP_UNAVAIL] = 4,
+ [BOOKE_INTERRUPT_SYSCALL] = 5,
+ [BOOKE_INTERRUPT_AP_UNAVAIL] = 6,
+ [BOOKE_INTERRUPT_DTLB_MISS] = 7,
+ [BOOKE_INTERRUPT_ITLB_MISS] = 8,
+ [BOOKE_INTERRUPT_MACHINE_CHECK] = 9,
+ [BOOKE_INTERRUPT_DEBUG] = 10,
+ [BOOKE_INTERRUPT_CRITICAL] = 11,
+ [BOOKE_INTERRUPT_WATCHDOG] = 12,
+ [BOOKE_INTERRUPT_EXTERNAL] = 13,
+ [BOOKE_INTERRUPT_FIT] = 14,
+ [BOOKE_INTERRUPT_DECREMENTER] = 15,
+};
+
+const unsigned char priority_exception[] = {
+ BOOKE_INTERRUPT_DATA_STORAGE,
+ BOOKE_INTERRUPT_INST_STORAGE,
+ BOOKE_INTERRUPT_ALIGNMENT,
+ BOOKE_INTERRUPT_PROGRAM,
+ BOOKE_INTERRUPT_FP_UNAVAIL,
+ BOOKE_INTERRUPT_SYSCALL,
+ BOOKE_INTERRUPT_AP_UNAVAIL,
+ BOOKE_INTERRUPT_DTLB_MISS,
+ BOOKE_INTERRUPT_ITLB_MISS,
+ BOOKE_INTERRUPT_MACHINE_CHECK,
+ BOOKE_INTERRUPT_DEBUG,
+ BOOKE_INTERRUPT_CRITICAL,
+ BOOKE_INTERRUPT_WATCHDOG,
+ BOOKE_INTERRUPT_EXTERNAL,
+ BOOKE_INTERRUPT_FIT,
+ BOOKE_INTERRUPT_DECREMENTER,
+};
+
+
+void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
+{
+ struct tlbe *tlbe;
+ int i;
+
+ printk("vcpu %d TLB dump:\n", vcpu->vcpu_id);
+ printk("| %2s | %3s | %8s | %8s | %8s |\n",
+ "nr", "tid", "word0", "word1", "word2");
+
+ for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+ tlbe = &vcpu->arch.guest_tlb[i];
+ if (tlbe->word0 & PPC44x_TLB_VALID)
+ printk(" G%2d | %02X | %08X | %08X | %08X |\n",
+ i, tlbe->tid, tlbe->word0, tlbe->word1,
+ tlbe->word2);
+ }
+
+ for (i = 0; i < PPC44x_TLB_SIZE; i++) {
+ tlbe = &vcpu->arch.shadow_tlb[i];
+ if (tlbe->word0 & PPC44x_TLB_VALID)
+ printk(" S%2d | %02X | %08X | %08X | %08X |\n",
+ i, tlbe->tid, tlbe->word0, tlbe->word1,
+ tlbe->word2);
+ }
+}
+
+/* TODO: use vcpu_printf() */
+void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
+{
+ int i;
+
+ printk("pc: %08x msr: %08x\n", vcpu->arch.pc, vcpu->arch.msr);
+ printk("lr: %08x ctr: %08x\n", vcpu->arch.lr, vcpu->arch.ctr);
+ printk("srr0: %08x srr1: %08x\n", vcpu->arch.srr0, vcpu->arch.srr1);
+
+ printk("exceptions: %08lx\n", vcpu->arch.pending_exceptions);
+
+ for (i = 0; i < 32; i += 4) {
+ printk("gpr%02d: %08x %08x %08x %08x\n", i,
+ vcpu->arch.gpr[i],
+ vcpu->arch.gpr[i+1],
+ vcpu->arch.gpr[i+2],
+ vcpu->arch.gpr[i+3]);
+ }
+}
+
+/* Check if we are ready to deliver the interrupt */
+static int kvmppc_can_deliver_interrupt(struct kvm_vcpu *vcpu, int interrupt)
+{
+ int r;
+
+ switch (interrupt) {
+ case BOOKE_INTERRUPT_CRITICAL:
+ r = vcpu->arch.msr & MSR_CE;
+ break;
+ case BOOKE_INTERRUPT_MACHINE_CHECK:
+ r = vcpu->arch.msr & MSR_ME;
+ break;
+ case BOOKE_INTERRUPT_EXTERNAL:
+ r = vcpu->arch.msr & MSR_EE;
+ break;
+ case BOOKE_INTERRUPT_DECREMENTER:
+ r = vcpu->arch.msr & MSR_EE;
+ break;
+ case BOOKE_INTERRUPT_FIT:
+ r = vcpu->arch.msr & MSR_EE;
+ break;
+ case BOOKE_INTERRUPT_WATCHDOG:
+ r = vcpu->arch.msr & MSR_CE;
+ break;
+ case BOOKE_INTERRUPT_DEBUG:
+ r = vcpu->arch.msr & MSR_DE;
+ break;
+ default:
+ r = 1;
+ }
+
+ return r;
+}
+
+static void kvmppc_deliver_interrupt(struct kvm_vcpu *vcpu, int interrupt)
+{
+ switch (interrupt) {
+ case BOOKE_INTERRUPT_DECREMENTER:
+ vcpu->arch.tsr |= TSR_DIS;
+ break;
+ }
+
+ vcpu->arch.srr0 = vcpu->arch.pc;
+ vcpu->arch.srr1 = vcpu->arch.msr;
+ vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[interrupt];
+ kvmppc_set_msr(vcpu, vcpu->arch.msr & interrupt_msr_mask[interrupt]);
+}
+
+/* Check pending exceptions and deliver one, if possible. */
+void kvmppc_check_and_deliver_interrupts(struct kvm_vcpu *vcpu)
+{
+ unsigned long *pending = &vcpu->arch.pending_exceptions;
+ unsigned int exception;
+ unsigned int priority;
+
+ priority = find_first_bit(pending, BITS_PER_BYTE * sizeof(*pending));
+ while (priority <= BOOKE_MAX_INTERRUPT) {
+ exception = priority_exception[priority];
+ if (kvmppc_can_deliver_interrupt(vcpu, exception)) {
+ kvmppc_clear_exception(vcpu, exception);
+ kvmppc_deliver_interrupt(vcpu, exception);
+ break;
+ }
+
+ priority = find_next_bit(pending,
+ BITS_PER_BYTE * sizeof(*pending),
+ priority + 1);
+ }
+}
+
+static int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+ enum emulation_result er;
+ int r;
+
+ er = kvmppc_emulate_instruction(run, vcpu);
+ switch (er) {
+ case EMULATE_DONE:
+ /* Future optimization: only reload non-volatiles if they were
+ * actually modified. */
+ r = RESUME_GUEST_NV;
+ break;
+ case EMULATE_DO_MMIO:
+ run->exit_reason = KVM_EXIT_MMIO;
+ /* We must reload nonvolatiles because "update" load/store
+ * instructions modify register state. */
+ /* Future optimization: only reload non-volatiles if they were
+ * actually modified. */
+ r = RESUME_HOST_NV;
+ break;
+ case EMULATE_FAIL:
+ /* XXX Deliver Program interrupt to guest. */
+ printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__,
+ vcpu->arch.last_inst);
+ r = RESUME_HOST;
+ break;
+ default:
+ BUG();
+ }
+
+ return r;
+}
+
+/**
+ * kvmppc_handle_exit
+ *
+ * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
+ */
+int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int exit_nr)
+{
+ enum emulation_result er;
+ int r = RESUME_HOST;
+
+ local_irq_enable();
+
+ run->exit_reason = KVM_EXIT_UNKNOWN;
+ run->ready_for_interrupt_injection = 1;
+
+ switch (exit_nr) {
+ case BOOKE_INTERRUPT_MACHINE_CHECK:
+ printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
+ kvmppc_dump_vcpu(vcpu);
+ r = RESUME_HOST;
+ break;
+
+ case BOOKE_INTERRUPT_EXTERNAL:
+ case BOOKE_INTERRUPT_DECREMENTER:
+ /* Since we switched IVPR back to the host's value, the host
+ * handled this interrupt the moment we enabled interrupts.
+ * Now we just offer it a chance to reschedule the guest. */
+
+ /* XXX At this point the TLB still holds our shadow TLB, so if
+ * we do reschedule the host will fault over it. Perhaps we
+ * should politely restore the host's entries to minimize
+ * misses before ceding control. */
+ if (need_resched())
+ cond_resched();
+ if (exit_nr == BOOKE_INTERRUPT_DECREMENTER)
+ vcpu->stat.dec_exits++;
+ else
+ vcpu->stat.ext_intr_exits++;
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_PROGRAM:
+ if (vcpu->arch.msr & MSR_PR) {
+ /* Program traps generated by user-level software must be handled
+ * by the guest kernel. */
+ vcpu->arch.esr = vcpu->arch.fault_esr;
+ kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_PROGRAM);
+ r = RESUME_GUEST;
+ break;
+ }
+
+ er = kvmppc_emulate_instruction(run, vcpu);
+ switch (er) {
+ case EMULATE_DONE:
+ /* Future optimization: only reload non-volatiles if
+ * they were actually modified by emulation. */
+ vcpu->stat.emulated_inst_exits++;
+ r = RESUME_GUEST_NV;
+ break;
+ case EMULATE_DO_DCR:
+ run->exit_reason = KVM_EXIT_DCR;
+ r = RESUME_HOST;
+ break;
+ case EMULATE_FAIL:
+ /* XXX Deliver Program interrupt to guest. */
+ printk(KERN_CRIT "%s: emulation at %x failed (%08x)\n",
+ __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+ /* For debugging, encode the failing instruction and
+ * report it to userspace. */
+ run->hw.hardware_exit_reason = ~0ULL << 32;
+ run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
+ r = RESUME_HOST;
+ break;
+ default:
+ BUG();
+ }
+ break;
+
+ case BOOKE_INTERRUPT_DATA_STORAGE:
+ vcpu->arch.dear = vcpu->arch.fault_dear;
+ vcpu->arch.esr = vcpu->arch.fault_esr;
+ kvmppc_queue_exception(vcpu, exit_nr);
+ vcpu->stat.dsi_exits++;
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_INST_STORAGE:
+ vcpu->arch.esr = vcpu->arch.fault_esr;
+ kvmppc_queue_exception(vcpu, exit_nr);
+ vcpu->stat.isi_exits++;
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_SYSCALL:
+ kvmppc_queue_exception(vcpu, exit_nr);
+ vcpu->stat.syscall_exits++;
+ r = RESUME_GUEST;
+ break;
+
+ case BOOKE_INTERRUPT_DTLB_MISS: {
+ struct tlbe *gtlbe;
+ unsigned long eaddr = vcpu->arch.fault_dear;
+ gfn_t gfn;
+
+ /* Check the guest TLB. */
+ gtlbe = kvmppc_44x_dtlb_search(vcpu, eaddr);
+ if (!gtlbe) {
+ /* The guest didn't have a mapping for it. */
+ kvmppc_queue_exception(vcpu, exit_nr);
+ vcpu->arch.dear = vcpu->arch.fault_dear;
+ vcpu->arch.esr = vcpu->arch.fault_esr;
+ vcpu->stat.dtlb_real_miss_exits++;
+ r = RESUME_GUEST;
+ break;
+ }
+
+ vcpu->arch.paddr_accessed = tlb_xlate(gtlbe, eaddr);
+ gfn = vcpu->arch.paddr_accessed >> PAGE_SHIFT;
+
+ if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+ /* The guest TLB had a mapping, but the shadow TLB
+ * didn't, and it is RAM. This could be because:
+ * a) the entry is mapping the host kernel, or
+ * b) the guest used a large mapping which we're faking
+ * Either way, we need to satisfy the fault without
+ * invoking the guest. */
+ kvmppc_mmu_map(vcpu, eaddr, gfn, gtlbe->tid,
+ gtlbe->word2);
+ vcpu->stat.dtlb_virt_miss_exits++;
+ r = RESUME_GUEST;
+ } else {
+ /* Guest has mapped and accessed a page which is not
+ * actually RAM. */
+ r = kvmppc_emulate_mmio(run, vcpu);
+ }
+
+ break;
+ }
+
+ case BOOKE_INTERRUPT_ITLB_MISS: {
+ struct tlbe *gtlbe;
+ unsigned long eaddr = vcpu->arch.pc;
+ gfn_t gfn;
+
+ r = RESUME_GUEST;
+
+ /* Check the guest TLB. */
+ gtlbe = kvmppc_44x_itlb_search(vcpu, eaddr);
+ if (!gtlbe) {
+ /* The guest didn't have a mapping for it. */
+ kvmppc_queue_exception(vcpu, exit_nr);
+ vcpu->stat.itlb_real_miss_exits++;
+ break;
+ }
+
+ vcpu->stat.itlb_virt_miss_exits++;
+
+ gfn = tlb_xlate(gtlbe, eaddr) >> PAGE_SHIFT;
+
+ if (kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+ /* The guest TLB had a mapping, but the shadow TLB
+ * didn't. This could be because:
+ * a) the entry is mapping the host kernel, or
+ * b) the guest used a large mapping which we're faking
+ * Either way, we need to satisfy the fault without
+ * invoking the guest. */
+ kvmppc_mmu_map(vcpu, eaddr, gfn, gtlbe->tid,
+ gtlbe->word2);
+ } else {
+ /* Guest mapped and leaped at non-RAM! */
+ kvmppc_queue_exception(vcpu,
+ BOOKE_INTERRUPT_MACHINE_CHECK);
+ }
+
+ break;
+ }
+
+ default:
+ printk(KERN_EMERG "exit_nr %d\n", exit_nr);
+ BUG();
+ }
+
+ local_irq_disable();
+
+ kvmppc_check_and_deliver_interrupts(vcpu);
+
+ /* Do some exit accounting. */
+ vcpu->stat.sum_exits++;
+ if (!(r & RESUME_HOST)) {
+ /* To avoid clobbering exit_reason, only check for signals if
+ * we aren't already exiting to userspace for some other
+ * reason. */
+ if (signal_pending(current)) {
+ run->exit_reason = KVM_EXIT_INTR;
+ r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
+
+ vcpu->stat.signal_exits++;
+ } else {
+ vcpu->stat.light_exits++;
+ }
+ } else {
+ switch (run->exit_reason) {
+ case KVM_EXIT_MMIO:
+ vcpu->stat.mmio_exits++;
+ break;
+ case KVM_EXIT_DCR:
+ vcpu->stat.dcr_exits++;
+ break;
+ case KVM_EXIT_INTR:
+ vcpu->stat.signal_exits++;
+ break;
+ }
+ }
+
+ return r;
+}
+
+/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ struct tlbe *tlbe = &vcpu->arch.guest_tlb[0];
+
+ tlbe->tid = 0;
+ tlbe->word0 = PPC44x_TLB_16M | PPC44x_TLB_VALID;
+ tlbe->word1 = 0;
+ tlbe->word2 = PPC44x_TLB_SX | PPC44x_TLB_SW | PPC44x_TLB_SR;
+
+ tlbe++;
+ tlbe->tid = 0;
+ tlbe->word0 = 0xef600000 | PPC44x_TLB_4K | PPC44x_TLB_VALID;
+ tlbe->word1 = 0xef600000;
+ tlbe->word2 = PPC44x_TLB_SX | PPC44x_TLB_SW | PPC44x_TLB_SR
+ | PPC44x_TLB_I | PPC44x_TLB_G;
+
+ vcpu->arch.pc = 0;
+ vcpu->arch.msr = 0;
+ vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */
+
+ /* Eye-catching number so we know if the guest takes an interrupt
+ * before it's programmed its own IVPR. */
+ vcpu->arch.ivpr = 0x55550000;
+
+ /* Since the guest can directly access the timebase, it must know the
+ * real timebase frequency. Accordingly, it must see the state of
+ * CCR1[TCS]. */
+ vcpu->arch.ccr1 = mfspr(SPRN_CCR1);
+
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ int i;
+
+ regs->pc = vcpu->arch.pc;
+ regs->cr = vcpu->arch.cr;
+ regs->ctr = vcpu->arch.ctr;
+ regs->lr = vcpu->arch.lr;
+ regs->xer = vcpu->arch.xer;
+ regs->msr = vcpu->arch.msr;
+ regs->srr0 = vcpu->arch.srr0;
+ regs->srr1 = vcpu->arch.srr1;
+ regs->pid = vcpu->arch.pid;
+ regs->sprg0 = vcpu->arch.sprg0;
+ regs->sprg1 = vcpu->arch.sprg1;
+ regs->sprg2 = vcpu->arch.sprg2;
+ regs->sprg3 = vcpu->arch.sprg3;
+ regs->sprg5 = vcpu->arch.sprg4;
+ regs->sprg6 = vcpu->arch.sprg5;
+ regs->sprg7 = vcpu->arch.sprg6;
+
+ for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+ regs->gpr[i] = vcpu->arch.gpr[i];
+
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ int i;
+
+ vcpu->arch.pc = regs->pc;
+ vcpu->arch.cr = regs->cr;
+ vcpu->arch.ctr = regs->ctr;
+ vcpu->arch.lr = regs->lr;
+ vcpu->arch.xer = regs->xer;
+ vcpu->arch.msr = regs->msr;
+ vcpu->arch.srr0 = regs->srr0;
+ vcpu->arch.srr1 = regs->srr1;
+ vcpu->arch.sprg0 = regs->sprg0;
+ vcpu->arch.sprg1 = regs->sprg1;
+ vcpu->arch.sprg2 = regs->sprg2;
+ vcpu->arch.sprg3 = regs->sprg3;
+ vcpu->arch.sprg5 = regs->sprg4;
+ vcpu->arch.sprg6 = regs->sprg5;
+ vcpu->arch.sprg7 = regs->sprg6;
+
+ for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
+ vcpu->arch.gpr[i] = regs->gpr[i];
+
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -ENOTSUPP;
+}
+
+/* 'linear_address' is actually an encoding of AS|PID|EADDR . */
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
+{
+ struct tlbe *gtlbe;
+ int index;
+ gva_t eaddr;
+ u8 pid;
+ u8 as;
+
+ eaddr = tr->linear_address;
+ pid = (tr->linear_address >> 32) & 0xff;
+ as = (tr->linear_address >> 40) & 0x1;
+
+ index = kvmppc_44x_tlb_index(vcpu, eaddr, pid, as);
+ if (index == -1) {
+ tr->valid = 0;
+ return 0;
+ }
+
+ gtlbe = &vcpu->arch.guest_tlb[index];
+
+ tr->physical_address = tlb_xlate(gtlbe, eaddr);
+ /* XXX what does "writeable" and "usermode" even mean? */
+ tr->valid = 1;
+
+ return 0;
+}
diff --git a/arch/powerpc/kvm/booke_host.c b/arch/powerpc/kvm/booke_host.c
new file mode 100644
index 00000000000..b480341bc31
--- /dev/null
+++ b/arch/powerpc/kvm/booke_host.c
@@ -0,0 +1,83 @@
+/*
+ * 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. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/kvm_ppc.h>
+
+unsigned long kvmppc_booke_handlers;
+
+static int kvmppc_booke_init(void)
+{
+ unsigned long ivor[16];
+ unsigned long max_ivor = 0;
+ int i;
+
+ /* We install our own exception handlers by hijacking IVPR. IVPR must
+ * be 16-bit aligned, so we need a 64KB allocation. */
+ kvmppc_booke_handlers = __get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ VCPU_SIZE_ORDER);
+ if (!kvmppc_booke_handlers)
+ return -ENOMEM;
+
+ /* XXX make sure our handlers are smaller than Linux's */
+
+ /* Copy our interrupt handlers to match host IVORs. That way we don't
+ * have to swap the IVORs on every guest/host transition. */
+ ivor[0] = mfspr(SPRN_IVOR0);
+ ivor[1] = mfspr(SPRN_IVOR1);
+ ivor[2] = mfspr(SPRN_IVOR2);
+ ivor[3] = mfspr(SPRN_IVOR3);
+ ivor[4] = mfspr(SPRN_IVOR4);
+ ivor[5] = mfspr(SPRN_IVOR5);
+ ivor[6] = mfspr(SPRN_IVOR6);
+ ivor[7] = mfspr(SPRN_IVOR7);
+ ivor[8] = mfspr(SPRN_IVOR8);
+ ivor[9] = mfspr(SPRN_IVOR9);
+ ivor[10] = mfspr(SPRN_IVOR10);
+ ivor[11] = mfspr(SPRN_IVOR11);
+ ivor[12] = mfspr(SPRN_IVOR12);
+ ivor[13] = mfspr(SPRN_IVOR13);
+ ivor[14] = mfspr(SPRN_IVOR14);
+ ivor[15] = mfspr(SPRN_IVOR15);
+
+ for (i = 0; i < 16; i++) {
+ if (ivor[i] > max_ivor)
+ max_ivor = ivor[i];
+
+ memcpy((void *)kvmppc_booke_handlers + ivor[i],
+ kvmppc_handlers_start + i * kvmppc_handler_len,
+ kvmppc_handler_len);
+ }
+ flush_icache_range(kvmppc_booke_handlers,
+ kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
+ return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+}
+
+static void __exit kvmppc_booke_exit(void)
+{
+ free_pages(kvmppc_booke_handlers, VCPU_SIZE_ORDER);
+ kvm_exit();
+}
+
+module_init(kvmppc_booke_init)
+module_exit(kvmppc_booke_exit)
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
new file mode 100644
index 00000000000..3b653b5309b
--- /dev/null
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -0,0 +1,436 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/mmu-44x.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+
+#define KVMPPC_MSR_MASK (MSR_CE|MSR_EE|MSR_PR|MSR_DE|MSR_ME|MSR_IS|MSR_DS)
+
+#define VCPU_GPR(n) (VCPU_GPRS + (n * 4))
+
+/* The host stack layout: */
+#define HOST_R1 0 /* Implied by stwu. */
+#define HOST_CALLEE_LR 4
+#define HOST_RUN 8
+/* r2 is special: it holds 'current', and it made nonvolatile in the
+ * kernel with the -ffixed-r2 gcc option. */
+#define HOST_R2 12
+#define HOST_NV_GPRS 16
+#define HOST_NV_GPR(n) (HOST_NV_GPRS + ((n - 14) * 4))
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + 4)
+#define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */
+#define HOST_STACK_LR (HOST_STACK_SIZE + 4) /* In caller stack frame. */
+
+#define NEED_INST_MASK ((1<<BOOKE_INTERRUPT_PROGRAM) | \
+ (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+#define NEED_DEAR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+ (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+#define NEED_ESR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
+ (1<<BOOKE_INTERRUPT_INST_STORAGE) | \
+ (1<<BOOKE_INTERRUPT_PROGRAM) | \
+ (1<<BOOKE_INTERRUPT_DTLB_MISS))
+
+.macro KVM_HANDLER ivor_nr
+_GLOBAL(kvmppc_handler_\ivor_nr)
+ /* Get pointer to vcpu and record exit number. */
+ mtspr SPRN_SPRG0, r4
+ mfspr r4, SPRN_SPRG1
+ stw r5, VCPU_GPR(r5)(r4)
+ stw r6, VCPU_GPR(r6)(r4)
+ mfctr r5
+ lis r6, kvmppc_resume_host@h
+ stw r5, VCPU_CTR(r4)
+ li r5, \ivor_nr
+ ori r6, r6, kvmppc_resume_host@l
+ mtctr r6
+ bctr
+.endm
+
+_GLOBAL(kvmppc_handlers_start)
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER
+KVM_HANDLER BOOKE_INTERRUPT_FIT
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
+KVM_HANDLER BOOKE_INTERRUPT_DEBUG
+
+_GLOBAL(kvmppc_handler_len)
+ .long kvmppc_handler_1 - kvmppc_handler_0
+
+
+/* Registers:
+ * SPRG0: guest r4
+ * r4: vcpu pointer
+ * r5: KVM exit number
+ */
+_GLOBAL(kvmppc_resume_host)
+ stw r3, VCPU_GPR(r3)(r4)
+ mfcr r3
+ stw r3, VCPU_CR(r4)
+ stw r7, VCPU_GPR(r7)(r4)
+ stw r8, VCPU_GPR(r8)(r4)
+ stw r9, VCPU_GPR(r9)(r4)
+
+ li r6, 1
+ slw r6, r6, r5
+
+ /* Save the faulting instruction and all GPRs for emulation. */
+ andi. r7, r6, NEED_INST_MASK
+ beq ..skip_inst_copy
+ mfspr r9, SPRN_SRR0
+ mfmsr r8
+ ori r7, r8, MSR_DS
+ mtmsr r7
+ isync
+ lwz r9, 0(r9)
+ mtmsr r8
+ isync
+ stw r9, VCPU_LAST_INST(r4)
+
+ stw r15, VCPU_GPR(r15)(r4)
+ stw r16, VCPU_GPR(r16)(r4)
+ stw r17, VCPU_GPR(r17)(r4)
+ stw r18, VCPU_GPR(r18)(r4)
+ stw r19, VCPU_GPR(r19)(r4)
+ stw r20, VCPU_GPR(r20)(r4)
+ stw r21, VCPU_GPR(r21)(r4)
+ stw r22, VCPU_GPR(r22)(r4)
+ stw r23, VCPU_GPR(r23)(r4)
+ stw r24, VCPU_GPR(r24)(r4)
+ stw r25, VCPU_GPR(r25)(r4)
+ stw r26, VCPU_GPR(r26)(r4)
+ stw r27, VCPU_GPR(r27)(r4)
+ stw r28, VCPU_GPR(r28)(r4)
+ stw r29, VCPU_GPR(r29)(r4)
+ stw r30, VCPU_GPR(r30)(r4)
+ stw r31, VCPU_GPR(r31)(r4)
+..skip_inst_copy:
+
+ /* Also grab DEAR and ESR before the host can clobber them. */
+
+ andi. r7, r6, NEED_DEAR_MASK
+ beq ..skip_dear
+ mfspr r9, SPRN_DEAR
+ stw r9, VCPU_FAULT_DEAR(r4)
+..skip_dear:
+
+ andi. r7, r6, NEED_ESR_MASK
+ beq ..skip_esr
+ mfspr r9, SPRN_ESR
+ stw r9, VCPU_FAULT_ESR(r4)
+..skip_esr:
+
+ /* Save remaining volatile guest register state to vcpu. */
+ stw r0, VCPU_GPR(r0)(r4)
+ stw r1, VCPU_GPR(r1)(r4)
+ stw r2, VCPU_GPR(r2)(r4)
+ stw r10, VCPU_GPR(r10)(r4)
+ stw r11, VCPU_GPR(r11)(r4)
+ stw r12, VCPU_GPR(r12)(r4)
+ stw r13, VCPU_GPR(r13)(r4)
+ stw r14, VCPU_GPR(r14)(r4) /* We need a NV GPR below. */
+ mflr r3
+ stw r3, VCPU_LR(r4)
+ mfxer r3
+ stw r3, VCPU_XER(r4)
+ mfspr r3, SPRN_SPRG0
+ stw r3, VCPU_GPR(r4)(r4)
+ mfspr r3, SPRN_SRR0
+ stw r3, VCPU_PC(r4)
+
+ /* Restore host stack pointer and PID before IVPR, since the host
+ * exception handlers use them. */
+ lwz r1, VCPU_HOST_STACK(r4)
+ lwz r3, VCPU_HOST_PID(r4)
+ mtspr SPRN_PID, r3
+
+ /* Restore host IVPR before re-enabling interrupts. We cheat and know
+ * that Linux IVPR is always 0xc0000000. */
+ lis r3, 0xc000
+ mtspr SPRN_IVPR, r3
+
+ /* Switch to kernel stack and jump to handler. */
+ LOAD_REG_ADDR(r3, kvmppc_handle_exit)
+ mtctr r3
+ lwz r3, HOST_RUN(r1)
+ lwz r2, HOST_R2(r1)
+ mr r14, r4 /* Save vcpu pointer. */
+
+ bctrl /* kvmppc_handle_exit() */
+
+ /* Restore vcpu pointer and the nonvolatiles we used. */
+ mr r4, r14
+ lwz r14, VCPU_GPR(r14)(r4)
+
+ /* Sometimes instruction emulation must restore complete GPR state. */
+ andi. r5, r3, RESUME_FLAG_NV
+ beq ..skip_nv_load
+ lwz r15, VCPU_GPR(r15)(r4)
+ lwz r16, VCPU_GPR(r16)(r4)
+ lwz r17, VCPU_GPR(r17)(r4)
+ lwz r18, VCPU_GPR(r18)(r4)
+ lwz r19, VCPU_GPR(r19)(r4)
+ lwz r20, VCPU_GPR(r20)(r4)
+ lwz r21, VCPU_GPR(r21)(r4)
+ lwz r22, VCPU_GPR(r22)(r4)
+ lwz r23, VCPU_GPR(r23)(r4)
+ lwz r24, VCPU_GPR(r24)(r4)
+ lwz r25, VCPU_GPR(r25)(r4)
+ lwz r26, VCPU_GPR(r26)(r4)
+ lwz r27, VCPU_GPR(r27)(r4)
+ lwz r28, VCPU_GPR(r28)(r4)
+ lwz r29, VCPU_GPR(r29)(r4)
+ lwz r30, VCPU_GPR(r30)(r4)
+ lwz r31, VCPU_GPR(r31)(r4)
+..skip_nv_load:
+
+ /* Should we return to the guest? */
+ andi. r5, r3, RESUME_FLAG_HOST
+ beq lightweight_exit
+
+ srawi r3, r3, 2 /* Shift -ERR back down. */
+
+heavyweight_exit:
+ /* Not returning to guest. */
+
+ /* We already saved guest volatile register state; now save the
+ * non-volatiles. */
+ stw r15, VCPU_GPR(r15)(r4)
+ stw r16, VCPU_GPR(r16)(r4)
+ stw r17, VCPU_GPR(r17)(r4)
+ stw r18, VCPU_GPR(r18)(r4)
+ stw r19, VCPU_GPR(r19)(r4)
+ stw r20, VCPU_GPR(r20)(r4)
+ stw r21, VCPU_GPR(r21)(r4)
+ stw r22, VCPU_GPR(r22)(r4)
+ stw r23, VCPU_GPR(r23)(r4)
+ stw r24, VCPU_GPR(r24)(r4)
+ stw r25, VCPU_GPR(r25)(r4)
+ stw r26, VCPU_GPR(r26)(r4)
+ stw r27, VCPU_GPR(r27)(r4)
+ stw r28, VCPU_GPR(r28)(r4)
+ stw r29, VCPU_GPR(r29)(r4)
+ stw r30, VCPU_GPR(r30)(r4)
+ stw r31, VCPU_GPR(r31)(r4)
+
+ /* Load host non-volatile register state from host stack. */
+ lwz r14, HOST_NV_GPR(r14)(r1)
+ lwz r15, HOST_NV_GPR(r15)(r1)
+ lwz r16, HOST_NV_GPR(r16)(r1)
+ lwz r17, HOST_NV_GPR(r17)(r1)
+ lwz r18, HOST_NV_GPR(r18)(r1)
+ lwz r19, HOST_NV_GPR(r19)(r1)
+ lwz r20, HOST_NV_GPR(r20)(r1)
+ lwz r21, HOST_NV_GPR(r21)(r1)
+ lwz r22, HOST_NV_GPR(r22)(r1)
+ lwz r23, HOST_NV_GPR(r23)(r1)
+ lwz r24, HOST_NV_GPR(r24)(r1)
+ lwz r25, HOST_NV_GPR(r25)(r1)
+ lwz r26, HOST_NV_GPR(r26)(r1)
+ lwz r27, HOST_NV_GPR(r27)(r1)
+ lwz r28, HOST_NV_GPR(r28)(r1)
+ lwz r29, HOST_NV_GPR(r29)(r1)
+ lwz r30, HOST_NV_GPR(r30)(r1)
+ lwz r31, HOST_NV_GPR(r31)(r1)
+
+ /* Return to kvm_vcpu_run(). */
+ lwz r4, HOST_STACK_LR(r1)
+ addi r1, r1, HOST_STACK_SIZE
+ mtlr r4
+ /* r3 still contains the return code from kvmppc_handle_exit(). */
+ blr
+
+
+/* Registers:
+ * r3: kvm_run pointer
+ * r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_run)
+ stwu r1, -HOST_STACK_SIZE(r1)
+ stw r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */
+
+ /* Save host state to stack. */
+ stw r3, HOST_RUN(r1)
+ mflr r3
+ stw r3, HOST_STACK_LR(r1)
+
+ /* Save host non-volatile register state to stack. */
+ stw r14, HOST_NV_GPR(r14)(r1)
+ stw r15, HOST_NV_GPR(r15)(r1)
+ stw r16, HOST_NV_GPR(r16)(r1)
+ stw r17, HOST_NV_GPR(r17)(r1)
+ stw r18, HOST_NV_GPR(r18)(r1)
+ stw r19, HOST_NV_GPR(r19)(r1)
+ stw r20, HOST_NV_GPR(r20)(r1)
+ stw r21, HOST_NV_GPR(r21)(r1)
+ stw r22, HOST_NV_GPR(r22)(r1)
+ stw r23, HOST_NV_GPR(r23)(r1)
+ stw r24, HOST_NV_GPR(r24)(r1)
+ stw r25, HOST_NV_GPR(r25)(r1)
+ stw r26, HOST_NV_GPR(r26)(r1)
+ stw r27, HOST_NV_GPR(r27)(r1)
+ stw r28, HOST_NV_GPR(r28)(r1)
+ stw r29, HOST_NV_GPR(r29)(r1)
+ stw r30, HOST_NV_GPR(r30)(r1)
+ stw r31, HOST_NV_GPR(r31)(r1)
+
+ /* Load guest non-volatiles. */
+ lwz r14, VCPU_GPR(r14)(r4)
+ lwz r15, VCPU_GPR(r15)(r4)
+ lwz r16, VCPU_GPR(r16)(r4)
+ lwz r17, VCPU_GPR(r17)(r4)
+ lwz r18, VCPU_GPR(r18)(r4)
+ lwz r19, VCPU_GPR(r19)(r4)
+ lwz r20, VCPU_GPR(r20)(r4)
+ lwz r21, VCPU_GPR(r21)(r4)
+ lwz r22, VCPU_GPR(r22)(r4)
+ lwz r23, VCPU_GPR(r23)(r4)
+ lwz r24, VCPU_GPR(r24)(r4)
+ lwz r25, VCPU_GPR(r25)(r4)
+ lwz r26, VCPU_GPR(r26)(r4)
+ lwz r27, VCPU_GPR(r27)(r4)
+ lwz r28, VCPU_GPR(r28)(r4)
+ lwz r29, VCPU_GPR(r29)(r4)
+ lwz r30, VCPU_GPR(r30)(r4)
+ lwz r31, VCPU_GPR(r31)(r4)
+
+lightweight_exit:
+ stw r2, HOST_R2(r1)
+
+ mfspr r3, SPRN_PID
+ stw r3, VCPU_HOST_PID(r4)
+ lwz r3, VCPU_PID(r4)
+ mtspr SPRN_PID, r3
+
+ /* Prevent all TLB updates. */
+ mfmsr r5
+ lis r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@h
+ ori r6, r6, (MSR_EE|MSR_CE|MSR_ME|MSR_DE)@l
+ andc r6, r5, r6
+ mtmsr r6
+
+ /* Save the host's non-pinned TLB mappings, and load the guest mappings
+ * over them. Leave the host's "pinned" kernel mappings in place. */
+ /* XXX optimization: use generation count to avoid swapping unmodified
+ * entries. */
+ mfspr r10, SPRN_MMUCR /* Save host MMUCR. */
+ lis r8, tlb_44x_hwater@ha
+ lwz r8, tlb_44x_hwater@l(r8)
+ addi r3, r4, VCPU_HOST_TLB - 4
+ addi r9, r4, VCPU_SHADOW_TLB - 4
+ li r6, 0
+1:
+ /* Save host entry. */
+ tlbre r7, r6, PPC44x_TLB_PAGEID
+ mfspr r5, SPRN_MMUCR
+ stwu r5, 4(r3)
+ stwu r7, 4(r3)
+ tlbre r7, r6, PPC44x_TLB_XLAT
+ stwu r7, 4(r3)
+ tlbre r7, r6, PPC44x_TLB_ATTRIB
+ stwu r7, 4(r3)
+ /* Load guest entry. */
+ lwzu r7, 4(r9)
+ mtspr SPRN_MMUCR, r7
+ lwzu r7, 4(r9)
+ tlbwe r7, r6, PPC44x_TLB_PAGEID
+ lwzu r7, 4(r9)
+ tlbwe r7, r6, PPC44x_TLB_XLAT
+ lwzu r7, 4(r9)
+ tlbwe r7, r6, PPC44x_TLB_ATTRIB
+ /* Increment index. */
+ addi r6, r6, 1
+ cmpw r6, r8
+ blt 1b
+ mtspr SPRN_MMUCR, r10 /* Restore host MMUCR. */
+
+ iccci 0, 0 /* XXX hack */
+
+ /* Load some guest volatiles. */
+ lwz r0, VCPU_GPR(r0)(r4)
+ lwz r2, VCPU_GPR(r2)(r4)
+ lwz r9, VCPU_GPR(r9)(r4)
+ lwz r10, VCPU_GPR(r10)(r4)
+ lwz r11, VCPU_GPR(r11)(r4)
+ lwz r12, VCPU_GPR(r12)(r4)
+ lwz r13, VCPU_GPR(r13)(r4)
+ lwz r3, VCPU_LR(r4)
+ mtlr r3
+ lwz r3, VCPU_XER(r4)
+ mtxer r3
+
+ /* Switch the IVPR. XXX If we take a TLB miss after this we're screwed,
+ * so how do we make sure vcpu won't fault? */
+ lis r8, kvmppc_booke_handlers@ha
+ lwz r8, kvmppc_booke_handlers@l(r8)
+ mtspr SPRN_IVPR, r8
+
+ /* Save vcpu pointer for the exception handlers. */
+ mtspr SPRN_SPRG1, r4
+
+ /* Can't switch the stack pointer until after IVPR is switched,
+ * because host interrupt handlers would get confused. */
+ lwz r1, VCPU_GPR(r1)(r4)
+
+ /* XXX handle USPRG0 */
+ /* Host interrupt handlers may have clobbered these guest-readable
+ * SPRGs, so we need to reload them here with the guest's values. */
+ lwz r3, VCPU_SPRG4(r4)
+ mtspr SPRN_SPRG4, r3
+ lwz r3, VCPU_SPRG5(r4)
+ mtspr SPRN_SPRG5, r3
+ lwz r3, VCPU_SPRG6(r4)
+ mtspr SPRN_SPRG6, r3
+ lwz r3, VCPU_SPRG7(r4)
+ mtspr SPRN_SPRG7, r3
+
+ /* Finish loading guest volatiles and jump to guest. */
+ lwz r3, VCPU_CTR(r4)
+ mtctr r3
+ lwz r3, VCPU_CR(r4)
+ mtcr r3
+ lwz r5, VCPU_GPR(r5)(r4)
+ lwz r6, VCPU_GPR(r6)(r4)
+ lwz r7, VCPU_GPR(r7)(r4)
+ lwz r8, VCPU_GPR(r8)(r4)
+ lwz r3, VCPU_PC(r4)
+ mtsrr0 r3
+ lwz r3, VCPU_MSR(r4)
+ oris r3, r3, KVMPPC_MSR_MASK@h
+ ori r3, r3, KVMPPC_MSR_MASK@l
+ mtsrr1 r3
+ lwz r3, VCPU_GPR(r3)(r4)
+ lwz r4, VCPU_GPR(r4)(r4)
+ rfi
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
new file mode 100644
index 00000000000..a03fe0c8069
--- /dev/null
+++ b/arch/powerpc/kvm/emulate.c
@@ -0,0 +1,760 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#include <linux/jiffies.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm_host.h>
+
+#include <asm/dcr.h>
+#include <asm/dcr-regs.h>
+#include <asm/time.h>
+#include <asm/byteorder.h>
+#include <asm/kvm_ppc.h>
+
+#include "44x_tlb.h"
+
+/* Instruction decoding */
+static inline unsigned int get_op(u32 inst)
+{
+ return inst >> 26;
+}
+
+static inline unsigned int get_xop(u32 inst)
+{
+ return (inst >> 1) & 0x3ff;
+}
+
+static inline unsigned int get_sprn(u32 inst)
+{
+ return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_dcrn(u32 inst)
+{
+ return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_rt(u32 inst)
+{
+ return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_rs(u32 inst)
+{
+ return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_ra(u32 inst)
+{
+ return (inst >> 16) & 0x1f;
+}
+
+static inline unsigned int get_rb(u32 inst)
+{
+ return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_rc(u32 inst)
+{
+ return inst & 0x1;
+}
+
+static inline unsigned int get_ws(u32 inst)
+{
+ return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_d(u32 inst)
+{
+ return inst & 0xffff;
+}
+
+static int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
+ const struct tlbe *tlbe)
+{
+ gpa_t gpa;
+
+ if (!get_tlb_v(tlbe))
+ return 0;
+
+ /* Does it match current guest AS? */
+ /* XXX what about IS != DS? */
+ if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+ return 0;
+
+ gpa = get_tlb_raddr(tlbe);
+ if (!gfn_to_memslot(vcpu->kvm, gpa >> PAGE_SHIFT))
+ /* Mapping is not for RAM. */
+ return 0;
+
+ return 1;
+}
+
+static int kvmppc_emul_tlbwe(struct kvm_vcpu *vcpu, u32 inst)
+{
+ u64 eaddr;
+ u64 raddr;
+ u64 asid;
+ u32 flags;
+ struct tlbe *tlbe;
+ unsigned int ra;
+ unsigned int rs;
+ unsigned int ws;
+ unsigned int index;
+
+ ra = get_ra(inst);
+ rs = get_rs(inst);
+ ws = get_ws(inst);
+
+ index = vcpu->arch.gpr[ra];
+ if (index > PPC44x_TLB_SIZE) {
+ printk("%s: index %d\n", __func__, index);
+ kvmppc_dump_vcpu(vcpu);
+ return EMULATE_FAIL;
+ }
+
+ tlbe = &vcpu->arch.guest_tlb[index];
+
+ /* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
+ if (tlbe->word0 & PPC44x_TLB_VALID) {
+ eaddr = get_tlb_eaddr(tlbe);
+ asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
+ kvmppc_mmu_invalidate(vcpu, eaddr, asid);
+ }
+
+ switch (ws) {
+ case PPC44x_TLB_PAGEID:
+ tlbe->tid = vcpu->arch.mmucr & 0xff;
+ tlbe->word0 = vcpu->arch.gpr[rs];
+ break;
+
+ case PPC44x_TLB_XLAT:
+ tlbe->word1 = vcpu->arch.gpr[rs];
+ break;
+
+ case PPC44x_TLB_ATTRIB:
+ tlbe->word2 = vcpu->arch.gpr[rs];
+ break;
+
+ default:
+ return EMULATE_FAIL;
+ }
+
+ if (tlbe_is_host_safe(vcpu, tlbe)) {
+ eaddr = get_tlb_eaddr(tlbe);
+ raddr = get_tlb_raddr(tlbe);
+ asid = (tlbe->word0 & PPC44x_TLB_TS) | tlbe->tid;
+ flags = tlbe->word2 & 0xffff;
+
+ /* Create a 4KB mapping on the host. If the guest wanted a
+ * large page, only the first 4KB is mapped here and the rest
+ * are mapped on the fly. */
+ kvmppc_mmu_map(vcpu, eaddr, raddr >> PAGE_SHIFT, asid, flags);
+ }
+
+ return EMULATE_DONE;
+}
+
+static void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->arch.tcr & TCR_DIE) {
+ /* The decrementer ticks at the same rate as the timebase, so
+ * that's how we convert the guest DEC value to the number of
+ * host ticks. */
+ unsigned long nr_jiffies;
+
+ nr_jiffies = vcpu->arch.dec / tb_ticks_per_jiffy;
+ mod_timer(&vcpu->arch.dec_timer,
+ get_jiffies_64() + nr_jiffies);
+ } else {
+ del_timer(&vcpu->arch.dec_timer);
+ }
+}
+
+static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pc = vcpu->arch.srr0;
+ kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+}
+
+/* XXX to do:
+ * lhax
+ * lhaux
+ * lswx
+ * lswi
+ * stswx
+ * stswi
+ * lha
+ * lhau
+ * lmw
+ * stmw
+ *
+ * XXX is_bigendian should depend on MMU mapping or MSR[LE]
+ */
+int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+ u32 inst = vcpu->arch.last_inst;
+ u32 ea;
+ int ra;
+ int rb;
+ int rc;
+ int rs;
+ int rt;
+ int sprn;
+ int dcrn;
+ enum emulation_result emulated = EMULATE_DONE;
+ int advance = 1;
+
+ switch (get_op(inst)) {
+ case 3: /* trap */
+ printk("trap!\n");
+ kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_PROGRAM);
+ advance = 0;
+ break;
+
+ case 19:
+ switch (get_xop(inst)) {
+ case 50: /* rfi */
+ kvmppc_emul_rfi(vcpu);
+ advance = 0;
+ break;
+
+ default:
+ emulated = EMULATE_FAIL;
+ break;
+ }
+ break;
+
+ case 31:
+ switch (get_xop(inst)) {
+
+ case 83: /* mfmsr */
+ rt = get_rt(inst);
+ vcpu->arch.gpr[rt] = vcpu->arch.msr;
+ break;
+
+ case 87: /* lbzx */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+ break;
+
+ case 131: /* wrtee */
+ rs = get_rs(inst);
+ vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+ | (vcpu->arch.gpr[rs] & MSR_EE);
+ break;
+
+ case 146: /* mtmsr */
+ rs = get_rs(inst);
+ kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
+ break;
+
+ case 163: /* wrteei */
+ vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+ | (inst & MSR_EE);
+ break;
+
+ case 215: /* stbx */
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 1, 1);
+ break;
+
+ case 247: /* stbux */
+ rs = get_rs(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ ea = vcpu->arch.gpr[rb];
+ if (ra)
+ ea += vcpu->arch.gpr[ra];
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 1, 1);
+ vcpu->arch.gpr[rs] = ea;
+ break;
+
+ case 279: /* lhzx */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+ break;
+
+ case 311: /* lhzux */
+ rt = get_rt(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ ea = vcpu->arch.gpr[rb];
+ if (ra)
+ ea += vcpu->arch.gpr[ra];
+
+ emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+ vcpu->arch.gpr[ra] = ea;
+ break;
+
+ case 323: /* mfdcr */
+ dcrn = get_dcrn(inst);
+ rt = get_rt(inst);
+
+ /* The guest may access CPR0 registers to determine the timebase
+ * frequency, and it must know the real host frequency because it
+ * can directly access the timebase registers.
+ *
+ * It would be possible to emulate those accesses in userspace,
+ * but userspace can really only figure out the end frequency.
+ * We could decompose that into the factors that compute it, but
+ * that's tricky math, and it's easier to just report the real
+ * CPR0 values.
+ */
+ switch (dcrn) {
+ case DCRN_CPR0_CONFIG_ADDR:
+ vcpu->arch.gpr[rt] = vcpu->arch.cpr0_cfgaddr;
+ break;
+ case DCRN_CPR0_CONFIG_DATA:
+ local_irq_disable();
+ mtdcr(DCRN_CPR0_CONFIG_ADDR,
+ vcpu->arch.cpr0_cfgaddr);
+ vcpu->arch.gpr[rt] = mfdcr(DCRN_CPR0_CONFIG_DATA);
+ local_irq_enable();
+ break;
+ default:
+ run->dcr.dcrn = dcrn;
+ run->dcr.data = 0;
+ run->dcr.is_write = 0;
+ vcpu->arch.io_gpr = rt;
+ vcpu->arch.dcr_needed = 1;
+ emulated = EMULATE_DO_DCR;
+ }
+
+ break;
+
+ case 339: /* mfspr */
+ sprn = get_sprn(inst);
+ rt = get_rt(inst);
+
+ switch (sprn) {
+ case SPRN_SRR0:
+ vcpu->arch.gpr[rt] = vcpu->arch.srr0; break;
+ case SPRN_SRR1:
+ vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
+ case SPRN_MMUCR:
+ vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break;
+ case SPRN_PID:
+ vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
+ case SPRN_IVPR:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
+ case SPRN_CCR0:
+ vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break;
+ case SPRN_CCR1:
+ vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break;
+ case SPRN_PVR:
+ vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+ case SPRN_DEAR:
+ vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
+ case SPRN_ESR:
+ vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
+ case SPRN_DBCR0:
+ vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
+ case SPRN_DBCR1:
+ vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+
+ /* Note: mftb and TBRL/TBWL are user-accessible, so
+ * the guest can always access the real TB anyways.
+ * In fact, we probably will never see these traps. */
+ case SPRN_TBWL:
+ vcpu->arch.gpr[rt] = mftbl(); break;
+ case SPRN_TBWU:
+ vcpu->arch.gpr[rt] = mftbu(); break;
+
+ case SPRN_SPRG0:
+ vcpu->arch.gpr[rt] = vcpu->arch.sprg0; break;
+ case SPRN_SPRG1:
+ vcpu->arch.gpr[rt] = vcpu->arch.sprg1; break;
+ case SPRN_SPRG2:
+ vcpu->arch.gpr[rt] = vcpu->arch.sprg2; break;
+ case SPRN_SPRG3:
+ vcpu->arch.gpr[rt] = vcpu->arch.sprg3; break;
+ /* Note: SPRG4-7 are user-readable, so we don't get
+ * a trap. */
+
+ case SPRN_IVOR0:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[0]; break;
+ case SPRN_IVOR1:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[1]; break;
+ case SPRN_IVOR2:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[2]; break;
+ case SPRN_IVOR3:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[3]; break;
+ case SPRN_IVOR4:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[4]; break;
+ case SPRN_IVOR5:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[5]; break;
+ case SPRN_IVOR6:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[6]; break;
+ case SPRN_IVOR7:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[7]; break;
+ case SPRN_IVOR8:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[8]; break;
+ case SPRN_IVOR9:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[9]; break;
+ case SPRN_IVOR10:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[10]; break;
+ case SPRN_IVOR11:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[11]; break;
+ case SPRN_IVOR12:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[12]; break;
+ case SPRN_IVOR13:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[13]; break;
+ case SPRN_IVOR14:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[14]; break;
+ case SPRN_IVOR15:
+ vcpu->arch.gpr[rt] = vcpu->arch.ivor[15]; break;
+
+ default:
+ printk("mfspr: unknown spr %x\n", sprn);
+ vcpu->arch.gpr[rt] = 0;
+ break;
+ }
+ break;
+
+ case 407: /* sthx */
+ rs = get_rs(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 2, 1);
+ break;
+
+ case 439: /* sthux */
+ rs = get_rs(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ ea = vcpu->arch.gpr[rb];
+ if (ra)
+ ea += vcpu->arch.gpr[ra];
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 2, 1);
+ vcpu->arch.gpr[ra] = ea;
+ break;
+
+ case 451: /* mtdcr */
+ dcrn = get_dcrn(inst);
+ rs = get_rs(inst);
+
+ /* emulate some access in kernel */
+ switch (dcrn) {
+ case DCRN_CPR0_CONFIG_ADDR:
+ vcpu->arch.cpr0_cfgaddr = vcpu->arch.gpr[rs];
+ break;
+ default:
+ run->dcr.dcrn = dcrn;
+ run->dcr.data = vcpu->arch.gpr[rs];
+ run->dcr.is_write = 1;
+ vcpu->arch.dcr_needed = 1;
+ emulated = EMULATE_DO_DCR;
+ }
+
+ break;
+
+ case 467: /* mtspr */
+ sprn = get_sprn(inst);
+ rs = get_rs(inst);
+ switch (sprn) {
+ case SPRN_SRR0:
+ vcpu->arch.srr0 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SRR1:
+ vcpu->arch.srr1 = vcpu->arch.gpr[rs]; break;
+ case SPRN_MMUCR:
+ vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
+ case SPRN_PID:
+ vcpu->arch.pid = vcpu->arch.gpr[rs]; break;
+ case SPRN_CCR0:
+ vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break;
+ case SPRN_CCR1:
+ vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break;
+ case SPRN_DEAR:
+ vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
+ case SPRN_ESR:
+ vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
+ case SPRN_DBCR0:
+ vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
+ case SPRN_DBCR1:
+ vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+
+ /* XXX We need to context-switch the timebase for
+ * watchdog and FIT. */
+ case SPRN_TBWL: break;
+ case SPRN_TBWU: break;
+
+ case SPRN_DEC:
+ vcpu->arch.dec = vcpu->arch.gpr[rs];
+ kvmppc_emulate_dec(vcpu);
+ break;
+
+ case SPRN_TSR:
+ vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
+
+ case SPRN_TCR:
+ vcpu->arch.tcr = vcpu->arch.gpr[rs];
+ kvmppc_emulate_dec(vcpu);
+ break;
+
+ case SPRN_SPRG0:
+ vcpu->arch.sprg0 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG1:
+ vcpu->arch.sprg1 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG2:
+ vcpu->arch.sprg2 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG3:
+ vcpu->arch.sprg3 = vcpu->arch.gpr[rs]; break;
+
+ /* Note: SPRG4-7 are user-readable. These values are
+ * loaded into the real SPRGs when resuming the
+ * guest. */
+ case SPRN_SPRG4:
+ vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG5:
+ vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG6:
+ vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
+ case SPRN_SPRG7:
+ vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
+
+ case SPRN_IVPR:
+ vcpu->arch.ivpr = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR0:
+ vcpu->arch.ivor[0] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR1:
+ vcpu->arch.ivor[1] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR2:
+ vcpu->arch.ivor[2] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR3:
+ vcpu->arch.ivor[3] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR4:
+ vcpu->arch.ivor[4] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR5:
+ vcpu->arch.ivor[5] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR6:
+ vcpu->arch.ivor[6] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR7:
+ vcpu->arch.ivor[7] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR8:
+ vcpu->arch.ivor[8] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR9:
+ vcpu->arch.ivor[9] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR10:
+ vcpu->arch.ivor[10] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR11:
+ vcpu->arch.ivor[11] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR12:
+ vcpu->arch.ivor[12] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR13:
+ vcpu->arch.ivor[13] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR14:
+ vcpu->arch.ivor[14] = vcpu->arch.gpr[rs]; break;
+ case SPRN_IVOR15:
+ vcpu->arch.ivor[15] = vcpu->arch.gpr[rs]; break;
+
+ default:
+ printk("mtspr: unknown spr %x\n", sprn);
+ emulated = EMULATE_FAIL;
+ break;
+ }
+ break;
+
+ case 470: /* dcbi */
+ /* Do nothing. The guest is performing dcbi because
+ * hardware DMA is not snooped by the dcache, but
+ * emulated DMA either goes through the dcache as
+ * normal writes, or the host kernel has handled dcache
+ * coherence. */
+ break;
+
+ case 534: /* lwbrx */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 4, 0);
+ break;
+
+ case 566: /* tlbsync */
+ break;
+
+ case 662: /* stwbrx */
+ rs = get_rs(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 4, 0);
+ break;
+
+ case 978: /* tlbwe */
+ emulated = kvmppc_emul_tlbwe(vcpu, inst);
+ break;
+
+ case 914: { /* tlbsx */
+ int index;
+ unsigned int as = get_mmucr_sts(vcpu);
+ unsigned int pid = get_mmucr_stid(vcpu);
+
+ rt = get_rt(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+ rc = get_rc(inst);
+
+ ea = vcpu->arch.gpr[rb];
+ if (ra)
+ ea += vcpu->arch.gpr[ra];
+
+ index = kvmppc_44x_tlb_index(vcpu, ea, pid, as);
+ if (rc) {
+ if (index < 0)
+ vcpu->arch.cr &= ~0x20000000;
+ else
+ vcpu->arch.cr |= 0x20000000;
+ }
+ vcpu->arch.gpr[rt] = index;
+
+ }
+ break;
+
+ case 790: /* lhbrx */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 2, 0);
+ break;
+
+ case 918: /* sthbrx */
+ rs = get_rs(inst);
+ ra = get_ra(inst);
+ rb = get_rb(inst);
+
+ emulated = kvmppc_handle_store(run, vcpu,
+ vcpu->arch.gpr[rs],
+ 2, 0);
+ break;
+
+ case 966: /* iccci */
+ break;
+
+ default:
+ printk("unknown: op %d xop %d\n", get_op(inst),
+ get_xop(inst));
+ emulated = EMULATE_FAIL;
+ break;
+ }
+ break;
+
+ case 32: /* lwz */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
+ break;
+
+ case 33: /* lwzu */
+ ra = get_ra(inst);
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ case 34: /* lbz */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+ break;
+
+ case 35: /* lbzu */
+ ra = get_ra(inst);
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ case 36: /* stw */
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 4, 1);
+ break;
+
+ case 37: /* stwu */
+ ra = get_ra(inst);
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 4, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ case 38: /* stb */
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 1, 1);
+ break;
+
+ case 39: /* stbu */
+ ra = get_ra(inst);
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 1, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ case 40: /* lhz */
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+ break;
+
+ case 41: /* lhzu */
+ ra = get_ra(inst);
+ rt = get_rt(inst);
+ emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ case 44: /* sth */
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 2, 1);
+ break;
+
+ case 45: /* sthu */
+ ra = get_ra(inst);
+ rs = get_rs(inst);
+ emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+ 2, 1);
+ vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+ break;
+
+ default:
+ printk("unknown op %d\n", get_op(inst));
+ emulated = EMULATE_FAIL;
+ break;
+ }
+
+ if (advance)
+ vcpu->arch.pc += 4; /* Advance past emulated instruction. */
+
+ return emulated;
+}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
new file mode 100644
index 00000000000..bad40bd2d3a
--- /dev/null
+++ b/arch/powerpc/kvm/powerpc.c
@@ -0,0 +1,436 @@
+/*
+ * 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. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ * Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputable.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_ppc.h>
+
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn;
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
+{
+ /* XXX implement me */
+ return 0;
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
+{
+ return 1;
+}
+
+
+int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+ enum emulation_result er;
+ int r;
+
+ er = kvmppc_emulate_instruction(run, vcpu);
+ switch (er) {
+ case EMULATE_DONE:
+ /* Future optimization: only reload non-volatiles if they were
+ * actually modified. */
+ r = RESUME_GUEST_NV;
+ break;
+ case EMULATE_DO_MMIO:
+ run->exit_reason = KVM_EXIT_MMIO;
+ /* We must reload nonvolatiles because "update" load/store
+ * instructions modify register state. */
+ /* Future optimization: only reload non-volatiles if they were
+ * actually modified. */
+ r = RESUME_HOST_NV;
+ break;
+ case EMULATE_FAIL:
+ /* XXX Deliver Program interrupt to guest. */
+ printk(KERN_EMERG "%s: emulation failed (%08x)\n", __func__,
+ vcpu->arch.last_inst);
+ r = RESUME_HOST;
+ break;
+ default:
+ BUG();
+ }
+
+ return r;
+}
+
+void kvm_arch_hardware_enable(void *garbage)
+{
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+}
+
+int kvm_arch_hardware_setup(void)
+{
+ return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+ int r;
+
+ if (strcmp(cur_cpu_spec->platform, "ppc440") == 0)
+ r = 0;
+ else
+ r = -ENOTSUPP;
+
+ *(int *)rtn = r;
+}
+
+struct kvm *kvm_arch_create_vm(void)
+{
+ struct kvm *kvm;
+
+ kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+ if (!kvm)
+ return ERR_PTR(-ENOMEM);
+
+ return kvm;
+}
+
+static void kvmppc_free_vcpus(struct kvm *kvm)
+{
+ unsigned int i;
+
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ if (kvm->vcpus[i]) {
+ kvm_arch_vcpu_free(kvm->vcpus[i]);
+ kvm->vcpus[i] = NULL;
+ }
+ }
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+ kvmppc_free_vcpus(kvm);
+ kvm_free_physmem(kvm);
+ kfree(kvm);
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+ int r;
+
+ switch (ext) {
+ case KVM_CAP_USER_MEMORY:
+ r = 1;
+ break;
+ default:
+ r = 0;
+ break;
+ }
+ return r;
+
+}
+
+long kvm_arch_dev_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ return 0;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+ struct kvm_vcpu *vcpu;
+ int err;
+
+ vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+ if (!vcpu) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = kvm_vcpu_init(vcpu, kvm, id);
+ if (err)
+ goto free_vcpu;
+
+ return vcpu;
+
+free_vcpu:
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
+out:
+ return ERR_PTR(err);
+}
+
+void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+{
+ kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(kvm_vcpu_cache, vcpu);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ kvm_arch_vcpu_free(vcpu);
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ unsigned int priority = exception_priority[BOOKE_INTERRUPT_DECREMENTER];
+
+ return test_bit(priority, &vcpu->arch.pending_exceptions);
+}
+
+static void kvmppc_decrementer_func(unsigned long data)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+ kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_DECREMENTER);
+}
+
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ setup_timer(&vcpu->arch.dec_timer, kvmppc_decrementer_func,
+ (unsigned long)vcpu);
+
+ return 0;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+}
+
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+ struct kvm_debug_guest *dbg)
+{
+ return -ENOTSUPP;
+}
+
+static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
+ struct kvm_run *run)
+{
+ u32 *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+ *gpr = run->dcr.data;
+}
+
+static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
+ struct kvm_run *run)
+{
+ u32 *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+
+ if (run->mmio.len > sizeof(*gpr)) {
+ printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
+ return;
+ }
+
+ if (vcpu->arch.mmio_is_bigendian) {
+ switch (run->mmio.len) {
+ case 4: *gpr = *(u32 *)run->mmio.data; break;
+ case 2: *gpr = *(u16 *)run->mmio.data; break;
+ case 1: *gpr = *(u8 *)run->mmio.data; break;
+ }
+ } else {
+ /* Convert BE data from userland back to LE. */
+ switch (run->mmio.len) {
+ case 4: *gpr = ld_le32((u32 *)run->mmio.data); break;
+ case 2: *gpr = ld_le16((u16 *)run->mmio.data); break;
+ case 1: *gpr = *(u8 *)run->mmio.data; break;
+ }
+ }
+}
+
+int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, unsigned int bytes, int is_bigendian)
+{
+ if (bytes > sizeof(run->mmio.data)) {
+ printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
+ run->mmio.len);
+ }
+
+ run->mmio.phys_addr = vcpu->arch.paddr_accessed;
+ run->mmio.len = bytes;
+ run->mmio.is_write = 0;
+
+ vcpu->arch.io_gpr = rt;
+ vcpu->arch.mmio_is_bigendian = is_bigendian;
+ vcpu->mmio_needed = 1;
+ vcpu->mmio_is_write = 0;
+
+ return EMULATE_DO_MMIO;
+}
+
+int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ u32 val, unsigned int bytes, int is_bigendian)
+{
+ void *data = run->mmio.data;
+
+ if (bytes > sizeof(run->mmio.data)) {
+ printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__,
+ run->mmio.len);
+ }
+
+ run->mmio.phys_addr = vcpu->arch.paddr_accessed;
+ run->mmio.len = bytes;
+ run->mmio.is_write = 1;
+ vcpu->mmio_needed = 1;
+ vcpu->mmio_is_write = 1;
+
+ /* Store the value at the lowest bytes in 'data'. */
+ if (is_bigendian) {
+ switch (bytes) {
+ case 4: *(u32 *)data = val; break;
+ case 2: *(u16 *)data = val; break;
+ case 1: *(u8 *)data = val; break;
+ }
+ } else {
+ /* Store LE value into 'data'. */
+ switch (bytes) {
+ case 4: st_le32(data, val); break;
+ case 2: st_le16(data, val); break;
+ case 1: *(u8 *)data = val; break;
+ }
+ }
+
+ return EMULATE_DO_MMIO;
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ int r;
+ sigset_t sigsaved;
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+ if (vcpu->mmio_needed) {
+ if (!vcpu->mmio_is_write)
+ kvmppc_complete_mmio_load(vcpu, run);
+ vcpu->mmio_needed = 0;
+ } else if (vcpu->arch.dcr_needed) {
+ if (!vcpu->arch.dcr_is_write)
+ kvmppc_complete_dcr_load(vcpu, run);
+ vcpu->arch.dcr_needed = 0;
+ }
+
+ kvmppc_check_and_deliver_interrupts(vcpu);
+
+ local_irq_disable();
+ kvm_guest_enter();
+ r = __kvmppc_vcpu_run(run, vcpu);
+ kvm_guest_exit();
+ local_irq_enable();
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+ return r;
+}
+
+int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
+{
+ kvmppc_queue_exception(vcpu, BOOKE_INTERRUPT_EXTERNAL);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ long r;
+
+ switch (ioctl) {
+ case KVM_INTERRUPT: {
+ struct kvm_interrupt irq;
+ r = -EFAULT;
+ if (copy_from_user(&irq, argp, sizeof(irq)))
+ goto out;
+ r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
+ break;
+ }
+ default:
+ r = -EINVAL;
+ }
+
+out:
+ return r;
+}
+
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+ return -ENOTSUPP;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ long r;
+
+ switch (ioctl) {
+ default:
+ r = -EINVAL;
+ }
+
+ return r;
+}
+
+int kvm_arch_init(void *opaque)
+{
+ return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index ada249bf977..ce10e2b1b90 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -202,7 +202,7 @@ adjust_total_lowmem(void)
cam_max_size = max_lowmem_size;
/* adjust lowmem size to max_lowmem_size */
- ram = min(max_lowmem_size, total_lowmem);
+ ram = min(max_lowmem_size, (phys_addr_t)total_lowmem);
/* Calculate CAM values */
__cam0 = 1UL << 2 * (__ilog2(ram) / 2);
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index e10d76a860d..ddeaf9e38ad 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -191,7 +191,7 @@ _GLOBAL(add_hash_page)
add r3,r3,r0 /* note create_hpte trims to 24 bits */
#ifdef CONFIG_SMP
- rlwinm r8,r1,0,0,18 /* use cpu number to make tag */
+ rlwinm r8,r1,0,0,(31-THREAD_SHIFT) /* use cpu number to make tag */
lwz r8,TI_CPU(r8) /* to go in mmu_hash_lock */
oris r8,r8,12
#endif /* CONFIG_SMP */
@@ -526,7 +526,7 @@ _GLOBAL(flush_hash_pages)
#ifdef CONFIG_SMP
addis r9,r7,mmu_hash_lock@ha
addi r9,r9,mmu_hash_lock@l
- rlwinm r8,r1,0,0,18
+ rlwinm r8,r1,0,0,(31-THREAD_SHIFT)
add r8,r8,r7
lwz r8,TI_CPU(r8)
oris r8,r8,9
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 47325f23c51..1952b4d3fa7 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -59,7 +59,10 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long total_memory;
unsigned long total_lowmem;
-phys_addr_t memstart_addr;
+phys_addr_t memstart_addr = (phys_addr_t)~0ull;
+EXPORT_SYMBOL(memstart_addr);
+phys_addr_t kernstart_addr;
+EXPORT_SYMBOL(kernstart_addr);
phys_addr_t lowmem_end_addr;
int boot_mapsize;
@@ -68,14 +71,6 @@ unsigned long agp_special_page;
EXPORT_SYMBOL(agp_special_page);
#endif
-#ifdef CONFIG_HIGHMEM
-pte_t *kmap_pte;
-pgprot_t kmap_prot;
-
-EXPORT_SYMBOL(kmap_prot);
-EXPORT_SYMBOL(kmap_pte);
-#endif
-
void MMU_init(void);
/* XXX should be in current.h -- paulus */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 698bd000f98..c5ac532a016 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -72,7 +72,8 @@
#warning TASK_SIZE is smaller than it needs to be.
#endif
-phys_addr_t memstart_addr;
+phys_addr_t memstart_addr = ~0;
+phys_addr_t kernstart_addr;
void free_initmem(void)
{
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 16def4dcff6..d9e37f365b5 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -45,6 +45,7 @@
#include <asm/tlb.h>
#include <asm/sections.h>
#include <asm/vdso.h>
+#include <asm/fixmap.h>
#include "mmu_decl.h"
@@ -57,6 +58,20 @@ int init_bootmem_done;
int mem_init_done;
unsigned long memory_limit;
+#ifdef CONFIG_HIGHMEM
+pte_t *kmap_pte;
+pgprot_t kmap_prot;
+
+EXPORT_SYMBOL(kmap_prot);
+EXPORT_SYMBOL(kmap_pte);
+
+static inline pte_t *virt_to_kpte(unsigned long vaddr)
+{
+ return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
+ vaddr), vaddr), vaddr);
+}
+#endif
+
int page_is_ram(unsigned long pfn)
{
unsigned long paddr = (pfn << PAGE_SHIFT);
@@ -95,15 +110,6 @@ EXPORT_SYMBOL(phys_mem_access_prot);
#ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- init_page_count(page);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
#ifdef CONFIG_NUMA
int memory_add_physaddr_to_nid(u64 start)
{
@@ -216,7 +222,7 @@ void __init do_init_bootmem(void)
unsigned long total_pages;
int boot_mapsize;
- max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
+ max_low_pfn = max_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
total_pages = (lmb_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT;
#ifdef CONFIG_HIGHMEM
total_pages = total_lowmem >> PAGE_SHIFT;
@@ -232,7 +238,8 @@ void __init do_init_bootmem(void)
start = lmb_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE);
- boot_mapsize = init_bootmem(start >> PAGE_SHIFT, total_pages);
+ min_low_pfn = MEMORY_START >> PAGE_SHIFT;
+ boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn);
/* Add active regions with valid PFNs */
for (i = 0; i < lmb.memory.cnt; i++) {
@@ -310,14 +317,19 @@ void __init paging_init(void)
unsigned long top_of_ram = lmb_end_of_DRAM();
unsigned long max_zone_pfns[MAX_NR_ZONES];
+#ifdef CONFIG_PPC32
+ unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
+ unsigned long end = __fix_to_virt(FIX_HOLE);
+
+ for (; v < end; v += PAGE_SIZE)
+ map_page(v, 0, 0); /* XXX gross */
+#endif
+
#ifdef CONFIG_HIGHMEM
map_page(PKMAP_BASE, 0, 0); /* XXX gross */
- pkmap_page_table = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k
- (PKMAP_BASE), PKMAP_BASE), PKMAP_BASE), PKMAP_BASE);
- map_page(KMAP_FIX_BEGIN, 0, 0); /* XXX gross */
- kmap_pte = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k
- (KMAP_FIX_BEGIN), KMAP_FIX_BEGIN), KMAP_FIX_BEGIN),
- KMAP_FIX_BEGIN);
+ pkmap_page_table = virt_to_kpte(PKMAP_BASE);
+
+ kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
kmap_prot = PAGE_KERNEL;
#endif /* CONFIG_HIGHMEM */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 1efd631211e..dc704da363e 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -18,6 +18,7 @@
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/lmb.h>
+#include <linux/of.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/system.h>
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 64c44bcc68d..80d1babb230 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -29,6 +29,7 @@
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/fixmap.h>
#include <asm/io.h>
#include "mmu_decl.h"
@@ -387,3 +388,25 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
}
#endif /* CONFIG_DEBUG_PAGEALLOC */
+
+static int fixmaps;
+unsigned long FIXADDR_TOP = 0xfffff000;
+EXPORT_SYMBOL(FIXADDR_TOP);
+
+void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
+{
+ unsigned long address = __fix_to_virt(idx);
+
+ if (idx >= __end_of_fixed_addresses) {
+ BUG();
+ return;
+ }
+
+ map_page(address, phys, flags);
+ fixmaps++;
+}
+
+void __this_fixmap_does_not_exist(void)
+{
+ WARN_ON(1);
+}
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 18b8ebe930d..5e1e8cf14e7 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -3,11 +3,12 @@
*
* Initial author: Xianghua Xiao <x.xiao@freescale.com>
* Recode: Jason Jin <jason.jin@freescale.com>
+ * York Sun <yorksun@freescale.com>
*
* Rewrite the interrupt routing. remove the 8259PIC support,
* All the integrated device in ULI use sideband interrupt.
*
- * Copyright 2007 Freescale Semiconductor Inc.
+ * Copyright 2008 Freescale Semiconductor Inc.
*
* 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
@@ -38,6 +39,8 @@
#include <sysdev/fsl_pci.h>
#include <sysdev/fsl_soc.h>
+static unsigned char *pixis_bdcfg0, *pixis_arch;
+
static struct of_device_id __initdata mpc8610_ids[] = {
{ .compatible = "fsl,mpc8610-immr", },
{}
@@ -52,8 +55,7 @@ static int __init mpc8610_declare_of_platform_devices(void)
}
machine_device_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices);
-static void __init
-mpc86xx_hpcd_init_irq(void)
+static void __init mpc86xx_hpcd_init_irq(void)
{
struct mpic *mpic1;
struct device_node *np;
@@ -161,12 +163,159 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5229, quirk_uli5229);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 0x5288, final_uli5288);
#endif /* CONFIG_PCI */
-static void __init
-mpc86xx_hpcd_setup_arch(void)
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
+static u32 get_busfreq(void)
{
-#ifdef CONFIG_PCI
- struct device_node *np;
+ struct device_node *node;
+
+ u32 fs_busfreq = 0;
+ node = of_find_node_by_type(NULL, "cpu");
+ if (node) {
+ unsigned int size;
+ const unsigned int *prop =
+ of_get_property(node, "bus-frequency", &size);
+ if (prop)
+ fs_busfreq = *prop;
+ of_node_put(node);
+ };
+ return fs_busfreq;
+}
+
+unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel,
+ int monitor_port)
+{
+ static const unsigned long pixelformat[][3] = {
+ {0x88882317, 0x88083218, 0x65052119},
+ {0x88883316, 0x88082219, 0x65053118},
+ };
+ unsigned int pix_fmt, arch_monitor;
+
+ arch_monitor = ((*pixis_arch == 0x01) && (monitor_port == 0))? 0 : 1;
+ /* DVI port for board version 0x01 */
+
+ if (bits_per_pixel == 32)
+ pix_fmt = pixelformat[arch_monitor][0];
+ else if (bits_per_pixel == 24)
+ pix_fmt = pixelformat[arch_monitor][1];
+ else if (bits_per_pixel == 16)
+ pix_fmt = pixelformat[arch_monitor][2];
+ else
+ pix_fmt = pixelformat[1][0];
+
+ return pix_fmt;
+}
+
+void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base)
+{
+ int i;
+ if (monitor_port == 2) { /* dual link LVDS */
+ for (i = 0; i < 256*3; i++)
+ gamma_table_base[i] = (gamma_table_base[i] << 2) |
+ ((gamma_table_base[i] >> 6) & 0x03);
+ }
+}
+
+void mpc8610hpcd_set_monitor_port(int monitor_port)
+{
+ static const u8 bdcfg[] = {0xBD, 0xB5, 0xA5};
+ if (monitor_port < 3)
+ *pixis_bdcfg0 = bdcfg[monitor_port];
+}
+
+void mpc8610hpcd_set_pixel_clock(unsigned int pixclock)
+{
+ u32 __iomem *clkdvdr;
+ u32 temp;
+ /* variables for pixel clock calcs */
+ ulong bestval, bestfreq, speed_ccb, minpixclock, maxpixclock;
+ ulong pixval;
+ long err;
+ int i;
+
+ clkdvdr = ioremap(get_immrbase() + 0xe0800, sizeof(u32));
+ if (!clkdvdr) {
+ printk(KERN_ERR "Err: can't map clock divider register!\n");
+ return;
+ }
+
+ /* Pixel Clock configuration */
+ pr_debug("DIU: Bus Frequency = %d\n", get_busfreq());
+ speed_ccb = get_busfreq();
+
+ /* Calculate the pixel clock with the smallest error */
+ /* calculate the following in steps to avoid overflow */
+ pr_debug("DIU pixclock in ps - %d\n", pixclock);
+ temp = 1000000000/pixclock;
+ temp *= 1000;
+ pixclock = temp;
+ pr_debug("DIU pixclock freq - %u\n", pixclock);
+
+ temp = pixclock * 5 / 100;
+ pr_debug("deviation = %d\n", temp);
+ minpixclock = pixclock - temp;
+ maxpixclock = pixclock + temp;
+ pr_debug("DIU minpixclock - %lu\n", minpixclock);
+ pr_debug("DIU maxpixclock - %lu\n", maxpixclock);
+ pixval = speed_ccb/pixclock;
+ pr_debug("DIU pixval = %lu\n", pixval);
+
+ err = 100000000;
+ bestval = pixval;
+ pr_debug("DIU bestval = %lu\n", bestval);
+
+ bestfreq = 0;
+ for (i = -1; i <= 1; i++) {
+ temp = speed_ccb / ((pixval+i) + 1);
+ pr_debug("DIU test pixval i= %d, pixval=%lu, temp freq. = %u\n",
+ i, pixval, temp);
+ if ((temp < minpixclock) || (temp > maxpixclock))
+ pr_debug("DIU exceeds monitor range (%lu to %lu)\n",
+ minpixclock, maxpixclock);
+ else if (abs(temp - pixclock) < err) {
+ pr_debug("Entered the else if block %d\n", i);
+ err = abs(temp - pixclock);
+ bestval = pixval+i;
+ bestfreq = temp;
+ }
+ }
+
+ pr_debug("DIU chose = %lx\n", bestval);
+ pr_debug("DIU error = %ld\n NomPixClk ", err);
+ pr_debug("DIU: Best Freq = %lx\n", bestfreq);
+ /* Modify PXCLK in GUTS CLKDVDR */
+ pr_debug("DIU: Current value of CLKDVDR = 0x%08x\n", (*clkdvdr));
+ temp = (*clkdvdr) & 0x2000FFFF;
+ *clkdvdr = temp; /* turn off clock */
+ *clkdvdr = temp | 0x80000000 | (((bestval) & 0x1F) << 16);
+ pr_debug("DIU: Modified value of CLKDVDR = 0x%08x\n", (*clkdvdr));
+ iounmap(clkdvdr);
+}
+
+ssize_t mpc8610hpcd_show_monitor_port(int monitor_port, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE,
+ "%c0 - DVI\n"
+ "%c1 - Single link LVDS\n"
+ "%c2 - Dual link LVDS\n",
+ monitor_port == 0 ? '*' : ' ',
+ monitor_port == 1 ? '*' : ' ',
+ monitor_port == 2 ? '*' : ' ');
+}
+
+int mpc8610hpcd_set_sysfs_monitor_port(int val)
+{
+ return val < 3 ? val : 0;
+}
+
#endif
+
+static void __init mpc86xx_hpcd_setup_arch(void)
+{
+ struct resource r;
+ struct device_node *np;
+ unsigned char *pixis;
+
if (ppc_md.progress)
ppc_md.progress("mpc86xx_hpcd_setup_arch()", 0);
@@ -183,6 +332,30 @@ mpc86xx_hpcd_setup_arch(void)
}
}
#endif
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+ preallocate_diu_videomemory();
+ diu_ops.get_pixel_format = mpc8610hpcd_get_pixel_format;
+ diu_ops.set_gamma_table = mpc8610hpcd_set_gamma_table;
+ diu_ops.set_monitor_port = mpc8610hpcd_set_monitor_port;
+ diu_ops.set_pixel_clock = mpc8610hpcd_set_pixel_clock;
+ diu_ops.show_monitor_port = mpc8610hpcd_show_monitor_port;
+ diu_ops.set_sysfs_monitor_port = mpc8610hpcd_set_sysfs_monitor_port;
+#endif
+
+ np = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis");
+ if (np) {
+ of_address_to_resource(np, 0, &r);
+ of_node_put(np);
+ pixis = ioremap(r.start, 32);
+ if (!pixis) {
+ printk(KERN_ERR "Err: can't map FPGA cfg register!\n");
+ return;
+ }
+ pixis_bdcfg0 = pixis + 8;
+ pixis_arch = pixis + 1;
+ } else
+ printk(KERN_ERR "Err: "
+ "can't find device node 'fsl,fpga-pixis'\n");
printk("MPC86xx HPCD board from Freescale Semiconductor\n");
}
@@ -200,8 +373,7 @@ static int __init mpc86xx_hpcd_probe(void)
return 0;
}
-static long __init
-mpc86xx_time_init(void)
+static long __init mpc86xx_time_init(void)
{
unsigned int temp;
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index f38c50b4ce5..87454c52697 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -45,7 +45,6 @@ source "arch/powerpc/platforms/powermac/Kconfig"
source "arch/powerpc/platforms/prep/Kconfig"
source "arch/powerpc/platforms/maple/Kconfig"
source "arch/powerpc/platforms/pasemi/Kconfig"
-source "arch/powerpc/platforms/celleb/Kconfig"
source "arch/powerpc/platforms/ps3/Kconfig"
source "arch/powerpc/platforms/cell/Kconfig"
source "arch/powerpc/platforms/8xx/Kconfig"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 5fc7fac10e9..f7efaa925a1 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -220,8 +220,8 @@ config SMP
If you don't know what to do here, say N.
config NR_CPUS
- int "Maximum number of CPUs (2-128)"
- range 2 128
+ int "Maximum number of CPUs (2-1024)"
+ range 2 1024
depends on SMP
default "32" if PPC64
default "4"
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index a984894466d..423a0234dc3 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -24,5 +24,4 @@ obj-$(CONFIG_PPC_MAPLE) += maple/
obj-$(CONFIG_PPC_PASEMI) += pasemi/
obj-$(CONFIG_PPC_CELL) += cell/
obj-$(CONFIG_PPC_PS3) += ps3/
-obj-$(CONFIG_PPC_CELLEB) += celleb/
obj-$(CONFIG_EMBEDDED6xx) += embedded6xx/
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 2f169991896..3959fcfe731 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -25,6 +25,19 @@ config PPC_IBM_CELL_BLADE
select PPC_UDBG_16550
select UDBG_RTAS_CONSOLE
+config PPC_CELLEB
+ bool "Toshiba's Cell Reference Set 'Celleb' Architecture"
+ depends on PPC_MULTIPLATFORM && PPC64
+ select PPC_CELL
+ select PPC_CELL_NATIVE
+ select PPC_RTAS
+ select PPC_INDIRECT_IO
+ select PPC_OF_PLATFORM_PCI
+ select HAS_TXX9_SERIAL
+ select PPC_UDBG_BEAT
+ select USB_OHCI_BIG_ENDIAN_MMIO
+ select USB_EHCI_BIG_ENDIAN_MMIO
+
menu "Cell Broadband Engine options"
depends on PPC_CELL
diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile
index c89964c6fb1..c2a7e4e5ddf 100644
--- a/arch/powerpc/platforms/cell/Makefile
+++ b/arch/powerpc/platforms/cell/Makefile
@@ -1,6 +1,7 @@
obj-$(CONFIG_PPC_CELL_NATIVE) += interrupt.o iommu.o setup.o \
cbe_regs.o spider-pic.o \
- pervasive.o pmu.o io-workarounds.o
+ pervasive.o pmu.o io-workarounds.o \
+ spider-pci.o
obj-$(CONFIG_CBE_RAS) += ras.o
obj-$(CONFIG_CBE_THERM) += cbe_thermal.o
@@ -26,3 +27,20 @@ obj-$(CONFIG_SPU_BASE) += spu_callbacks.o spu_base.o \
spufs/
obj-$(CONFIG_PCI_MSI) += axon_msi.o
+
+
+# celleb stuff
+ifeq ($(CONFIG_PPC_CELLEB),y)
+obj-y += celleb_setup.o \
+ celleb_pci.o celleb_scc_epci.o \
+ celleb_scc_pciex.o \
+ celleb_scc_uhc.o \
+ io-workarounds.o spider-pci.o \
+ beat.o beat_htab.o beat_hvCall.o \
+ beat_interrupt.o beat_iommu.o
+
+obj-$(CONFIG_SMP) += beat_smp.o
+obj-$(CONFIG_PPC_UDBG_BEAT) += beat_udbg.o
+obj-$(CONFIG_SERIAL_TXX9) += celleb_scc_sio.o
+obj-$(CONFIG_SPU_BASE) += beat_spu_priv1.o
+endif
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index d95e71dee91..c39f5c225f2 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -123,7 +123,7 @@ static struct axon_msic *find_msi_translator(struct pci_dev *dev)
return NULL;
}
- for (; dn; tmp = of_get_parent(dn), of_node_put(dn), dn = tmp) {
+ for (; dn; dn = of_get_next_parent(dn)) {
ph = of_get_property(dn, "msi-translator", NULL);
if (ph)
break;
@@ -169,7 +169,7 @@ static int axon_msi_check_device(struct pci_dev *dev, int nvec, int type)
static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
{
- struct device_node *dn, *tmp;
+ struct device_node *dn;
struct msi_desc *entry;
int len;
const u32 *prop;
@@ -182,7 +182,7 @@ static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
- for (; dn; tmp = of_get_parent(dn), of_node_put(dn), dn = tmp) {
+ for (; dn; dn = of_get_next_parent(dn)) {
if (entry->msi_attrib.is_64) {
prop = of_get_property(dn, "msi-address-64", &len);
if (prop)
diff --git a/arch/powerpc/platforms/celleb/beat.c b/arch/powerpc/platforms/cell/beat.c
index b64b171f245..48c690ea65d 100644
--- a/arch/powerpc/platforms/celleb/beat.c
+++ b/arch/powerpc/platforms/cell/beat.c
@@ -33,7 +33,7 @@
#include "beat_wrapper.h"
#include "beat.h"
-#include "interrupt.h"
+#include "beat_interrupt.h"
static int beat_pm_poweroff_flag;
diff --git a/arch/powerpc/platforms/celleb/beat.h b/arch/powerpc/platforms/cell/beat.h
index 32c8efcedc8..32c8efcedc8 100644
--- a/arch/powerpc/platforms/celleb/beat.h
+++ b/arch/powerpc/platforms/cell/beat.h
diff --git a/arch/powerpc/platforms/celleb/htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 81467ff055c..81467ff055c 100644
--- a/arch/powerpc/platforms/celleb/htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
diff --git a/arch/powerpc/platforms/celleb/hvCall.S b/arch/powerpc/platforms/cell/beat_hvCall.S
index 74c81744894..74c81744894 100644
--- a/arch/powerpc/platforms/celleb/hvCall.S
+++ b/arch/powerpc/platforms/cell/beat_hvCall.S
diff --git a/arch/powerpc/platforms/celleb/interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index 69562a86787..192a9350937 100644
--- a/arch/powerpc/platforms/celleb/interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -26,7 +26,7 @@
#include <asm/machdep.h>
-#include "interrupt.h"
+#include "beat_interrupt.h"
#include "beat_wrapper.h"
#define MAX_IRQS NR_IRQS
diff --git a/arch/powerpc/platforms/celleb/interrupt.h b/arch/powerpc/platforms/cell/beat_interrupt.h
index b470fd0051f..b470fd0051f 100644
--- a/arch/powerpc/platforms/celleb/interrupt.h
+++ b/arch/powerpc/platforms/cell/beat_interrupt.h
diff --git a/arch/powerpc/platforms/celleb/iommu.c b/arch/powerpc/platforms/cell/beat_iommu.c
index 93b0efddd65..93b0efddd65 100644
--- a/arch/powerpc/platforms/celleb/iommu.c
+++ b/arch/powerpc/platforms/cell/beat_iommu.c
diff --git a/arch/powerpc/platforms/celleb/smp.c b/arch/powerpc/platforms/cell/beat_smp.c
index a7631250aeb..26efc204c47 100644
--- a/arch/powerpc/platforms/celleb/smp.c
+++ b/arch/powerpc/platforms/cell/beat_smp.c
@@ -37,7 +37,7 @@
#include <asm/machdep.h>
#include <asm/udbg.h>
-#include "interrupt.h"
+#include "beat_interrupt.h"
#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
diff --git a/arch/powerpc/platforms/celleb/spu_priv1.c b/arch/powerpc/platforms/cell/beat_spu_priv1.c
index bcc17f7fe8a..bcc17f7fe8a 100644
--- a/arch/powerpc/platforms/celleb/spu_priv1.c
+++ b/arch/powerpc/platforms/cell/beat_spu_priv1.c
diff --git a/arch/powerpc/platforms/celleb/beat_syscall.h b/arch/powerpc/platforms/cell/beat_syscall.h
index 8580dc7e179..8580dc7e179 100644
--- a/arch/powerpc/platforms/celleb/beat_syscall.h
+++ b/arch/powerpc/platforms/cell/beat_syscall.h
diff --git a/arch/powerpc/platforms/celleb/udbg_beat.c b/arch/powerpc/platforms/cell/beat_udbg.c
index 6b418f6b617..6b418f6b617 100644
--- a/arch/powerpc/platforms/celleb/udbg_beat.c
+++ b/arch/powerpc/platforms/cell/beat_udbg.c
diff --git a/arch/powerpc/platforms/celleb/beat_wrapper.h b/arch/powerpc/platforms/cell/beat_wrapper.h
index b47dfda48d0..b47dfda48d0 100644
--- a/arch/powerpc/platforms/celleb/beat_wrapper.h
+++ b/arch/powerpc/platforms/cell/beat_wrapper.h
diff --git a/arch/powerpc/platforms/celleb/pci.c b/arch/powerpc/platforms/cell/celleb_pci.c
index 51b390d34e4..f39a3b2a166 100644
--- a/arch/powerpc/platforms/celleb/pci.c
+++ b/arch/powerpc/platforms/cell/celleb_pci.c
@@ -37,12 +37,11 @@
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/prom.h>
-#include <asm/machdep.h>
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
-#include "pci.h"
-#include "interrupt.h"
+#include "io-workarounds.h"
+#include "celleb_pci.h"
#define MAX_PCI_DEVICES 32
#define MAX_PCI_FUNCTIONS 8
@@ -190,7 +189,7 @@ static int celleb_fake_pci_read_config(struct pci_bus *bus,
static int celleb_fake_pci_write_config(struct pci_bus *bus,
- unsigned int devfn, int where, int size, u32 val)
+ unsigned int devfn, int where, int size, u32 val)
{
char *config;
struct device_node *node;
@@ -457,33 +456,42 @@ static int __init celleb_setup_fake_pci(struct device_node *dev,
return 0;
}
-void __init fake_pci_workaround_init(struct pci_controller *phb)
-{
- /**
- * We will add fake pci bus to scc_pci_bus for the purpose to improve
- * I/O Macro performance. But device-tree and device drivers
- * are not ready to use address with a token.
- */
-
- /* celleb_pci_add_one(phb, NULL); */
-}
+static struct celleb_phb_spec celleb_fake_pci_spec __initdata = {
+ .setup = celleb_setup_fake_pci,
+};
static struct of_device_id celleb_phb_match[] __initdata = {
{
.name = "pci-pseudo",
- .data = celleb_setup_fake_pci,
+ .data = &celleb_fake_pci_spec,
}, {
.name = "epci",
- .data = celleb_setup_epci,
+ .data = &celleb_epci_spec,
+ }, {
+ .name = "pcie",
+ .data = &celleb_pciex_spec,
}, {
},
};
+static int __init celleb_io_workaround_init(struct pci_controller *phb,
+ struct celleb_phb_spec *phb_spec)
+{
+ if (phb_spec->ops) {
+ iowa_register_bus(phb, phb_spec->ops, phb_spec->iowa_init,
+ phb_spec->iowa_data);
+ io_workaround_init();
+ }
+
+ return 0;
+}
+
int __init celleb_setup_phb(struct pci_controller *phb)
{
struct device_node *dev = phb->dn;
const struct of_device_id *match;
- int (*setup_func)(struct device_node *, struct pci_controller *);
+ struct celleb_phb_spec *phb_spec;
+ int rc;
match = of_match_node(celleb_phb_match, dev);
if (!match)
@@ -492,8 +500,12 @@ int __init celleb_setup_phb(struct pci_controller *phb)
phb_set_bus_ranges(dev, phb);
phb->buid = 1;
- setup_func = match->data;
- return (*setup_func)(dev, phb);
+ phb_spec = match->data;
+ rc = (*phb_spec->setup)(dev, phb);
+ if (rc)
+ return 1;
+
+ return celleb_io_workaround_init(phb, phb_spec);
}
int celleb_pci_probe_mode(struct pci_bus *bus)
diff --git a/arch/powerpc/platforms/celleb/pci.h b/arch/powerpc/platforms/cell/celleb_pci.h
index 5d5544ffedd..4cba1523ec5 100644
--- a/arch/powerpc/platforms/celleb/pci.h
+++ b/arch/powerpc/platforms/cell/celleb_pci.h
@@ -27,16 +27,19 @@
#include <asm/prom.h>
#include <asm/ppc-pci.h>
+#include "io-workarounds.h"
+
+struct celleb_phb_spec {
+ int (*setup)(struct device_node *, struct pci_controller *);
+ struct ppc_pci_io *ops;
+ int (*iowa_init)(struct iowa_bus *, void *);
+ void *iowa_data;
+};
+
extern int celleb_setup_phb(struct pci_controller *);
extern int celleb_pci_probe_mode(struct pci_bus *);
-extern int celleb_setup_epci(struct device_node *, struct pci_controller *);
-
-extern void *celleb_dummy_page_va;
-extern int __init celleb_pci_workaround_init(void);
-extern void __init celleb_pci_add_one(struct pci_controller *,
- void (*)(struct pci_controller *));
-extern void fake_pci_workaround_init(struct pci_controller *);
-extern void epci_workaround_init(struct pci_controller *);
+extern struct celleb_phb_spec celleb_epci_spec;
+extern struct celleb_phb_spec celleb_pciex_spec;
#endif /* _CELLEB_PCI_H */
diff --git a/arch/powerpc/platforms/celleb/scc.h b/arch/powerpc/platforms/cell/celleb_scc.h
index 6be1542a6e6..b596a711c34 100644
--- a/arch/powerpc/platforms/celleb/scc.h
+++ b/arch/powerpc/platforms/cell/celleb_scc.h
@@ -125,6 +125,93 @@
/* bits for SCC_EPCI_CNTOPT */
#define SCC_EPCI_CNTOPT_O2PMB 0x00000002
+/* SCC PCIEXC SMMIO registers */
+#define PEXCADRS 0x000
+#define PEXCWDATA 0x004
+#define PEXCRDATA 0x008
+#define PEXDADRS 0x010
+#define PEXDCMND 0x014
+#define PEXDWDATA 0x018
+#define PEXDRDATA 0x01c
+#define PEXREQID 0x020
+#define PEXTIDMAP 0x024
+#define PEXINTMASK 0x028
+#define PEXINTSTS 0x02c
+#define PEXAERRMASK 0x030
+#define PEXAERRSTS 0x034
+#define PEXPRERRMASK 0x040
+#define PEXPRERRSTS 0x044
+#define PEXPRERRID01 0x048
+#define PEXPRERRID23 0x04c
+#define PEXVDMASK 0x050
+#define PEXVDSTS 0x054
+#define PEXRCVCPLIDA 0x060
+#define PEXLENERRIDA 0x068
+#define PEXPHYPLLST 0x070
+#define PEXDMRDEN0 0x100
+#define PEXDMRDADR0 0x104
+#define PEXDMRDENX 0x110
+#define PEXDMRDADRX 0x114
+#define PEXECMODE 0xf00
+#define PEXMAEA(n) (0xf50 + (8 * n))
+#define PEXMAEC(n) (0xf54 + (8 * n))
+#define PEXCCRCTRL 0xff0
+
+/* SCC PCIEXC bits and shifts for PEXCADRS */
+#define PEXCADRS_BYTE_EN_SHIFT 20
+#define PEXCADRS_CMD_SHIFT 16
+#define PEXCADRS_CMD_READ (0xa << PEXCADRS_CMD_SHIFT)
+#define PEXCADRS_CMD_WRITE (0xb << PEXCADRS_CMD_SHIFT)
+
+/* SCC PCIEXC shifts for PEXDADRS */
+#define PEXDADRS_BUSNO_SHIFT 20
+#define PEXDADRS_DEVNO_SHIFT 15
+#define PEXDADRS_FUNCNO_SHIFT 12
+
+/* SCC PCIEXC bits and shifts for PEXDCMND */
+#define PEXDCMND_BYTE_EN_SHIFT 4
+#define PEXDCMND_IO_READ 0x2
+#define PEXDCMND_IO_WRITE 0x3
+#define PEXDCMND_CONFIG_READ 0xa
+#define PEXDCMND_CONFIG_WRITE 0xb
+
+/* SCC PCIEXC bits for PEXPHYPLLST */
+#define PEXPHYPLLST_PEXPHYAPLLST 0x00000001
+
+/* SCC PCIEXC bits for PEXECMODE */
+#define PEXECMODE_ALL_THROUGH 0x00000000
+#define PEXECMODE_ALL_8BIT 0x00550155
+#define PEXECMODE_ALL_16BIT 0x00aa02aa
+
+/* SCC PCIEXC bits for PEXCCRCTRL */
+#define PEXCCRCTRL_PEXIPCOREEN 0x00040000
+#define PEXCCRCTRL_PEXIPCONTEN 0x00020000
+#define PEXCCRCTRL_PEXPHYPLLEN 0x00010000
+#define PEXCCRCTRL_PCIEXCAOCKEN 0x00000100
+
+/* SCC PCIEXC port configuration registers */
+#define PEXTCERRCHK 0x21c
+#define PEXTAMAPB0 0x220
+#define PEXTAMAPL0 0x224
+#define PEXTAMAPB(n) (PEXTAMAPB0 + 8 * (n))
+#define PEXTAMAPL(n) (PEXTAMAPL0 + 8 * (n))
+#define PEXCHVC0P 0x500
+#define PEXCHVC0NP 0x504
+#define PEXCHVC0C 0x508
+#define PEXCDVC0P 0x50c
+#define PEXCDVC0NP 0x510
+#define PEXCDVC0C 0x514
+#define PEXCHVCXP 0x518
+#define PEXCHVCXNP 0x51c
+#define PEXCHVCXC 0x520
+#define PEXCDVCXP 0x524
+#define PEXCDVCXNP 0x528
+#define PEXCDVCXC 0x52c
+#define PEXCTTRG 0x530
+#define PEXTSCTRL 0x700
+#define PEXTSSTS 0x704
+#define PEXSKPCTRL 0x708
+
/* UHC registers */
#define SCC_UHC_CKRCTRL 0xff0
#define SCC_UHC_ECMODE 0xf00
diff --git a/arch/powerpc/platforms/celleb/scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c
index a999b393f6f..08c285b10e3 100644
--- a/arch/powerpc/platforms/celleb/scc_epci.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_epci.c
@@ -30,23 +30,17 @@
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/prom.h>
-#include <asm/machdep.h>
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
-#include "scc.h"
-#include "pci.h"
-#include "interrupt.h"
+#include "celleb_scc.h"
+#include "celleb_pci.h"
#define MAX_PCI_DEVICES 32
#define MAX_PCI_FUNCTIONS 8
#define iob() __asm__ __volatile__("eieio; sync":::"memory")
-struct epci_private {
- dma_addr_t dummy_page_da;
-};
-
static inline PCI_IO_ADDR celleb_epci_get_epci_base(
struct pci_controller *hose)
{
@@ -71,42 +65,6 @@ static inline PCI_IO_ADDR celleb_epci_get_epci_cfg(
return hose->cfg_data;
}
-static void scc_epci_dummy_read(struct pci_controller *hose)
-{
- PCI_IO_ADDR epci_base;
- u32 val;
-
- epci_base = celleb_epci_get_epci_base(hose);
-
- val = in_be32(epci_base + SCC_EPCI_WATRP);
- iosync();
-
- return;
-}
-
-void __init epci_workaround_init(struct pci_controller *hose)
-{
- PCI_IO_ADDR epci_base;
- PCI_IO_ADDR reg;
- struct epci_private *private = hose->private_data;
-
- BUG_ON(!private);
-
- private->dummy_page_da = dma_map_single(hose->parent,
- celleb_dummy_page_va, PAGE_SIZE, DMA_FROM_DEVICE);
- if (private->dummy_page_da == DMA_ERROR_CODE) {
- printk(KERN_ERR "EPCI: dummy read disabled. "
- "Map dummy page failed.\n");
- return;
- }
-
- celleb_pci_add_one(hose, scc_epci_dummy_read);
- epci_base = celleb_epci_get_epci_base(hose);
-
- reg = epci_base + SCC_EPCI_DUMYRADR;
- out_be32(reg, private->dummy_page_da);
-}
-
static inline void clear_and_disable_master_abort_interrupt(
struct pci_controller *hose)
{
@@ -151,10 +109,8 @@ static int celleb_epci_check_abort(struct pci_controller *hose,
return PCIBIOS_SUCCESSFUL;
}
-static PCI_IO_ADDR celleb_epci_make_config_addr(
- struct pci_bus *bus,
- struct pci_controller *hose,
- unsigned int devfn, int where)
+static PCI_IO_ADDR celleb_epci_make_config_addr(struct pci_bus *bus,
+ struct pci_controller *hose, unsigned int devfn, int where)
{
PCI_IO_ADDR addr;
@@ -425,8 +381,8 @@ static int __init celleb_epci_init(struct pci_controller *hose)
return 0;
}
-int __init celleb_setup_epci(struct device_node *node,
- struct pci_controller *hose)
+static int __init celleb_setup_epci(struct device_node *node,
+ struct pci_controller *hose)
{
struct resource r;
@@ -450,8 +406,7 @@ int __init celleb_setup_epci(struct device_node *node,
if (!hose->cfg_addr)
goto error;
pr_debug("EPCI: cfg_addr map 0x%016lx->0x%016lx + 0x%016lx\n",
- r.start, (unsigned long)hose->cfg_addr,
- (r.end - r.start + 1));
+ r.start, (unsigned long)hose->cfg_addr, (r.end - r.start + 1));
if (of_address_to_resource(node, 2, &r))
goto error;
@@ -459,14 +414,7 @@ int __init celleb_setup_epci(struct device_node *node,
if (!hose->cfg_data)
goto error;
pr_debug("EPCI: cfg_data map 0x%016lx->0x%016lx + 0x%016lx\n",
- r.start, (unsigned long)hose->cfg_data,
- (r.end - r.start + 1));
-
- hose->private_data = kzalloc(sizeof(struct epci_private), GFP_KERNEL);
- if (hose->private_data == NULL) {
- printk(KERN_ERR "EPCI: no memory for private data.\n");
- goto error;
- }
+ r.start, (unsigned long)hose->cfg_data, (r.end - r.start + 1));
hose->ops = &celleb_epci_ops;
celleb_epci_init(hose);
@@ -474,8 +422,6 @@ int __init celleb_setup_epci(struct device_node *node,
return 0;
error:
- kfree(hose->private_data);
-
if (hose->cfg_addr)
iounmap(hose->cfg_addr);
@@ -483,3 +429,10 @@ error:
iounmap(hose->cfg_data);
return 1;
}
+
+struct celleb_phb_spec celleb_epci_spec __initdata = {
+ .setup = celleb_setup_epci,
+ .ops = &spiderpci_ops,
+ .iowa_init = &spiderpci_iowa_init,
+ .iowa_data = (void *)0,
+};
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
new file mode 100644
index 00000000000..31da84c458d
--- /dev/null
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -0,0 +1,547 @@
+/*
+ * Support for Celleb PCI-Express.
+ *
+ * (C) Copyright 2007-2008 TOSHIBA CORPORATION
+ *
+ * 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.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/iommu.h>
+#include <asm/byteorder.h>
+
+#include "celleb_scc.h"
+#include "celleb_pci.h"
+
+#define PEX_IN(base, off) in_be32((void __iomem *)(base) + (off))
+#define PEX_OUT(base, off, data) out_be32((void __iomem *)(base) + (off), (data))
+
+static void scc_pciex_io_flush(struct iowa_bus *bus)
+{
+ (void)PEX_IN(bus->phb->cfg_addr, PEXDMRDEN0);
+}
+
+/*
+ * Memory space access to device on PCIEX
+ */
+#define PCIEX_MMIO_READ(name, ret) \
+static ret scc_pciex_##name(const PCI_IO_ADDR addr) \
+{ \
+ ret val = __do_##name(addr); \
+ scc_pciex_io_flush(iowa_mem_find_bus(addr)); \
+ return val; \
+}
+
+#define PCIEX_MMIO_READ_STR(name) \
+static void scc_pciex_##name(const PCI_IO_ADDR addr, void *buf, \
+ unsigned long count) \
+{ \
+ __do_##name(addr, buf, count); \
+ scc_pciex_io_flush(iowa_mem_find_bus(addr)); \
+}
+
+PCIEX_MMIO_READ(readb, u8)
+PCIEX_MMIO_READ(readw, u16)
+PCIEX_MMIO_READ(readl, u32)
+PCIEX_MMIO_READ(readq, u64)
+PCIEX_MMIO_READ(readw_be, u16)
+PCIEX_MMIO_READ(readl_be, u32)
+PCIEX_MMIO_READ(readq_be, u64)
+PCIEX_MMIO_READ_STR(readsb)
+PCIEX_MMIO_READ_STR(readsw)
+PCIEX_MMIO_READ_STR(readsl)
+
+static void scc_pciex_memcpy_fromio(void *dest, const PCI_IO_ADDR src,
+ unsigned long n)
+{
+ __do_memcpy_fromio(dest, src, n);
+ scc_pciex_io_flush(iowa_mem_find_bus(src));
+}
+
+/*
+ * I/O port access to devices on PCIEX.
+ */
+
+static inline unsigned long get_bus_address(struct pci_controller *phb,
+ unsigned long port)
+{
+ return port - ((unsigned long)(phb->io_base_virt) - _IO_BASE);
+}
+
+static u32 scc_pciex_read_port(struct pci_controller *phb,
+ unsigned long port, int size)
+{
+ unsigned int byte_enable;
+ unsigned int cmd, shift;
+ unsigned long addr;
+ u32 data, ret;
+
+ BUG_ON(((port & 0x3ul) + size) > 4);
+
+ addr = get_bus_address(phb, port);
+ shift = addr & 0x3ul;
+ byte_enable = ((1 << size) - 1) << shift;
+ cmd = PEXDCMND_IO_READ | (byte_enable << PEXDCMND_BYTE_EN_SHIFT);
+ PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul));
+ PEX_OUT(phb->cfg_addr, PEXDCMND, cmd);
+ data = PEX_IN(phb->cfg_addr, PEXDRDATA);
+ ret = (data >> (shift * 8)) & (0xFFFFFFFF >> ((4 - size) * 8));
+
+ pr_debug("PCIEX:PIO READ:port=0x%lx, addr=0x%lx, size=%d, be=%x,"
+ " cmd=%x, data=%x, ret=%x\n", port, addr, size, byte_enable,
+ cmd, data, ret);
+
+ return ret;
+}
+
+static void scc_pciex_write_port(struct pci_controller *phb,
+ unsigned long port, int size, u32 val)
+{
+ unsigned int byte_enable;
+ unsigned int cmd, shift;
+ unsigned long addr;
+ u32 data;
+
+ BUG_ON(((port & 0x3ul) + size) > 4);
+
+ addr = get_bus_address(phb, port);
+ shift = addr & 0x3ul;
+ byte_enable = ((1 << size) - 1) << shift;
+ cmd = PEXDCMND_IO_WRITE | (byte_enable << PEXDCMND_BYTE_EN_SHIFT);
+ data = (val & (0xFFFFFFFF >> (4 - size) * 8)) << (shift * 8);
+ PEX_OUT(phb->cfg_addr, PEXDADRS, (addr & ~0x3ul));
+ PEX_OUT(phb->cfg_addr, PEXDCMND, cmd);
+ PEX_OUT(phb->cfg_addr, PEXDWDATA, data);
+
+ pr_debug("PCIEX:PIO WRITE:port=0x%lx, addr=%lx, size=%d, val=%x,"
+ " be=%x, cmd=%x, data=%x\n", port, addr, size, val,
+ byte_enable, cmd, data);
+}
+
+static u8 __scc_pciex_inb(struct pci_controller *phb, unsigned long port)
+{
+ return (u8)scc_pciex_read_port(phb, port, 1);
+}
+
+static u16 __scc_pciex_inw(struct pci_controller *phb, unsigned long port)
+{
+ u32 data;
+ if ((port & 0x3ul) < 3)
+ data = scc_pciex_read_port(phb, port, 2);
+ else {
+ u32 d1 = scc_pciex_read_port(phb, port, 1);
+ u32 d2 = scc_pciex_read_port(phb, port + 1, 1);
+ data = d1 | (d2 << 8);
+ }
+ return (u16)data;
+}
+
+static u32 __scc_pciex_inl(struct pci_controller *phb, unsigned long port)
+{
+ unsigned int mod = port & 0x3ul;
+ u32 data;
+ if (mod == 0)
+ data = scc_pciex_read_port(phb, port, 4);
+ else {
+ u32 d1 = scc_pciex_read_port(phb, port, 4 - mod);
+ u32 d2 = scc_pciex_read_port(phb, port + 1, mod);
+ data = d1 | (d2 << (mod * 8));
+ }
+ return data;
+}
+
+static void __scc_pciex_outb(struct pci_controller *phb,
+ u8 val, unsigned long port)
+{
+ scc_pciex_write_port(phb, port, 1, (u32)val);
+}
+
+static void __scc_pciex_outw(struct pci_controller *phb,
+ u16 val, unsigned long port)
+{
+ if ((port & 0x3ul) < 3)
+ scc_pciex_write_port(phb, port, 2, (u32)val);
+ else {
+ u32 d1 = val & 0x000000FF;
+ u32 d2 = (val & 0x0000FF00) >> 8;
+ scc_pciex_write_port(phb, port, 1, d1);
+ scc_pciex_write_port(phb, port + 1, 1, d2);
+ }
+}
+
+static void __scc_pciex_outl(struct pci_controller *phb,
+ u32 val, unsigned long port)
+{
+ unsigned int mod = port & 0x3ul;
+ if (mod == 0)
+ scc_pciex_write_port(phb, port, 4, val);
+ else {
+ u32 d1 = val & (0xFFFFFFFFul >> (mod * 8));
+ u32 d2 = val >> ((4 - mod) * 8);
+ scc_pciex_write_port(phb, port, 4 - mod, d1);
+ scc_pciex_write_port(phb, port + 1, mod, d2);
+ }
+}
+
+#define PCIEX_PIO_FUNC(size, name) \
+static u##size scc_pciex_in##name(unsigned long port) \
+{ \
+ struct iowa_bus *bus = iowa_pio_find_bus(port); \
+ u##size data = __scc_pciex_in##name(bus->phb, port); \
+ scc_pciex_io_flush(bus); \
+ return data; \
+} \
+static void scc_pciex_ins##name(unsigned long p, void *b, unsigned long c) \
+{ \
+ struct iowa_bus *bus = iowa_pio_find_bus(p); \
+ u##size *dst = b; \
+ for (; c != 0; c--, dst++) \
+ *dst = cpu_to_le##size(__scc_pciex_in##name(bus->phb, p)); \
+ scc_pciex_io_flush(bus); \
+} \
+static void scc_pciex_out##name(u##size val, unsigned long port) \
+{ \
+ struct iowa_bus *bus = iowa_pio_find_bus(port); \
+ __scc_pciex_out##name(bus->phb, val, port); \
+} \
+static void scc_pciex_outs##name(unsigned long p, const void *b, \
+ unsigned long c) \
+{ \
+ struct iowa_bus *bus = iowa_pio_find_bus(p); \
+ const u##size *src = b; \
+ for (; c != 0; c--, src++) \
+ __scc_pciex_out##name(bus->phb, le##size##_to_cpu(*src), p); \
+}
+#define cpu_to_le8(x) (x)
+#define le8_to_cpu(x) (x)
+PCIEX_PIO_FUNC(8, b)
+PCIEX_PIO_FUNC(16, w)
+PCIEX_PIO_FUNC(32, l)
+
+static struct ppc_pci_io scc_pciex_ops = {
+ .readb = scc_pciex_readb,
+ .readw = scc_pciex_readw,
+ .readl = scc_pciex_readl,
+ .readq = scc_pciex_readq,
+ .readw_be = scc_pciex_readw_be,
+ .readl_be = scc_pciex_readl_be,
+ .readq_be = scc_pciex_readq_be,
+ .readsb = scc_pciex_readsb,
+ .readsw = scc_pciex_readsw,
+ .readsl = scc_pciex_readsl,
+ .memcpy_fromio = scc_pciex_memcpy_fromio,
+ .inb = scc_pciex_inb,
+ .inw = scc_pciex_inw,
+ .inl = scc_pciex_inl,
+ .outb = scc_pciex_outb,
+ .outw = scc_pciex_outw,
+ .outl = scc_pciex_outl,
+ .insb = scc_pciex_insb,
+ .insw = scc_pciex_insw,
+ .insl = scc_pciex_insl,
+ .outsb = scc_pciex_outsb,
+ .outsw = scc_pciex_outsw,
+ .outsl = scc_pciex_outsl,
+};
+
+static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data)
+{
+ dma_addr_t dummy_page_da;
+ void *dummy_page_va;
+
+ dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!dummy_page_va) {
+ pr_err("PCIEX:Alloc dummy_page_va failed\n");
+ return -1;
+ }
+
+ dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dummy_page_da)) {
+ pr_err("PCIEX:Map dummy page failed.\n");
+ kfree(dummy_page_va);
+ return -1;
+ }
+
+ PEX_OUT(bus->phb->cfg_addr, PEXDMRDADR0, dummy_page_da);
+
+ return 0;
+}
+
+/*
+ * config space access
+ */
+#define MK_PEXDADRS(bus_no, dev_no, func_no, addr) \
+ ((uint32_t)(((addr) & ~0x3UL) | \
+ ((bus_no) << PEXDADRS_BUSNO_SHIFT) | \
+ ((dev_no) << PEXDADRS_DEVNO_SHIFT) | \
+ ((func_no) << PEXDADRS_FUNCNO_SHIFT)))
+
+#define MK_PEXDCMND_BYTE_EN(addr, size) \
+ ((((0x1 << (size))-1) << ((addr) & 0x3)) << PEXDCMND_BYTE_EN_SHIFT)
+#define MK_PEXDCMND(cmd, addr, size) ((cmd) | MK_PEXDCMND_BYTE_EN(addr, size))
+
+static uint32_t config_read_pciex_dev(unsigned int __iomem *base,
+ uint64_t bus_no, uint64_t dev_no, uint64_t func_no,
+ uint64_t off, uint64_t size)
+{
+ uint32_t ret;
+ uint32_t addr, cmd;
+
+ addr = MK_PEXDADRS(bus_no, dev_no, func_no, off);
+ cmd = MK_PEXDCMND(PEXDCMND_CONFIG_READ, off, size);
+ PEX_OUT(base, PEXDADRS, addr);
+ PEX_OUT(base, PEXDCMND, cmd);
+ ret = (PEX_IN(base, PEXDRDATA)
+ >> ((off & (4-size)) * 8)) & ((0x1 << (size * 8)) - 1);
+ return ret;
+}
+
+static void config_write_pciex_dev(unsigned int __iomem *base, uint64_t bus_no,
+ uint64_t dev_no, uint64_t func_no, uint64_t off, uint64_t size,
+ uint32_t data)
+{
+ uint32_t addr, cmd;
+
+ addr = MK_PEXDADRS(bus_no, dev_no, func_no, off);
+ cmd = MK_PEXDCMND(PEXDCMND_CONFIG_WRITE, off, size);
+ PEX_OUT(base, PEXDADRS, addr);
+ PEX_OUT(base, PEXDCMND, cmd);
+ PEX_OUT(base, PEXDWDATA,
+ (data & ((0x1 << (size * 8)) - 1)) << ((off & (4-size)) * 8));
+}
+
+#define MK_PEXCADRS_BYTE_EN(off, len) \
+ ((((0x1 << (len)) - 1) << ((off) & 0x3)) << PEXCADRS_BYTE_EN_SHIFT)
+#define MK_PEXCADRS(cmd, addr, size) \
+ ((cmd) | MK_PEXCADRS_BYTE_EN(addr, size) | ((addr) & ~0x3))
+static uint32_t config_read_pciex_rc(unsigned int __iomem *base,
+ uint32_t where, uint32_t size)
+{
+ PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_READ, where, size));
+ return (PEX_IN(base, PEXCRDATA)
+ >> ((where & (4 - size)) * 8)) & ((0x1 << (size * 8)) - 1);
+}
+
+static void config_write_pciex_rc(unsigned int __iomem *base, uint32_t where,
+ uint32_t size, uint32_t val)
+{
+ uint32_t data;
+
+ data = (val & ((0x1 << (size * 8)) - 1)) << ((where & (4 - size)) * 8);
+ PEX_OUT(base, PEXCADRS, MK_PEXCADRS(PEXCADRS_CMD_WRITE, where, size));
+ PEX_OUT(base, PEXCWDATA, data);
+}
+
+/* Interfaces */
+/* Note: Work-around
+ * On SCC PCIEXC, one device is seen on all 32 dev_no.
+ * As SCC PCIEXC can have only one device on the bus, we look only one dev_no.
+ * (dev_no = 1)
+ */
+static int scc_pciex_read_config(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, unsigned int *val)
+{
+ struct device_node *dn;
+ struct pci_controller *phb;
+
+ dn = bus->sysdata;
+ phb = pci_find_hose_for_OF_device(dn);
+
+ if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1) {
+ *val = ~0;
+ return PCIBIOS_DEVICE_NOT_FOUND;
+ }
+
+ if (bus->number == 0 && PCI_SLOT(devfn) == 0)
+ *val = config_read_pciex_rc(phb->cfg_addr, where, size);
+ else
+ *val = config_read_pciex_dev(phb->cfg_addr, bus->number,
+ PCI_SLOT(devfn), PCI_FUNC(devfn), where, size);
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static int scc_pciex_write_config(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, unsigned int val)
+{
+ struct device_node *dn;
+ struct pci_controller *phb;
+
+ dn = bus->sysdata;
+ phb = pci_find_hose_for_OF_device(dn);
+
+ if (bus->number == phb->first_busno && PCI_SLOT(devfn) != 1)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ if (bus->number == 0 && PCI_SLOT(devfn) == 0)
+ config_write_pciex_rc(phb->cfg_addr, where, size, val);
+ else
+ config_write_pciex_dev(phb->cfg_addr, bus->number,
+ PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+ return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops scc_pciex_pci_ops = {
+ scc_pciex_read_config,
+ scc_pciex_write_config,
+};
+
+static void pciex_clear_intr_all(unsigned int __iomem *base)
+{
+ PEX_OUT(base, PEXAERRSTS, 0xffffffff);
+ PEX_OUT(base, PEXPRERRSTS, 0xffffffff);
+ PEX_OUT(base, PEXINTSTS, 0xffffffff);
+}
+
+#if 0
+static void pciex_disable_intr_all(unsigned int *base)
+{
+ PEX_OUT(base, PEXINTMASK, 0x0);
+ PEX_OUT(base, PEXAERRMASK, 0x0);
+ PEX_OUT(base, PEXPRERRMASK, 0x0);
+ PEX_OUT(base, PEXVDMASK, 0x0);
+}
+#endif
+
+static void pciex_enable_intr_all(unsigned int __iomem *base)
+{
+ PEX_OUT(base, PEXINTMASK, 0x0000e7f1);
+ PEX_OUT(base, PEXAERRMASK, 0x03ff01ff);
+ PEX_OUT(base, PEXPRERRMASK, 0x0001010f);
+ PEX_OUT(base, PEXVDMASK, 0x00000001);
+}
+
+static void pciex_check_status(unsigned int __iomem *base)
+{
+ uint32_t err = 0;
+ uint32_t intsts, aerr, prerr, rcvcp, lenerr;
+ uint32_t maea, maec;
+
+ intsts = PEX_IN(base, PEXINTSTS);
+ aerr = PEX_IN(base, PEXAERRSTS);
+ prerr = PEX_IN(base, PEXPRERRSTS);
+ rcvcp = PEX_IN(base, PEXRCVCPLIDA);
+ lenerr = PEX_IN(base, PEXLENERRIDA);
+
+ if (intsts || aerr || prerr || rcvcp || lenerr)
+ err = 1;
+
+ pr_info("PCEXC interrupt!!\n");
+ pr_info("PEXINTSTS :0x%08x\n", intsts);
+ pr_info("PEXAERRSTS :0x%08x\n", aerr);
+ pr_info("PEXPRERRSTS :0x%08x\n", prerr);
+ pr_info("PEXRCVCPLIDA :0x%08x\n", rcvcp);
+ pr_info("PEXLENERRIDA :0x%08x\n", lenerr);
+
+ /* print detail of Protection Error */
+ if (intsts & 0x00004000) {
+ uint32_t i, n;
+ for (i = 0; i < 4; i++) {
+ n = 1 << i;
+ if (prerr & n) {
+ maea = PEX_IN(base, PEXMAEA(i));
+ maec = PEX_IN(base, PEXMAEC(i));
+ pr_info("PEXMAEC%d :0x%08x\n", i, maec);
+ pr_info("PEXMAEA%d :0x%08x\n", i, maea);
+ }
+ }
+ }
+
+ if (err)
+ pciex_clear_intr_all(base);
+}
+
+static irqreturn_t pciex_handle_internal_irq(int irq, void *dev_id)
+{
+ struct pci_controller *phb = dev_id;
+
+ pr_debug("PCIEX:pciex_handle_internal_irq(irq=%d)\n", irq);
+
+ BUG_ON(phb->cfg_addr == NULL);
+
+ pciex_check_status(phb->cfg_addr);
+
+ return IRQ_HANDLED;
+}
+
+static __init int celleb_setup_pciex(struct device_node *node,
+ struct pci_controller *phb)
+{
+ struct resource r;
+ struct of_irq oirq;
+ int virq;
+
+ /* SMMIO registers; used inside this file */
+ if (of_address_to_resource(node, 0, &r)) {
+ pr_err("PCIEXC:Failed to get config resource.\n");
+ return 1;
+ }
+ phb->cfg_addr = ioremap(r.start, r.end - r.start + 1);
+ if (!phb->cfg_addr) {
+ pr_err("PCIEXC:Failed to remap SMMIO region.\n");
+ return 1;
+ }
+
+ /* Not use cfg_data, cmd and data regs are near address reg */
+ phb->cfg_data = NULL;
+
+ /* set pci_ops */
+ phb->ops = &scc_pciex_pci_ops;
+
+ /* internal interrupt handler */
+ if (of_irq_map_one(node, 1, &oirq)) {
+ pr_err("PCIEXC:Failed to map irq\n");
+ goto error;
+ }
+ virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
+ oirq.size);
+ if (request_irq(virq, pciex_handle_internal_irq,
+ IRQF_DISABLED, "pciex", (void *)phb)) {
+ pr_err("PCIEXC:Failed to request irq\n");
+ goto error;
+ }
+
+ /* enable all interrupts */
+ pciex_clear_intr_all(phb->cfg_addr);
+ pciex_enable_intr_all(phb->cfg_addr);
+ /* MSI: TBD */
+
+ return 0;
+
+error:
+ phb->cfg_data = NULL;
+ if (phb->cfg_addr)
+ iounmap(phb->cfg_addr);
+ phb->cfg_addr = NULL;
+ return 1;
+}
+
+struct celleb_phb_spec celleb_pciex_spec __initdata = {
+ .setup = celleb_setup_pciex,
+ .ops = &scc_pciex_ops,
+ .iowa_init = &scc_pciex_iowa_init,
+};
diff --git a/arch/powerpc/platforms/celleb/scc_sio.c b/arch/powerpc/platforms/cell/celleb_scc_sio.c
index 3a16c5b3c46..3a16c5b3c46 100644
--- a/arch/powerpc/platforms/celleb/scc_sio.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_sio.c
diff --git a/arch/powerpc/platforms/celleb/scc_uhc.c b/arch/powerpc/platforms/cell/celleb_scc_uhc.c
index cb430799408..d63b720bfe3 100644
--- a/arch/powerpc/platforms/celleb/scc_uhc.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_uhc.c
@@ -25,7 +25,7 @@
#include <asm/io.h>
#include <asm/machdep.h>
-#include "scc.h"
+#include "celleb_scc.h"
#define UHC_RESET_WAIT_MAX 10000
diff --git a/arch/powerpc/platforms/celleb/setup.c b/arch/powerpc/platforms/cell/celleb_setup.c
index f27ae1e3fb5..b11cb30decb 100644
--- a/arch/powerpc/platforms/celleb/setup.c
+++ b/arch/powerpc/platforms/cell/celleb_setup.c
@@ -56,13 +56,13 @@
#include <asm/rtas.h>
#include <asm/cell-regs.h>
-#include "interrupt.h"
+#include "beat_interrupt.h"
#include "beat_wrapper.h"
#include "beat.h"
-#include "pci.h"
-#include "../cell/interrupt.h"
-#include "../cell/pervasive.h"
-#include "../cell/ras.h"
+#include "celleb_pci.h"
+#include "interrupt.h"
+#include "pervasive.h"
+#include "ras.h"
static char celleb_machine_type[128] = "Celleb";
@@ -114,8 +114,6 @@ static int __init celleb_publish_devices(void)
/* Publish OF platform devices for southbridge IOs */
of_platform_bus_probe(NULL, celleb_bus_ids, NULL);
- celleb_pci_workaround_init();
-
return 0;
}
machine_device_initcall(celleb_beat, celleb_publish_devices);
diff --git a/arch/powerpc/platforms/cell/io-workarounds.c b/arch/powerpc/platforms/cell/io-workarounds.c
index 979d4b67efb..3b84e8be314 100644
--- a/arch/powerpc/platforms/cell/io-workarounds.c
+++ b/arch/powerpc/platforms/cell/io-workarounds.c
@@ -1,6 +1,9 @@
/*
+ * Support PCI IO workaround
+ *
* Copyright (C) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>
* IBM, Corp.
+ * (C) Copyright 2007-2008 TOSHIBA CORPORATION
*
* 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
@@ -9,335 +12,174 @@
#undef DEBUG
#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/pci.h>
+
#include <asm/io.h>
#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
+#include <asm/pgtable.h>
#include <asm/ppc-pci.h>
+#include "io-workarounds.h"
-#define SPIDER_PCI_REG_BASE 0xd000
-#define SPIDER_PCI_VCI_CNTL_STAT 0x0110
-#define SPIDER_PCI_DUMMY_READ 0x0810
-#define SPIDER_PCI_DUMMY_READ_BASE 0x0814
+#define IOWA_MAX_BUS 8
-/* Undefine that to re-enable bogus prefetch
- *
- * Without that workaround, the chip will do bogus prefetch past
- * page boundary from system memory. This setting will disable that,
- * though the documentation is unclear as to the consequences of doing
- * so, either purely performances, or possible misbehaviour... It's not
- * clear wether the chip can handle unaligned accesses at all without
- * prefetching enabled.
- *
- * For now, things appear to be behaving properly with that prefetching
- * disabled and IDE, possibly because IDE isn't doing any unaligned
- * access.
- */
-#define SPIDER_DISABLE_PREFETCH
+static struct iowa_bus iowa_busses[IOWA_MAX_BUS];
+static unsigned int iowa_bus_count;
-#define MAX_SPIDERS 3
+static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
+{
+ int i, j;
+ struct resource *res;
+ unsigned long vstart, vend;
-static struct spider_pci_bus {
- void __iomem *regs;
- unsigned long mmio_start;
- unsigned long mmio_end;
- unsigned long pio_vstart;
- unsigned long pio_vend;
-} spider_pci_busses[MAX_SPIDERS];
-static int spider_pci_count;
+ for (i = 0; i < iowa_bus_count; i++) {
+ struct iowa_bus *bus = &iowa_busses[i];
+ struct pci_controller *phb = bus->phb;
-static struct spider_pci_bus *spider_pci_find(unsigned long vaddr,
- unsigned long paddr)
-{
- int i;
-
- for (i = 0; i < spider_pci_count; i++) {
- struct spider_pci_bus *bus = &spider_pci_busses[i];
- if (paddr && paddr >= bus->mmio_start && paddr < bus->mmio_end)
- return bus;
- if (vaddr && vaddr >= bus->pio_vstart && vaddr < bus->pio_vend)
- return bus;
+ if (vaddr) {
+ vstart = (unsigned long)phb->io_base_virt;
+ vend = vstart + phb->pci_io_size - 1;
+ if ((vaddr >= vstart) && (vaddr <= vend))
+ return bus;
+ }
+
+ if (paddr)
+ for (j = 0; j < 3; j++) {
+ res = &phb->mem_resources[j];
+ if (paddr >= res->start && paddr <= res->end)
+ return bus;
+ }
}
+
return NULL;
}
-static void spider_io_flush(const volatile void __iomem *addr)
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
{
- struct spider_pci_bus *bus;
+ struct iowa_bus *bus;
int token;
- /* Get platform token (set by ioremap) from address */
token = PCI_GET_ADDR_TOKEN(addr);
- /* Fast path if we have a non-0 token, it indicates which bus we
- * are on.
- *
- * If the token is 0, that means either that the ioremap was done
- * before we initialized this layer, or it's a PIO operation. We
- * fallback to a low path in this case. Hopefully, internal devices
- * which are ioremap'ed early should use in_XX/out_XX functions
- * instead of the PCI ones and thus not suffer from the slowdown.
- *
- * Also note that currently, the workaround will not work for areas
- * that are not mapped with PTEs (bolted in the hash table). This
- * is the case for ioremaps done very early at boot (before
- * mem_init_done) and includes the mapping of the ISA IO space.
- *
- * Fortunately, none of the affected devices is expected to do DMA
- * and thus there should be no problem in practice.
- *
- * In order to improve performances, we only do the PTE search for
- * addresses falling in the PHB IO space area. That means it will
- * not work for hotplug'ed PHBs but those don't exist with Spider.
- */
- if (token && token <= spider_pci_count)
- bus = &spider_pci_busses[token - 1];
+ if (token && token <= iowa_bus_count)
+ bus = &iowa_busses[token - 1];
else {
unsigned long vaddr, paddr;
pte_t *ptep;
- /* Fixup physical address */
vaddr = (unsigned long)PCI_FIX_ADDR(addr);
+ if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
+ return NULL;
- /* Check if it's in allowed range for PIO */
- if (vaddr < PHB_IO_BASE || vaddr > PHB_IO_END)
- return;
-
- /* Try to find a PTE. If not, clear the paddr, we'll do
- * a vaddr only lookup (PIO only)
- */
ptep = find_linux_pte(init_mm.pgd, vaddr);
if (ptep == NULL)
paddr = 0;
else
paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+ bus = iowa_pci_find(vaddr, paddr);
- bus = spider_pci_find(vaddr, paddr);
if (bus == NULL)
- return;
+ return NULL;
}
- /* Now do the workaround
- */
- (void)in_be32(bus->regs + SPIDER_PCI_DUMMY_READ);
+ return bus;
}
-static u8 spider_readb(const volatile void __iomem *addr)
+struct iowa_bus *iowa_pio_find_bus(unsigned long port)
{
- u8 val = __do_readb(addr);
- spider_io_flush(addr);
- return val;
+ unsigned long vaddr = (unsigned long)pci_io_base + port;
+ return iowa_pci_find(vaddr, 0);
}
-static u16 spider_readw(const volatile void __iomem *addr)
-{
- u16 val = __do_readw(addr);
- spider_io_flush(addr);
- return val;
-}
-static u32 spider_readl(const volatile void __iomem *addr)
-{
- u32 val = __do_readl(addr);
- spider_io_flush(addr);
- return val;
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) \
+static ret iowa_##name at \
+{ \
+ struct iowa_bus *bus; \
+ bus = iowa_##space##_find_bus(aa); \
+ if (bus && bus->ops && bus->ops->name) \
+ return bus->ops->name al; \
+ return __do_##name al; \
}
-static u64 spider_readq(const volatile void __iomem *addr)
-{
- u64 val = __do_readq(addr);
- spider_io_flush(addr);
- return val;
+#define DEF_PCI_AC_NORET(name, at, al, space, aa) \
+static void iowa_##name at \
+{ \
+ struct iowa_bus *bus; \
+ bus = iowa_##space##_find_bus(aa); \
+ if (bus && bus->ops && bus->ops->name) { \
+ bus->ops->name al; \
+ return; \
+ } \
+ __do_##name al; \
}
-static u16 spider_readw_be(const volatile void __iomem *addr)
-{
- u16 val = __do_readw_be(addr);
- spider_io_flush(addr);
- return val;
-}
+#include <asm/io-defs.h>
-static u32 spider_readl_be(const volatile void __iomem *addr)
-{
- u32 val = __do_readl_be(addr);
- spider_io_flush(addr);
- return val;
-}
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
-static u64 spider_readq_be(const volatile void __iomem *addr)
-{
- u64 val = __do_readq_be(addr);
- spider_io_flush(addr);
- return val;
-}
+static struct ppc_pci_io __initdata iowa_pci_io = {
-static void spider_readsb(const volatile void __iomem *addr, void *buf,
- unsigned long count)
-{
- __do_readsb(addr, buf, count);
- spider_io_flush(addr);
-}
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa) .name = iowa_##name,
+#define DEF_PCI_AC_NORET(name, at, al, space, aa) .name = iowa_##name,
-static void spider_readsw(const volatile void __iomem *addr, void *buf,
- unsigned long count)
-{
- __do_readsw(addr, buf, count);
- spider_io_flush(addr);
-}
+#include <asm/io-defs.h>
-static void spider_readsl(const volatile void __iomem *addr, void *buf,
- unsigned long count)
-{
- __do_readsl(addr, buf, count);
- spider_io_flush(addr);
-}
-
-static void spider_memcpy_fromio(void *dest, const volatile void __iomem *src,
- unsigned long n)
-{
- __do_memcpy_fromio(dest, src, n);
- spider_io_flush(src);
-}
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+};
-static void __iomem * spider_ioremap(unsigned long addr, unsigned long size,
- unsigned long flags)
+static void __iomem *iowa_ioremap(unsigned long addr, unsigned long size,
+ unsigned long flags)
{
- struct spider_pci_bus *bus;
+ struct iowa_bus *bus;
void __iomem *res = __ioremap(addr, size, flags);
int busno;
- pr_debug("spider_ioremap(0x%lx, 0x%lx, 0x%lx) -> 0x%p\n",
- addr, size, flags, res);
-
- bus = spider_pci_find(0, addr);
+ bus = iowa_pci_find(0, addr);
if (bus != NULL) {
- busno = bus - spider_pci_busses;
- pr_debug(" found bus %d, setting token\n", busno);
+ busno = bus - iowa_busses;
PCI_SET_ADDR_TOKEN(res, busno + 1);
}
- pr_debug(" result=0x%p\n", res);
-
return res;
}
-static void __init spider_pci_setup_chip(struct spider_pci_bus *bus)
-{
-#ifdef SPIDER_DISABLE_PREFETCH
- u32 val = in_be32(bus->regs + SPIDER_PCI_VCI_CNTL_STAT);
- pr_debug(" PVCI_Control_Status was 0x%08x\n", val);
- out_be32(bus->regs + SPIDER_PCI_VCI_CNTL_STAT, val | 0x8);
-#endif
-
- /* Configure the dummy address for the workaround */
- out_be32(bus->regs + SPIDER_PCI_DUMMY_READ_BASE, 0x80000000);
-}
-
-static void __init spider_pci_add_one(struct pci_controller *phb)
+/* Regist new bus to support workaround */
+void __init iowa_register_bus(struct pci_controller *phb,
+ struct ppc_pci_io *ops,
+ int (*initfunc)(struct iowa_bus *, void *), void *data)
{
- struct spider_pci_bus *bus = &spider_pci_busses[spider_pci_count];
+ struct iowa_bus *bus;
struct device_node *np = phb->dn;
- struct resource rsrc;
- void __iomem *regs;
- if (spider_pci_count >= MAX_SPIDERS) {
- printk(KERN_ERR "Too many spider bridges, workarounds"
- " disabled for %s\n", np->full_name);
+ if (iowa_bus_count >= IOWA_MAX_BUS) {
+ pr_err("IOWA:Too many pci bridges, "
+ "workarounds disabled for %s\n", np->full_name);
return;
}
- /* Get the registers for the beast */
- if (of_address_to_resource(np, 0, &rsrc)) {
- printk(KERN_ERR "Failed to get registers for spider %s"
- " workarounds disabled\n", np->full_name);
- return;
- }
+ bus = &iowa_busses[iowa_bus_count];
+ bus->phb = phb;
+ bus->ops = ops;
- /* Mask out some useless bits in there to get to the base of the
- * spider chip
- */
- rsrc.start &= ~0xfffffffful;
-
- /* Map them */
- regs = ioremap(rsrc.start + SPIDER_PCI_REG_BASE, 0x1000);
- if (regs == NULL) {
- printk(KERN_ERR "Failed to map registers for spider %s"
- " workarounds disabled\n", np->full_name);
- return;
- }
-
- spider_pci_count++;
-
- /* We assume spiders only have one MMIO resource */
- bus->mmio_start = phb->mem_resources[0].start;
- bus->mmio_end = phb->mem_resources[0].end + 1;
-
- bus->pio_vstart = (unsigned long)phb->io_base_virt;
- bus->pio_vend = bus->pio_vstart + phb->pci_io_size;
-
- bus->regs = regs;
-
- printk(KERN_INFO "PCI: Spider MMIO workaround for %s\n",np->full_name);
+ if (initfunc)
+ if ((*initfunc)(bus, data))
+ return;
- pr_debug(" mmio (P) = 0x%016lx..0x%016lx\n",
- bus->mmio_start, bus->mmio_end);
- pr_debug(" pio (V) = 0x%016lx..0x%016lx\n",
- bus->pio_vstart, bus->pio_vend);
- pr_debug(" regs (P) = 0x%016lx (V) = 0x%p\n",
- rsrc.start + SPIDER_PCI_REG_BASE, bus->regs);
+ iowa_bus_count++;
- spider_pci_setup_chip(bus);
+ pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name);
}
-static struct ppc_pci_io __initdata spider_pci_io = {
- .readb = spider_readb,
- .readw = spider_readw,
- .readl = spider_readl,
- .readq = spider_readq,
- .readw_be = spider_readw_be,
- .readl_be = spider_readl_be,
- .readq_be = spider_readq_be,
- .readsb = spider_readsb,
- .readsw = spider_readsw,
- .readsl = spider_readsl,
- .memcpy_fromio = spider_memcpy_fromio,
-};
-
-static int __init spider_pci_workaround_init(void)
+/* enable IO workaround */
+void __init io_workaround_init(void)
{
- struct pci_controller *phb;
-
- /* Find spider bridges. We assume they have been all probed
- * in setup_arch(). If that was to change, we would need to
- * update this code to cope with dynamically added busses
- */
- list_for_each_entry(phb, &hose_list, list_node) {
- struct device_node *np = phb->dn;
- const char *model = of_get_property(np, "model", NULL);
-
- /* If no model property or name isn't exactly "pci", skip */
- if (model == NULL || strcmp(np->name, "pci"))
- continue;
- /* If model is not "Spider", skip */
- if (strcmp(model, "Spider"))
- continue;
- spider_pci_add_one(phb);
- }
-
- /* No Spider PCI found, exit */
- if (spider_pci_count == 0)
- return 0;
+ static int io_workaround_inited;
- /* Setup IO callbacks. We only setup MMIO reads. PIO reads will
- * fallback to MMIO reads (though without a token, thus slower)
- */
- ppc_pci_io = spider_pci_io;
-
- /* Setup ioremap callback */
- ppc_md.ioremap = spider_ioremap;
-
- return 0;
+ if (io_workaround_inited)
+ return;
+ ppc_pci_io = iowa_pci_io;
+ ppc_md.ioremap = iowa_ioremap;
+ io_workaround_inited = 1;
}
-machine_arch_initcall(cell, spider_pci_workaround_init);
diff --git a/arch/powerpc/platforms/cell/io-workarounds.h b/arch/powerpc/platforms/cell/io-workarounds.h
new file mode 100644
index 00000000000..79d8ed3d510
--- /dev/null
+++ b/arch/powerpc/platforms/cell/io-workarounds.h
@@ -0,0 +1,49 @@
+/*
+ * Support PCI IO workaround
+ *
+ * (C) Copyright 2007-2008 TOSHIBA CORPORATION
+ *
+ * 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.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef _IO_WORKAROUNDS_H
+#define _IO_WORKAROUNDS_H
+
+#include <linux/io.h>
+#include <asm/pci-bridge.h>
+
+/* Bus info */
+struct iowa_bus {
+ struct pci_controller *phb;
+ struct ppc_pci_io *ops;
+ void *private;
+};
+
+void __init io_workaround_init(void);
+void __init iowa_register_bus(struct pci_controller *, struct ppc_pci_io *,
+ int (*)(struct iowa_bus *, void *), void *);
+struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR);
+struct iowa_bus *iowa_pio_find_bus(unsigned long);
+
+extern struct ppc_pci_io spiderpci_ops;
+extern int spiderpci_iowa_init(struct iowa_bus *, void *);
+
+#define SPIDER_PCI_REG_BASE 0xd000
+#define SPIDER_PCI_REG_SIZE 0x1000
+#define SPIDER_PCI_VCI_CNTL_STAT 0x0110
+#define SPIDER_PCI_DUMMY_READ 0x0810
+#define SPIDER_PCI_DUMMY_READ_BASE 0x0814
+
+#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 5c531e8f9f6..ab721b50fbb 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -57,6 +57,7 @@
#include "interrupt.h"
#include "pervasive.h"
#include "ras.h"
+#include "io-workarounds.h"
#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
@@ -117,13 +118,50 @@ static void cell_fixup_pcie_rootcomplex(struct pci_dev *dev)
}
DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, cell_fixup_pcie_rootcomplex);
+static int __devinit cell_setup_phb(struct pci_controller *phb)
+{
+ const char *model;
+ struct device_node *np;
+
+ int rc = rtas_setup_phb(phb);
+ if (rc)
+ return rc;
+
+ np = phb->dn;
+ model = of_get_property(np, "model", NULL);
+ if (model == NULL || strcmp(np->name, "pci"))
+ return 0;
+
+ /* Setup workarounds for spider */
+ if (strcmp(model, "Spider"))
+ return 0;
+
+ iowa_register_bus(phb, &spiderpci_ops, &spiderpci_iowa_init,
+ (void *)SPIDER_PCI_REG_BASE);
+ io_workaround_init();
+
+ return 0;
+}
+
static int __init cell_publish_devices(void)
{
+ struct device_node *root = of_find_node_by_path("/");
+ struct device_node *np;
int node;
/* Publish OF platform devices for southbridge IOs */
of_platform_bus_probe(NULL, NULL, NULL);
+ /* On spider based blades, we need to manually create the OF
+ * platform devices for the PCI host bridges
+ */
+ for_each_child_of_node(root, np) {
+ if (np->type == NULL || (strcmp(np->type, "pci") != 0 &&
+ strcmp(np->type, "pciex") != 0))
+ continue;
+ of_platform_device_create(np, NULL, NULL);
+ }
+
/* There is no device for the MIC memory controller, thus we create
* a platform device for it to attach the EDAC driver to.
*/
@@ -132,6 +170,7 @@ static int __init cell_publish_devices(void)
continue;
platform_device_register_simple("cbe-mic", node, NULL, 0);
}
+
return 0;
}
machine_subsys_initcall(cell, cell_publish_devices);
@@ -213,7 +252,7 @@ static void __init cell_setup_arch(void)
/* Find and initialize PCI host bridges */
init_pci_config_tokens();
- find_and_init_phbs();
+
cbe_pervasive_init();
#ifdef CONFIG_DUMMY_CONSOLE
conswitchp = &dummy_con;
@@ -249,7 +288,7 @@ define_machine(cell) {
.calibrate_decr = generic_calibrate_decr,
.progress = cell_progress,
.init_IRQ = cell_init_irq,
- .pci_setup_phb = rtas_setup_phb,
+ .pci_setup_phb = cell_setup_phb,
#ifdef CONFIG_KEXEC
.machine_kexec = default_machine_kexec,
.machine_kexec_prepare = default_machine_kexec_prepare,
diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c
new file mode 100644
index 00000000000..418b605ac35
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spider-pci.c
@@ -0,0 +1,184 @@
+/*
+ * IO workarounds for PCI on Celleb/Cell platform
+ *
+ * (C) Copyright 2006-2007 TOSHIBA CORPORATION
+ *
+ * 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.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+#include <linux/io.h>
+
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+
+#include "io-workarounds.h"
+
+#define SPIDER_PCI_DISABLE_PREFETCH
+
+struct spiderpci_iowa_private {
+ void __iomem *regs;
+};
+
+static void spiderpci_io_flush(struct iowa_bus *bus)
+{
+ struct spiderpci_iowa_private *priv;
+ u32 val;
+
+ priv = bus->private;
+ val = in_be32(priv->regs + SPIDER_PCI_DUMMY_READ);
+ iosync();
+}
+
+#define SPIDER_PCI_MMIO_READ(name, ret) \
+static ret spiderpci_##name(const PCI_IO_ADDR addr) \
+{ \
+ ret val = __do_##name(addr); \
+ spiderpci_io_flush(iowa_mem_find_bus(addr)); \
+ return val; \
+}
+
+#define SPIDER_PCI_MMIO_READ_STR(name) \
+static void spiderpci_##name(const PCI_IO_ADDR addr, void *buf, \
+ unsigned long count) \
+{ \
+ __do_##name(addr, buf, count); \
+ spiderpci_io_flush(iowa_mem_find_bus(addr)); \
+}
+
+SPIDER_PCI_MMIO_READ(readb, u8)
+SPIDER_PCI_MMIO_READ(readw, u16)
+SPIDER_PCI_MMIO_READ(readl, u32)
+SPIDER_PCI_MMIO_READ(readq, u64)
+SPIDER_PCI_MMIO_READ(readw_be, u16)
+SPIDER_PCI_MMIO_READ(readl_be, u32)
+SPIDER_PCI_MMIO_READ(readq_be, u64)
+SPIDER_PCI_MMIO_READ_STR(readsb)
+SPIDER_PCI_MMIO_READ_STR(readsw)
+SPIDER_PCI_MMIO_READ_STR(readsl)
+
+static void spiderpci_memcpy_fromio(void *dest, const PCI_IO_ADDR src,
+ unsigned long n)
+{
+ __do_memcpy_fromio(dest, src, n);
+ spiderpci_io_flush(iowa_mem_find_bus(src));
+}
+
+static int __init spiderpci_pci_setup_chip(struct pci_controller *phb,
+ void __iomem *regs)
+{
+ void *dummy_page_va;
+ dma_addr_t dummy_page_da;
+
+#ifdef SPIDER_PCI_DISABLE_PREFETCH
+ u32 val = in_be32(regs + SPIDER_PCI_VCI_CNTL_STAT);
+ pr_debug("SPIDER_IOWA:PVCI_Control_Status was 0x%08x\n", val);
+ out_be32(regs + SPIDER_PCI_VCI_CNTL_STAT, val | 0x8);
+#endif /* SPIDER_PCI_DISABLE_PREFETCH */
+
+ /* setup dummy read */
+ /*
+ * On CellBlade, we can't know that which XDR memory is used by
+ * kmalloc() to allocate dummy_page_va.
+ * In order to imporve the performance, the XDR which is used to
+ * allocate dummy_page_va is the nearest the spider-pci.
+ * We have to select the CBE which is the nearest the spider-pci
+ * to allocate memory from the best XDR, but I don't know that
+ * how to do.
+ *
+ * Celleb does not have this problem, because it has only one XDR.
+ */
+ dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!dummy_page_va) {
+ pr_err("SPIDERPCI-IOWA:Alloc dummy_page_va failed.\n");
+ return -1;
+ }
+
+ dummy_page_da = dma_map_single(phb->parent, dummy_page_va,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dummy_page_da)) {
+ pr_err("SPIDER-IOWA:Map dummy page filed.\n");
+ kfree(dummy_page_va);
+ return -1;
+ }
+
+ out_be32(regs + SPIDER_PCI_DUMMY_READ_BASE, dummy_page_da);
+
+ return 0;
+}
+
+int __init spiderpci_iowa_init(struct iowa_bus *bus, void *data)
+{
+ void __iomem *regs = NULL;
+ struct spiderpci_iowa_private *priv;
+ struct device_node *np = bus->phb->dn;
+ struct resource r;
+ unsigned long offset = (unsigned long)data;
+
+ pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%s)\n",
+ np->full_name);
+
+ priv = kzalloc(sizeof(struct spiderpci_iowa_private), GFP_KERNEL);
+ if (!priv) {
+ pr_err("SPIDERPCI-IOWA:"
+ "Can't allocate struct spiderpci_iowa_private");
+ return -1;
+ }
+
+ if (of_address_to_resource(np, 0, &r)) {
+ pr_err("SPIDERPCI-IOWA:Can't get resource.\n");
+ goto error;
+ }
+
+ regs = ioremap(r.start + offset, SPIDER_PCI_REG_SIZE);
+ if (!regs) {
+ pr_err("SPIDERPCI-IOWA:ioremap failed.\n");
+ goto error;
+ }
+ priv->regs = regs;
+ bus->private = priv;
+
+ if (spiderpci_pci_setup_chip(bus->phb, regs))
+ goto error;
+
+ return 0;
+
+error:
+ kfree(priv);
+ bus->private = NULL;
+
+ if (regs)
+ iounmap(regs);
+
+ return -1;
+}
+
+struct ppc_pci_io spiderpci_ops = {
+ .readb = spiderpci_readb,
+ .readw = spiderpci_readw,
+ .readl = spiderpci_readl,
+ .readq = spiderpci_readq,
+ .readw_be = spiderpci_readw_be,
+ .readl_be = spiderpci_readl_be,
+ .readq_be = spiderpci_readq_be,
+ .readsb = spiderpci_readsb,
+ .readsw = spiderpci_readsw,
+ .readsl = spiderpci_readsl,
+ .memcpy_fromio = spiderpci_memcpy_fromio,
+};
+
diff --git a/arch/powerpc/platforms/celleb/Kconfig b/arch/powerpc/platforms/celleb/Kconfig
deleted file mode 100644
index 372891edcdd..00000000000
--- a/arch/powerpc/platforms/celleb/Kconfig
+++ /dev/null
@@ -1,12 +0,0 @@
-config PPC_CELLEB
- bool "Toshiba's Cell Reference Set 'Celleb' Architecture"
- depends on PPC_MULTIPLATFORM && PPC64
- select PPC_CELL
- select PPC_CELL_NATIVE
- select PPC_RTAS
- select PPC_INDIRECT_IO
- select PPC_OF_PLATFORM_PCI
- select HAS_TXX9_SERIAL
- select PPC_UDBG_BEAT
- select USB_OHCI_BIG_ENDIAN_MMIO
- select USB_EHCI_BIG_ENDIAN_MMIO
diff --git a/arch/powerpc/platforms/celleb/Makefile b/arch/powerpc/platforms/celleb/Makefile
deleted file mode 100644
index 889d43f715e..00000000000
--- a/arch/powerpc/platforms/celleb/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-obj-y += interrupt.o iommu.o setup.o \
- htab.o beat.o hvCall.o pci.o \
- scc_epci.o scc_uhc.o \
- io-workarounds.o
-
-obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_PPC_UDBG_BEAT) += udbg_beat.o
-obj-$(CONFIG_SERIAL_TXX9) += scc_sio.o
-obj-$(CONFIG_SPU_BASE) += spu_priv1.o
diff --git a/arch/powerpc/platforms/celleb/io-workarounds.c b/arch/powerpc/platforms/celleb/io-workarounds.c
deleted file mode 100644
index 423339be1ba..00000000000
--- a/arch/powerpc/platforms/celleb/io-workarounds.c
+++ /dev/null
@@ -1,280 +0,0 @@
-/*
- * Support for Celleb io workarounds
- *
- * (C) Copyright 2006-2007 TOSHIBA CORPORATION
- *
- * This file is based to arch/powerpc/platform/cell/io-workarounds.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#undef DEBUG
-
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/irq.h>
-
-#include <asm/io.h>
-#include <asm/prom.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-
-#include "pci.h"
-
-#define MAX_CELLEB_PCI_BUS 4
-
-void *celleb_dummy_page_va;
-
-static struct celleb_pci_bus {
- struct pci_controller *phb;
- void (*dummy_read)(struct pci_controller *);
-} celleb_pci_busses[MAX_CELLEB_PCI_BUS];
-
-static int celleb_pci_count = 0;
-
-static struct celleb_pci_bus *celleb_pci_find(unsigned long vaddr,
- unsigned long paddr)
-{
- int i, j;
- struct resource *res;
-
- for (i = 0; i < celleb_pci_count; i++) {
- struct celleb_pci_bus *bus = &celleb_pci_busses[i];
- struct pci_controller *phb = bus->phb;
- if (paddr)
- for (j = 0; j < 3; j++) {
- res = &phb->mem_resources[j];
- if (paddr >= res->start && paddr <= res->end)
- return bus;
- }
- res = &phb->io_resource;
- if (vaddr && vaddr >= res->start && vaddr <= res->end)
- return bus;
- }
- return NULL;
-}
-
-static void celleb_io_flush(const PCI_IO_ADDR addr)
-{
- struct celleb_pci_bus *bus;
- int token;
-
- token = PCI_GET_ADDR_TOKEN(addr);
-
- if (token && token <= celleb_pci_count)
- bus = &celleb_pci_busses[token - 1];
- else {
- unsigned long vaddr, paddr;
- pte_t *ptep;
-
- vaddr = (unsigned long)PCI_FIX_ADDR(addr);
- if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
- return;
-
- ptep = find_linux_pte(init_mm.pgd, vaddr);
- if (ptep == NULL)
- paddr = 0;
- else
- paddr = pte_pfn(*ptep) << PAGE_SHIFT;
- bus = celleb_pci_find(vaddr, paddr);
-
- if (bus == NULL)
- return;
- }
-
- if (bus->dummy_read)
- bus->dummy_read(bus->phb);
-}
-
-static u8 celleb_readb(const PCI_IO_ADDR addr)
-{
- u8 val;
- val = __do_readb(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u16 celleb_readw(const PCI_IO_ADDR addr)
-{
- u16 val;
- val = __do_readw(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u32 celleb_readl(const PCI_IO_ADDR addr)
-{
- u32 val;
- val = __do_readl(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u64 celleb_readq(const PCI_IO_ADDR addr)
-{
- u64 val;
- val = __do_readq(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u16 celleb_readw_be(const PCI_IO_ADDR addr)
-{
- u16 val;
- val = __do_readw_be(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u32 celleb_readl_be(const PCI_IO_ADDR addr)
-{
- u32 val;
- val = __do_readl_be(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static u64 celleb_readq_be(const PCI_IO_ADDR addr)
-{
- u64 val;
- val = __do_readq_be(addr);
- celleb_io_flush(addr);
- return val;
-}
-
-static void celleb_readsb(const PCI_IO_ADDR addr,
- void *buf, unsigned long count)
-{
- __do_readsb(addr, buf, count);
- celleb_io_flush(addr);
-}
-
-static void celleb_readsw(const PCI_IO_ADDR addr,
- void *buf, unsigned long count)
-{
- __do_readsw(addr, buf, count);
- celleb_io_flush(addr);
-}
-
-static void celleb_readsl(const PCI_IO_ADDR addr,
- void *buf, unsigned long count)
-{
- __do_readsl(addr, buf, count);
- celleb_io_flush(addr);
-}
-
-static void celleb_memcpy_fromio(void *dest,
- const PCI_IO_ADDR src,
- unsigned long n)
-{
- __do_memcpy_fromio(dest, src, n);
- celleb_io_flush(src);
-}
-
-static void __iomem *celleb_ioremap(unsigned long addr,
- unsigned long size,
- unsigned long flags)
-{
- struct celleb_pci_bus *bus;
- void __iomem *res = __ioremap(addr, size, flags);
- int busno;
-
- bus = celleb_pci_find(0, addr);
- if (bus != NULL) {
- busno = bus - celleb_pci_busses;
- PCI_SET_ADDR_TOKEN(res, busno + 1);
- }
- return res;
-}
-
-static void celleb_iounmap(volatile void __iomem *addr)
-{
- return __iounmap(PCI_FIX_ADDR(addr));
-}
-
-static struct ppc_pci_io celleb_pci_io __initdata = {
- .readb = celleb_readb,
- .readw = celleb_readw,
- .readl = celleb_readl,
- .readq = celleb_readq,
- .readw_be = celleb_readw_be,
- .readl_be = celleb_readl_be,
- .readq_be = celleb_readq_be,
- .readsb = celleb_readsb,
- .readsw = celleb_readsw,
- .readsl = celleb_readsl,
- .memcpy_fromio = celleb_memcpy_fromio,
-};
-
-void __init celleb_pci_add_one(struct pci_controller *phb,
- void (*dummy_read)(struct pci_controller *))
-{
- struct celleb_pci_bus *bus = &celleb_pci_busses[celleb_pci_count];
- struct device_node *np = phb->dn;
-
- if (celleb_pci_count >= MAX_CELLEB_PCI_BUS) {
- printk(KERN_ERR "Too many pci bridges, workarounds"
- " disabled for %s\n", np->full_name);
- return;
- }
-
- celleb_pci_count++;
-
- bus->phb = phb;
- bus->dummy_read = dummy_read;
-}
-
-static struct of_device_id celleb_pci_workaround_match[] __initdata = {
- {
- .name = "pci-pseudo",
- .data = fake_pci_workaround_init,
- }, {
- .name = "epci",
- .data = epci_workaround_init,
- }, {
- },
-};
-
-int __init celleb_pci_workaround_init(void)
-{
- struct pci_controller *phb;
- struct device_node *node;
- const struct of_device_id *match;
- void (*init_func)(struct pci_controller *);
-
- celleb_dummy_page_va = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!celleb_dummy_page_va) {
- printk(KERN_ERR "Celleb: dummy read disabled. "
- "Alloc celleb_dummy_page_va failed\n");
- return 1;
- }
-
- list_for_each_entry(phb, &hose_list, list_node) {
- node = phb->dn;
- match = of_match_node(celleb_pci_workaround_match, node);
-
- if (match) {
- init_func = match->data;
- (*init_func)(phb);
- }
- }
-
- ppc_pci_io = celleb_pci_io;
- ppc_md.ioremap = celleb_ioremap;
- ppc_md.iounmap = celleb_iounmap;
-
- return 0;
-}
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index c775cd4b3d6..8ff330d026c 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -59,8 +59,33 @@ system_reset_iSeries:
andc r4,r4,r5
mtspr SPRN_CTRLT,r4
+/* Spin on __secondary_hold_spinloop until it is updated by the boot cpu. */
+/* In the UP case we'll yeild() later, and we will not access the paca anyway */
+#ifdef CONFIG_SMP
1:
HMT_LOW
+ LOAD_REG_IMMEDIATE(r23, __secondary_hold_spinloop)
+ ld r23,0(r23)
+ sync
+ LOAD_REG_IMMEDIATE(r3,current_set)
+ sldi r28,r24,3 /* get current_set[cpu#] */
+ ldx r3,r3,r28
+ addi r1,r3,THREAD_SIZE
+ subi r1,r1,STACK_FRAME_OVERHEAD
+
+ cmpwi 0,r23,0 /* Keep poking the Hypervisor until */
+ bne 2f /* we're released */
+ /* Let the Hypervisor know we are alive */
+ /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
+ lis r3,0x8002
+ rldicr r3,r3,32,15 /* r0 = (r3 << 32) & 0xffff000000000000 */
+ li r0,-1 /* r0=-1 indicates a Hypervisor call */
+ sc /* Invoke the hypervisor via a system call */
+ b 1b
+#endif
+
+2:
+ HMT_LOW
#ifdef CONFIG_SMP
lbz r23,PACAPROCSTART(r13) /* Test if this processor
* should start */
@@ -91,7 +116,7 @@ iSeries_secondary_smp_loop:
li r0,-1 /* r0=-1 indicates a Hypervisor call */
sc /* Invoke the hypervisor via a system call */
mfspr r13,SPRN_SPRG3 /* Put r13 back ???? */
- b 1b /* If SMP not configured, secondaries
+ b 2b /* If SMP not configured, secondaries
* loop forever */
/*** ISeries-LPAR interrupt handlers ***/
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index c73379ec914..1d201782d4e 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -25,6 +25,7 @@
#include <linux/syscalls.h>
#include <linux/ctype.h>
#include <linux/lmb.h>
+#include <linux/of.h>
#include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 306a9d07491..07fe5b69b9e 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -34,3 +34,8 @@ config LPARCFG
help
Provide system capacity information via human readable
<key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
+
+config PPC_PSERIES_DEBUG
+ depends on PPC_PSERIES && PPC_EARLY_DEBUG
+ bool "Enable extra debug logging in platforms/pseries"
+ default y
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index bdae04bb7a0..bd2593ed28d 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -2,6 +2,10 @@ ifeq ($(CONFIG_PPC64),y)
EXTRA_CFLAGS += -mno-minimal-toc
endif
+ifeq ($(CONFIG_PPC_PSERIES_DEBUG),y)
+EXTRA_CFLAGS += -DDEBUG
+endif
+
obj-y := lpar.o hvCall.o nvram.o reconfig.o \
setup.o iommu.o ras.o rtasd.o \
firmware.o power.o
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 550b2f7d2cc..a3fd56b186e 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -39,7 +39,6 @@
#include <asm/ppc-pci.h>
#include <asm/rtas.h>
-#undef DEBUG
/** Overview:
* EEH, or "Extended Error Handling" is a PCI bridge technology for
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index 1e83fcd0df3..ce37040af87 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -28,7 +28,6 @@
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
-#undef DEBUG
/**
* The pci address cache subsystem. This subsystem places
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index b765b7c77b6..9d3a40f4597 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -21,17 +21,11 @@
* 2 of the License, or (at your option) any later version.
*/
-#undef DEBUG
#include <asm/firmware.h>
#include <asm/prom.h>
#include <asm/udbg.h>
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
typedef struct {
unsigned long val;
@@ -72,7 +66,7 @@ void __init fw_feature_init(const char *hypertas, unsigned long len)
const char *s;
int i;
- DBG(" -> fw_feature_init()\n");
+ pr_debug(" -> fw_feature_init()\n");
for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) {
for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) {
@@ -88,5 +82,5 @@ void __init fw_feature_init(const char *hypertas, unsigned long len)
}
}
- DBG(" <- fw_feature_init()\n");
+ pr_debug(" <- fw_feature_init()\n");
}
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index a65c7630820..176f1f39d2d 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -47,7 +47,6 @@
#include "plpar_wrappers.h"
-#define DBG(fmt...)
static void tce_build_pSeries(struct iommu_table *tbl, long index,
long npages, unsigned long uaddr,
@@ -322,7 +321,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
dn = pci_bus_to_OF_node(bus);
- DBG("pci_dma_bus_setup_pSeries: setting up bus %s\n", dn->full_name);
+ pr_debug("pci_dma_bus_setup_pSeries: setting up bus %s\n", dn->full_name);
if (bus->self) {
/* This is not a root bus, any setup will be done for the
@@ -347,7 +346,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling)
children++;
- DBG("Children: %d\n", children);
+ pr_debug("Children: %d\n", children);
/* Calculate amount of DMA window per slot. Each window must be
* a power of two (due to pci_alloc_consistent requirements).
@@ -361,8 +360,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
while (pci->phb->dma_window_size * children > 0x80000000ul)
pci->phb->dma_window_size >>= 1;
- DBG("No ISA/IDE, window size is 0x%lx\n",
- pci->phb->dma_window_size);
+ pr_debug("No ISA/IDE, window size is 0x%lx\n",
+ pci->phb->dma_window_size);
pci->phb->dma_window_base_cur = 0;
return;
@@ -387,8 +386,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
while (pci->phb->dma_window_size * children > 0x70000000ul)
pci->phb->dma_window_size >>= 1;
- DBG("ISA/IDE, window size is 0x%lx\n", pci->phb->dma_window_size);
-
+ pr_debug("ISA/IDE, window size is 0x%lx\n", pci->phb->dma_window_size);
}
@@ -401,7 +399,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
dn = pci_bus_to_OF_node(bus);
- DBG("pci_dma_bus_setup_pSeriesLP: setting up bus %s\n", dn->full_name);
+ pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %s\n",
+ dn->full_name);
/* Find nearest ibm,dma-window, walking up the device tree */
for (pdn = dn; pdn != NULL; pdn = pdn->parent) {
@@ -411,14 +410,14 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
}
if (dma_window == NULL) {
- DBG(" no ibm,dma-window property !\n");
+ pr_debug(" no ibm,dma-window property !\n");
return;
}
ppci = PCI_DN(pdn);
- DBG(" parent is %s, iommu_table: 0x%p\n",
- pdn->full_name, ppci->iommu_table);
+ pr_debug(" parent is %s, iommu_table: 0x%p\n",
+ pdn->full_name, ppci->iommu_table);
if (!ppci->iommu_table) {
tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
@@ -426,7 +425,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window,
bus->number);
ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
- DBG(" created table: %p\n", ppci->iommu_table);
+ pr_debug(" created table: %p\n", ppci->iommu_table);
}
if (pdn != dn)
@@ -439,7 +438,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
struct device_node *dn;
struct iommu_table *tbl;
- DBG("pci_dma_dev_setup_pSeries: %s\n", pci_name(dev));
+ pr_debug("pci_dma_dev_setup_pSeries: %s\n", pci_name(dev));
dn = dev->dev.archdata.of_node;
@@ -450,7 +449,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
if (!dev->bus->self) {
struct pci_controller *phb = PCI_DN(dn)->phb;
- DBG(" --> first child, no bridge. Allocating iommu table.\n");
+ pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
phb->node);
iommu_table_setparms(phb, dn, tbl);
@@ -480,7 +479,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
const void *dma_window = NULL;
struct pci_dn *pci;
- DBG("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
+ pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
/* dev setup for LPAR is a little tricky, since the device tree might
* contain the dma-window properties per-device and not neccesarily
@@ -489,7 +488,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
* already allocated.
*/
dn = pci_device_to_OF_node(dev);
- DBG(" node is %s\n", dn->full_name);
+ pr_debug(" node is %s\n", dn->full_name);
for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
pdn = pdn->parent) {
@@ -504,13 +503,13 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
pci_name(dev), dn? dn->full_name : "<null>");
return;
}
- DBG(" parent is %s\n", pdn->full_name);
+ pr_debug(" parent is %s\n", pdn->full_name);
/* Check for parent == NULL so we don't try to setup the empty EADS
* slots on POWER4 machines.
*/
if (dma_window == NULL || pdn->parent == NULL) {
- DBG(" no dma window for device, linking to parent\n");
+ pr_debug(" no dma window for device, linking to parent\n");
dev->dev.archdata.dma_data = PCI_DN(pdn)->iommu_table;
return;
}
@@ -522,9 +521,9 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window,
pci->phb->bus->number);
pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
- DBG(" created table: %p\n", pci->iommu_table);
+ pr_debug(" created table: %p\n", pci->iommu_table);
} else {
- DBG(" found DMA window, table: %p\n", pci->iommu_table);
+ pr_debug(" found DMA window, table: %p\n", pci->iommu_table);
}
dev->dev.archdata.dma_data = pci->iommu_table;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 9235c469449..2cbaedb17f3 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -19,7 +19,8 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#undef DEBUG_LOW
+/* Enables debugging of low-level hash table routines - careful! */
+#undef DEBUG
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
@@ -42,11 +43,6 @@
#include "plpar_wrappers.h"
#include "pseries.h"
-#ifdef DEBUG_LOW
-#define DBG_LOW(fmt...) do { udbg_printf(fmt); } while(0)
-#else
-#define DBG_LOW(fmt...) do { } while(0)
-#endif
/* in hvCall.S */
EXPORT_SYMBOL(plpar_hcall);
@@ -196,6 +192,8 @@ void __init udbg_init_debug_lpar(void)
udbg_putc = udbg_putcLP;
udbg_getc = udbg_getcLP;
udbg_getc_poll = udbg_getc_pollLP;
+
+ register_early_udbg_console();
}
/* returns 0 if couldn't find or use /chosen/stdout as console */
@@ -288,15 +286,15 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
unsigned long hpte_v, hpte_r;
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
- "rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ pr_debug("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
+ "rflags=%lx, vflags=%lx, psize=%d)\n",
+ hpte_group, va, pa, rflags, vflags, psize);
hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
+ pr_debug(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
/* Now fill in the actual HPTE */
/* Set CEC cookie to 0 */
@@ -313,7 +311,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
if (unlikely(lpar_rc == H_PTEG_FULL)) {
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW(" full\n");
+ pr_debug(" full\n");
return -1;
}
@@ -324,11 +322,11 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
*/
if (unlikely(lpar_rc != H_SUCCESS)) {
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW(" lpar err %d\n", lpar_rc);
+ pr_debug(" lpar err %lu\n", lpar_rc);
return -2;
}
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW(" -> slot: %d\n", slot & 7);
+ pr_debug(" -> slot: %lu\n", slot & 7);
/* Because of iSeries, we have to pass down the secondary
* bucket bit here as well
@@ -420,17 +418,17 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot,
want_v = hpte_encode_avpn(va, psize, ssize);
- DBG_LOW(" update: avpnv=%016lx, hash=%016lx, f=%x, psize: %d ... ",
- want_v, slot, flags, psize);
+ pr_debug(" update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
+ want_v, slot, flags, psize);
lpar_rc = plpar_pte_protect(flags, slot, want_v);
if (lpar_rc == H_NOT_FOUND) {
- DBG_LOW("not found !\n");
+ pr_debug("not found !\n");
return -1;
}
- DBG_LOW("ok\n");
+ pr_debug("ok\n");
BUG_ON(lpar_rc != H_SUCCESS);
@@ -505,8 +503,8 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
unsigned long lpar_rc;
unsigned long dummy1, dummy2;
- DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d",
- slot, va, psize, local);
+ pr_debug(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
+ slot, va, psize, local);
want_v = hpte_encode_avpn(va, psize, ssize);
lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index a1ab25c7082..2b548afd100 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -67,8 +67,6 @@ static int ras_check_exception_token;
static irqreturn_t ras_epow_interrupt(int irq, void *dev_id);
static irqreturn_t ras_error_interrupt(int irq, void *dev_id);
-/* #define DEBUG */
-
static void request_ras_irqs(struct device_node *np,
irq_handler_t handler,
@@ -237,7 +235,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
printk(KERN_EMERG "Error: Fatal hardware error <0x%lx 0x%x>\n",
*((unsigned long *)&ras_log_buf), status);
-#ifndef DEBUG
+#ifndef DEBUG_RTAS_POWER_OFF
/* Don't actually power off when debugging so we can test
* without actually failing while injecting errors.
* Error data will not be logged to syslog.
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index e3078ce4151..befadd4f952 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -29,11 +29,6 @@
#include <asm/atomic.h>
#include <asm/machdep.h>
-#if 0
-#define DEBUG(A...) printk(KERN_ERR A)
-#else
-#define DEBUG(A...)
-#endif
static DEFINE_SPINLOCK(rtasd_log_lock);
@@ -198,7 +193,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
unsigned long s;
int len = 0;
- DEBUG("logging event\n");
+ pr_debug("rtasd: logging event\n");
if (buf == NULL)
return;
@@ -409,7 +404,8 @@ static int rtasd(void *unused)
daemonize("rtasd");
printk(KERN_DEBUG "RTAS daemon started\n");
- DEBUG("will sleep for %d milliseconds\n", (30000/rtas_event_scan_rate));
+ pr_debug("rtasd: will sleep for %d milliseconds\n",
+ (30000 / rtas_event_scan_rate));
/* See if we have any error stored in NVRAM */
memset(logdata, 0, rtas_error_log_max);
@@ -428,9 +424,9 @@ static int rtasd(void *unused)
do_event_scan_all_cpus(1000);
if (surveillance_timeout != -1) {
- DEBUG("enabling surveillance\n");
+ pr_debug("rtasd: enabling surveillance\n");
enable_surveillance(surveillance_timeout);
- DEBUG("surveillance enabled\n");
+ pr_debug("rtasd: surveillance enabled\n");
}
/* Delay should be at least one second since some
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index e5b0ea87016..bec3803f061 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -38,9 +38,7 @@
#define SCANLOG_HWERROR -1
#define SCANLOG_CONTINUE 1
-#define DEBUG(A...) do { if (scanlog_debug) printk(KERN_ERR "scanlog: " A); } while (0)
-static int scanlog_debug;
static unsigned int ibm_scan_log_dump; /* RTAS token */
static struct proc_dir_entry *proc_ppc64_scan_log_dump; /* The proc file */
@@ -86,14 +84,14 @@ static ssize_t scanlog_read(struct file *file, char __user *buf,
memcpy(data, rtas_data_buf, RTAS_DATA_BUF_SIZE);
spin_unlock(&rtas_data_buf_lock);
- DEBUG("status=%d, data[0]=%x, data[1]=%x, data[2]=%x\n",
- status, data[0], data[1], data[2]);
+ pr_debug("scanlog: status=%d, data[0]=%x, data[1]=%x, " \
+ "data[2]=%x\n", status, data[0], data[1], data[2]);
switch (status) {
case SCANLOG_COMPLETE:
- DEBUG("hit eof\n");
+ pr_debug("scanlog: hit eof\n");
return 0;
case SCANLOG_HWERROR:
- DEBUG("hardware error reading scan log data\n");
+ pr_debug("scanlog: hardware error reading data\n");
return -EIO;
case SCANLOG_CONTINUE:
/* We may or may not have data yet */
@@ -110,7 +108,8 @@ static ssize_t scanlog_read(struct file *file, char __user *buf,
/* Assume extended busy */
wait_time = rtas_busy_delay_time(status);
if (!wait_time) {
- printk(KERN_ERR "scanlog: unknown error from rtas: %d\n", status);
+ printk(KERN_ERR "scanlog: unknown error " \
+ "from rtas: %d\n", status);
return -EIO;
}
}
@@ -134,15 +133,9 @@ static ssize_t scanlog_write(struct file * file, const char __user * buf,
if (buf) {
if (strncmp(stkbuf, "reset", 5) == 0) {
- DEBUG("reset scanlog\n");
+ pr_debug("scanlog: reset scanlog\n");
status = rtas_call(ibm_scan_log_dump, 2, 1, NULL, 0, 0);
- DEBUG("rtas returns %d\n", status);
- } else if (strncmp(stkbuf, "debugon", 7) == 0) {
- printk(KERN_ERR "scanlog: debug on\n");
- scanlog_debug = 1;
- } else if (strncmp(stkbuf, "debugoff", 8) == 0) {
- printk(KERN_ERR "scanlog: debug off\n");
- scanlog_debug = 0;
+ pr_debug("scanlog: rtas returns %d\n", status);
}
}
return count;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f66aa9c3b13..f5d29f5b13c 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -16,8 +16,6 @@
* bootup setup stuff..
*/
-#undef DEBUG
-
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
@@ -70,11 +68,6 @@
#include "plpar_wrappers.h"
#include "pseries.h"
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
int fwnmi_active; /* TRUE if an FWNMI handler is present */
@@ -326,7 +319,7 @@ static int pseries_set_xdabr(unsigned long dabr)
*/
static void __init pSeries_init_early(void)
{
- DBG(" -> pSeries_init_early()\n");
+ pr_debug(" -> pSeries_init_early()\n");
if (firmware_has_feature(FW_FEATURE_LPAR))
find_udbg_vterm();
@@ -338,7 +331,7 @@ static void __init pSeries_init_early(void)
iommu_init_early_pSeries();
- DBG(" <- pSeries_init_early()\n");
+ pr_debug(" <- pSeries_init_early()\n");
}
/*
@@ -383,7 +376,7 @@ static int __init pSeries_probe(void)
of_flat_dt_is_compatible(root, "IBM,CBEA"))
return 0;
- DBG("pSeries detected, looking for LPAR capability...\n");
+ pr_debug("pSeries detected, looking for LPAR capability...\n");
/* Now try to figure out if we are running on LPAR */
of_scan_flat_dt(pSeries_probe_hypertas, NULL);
@@ -393,8 +386,8 @@ static int __init pSeries_probe(void)
else
hpte_init_native();
- DBG("Machine is%s LPAR !\n",
- (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
+ pr_debug("Machine is%s LPAR !\n",
+ (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
return 1;
}
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index ea4c65917a6..9d8f8c84ab8 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -12,7 +12,6 @@
* 2 of the License, or (at your option) any later version.
*/
-#undef DEBUG
#include <linux/kernel.h>
#include <linux/module.h>
@@ -51,12 +50,6 @@
#include "plpar_wrappers.h"
#include "pseries.h"
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
/*
* The primary thread of each non-boot processor is recorded here before
@@ -231,7 +224,7 @@ static void __init smp_init_pseries(void)
{
int i;
- DBG(" -> smp_init_pSeries()\n");
+ pr_debug(" -> smp_init_pSeries()\n");
/* Mark threads which are still spinning in hold loops. */
if (cpu_has_feature(CPU_FTR_SMT)) {
@@ -255,7 +248,7 @@ static void __init smp_init_pseries(void)
smp_ops->take_timebase = pSeries_take_timebase;
}
- DBG(" <- smp_init_pSeries()\n");
+ pr_debug(" <- smp_init_pSeries()\n");
}
#ifdef CONFIG_MPIC
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 43df53c30aa..ebebc28fe89 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -9,7 +9,6 @@
* 2 of the License, or (at your option) any later version.
*/
-#undef DEBUG
#include <linux/types.h>
#include <linux/threads.h>
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index d359d6e9297..7f59188cd9a 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/
static int
axon_ram_direct_access(struct block_device *device, sector_t sector,
- unsigned long *data)
+ void **kaddr, unsigned long *pfn)
{
struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset;
@@ -154,7 +154,8 @@ axon_ram_direct_access(struct block_device *device, sector_t sector,
return -ERANGE;
}
- *data = bank->ph_addr + offset;
+ *kaddr = (void *)(bank->ph_addr + offset);
+ *pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
return 0;
}
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 5c1b246aacc..7b45670c7af 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -892,3 +892,44 @@ void fsl_rstcr_restart(char *cmd)
while (1) ;
}
#endif
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+struct platform_diu_data_ops diu_ops = {
+ .diu_size = 1280 * 1024 * 4, /* default one 1280x1024 buffer */
+};
+EXPORT_SYMBOL(diu_ops);
+
+int __init preallocate_diu_videomemory(void)
+{
+ pr_debug("diu_size=%lu\n", diu_ops.diu_size);
+
+ diu_ops.diu_mem = __alloc_bootmem(diu_ops.diu_size, 8, 0);
+ if (!diu_ops.diu_mem) {
+ printk(KERN_ERR "fsl-diu: cannot allocate %lu bytes\n",
+ diu_ops.diu_size);
+ return -ENOMEM;
+ }
+
+ pr_debug("diu_mem=%p\n", diu_ops.diu_mem);
+
+ rh_init(&diu_ops.diu_rh_info, 4096, ARRAY_SIZE(diu_ops.diu_rh_block),
+ diu_ops.diu_rh_block);
+ return rh_attach_region(&diu_ops.diu_rh_info,
+ (unsigned long) diu_ops.diu_mem,
+ diu_ops.diu_size);
+}
+
+static int __init early_parse_diufb(char *p)
+{
+ if (!p)
+ return 1;
+
+ diu_ops.diu_size = _ALIGN_UP(memparse(p, &p), 8);
+
+ pr_debug("diu_size=%lu\n", diu_ops.diu_size);
+
+ return 0;
+}
+early_param("diufb", early_parse_diufb);
+
+#endif
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 74c4a9657b3..52c831fa188 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -17,5 +17,28 @@ extern int fsl_spi_init(struct spi_board_info *board_infos,
void (*deactivate_cs)(u8 cs, u8 polarity));
extern void fsl_rstcr_restart(char *cmd);
+
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+#include <linux/bootmem.h>
+#include <asm/rheap.h>
+struct platform_diu_data_ops {
+ rh_block_t diu_rh_block[16];
+ rh_info_t diu_rh_info;
+ unsigned long diu_size;
+ void *diu_mem;
+
+ unsigned int (*get_pixel_format) (unsigned int bits_per_pixel,
+ int monitor_port);
+ void (*set_gamma_table) (int monitor_port, char *gamma_table_base);
+ void (*set_monitor_port) (int monitor_port);
+ void (*set_pixel_clock) (unsigned int pixclock);
+ ssize_t (*show_monitor_port) (int monitor_port, char *buf);
+ int (*set_sysfs_monitor_port) (int val);
+};
+
+extern struct platform_diu_data_ops diu_ops;
+int __init preallocate_diu_videomemory(void);
+#endif
+
#endif
#endif
diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c
index 047b31027fa..41af1223e2a 100644
--- a/arch/powerpc/sysdev/mv64x60_dev.c
+++ b/arch/powerpc/sysdev/mv64x60_dev.c
@@ -338,15 +338,13 @@ static int __init mv64x60_i2c_device_setup(struct device_node *np, int id)
pdata.freq_m = 8; /* default */
prop = of_get_property(np, "freq_m", NULL);
- if (!prop)
- return -ENODEV;
- pdata.freq_m = *prop;
+ if (prop)
+ pdata.freq_m = *prop;
pdata.freq_m = 3; /* default */
prop = of_get_property(np, "freq_n", NULL);
- if (!prop)
- return -ENODEV;
- pdata.freq_n = *prop;
+ if (prop)
+ pdata.freq_n = *prop;
pdata.timeout = 1000; /* default: 1 second */
@@ -433,9 +431,13 @@ static int __init mv64x60_device_setup(void)
int err;
id = 0;
- for_each_compatible_node(np, "serial", "marvell,mv64360-mpsc")
- if ((err = mv64x60_mpsc_device_setup(np, id++)))
- goto error;
+ for_each_compatible_node(np, "serial", "marvell,mv64360-mpsc") {
+ err = mv64x60_mpsc_device_setup(np, id++);
+ if (err)
+ printk(KERN_ERR "Failed to initialize MV64x60 "
+ "serial device %s: error %d.\n",
+ np->full_name, err);
+ }
id = 0;
id2 = 0;
@@ -443,38 +445,44 @@ static int __init mv64x60_device_setup(void)
pdev = mv64x60_eth_register_shared_pdev(np, id++);
if (IS_ERR(pdev)) {
err = PTR_ERR(pdev);
- goto error;
+ printk(KERN_ERR "Failed to initialize MV64x60 "
+ "network block %s: error %d.\n",
+ np->full_name, err);
+ continue;
}
for_each_child_of_node(np, np2) {
if (!of_device_is_compatible(np2,
"marvell,mv64360-eth"))
continue;
err = mv64x60_eth_device_setup(np2, id2++, pdev);
- if (err) {
- of_node_put(np2);
- goto error;
- }
+ if (err)
+ printk(KERN_ERR "Failed to initialize "
+ "MV64x60 network device %s: "
+ "error %d.\n",
+ np2->full_name, err);
}
}
id = 0;
- for_each_compatible_node(np, "i2c", "marvell,mv64360-i2c")
- if ((err = mv64x60_i2c_device_setup(np, id++)))
- goto error;
+ for_each_compatible_node(np, "i2c", "marvell,mv64360-i2c") {
+ err = mv64x60_i2c_device_setup(np, id++);
+ if (err)
+ printk(KERN_ERR "Failed to initialize MV64x60 I2C "
+ "bus %s: error %d.\n",
+ np->full_name, err);
+ }
/* support up to one watchdog timer */
np = of_find_compatible_node(np, NULL, "marvell,mv64360-wdt");
if (np) {
if ((err = mv64x60_wdt_device_setup(np, id)))
- goto error;
+ printk(KERN_ERR "Failed to initialize MV64x60 "
+ "Watchdog %s: error %d.\n",
+ np->full_name, err);
of_node_put(np);
}
return 0;
-
-error:
- of_node_put(np);
- return err;
}
arch_initcall(mv64x60_device_setup);
diff --git a/arch/powerpc/sysdev/mv64x60_udbg.c b/arch/powerpc/sysdev/mv64x60_udbg.c
index ccdb3b0418f..2792dc8b038 100644
--- a/arch/powerpc/sysdev/mv64x60_udbg.c
+++ b/arch/powerpc/sysdev/mv64x60_udbg.c
@@ -94,7 +94,7 @@ static void mv64x60_udbg_init(void)
if (!np)
return;
- block_index = of_get_property(np, "block-index", NULL);
+ block_index = of_get_property(np, "cell-index", NULL);
if (!block_index)
goto error;
diff --git a/arch/ppc/8260_io/fcc_enet.c b/arch/ppc/8260_io/fcc_enet.c
index bcc3aa9d04f..d38b57e24ce 100644
--- a/arch/ppc/8260_io/fcc_enet.c
+++ b/arch/ppc/8260_io/fcc_enet.c
@@ -165,9 +165,6 @@ static int fcc_enet_set_mac_address(struct net_device *dev, void *addr);
#ifdef CONFIG_SBC82xx
#define F1_RXCLK 9
#define F1_TXCLK 10
-#elif defined(CONFIG_ADS8272)
-#define F1_RXCLK 11
-#define F1_TXCLK 10
#else
#define F1_RXCLK 12
#define F1_TXCLK 11
@@ -175,13 +172,8 @@ static int fcc_enet_set_mac_address(struct net_device *dev, void *addr);
/* FCC2 Clock Source Configuration. There are board specific.
Can only choose from CLK13-16 */
-#ifdef CONFIG_ADS8272
-#define F2_RXCLK 15
-#define F2_TXCLK 16
-#else
#define F2_RXCLK 13
#define F2_TXCLK 14
-#endif
/* FCC3 Clock Source Configuration. There are board specific.
Can only choose from CLK13-16 */
@@ -289,10 +281,7 @@ static int fcc_enet_set_mac_address(struct net_device *dev, void *addr);
/* TQM8260 has MDIO and MDCK on PC30 and PC31 respectively */
#define PC_MDIO ((uint)0x00000002)
#define PC_MDCK ((uint)0x00000001)
-#elif defined(CONFIG_ADS8272)
-#define PC_MDIO ((uint)0x00002000)
-#define PC_MDCK ((uint)0x00001000)
-#elif defined(CONFIG_EST8260) || defined(CONFIG_ADS8260) || defined(CONFIG_PQ2FADS)
+#elif defined(CONFIG_EST8260) || defined(CONFIG_ADS8260)
#define PC_MDIO ((uint)0x00400000)
#define PC_MDCK ((uint)0x00200000)
#else
@@ -2118,11 +2107,6 @@ init_fcc_startup(fcc_info_t *fip, struct net_device *dev)
printk("Can't get FCC IRQ %d\n", fip->fc_interrupt);
#ifdef PHY_INTERRUPT
-#ifdef CONFIG_ADS8272
- if (request_irq(PHY_INTERRUPT, mii_link_interrupt, IRQF_SHARED,
- "mii", dev) < 0)
- printk(KERN_CRIT "Can't get MII IRQ %d\n", PHY_INTERRUPT);
-#else
/* Make IRQn edge triggered. This does not work if PHY_INTERRUPT is
* on Port C.
*/
@@ -2132,7 +2116,6 @@ init_fcc_startup(fcc_info_t *fip, struct net_device *dev)
if (request_irq(PHY_INTERRUPT, mii_link_interrupt, 0,
"mii", dev) < 0)
printk(KERN_CRIT "Can't get MII IRQ %d\n", PHY_INTERRUPT);
-#endif
#endif /* PHY_INTERRUPT */
/* Set GFMR to enable Ethernet operating mode.
diff --git a/arch/ppc/8xx_io/enet.c b/arch/ppc/8xx_io/enet.c
index c6d047ae77a..5899aea1644 100644
--- a/arch/ppc/8xx_io/enet.c
+++ b/arch/ppc/8xx_io/enet.c
@@ -946,29 +946,6 @@ static int __init scc_enet_init(void)
*((volatile uint *)BCSR1) &= ~BCSR1_ETHEN;
#endif
-#ifdef CONFIG_MPC885ADS
-
- /* Deassert PHY reset and enable the PHY.
- */
- {
- volatile uint __iomem *bcsr = ioremap(BCSR_ADDR, BCSR_SIZE);
- uint tmp;
-
- tmp = in_be32(bcsr + 1 /* BCSR1 */);
- tmp |= BCSR1_ETHEN;
- out_be32(bcsr + 1, tmp);
- tmp = in_be32(bcsr + 4 /* BCSR4 */);
- tmp |= BCSR4_ETH10_RST;
- out_be32(bcsr + 4, tmp);
- iounmap(bcsr);
- }
-
- /* On MPC885ADS SCC ethernet PHY defaults to the full duplex mode
- * upon reset. SCC is set to half duplex by default. So this
- * inconsistency should be better fixed by the software.
- */
-#endif
-
dev->base_addr = (unsigned long)ep;
#if 0
dev->name = "CPM_ENET";
diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
index abc877faf12..0f1863ed9c1 100644
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -372,22 +372,6 @@ config MPC8XXFADS
bool "FADS"
select FADS
-config MPC86XADS
- bool "MPC86XADS"
- help
- MPC86x Application Development System by Freescale Semiconductor.
- The MPC86xADS is meant to serve as a platform for s/w and h/w
- development around the MPC86X processor families.
- select FADS
-
-config MPC885ADS
- bool "MPC885ADS"
- help
- Freescale Semiconductor MPC885 Application Development System (ADS).
- Also known as DUET.
- The MPC885ADS is meant to serve as a platform for s/w and h/w
- development around the MPC885 processor family.
-
config TQM823L
bool "TQM823L"
help
@@ -479,53 +463,6 @@ config WINCEPT
endchoice
-menu "Freescale Ethernet driver platform-specific options"
- depends on FS_ENET
-
- config MPC8xx_SECOND_ETH
- bool "Second Ethernet channel"
- depends on (MPC885ADS || MPC86XADS)
- default y
- help
- This enables support for second Ethernet on MPC885ADS and MPC86xADS boards.
- The latter will use SCC1, for 885ADS you can select it below.
-
- choice
- prompt "Second Ethernet channel"
- depends on MPC8xx_SECOND_ETH
- default MPC8xx_SECOND_ETH_FEC2
-
- config MPC8xx_SECOND_ETH_FEC2
- bool "FEC2"
- depends on MPC885ADS
- help
- Enable FEC2 to serve as 2-nd Ethernet channel. Note that SMC2
- (often 2-nd UART) will not work if this is enabled.
-
- config MPC8xx_SECOND_ETH_SCC1
- bool "SCC1"
- depends on MPC86XADS
- select MPC8xx_SCC_ENET_FIXED
- help
- Enable SCC1 to serve as 2-nd Ethernet channel. Note that SMC1
- (often 1-nd UART) will not work if this is enabled.
-
- config MPC8xx_SECOND_ETH_SCC3
- bool "SCC3"
- depends on MPC885ADS
- help
- Enable SCC3 to serve as 2-nd Ethernet channel. Note that SMC1
- (often 1-nd UART) will not work if this is enabled.
-
- endchoice
-
- config MPC8xx_SCC_ENET_FIXED
- depends on MPC8xx_SECOND_ETH_SCC
- default n
- bool "Use fixed MII-less mode for SCC Ethernet"
-
-endmenu
-
choice
prompt "Machine Type"
depends on 6xx
@@ -666,9 +603,6 @@ config TQM8260
End of Life: not yet :-)
URL: <http://www.denx.de/PDF/TQM82xx_SPEC_Rev005.pdf>
-config ADS8272
- bool "ADS8272"
-
config PQ2FADS
bool "Freescale-PQ2FADS"
help
@@ -698,11 +632,6 @@ config EV64360
platform.
endchoice
-config PQ2ADS
- bool
- depends on ADS8272
- default y
-
config TQM8xxL
bool
depends on 8xx && (TQM823L || TQM850L || FPS850L || TQM855L || TQM860L)
@@ -725,15 +654,6 @@ config 8260
this option means that you wish to build a kernel for a machine with
an 8260 class CPU.
-config 8272
- bool
- depends on 6xx
- default y if ADS8272
- select 8260
- help
- The MPC8272 CPM has a different internal dpram setup than other CPM2
- devices
-
config CPM1
bool
depends on 8xx
@@ -1069,7 +989,7 @@ config PCI_8260
config 8260_PCI9
bool "Enable workaround for MPC826x erratum PCI 9"
- depends on PCI_8260 && !ADS8272
+ depends on PCI_8260
default y
choice
diff --git a/arch/ppc/configs/ads8272_defconfig b/arch/ppc/configs/ads8272_defconfig
deleted file mode 100644
index 6619f9118b0..00000000000
--- a/arch/ppc/configs/ads8272_defconfig
+++ /dev/null
@@ -1,930 +0,0 @@
-#
-# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.21-rc5
-# Wed Apr 4 20:55:16 2007
-#
-CONFIG_MMU=y
-CONFIG_GENERIC_HARDIRQS=y
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
-CONFIG_ARCH_HAS_ILOG2_U32=y
-# CONFIG_ARCH_HAS_ILOG2_U64 is not set
-CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_PPC=y
-CONFIG_PPC32=y
-CONFIG_GENERIC_NVRAM=y
-CONFIG_GENERIC_FIND_NEXT_BIT=y
-CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
-CONFIG_ARCH_MAY_HAVE_PC_FDC=y
-CONFIG_GENERIC_BUG=y
-CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
-
-#
-# Code maturity level options
-#
-CONFIG_EXPERIMENTAL=y
-CONFIG_BROKEN_ON_SMP=y
-CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
-CONFIG_LOCALVERSION=""
-CONFIG_LOCALVERSION_AUTO=y
-CONFIG_SWAP=y
-CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
-CONFIG_SYSVIPC_SYSCTL=y
-# CONFIG_POSIX_MQUEUE is not set
-# CONFIG_BSD_PROCESS_ACCT is not set
-# CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
-# CONFIG_AUDIT is not set
-# CONFIG_IKCONFIG is not set
-CONFIG_SYSFS_DEPRECATED=y
-# CONFIG_RELAY is not set
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE=""
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_SYSCTL=y
-CONFIG_EMBEDDED=y
-CONFIG_SYSCTL_SYSCALL=y
-# CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
-CONFIG_PRINTK=y
-CONFIG_BUG=y
-CONFIG_ELF_CORE=y
-CONFIG_BASE_FULL=y
-CONFIG_FUTEX=y
-# CONFIG_EPOLL is not set
-CONFIG_SHMEM=y
-CONFIG_SLAB=y
-CONFIG_VM_EVENT_COUNTERS=y
-CONFIG_RT_MUTEXES=y
-# CONFIG_TINY_SHMEM is not set
-CONFIG_BASE_SMALL=0
-# CONFIG_SLOB is not set
-
-#
-# Loadable module support
-#
-# CONFIG_MODULES is not set
-
-#
-# Block layer
-#
-CONFIG_BLOCK=y
-# CONFIG_LBD is not set
-# CONFIG_BLK_DEV_IO_TRACE is not set
-# CONFIG_LSF is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
-# CONFIG_DEFAULT_AS is not set
-# CONFIG_DEFAULT_DEADLINE is not set
-CONFIG_DEFAULT_CFQ=y
-# CONFIG_DEFAULT_NOOP is not set
-CONFIG_DEFAULT_IOSCHED="cfq"
-
-#
-# Processor
-#
-CONFIG_6xx=y
-# CONFIG_40x is not set
-# CONFIG_44x is not set
-# CONFIG_8xx is not set
-# CONFIG_E200 is not set
-# CONFIG_E500 is not set
-CONFIG_PPC_FPU=y
-# CONFIG_PPC_DCR_NATIVE is not set
-# CONFIG_KEXEC is not set
-# CONFIG_CPU_FREQ is not set
-# CONFIG_WANT_EARLY_SERIAL is not set
-CONFIG_EMBEDDEDBOOT=y
-CONFIG_PPC_STD_MMU=y
-
-#
-# Platform options
-#
-
-#
-# Freescale Ethernet driver platform-specific options
-#
-# CONFIG_PPC_PREP is not set
-# CONFIG_APUS is not set
-# CONFIG_KATANA is not set
-# CONFIG_WILLOW is not set
-# CONFIG_CPCI690 is not set
-# CONFIG_POWERPMC250 is not set
-# CONFIG_CHESTNUT is not set
-# CONFIG_SPRUCE is not set
-# CONFIG_HDPU is not set
-# CONFIG_EV64260 is not set
-# CONFIG_LOPEC is not set
-# CONFIG_MVME5100 is not set
-# CONFIG_PPLUS is not set
-# CONFIG_PRPMC750 is not set
-# CONFIG_PRPMC800 is not set
-# CONFIG_SANDPOINT is not set
-# CONFIG_RADSTONE_PPC7D is not set
-# CONFIG_PAL4 is not set
-# CONFIG_EST8260 is not set
-# CONFIG_SBC82xx is not set
-# CONFIG_SBS8260 is not set
-# CONFIG_RPX8260 is not set
-# CONFIG_TQM8260 is not set
-CONFIG_ADS8272=y
-# CONFIG_PQ2FADS is not set
-# CONFIG_LITE5200 is not set
-# CONFIG_MPC834x_SYS is not set
-# CONFIG_EV64360 is not set
-CONFIG_PQ2ADS=y
-CONFIG_8260=y
-CONFIG_8272=y
-CONFIG_CPM2=y
-# CONFIG_PC_KEYBOARD is not set
-# CONFIG_SMP is not set
-# CONFIG_HIGHMEM is not set
-CONFIG_ARCH_POPULATES_NODE_MAP=y
-# CONFIG_HZ_100 is not set
-CONFIG_HZ_250=y
-# CONFIG_HZ_300 is not set
-# CONFIG_HZ_1000 is not set
-CONFIG_HZ=250
-CONFIG_PREEMPT_NONE=y
-# CONFIG_PREEMPT_VOLUNTARY is not set
-# CONFIG_PREEMPT is not set
-CONFIG_SELECT_MEMORY_MODEL=y
-CONFIG_FLATMEM_MANUAL=y
-# CONFIG_DISCONTIGMEM_MANUAL is not set
-# CONFIG_SPARSEMEM_MANUAL is not set
-CONFIG_FLATMEM=y
-CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
-CONFIG_SPLIT_PTLOCK_CPUS=4
-# CONFIG_RESOURCES_64BIT is not set
-CONFIG_ZONE_DMA_FLAG=1
-CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
-# CONFIG_CMDLINE_BOOL is not set
-# CONFIG_PM is not set
-CONFIG_SECCOMP=y
-CONFIG_ISA_DMA_API=y
-
-#
-# Bus options
-#
-CONFIG_ZONE_DMA=y
-# CONFIG_PPC_I8259 is not set
-CONFIG_PPC_INDIRECT_PCI=y
-CONFIG_PCI=y
-CONFIG_PCI_DOMAINS=y
-CONFIG_PCI_8260=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
-
-#
-# Advanced setup
-#
-# CONFIG_ADVANCED_OPTIONS is not set
-
-#
-# Default settings for advanced configuration options are used
-#
-CONFIG_HIGHMEM_START=0xfe000000
-CONFIG_LOWMEM_SIZE=0x30000000
-CONFIG_KERNEL_START=0xc0000000
-CONFIG_TASK_SIZE=0x80000000
-CONFIG_BOOT_LOAD=0x00400000
-
-#
-# Networking
-#
-CONFIG_NET=y
-
-#
-# Networking options
-#
-# CONFIG_NETDEBUG is not set
-CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
-CONFIG_UNIX=y
-CONFIG_XFRM=y
-# CONFIG_XFRM_USER is not set
-# CONFIG_XFRM_SUB_POLICY is not set
-# CONFIG_XFRM_MIGRATE is not set
-# CONFIG_NET_KEY is not set
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-# CONFIG_IP_ADVANCED_ROUTER is not set
-CONFIG_IP_FIB_HASH=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IP_PNP_RARP is not set
-# CONFIG_NET_IPIP is not set
-# CONFIG_NET_IPGRE is not set
-# CONFIG_IP_MROUTE is not set
-# CONFIG_ARPD is not set
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_AH is not set
-# CONFIG_INET_ESP is not set
-# CONFIG_INET_IPCOMP is not set
-# CONFIG_INET_XFRM_TUNNEL is not set
-# CONFIG_INET_TUNNEL is not set
-CONFIG_INET_XFRM_MODE_TRANSPORT=y
-CONFIG_INET_XFRM_MODE_TUNNEL=y
-CONFIG_INET_XFRM_MODE_BEET=y
-CONFIG_INET_DIAG=y
-CONFIG_INET_TCP_DIAG=y
-# CONFIG_TCP_CONG_ADVANCED is not set
-CONFIG_TCP_CONG_CUBIC=y
-CONFIG_DEFAULT_TCP_CONG="cubic"
-# CONFIG_TCP_MD5SIG is not set
-# CONFIG_IPV6 is not set
-# CONFIG_INET6_XFRM_TUNNEL is not set
-# CONFIG_INET6_TUNNEL is not set
-# CONFIG_NETWORK_SECMARK is not set
-# CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
-# CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
-# CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
-# CONFIG_TIPC is not set
-# CONFIG_ATM is not set
-# CONFIG_BRIDGE is not set
-# CONFIG_VLAN_8021Q is not set
-# CONFIG_DECNET is not set
-# CONFIG_LLC2 is not set
-# CONFIG_IPX is not set
-# CONFIG_ATALK is not set
-# CONFIG_X25 is not set
-# CONFIG_LAPB is not set
-# CONFIG_ECONET is not set
-# CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
-# CONFIG_NET_SCHED is not set
-
-#
-# Network testing
-#
-# CONFIG_NET_PKTGEN is not set
-# CONFIG_HAMRADIO is not set
-# CONFIG_IRDA is not set
-# CONFIG_BT is not set
-# CONFIG_IEEE80211 is not set
-
-#
-# Device Drivers
-#
-
-#
-# Generic Driver Options
-#
-CONFIG_STANDALONE=y
-CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
-# CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
-# CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
-# CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-# CONFIG_PNPACPI is not set
-
-#
-# Block devices
-#
-# CONFIG_BLK_DEV_FD is not set
-# CONFIG_BLK_CPQ_DA is not set
-# CONFIG_BLK_CPQ_CISS_DA is not set
-# CONFIG_BLK_DEV_DAC960 is not set
-# CONFIG_BLK_DEV_UMEM is not set
-# CONFIG_BLK_DEV_COW_COMMON is not set
-CONFIG_BLK_DEV_LOOP=y
-# CONFIG_BLK_DEV_CRYPTOLOOP is not set
-# CONFIG_BLK_DEV_NBD is not set
-# CONFIG_BLK_DEV_SX8 is not set
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_COUNT=16
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
-# CONFIG_CDROM_PKTCDVD is not set
-# CONFIG_ATA_OVER_ETH is not set
-
-#
-# Misc devices
-#
-# CONFIG_SGI_IOC4 is not set
-# CONFIG_TIFM_CORE is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
-# CONFIG_IDE is not set
-
-#
-# SCSI device support
-#
-# CONFIG_RAID_ATTRS is not set
-# CONFIG_SCSI is not set
-# CONFIG_SCSI_NETLINK is not set
-
-#
-# Serial ATA (prod) and Parallel ATA (experimental) drivers
-#
-# CONFIG_ATA is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
-# CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
-# CONFIG_FUSION is not set
-
-#
-# IEEE 1394 (FireWire) support
-#
-# CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
-# CONFIG_I2O is not set
-
-#
-# Macintosh device drivers
-#
-# CONFIG_MAC_EMUMOUSEBTN is not set
-# CONFIG_WINDFARM is not set
-
-#
-# Network device support
-#
-CONFIG_NETDEVICES=y
-# CONFIG_DUMMY is not set
-# CONFIG_BONDING is not set
-# CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
-
-#
-# ARCnet devices
-#
-# CONFIG_ARCNET is not set
-
-#
-# PHY device support
-#
-CONFIG_PHYLIB=y
-
-#
-# MII PHY device drivers
-#
-# CONFIG_MARVELL_PHY is not set
-CONFIG_DAVICOM_PHY=y
-# CONFIG_QSEMI_PHY is not set
-# CONFIG_LXT_PHY is not set
-# CONFIG_CICADA_PHY is not set
-# CONFIG_VITESSE_PHY is not set
-# CONFIG_SMSC_PHY is not set
-# CONFIG_BROADCOM_PHY is not set
-# CONFIG_FIXED_PHY is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-# CONFIG_HAPPYMEAL is not set
-# CONFIG_SUNGEM is not set
-# CONFIG_CASSINI is not set
-# CONFIG_NET_VENDOR_3COM is not set
-
-#
-# Tulip family network device support
-#
-# CONFIG_NET_TULIP is not set
-# CONFIG_HP100 is not set
-# CONFIG_NET_PCI is not set
-CONFIG_FS_ENET=y
-# CONFIG_FS_ENET_HAS_SCC is not set
-CONFIG_FS_ENET_HAS_FCC=y
-
-#
-# Ethernet (1000 Mbit)
-#
-# CONFIG_ACENIC is not set
-# CONFIG_DL2K is not set
-# CONFIG_E1000 is not set
-# CONFIG_NS83820 is not set
-# CONFIG_HAMACHI is not set
-# CONFIG_YELLOWFIN is not set
-# CONFIG_R8169 is not set
-# CONFIG_SIS190 is not set
-# CONFIG_SKGE is not set
-# CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
-# CONFIG_TIGON3 is not set
-# CONFIG_BNX2 is not set
-# CONFIG_QLA3XXX is not set
-# CONFIG_ATL1 is not set
-
-#
-# Ethernet (10000 Mbit)
-#
-# CONFIG_CHELSIO_T1 is not set
-# CONFIG_CHELSIO_T3 is not set
-# CONFIG_IXGB is not set
-# CONFIG_S2IO is not set
-# CONFIG_MYRI10GE is not set
-# CONFIG_NETXEN_NIC is not set
-
-#
-# Token Ring devices
-#
-# CONFIG_TR is not set
-
-#
-# Wireless LAN (non-hamradio)
-#
-# CONFIG_NET_RADIO is not set
-
-#
-# Wan interfaces
-#
-# CONFIG_WAN is not set
-# CONFIG_FDDI is not set
-# CONFIG_HIPPI is not set
-# CONFIG_PPP is not set
-# CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
-# CONFIG_NETCONSOLE is not set
-# CONFIG_NETPOLL is not set
-# CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
-# CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
-# CONFIG_PHONE is not set
-
-#
-# Input device support
-#
-CONFIG_INPUT=y
-# CONFIG_INPUT_FF_MEMLESS is not set
-
-#
-# Userland interfaces
-#
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
-# CONFIG_INPUT_EVDEV is not set
-# CONFIG_INPUT_EVBUG is not set
-
-#
-# Input Device Drivers
-#
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_INPUT_JOYSTICK is not set
-# CONFIG_INPUT_TOUCHSCREEN is not set
-# CONFIG_INPUT_MISC is not set
-
-#
-# Hardware I/O ports
-#
-# CONFIG_SERIO is not set
-# CONFIG_GAMEPORT is not set
-
-#
-# Character devices
-#
-# CONFIG_VT is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
-
-#
-# Serial drivers
-#
-# CONFIG_SERIAL_8250 is not set
-
-#
-# Non-8250 serial port support
-#
-# CONFIG_SERIAL_UARTLITE is not set
-CONFIG_SERIAL_CORE=y
-CONFIG_SERIAL_CORE_CONSOLE=y
-CONFIG_SERIAL_CPM=y
-CONFIG_SERIAL_CPM_CONSOLE=y
-CONFIG_SERIAL_CPM_SCC1=y
-# CONFIG_SERIAL_CPM_SCC2 is not set
-# CONFIG_SERIAL_CPM_SCC3 is not set
-CONFIG_SERIAL_CPM_SCC4=y
-# CONFIG_SERIAL_CPM_SMC1 is not set
-# CONFIG_SERIAL_CPM_SMC2 is not set
-# CONFIG_SERIAL_JSM is not set
-CONFIG_UNIX98_PTYS=y
-CONFIG_LEGACY_PTYS=y
-CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
-# CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
-CONFIG_HW_RANDOM=y
-# CONFIG_NVRAM is not set
-CONFIG_GEN_RTC=y
-# CONFIG_GEN_RTC_X is not set
-# CONFIG_DTLK is not set
-# CONFIG_R3964 is not set
-# CONFIG_APPLICOM is not set
-# CONFIG_AGP is not set
-# CONFIG_DRM is not set
-# CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
-# CONFIG_TCG_TPM is not set
-
-#
-# I2C support
-#
-# CONFIG_I2C is not set
-
-#
-# SPI support
-#
-# CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
-# CONFIG_W1 is not set
-
-#
-# Hardware Monitoring support
-#
-CONFIG_HWMON=y
-# CONFIG_HWMON_VID is not set
-# CONFIG_SENSORS_ABITUGURU is not set
-# CONFIG_SENSORS_F71805F is not set
-# CONFIG_SENSORS_PC87427 is not set
-# CONFIG_SENSORS_VT1211 is not set
-# CONFIG_HWMON_DEBUG_CHIP is not set
-
-#
-# Multifunction device drivers
-#
-# CONFIG_MFD_SM501 is not set
-
-#
-# Multimedia devices
-#
-# CONFIG_VIDEO_DEV is not set
-
-#
-# Digital Video Broadcasting Devices
-#
-# CONFIG_DVB is not set
-
-#
-# Graphics support
-#
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
-# CONFIG_FB is not set
-# CONFIG_FB_IBM_GXT4500 is not set
-
-#
-# Sound
-#
-# CONFIG_SOUND is not set
-
-#
-# HID Devices
-#
-CONFIG_HID=y
-# CONFIG_HID_DEBUG is not set
-
-#
-# USB support
-#
-CONFIG_USB_ARCH_HAS_HCD=y
-CONFIG_USB_ARCH_HAS_OHCI=y
-CONFIG_USB_ARCH_HAS_EHCI=y
-# CONFIG_USB is not set
-
-#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
-#
-
-#
-# USB Gadget Support
-#
-# CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
-# CONFIG_MMC is not set
-
-#
-# LED devices
-#
-# CONFIG_NEW_LEDS is not set
-
-#
-# LED drivers
-#
-
-#
-# LED Triggers
-#
-
-#
-# InfiniBand support
-#
-# CONFIG_INFINIBAND is not set
-
-#
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
-#
-
-#
-# Real Time Clock
-#
-# CONFIG_RTC_CLASS is not set
-
-#
-# DMA Engine support
-#
-# CONFIG_DMA_ENGINE is not set
-
-#
-# DMA Clients
-#
-
-#
-# DMA Devices
-#
-
-#
-# Auxiliary Display support
-#
-
-#
-# Virtualization
-#
-
-#
-# File systems
-#
-CONFIG_EXT2_FS=y
-# CONFIG_EXT2_FS_XATTR is not set
-# CONFIG_EXT2_FS_XIP is not set
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_XATTR=y
-# CONFIG_EXT3_FS_POSIX_ACL is not set
-# CONFIG_EXT3_FS_SECURITY is not set
-# CONFIG_EXT4DEV_FS is not set
-CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
-CONFIG_FS_MBCACHE=y
-# CONFIG_REISERFS_FS is not set
-# CONFIG_JFS_FS is not set
-CONFIG_FS_POSIX_ACL=y
-# CONFIG_XFS_FS is not set
-# CONFIG_GFS2_FS is not set
-# CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
-CONFIG_INOTIFY=y
-CONFIG_INOTIFY_USER=y
-# CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
-# CONFIG_AUTOFS_FS is not set
-# CONFIG_AUTOFS4_FS is not set
-# CONFIG_FUSE_FS is not set
-
-#
-# CD-ROM/DVD Filesystems
-#
-# CONFIG_ISO9660_FS is not set
-# CONFIG_UDF_FS is not set
-
-#
-# DOS/FAT/NT Filesystems
-#
-# CONFIG_MSDOS_FS is not set
-# CONFIG_VFAT_FS is not set
-# CONFIG_NTFS_FS is not set
-
-#
-# Pseudo filesystems
-#
-CONFIG_PROC_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_PROC_SYSCTL=y
-CONFIG_SYSFS=y
-CONFIG_TMPFS=y
-# CONFIG_TMPFS_POSIX_ACL is not set
-# CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
-# CONFIG_CONFIGFS_FS is not set
-
-#
-# Miscellaneous filesystems
-#
-# CONFIG_ADFS_FS is not set
-# CONFIG_AFFS_FS is not set
-# CONFIG_HFS_FS is not set
-# CONFIG_HFSPLUS_FS is not set
-# CONFIG_BEFS_FS is not set
-# CONFIG_BFS_FS is not set
-# CONFIG_EFS_FS is not set
-# CONFIG_CRAMFS is not set
-# CONFIG_VXFS_FS is not set
-# CONFIG_HPFS_FS is not set
-# CONFIG_QNX4FS_FS is not set
-# CONFIG_SYSV_FS is not set
-# CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-# CONFIG_NFS_DIRECTIO is not set
-# CONFIG_NFSD is not set
-CONFIG_ROOT_NFS=y
-CONFIG_LOCKD=y
-CONFIG_LOCKD_V4=y
-CONFIG_NFS_ACL_SUPPORT=y
-CONFIG_NFS_COMMON=y
-CONFIG_SUNRPC=y
-CONFIG_SUNRPC_GSS=y
-CONFIG_RPCSEC_GSS_KRB5=y
-# CONFIG_RPCSEC_GSS_SPKM3 is not set
-# CONFIG_SMB_FS is not set
-# CONFIG_CIFS is not set
-# CONFIG_NCP_FS is not set
-# CONFIG_CODA_FS is not set
-# CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
-
-#
-# Partition Types
-#
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_ACORN_PARTITION is not set
-# CONFIG_OSF_PARTITION is not set
-# CONFIG_AMIGA_PARTITION is not set
-# CONFIG_ATARI_PARTITION is not set
-# CONFIG_MAC_PARTITION is not set
-# CONFIG_MSDOS_PARTITION is not set
-# CONFIG_LDM_PARTITION is not set
-# CONFIG_SGI_PARTITION is not set
-# CONFIG_ULTRIX_PARTITION is not set
-# CONFIG_SUN_PARTITION is not set
-# CONFIG_KARMA_PARTITION is not set
-# CONFIG_EFI_PARTITION is not set
-
-#
-# Native Language Support
-#
-# CONFIG_NLS is not set
-
-#
-# Distributed Lock Manager
-#
-# CONFIG_DLM is not set
-# CONFIG_SCC_ENET is not set
-# CONFIG_FEC_ENET is not set
-
-#
-# CPM2 Options
-#
-
-#
-# Library routines
-#
-# CONFIG_CRC_CCITT is not set
-# CONFIG_CRC16 is not set
-# CONFIG_CRC32 is not set
-# CONFIG_LIBCRC32C is not set
-CONFIG_PLIST=y
-CONFIG_HAS_IOMEM=y
-CONFIG_HAS_IOPORT=y
-# CONFIG_PROFILING is not set
-
-#
-# Kernel hacking
-#
-# CONFIG_PRINTK_TIME is not set
-CONFIG_ENABLE_MUST_CHECK=y
-# CONFIG_MAGIC_SYSRQ is not set
-# CONFIG_UNUSED_SYMBOLS is not set
-# CONFIG_DEBUG_FS is not set
-# CONFIG_HEADERS_CHECK is not set
-# CONFIG_DEBUG_KERNEL is not set
-CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_KGDB_CONSOLE is not set
-
-#
-# Security options
-#
-# CONFIG_KEYS is not set
-# CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_ALGAPI=y
-CONFIG_CRYPTO_BLKCIPHER=y
-CONFIG_CRYPTO_MANAGER=y
-# CONFIG_CRYPTO_HMAC is not set
-# CONFIG_CRYPTO_XCBC is not set
-# CONFIG_CRYPTO_NULL is not set
-# CONFIG_CRYPTO_MD4 is not set
-CONFIG_CRYPTO_MD5=y
-# CONFIG_CRYPTO_SHA1 is not set
-# CONFIG_CRYPTO_SHA256 is not set
-# CONFIG_CRYPTO_SHA512 is not set
-# CONFIG_CRYPTO_WP512 is not set
-# CONFIG_CRYPTO_TGR192 is not set
-# CONFIG_CRYPTO_GF128MUL is not set
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_PCBC=y
-# CONFIG_CRYPTO_LRW is not set
-CONFIG_CRYPTO_DES=y
-# CONFIG_CRYPTO_FCRYPT is not set
-# CONFIG_CRYPTO_BLOWFISH is not set
-# CONFIG_CRYPTO_TWOFISH is not set
-# CONFIG_CRYPTO_SERPENT is not set
-# CONFIG_CRYPTO_AES is not set
-# CONFIG_CRYPTO_CAST5 is not set
-# CONFIG_CRYPTO_CAST6 is not set
-# CONFIG_CRYPTO_TEA is not set
-# CONFIG_CRYPTO_ARC4 is not set
-# CONFIG_CRYPTO_KHAZAD is not set
-# CONFIG_CRYPTO_ANUBIS is not set
-# CONFIG_CRYPTO_DEFLATE is not set
-# CONFIG_CRYPTO_MICHAEL_MIC is not set
-# CONFIG_CRYPTO_CRC32C is not set
-# CONFIG_CRYPTO_CAMELLIA is not set
-
-#
-# Hardware crypto devices
-#
diff --git a/arch/ppc/configs/mpc86x_ads_defconfig b/arch/ppc/configs/mpc86x_ads_defconfig
deleted file mode 100644
index f63c6f59d68..00000000000
--- a/arch/ppc/configs/mpc86x_ads_defconfig
+++ /dev/null
@@ -1,633 +0,0 @@
-#
-# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.12-rc4
-# Tue Jun 14 13:36:35 2005
-#
-CONFIG_MMU=y
-CONFIG_GENERIC_HARDIRQS=y
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
-CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_HAVE_DEC_LOCK=y
-CONFIG_PPC=y
-CONFIG_PPC32=y
-CONFIG_GENERIC_NVRAM=y
-CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
-
-#
-# Code maturity level options
-#
-CONFIG_EXPERIMENTAL=y
-# CONFIG_CLEAN_COMPILE is not set
-CONFIG_BROKEN=y
-CONFIG_BROKEN_ON_SMP=y
-CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
-CONFIG_LOCALVERSION=""
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-# CONFIG_POSIX_MQUEUE is not set
-# CONFIG_BSD_PROCESS_ACCT is not set
-CONFIG_SYSCTL=y
-# CONFIG_AUDIT is not set
-# CONFIG_HOTPLUG is not set
-CONFIG_KOBJECT_UEVENT=y
-# CONFIG_IKCONFIG is not set
-CONFIG_EMBEDDED=y
-# CONFIG_KALLSYMS is not set
-CONFIG_PRINTK=y
-CONFIG_BUG=y
-# CONFIG_BASE_FULL is not set
-CONFIG_FUTEX=y
-# CONFIG_EPOLL is not set
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-# CONFIG_SHMEM is not set
-CONFIG_CC_ALIGN_FUNCTIONS=0
-CONFIG_CC_ALIGN_LABELS=0
-CONFIG_CC_ALIGN_LOOPS=0
-CONFIG_CC_ALIGN_JUMPS=0
-CONFIG_TINY_SHMEM=y
-CONFIG_BASE_SMALL=1
-
-#
-# Loadable module support
-#
-CONFIG_MODULES=y
-# CONFIG_MODULE_UNLOAD is not set
-CONFIG_OBSOLETE_MODPARM=y
-# CONFIG_MODVERSIONS is not set
-# CONFIG_MODULE_SRCVERSION_ALL is not set
-# CONFIG_KMOD is not set
-
-#
-# Processor
-#
-# CONFIG_6xx is not set
-# CONFIG_40x is not set
-# CONFIG_44x is not set
-# CONFIG_POWER3 is not set
-# CONFIG_POWER4 is not set
-CONFIG_8xx=y
-# CONFIG_E500 is not set
-# CONFIG_MATH_EMULATION is not set
-# CONFIG_CPU_FREQ is not set
-CONFIG_EMBEDDEDBOOT=y
-# CONFIG_PM is not set
-CONFIG_NOT_COHERENT_CACHE=y
-
-#
-# Platform options
-#
-CONFIG_FADS=y
-# CONFIG_RPXLITE is not set
-# CONFIG_RPXCLASSIC is not set
-# CONFIG_BSEIP is not set
-# CONFIG_MPC8XXFADS is not set
-CONFIG_MPC86XADS=y
-# CONFIG_TQM823L is not set
-# CONFIG_TQM850L is not set
-# CONFIG_TQM855L is not set
-# CONFIG_TQM860L is not set
-# CONFIG_FPS850L is not set
-# CONFIG_SPD823TS is not set
-# CONFIG_IVMS8 is not set
-# CONFIG_IVML24 is not set
-# CONFIG_SM850 is not set
-# CONFIG_HERMES_PRO is not set
-# CONFIG_IP860 is not set
-# CONFIG_LWMON is not set
-# CONFIG_PCU_E is not set
-# CONFIG_CCM is not set
-# CONFIG_LANTEC is not set
-# CONFIG_MBX is not set
-# CONFIG_WINCEPT is not set
-# CONFIG_SMP is not set
-# CONFIG_PREEMPT is not set
-# CONFIG_HIGHMEM is not set
-CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
-# CONFIG_CMDLINE_BOOL is not set
-CONFIG_ISA_DMA_API=y
-
-#
-# Bus options
-#
-# CONFIG_PCI is not set
-# CONFIG_PCI_DOMAINS is not set
-# CONFIG_PCI_QSPAN is not set
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
-# CONFIG_PCCARD is not set
-
-#
-# Advanced setup
-#
-# CONFIG_ADVANCED_OPTIONS is not set
-
-#
-# Default settings for advanced configuration options are used
-#
-CONFIG_HIGHMEM_START=0xfe000000
-CONFIG_LOWMEM_SIZE=0x30000000
-CONFIG_KERNEL_START=0xc0000000
-CONFIG_TASK_SIZE=0x80000000
-CONFIG_CONSISTENT_START=0xff100000
-CONFIG_CONSISTENT_SIZE=0x00200000
-CONFIG_BOOT_LOAD=0x00400000
-
-#
-# Device Drivers
-#
-
-#
-# Generic Driver Options
-#
-# CONFIG_STANDALONE is not set
-CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
-
-#
-# Memory Technology Devices (MTD)
-#
-# CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
-# CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-
-#
-# Block devices
-#
-# CONFIG_BLK_DEV_FD is not set
-# CONFIG_BLK_DEV_COW_COMMON is not set
-CONFIG_BLK_DEV_LOOP=y
-# CONFIG_BLK_DEV_CRYPTOLOOP is not set
-# CONFIG_BLK_DEV_NBD is not set
-# CONFIG_BLK_DEV_RAM is not set
-CONFIG_BLK_DEV_RAM_COUNT=16
-CONFIG_INITRAMFS_SOURCE=""
-# CONFIG_LBD is not set
-# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-CONFIG_IOSCHED_AS=y
-CONFIG_IOSCHED_DEADLINE=y
-CONFIG_IOSCHED_CFQ=y
-# CONFIG_ATA_OVER_ETH is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
-# CONFIG_IDE is not set
-
-#
-# SCSI device support
-#
-# CONFIG_SCSI is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
-# CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
-
-#
-# IEEE 1394 (FireWire) support
-#
-# CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
-
-#
-# Macintosh device drivers
-#
-
-#
-# Networking support
-#
-CONFIG_NET=y
-
-#
-# Networking options
-#
-CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
-CONFIG_UNIX=y
-# CONFIG_NET_KEY is not set
-CONFIG_INET=y
-# CONFIG_IP_MULTICAST is not set
-# CONFIG_IP_ADVANCED_ROUTER is not set
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-# CONFIG_IP_PNP_BOOTP is not set
-# CONFIG_IP_PNP_RARP is not set
-# CONFIG_NET_IPIP is not set
-# CONFIG_NET_IPGRE is not set
-# CONFIG_ARPD is not set
-# CONFIG_SYN_COOKIES is not set
-# CONFIG_INET_AH is not set
-# CONFIG_INET_ESP is not set
-# CONFIG_INET_IPCOMP is not set
-# CONFIG_INET_TUNNEL is not set
-CONFIG_IP_TCPDIAG=y
-# CONFIG_IP_TCPDIAG_IPV6 is not set
-CONFIG_IPV6=m
-# CONFIG_IPV6_PRIVACY is not set
-# CONFIG_INET6_AH is not set
-# CONFIG_INET6_ESP is not set
-# CONFIG_INET6_IPCOMP is not set
-# CONFIG_INET6_TUNNEL is not set
-# CONFIG_IPV6_TUNNEL is not set
-# CONFIG_NETFILTER is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
-# CONFIG_IP_SCTP is not set
-# CONFIG_ATM is not set
-# CONFIG_BRIDGE is not set
-# CONFIG_VLAN_8021Q is not set
-# CONFIG_DECNET is not set
-# CONFIG_LLC2 is not set
-# CONFIG_IPX is not set
-# CONFIG_ATALK is not set
-# CONFIG_X25 is not set
-# CONFIG_LAPB is not set
-# CONFIG_NET_DIVERT is not set
-# CONFIG_ECONET is not set
-# CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
-# CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
-
-#
-# Network testing
-#
-# CONFIG_NET_PKTGEN is not set
-# CONFIG_NETPOLL is not set
-# CONFIG_NET_POLL_CONTROLLER is not set
-# CONFIG_HAMRADIO is not set
-# CONFIG_IRDA is not set
-# CONFIG_BT is not set
-CONFIG_NETDEVICES=y
-# CONFIG_DUMMY is not set
-# CONFIG_BONDING is not set
-# CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
-CONFIG_NET_ETHERNET=y
-# CONFIG_MII is not set
-# CONFIG_OAKNET is not set
-
-#
-# Ethernet (1000 Mbit)
-#
-
-#
-# Ethernet (10000 Mbit)
-#
-
-#
-# Token Ring devices
-#
-
-#
-# Wireless LAN (non-hamradio)
-#
-# CONFIG_NET_RADIO is not set
-
-#
-# Wan interfaces
-#
-# CONFIG_WAN is not set
-# CONFIG_PPP is not set
-# CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
-# CONFIG_NETCONSOLE is not set
-
-#
-# ISDN subsystem
-#
-# CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
-# CONFIG_PHONE is not set
-
-#
-# Input device support
-#
-# CONFIG_INPUT is not set
-
-#
-# Hardware I/O ports
-#
-# CONFIG_SERIO is not set
-# CONFIG_GAMEPORT is not set
-CONFIG_SOUND_GAMEPORT=y
-
-#
-# Character devices
-#
-# CONFIG_VT is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
-
-#
-# Serial drivers
-#
-# CONFIG_SERIAL_8250 is not set
-
-#
-# Non-8250 serial port support
-#
-CONFIG_SERIAL_CORE=y
-CONFIG_SERIAL_CORE_CONSOLE=y
-CONFIG_SERIAL_CPM=y
-CONFIG_SERIAL_CPM_CONSOLE=y
-# CONFIG_SERIAL_CPM_SCC1 is not set
-# CONFIG_SERIAL_CPM_SCC2 is not set
-# CONFIG_SERIAL_CPM_SCC3 is not set
-# CONFIG_SERIAL_CPM_SCC4 is not set
-CONFIG_SERIAL_CPM_SMC1=y
-# CONFIG_SERIAL_CPM_SMC2 is not set
-CONFIG_UNIX98_PTYS=y
-# CONFIG_LEGACY_PTYS is not set
-
-#
-# IPMI
-#
-# CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
-# CONFIG_NVRAM is not set
-# CONFIG_GEN_RTC is not set
-# CONFIG_DTLK is not set
-# CONFIG_R3964 is not set
-
-#
-# Ftape, the floppy tape device driver
-#
-# CONFIG_AGP is not set
-# CONFIG_DRM is not set
-# CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
-
-#
-# I2C support
-#
-# CONFIG_I2C is not set
-
-#
-# Dallas's 1-wire bus
-#
-# CONFIG_W1 is not set
-
-#
-# Misc devices
-#
-
-#
-# Multimedia devices
-#
-# CONFIG_VIDEO_DEV is not set
-
-#
-# Digital Video Broadcasting Devices
-#
-# CONFIG_DVB is not set
-
-#
-# Graphics support
-#
-# CONFIG_FB is not set
-
-#
-# Sound
-#
-# CONFIG_SOUND is not set
-
-#
-# USB support
-#
-# CONFIG_USB_ARCH_HAS_HCD is not set
-# CONFIG_USB_ARCH_HAS_OHCI is not set
-
-#
-# USB Gadget Support
-#
-# CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
-# CONFIG_MMC is not set
-
-#
-# InfiniBand support
-#
-# CONFIG_INFINIBAND is not set
-
-#
-# File systems
-#
-# CONFIG_EXT2_FS is not set
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
-# CONFIG_REISERFS_FS is not set
-# CONFIG_JFS_FS is not set
-
-#
-# XFS support
-#
-# CONFIG_XFS_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
-# CONFIG_QUOTA is not set
-# CONFIG_DNOTIFY is not set
-# CONFIG_AUTOFS_FS is not set
-# CONFIG_AUTOFS4_FS is not set
-
-#
-# CD-ROM/DVD Filesystems
-#
-# CONFIG_ISO9660_FS is not set
-# CONFIG_UDF_FS is not set
-
-#
-# DOS/FAT/NT Filesystems
-#
-# CONFIG_MSDOS_FS is not set
-# CONFIG_VFAT_FS is not set
-# CONFIG_NTFS_FS is not set
-
-#
-# Pseudo filesystems
-#
-CONFIG_PROC_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_SYSFS=y
-# CONFIG_DEVFS_FS is not set
-# CONFIG_DEVPTS_FS_XATTR is not set
-# CONFIG_TMPFS is not set
-# CONFIG_HUGETLBFS is not set
-# CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
-
-#
-# Miscellaneous filesystems
-#
-# CONFIG_ADFS_FS is not set
-# CONFIG_AFFS_FS is not set
-# CONFIG_HFS_FS is not set
-# CONFIG_HFSPLUS_FS is not set
-# CONFIG_BEFS_FS is not set
-# CONFIG_BFS_FS is not set
-# CONFIG_EFS_FS is not set
-# CONFIG_CRAMFS is not set
-# CONFIG_VXFS_FS is not set
-# CONFIG_HPFS_FS is not set
-# CONFIG_QNX4FS_FS is not set
-# CONFIG_SYSV_FS is not set
-# CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V4=y
-# CONFIG_NFS_DIRECTIO is not set
-# CONFIG_NFSD is not set
-CONFIG_ROOT_NFS=y
-CONFIG_LOCKD=y
-CONFIG_LOCKD_V4=y
-CONFIG_SUNRPC=y
-CONFIG_SUNRPC_GSS=y
-CONFIG_RPCSEC_GSS_KRB5=y
-# CONFIG_RPCSEC_GSS_SPKM3 is not set
-# CONFIG_SMB_FS is not set
-# CONFIG_CIFS is not set
-# CONFIG_NCP_FS is not set
-# CONFIG_CODA_FS is not set
-# CONFIG_AFS_FS is not set
-
-#
-# Partition Types
-#
-# CONFIG_PARTITION_ADVANCED is not set
-CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
-# CONFIG_NLS is not set
-
-#
-# MPC8xx CPM Options
-#
-CONFIG_SCC_ENET=y
-CONFIG_SCC1_ENET=y
-# CONFIG_SCC2_ENET is not set
-# CONFIG_SCC3_ENET is not set
-# CONFIG_FEC_ENET is not set
-# CONFIG_ENET_BIG_BUFFERS is not set
-
-#
-# Generic MPC8xx Options
-#
-# CONFIG_8xx_COPYBACK is not set
-# CONFIG_8xx_CPU6 is not set
-CONFIG_NO_UCODE_PATCH=y
-# CONFIG_USB_SOF_UCODE_PATCH is not set
-# CONFIG_I2C_SPI_UCODE_PATCH is not set
-# CONFIG_I2C_SPI_SMC1_UCODE_PATCH is not set
-
-#
-# Library routines
-#
-# CONFIG_CRC_CCITT is not set
-# CONFIG_CRC32 is not set
-# CONFIG_LIBCRC32C is not set
-
-#
-# Profiling support
-#
-# CONFIG_PROFILING is not set
-
-#
-# Kernel hacking
-#
-# CONFIG_PRINTK_TIME is not set
-# CONFIG_DEBUG_KERNEL is not set
-CONFIG_LOG_BUF_SHIFT=14
-
-#
-# Security options
-#
-# CONFIG_KEYS is not set
-# CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
-CONFIG_CRYPTO=y
-# CONFIG_CRYPTO_HMAC is not set
-# CONFIG_CRYPTO_NULL is not set
-# CONFIG_CRYPTO_MD4 is not set
-CONFIG_CRYPTO_MD5=y
-# CONFIG_CRYPTO_SHA1 is not set
-# CONFIG_CRYPTO_SHA256 is not set
-# CONFIG_CRYPTO_SHA512 is not set
-# CONFIG_CRYPTO_WP512 is not set
-# CONFIG_CRYPTO_TGR192 is not set
-CONFIG_CRYPTO_DES=y
-# CONFIG_CRYPTO_BLOWFISH is not set
-# CONFIG_CRYPTO_TWOFISH is not set
-# CONFIG_CRYPTO_SERPENT is not set
-# CONFIG_CRYPTO_AES is not set
-# CONFIG_CRYPTO_CAST5 is not set
-# CONFIG_CRYPTO_CAST6 is not set
-# CONFIG_CRYPTO_TEA is not set
-# CONFIG_CRYPTO_ARC4 is not set
-# CONFIG_CRYPTO_KHAZAD is not set
-# CONFIG_CRYPTO_ANUBIS is not set
-# CONFIG_CRYPTO_DEFLATE is not set
-# CONFIG_CRYPTO_MICHAEL_MIC is not set
-# CONFIG_CRYPTO_CRC32C is not set
-# CONFIG_CRYPTO_TEST is not set
-
-#
-# Hardware crypto devices
-#
diff --git a/arch/ppc/configs/mpc885ads_defconfig b/arch/ppc/configs/mpc885ads_defconfig
deleted file mode 100644
index 016f94d9325..00000000000
--- a/arch/ppc/configs/mpc885ads_defconfig
+++ /dev/null
@@ -1,622 +0,0 @@
-#
-# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.12-rc6
-# Thu Jun 9 21:17:29 2005
-#
-CONFIG_MMU=y
-CONFIG_GENERIC_HARDIRQS=y
-CONFIG_RWSEM_XCHGADD_ALGORITHM=y
-CONFIG_GENERIC_CALIBRATE_DELAY=y
-CONFIG_HAVE_DEC_LOCK=y
-CONFIG_PPC=y
-CONFIG_PPC32=y
-CONFIG_GENERIC_NVRAM=y
-CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
-
-#
-# Code maturity level options
-#
-CONFIG_EXPERIMENTAL=y
-# CONFIG_CLEAN_COMPILE is not set
-CONFIG_BROKEN=y
-CONFIG_BROKEN_ON_SMP=y
-CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
-CONFIG_LOCALVERSION=""
-# CONFIG_SWAP is not set
-CONFIG_SYSVIPC=y
-# CONFIG_POSIX_MQUEUE is not set
-# CONFIG_BSD_PROCESS_ACCT is not set
-CONFIG_SYSCTL=y
-# CONFIG_AUDIT is not set
-CONFIG_HOTPLUG=y
-CONFIG_KOBJECT_UEVENT=y
-# CONFIG_IKCONFIG is not set
-CONFIG_EMBEDDED=y
-# CONFIG_KALLSYMS is not set
-CONFIG_PRINTK=y
-CONFIG_BUG=y
-CONFIG_BASE_FULL=y
-CONFIG_FUTEX=y
-# CONFIG_EPOLL is not set
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_SHMEM=y
-CONFIG_CC_ALIGN_FUNCTIONS=0
-CONFIG_CC_ALIGN_LABELS=0
-CONFIG_CC_ALIGN_LOOPS=0
-CONFIG_CC_ALIGN_JUMPS=0
-# CONFIG_TINY_SHMEM is not set
-CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
-# CONFIG_MODULES is not set
-
-#
-# Processor
-#
-# CONFIG_6xx is not set
-# CONFIG_40x is not set
-# CONFIG_44x is not set
-# CONFIG_POWER3 is not set
-# CONFIG_POWER4 is not set
-CONFIG_8xx=y
-# CONFIG_E500 is not set
-# CONFIG_MATH_EMULATION is not set
-# CONFIG_CPU_FREQ is not set
-CONFIG_EMBEDDEDBOOT=y
-# CONFIG_PM is not set
-CONFIG_NOT_COHERENT_CACHE=y
-
-#
-# Platform options
-#
-# CONFIG_RPXLITE is not set
-# CONFIG_RPXCLASSIC is not set
-# CONFIG_BSEIP is not set
-# CONFIG_FADS is not set
-CONFIG_MPC885ADS=y
-# CONFIG_TQM823L is not set
-# CONFIG_TQM850L is not set
-# CONFIG_TQM855L is not set
-# CONFIG_TQM860L is not set
-# CONFIG_FPS850L is not set
-# CONFIG_SPD823TS is not set
-# CONFIG_IVMS8 is not set
-# CONFIG_IVML24 is not set
-# CONFIG_SM850 is not set
-# CONFIG_HERMES_PRO is not set
-# CONFIG_IP860 is not set
-# CONFIG_LWMON is not set
-# CONFIG_PCU_E is not set
-# CONFIG_CCM is not set
-# CONFIG_LANTEC is not set
-# CONFIG_MBX is not set
-# CONFIG_WINCEPT is not set
-# CONFIG_SMP is not set
-# CONFIG_PREEMPT is not set
-# CONFIG_HIGHMEM is not set
-CONFIG_BINFMT_ELF=y
-# CONFIG_BINFMT_MISC is not set
-# CONFIG_CMDLINE_BOOL is not set
-CONFIG_ISA_DMA_API=y
-
-#
-# Bus options
-#
-# CONFIG_PCI is not set
-# CONFIG_PCI_DOMAINS is not set
-# CONFIG_PCI_QSPAN is not set
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
-# CONFIG_PCCARD is not set
-
-#
-# Advanced setup
-#
-# CONFIG_ADVANCED_OPTIONS is not set
-
-#
-# Default settings for advanced configuration options are used
-#
-CONFIG_HIGHMEM_START=0xfe000000
-CONFIG_LOWMEM_SIZE=0x30000000
-CONFIG_KERNEL_START=0xc0000000
-CONFIG_TASK_SIZE=0x80000000
-CONFIG_CONSISTENT_START=0xff100000
-CONFIG_CONSISTENT_SIZE=0x00200000
-CONFIG_BOOT_LOAD=0x00400000
-
-#
-# Device Drivers
-#
-
-#
-# Generic Driver Options
-#
-CONFIG_STANDALONE=y
-CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
-
-#
-# Memory Technology Devices (MTD)
-#
-# CONFIG_MTD is not set
-
-#
-# Parallel port support
-#
-# CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-
-#
-# Block devices
-#
-# CONFIG_BLK_DEV_FD is not set
-# CONFIG_BLK_DEV_COW_COMMON is not set
-# CONFIG_BLK_DEV_LOOP is not set
-# CONFIG_BLK_DEV_NBD is not set
-# CONFIG_BLK_DEV_RAM is not set
-CONFIG_BLK_DEV_RAM_COUNT=16
-CONFIG_INITRAMFS_SOURCE=""
-# CONFIG_LBD is not set
-# CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-# CONFIG_IOSCHED_AS is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
-# CONFIG_ATA_OVER_ETH is not set
-
-#
-# ATA/ATAPI/MFM/RLL support
-#
-# CONFIG_IDE is not set
-
-#
-# SCSI device support
-#
-# CONFIG_SCSI is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
-# CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
-
-#
-# IEEE 1394 (FireWire) support
-#
-# CONFIG_IEEE1394 is not set
-
-#
-# I2O device support
-#
-
-#
-# Macintosh device drivers
-#
-
-#
-# Networking support
-#
-CONFIG_NET=y
-
-#
-# Networking options
-#
-CONFIG_PACKET=y
-# CONFIG_PACKET_MMAP is not set
-CONFIG_UNIX=y
-# CONFIG_NET_KEY is not set
-CONFIG_INET=y
-# CONFIG_IP_MULTICAST is not set
-# CONFIG_IP_ADVANCED_ROUTER is not set
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IP_PNP_RARP is not set
-# CONFIG_NET_IPIP is not set
-# CONFIG_NET_IPGRE is not set
-# CONFIG_ARPD is not set
-# CONFIG_SYN_COOKIES is not set
-# CONFIG_INET_AH is not set
-# CONFIG_INET_ESP is not set
-# CONFIG_INET_IPCOMP is not set
-# CONFIG_INET_TUNNEL is not set
-CONFIG_IP_TCPDIAG=y
-# CONFIG_IP_TCPDIAG_IPV6 is not set
-# CONFIG_IPV6 is not set
-# CONFIG_NETFILTER is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
-# CONFIG_IP_SCTP is not set
-# CONFIG_ATM is not set
-# CONFIG_BRIDGE is not set
-# CONFIG_VLAN_8021Q is not set
-# CONFIG_DECNET is not set
-# CONFIG_LLC2 is not set
-# CONFIG_IPX is not set
-# CONFIG_ATALK is not set
-# CONFIG_X25 is not set
-# CONFIG_LAPB is not set
-# CONFIG_NET_DIVERT is not set
-# CONFIG_ECONET is not set
-# CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
-# CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
-
-#
-# Network testing
-#
-# CONFIG_NET_PKTGEN is not set
-# CONFIG_NETPOLL is not set
-# CONFIG_NET_POLL_CONTROLLER is not set
-# CONFIG_HAMRADIO is not set
-# CONFIG_IRDA is not set
-# CONFIG_BT is not set
-CONFIG_NETDEVICES=y
-# CONFIG_DUMMY is not set
-# CONFIG_BONDING is not set
-# CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-# CONFIG_OAKNET is not set
-
-#
-# Ethernet (1000 Mbit)
-#
-
-#
-# Ethernet (10000 Mbit)
-#
-
-#
-# Token Ring devices
-#
-
-#
-# Wireless LAN (non-hamradio)
-#
-# CONFIG_NET_RADIO is not set
-
-#
-# Wan interfaces
-#
-# CONFIG_WAN is not set
-CONFIG_PPP=y
-# CONFIG_PPP_MULTILINK is not set
-# CONFIG_PPP_FILTER is not set
-CONFIG_PPP_ASYNC=y
-CONFIG_PPP_SYNC_TTY=y
-CONFIG_PPP_DEFLATE=y
-# CONFIG_PPP_BSDCOMP is not set
-# CONFIG_PPPOE is not set
-# CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
-# CONFIG_NETCONSOLE is not set
-
-#
-# ISDN subsystem
-#
-# CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
-# CONFIG_PHONE is not set
-
-#
-# Input device support
-#
-# CONFIG_INPUT is not set
-
-#
-# Hardware I/O ports
-#
-# CONFIG_SERIO is not set
-# CONFIG_GAMEPORT is not set
-
-#
-# Character devices
-#
-# CONFIG_VT is not set
-# CONFIG_SERIAL_NONSTANDARD is not set
-
-#
-# Serial drivers
-#
-# CONFIG_SERIAL_8250 is not set
-
-#
-# Non-8250 serial port support
-#
-CONFIG_SERIAL_CORE=y
-CONFIG_SERIAL_CORE_CONSOLE=y
-CONFIG_SERIAL_CPM=y
-CONFIG_SERIAL_CPM_CONSOLE=y
-# CONFIG_SERIAL_CPM_SCC1 is not set
-# CONFIG_SERIAL_CPM_SCC2 is not set
-# CONFIG_SERIAL_CPM_SCC3 is not set
-# CONFIG_SERIAL_CPM_SCC4 is not set
-CONFIG_SERIAL_CPM_SMC1=y
-CONFIG_SERIAL_CPM_SMC2=y
-CONFIG_UNIX98_PTYS=y
-# CONFIG_LEGACY_PTYS is not set
-
-#
-# IPMI
-#
-# CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
-# CONFIG_NVRAM is not set
-# CONFIG_GEN_RTC is not set
-# CONFIG_DTLK is not set
-# CONFIG_R3964 is not set
-
-#
-# Ftape, the floppy tape device driver
-#
-# CONFIG_AGP is not set
-# CONFIG_DRM is not set
-# CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
-
-#
-# I2C support
-#
-# CONFIG_I2C is not set
-
-#
-# Dallas's 1-wire bus
-#
-# CONFIG_W1 is not set
-
-#
-# Misc devices
-#
-
-#
-# Multimedia devices
-#
-# CONFIG_VIDEO_DEV is not set
-
-#
-# Digital Video Broadcasting Devices
-#
-# CONFIG_DVB is not set
-
-#
-# Graphics support
-#
-# CONFIG_FB is not set
-
-#
-# Sound
-#
-# CONFIG_SOUND is not set
-
-#
-# USB support
-#
-# CONFIG_USB_ARCH_HAS_HCD is not set
-# CONFIG_USB_ARCH_HAS_OHCI is not set
-
-#
-# USB Gadget Support
-#
-# CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
-# CONFIG_MMC is not set
-
-#
-# InfiniBand support
-#
-# CONFIG_INFINIBAND is not set
-
-#
-# File systems
-#
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-# CONFIG_EXT2_FS_POSIX_ACL is not set
-# CONFIG_EXT2_FS_SECURITY is not set
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_XATTR=y
-# CONFIG_EXT3_FS_POSIX_ACL is not set
-# CONFIG_EXT3_FS_SECURITY is not set
-CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
-CONFIG_FS_MBCACHE=y
-# CONFIG_REISERFS_FS is not set
-# CONFIG_JFS_FS is not set
-
-#
-# XFS support
-#
-# CONFIG_XFS_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
-# CONFIG_QUOTA is not set
-# CONFIG_DNOTIFY is not set
-# CONFIG_AUTOFS_FS is not set
-# CONFIG_AUTOFS4_FS is not set
-
-#
-# CD-ROM/DVD Filesystems
-#
-# CONFIG_ISO9660_FS is not set
-# CONFIG_UDF_FS is not set
-
-#
-# DOS/FAT/NT Filesystems
-#
-# CONFIG_MSDOS_FS is not set
-# CONFIG_VFAT_FS is not set
-# CONFIG_NTFS_FS is not set
-
-#
-# Pseudo filesystems
-#
-CONFIG_PROC_FS=y
-# CONFIG_PROC_KCORE is not set
-CONFIG_SYSFS=y
-# CONFIG_DEVFS_FS is not set
-# CONFIG_DEVPTS_FS_XATTR is not set
-# CONFIG_TMPFS is not set
-# CONFIG_HUGETLBFS is not set
-# CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
-
-#
-# Miscellaneous filesystems
-#
-# CONFIG_ADFS_FS is not set
-# CONFIG_AFFS_FS is not set
-# CONFIG_HFS_FS is not set
-# CONFIG_HFSPLUS_FS is not set
-# CONFIG_BEFS_FS is not set
-# CONFIG_BFS_FS is not set
-# CONFIG_EFS_FS is not set
-# CONFIG_CRAMFS is not set
-# CONFIG_VXFS_FS is not set
-# CONFIG_HPFS_FS is not set
-# CONFIG_QNX4FS_FS is not set
-# CONFIG_SYSV_FS is not set
-# CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
-CONFIG_NFS_FS=y
-# CONFIG_NFS_V3 is not set
-# CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
-# CONFIG_NFSD is not set
-CONFIG_ROOT_NFS=y
-CONFIG_LOCKD=y
-CONFIG_SUNRPC=y
-# CONFIG_RPCSEC_GSS_KRB5 is not set
-# CONFIG_RPCSEC_GSS_SPKM3 is not set
-# CONFIG_SMB_FS is not set
-# CONFIG_CIFS is not set
-# CONFIG_NCP_FS is not set
-# CONFIG_CODA_FS is not set
-# CONFIG_AFS_FS is not set
-
-#
-# Partition Types
-#
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_ACORN_PARTITION is not set
-# CONFIG_OSF_PARTITION is not set
-# CONFIG_AMIGA_PARTITION is not set
-# CONFIG_ATARI_PARTITION is not set
-# CONFIG_MAC_PARTITION is not set
-CONFIG_MSDOS_PARTITION=y
-# CONFIG_BSD_DISKLABEL is not set
-# CONFIG_MINIX_SUBPARTITION is not set
-# CONFIG_SOLARIS_X86_PARTITION is not set
-# CONFIG_UNIXWARE_DISKLABEL is not set
-# CONFIG_LDM_PARTITION is not set
-# CONFIG_SGI_PARTITION is not set
-# CONFIG_ULTRIX_PARTITION is not set
-# CONFIG_SUN_PARTITION is not set
-# CONFIG_EFI_PARTITION is not set
-
-#
-# Native Language Support
-#
-# CONFIG_NLS is not set
-
-#
-# MPC8xx CPM Options
-#
-CONFIG_SCC_ENET=y
-# CONFIG_SCC1_ENET is not set
-# CONFIG_SCC2_ENET is not set
-CONFIG_SCC3_ENET=y
-# CONFIG_FEC_ENET is not set
-# CONFIG_ENET_BIG_BUFFERS is not set
-
-#
-# Generic MPC8xx Options
-#
-CONFIG_8xx_COPYBACK=y
-CONFIG_8xx_CPU6=y
-CONFIG_NO_UCODE_PATCH=y
-# CONFIG_USB_SOF_UCODE_PATCH is not set
-# CONFIG_I2C_SPI_UCODE_PATCH is not set
-# CONFIG_I2C_SPI_SMC1_UCODE_PATCH is not set
-
-#
-# Library routines
-#
-CONFIG_CRC_CCITT=y
-# CONFIG_CRC32 is not set
-# CONFIG_LIBCRC32C is not set
-CONFIG_ZLIB_INFLATE=y
-CONFIG_ZLIB_DEFLATE=y
-
-#
-# Profiling support
-#
-# CONFIG_PROFILING is not set
-
-#
-# Kernel hacking
-#
-# CONFIG_PRINTK_TIME is not set
-# CONFIG_DEBUG_KERNEL is not set
-CONFIG_LOG_BUF_SHIFT=14
-
-#
-# Security options
-#
-# CONFIG_KEYS is not set
-# CONFIG_SECURITY is not set
-
-#
-# Cryptographic options
-#
-# CONFIG_CRYPTO is not set
-
-#
-# Hardware crypto devices
-#
diff --git a/arch/ppc/kernel/ppc_ksyms.c b/arch/ppc/kernel/ppc_ksyms.c
index 2ba659f401b..d9036ef0b65 100644
--- a/arch/ppc/kernel/ppc_ksyms.c
+++ b/arch/ppc/kernel/ppc_ksyms.c
@@ -88,6 +88,7 @@ EXPORT_SYMBOL(strncpy);
EXPORT_SYMBOL(strcat);
EXPORT_SYMBOL(strlen);
EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
EXPORT_SYMBOL(csum_partial);
EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/ppc/lib/string.S b/arch/ppc/lib/string.S
index 84ed33ab4c2..927253bfc82 100644
--- a/arch/ppc/lib/string.S
+++ b/arch/ppc/lib/string.S
@@ -121,6 +121,20 @@ _GLOBAL(strcmp)
beq 1b
blr
+_GLOBAL(strncmp)
+ PPC_LCMPI r5,0
+ beqlr
+ mtctr r5
+ addi r5,r3,-1
+ addi r4,r4,-1
+1: lbzu r3,1(r5)
+ cmpwi 1,r3,0
+ lbzu r0,1(r4)
+ subf. r3,r0,r3
+ beqlr 1
+ bdnzt eq,1b
+ blr
+
_GLOBAL(strlen)
addi r4,r3,-1
1: lbzu r0,1(r4)
diff --git a/arch/ppc/platforms/Makefile b/arch/ppc/platforms/Makefile
index 40f53fbe6d3..6260231987c 100644
--- a/arch/ppc/platforms/Makefile
+++ b/arch/ppc/platforms/Makefile
@@ -4,7 +4,6 @@
obj-$(CONFIG_PPC_PREP) += prep_pci.o prep_setup.o
obj-$(CONFIG_PREP_RESIDUAL) += residual.o
-obj-$(CONFIG_PQ2ADS) += pq2ads.o
obj-$(CONFIG_TQM8260) += tqm8260_setup.o
obj-$(CONFIG_CPCI690) += cpci690.o
obj-$(CONFIG_EV64260) += ev64260.o
@@ -24,6 +23,3 @@ obj-$(CONFIG_SBC82xx) += sbc82xx.o
obj-$(CONFIG_SPRUCE) += spruce.o
obj-$(CONFIG_LITE5200) += lite5200.o
obj-$(CONFIG_EV64360) += ev64360.o
-obj-$(CONFIG_MPC86XADS) += mpc866ads_setup.o
-obj-$(CONFIG_MPC885ADS) += mpc885ads_setup.o
-obj-$(CONFIG_ADS8272) += mpc8272ads_setup.o
diff --git a/arch/ppc/platforms/fads.h b/arch/ppc/platforms/fads.h
index 2f9f0f60e3f..5219366667b 100644
--- a/arch/ppc/platforms/fads.h
+++ b/arch/ppc/platforms/fads.h
@@ -22,29 +22,6 @@
#include <asm/ppcboot.h>
-#if defined(CONFIG_MPC86XADS)
-
-#define BOARD_CHIP_NAME "MPC86X"
-
-/* U-Boot maps BCSR to 0xff080000 */
-#define BCSR_ADDR ((uint)0xff080000)
-
-/* MPC86XADS has one more CPLD and an additional BCSR.
- */
-#define CFG_PHYDEV_ADDR ((uint)0xff0a0000)
-#define BCSR5 ((uint)(CFG_PHYDEV_ADDR + 0x300))
-
-#define BCSR5_T1_RST 0x10
-#define BCSR5_ATM155_RST 0x08
-#define BCSR5_ATM25_RST 0x04
-#define BCSR5_MII1_EN 0x02
-#define BCSR5_MII1_RST 0x01
-
-/* There is no PHY link change interrupt */
-#define PHY_INTERRUPT (-1)
-
-#else /* FADS */
-
/* Memory map is configured by the PROM startup.
* I tried to follow the FADS manual, although the startup PROM
* dictates this and we simply have to move some of the physical
@@ -55,8 +32,6 @@
/* PHY link change interrupt */
#define PHY_INTERRUPT SIU_IRQ2
-#endif /* CONFIG_MPC86XADS */
-
#define BCSR_SIZE ((uint)(64 * 1024))
#define BCSR0 ((uint)(BCSR_ADDR + 0x00))
#define BCSR1 ((uint)(BCSR_ADDR + 0x04))
diff --git a/arch/ppc/platforms/mpc8272ads_setup.c b/arch/ppc/platforms/mpc8272ads_setup.c
deleted file mode 100644
index 47f4b38edb5..00000000000
--- a/arch/ppc/platforms/mpc8272ads_setup.c
+++ /dev/null
@@ -1,367 +0,0 @@
-/*
- * arch/ppc/platforms/mpc8272ads_setup.c
- *
- * MPC82xx Board-specific PlatformDevice descriptions
- *
- * 2005 (c) MontaVista Software, Inc.
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/ioport.h>
-#include <linux/fs_enet_pd.h>
-#include <linux/platform_device.h>
-#include <linux/phy.h>
-
-#include <asm/io.h>
-#include <asm/mpc8260.h>
-#include <asm/cpm2.h>
-#include <asm/immap_cpm2.h>
-#include <asm/irq.h>
-#include <asm/ppc_sys.h>
-#include <asm/ppcboot.h>
-#include <linux/fs_uart_pd.h>
-
-#include "pq2ads_pd.h"
-
-static void init_fcc1_ioports(struct fs_platform_info*);
-static void init_fcc2_ioports(struct fs_platform_info*);
-static void init_scc1_uart_ioports(struct fs_uart_platform_info*);
-static void init_scc4_uart_ioports(struct fs_uart_platform_info*);
-
-static struct fs_uart_platform_info mpc8272_uart_pdata[] = {
- [fsid_scc1_uart] = {
- .init_ioports = init_scc1_uart_ioports,
- .fs_no = fsid_scc1_uart,
- .brg = 1,
- .tx_num_fifo = 4,
- .tx_buf_size = 32,
- .rx_num_fifo = 4,
- .rx_buf_size = 32,
- },
- [fsid_scc4_uart] = {
- .init_ioports = init_scc4_uart_ioports,
- .fs_no = fsid_scc4_uart,
- .brg = 4,
- .tx_num_fifo = 4,
- .tx_buf_size = 32,
- .rx_num_fifo = 4,
- .rx_buf_size = 32,
- },
-};
-
-static struct fs_mii_bb_platform_info m82xx_mii_bb_pdata = {
- .mdio_dat.bit = 18,
- .mdio_dir.bit = 18,
- .mdc_dat.bit = 19,
- .delay = 1,
-};
-
-static struct fs_platform_info mpc82xx_enet_pdata[] = {
- [fsid_fcc1] = {
- .fs_no = fsid_fcc1,
- .cp_page = CPM_CR_FCC1_PAGE,
- .cp_block = CPM_CR_FCC1_SBLOCK,
-
- .clk_trx = (PC_F1RXCLK | PC_F1TXCLK),
- .clk_route = CMX1_CLK_ROUTE,
- .clk_mask = CMX1_CLK_MASK,
- .init_ioports = init_fcc1_ioports,
-
- .mem_offset = FCC1_MEM_OFFSET,
-
- .rx_ring = 32,
- .tx_ring = 32,
- .rx_copybreak = 240,
- .use_napi = 0,
- .napi_weight = 17,
- .bus_id = "0:00",
- },
- [fsid_fcc2] = {
- .fs_no = fsid_fcc2,
- .cp_page = CPM_CR_FCC2_PAGE,
- .cp_block = CPM_CR_FCC2_SBLOCK,
- .clk_trx = (PC_F2RXCLK | PC_F2TXCLK),
- .clk_route = CMX2_CLK_ROUTE,
- .clk_mask = CMX2_CLK_MASK,
- .init_ioports = init_fcc2_ioports,
-
- .mem_offset = FCC2_MEM_OFFSET,
-
- .rx_ring = 32,
- .tx_ring = 32,
- .rx_copybreak = 240,
- .use_napi = 0,
- .napi_weight = 17,
- .bus_id = "0:03",
- },
-};
-
-static void init_fcc1_ioports(struct fs_platform_info* pdata)
-{
- struct io_port *io;
- u32 tempval;
- cpm2_map_t* immap = ioremap(CPM_MAP_ADDR, sizeof(cpm2_map_t));
- u32 *bcsr = ioremap(BCSR_ADDR+4, sizeof(u32));
-
- io = &immap->im_ioport;
-
- /* Enable the PHY */
- clrbits32(bcsr, BCSR1_FETHIEN);
- setbits32(bcsr, BCSR1_FETH_RST);
-
- /* FCC1 pins are on port A/C. */
- /* Configure port A and C pins for FCC1 Ethernet. */
-
- tempval = in_be32(&io->iop_pdira);
- tempval &= ~PA1_DIRA0;
- tempval |= PA1_DIRA1;
- out_be32(&io->iop_pdira, tempval);
-
- tempval = in_be32(&io->iop_psora);
- tempval &= ~PA1_PSORA0;
- tempval |= PA1_PSORA1;
- out_be32(&io->iop_psora, tempval);
-
- setbits32(&io->iop_ppara,PA1_DIRA0 | PA1_DIRA1);
-
- /* Alter clocks */
- tempval = PC_F1TXCLK|PC_F1RXCLK;
-
- clrbits32(&io->iop_psorc, tempval);
- clrbits32(&io->iop_pdirc, tempval);
- setbits32(&io->iop_pparc, tempval);
-
- clrbits32(&immap->im_cpmux.cmx_fcr, CMX1_CLK_MASK);
- setbits32(&immap->im_cpmux.cmx_fcr, CMX1_CLK_ROUTE);
- iounmap(bcsr);
- iounmap(immap);
-}
-
-static void init_fcc2_ioports(struct fs_platform_info* pdata)
-{
- cpm2_map_t* immap = ioremap(CPM_MAP_ADDR, sizeof(cpm2_map_t));
- u32 *bcsr = ioremap(BCSR_ADDR+12, sizeof(u32));
-
- struct io_port *io;
- u32 tempval;
-
- immap = cpm2_immr;
-
- io = &immap->im_ioport;
-
- /* Enable the PHY */
- clrbits32(bcsr, BCSR3_FETHIEN2);
- setbits32(bcsr, BCSR3_FETH2_RST);
-
- /* FCC2 are port B/C. */
- /* Configure port A and C pins for FCC2 Ethernet. */
-
- tempval = in_be32(&io->iop_pdirb);
- tempval &= ~PB2_DIRB0;
- tempval |= PB2_DIRB1;
- out_be32(&io->iop_pdirb, tempval);
-
- tempval = in_be32(&io->iop_psorb);
- tempval &= ~PB2_PSORB0;
- tempval |= PB2_PSORB1;
- out_be32(&io->iop_psorb, tempval);
-
- setbits32(&io->iop_pparb,PB2_DIRB0 | PB2_DIRB1);
-
- tempval = PC_F2RXCLK|PC_F2TXCLK;
-
- /* Alter clocks */
- clrbits32(&io->iop_psorc,tempval);
- clrbits32(&io->iop_pdirc,tempval);
- setbits32(&io->iop_pparc,tempval);
-
- clrbits32(&immap->im_cpmux.cmx_fcr, CMX2_CLK_MASK);
- setbits32(&immap->im_cpmux.cmx_fcr, CMX2_CLK_ROUTE);
-
- iounmap(bcsr);
- iounmap(immap);
-}
-
-
-static void __init mpc8272ads_fixup_enet_pdata(struct platform_device *pdev,
- int idx)
-{
- bd_t* bi = (void*)__res;
- int fs_no = fsid_fcc1+pdev->id-1;
-
- if(fs_no >= ARRAY_SIZE(mpc82xx_enet_pdata)) {
- return;
- }
-
- mpc82xx_enet_pdata[fs_no].dpram_offset=
- (u32)cpm2_immr->im_dprambase;
- mpc82xx_enet_pdata[fs_no].fcc_regs_c =
- (u32)cpm2_immr->im_fcc_c;
- memcpy(&mpc82xx_enet_pdata[fs_no].macaddr,bi->bi_enetaddr,6);
-
- /* prevent dup mac */
- if(fs_no == fsid_fcc2)
- mpc82xx_enet_pdata[fs_no].macaddr[5] ^= 1;
-
- pdev->dev.platform_data = &mpc82xx_enet_pdata[fs_no];
-}
-
-static void mpc8272ads_fixup_uart_pdata(struct platform_device *pdev,
- int idx)
-{
- bd_t *bd = (bd_t *) __res;
- struct fs_uart_platform_info *pinfo;
- int num = ARRAY_SIZE(mpc8272_uart_pdata);
- int id = fs_uart_id_scc2fsid(idx);
-
- /* no need to alter anything if console */
- if ((id < num) && (!pdev->dev.platform_data)) {
- pinfo = &mpc8272_uart_pdata[id];
- pinfo->uart_clk = bd->bi_intfreq;
- pdev->dev.platform_data = pinfo;
- }
-}
-
-static void init_scc1_uart_ioports(struct fs_uart_platform_info* pdata)
-{
- cpm2_map_t* immap = ioremap(CPM_MAP_ADDR, sizeof(cpm2_map_t));
-
- /* SCC1 is only on port D */
- setbits32(&immap->im_ioport.iop_ppard,0x00000003);
- clrbits32(&immap->im_ioport.iop_psord,0x00000001);
- setbits32(&immap->im_ioport.iop_psord,0x00000002);
- clrbits32(&immap->im_ioport.iop_pdird,0x00000001);
- setbits32(&immap->im_ioport.iop_pdird,0x00000002);
-
- /* Wire BRG1 to SCC1 */
- clrbits32(&immap->im_cpmux.cmx_scr,0x00ffffff);
-
- iounmap(immap);
-}
-
-static void init_scc4_uart_ioports(struct fs_uart_platform_info* pdata)
-{
- cpm2_map_t* immap = ioremap(CPM_MAP_ADDR, sizeof(cpm2_map_t));
-
- setbits32(&immap->im_ioport.iop_ppard,0x00000600);
- clrbits32(&immap->im_ioport.iop_psord,0x00000600);
- clrbits32(&immap->im_ioport.iop_pdird,0x00000200);
- setbits32(&immap->im_ioport.iop_pdird,0x00000400);
-
- /* Wire BRG4 to SCC4 */
- clrbits32(&immap->im_cpmux.cmx_scr,0x000000ff);
- setbits32(&immap->im_cpmux.cmx_scr,0x0000001b);
-
- iounmap(immap);
-}
-
-static void __init mpc8272ads_fixup_mdio_pdata(struct platform_device *pdev,
- int idx)
-{
- m82xx_mii_bb_pdata.irq[0] = PHY_INTERRUPT;
- m82xx_mii_bb_pdata.irq[1] = PHY_POLL;
- m82xx_mii_bb_pdata.irq[2] = PHY_POLL;
- m82xx_mii_bb_pdata.irq[3] = PHY_INTERRUPT;
- m82xx_mii_bb_pdata.irq[31] = PHY_POLL;
-
-
- m82xx_mii_bb_pdata.mdio_dat.offset =
- (u32)&cpm2_immr->im_ioport.iop_pdatc;
-
- m82xx_mii_bb_pdata.mdio_dir.offset =
- (u32)&cpm2_immr->im_ioport.iop_pdirc;
-
- m82xx_mii_bb_pdata.mdc_dat.offset =
- (u32)&cpm2_immr->im_ioport.iop_pdatc;
-
-
- pdev->dev.platform_data = &m82xx_mii_bb_pdata;
-}
-
-static int mpc8272ads_platform_notify(struct device *dev)
-{
- static const struct platform_notify_dev_map dev_map[] = {
- {
- .bus_id = "fsl-cpm-fcc",
- .rtn = mpc8272ads_fixup_enet_pdata,
- },
- {
- .bus_id = "fsl-cpm-scc:uart",
- .rtn = mpc8272ads_fixup_uart_pdata,
- },
- {
- .bus_id = "fsl-bb-mdio",
- .rtn = mpc8272ads_fixup_mdio_pdata,
- },
- {
- .bus_id = NULL
- }
- };
- platform_notify_map(dev_map,dev);
-
- return 0;
-
-}
-
-int __init mpc8272ads_init(void)
-{
- printk(KERN_NOTICE "mpc8272ads: Init\n");
-
- platform_notify = mpc8272ads_platform_notify;
-
- ppc_sys_device_initfunc();
-
- ppc_sys_device_disable_all();
- ppc_sys_device_enable(MPC82xx_CPM_FCC1);
- ppc_sys_device_enable(MPC82xx_CPM_FCC2);
-
- /* to be ready for console, let's attach pdata here */
-#ifdef CONFIG_SERIAL_CPM_SCC1
- ppc_sys_device_setfunc(MPC82xx_CPM_SCC1, PPC_SYS_FUNC_UART);
- ppc_sys_device_enable(MPC82xx_CPM_SCC1);
-
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SCC4
- ppc_sys_device_setfunc(MPC82xx_CPM_SCC4, PPC_SYS_FUNC_UART);
- ppc_sys_device_enable(MPC82xx_CPM_SCC4);
-#endif
-
- ppc_sys_device_enable(MPC82xx_MDIO_BB);
-
- return 0;
-}
-
-/*
- To prevent confusion, console selection is gross:
- by 0 assumed SCC1 and by 1 assumed SCC4
- */
-struct platform_device* early_uart_get_pdev(int index)
-{
- bd_t *bd = (bd_t *) __res;
- struct fs_uart_platform_info *pinfo;
-
- struct platform_device* pdev = NULL;
- if(index) { /*assume SCC4 here*/
- pdev = &ppc_sys_platform_devices[MPC82xx_CPM_SCC4];
- pinfo = &mpc8272_uart_pdata[fsid_scc4_uart];
- } else { /*over SCC1*/
- pdev = &ppc_sys_platform_devices[MPC82xx_CPM_SCC1];
- pinfo = &mpc8272_uart_pdata[fsid_scc1_uart];
- }
-
- pinfo->uart_clk = bd->bi_intfreq;
- pdev->dev.platform_data = pinfo;
- ppc_sys_fixup_mem_resource(pdev, CPM_MAP_ADDR);
- return NULL;
-}
-
-arch_initcall(mpc8272ads_init);
diff --git a/arch/ppc/platforms/mpc885ads.h b/arch/ppc/platforms/mpc885ads.h
deleted file mode 100644
index d3bbbb3c9a1..00000000000
--- a/arch/ppc/platforms/mpc885ads.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * A collection of structures, addresses, and values associated with
- * the Freescale MPC885ADS board.
- * Copied from the FADS stuff.
- *
- * Author: MontaVista Software, Inc.
- * source@mvista.com
- *
- * 2005 (c) MontaVista Software, Inc. This file is licensed under the
- * terms of the GNU General Public License version 2. This program is licensed
- * "as is" without any warranty of any kind, whether express or implied.
- */
-
-#ifdef __KERNEL__
-#ifndef __ASM_MPC885ADS_H__
-#define __ASM_MPC885ADS_H__
-
-
-#include <asm/ppcboot.h>
-
-/* U-Boot maps BCSR to 0xff080000 */
-#define BCSR_ADDR ((uint)0xff080000)
-#define BCSR_SIZE ((uint)32)
-#define BCSR0 ((uint)(BCSR_ADDR + 0x00))
-#define BCSR1 ((uint)(BCSR_ADDR + 0x04))
-#define BCSR2 ((uint)(BCSR_ADDR + 0x08))
-#define BCSR3 ((uint)(BCSR_ADDR + 0x0c))
-#define BCSR4 ((uint)(BCSR_ADDR + 0x10))
-
-#define CFG_PHYDEV_ADDR ((uint)0xff0a0000)
-#define BCSR5 ((uint)(CFG_PHYDEV_ADDR + 0x300))
-
-#define IMAP_ADDR ((uint)0xff000000)
-#define IMAP_SIZE ((uint)(64 * 1024))
-
-#define PCMCIA_MEM_ADDR ((uint)0xff020000)
-#define PCMCIA_MEM_SIZE ((uint)(64 * 1024))
-
-/* Bits of interest in the BCSRs.
- */
-#define BCSR1_ETHEN ((uint)0x20000000)
-#define BCSR1_IRDAEN ((uint)0x10000000)
-#define BCSR1_RS232EN_1 ((uint)0x01000000)
-#define BCSR1_PCCEN ((uint)0x00800000)
-#define BCSR1_PCCVCC0 ((uint)0x00400000)
-#define BCSR1_PCCVPP0 ((uint)0x00200000)
-#define BCSR1_PCCVPP1 ((uint)0x00100000)
-#define BCSR1_PCCVPP_MASK (BCSR1_PCCVPP0 | BCSR1_PCCVPP1)
-#define BCSR1_RS232EN_2 ((uint)0x00040000)
-#define BCSR1_PCCVCC1 ((uint)0x00010000)
-#define BCSR1_PCCVCC_MASK (BCSR1_PCCVCC0 | BCSR1_PCCVCC1)
-
-#define BCSR4_ETH10_RST ((uint)0x80000000) /* 10Base-T PHY reset*/
-#define BCSR4_USB_LO_SPD ((uint)0x04000000)
-#define BCSR4_USB_VCC ((uint)0x02000000)
-#define BCSR4_USB_FULL_SPD ((uint)0x00040000)
-#define BCSR4_USB_EN ((uint)0x00020000)
-
-#define BCSR5_MII2_EN 0x40
-#define BCSR5_MII2_RST 0x20
-#define BCSR5_T1_RST 0x10
-#define BCSR5_ATM155_RST 0x08
-#define BCSR5_ATM25_RST 0x04
-#define BCSR5_MII1_EN 0x02
-#define BCSR5_MII1_RST 0x01
-
-/* Interrupt level assignments */
-#define PHY_INTERRUPT SIU_IRQ7 /* PHY link change interrupt */
-#define SIU_INT_FEC1 SIU_LEVEL1 /* FEC1 interrupt */
-#define SIU_INT_FEC2 SIU_LEVEL3 /* FEC2 interrupt */
-#define FEC_INTERRUPT SIU_INT_FEC1 /* FEC interrupt */
-
-/* We don't use the 8259 */
-#define NR_8259_INTS 0
-
-/* CPM Ethernet through SCC3 */
-#define PA_ENET_RXD ((ushort)0x0040)
-#define PA_ENET_TXD ((ushort)0x0080)
-#define PE_ENET_TCLK ((uint)0x00004000)
-#define PE_ENET_RCLK ((uint)0x00008000)
-#define PE_ENET_TENA ((uint)0x00000010)
-#define PC_ENET_CLSN ((ushort)0x0400)
-#define PC_ENET_RENA ((ushort)0x0800)
-
-/* Control bits in the SICR to route TCLK (CLK5) and RCLK (CLK6) to
- * SCC3. Also, make sure GR3 (bit 8) and SC3 (bit 9) are zero */
-#define SICR_ENET_MASK ((uint)0x00ff0000)
-#define SICR_ENET_CLKRT ((uint)0x002c0000)
-
-#define BOARD_CHIP_NAME "MPC885"
-
-#endif /* __ASM_MPC885ADS_H__ */
-#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/mpc885ads_setup.c b/arch/ppc/platforms/mpc885ads_setup.c
deleted file mode 100644
index ba06cc08cda..00000000000
--- a/arch/ppc/platforms/mpc885ads_setup.c
+++ /dev/null
@@ -1,476 +0,0 @@
-/*arch/ppc/platforms/mpc885ads_setup.c
- *
- * Platform setup for the Freescale mpc885ads board
- *
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * Copyright 2005 MontaVista Software Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/ioport.h>
-#include <linux/device.h>
-
-#include <linux/fs_enet_pd.h>
-#include <linux/fs_uart_pd.h>
-#include <linux/mii.h>
-
-#include <asm/delay.h>
-#include <asm/io.h>
-#include <asm/machdep.h>
-#include <asm/page.h>
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/time.h>
-#include <asm/ppcboot.h>
-#include <asm/8xx_immap.h>
-#include <asm/cpm1.h>
-#include <asm/ppc_sys.h>
-
-extern unsigned char __res[];
-static void setup_smc1_ioports(struct fs_uart_platform_info*);
-static void setup_smc2_ioports(struct fs_uart_platform_info*);
-
-static struct fs_mii_fec_platform_info mpc8xx_mdio_fec_pdata;
-static void setup_fec1_ioports(struct fs_platform_info*);
-static void setup_fec2_ioports(struct fs_platform_info*);
-static void setup_scc3_ioports(struct fs_platform_info*);
-
-static struct fs_uart_platform_info mpc885_uart_pdata[] = {
- [fsid_smc1_uart] = {
- .brg = 1,
- .fs_no = fsid_smc1_uart,
- .init_ioports = setup_smc1_ioports,
- .tx_num_fifo = 4,
- .tx_buf_size = 32,
- .rx_num_fifo = 4,
- .rx_buf_size = 32,
- },
- [fsid_smc2_uart] = {
- .brg = 2,
- .fs_no = fsid_smc2_uart,
- .init_ioports = setup_smc2_ioports,
- .tx_num_fifo = 4,
- .tx_buf_size = 32,
- .rx_num_fifo = 4,
- .rx_buf_size = 32,
- },
-};
-
-static struct fs_platform_info mpc8xx_enet_pdata[] = {
- [fsid_fec1] = {
- .rx_ring = 128,
- .tx_ring = 16,
- .rx_copybreak = 240,
-
- .use_napi = 1,
- .napi_weight = 17,
-
- .init_ioports = setup_fec1_ioports,
-
- .bus_id = "0:00",
- .has_phy = 1,
- },
- [fsid_fec2] = {
- .rx_ring = 128,
- .tx_ring = 16,
- .rx_copybreak = 240,
-
- .use_napi = 1,
- .napi_weight = 17,
-
- .init_ioports = setup_fec2_ioports,
-
- .bus_id = "0:01",
- .has_phy = 1,
- },
- [fsid_scc3] = {
- .rx_ring = 64,
- .tx_ring = 8,
- .rx_copybreak = 240,
-
- .use_napi = 1,
- .napi_weight = 17,
-
- .init_ioports = setup_scc3_ioports,
-#ifdef CONFIG_FIXED_MII_10_FDX
- .bus_id = "fixed@100:1",
-#else
- .bus_id = "0:02",
- #endif
- },
-};
-
-void __init board_init(void)
-{
- cpm8xx_t *cp = cpmp;
- unsigned int *bcsr_io;
-
-#ifdef CONFIG_FS_ENET
- immap_t *immap = (immap_t *) IMAP_ADDR;
-#endif
- bcsr_io = ioremap(BCSR1, sizeof(unsigned long));
-
- if (bcsr_io == NULL) {
- printk(KERN_CRIT "Could not remap BCSR\n");
- return;
- }
-#ifdef CONFIG_SERIAL_CPM_SMC1
- cp->cp_simode &= ~(0xe0000000 >> 17); /* brg1 */
- clrbits32(bcsr_io, BCSR1_RS232EN_1);
- cp->cp_smc[0].smc_smcm |= (SMCM_RX | SMCM_TX);
- cp->cp_smc[0].smc_smcmr &= ~(SMCMR_REN | SMCMR_TEN);
-#else
- setbits32(bcsr_io,BCSR1_RS232EN_1);
- cp->cp_smc[0].smc_smcmr = 0;
- cp->cp_smc[0].smc_smce = 0;
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SMC2
- cp->cp_simode &= ~(0xe0000000 >> 1);
- cp->cp_simode |= (0x20000000 >> 1); /* brg2 */
- clrbits32(bcsr_io,BCSR1_RS232EN_2);
- cp->cp_smc[1].smc_smcm |= (SMCM_RX | SMCM_TX);
- cp->cp_smc[1].smc_smcmr &= ~(SMCMR_REN | SMCMR_TEN);
-#else
- setbits32(bcsr_io,BCSR1_RS232EN_2);
- cp->cp_smc[1].smc_smcmr = 0;
- cp->cp_smc[1].smc_smce = 0;
-#endif
- iounmap(bcsr_io);
-
-#ifdef CONFIG_FS_ENET
- /* use MDC for MII (common) */
- setbits16(&immap->im_ioport.iop_pdpar, 0x0080);
- clrbits16(&immap->im_ioport.iop_pddir, 0x0080);
- bcsr_io = ioremap(BCSR5, sizeof(unsigned long));
- clrbits32(bcsr_io,BCSR5_MII1_EN);
- clrbits32(bcsr_io,BCSR5_MII1_RST);
-#ifdef CONFIG_MPC8xx_SECOND_ETH_FEC2
- clrbits32(bcsr_io,BCSR5_MII2_EN);
- clrbits32(bcsr_io,BCSR5_MII2_RST);
-#endif
- iounmap(bcsr_io);
-#endif
-}
-
-static void setup_fec1_ioports(struct fs_platform_info* pdata)
-{
- immap_t *immap = (immap_t *) IMAP_ADDR;
-
- /* configure FEC1 pins */
- setbits16(&immap->im_ioport.iop_papar, 0xf830);
- setbits16(&immap->im_ioport.iop_padir, 0x0830);
- clrbits16(&immap->im_ioport.iop_padir, 0xf000);
- setbits32(&immap->im_cpm.cp_pbpar, 0x00001001);
-
- clrbits32(&immap->im_cpm.cp_pbdir, 0x00001001);
- setbits16(&immap->im_ioport.iop_pcpar, 0x000c);
- clrbits16(&immap->im_ioport.iop_pcdir, 0x000c);
- setbits32(&immap->im_cpm.cp_pepar, 0x00000003);
-
- setbits32(&immap->im_cpm.cp_pedir, 0x00000003);
- clrbits32(&immap->im_cpm.cp_peso, 0x00000003);
- clrbits32(&immap->im_cpm.cp_cptr, 0x00000100);
-}
-
-static void setup_fec2_ioports(struct fs_platform_info* pdata)
-{
- immap_t *immap = (immap_t *) IMAP_ADDR;
-
- /* configure FEC2 pins */
- setbits32(&immap->im_cpm.cp_pepar, 0x0003fffc);
- setbits32(&immap->im_cpm.cp_pedir, 0x0003fffc);
- clrbits32(&immap->im_cpm.cp_peso, 0x000087fc);
- setbits32(&immap->im_cpm.cp_peso, 0x00037800);
- clrbits32(&immap->im_cpm.cp_cptr, 0x00000080);
-}
-
-static void setup_scc3_ioports(struct fs_platform_info* pdata)
-{
- immap_t *immap = (immap_t *) IMAP_ADDR;
- unsigned *bcsr_io;
-
- bcsr_io = ioremap(BCSR_ADDR, BCSR_SIZE);
-
- if (bcsr_io == NULL) {
- printk(KERN_CRIT "Could not remap BCSR\n");
- return;
- }
-
- /* Enable the PHY.
- */
- clrbits32(bcsr_io+4, BCSR4_ETH10_RST);
- udelay(1000);
- setbits32(bcsr_io+4, BCSR4_ETH10_RST);
- /* Configure port A pins for Txd and Rxd.
- */
- setbits16(&immap->im_ioport.iop_papar, PA_ENET_RXD | PA_ENET_TXD);
- clrbits16(&immap->im_ioport.iop_padir, PA_ENET_RXD | PA_ENET_TXD);
-
- /* Configure port C pins to enable CLSN and RENA.
- */
- clrbits16(&immap->im_ioport.iop_pcpar, PC_ENET_CLSN | PC_ENET_RENA);
- clrbits16(&immap->im_ioport.iop_pcdir, PC_ENET_CLSN | PC_ENET_RENA);
- setbits16(&immap->im_ioport.iop_pcso, PC_ENET_CLSN | PC_ENET_RENA);
-
- /* Configure port E for TCLK and RCLK.
- */
- setbits32(&immap->im_cpm.cp_pepar, PE_ENET_TCLK | PE_ENET_RCLK);
- clrbits32(&immap->im_cpm.cp_pepar, PE_ENET_TENA);
- clrbits32(&immap->im_cpm.cp_pedir,
- PE_ENET_TCLK | PE_ENET_RCLK | PE_ENET_TENA);
- clrbits32(&immap->im_cpm.cp_peso, PE_ENET_TCLK | PE_ENET_RCLK);
- setbits32(&immap->im_cpm.cp_peso, PE_ENET_TENA);
-
- /* Configure Serial Interface clock routing.
- * First, clear all SCC bits to zero, then set the ones we want.
- */
- clrbits32(&immap->im_cpm.cp_sicr, SICR_ENET_MASK);
- setbits32(&immap->im_cpm.cp_sicr, SICR_ENET_CLKRT);
-
- /* Disable Rx and Tx. SMC1 sshould be stopped if SCC3 eternet are used.
- */
- immap->im_cpm.cp_smc[0].smc_smcmr &= ~(SMCMR_REN | SMCMR_TEN);
- /* On the MPC885ADS SCC ethernet PHY is initialized in the full duplex mode
- * by H/W setting after reset. SCC ethernet controller support only half duplex.
- * This discrepancy of modes causes a lot of carrier lost errors.
- */
-
- /* In the original SCC enet driver the following code is placed at
- the end of the initialization */
- setbits32(&immap->im_cpm.cp_pepar, PE_ENET_TENA);
- clrbits32(&immap->im_cpm.cp_pedir, PE_ENET_TENA);
- setbits32(&immap->im_cpm.cp_peso, PE_ENET_TENA);
-
- setbits32(bcsr_io+4, BCSR1_ETHEN);
- iounmap(bcsr_io);
-}
-
-static int mac_count = 0;
-
-static void mpc885ads_fixup_enet_pdata(struct platform_device *pdev, int fs_no)
-{
- struct fs_platform_info *fpi;
- bd_t *bd = (bd_t *) __res;
- char *e;
- int i;
-
- if(fs_no >= ARRAY_SIZE(mpc8xx_enet_pdata)) {
- printk(KERN_ERR"No network-suitable #%d device on bus", fs_no);
- return;
- }
-
- fpi = &mpc8xx_enet_pdata[fs_no];
-
- switch (fs_no) {
- case fsid_fec1:
- fpi->init_ioports = &setup_fec1_ioports;
- break;
- case fsid_fec2:
- fpi->init_ioports = &setup_fec2_ioports;
- break;
- case fsid_scc3:
- fpi->init_ioports = &setup_scc3_ioports;
- break;
- default:
- printk(KERN_WARNING "Device %s is not supported!\n", pdev->name);
- return;
- }
-
- pdev->dev.platform_data = fpi;
- fpi->fs_no = fs_no;
-
- e = (unsigned char *)&bd->bi_enetaddr;
- for (i = 0; i < 6; i++)
- fpi->macaddr[i] = *e++;
-
- fpi->macaddr[5] += mac_count++;
-
-}
-
-static void mpc885ads_fixup_fec_enet_pdata(struct platform_device *pdev,
- int idx)
-{
- /* This is for FEC devices only */
- if (!pdev || !pdev->name || (!strstr(pdev->name, "fsl-cpm-fec")))
- return;
- mpc885ads_fixup_enet_pdata(pdev, fsid_fec1 + pdev->id - 1);
-}
-
-static void __init mpc885ads_fixup_scc_enet_pdata(struct platform_device *pdev,
- int idx)
-{
- /* This is for SCC devices only */
- if (!pdev || !pdev->name || (!strstr(pdev->name, "fsl-cpm-scc")))
- return;
-
- mpc885ads_fixup_enet_pdata(pdev, fsid_scc1 + pdev->id - 1);
-}
-
-static void setup_smc1_ioports(struct fs_uart_platform_info* pdata)
-{
- immap_t *immap = (immap_t *) IMAP_ADDR;
- unsigned *bcsr_io;
- unsigned int iobits = 0x000000c0;
-
- bcsr_io = ioremap(BCSR1, sizeof(unsigned long));
-
- if (bcsr_io == NULL) {
- printk(KERN_CRIT "Could not remap BCSR1\n");
- return;
- }
- clrbits32(bcsr_io,BCSR1_RS232EN_1);
- iounmap(bcsr_io);
-
- setbits32(&immap->im_cpm.cp_pbpar, iobits);
- clrbits32(&immap->im_cpm.cp_pbdir, iobits);
- clrbits16(&immap->im_cpm.cp_pbodr, iobits);
-}
-
-static void setup_smc2_ioports(struct fs_uart_platform_info* pdata)
-{
- immap_t *immap = (immap_t *) IMAP_ADDR;
- unsigned *bcsr_io;
- unsigned int iobits = 0x00000c00;
-
- bcsr_io = ioremap(BCSR1, sizeof(unsigned long));
-
- if (bcsr_io == NULL) {
- printk(KERN_CRIT "Could not remap BCSR1\n");
- return;
- }
- clrbits32(bcsr_io,BCSR1_RS232EN_2);
- iounmap(bcsr_io);
-
-#ifndef CONFIG_SERIAL_CPM_ALT_SMC2
- setbits32(&immap->im_cpm.cp_pbpar, iobits);
- clrbits32(&immap->im_cpm.cp_pbdir, iobits);
- clrbits16(&immap->im_cpm.cp_pbodr, iobits);
-#else
- setbits16(&immap->im_ioport.iop_papar, iobits);
- clrbits16(&immap->im_ioport.iop_padir, iobits);
- clrbits16(&immap->im_ioport.iop_paodr, iobits);
-#endif
-}
-
-static void __init mpc885ads_fixup_uart_pdata(struct platform_device *pdev,
- int idx)
-{
- bd_t *bd = (bd_t *) __res;
- struct fs_uart_platform_info *pinfo;
- int num = ARRAY_SIZE(mpc885_uart_pdata);
-
- int id = fs_uart_id_smc2fsid(idx);
-
- /* no need to alter anything if console */
- if ((id < num) && (!pdev->dev.platform_data)) {
- pinfo = &mpc885_uart_pdata[id];
- pinfo->uart_clk = bd->bi_intfreq;
- pdev->dev.platform_data = pinfo;
- }
-}
-
-
-static int mpc885ads_platform_notify(struct device *dev)
-{
-
- static const struct platform_notify_dev_map dev_map[] = {
- {
- .bus_id = "fsl-cpm-fec",
- .rtn = mpc885ads_fixup_fec_enet_pdata,
- },
- {
- .bus_id = "fsl-cpm-scc",
- .rtn = mpc885ads_fixup_scc_enet_pdata,
- },
- {
- .bus_id = "fsl-cpm-smc:uart",
- .rtn = mpc885ads_fixup_uart_pdata
- },
- {
- .bus_id = NULL
- }
- };
-
- platform_notify_map(dev_map,dev);
-
- return 0;
-}
-
-int __init mpc885ads_init(void)
-{
- struct fs_mii_fec_platform_info* fmpi;
- bd_t *bd = (bd_t *) __res;
-
- printk(KERN_NOTICE "mpc885ads: Init\n");
-
- platform_notify = mpc885ads_platform_notify;
-
- ppc_sys_device_initfunc();
- ppc_sys_device_disable_all();
-
- ppc_sys_device_enable(MPC8xx_CPM_FEC1);
-
- ppc_sys_device_enable(MPC8xx_MDIO_FEC);
- fmpi = ppc_sys_platform_devices[MPC8xx_MDIO_FEC].dev.platform_data =
- &mpc8xx_mdio_fec_pdata;
-
- fmpi->mii_speed = ((((bd->bi_intfreq + 4999999) / 2500000) / 2) & 0x3F) << 1;
-
- /* No PHY interrupt line here */
- fmpi->irq[0xf] = SIU_IRQ7;
-
-#ifdef CONFIG_MPC8xx_SECOND_ETH_SCC3
- ppc_sys_device_enable(MPC8xx_CPM_SCC3);
-
-#endif
-#ifdef CONFIG_MPC8xx_SECOND_ETH_FEC2
- ppc_sys_device_enable(MPC8xx_CPM_FEC2);
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SMC1
- ppc_sys_device_enable(MPC8xx_CPM_SMC1);
- ppc_sys_device_setfunc(MPC8xx_CPM_SMC1, PPC_SYS_FUNC_UART);
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SMC2
- ppc_sys_device_enable(MPC8xx_CPM_SMC2);
- ppc_sys_device_setfunc(MPC8xx_CPM_SMC2, PPC_SYS_FUNC_UART);
-#endif
- return 0;
-}
-
-arch_initcall(mpc885ads_init);
-
-/*
- To prevent confusion, console selection is gross:
- by 0 assumed SMC1 and by 1 assumed SMC2
- */
-struct platform_device* early_uart_get_pdev(int index)
-{
- bd_t *bd = (bd_t *) __res;
- struct fs_uart_platform_info *pinfo;
-
- struct platform_device* pdev = NULL;
- if(index) { /*assume SMC2 here*/
- pdev = &ppc_sys_platform_devices[MPC8xx_CPM_SMC2];
- pinfo = &mpc885_uart_pdata[1];
- } else { /*over SMC1*/
- pdev = &ppc_sys_platform_devices[MPC8xx_CPM_SMC1];
- pinfo = &mpc885_uart_pdata[0];
- }
-
- pinfo->uart_clk = bd->bi_intfreq;
- pdev->dev.platform_data = pinfo;
- ppc_sys_fixup_mem_resource(pdev, IMAP_ADDR);
- return NULL;
-}
-
diff --git a/arch/ppc/platforms/pq2ads.c b/arch/ppc/platforms/pq2ads.c
deleted file mode 100644
index 7fc2e02f524..00000000000
--- a/arch/ppc/platforms/pq2ads.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * PQ2ADS platform support
- *
- * Author: Kumar Gala <galak@kernel.crashing.org>
- * Derived from: est8260_setup.c by Allen Curtis
- *
- * Copyright 2004 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#include <linux/init.h>
-
-#include <asm/io.h>
-#include <asm/mpc8260.h>
-#include <asm/cpm2.h>
-#include <asm/immap_cpm2.h>
-
-void __init
-m82xx_board_setup(void)
-{
- cpm2_map_t* immap = ioremap(CPM_MAP_ADDR, sizeof(cpm2_map_t));
- u32 *bcsr = ioremap(BCSR_ADDR+4, sizeof(u32));
-
- /* Enable the 2nd UART port */
- clrbits32(bcsr, BCSR1_RS232_EN2);
-
-#ifdef CONFIG_SERIAL_CPM_SCC1
- clrbits32((u32*)&immap->im_scc[0].scc_sccm, UART_SCCM_TX | UART_SCCM_RX);
- clrbits32((u32*)&immap->im_scc[0].scc_gsmrl, SCC_GSMRL_ENR | SCC_GSMRL_ENT);
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SCC2
- clrbits32((u32*)&immap->im_scc[1].scc_sccm, UART_SCCM_TX | UART_SCCM_RX);
- clrbits32((u32*)&immap->im_scc[1].scc_gsmrl, SCC_GSMRL_ENR | SCC_GSMRL_ENT);
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SCC3
- clrbits32((u32*)&immap->im_scc[2].scc_sccm, UART_SCCM_TX | UART_SCCM_RX);
- clrbits32((u32*)&immap->im_scc[2].scc_gsmrl, SCC_GSMRL_ENR | SCC_GSMRL_ENT);
-#endif
-
-#ifdef CONFIG_SERIAL_CPM_SCC4
- clrbits32((u32*)&immap->im_scc[3].scc_sccm, UART_SCCM_TX | UART_SCCM_RX);
- clrbits32((u32*)&immap->im_scc[3].scc_gsmrl, SCC_GSMRL_ENR | SCC_GSMRL_ENT);
-#endif
-
- iounmap(bcsr);
- iounmap(immap);
-}
diff --git a/arch/ppc/platforms/pq2ads.h b/arch/ppc/platforms/pq2ads.h
deleted file mode 100644
index 2b287f4e0ca..00000000000
--- a/arch/ppc/platforms/pq2ads.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * A collection of structures, addresses, and values associated with
- * the Motorola MPC8260ADS/MPC8266ADS-PCI boards.
- * Copied from the RPX-Classic and SBS8260 stuff.
- *
- * Copyright (c) 2001 Dan Malek (dan@mvista.com)
- */
-#ifdef __KERNEL__
-#ifndef __MACH_ADS8260_DEFS
-#define __MACH_ADS8260_DEFS
-
-
-#include <asm/ppcboot.h>
-
-#if defined(CONFIG_ADS8272)
-#define BOARD_CHIP_NAME "8272"
-#endif
-
-/* Memory map is configured by the PROM startup.
- * We just map a few things we need. The CSR is actually 4 byte-wide
- * registers that can be accessed as 8-, 16-, or 32-bit values.
- */
-#define CPM_MAP_ADDR ((uint)0xf0000000)
-#define BCSR_ADDR ((uint)0xf4500000)
-#define BCSR_SIZE ((uint)(32 * 1024))
-
-#define BOOTROM_RESTART_ADDR ((uint)0xff000104)
-
-/* For our show_cpuinfo hooks. */
-#define CPUINFO_VENDOR "Motorola"
-#define CPUINFO_MACHINE "PQ2 ADS PowerPC"
-
-/* The ADS8260 has 16, 32-bit wide control/status registers, accessed
- * only on word boundaries.
- * Not all are used (yet), or are interesting to us (yet).
- */
-
-/* Things of interest in the CSR.
-*/
-#define BCSR0_LED0 ((uint)0x02000000) /* 0 == on */
-#define BCSR0_LED1 ((uint)0x01000000) /* 0 == on */
-#define BCSR1_FETHIEN ((uint)0x08000000) /* 0 == enable */
-#define BCSR1_FETH_RST ((uint)0x04000000) /* 0 == reset */
-#define BCSR1_RS232_EN1 ((uint)0x02000000) /* 0 == enable */
-#define BCSR1_RS232_EN2 ((uint)0x01000000) /* 0 == enable */
-#define BCSR3_FETHIEN2 ((uint)0x10000000) /* 0 == enable */
-#define BCSR3_FETH2_RST ((uint)0x80000000) /* 0 == reset */
-
-#define PHY_INTERRUPT SIU_INT_IRQ7
-
-#ifdef CONFIG_PCI
-/* PCI interrupt controller */
-#define PCI_INT_STAT_REG 0xF8200000
-#define PCI_INT_MASK_REG 0xF8200004
-#define PIRQA (NR_CPM_INTS + 0)
-#define PIRQB (NR_CPM_INTS + 1)
-#define PIRQC (NR_CPM_INTS + 2)
-#define PIRQD (NR_CPM_INTS + 3)
-
-/*
- * PCI memory map definitions for MPC8266ADS-PCI.
- *
- * processor view
- * local address PCI address target
- * 0x80000000-0x9FFFFFFF 0x80000000-0x9FFFFFFF PCI mem with prefetch
- * 0xA0000000-0xBFFFFFFF 0xA0000000-0xBFFFFFFF PCI mem w/o prefetch
- * 0xF4000000-0xF7FFFFFF 0x00000000-0x03FFFFFF PCI IO
- *
- * PCI master view
- * local address PCI address target
- * 0x00000000-0x1FFFFFFF 0x00000000-0x1FFFFFFF MPC8266 local memory
- */
-
-/* All the other PCI memory map definitions reside at syslib/m82xx_pci.h
- Here we should redefine what is unique for this board */
-#define M82xx_PCI_SLAVE_MEM_LOCAL 0x00000000 /* Local base */
-#define M82xx_PCI_SLAVE_MEM_BUS 0x00000000 /* PCI base */
-#define M82xx_PCI_SLAVE_MEM_SIZE 0x10000000 /* 256 Mb */
-
-#define M82xx_PCI_SLAVE_SEC_WND_SIZE ~(0x40000000 - 1U) /* 2 x 512Mb */
-#define M82xx_PCI_SLAVE_SEC_WND_BASE 0x80000000 /* PCI Memory base */
-
-#if defined(CONFIG_ADS8272)
-#define PCI_INT_TO_SIU SIU_INT_IRQ2
-#elif defined(CONFIG_PQ2FADS)
-#define PCI_INT_TO_SIU SIU_INT_IRQ6
-#else
-#warning PCI Bridge will be without interrupts support
-#endif
-
-#endif /* CONFIG_PCI */
-
-#endif /* __MACH_ADS8260_DEFS */
-#endif /* __KERNEL__ */
diff --git a/arch/ppc/platforms/pq2ads_pd.h b/arch/ppc/platforms/pq2ads_pd.h
deleted file mode 100644
index 672483df807..00000000000
--- a/arch/ppc/platforms/pq2ads_pd.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef __PQ2ADS_PD_H
-#define __PQ2ADS_PD_H
-/*
- * arch/ppc/platforms/82xx/pq2ads_pd.h
- *
- * Some defines for MPC82xx board-specific PlatformDevice descriptions
- *
- * 2005 (c) MontaVista Software, Inc.
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-/* FCC1 Clock Source Configuration. These can be redefined in the board specific file.
- Can only choose from CLK9-12 */
-
-#define F1_RXCLK 11
-#define F1_TXCLK 10
-
-/* FCC2 Clock Source Configuration. These can be redefined in the board specific file.
- Can only choose from CLK13-16 */
-#define F2_RXCLK 15
-#define F2_TXCLK 16
-
-/* FCC3 Clock Source Configuration. These can be redefined in the board specific file.
- Can only choose from CLK13-16 */
-#define F3_RXCLK 13
-#define F3_TXCLK 14
-
-#endif
diff --git a/arch/ppc/syslib/m8260_setup.c b/arch/ppc/syslib/m8260_setup.c
index 46588fa9438..b40583724de 100644
--- a/arch/ppc/syslib/m8260_setup.c
+++ b/arch/ppc/syslib/m8260_setup.c
@@ -175,12 +175,6 @@ m8260_init_IRQ(void)
* in case the boot rom changed something on us.
*/
cpm2_immr->im_intctl.ic_siprr = 0x05309770;
-
-#if defined(CONFIG_PCI) && (defined(CONFIG_ADS8272) || defined(CONFIG_PQ2FADS))
- /* Initialize stuff for the 82xx CPLD IC and install demux */
- pq2pci_init_irq();
-#endif
-
}
/*
diff --git a/arch/ppc/syslib/m82xx_pci.c b/arch/ppc/syslib/m82xx_pci.c
index fe860d52e2e..657a1c25a2a 100644
--- a/arch/ppc/syslib/m82xx_pci.c
+++ b/arch/ppc/syslib/m82xx_pci.c
@@ -150,14 +150,6 @@ pq2pci_init_irq(void)
{
int irq;
volatile cpm2_map_t *immap = cpm2_immr;
-#if defined CONFIG_ADS8272
- /* configure chip select for PCI interrupt controller */
- immap->im_memctl.memc_br3 = PCI_INT_STAT_REG | 0x00001801;
- immap->im_memctl.memc_or3 = 0xffff8010;
-#elif defined CONFIG_PQ2FADS
- immap->im_memctl.memc_br8 = PCI_INT_STAT_REG | 0x00001801;
- immap->im_memctl.memc_or8 = 0xffff8010;
-#endif
for (irq = NR_CPM_INTS; irq < NR_CPM_INTS + 4; irq++)
irq_desc[irq].chip = &pq2pci_ic;
@@ -222,26 +214,6 @@ pq2ads_setup_pci(struct pci_controller *hose)
immap->im_memctl.memc_pcibr1 = M82xx_PCI_SEC_WND_BASE | PCIBR_ENABLE;
#endif
-#if defined CONFIG_ADS8272
- immap->im_siu_conf.siu_82xx.sc_siumcr =
- (immap->im_siu_conf.siu_82xx.sc_siumcr &
- ~(SIUMCR_BBD | SIUMCR_ESE | SIUMCR_PBSE |
- SIUMCR_CDIS | SIUMCR_DPPC11 | SIUMCR_L2CPC11 |
- SIUMCR_LBPC11 | SIUMCR_APPC11 |
- SIUMCR_CS10PC11 | SIUMCR_BCTLC11 | SIUMCR_MMR11)) |
- SIUMCR_DPPC11 | SIUMCR_L2CPC01 | SIUMCR_LBPC00 |
- SIUMCR_APPC10 | SIUMCR_CS10PC00 |
- SIUMCR_BCTLC00 | SIUMCR_MMR11 ;
-
-#elif defined CONFIG_PQ2FADS
- /*
- * Setting required to enable IRQ1-IRQ7 (SIUMCR [DPPC]),
- * and local bus for PCI (SIUMCR [LBPC]).
- */
- immap->im_siu_conf.siu_82xx.sc_siumcr = (immap->im_siu_conf.siu_82xx.sc_siumcr &
- ~(SIUMCR_L2CPC11 | SIUMCR_LBPC11 | SIUMCR_CS10PC11 | SIUMCR_APPC11) |
- SIUMCR_BBD | SIUMCR_LBPC01 | SIUMCR_DPPC11 | SIUMCR_APPC10);
-#endif
/* Enable PCI */
immap->im_pci.pci_gcr = cpu_to_le32(PCIGCR_PCI_BUS_EN);
@@ -284,12 +256,6 @@ pq2ads_setup_pci(struct pci_controller *hose)
immap->im_pci.pci_pibar0 = cpu_to_le32(M82xx_PCI_SLAVE_MEM_BUS >> PITA_ADDR_SHIFT);
immap->im_pci.pci_pitar0 = cpu_to_le32(M82xx_PCI_SLAVE_MEM_LOCAL>> PITA_ADDR_SHIFT);
-#if defined CONFIG_ADS8272
- /* PCI int highest prio */
- immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x01236745;
-#elif defined CONFIG_PQ2FADS
- immap->im_siu_conf.siu_82xx.sc_ppc_alrh = 0x03124567;
-#endif
/* park bus on PCI */
immap->im_siu_conf.siu_82xx.sc_ppc_acr = PPC_ACR_BUS_PARK_PCI;
@@ -320,10 +286,6 @@ void __init pq2_find_bridges(void)
hose->bus_offset = 0;
hose->last_busno = 0xff;
-#ifdef CONFIG_ADS8272
- hose->set_cfg_type = 1;
-#endif
-
setup_m8260_indirect_pci(hose,
(unsigned long)&cpm2_immr->im_pci.pci_cfg_addr,
(unsigned long)&cpm2_immr->im_pci.pci_cfg_data);
diff --git a/arch/ppc/syslib/m8xx_setup.c b/arch/ppc/syslib/m8xx_setup.c
index 19749e9bcf9..18da720fc1b 100644
--- a/arch/ppc/syslib/m8xx_setup.c
+++ b/arch/ppc/syslib/m8xx_setup.c
@@ -141,16 +141,6 @@ m8xx_setup_arch(void)
#endif
#endif
-#if defined (CONFIG_MPC86XADS) || defined (CONFIG_MPC885ADS)
-#if defined(CONFIG_MTD_PHYSMAP)
- physmap_configure(binfo->bi_flashstart, binfo->bi_flashsize,
- MPC8xxADS_BANK_WIDTH, NULL);
-#ifdef CONFIG_MTD_PARTITIONS
- physmap_set_partitions(mpc8xxads_partitions, mpc8xxads_part_num);
-#endif /* CONFIG_MTD_PARTITIONS */
-#endif /* CONFIG_MTD_PHYSMAP */
-#endif
-
board_init();
}
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f6a68e178fc..8f5f02160ff 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -62,6 +62,10 @@ config GENERIC_LOCKBREAK
default y
depends on SMP && PREEMPT
+config PGSTE
+ bool
+ default y if KVM
+
mainmenu "Linux Kernel Configuration"
config S390
@@ -69,6 +73,7 @@ config S390
select HAVE_OPROFILE
select HAVE_KPROBES
select HAVE_KRETPROBES
+ select HAVE_KVM if 64BIT
source "init/Kconfig"
@@ -515,6 +520,13 @@ config ZFCPDUMP
Select this option if you want to build an zfcpdump enabled kernel.
Refer to <file:Documentation/s390/zfcpdump.txt> for more details on this.
+config S390_GUEST
+bool "s390 guest support (EXPERIMENTAL)"
+ depends on 64BIT && EXPERIMENTAL
+ select VIRTIO
+ select VIRTIO_RING
+ help
+ Select this option if you want to run the kernel under s390 linux
endmenu
source "net/Kconfig"
@@ -536,3 +548,5 @@ source "security/Kconfig"
source "crypto/Kconfig"
source "lib/Kconfig"
+
+source "arch/s390/kvm/Kconfig"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index f708be367b0..792a4e7743c 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -87,7 +87,7 @@ LDFLAGS_vmlinux := -e start
head-y := arch/s390/kernel/head.o arch/s390/kernel/init_task.o
core-y += arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \
- arch/s390/appldata/ arch/s390/hypfs/
+ arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/
libs-y += arch/s390/lib/
drivers-y += drivers/s390/
drivers-$(CONFIG_MATHEMU) += arch/s390/math-emu/
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 540a67f979b..68ec4083bf7 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -144,6 +144,10 @@ static noinline __init void detect_machine_type(void)
/* Running on a P/390 ? */
if (cpuinfo->cpu_id.machine == 0x7490)
machine_flags |= 4;
+
+ /* Running under KVM ? */
+ if (cpuinfo->cpu_id.version == 0xfe)
+ machine_flags |= 64;
}
#ifdef CONFIG_64BIT
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 7141147e6b6..a9d18aafa5f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -316,7 +316,11 @@ static int __init early_parse_ipldelay(char *p)
early_param("ipldelay", early_parse_ipldelay);
#ifdef CONFIG_S390_SWITCH_AMODE
+#ifdef CONFIG_PGSTE
+unsigned int switch_amode = 1;
+#else
unsigned int switch_amode = 0;
+#endif
EXPORT_SYMBOL_GPL(switch_amode);
static void set_amode_and_uaccess(unsigned long user_amode,
@@ -797,9 +801,13 @@ setup_arch(char **cmdline_p)
"This machine has an IEEE fpu\n" :
"This machine has no IEEE fpu\n");
#else /* CONFIG_64BIT */
- printk((MACHINE_IS_VM) ?
- "We are running under VM (64 bit mode)\n" :
- "We are running native (64 bit mode)\n");
+ if (MACHINE_IS_VM)
+ printk("We are running under VM (64 bit mode)\n");
+ else if (MACHINE_IS_KVM) {
+ printk("We are running under KVM (64 bit mode)\n");
+ add_preferred_console("ttyS", 1, NULL);
+ } else
+ printk("We are running native (64 bit mode)\n");
#endif /* CONFIG_64BIT */
/* Save unparsed command line copy for /proc/cmdline */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c5f05b3fb2c..ca90ee3f930 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -110,6 +110,7 @@ void account_system_vtime(struct task_struct *tsk)
S390_lowcore.steal_clock -= cputime << 12;
account_system_time(tsk, 0, cputime);
}
+EXPORT_SYMBOL_GPL(account_system_vtime);
static inline void set_vtimer(__u64 expires)
{
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
new file mode 100644
index 00000000000..1761b74d639
--- /dev/null
+++ b/arch/s390/kvm/Kconfig
@@ -0,0 +1,46 @@
+#
+# KVM configuration
+#
+config HAVE_KVM
+ bool
+
+menuconfig VIRTUALIZATION
+ bool "Virtualization"
+ default y
+ ---help---
+ Say Y here to get to see options for using your Linux host to run other
+ operating systems inside virtual machines (guests).
+ This option alone does not add any kernel code.
+
+ If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRTUALIZATION
+
+config KVM
+ tristate "Kernel-based Virtual Machine (KVM) support"
+ depends on HAVE_KVM && EXPERIMENTAL
+ select PREEMPT_NOTIFIERS
+ select ANON_INODES
+ select S390_SWITCH_AMODE
+ select PREEMPT
+ ---help---
+ Support hosting paravirtualized guest machines using the SIE
+ virtualization capability on the mainframe. This should work
+ on any 64bit machine.
+
+ This module provides access to the hardware capabilities through
+ a character device node named /dev/kvm.
+
+ To compile this as a module, choose M here: the module
+ will be called kvm.
+
+ If unsure, say N.
+
+config KVM_TRACE
+ bool
+
+# OK, it's a little counter-intuitive to do this, but it puts it neatly under
+# the virtualization menu.
+source drivers/virtio/Kconfig
+
+endif # VIRTUALIZATION
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
new file mode 100644
index 00000000000..e5221ec0b8e
--- /dev/null
+++ b/arch/s390/kvm/Makefile
@@ -0,0 +1,14 @@
+# Makefile for kernel virtual machines on s390
+#
+# Copyright IBM Corp. 2008
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License (version 2 only)
+# as published by the Free Software Foundation.
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
+
+EXTRA_CFLAGS += -Ivirt/kvm -Iarch/s390/kvm
+
+kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o
+obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
new file mode 100644
index 00000000000..f639a152869
--- /dev/null
+++ b/arch/s390/kvm/diag.c
@@ -0,0 +1,67 @@
+/*
+ * diag.c - handling diagnose instructions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include "kvm-s390.h"
+
+static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
+{
+ VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
+ vcpu->stat.diagnose_44++;
+ vcpu_put(vcpu);
+ schedule();
+ vcpu_load(vcpu);
+ return 0;
+}
+
+static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
+{
+ unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
+ unsigned long subcode = vcpu->arch.guest_gprs[reg] & 0xffff;
+
+ VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+ switch (subcode) {
+ case 3:
+ vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
+ break;
+ case 4:
+ vcpu->run->s390_reset_flags = 0;
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+
+ atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
+ vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
+ vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
+ vcpu->run->exit_reason = KVM_EXIT_S390_RESET;
+ VCPU_EVENT(vcpu, 3, "requesting userspace resets %lx",
+ vcpu->run->s390_reset_flags);
+ return -EREMOTE;
+}
+
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
+{
+ int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+
+ switch (code) {
+ case 0x44:
+ return __diag_time_slice_end(vcpu);
+ case 0x308:
+ return __diag_ipl_functions(vcpu);
+ default:
+ return -ENOTSUPP;
+ }
+}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
new file mode 100644
index 00000000000..4e0633c413f
--- /dev/null
+++ b/arch/s390/kvm/gaccess.h
@@ -0,0 +1,274 @@
+/*
+ * gaccess.h - access guest memory
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#ifndef __KVM_S390_GACCESS_H
+#define __KVM_S390_GACCESS_H
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/uaccess.h>
+
+static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
+ u64 guestaddr)
+{
+ u64 prefix = vcpu->arch.sie_block->prefix;
+ u64 origin = vcpu->kvm->arch.guest_origin;
+ u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+ if (guestaddr < 2 * PAGE_SIZE)
+ guestaddr += prefix;
+ else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE))
+ guestaddr -= prefix;
+
+ if (guestaddr > memsize)
+ return (void __user __force *) ERR_PTR(-EFAULT);
+
+ guestaddr += origin;
+
+ return (void __user *) guestaddr;
+}
+
+static inline int get_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u64 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 7);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (u64 __user *) uptr);
+}
+
+static inline int get_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u32 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 3);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (u32 __user *) uptr);
+}
+
+static inline int get_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u16 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 1);
+
+ if (IS_ERR(uptr))
+ return PTR_ERR(uptr);
+
+ return get_user(*result, (u16 __user *) uptr);
+}
+
+static inline int get_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u8 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (u8 __user *) uptr);
+}
+
+static inline int put_guest_u64(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u64 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 7);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u64 __user *) uptr);
+}
+
+static inline int put_guest_u32(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u32 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 3);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u32 __user *) uptr);
+}
+
+static inline int put_guest_u16(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u16 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 1);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u16 __user *) uptr);
+}
+
+static inline int put_guest_u8(struct kvm_vcpu *vcpu, u64 guestaddr,
+ u8 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u8 __user *) uptr);
+}
+
+
+static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu, u64 guestdest,
+ const void *from, unsigned long n)
+{
+ int rc;
+ unsigned long i;
+ const u8 *data = from;
+
+ for (i = 0; i < n; i++) {
+ rc = put_guest_u8(vcpu, guestdest++, *(data++));
+ if (rc < 0)
+ return rc;
+ }
+ return 0;
+}
+
+static inline int copy_to_guest(struct kvm_vcpu *vcpu, u64 guestdest,
+ const void *from, unsigned long n)
+{
+ u64 prefix = vcpu->arch.sie_block->prefix;
+ u64 origin = vcpu->kvm->arch.guest_origin;
+ u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+ if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if ((guestdest < prefix) && (guestdest + n > prefix))
+ goto slowpath;
+
+ if ((guestdest < prefix + 2 * PAGE_SIZE)
+ && (guestdest + n > prefix + 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if (guestdest < 2 * PAGE_SIZE)
+ guestdest += prefix;
+ else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE))
+ guestdest -= prefix;
+
+ if (guestdest + n > memsize)
+ return -EFAULT;
+
+ if (guestdest + n < guestdest)
+ return -EFAULT;
+
+ guestdest += origin;
+
+ return copy_to_user((void __user *) guestdest, from, n);
+slowpath:
+ return __copy_to_guest_slow(vcpu, guestdest, from, n);
+}
+
+static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to,
+ u64 guestsrc, unsigned long n)
+{
+ int rc;
+ unsigned long i;
+ u8 *data = to;
+
+ for (i = 0; i < n; i++) {
+ rc = get_guest_u8(vcpu, guestsrc++, data++);
+ if (rc < 0)
+ return rc;
+ }
+ return 0;
+}
+
+static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
+ u64 guestsrc, unsigned long n)
+{
+ u64 prefix = vcpu->arch.sie_block->prefix;
+ u64 origin = vcpu->kvm->arch.guest_origin;
+ u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+ if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if ((guestsrc < prefix) && (guestsrc + n > prefix))
+ goto slowpath;
+
+ if ((guestsrc < prefix + 2 * PAGE_SIZE)
+ && (guestsrc + n > prefix + 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if (guestsrc < 2 * PAGE_SIZE)
+ guestsrc += prefix;
+ else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
+ guestsrc -= prefix;
+
+ if (guestsrc + n > memsize)
+ return -EFAULT;
+
+ if (guestsrc + n < guestsrc)
+ return -EFAULT;
+
+ guestsrc += origin;
+
+ return copy_from_user(to, (void __user *) guestsrc, n);
+slowpath:
+ return __copy_from_guest_slow(vcpu, to, guestsrc, n);
+}
+
+static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu, u64 guestdest,
+ const void *from, unsigned long n)
+{
+ u64 origin = vcpu->kvm->arch.guest_origin;
+ u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+ if (guestdest + n > memsize)
+ return -EFAULT;
+
+ if (guestdest + n < guestdest)
+ return -EFAULT;
+
+ guestdest += origin;
+
+ return copy_to_user((void __user *) guestdest, from, n);
+}
+
+static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
+ u64 guestsrc, unsigned long n)
+{
+ u64 origin = vcpu->kvm->arch.guest_origin;
+ u64 memsize = vcpu->kvm->arch.guest_memsize;
+
+ if (guestsrc + n > memsize)
+ return -EFAULT;
+
+ if (guestsrc + n < guestsrc)
+ return -EFAULT;
+
+ guestsrc += origin;
+
+ return copy_from_user(to, (void __user *) guestsrc, n);
+}
+#endif
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
new file mode 100644
index 00000000000..349581a2610
--- /dev/null
+++ b/arch/s390/kvm/intercept.c
@@ -0,0 +1,216 @@
+/*
+ * intercept.c - in-kernel handling for sie intercepts
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include <linux/pagemap.h>
+
+#include <asm/kvm_host.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+static int handle_lctg(struct kvm_vcpu *vcpu)
+{
+ int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+ int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+ ((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+ u64 useraddr;
+ int reg, rc;
+
+ vcpu->stat.instruction_lctg++;
+ if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
+ return -ENOTSUPP;
+
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ reg = reg1;
+
+ VCPU_EVENT(vcpu, 5, "lctg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+ disp2);
+
+ do {
+ rc = get_guest_u64(vcpu, useraddr,
+ &vcpu->arch.sie_block->gcr[reg]);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ break;
+ }
+ useraddr += 8;
+ if (reg == reg3)
+ break;
+ reg = (reg + 1) % 16;
+ } while (1);
+ return 0;
+}
+
+static int handle_lctl(struct kvm_vcpu *vcpu)
+{
+ int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+ int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 useraddr;
+ u32 val = 0;
+ int reg, rc;
+
+ vcpu->stat.instruction_lctl++;
+
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+ disp2);
+
+ reg = reg1;
+ do {
+ rc = get_guest_u32(vcpu, useraddr, &val);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ break;
+ }
+ vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
+ vcpu->arch.sie_block->gcr[reg] |= val;
+ useraddr += 4;
+ if (reg == reg3)
+ break;
+ reg = (reg + 1) % 16;
+ } while (1);
+ return 0;
+}
+
+static intercept_handler_t instruction_handlers[256] = {
+ [0x83] = kvm_s390_handle_diag,
+ [0xae] = kvm_s390_handle_sigp,
+ [0xb2] = kvm_s390_handle_priv,
+ [0xb7] = handle_lctl,
+ [0xeb] = handle_lctg,
+};
+
+static int handle_noop(struct kvm_vcpu *vcpu)
+{
+ switch (vcpu->arch.sie_block->icptcode) {
+ case 0x10:
+ vcpu->stat.exit_external_request++;
+ break;
+ case 0x14:
+ vcpu->stat.exit_external_interrupt++;
+ break;
+ default:
+ break; /* nothing */
+ }
+ return 0;
+}
+
+static int handle_stop(struct kvm_vcpu *vcpu)
+{
+ int rc;
+
+ vcpu->stat.exit_stop_request++;
+ atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ spin_lock_bh(&vcpu->arch.local_int.lock);
+ if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+ vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+ rc = __kvm_s390_vcpu_store_status(vcpu,
+ KVM_S390_STORE_STATUS_NOADDR);
+ if (rc >= 0)
+ rc = -ENOTSUPP;
+ }
+
+ if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+ vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
+ VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
+ rc = -ENOTSUPP;
+ } else
+ rc = 0;
+ spin_unlock_bh(&vcpu->arch.local_int.lock);
+ return rc;
+}
+
+static int handle_validity(struct kvm_vcpu *vcpu)
+{
+ int viwhy = vcpu->arch.sie_block->ipb >> 16;
+ vcpu->stat.exit_validity++;
+ if (viwhy == 0x37) {
+ fault_in_pages_writeable((char __user *)
+ vcpu->kvm->arch.guest_origin +
+ vcpu->arch.sie_block->prefix,
+ PAGE_SIZE);
+ return 0;
+ }
+ VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
+ viwhy);
+ return -ENOTSUPP;
+}
+
+static int handle_instruction(struct kvm_vcpu *vcpu)
+{
+ intercept_handler_t handler;
+
+ vcpu->stat.exit_instruction++;
+ handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
+ if (handler)
+ return handler(vcpu);
+ return -ENOTSUPP;
+}
+
+static int handle_prog(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.exit_program_interruption++;
+ return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
+}
+
+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 == -ENOTSUPP)
+ vcpu->arch.sie_block->icptcode = 0x04;
+ if (rc)
+ return rc;
+ return rc2;
+}
+
+static const intercept_handler_t intercept_funcs[0x48 >> 2] = {
+ [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_noop,
+ [0x1C >> 2] = kvm_s390_handle_wait,
+ [0x20 >> 2] = handle_validity,
+ [0x28 >> 2] = handle_stop,
+};
+
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
+{
+ intercept_handler_t func;
+ u8 code = vcpu->arch.sie_block->icptcode;
+
+ if (code & 3 || code > 0x48)
+ return -ENOTSUPP;
+ func = intercept_funcs[code >> 2];
+ if (func)
+ return func(vcpu);
+ return -ENOTSUPP;
+}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
new file mode 100644
index 00000000000..fcd1ed8015c
--- /dev/null
+++ b/arch/s390/kvm/interrupt.c
@@ -0,0 +1,592 @@
+/*
+ * interrupt.c - handling kvm guest interrupts
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#include <asm/lowcore.h>
+#include <asm/uaccess.h>
+#include <linux/kvm_host.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+{
+ return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
+}
+
+static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
+{
+ if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
+ (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) ||
+ (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT))
+ return 0;
+ return 1;
+}
+
+static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
+ struct interrupt_info *inti)
+{
+ switch (inti->type) {
+ case KVM_S390_INT_EMERGENCY:
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
+ return 1;
+ return 0;
+ case KVM_S390_INT_SERVICE:
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+ return 1;
+ return 0;
+ case KVM_S390_INT_VIRTIO:
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+ return 1;
+ return 0;
+ case KVM_S390_PROGRAM_INT:
+ case KVM_S390_SIGP_STOP:
+ case KVM_S390_SIGP_SET_PREFIX:
+ case KVM_S390_RESTART:
+ return 1;
+ default:
+ BUG();
+ }
+ return 0;
+}
+
+static void __set_cpu_idle(struct kvm_vcpu *vcpu)
+{
+ BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+ atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
+{
+ BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+ atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
+{
+ atomic_clear_mask(CPUSTAT_ECALL_PEND |
+ CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
+ &vcpu->arch.sie_block->cpuflags);
+ vcpu->arch.sie_block->lctl = 0x0000;
+}
+
+static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
+{
+ atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
+}
+
+static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
+ struct interrupt_info *inti)
+{
+ switch (inti->type) {
+ case KVM_S390_INT_EMERGENCY:
+ case KVM_S390_INT_SERVICE:
+ case KVM_S390_INT_VIRTIO:
+ if (psw_extint_disabled(vcpu))
+ __set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+ else
+ vcpu->arch.sie_block->lctl |= LCTL_CR0;
+ break;
+ case KVM_S390_SIGP_STOP:
+ __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ break;
+ default:
+ BUG();
+ }
+}
+
+static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
+ struct interrupt_info *inti)
+{
+ const unsigned short table[] = { 2, 4, 4, 6 };
+ int rc, exception = 0;
+
+ switch (inti->type) {
+ case KVM_S390_INT_EMERGENCY:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+ vcpu->stat.deliver_emergency_signal++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_INT_SERVICE:
+ VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+ inti->ext.ext_params);
+ vcpu->stat.deliver_service_signal++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_INT_VIRTIO:
+ VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%lx",
+ inti->ext.ext_params, inti->ext.ext_params2);
+ vcpu->stat.deliver_virtio_interrupt++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, 0x0d00);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u64(vcpu, __LC_PFAULT_INTPARM,
+ inti->ext.ext_params2);
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_SIGP_STOP:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
+ vcpu->stat.deliver_stop_signal++;
+ __set_intercept_indicator(vcpu, inti);
+ break;
+
+ case KVM_S390_SIGP_SET_PREFIX:
+ VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
+ inti->prefix.address);
+ vcpu->stat.deliver_prefix_signal++;
+ vcpu->arch.sie_block->prefix = inti->prefix.address;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+ break;
+
+ case KVM_S390_RESTART:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+ vcpu->stat.deliver_restart_signal++;
+ rc = copy_to_guest(vcpu, offsetof(struct _lowcore,
+ restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_PROGRAM_INT:
+ VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+ inti->pgm.code,
+ table[vcpu->arch.sie_block->ipa >> 14]);
+ vcpu->stat.deliver_program_int++;
+ rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_PGM_ILC,
+ table[vcpu->arch.sie_block->ipa >> 14]);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_PGM_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ default:
+ BUG();
+ }
+
+ if (exception) {
+ VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering"
+ " interrupt");
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ if (inti->type == KVM_S390_PROGRAM_INT) {
+ printk(KERN_WARNING "kvm: recursive program check\n");
+ BUG();
+ }
+ }
+}
+
+static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
+{
+ int rc, exception = 0;
+
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ return 0;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1004);
+ if (rc == -EFAULT)
+ exception = 1;
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ if (exception) {
+ VCPU_EVENT(vcpu, 1, "%s", "program exception while delivering" \
+ " ckc interrupt");
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ return 0;
+ }
+
+ return 1;
+}
+
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct local_interrupt *li = &vcpu->arch.local_int;
+ struct float_interrupt *fi = vcpu->arch.local_int.float_int;
+ struct interrupt_info *inti;
+ int rc = 0;
+
+ if (atomic_read(&li->active)) {
+ spin_lock_bh(&li->lock);
+ list_for_each_entry(inti, &li->list, list)
+ if (__interrupt_is_deliverable(vcpu, inti)) {
+ rc = 1;
+ break;
+ }
+ spin_unlock_bh(&li->lock);
+ }
+
+ if ((!rc) && atomic_read(&fi->active)) {
+ spin_lock_bh(&fi->lock);
+ list_for_each_entry(inti, &fi->list, list)
+ if (__interrupt_is_deliverable(vcpu, inti)) {
+ rc = 1;
+ break;
+ }
+ spin_unlock_bh(&fi->lock);
+ }
+
+ if ((!rc) && (vcpu->arch.sie_block->ckc <
+ get_clock() + vcpu->arch.sie_block->epoch)) {
+ if ((!psw_extint_disabled(vcpu)) &&
+ (vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ rc = 1;
+ }
+
+ return rc;
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
+{
+ u64 now, sltime;
+ DECLARE_WAITQUEUE(wait, current);
+
+ vcpu->stat.exit_wait_state++;
+ if (kvm_cpu_has_interrupt(vcpu))
+ return 0;
+
+ if (psw_interrupts_disabled(vcpu)) {
+ VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
+ __unset_cpu_idle(vcpu);
+ return -ENOTSUPP; /* disabled wait */
+ }
+
+ if (psw_extint_disabled(vcpu) ||
+ (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
+ VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
+ goto no_timer;
+ }
+
+ now = get_clock() + vcpu->arch.sie_block->epoch;
+ if (vcpu->arch.sie_block->ckc < now) {
+ __unset_cpu_idle(vcpu);
+ return 0;
+ }
+
+ sltime = (vcpu->arch.sie_block->ckc - now) / (0xf4240000ul / HZ) + 1;
+
+ vcpu->arch.ckc_timer.expires = jiffies + sltime;
+
+ add_timer(&vcpu->arch.ckc_timer);
+ VCPU_EVENT(vcpu, 5, "enabled wait timer:%lx jiffies", sltime);
+no_timer:
+ spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+ spin_lock_bh(&vcpu->arch.local_int.lock);
+ __set_cpu_idle(vcpu);
+ vcpu->arch.local_int.timer_due = 0;
+ add_wait_queue(&vcpu->arch.local_int.wq, &wait);
+ while (list_empty(&vcpu->arch.local_int.list) &&
+ list_empty(&vcpu->arch.local_int.float_int->list) &&
+ (!vcpu->arch.local_int.timer_due) &&
+ !signal_pending(current)) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_bh(&vcpu->arch.local_int.lock);
+ spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
+ vcpu_put(vcpu);
+ schedule();
+ vcpu_load(vcpu);
+ spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
+ spin_lock_bh(&vcpu->arch.local_int.lock);
+ }
+ __unset_cpu_idle(vcpu);
+ __set_current_state(TASK_RUNNING);
+ remove_wait_queue(&vcpu->wq, &wait);
+ spin_unlock_bh(&vcpu->arch.local_int.lock);
+ spin_unlock_bh(&vcpu->arch.local_int.float_int->lock);
+ del_timer(&vcpu->arch.ckc_timer);
+ return 0;
+}
+
+void kvm_s390_idle_wakeup(unsigned long data)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+ spin_lock_bh(&vcpu->arch.local_int.lock);
+ vcpu->arch.local_int.timer_due = 1;
+ if (waitqueue_active(&vcpu->arch.local_int.wq))
+ wake_up_interruptible(&vcpu->arch.local_int.wq);
+ spin_unlock_bh(&vcpu->arch.local_int.lock);
+}
+
+
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
+{
+ struct local_interrupt *li = &vcpu->arch.local_int;
+ struct float_interrupt *fi = vcpu->arch.local_int.float_int;
+ struct interrupt_info *n, *inti = NULL;
+ int deliver;
+
+ __reset_intercept_indicators(vcpu);
+ if (atomic_read(&li->active)) {
+ do {
+ deliver = 0;
+ spin_lock_bh(&li->lock);
+ list_for_each_entry_safe(inti, n, &li->list, list) {
+ if (__interrupt_is_deliverable(vcpu, inti)) {
+ list_del(&inti->list);
+ deliver = 1;
+ break;
+ }
+ __set_intercept_indicator(vcpu, inti);
+ }
+ if (list_empty(&li->list))
+ atomic_set(&li->active, 0);
+ spin_unlock_bh(&li->lock);
+ if (deliver) {
+ __do_deliver_interrupt(vcpu, inti);
+ kfree(inti);
+ }
+ } while (deliver);
+ }
+
+ if ((vcpu->arch.sie_block->ckc <
+ get_clock() + vcpu->arch.sie_block->epoch))
+ __try_deliver_ckc_interrupt(vcpu);
+
+ if (atomic_read(&fi->active)) {
+ do {
+ deliver = 0;
+ spin_lock_bh(&fi->lock);
+ list_for_each_entry_safe(inti, n, &fi->list, list) {
+ if (__interrupt_is_deliverable(vcpu, inti)) {
+ list_del(&inti->list);
+ deliver = 1;
+ break;
+ }
+ __set_intercept_indicator(vcpu, inti);
+ }
+ if (list_empty(&fi->list))
+ atomic_set(&fi->active, 0);
+ spin_unlock_bh(&fi->lock);
+ if (deliver) {
+ __do_deliver_interrupt(vcpu, inti);
+ kfree(inti);
+ }
+ } while (deliver);
+ }
+}
+
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
+{
+ struct local_interrupt *li = &vcpu->arch.local_int;
+ struct interrupt_info *inti;
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ inti->type = KVM_S390_PROGRAM_INT;;
+ inti->pgm.code = code;
+
+ VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
+ spin_lock_bh(&li->lock);
+ list_add(&inti->list, &li->list);
+ atomic_set(&li->active, 1);
+ BUG_ON(waitqueue_active(&li->wq));
+ spin_unlock_bh(&li->lock);
+ return 0;
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+ struct kvm_s390_interrupt *s390int)
+{
+ struct local_interrupt *li;
+ struct float_interrupt *fi;
+ struct interrupt_info *inti;
+ int sigcpu;
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ switch (s390int->type) {
+ case KVM_S390_INT_VIRTIO:
+ VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%lx",
+ s390int->parm, s390int->parm64);
+ inti->type = s390int->type;
+ inti->ext.ext_params = s390int->parm;
+ inti->ext.ext_params2 = s390int->parm64;
+ break;
+ case KVM_S390_INT_SERVICE:
+ VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
+ inti->type = s390int->type;
+ inti->ext.ext_params = s390int->parm;
+ break;
+ case KVM_S390_PROGRAM_INT:
+ case KVM_S390_SIGP_STOP:
+ case KVM_S390_INT_EMERGENCY:
+ default:
+ kfree(inti);
+ return -EINVAL;
+ }
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock_bh(&fi->lock);
+ list_add_tail(&inti->list, &fi->list);
+ atomic_set(&fi->active, 1);
+ 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 (fi->local_int[sigcpu] == NULL);
+ }
+ li = fi->local_int[sigcpu];
+ spin_lock_bh(&li->lock);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&li->wq);
+ spin_unlock_bh(&li->lock);
+ spin_unlock_bh(&fi->lock);
+ mutex_unlock(&kvm->lock);
+ return 0;
+}
+
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+ struct kvm_s390_interrupt *s390int)
+{
+ struct local_interrupt *li;
+ struct interrupt_info *inti;
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ switch (s390int->type) {
+ case KVM_S390_PROGRAM_INT:
+ if (s390int->parm & 0xffff0000) {
+ kfree(inti);
+ return -EINVAL;
+ }
+ inti->type = s390int->type;
+ inti->pgm.code = s390int->parm;
+ VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
+ s390int->parm);
+ break;
+ case KVM_S390_SIGP_STOP:
+ case KVM_S390_RESTART:
+ case KVM_S390_SIGP_SET_PREFIX:
+ case KVM_S390_INT_EMERGENCY:
+ VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
+ inti->type = s390int->type;
+ break;
+ case KVM_S390_INT_VIRTIO:
+ case KVM_S390_INT_SERVICE:
+ default:
+ kfree(inti);
+ return -EINVAL;
+ }
+
+ mutex_lock(&vcpu->kvm->lock);
+ li = &vcpu->arch.local_int;
+ spin_lock_bh(&li->lock);
+ if (inti->type == KVM_S390_PROGRAM_INT)
+ list_add(&inti->list, &li->list);
+ else
+ list_add_tail(&inti->list, &li->list);
+ atomic_set(&li->active, 1);
+ if (inti->type == KVM_S390_SIGP_STOP)
+ li->action_bits |= ACTION_STOP_ON_STOP;
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&vcpu->arch.local_int.wq);
+ spin_unlock_bh(&li->lock);
+ mutex_unlock(&vcpu->kvm->lock);
+ return 0;
+}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
new file mode 100644
index 00000000000..98d1e73e01f
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.c
@@ -0,0 +1,685 @@
+/*
+ * s390host.c -- hosting zSeries kernel virtual machines
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ * Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <asm/lowcore.h>
+#include <asm/pgtable.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+ { "userspace_handled", VCPU_STAT(exit_userspace) },
+ { "exit_validity", VCPU_STAT(exit_validity) },
+ { "exit_stop_request", VCPU_STAT(exit_stop_request) },
+ { "exit_external_request", VCPU_STAT(exit_external_request) },
+ { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
+ { "exit_instruction", VCPU_STAT(exit_instruction) },
+ { "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
+ { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+ { "instruction_lctg", VCPU_STAT(instruction_lctg) },
+ { "instruction_lctl", VCPU_STAT(instruction_lctl) },
+ { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
+ { "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
+ { "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
+ { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
+ { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
+ { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
+ { "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
+ { "exit_wait_state", VCPU_STAT(exit_wait_state) },
+ { "instruction_stidp", VCPU_STAT(instruction_stidp) },
+ { "instruction_spx", VCPU_STAT(instruction_spx) },
+ { "instruction_stpx", VCPU_STAT(instruction_stpx) },
+ { "instruction_stap", VCPU_STAT(instruction_stap) },
+ { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+ { "instruction_stsch", VCPU_STAT(instruction_stsch) },
+ { "instruction_chsc", VCPU_STAT(instruction_chsc) },
+ { "instruction_stsi", VCPU_STAT(instruction_stsi) },
+ { "instruction_stfl", VCPU_STAT(instruction_stfl) },
+ { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+ { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+ { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+ { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
+ { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
+ { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+ { "diagnose_44", VCPU_STAT(diagnose_44) },
+ { NULL }
+};
+
+
+/* Section: not file related */
+void kvm_arch_hardware_enable(void *garbage)
+{
+ /* every s390 is virtualization enabled ;-) */
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+}
+
+void decache_vcpus_on_cpu(int cpu)
+{
+}
+
+int kvm_arch_hardware_setup(void)
+{
+ return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+}
+
+int kvm_arch_init(void *opaque)
+{
+ return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
+
+/* Section: device related */
+long kvm_arch_dev_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ if (ioctl == KVM_S390_ENABLE_SIE)
+ return s390_enable_sie();
+ return -EINVAL;
+}
+
+int kvm_dev_ioctl_check_extension(long ext)
+{
+ return 0;
+}
+
+/* Section: vm related */
+/*
+ * 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)
+{
+ return 0;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm *kvm = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int r;
+
+ switch (ioctl) {
+ case KVM_S390_INTERRUPT: {
+ struct kvm_s390_interrupt s390int;
+
+ r = -EFAULT;
+ if (copy_from_user(&s390int, argp, sizeof(s390int)))
+ break;
+ r = kvm_s390_inject_vm(kvm, &s390int);
+ break;
+ }
+ default:
+ r = -EINVAL;
+ }
+
+ return r;
+}
+
+struct kvm *kvm_arch_create_vm(void)
+{
+ struct kvm *kvm;
+ int rc;
+ char debug_name[16];
+
+ rc = s390_enable_sie();
+ if (rc)
+ goto out_nokvm;
+
+ rc = -ENOMEM;
+ kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
+ if (!kvm)
+ goto out_nokvm;
+
+ kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+ if (!kvm->arch.sca)
+ goto out_nosca;
+
+ sprintf(debug_name, "kvm-%u", current->pid);
+
+ kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
+ if (!kvm->arch.dbf)
+ goto out_nodbf;
+
+ spin_lock_init(&kvm->arch.float_int.lock);
+ INIT_LIST_HEAD(&kvm->arch.float_int.list);
+
+ debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
+ VM_EVENT(kvm, 3, "%s", "vm created");
+
+ try_module_get(THIS_MODULE);
+
+ return kvm;
+out_nodbf:
+ free_page((unsigned long)(kvm->arch.sca));
+out_nosca:
+ kfree(kvm);
+out_nokvm:
+ return ERR_PTR(rc);
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+ debug_unregister(kvm->arch.dbf);
+ free_page((unsigned long)(kvm->arch.sca));
+ kfree(kvm);
+ module_put(THIS_MODULE);
+}
+
+/* Section: vcpu related */
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+ /* kvm common code refers to this, but does'nt call it */
+ BUG();
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ save_fp_regs(&vcpu->arch.host_fpregs);
+ save_access_regs(vcpu->arch.host_acrs);
+ vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
+ restore_fp_regs(&vcpu->arch.guest_fpregs);
+ restore_access_regs(vcpu->arch.guest_acrs);
+
+ if (signal_pending(current))
+ atomic_set_mask(CPUSTAT_STOP_INT,
+ &vcpu->arch.sie_block->cpuflags);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+ save_fp_regs(&vcpu->arch.guest_fpregs);
+ save_access_regs(vcpu->arch.guest_acrs);
+ restore_fp_regs(&vcpu->arch.host_fpregs);
+ restore_access_regs(vcpu->arch.host_acrs);
+}
+
+static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
+{
+ /* this equals initial cpu reset in pop, but we don't switch to ESA */
+ vcpu->arch.sie_block->gpsw.mask = 0UL;
+ vcpu->arch.sie_block->gpsw.addr = 0UL;
+ vcpu->arch.sie_block->prefix = 0UL;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+ vcpu->arch.sie_block->cputm = 0UL;
+ vcpu->arch.sie_block->ckc = 0UL;
+ vcpu->arch.sie_block->todpr = 0;
+ memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
+ vcpu->arch.sie_block->gcr[0] = 0xE0UL;
+ vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
+ vcpu->arch.guest_fpregs.fpc = 0;
+ asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+ vcpu->arch.sie_block->gbea = 1;
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
+ vcpu->arch.sie_block->gmslm = 0xffffffffffUL;
+ vcpu->arch.sie_block->gmsor = 0x000000000000;
+ vcpu->arch.sie_block->ecb = 2;
+ vcpu->arch.sie_block->eca = 0xC1002001U;
+ setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
+ (unsigned long) vcpu);
+ get_cpu_id(&vcpu->arch.cpu_id);
+ vcpu->arch.cpu_id.version = 0xfe;
+ return 0;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
+ unsigned int id)
+{
+ struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+ int rc = -ENOMEM;
+
+ if (!vcpu)
+ goto out_nomem;
+
+ vcpu->arch.sie_block = (struct sie_block *) get_zeroed_page(GFP_KERNEL);
+
+ if (!vcpu->arch.sie_block)
+ goto out_free_cpu;
+
+ vcpu->arch.sie_block->icpua = id;
+ BUG_ON(!kvm->arch.sca);
+ BUG_ON(kvm->arch.sca->cpu[id].sda);
+ kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+
+ spin_lock_init(&vcpu->arch.local_int.lock);
+ INIT_LIST_HEAD(&vcpu->arch.local_int.list);
+ vcpu->arch.local_int.float_int = &kvm->arch.float_int;
+ spin_lock_bh(&kvm->arch.float_int.lock);
+ kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
+ init_waitqueue_head(&vcpu->arch.local_int.wq);
+ vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+ spin_unlock_bh(&kvm->arch.float_int.lock);
+
+ rc = kvm_vcpu_init(vcpu, kvm, id);
+ if (rc)
+ goto out_free_cpu;
+ VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+ vcpu->arch.sie_block);
+
+ try_module_get(THIS_MODULE);
+
+ return vcpu;
+out_free_cpu:
+ kfree(vcpu);
+out_nomem:
+ return ERR_PTR(rc);
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ VCPU_EVENT(vcpu, 3, "%s", "destroy cpu");
+ free_page((unsigned long)(vcpu->arch.sie_block));
+ kfree(vcpu);
+ module_put(THIS_MODULE);
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+ /* kvm common code refers to this, but never calls it */
+ BUG();
+ return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
+{
+ vcpu_load(vcpu);
+ kvm_s390_vcpu_initial_reset(vcpu);
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_load(vcpu);
+ memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ vcpu_load(vcpu);
+ memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ vcpu_load(vcpu);
+ memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+ memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ vcpu_load(vcpu);
+ memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
+ memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ vcpu_load(vcpu);
+ memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ vcpu_load(vcpu);
+ memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
+ fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+ vcpu_put(vcpu);
+ return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
+{
+ int rc = 0;
+
+ vcpu_load(vcpu);
+ if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+ rc = -EBUSY;
+ else
+ vcpu->arch.sie_block->gpsw = psw;
+ vcpu_put(vcpu);
+ return rc;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
+ struct kvm_debug_guest *dbg)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+static void __vcpu_run(struct kvm_vcpu *vcpu)
+{
+ memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+
+ if (need_resched())
+ schedule();
+
+ vcpu->arch.sie_block->icptcode = 0;
+ local_irq_disable();
+ kvm_guest_enter();
+ local_irq_enable();
+ VCPU_EVENT(vcpu, 6, "entering sie flags %x",
+ atomic_read(&vcpu->arch.sie_block->cpuflags));
+ sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+ VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+ vcpu->arch.sie_block->icptcode);
+ local_irq_disable();
+ kvm_guest_exit();
+ local_irq_enable();
+
+ memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ int rc;
+ sigset_t sigsaved;
+
+ vcpu_load(vcpu);
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+ atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+
+ BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
+
+ switch (kvm_run->exit_reason) {
+ case KVM_EXIT_S390_SIEIC:
+ vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask;
+ vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
+ break;
+ case KVM_EXIT_UNKNOWN:
+ case KVM_EXIT_S390_RESET:
+ break;
+ default:
+ BUG();
+ }
+
+ might_sleep();
+
+ do {
+ kvm_s390_deliver_pending_interrupts(vcpu);
+ __vcpu_run(vcpu);
+ rc = kvm_handle_sie_intercept(vcpu);
+ } while (!signal_pending(current) && !rc);
+
+ if (signal_pending(current) && !rc)
+ rc = -EINTR;
+
+ if (rc == -ENOTSUPP) {
+ /* intercept cannot be handled in-kernel, prepare kvm-run */
+ kvm_run->exit_reason = KVM_EXIT_S390_SIEIC;
+ kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+ kvm_run->s390_sieic.mask = vcpu->arch.sie_block->gpsw.mask;
+ kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr;
+ kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
+ kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
+ rc = 0;
+ }
+
+ if (rc == -EREMOTE) {
+ /* intercept was handled, but userspace support is needed
+ * kvm_run has been prepared by the handler */
+ rc = 0;
+ }
+
+ if (vcpu->sigset_active)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+ vcpu_put(vcpu);
+
+ vcpu->stat.exit_userspace++;
+ return rc;
+}
+
+static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
+ unsigned long n, int prefix)
+{
+ if (prefix)
+ return copy_to_guest(vcpu, guestdest, from, n);
+ else
+ return copy_to_guest_absolute(vcpu, guestdest, from, n);
+}
+
+/*
+ * store status at address
+ * we use have two special cases:
+ * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
+ * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
+ */
+int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+ const unsigned char archmode = 1;
+ int prefix;
+
+ if (addr == KVM_S390_STORE_STATUS_NOADDR) {
+ if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
+ return -EFAULT;
+ addr = SAVE_AREA_BASE;
+ prefix = 0;
+ } else if (addr == KVM_S390_STORE_STATUS_PREFIXED) {
+ if (copy_to_guest(vcpu, 163ul, &archmode, 1))
+ return -EFAULT;
+ addr = SAVE_AREA_BASE;
+ prefix = 1;
+ } else
+ prefix = 0;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, fp_regs),
+ vcpu->arch.guest_fpregs.fprs, 128, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, gp_regs),
+ vcpu->arch.guest_gprs, 128, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, psw),
+ &vcpu->arch.sie_block->gpsw, 16, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, pref_reg),
+ &vcpu->arch.sie_block->prefix, 4, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu,
+ addr + offsetof(struct save_area_s390x, fp_ctrl_reg),
+ &vcpu->arch.guest_fpregs.fpc, 4, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, tod_reg),
+ &vcpu->arch.sie_block->todpr, 4, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, timer),
+ &vcpu->arch.sie_block->cputm, 8, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, clk_cmp),
+ &vcpu->arch.sie_block->ckc, 8, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, acc_regs),
+ &vcpu->arch.guest_acrs, 64, prefix))
+ return -EFAULT;
+
+ if (__guestcopy(vcpu,
+ addr + offsetof(struct save_area_s390x, ctrl_regs),
+ &vcpu->arch.sie_block->gcr, 128, prefix))
+ return -EFAULT;
+ return 0;
+}
+
+static int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+ int rc;
+
+ vcpu_load(vcpu);
+ rc = __kvm_s390_vcpu_store_status(vcpu, addr);
+ vcpu_put(vcpu);
+ return rc;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+
+ switch (ioctl) {
+ case KVM_S390_INTERRUPT: {
+ struct kvm_s390_interrupt s390int;
+
+ if (copy_from_user(&s390int, argp, sizeof(s390int)))
+ return -EFAULT;
+ return kvm_s390_inject_vcpu(vcpu, &s390int);
+ }
+ case KVM_S390_STORE_STATUS:
+ return kvm_s390_vcpu_store_status(vcpu, arg);
+ case KVM_S390_SET_INITIAL_PSW: {
+ psw_t psw;
+
+ if (copy_from_user(&psw, argp, sizeof(psw)))
+ return -EFAULT;
+ return kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
+ }
+ case KVM_S390_INITIAL_RESET:
+ return kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+ default:
+ ;
+ }
+ return -EINVAL;
+}
+
+/* Section: memory related */
+int kvm_arch_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ /* A few sanity checks. We can have exactly one memory slot which has
+ to start at guest virtual zero and which has to be located at a
+ page boundary in userland and which has to end at a page boundary.
+ The memory in userland is ok to be fragmented into various different
+ vmas. It is okay to mmap() and munmap() stuff in this slot after
+ doing this call at any time */
+
+ if (mem->slot)
+ return -EINVAL;
+
+ if (mem->guest_phys_addr)
+ return -EINVAL;
+
+ if (mem->userspace_addr & (PAGE_SIZE - 1))
+ return -EINVAL;
+
+ if (mem->memory_size & (PAGE_SIZE - 1))
+ return -EINVAL;
+
+ kvm->arch.guest_origin = mem->userspace_addr;
+ kvm->arch.guest_memsize = mem->memory_size;
+
+ /* FIXME: we do want to interrupt running CPUs and update their memory
+ configuration now to avoid race conditions. But hey, changing the
+ memory layout while virtual CPUs are running is usually bad
+ programming practice. */
+
+ return 0;
+}
+
+gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
+{
+ return gfn;
+}
+
+static int __init kvm_s390_init(void)
+{
+ return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+}
+
+static void __exit kvm_s390_exit(void)
+{
+ kvm_exit();
+}
+
+module_init(kvm_s390_init);
+module_exit(kvm_s390_exit);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
new file mode 100644
index 00000000000..3893cf12eac
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.h
@@ -0,0 +1,64 @@
+/*
+ * kvm_s390.h - definition for kvm on s390
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#ifndef ARCH_S390_KVM_S390_H
+#define ARCH_S390_KVM_S390_H
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
+
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+
+#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
+do { \
+ debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
+ d_args); \
+} while (0)
+
+#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)\
+do { \
+ debug_sprintf_event(d_vcpu->kvm->arch.dbf, d_loglevel, \
+ "%02d[%016lx-%016lx]: " d_string "\n", d_vcpu->vcpu_id, \
+ d_vcpu->arch.sie_block->gpsw.mask, d_vcpu->arch.sie_block->gpsw.addr,\
+ d_args); \
+} while (0)
+
+static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+{
+ return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
+void kvm_s390_idle_wakeup(unsigned long data);
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+int kvm_s390_inject_vm(struct kvm *kvm,
+ struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+ struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+
+/* implemented in priv.c */
+int kvm_s390_handle_priv(struct kvm_vcpu *vcpu);
+
+/* implemented in sigp.c */
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
+
+/* implemented in kvm-s390.c */
+int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
+ unsigned long addr);
+/* implemented in diag.c */
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
new file mode 100644
index 00000000000..1465946325c
--- /dev/null
+++ b/arch/s390/kvm/priv.c
@@ -0,0 +1,323 @@
+/*
+ * priv.c - handling privileged instructions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <asm/current.h>
+#include <asm/debug.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+
+static int handle_set_prefix(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ u32 address = 0;
+ u8 tmp;
+
+ vcpu->stat.instruction_spx++;
+
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ /* must be word boundary */
+ if (operand2 & 3) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ /* get the value */
+ if (get_guest_u32(vcpu, operand2, &address)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ address = address & 0x7fffe000u;
+
+ /* make sure that the new value is valid memory */
+ if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+ (copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1))) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ vcpu->arch.sie_block->prefix = address;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+
+ VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
+out:
+ return 0;
+}
+
+static int handle_store_prefix(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ u32 address;
+
+ vcpu->stat.instruction_stpx++;
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ /* must be word boundary */
+ if (operand2 & 3) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ address = vcpu->arch.sie_block->prefix;
+ address = address & 0x7fffe000u;
+
+ /* get the value */
+ if (put_guest_u32(vcpu, operand2, address)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+out:
+ return 0;
+}
+
+static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 useraddr;
+ int rc;
+
+ vcpu->stat.instruction_stap++;
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ if (useraddr & 1) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "storing cpu address to %lx", useraddr);
+out:
+ return 0;
+}
+
+static int handle_skey(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.instruction_storage_key++;
+ vcpu->arch.sie_block->gpsw.addr -= 4;
+ VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
+ return 0;
+}
+
+static int handle_stsch(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.instruction_stsch++;
+ VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
+ /* condition code 3 */
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+ return 0;
+}
+
+static int handle_chsc(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.instruction_chsc++;
+ VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
+ /* condition code 3 */
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+ return 0;
+}
+
+static unsigned int kvm_stfl(void)
+{
+ asm volatile(
+ " .insn s,0xb2b10000,0(0)\n" /* stfl */
+ "0:\n"
+ EX_TABLE(0b, 0b));
+ return S390_lowcore.stfl_fac_list;
+}
+
+static int handle_stfl(struct kvm_vcpu *vcpu)
+{
+ unsigned int facility_list = kvm_stfl();
+ int rc;
+
+ vcpu->stat.instruction_stfl++;
+ facility_list &= ~(1UL<<24); /* no stfle */
+
+ rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+ &facility_list, sizeof(facility_list));
+ if (rc == -EFAULT)
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ else
+ VCPU_EVENT(vcpu, 5, "store facility list value %x",
+ facility_list);
+ return 0;
+}
+
+static int handle_stidp(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ int rc;
+
+ vcpu->stat.instruction_stidp++;
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ if (operand2 & 7) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+out:
+ return 0;
+}
+
+static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
+{
+ struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ int cpus = 0;
+ int n;
+
+ spin_lock_bh(&fi->lock);
+ for (n = 0; n < KVM_MAX_VCPUS; n++)
+ if (fi->local_int[n])
+ cpus++;
+ spin_unlock_bh(&fi->lock);
+
+ /* deal with other level 3 hypervisors */
+ if (stsi(mem, 3, 2, 2) == -ENOSYS)
+ mem->count = 0;
+ if (mem->count < 8)
+ mem->count++;
+ for (n = mem->count - 1; n > 0 ; n--)
+ memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
+
+ mem->vm[0].cpus_total = cpus;
+ mem->vm[0].cpus_configured = cpus;
+ mem->vm[0].cpus_standby = 0;
+ mem->vm[0].cpus_reserved = 0;
+ mem->vm[0].caf = 1000;
+ memcpy(mem->vm[0].name, "KVMguest", 8);
+ ASCEBC(mem->vm[0].name, 8);
+ memcpy(mem->vm[0].cpi, "KVM/Linux ", 16);
+ ASCEBC(mem->vm[0].cpi, 16);
+}
+
+static int handle_stsi(struct kvm_vcpu *vcpu)
+{
+ int fc = (vcpu->arch.guest_gprs[0] & 0xf0000000) >> 28;
+ int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
+ int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ unsigned long mem;
+
+ vcpu->stat.instruction_stsi++;
+ VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ if (operand2 & 0xfff && fc > 0)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ switch (fc) {
+ case 0:
+ vcpu->arch.guest_gprs[0] = 3 << 28;
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ return 0;
+ case 1: /* same handling for 1 and 2 */
+ case 2:
+ mem = get_zeroed_page(GFP_KERNEL);
+ if (!mem)
+ goto out_fail;
+ if (stsi((void *) mem, fc, sel1, sel2) == -ENOSYS)
+ goto out_mem;
+ break;
+ case 3:
+ if (sel1 != 2 || sel2 != 2)
+ goto out_fail;
+ mem = get_zeroed_page(GFP_KERNEL);
+ if (!mem)
+ goto out_fail;
+ handle_stsi_3_2_2(vcpu, (void *) mem);
+ break;
+ default:
+ goto out_fail;
+ }
+
+ if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out_mem;
+ }
+ free_page(mem);
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.guest_gprs[0] = 0;
+ return 0;
+out_mem:
+ free_page(mem);
+out_fail:
+ /* condition code 3 */
+ vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
+ return 0;
+}
+
+static intercept_handler_t priv_handlers[256] = {
+ [0x02] = handle_stidp,
+ [0x10] = handle_set_prefix,
+ [0x11] = handle_store_prefix,
+ [0x12] = handle_store_cpu_address,
+ [0x29] = handle_skey,
+ [0x2a] = handle_skey,
+ [0x2b] = handle_skey,
+ [0x34] = handle_stsch,
+ [0x5f] = handle_chsc,
+ [0x7d] = handle_stsi,
+ [0xb1] = handle_stfl,
+};
+
+int kvm_s390_handle_priv(struct kvm_vcpu *vcpu)
+{
+ intercept_handler_t handler;
+
+ handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+ if (handler)
+ return handler(vcpu);
+ return -ENOTSUPP;
+}
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
new file mode 100644
index 00000000000..934fd6a885f
--- /dev/null
+++ b/arch/s390/kvm/sie64a.S
@@ -0,0 +1,47 @@
+/*
+ * sie64a.S - low level sie call
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
+ */
+
+#include <linux/errno.h>
+#include <asm/asm-offsets.h>
+
+SP_R5 = 5 * 8 # offset into stackframe
+SP_R6 = 6 * 8
+
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+ .globl sie64a
+sie64a:
+ lgr %r5,%r3
+ stmg %r5,%r14,SP_R5(%r15) # save register on entry
+ lgr %r14,%r2 # pointer to sie control block
+ lmg %r0,%r13,0(%r3) # load guest gprs 0-13
+sie_inst:
+ sie 0(%r14)
+ lg %r14,SP_R5(%r15)
+ stmg %r0,%r13,0(%r14) # save guest gprs 0-13
+ lghi %r2,0
+ lmg %r6,%r14,SP_R6(%r15)
+ br %r14
+
+sie_err:
+ lg %r14,SP_R5(%r15)
+ stmg %r0,%r13,0(%r14) # save guest gprs 0-13
+ lghi %r2,-EFAULT
+ lmg %r6,%r14,SP_R6(%r15)
+ br %r14
+
+ .section __ex_table,"a"
+ .quad sie_inst,sie_err
+ .previous
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
new file mode 100644
index 00000000000..0a236acfb5f
--- /dev/null
+++ b/arch/s390/kvm/sigp.c
@@ -0,0 +1,288 @@
+/*
+ * sigp.c - handlinge interprocessor communication
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Author(s): Carsten Otte <cotte@de.ibm.com>
+ * Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+
+/* sigp order codes */
+#define SIGP_SENSE 0x01
+#define SIGP_EXTERNAL_CALL 0x02
+#define SIGP_EMERGENCY 0x03
+#define SIGP_START 0x04
+#define SIGP_STOP 0x05
+#define SIGP_RESTART 0x06
+#define SIGP_STOP_STORE_STATUS 0x09
+#define SIGP_INITIAL_CPU_RESET 0x0b
+#define SIGP_CPU_RESET 0x0c
+#define SIGP_SET_PREFIX 0x0d
+#define SIGP_STORE_STATUS_ADDR 0x0e
+#define SIGP_SET_ARCH 0x12
+
+/* cpu status bits */
+#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL
+#define SIGP_STAT_INCORRECT_STATE 0x00000200UL
+#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
+#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL
+#define SIGP_STAT_STOPPED 0x00000040UL
+#define SIGP_STAT_OPERATOR_INTERV 0x00000020UL
+#define SIGP_STAT_CHECK_STOP 0x00000010UL
+#define SIGP_STAT_INOPERATIVE 0x00000004UL
+#define SIGP_STAT_INVALID_ORDER 0x00000002UL
+#define SIGP_STAT_RECEIVER_CHECK 0x00000001UL
+
+
+static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, u64 *reg)
+{
+ struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ int rc;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ spin_lock_bh(&fi->lock);
+ if (fi->local_int[cpu_addr] == NULL)
+ rc = 3; /* not operational */
+ else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+ & CPUSTAT_RUNNING) {
+ *reg &= 0xffffffff00000000UL;
+ rc = 1; /* status stored */
+ } else {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STAT_STOPPED;
+ rc = 1; /* status stored */
+ }
+ spin_unlock_bh(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
+ return rc;
+}
+
+static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+ struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct local_interrupt *li;
+ struct interrupt_info *inti;
+ int rc;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ inti->type = KVM_S390_INT_EMERGENCY;
+
+ spin_lock_bh(&fi->lock);
+ li = fi->local_int[cpu_addr];
+ if (li == NULL) {
+ rc = 3; /* not operational */
+ kfree(inti);
+ goto unlock;
+ }
+ spin_lock_bh(&li->lock);
+ list_add_tail(&inti->list, &li->list);
+ atomic_set(&li->active, 1);
+ atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&li->wq);
+ spin_unlock_bh(&li->lock);
+ rc = 0; /* order accepted */
+unlock:
+ spin_unlock_bh(&fi->lock);
+ VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
+ return rc;
+}
+
+static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int store)
+{
+ struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct local_interrupt *li;
+ struct interrupt_info *inti;
+ int rc;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return -ENOMEM;
+
+ inti->type = KVM_S390_SIGP_STOP;
+
+ spin_lock_bh(&fi->lock);
+ li = fi->local_int[cpu_addr];
+ if (li == NULL) {
+ rc = 3; /* not operational */
+ kfree(inti);
+ goto unlock;
+ }
+ spin_lock_bh(&li->lock);
+ list_add_tail(&inti->list, &li->list);
+ atomic_set(&li->active, 1);
+ atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+ if (store)
+ li->action_bits |= ACTION_STORE_ON_STOP;
+ li->action_bits |= ACTION_STOP_ON_STOP;
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&li->wq);
+ spin_unlock_bh(&li->lock);
+ rc = 0; /* order accepted */
+unlock:
+ spin_unlock_bh(&fi->lock);
+ VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
+ return rc;
+}
+
+static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
+{
+ int rc;
+
+ switch (parameter & 0xff) {
+ case 0:
+ printk(KERN_WARNING "kvm: request to switch to ESA/390 mode"
+ " not supported");
+ rc = 3; /* not operational */
+ break;
+ case 1:
+ case 2:
+ rc = 0; /* order accepted */
+ break;
+ default:
+ rc = -ENOTSUPP;
+ }
+ return rc;
+}
+
+static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
+ u64 *reg)
+{
+ struct float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ struct local_interrupt *li;
+ struct interrupt_info *inti;
+ int rc;
+ u8 tmp;
+
+ /* make sure that the new value is valid memory */
+ address = address & 0x7fffe000u;
+ if ((copy_from_guest(vcpu, &tmp,
+ (u64) (address + vcpu->kvm->arch.guest_origin) , 1)) ||
+ (copy_from_guest(vcpu, &tmp, (u64) (address +
+ vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) {
+ *reg |= SIGP_STAT_INVALID_PARAMETER;
+ return 1; /* invalid parameter */
+ }
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return 2; /* busy */
+
+ spin_lock_bh(&fi->lock);
+ li = fi->local_int[cpu_addr];
+
+ if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) {
+ rc = 1; /* incorrect state */
+ *reg &= SIGP_STAT_INCORRECT_STATE;
+ kfree(inti);
+ goto out_fi;
+ }
+
+ spin_lock_bh(&li->lock);
+ /* cpu must be in stopped state */
+ if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+ rc = 1; /* incorrect state */
+ *reg &= SIGP_STAT_INCORRECT_STATE;
+ kfree(inti);
+ goto out_li;
+ }
+
+ inti->type = KVM_S390_SIGP_SET_PREFIX;
+ inti->prefix.address = address;
+
+ list_add_tail(&inti->list, &li->list);
+ atomic_set(&li->active, 1);
+ if (waitqueue_active(&li->wq))
+ wake_up_interruptible(&li->wq);
+ rc = 0; /* order accepted */
+
+ VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
+out_li:
+ spin_unlock_bh(&li->lock);
+out_fi:
+ spin_unlock_bh(&fi->lock);
+ return rc;
+}
+
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
+{
+ int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+ int r3 = vcpu->arch.sie_block->ipa & 0x000f;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u32 parameter;
+ u16 cpu_addr = vcpu->arch.guest_gprs[r3];
+ u8 order_code;
+ int rc;
+
+ order_code = disp2;
+ if (base2)
+ order_code += vcpu->arch.guest_gprs[base2];
+
+ if (r1 % 2)
+ parameter = vcpu->arch.guest_gprs[r1];
+ else
+ parameter = vcpu->arch.guest_gprs[r1 + 1];
+
+ switch (order_code) {
+ case SIGP_SENSE:
+ vcpu->stat.instruction_sigp_sense++;
+ rc = __sigp_sense(vcpu, cpu_addr,
+ &vcpu->arch.guest_gprs[r1]);
+ break;
+ case SIGP_EMERGENCY:
+ vcpu->stat.instruction_sigp_emergency++;
+ rc = __sigp_emergency(vcpu, cpu_addr);
+ break;
+ case SIGP_STOP:
+ vcpu->stat.instruction_sigp_stop++;
+ rc = __sigp_stop(vcpu, cpu_addr, 0);
+ break;
+ case SIGP_STOP_STORE_STATUS:
+ vcpu->stat.instruction_sigp_stop++;
+ rc = __sigp_stop(vcpu, cpu_addr, 1);
+ break;
+ case SIGP_SET_ARCH:
+ vcpu->stat.instruction_sigp_arch++;
+ rc = __sigp_set_arch(vcpu, parameter);
+ break;
+ case SIGP_SET_PREFIX:
+ vcpu->stat.instruction_sigp_prefix++;
+ rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
+ &vcpu->arch.guest_gprs[r1]);
+ break;
+ case SIGP_RESTART:
+ vcpu->stat.instruction_sigp_restart++;
+ /* user space must know about restart */
+ default:
+ return -ENOTSUPP;
+ }
+
+ if (rc < 0)
+ return rc;
+
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.sie_block->gpsw.mask |= (rc & 3ul) << 44;
+ return 0;
+}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index fd072013f88..5c1aea97cd1 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -30,11 +30,27 @@
#define TABLES_PER_PAGE 4
#define FRAG_MASK 15UL
#define SECOND_HALVES 10UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+ memset(table + 256, 0, PAGE_SIZE/4);
+ clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
+ memset(table + 768, 0, PAGE_SIZE/4);
+}
+
#else
#define ALLOC_ORDER 2
#define TABLES_PER_PAGE 2
#define FRAG_MASK 3UL
#define SECOND_HALVES 2UL
+
+void clear_table_pgstes(unsigned long *table)
+{
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
+ memset(table + 256, 0, PAGE_SIZE/2);
+}
+
#endif
unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
@@ -153,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
unsigned long *table;
unsigned long bits;
- bits = mm->context.noexec ? 3UL : 1UL;
+ bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
spin_lock(&mm->page_table_lock);
page = NULL;
if (!list_empty(&mm->context.pgtable_list)) {
@@ -170,7 +186,10 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
pgtable_page_ctor(page);
page->flags &= ~FRAG_MASK;
table = (unsigned long *) page_to_phys(page);
- clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+ if (mm->context.pgstes)
+ clear_table_pgstes(table);
+ else
+ clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
spin_lock(&mm->page_table_lock);
list_add(&page->lru, &mm->context.pgtable_list);
}
@@ -191,7 +210,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
struct page *page;
unsigned long bits;
- bits = mm->context.noexec ? 3UL : 1UL;
+ bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
spin_lock(&mm->page_table_lock);
@@ -228,3 +247,43 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
mm->context.noexec = 0;
update_mm(mm, tsk);
}
+
+/*
+ * switch on pgstes for its userspace process (for kvm)
+ */
+int s390_enable_sie(void)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm;
+ int rc;
+
+ task_lock(tsk);
+
+ rc = 0;
+ if (tsk->mm->context.pgstes)
+ goto unlock;
+
+ rc = -EINVAL;
+ if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
+ tsk->mm != tsk->active_mm || tsk->mm->ioctx_list)
+ goto unlock;
+
+ tsk->mm->context.pgstes = 1; /* dirty little tricks .. */
+ mm = dup_mm(tsk);
+ tsk->mm->context.pgstes = 0;
+
+ rc = -ENOMEM;
+ if (!mm)
+ goto unlock;
+ mmput(tsk->mm);
+ tsk->mm = tsk->active_mm = mm;
+ preempt_disable();
+ update_mm(mm, tsk);
+ cpu_set(smp_processor_id(), mm->cpu_vm_mask);
+ preempt_enable();
+ rc = 0;
+unlock:
+ task_unlock(tsk);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(s390_enable_sie);
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 53dde060736..d7df26bd1e5 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -307,15 +307,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- init_page_count(page);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
int arch_add_memory(int nid, u64 start, u64 size)
{
pg_data_t *pgdat;
diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process.c
index 70c0dd22491..e7f35198ae3 100644
--- a/arch/sparc/kernel/process.c
+++ b/arch/sparc/kernel/process.c
@@ -357,8 +357,6 @@ void flush_thread(void)
{
current_thread_info()->w_saved = 0;
- /* No new signal delivery by default */
- current->thread.new_signal = 0;
#ifndef CONFIG_SMP
if(last_task_used_math == current) {
#else
diff --git a/arch/sparc/kernel/signal.c b/arch/sparc/kernel/signal.c
index 3e849e8e348..3c312290c3c 100644
--- a/arch/sparc/kernel/signal.c
+++ b/arch/sparc/kernel/signal.c
@@ -1,5 +1,4 @@
-/* $Id: signal.c,v 1.110 2002/02/08 03:57:14 davem Exp $
- * linux/arch/sparc/kernel/signal.c
+/* linux/arch/sparc/kernel/signal.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
@@ -32,37 +31,7 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
void *fpqueue, unsigned long *fpqdepth);
extern void fpload(unsigned long *fpregs, unsigned long *fsr);
-/* Signal frames: the original one (compatible with SunOS):
- *
- * Set up a signal frame... Make the stack look the way SunOS
- * expects it to look which is basically:
- *
- * ---------------------------------- <-- %sp at signal time
- * Struct sigcontext
- * Signal address
- * Ptr to sigcontext area above
- * Signal code
- * The signal number itself
- * One register window
- * ---------------------------------- <-- New %sp
- */
-struct signal_sframe {
- struct reg_window sig_window;
- int sig_num;
- int sig_code;
- struct sigcontext __user *sig_scptr;
- int sig_address;
- struct sigcontext sig_context;
- unsigned int extramask[_NSIG_WORDS - 1];
-};
-
-/*
- * And the new one, intended to be used for Linux applications only
- * (we have enough in there to work with clone).
- * All the interesting bits are in the info field.
- */
-
-struct new_signal_frame {
+struct signal_frame {
struct sparc_stackf ss;
__siginfo_t info;
__siginfo_fpu_t __user *fpu_save;
@@ -85,8 +54,7 @@ struct rt_signal_frame {
};
/* Align macros */
-#define SF_ALIGNEDSZ (((sizeof(struct signal_sframe) + 7) & (~7)))
-#define NF_ALIGNEDSZ (((sizeof(struct new_signal_frame) + 7) & (~7)))
+#define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7)))
#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7)))
static int _sigpause_common(old_sigset_t set)
@@ -141,15 +109,20 @@ restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
return err;
}
-static inline void do_new_sigreturn (struct pt_regs *regs)
+asmlinkage void do_sigreturn(struct pt_regs *regs)
{
- struct new_signal_frame __user *sf;
+ struct signal_frame __user *sf;
unsigned long up_psr, pc, npc;
sigset_t set;
__siginfo_fpu_t __user *fpu_save;
int err;
- sf = (struct new_signal_frame __user *) regs->u_regs[UREG_FP];
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+ synchronize_user_stack();
+
+ sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
@@ -198,73 +171,6 @@ segv_and_exit:
force_sig(SIGSEGV, current);
}
-asmlinkage void do_sigreturn(struct pt_regs *regs)
-{
- struct sigcontext __user *scptr;
- unsigned long pc, npc, psr;
- sigset_t set;
- int err;
-
- /* Always make any pending restarted system calls return -EINTR */
- current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
- synchronize_user_stack();
-
- if (current->thread.new_signal) {
- do_new_sigreturn(regs);
- return;
- }
-
- scptr = (struct sigcontext __user *) regs->u_regs[UREG_I0];
-
- /* Check sanity of the user arg. */
- if (!access_ok(VERIFY_READ, scptr, sizeof(struct sigcontext)) ||
- (((unsigned long) scptr) & 3))
- goto segv_and_exit;
-
- err = __get_user(pc, &scptr->sigc_pc);
- err |= __get_user(npc, &scptr->sigc_npc);
-
- if ((pc | npc) & 3)
- goto segv_and_exit;
-
- /* This is pretty much atomic, no amount locking would prevent
- * the races which exist anyways.
- */
- err |= __get_user(set.sig[0], &scptr->sigc_mask);
- /* Note that scptr + 1 points to extramask */
- err |= __copy_from_user(&set.sig[1], scptr + 1,
- (_NSIG_WORDS - 1) * sizeof(unsigned int));
-
- if (err)
- goto segv_and_exit;
-
- sigdelsetmask(&set, ~_BLOCKABLE);
- spin_lock_irq(&current->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
-
- regs->pc = pc;
- regs->npc = npc;
-
- err = __get_user(regs->u_regs[UREG_FP], &scptr->sigc_sp);
- err |= __get_user(regs->u_regs[UREG_I0], &scptr->sigc_o0);
- err |= __get_user(regs->u_regs[UREG_G1], &scptr->sigc_g1);
-
- /* User can only change condition codes in %psr. */
- err |= __get_user(psr, &scptr->sigc_psr);
- if (err)
- goto segv_and_exit;
-
- regs->psr &= ~(PSR_ICC);
- regs->psr |= (psr & PSR_ICC);
- return;
-
-segv_and_exit:
- force_sig(SIGSEGV, current);
-}
-
asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
{
struct rt_signal_frame __user *sf;
@@ -351,128 +257,6 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re
return (void __user *)(sp - framesize);
}
-static inline void
-setup_frame(struct sigaction *sa, struct pt_regs *regs, int signr, sigset_t *oldset, siginfo_t *info)
-{
- struct signal_sframe __user *sframep;
- struct sigcontext __user *sc;
- int window = 0, err;
- unsigned long pc = regs->pc;
- unsigned long npc = regs->npc;
- struct thread_info *tp = current_thread_info();
- void __user *sig_address;
- int sig_code;
-
- synchronize_user_stack();
- sframep = (struct signal_sframe __user *)
- get_sigframe(sa, regs, SF_ALIGNEDSZ);
- if (invalid_frame_pointer(sframep, sizeof(*sframep))){
- /* Don't change signal code and address, so that
- * post mortem debuggers can have a look.
- */
- goto sigill_and_return;
- }
-
- sc = &sframep->sig_context;
-
- /* We've already made sure frame pointer isn't in kernel space... */
- err = __put_user((sas_ss_flags(regs->u_regs[UREG_FP]) == SS_ONSTACK),
- &sc->sigc_onstack);
- err |= __put_user(oldset->sig[0], &sc->sigc_mask);
- err |= __copy_to_user(sframep->extramask, &oldset->sig[1],
- (_NSIG_WORDS - 1) * sizeof(unsigned int));
- err |= __put_user(regs->u_regs[UREG_FP], &sc->sigc_sp);
- err |= __put_user(pc, &sc->sigc_pc);
- err |= __put_user(npc, &sc->sigc_npc);
- err |= __put_user(regs->psr, &sc->sigc_psr);
- err |= __put_user(regs->u_regs[UREG_G1], &sc->sigc_g1);
- err |= __put_user(regs->u_regs[UREG_I0], &sc->sigc_o0);
- err |= __put_user(tp->w_saved, &sc->sigc_oswins);
- if (tp->w_saved)
- for (window = 0; window < tp->w_saved; window++) {
- put_user((char *)tp->rwbuf_stkptrs[window],
- &sc->sigc_spbuf[window]);
- err |= __copy_to_user(&sc->sigc_wbuf[window],
- &tp->reg_window[window],
- sizeof(struct reg_window));
- }
- else
- err |= __copy_to_user(sframep, (char *) regs->u_regs[UREG_FP],
- sizeof(struct reg_window));
-
- tp->w_saved = 0; /* So process is allowed to execute. */
-
- err |= __put_user(signr, &sframep->sig_num);
- sig_address = NULL;
- sig_code = 0;
- if (SI_FROMKERNEL (info) && (info->si_code & __SI_MASK) == __SI_FAULT) {
- sig_address = info->si_addr;
- switch (signr) {
- case SIGSEGV:
- switch (info->si_code) {
- case SEGV_MAPERR: sig_code = SUBSIG_NOMAPPING; break;
- default: sig_code = SUBSIG_PROTECTION; break;
- }
- break;
- case SIGILL:
- switch (info->si_code) {
- case ILL_ILLOPC: sig_code = SUBSIG_ILLINST; break;
- case ILL_PRVOPC: sig_code = SUBSIG_PRIVINST; break;
- case ILL_ILLTRP: sig_code = SUBSIG_BADTRAP(info->si_trapno); break;
- default: sig_code = SUBSIG_STACK; break;
- }
- break;
- case SIGFPE:
- switch (info->si_code) {
- case FPE_INTDIV: sig_code = SUBSIG_IDIVZERO; break;
- case FPE_INTOVF: sig_code = SUBSIG_FPINTOVFL; break;
- case FPE_FLTDIV: sig_code = SUBSIG_FPDIVZERO; break;
- case FPE_FLTOVF: sig_code = SUBSIG_FPOVFLOW; break;
- case FPE_FLTUND: sig_code = SUBSIG_FPUNFLOW; break;
- case FPE_FLTRES: sig_code = SUBSIG_FPINEXACT; break;
- case FPE_FLTINV: sig_code = SUBSIG_FPOPERROR; break;
- default: sig_code = SUBSIG_FPERROR; break;
- }
- break;
- case SIGBUS:
- switch (info->si_code) {
- case BUS_ADRALN: sig_code = SUBSIG_ALIGNMENT; break;
- case BUS_ADRERR: sig_code = SUBSIG_MISCERROR; break;
- default: sig_code = SUBSIG_BUSTIMEOUT; break;
- }
- break;
- case SIGEMT:
- switch (info->si_code) {
- case EMT_TAGOVF: sig_code = SUBSIG_TAG; break;
- }
- break;
- case SIGSYS:
- if (info->si_code == (__SI_FAULT|0x100)) {
- sig_code = info->si_trapno;
- break;
- }
- default:
- sig_address = NULL;
- }
- }
- err |= __put_user((unsigned long)sig_address, &sframep->sig_address);
- err |= __put_user(sig_code, &sframep->sig_code);
- err |= __put_user(sc, &sframep->sig_scptr);
- if (err)
- goto sigsegv;
-
- regs->u_regs[UREG_FP] = (unsigned long) sframep;
- regs->pc = (unsigned long) sa->sa_handler;
- regs->npc = (regs->pc + 4);
- return;
-
-sigill_and_return:
- do_exit(SIGILL);
-sigsegv:
- force_sigsegv(signr, current);
-}
-
-
static inline int
save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
{
@@ -508,21 +292,20 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
return err;
}
-static inline void
-new_setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
- int signo, sigset_t *oldset)
+static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs,
+ int signo, sigset_t *oldset)
{
- struct new_signal_frame __user *sf;
+ struct signal_frame __user *sf;
int sigframe_size, err;
/* 1. Make sure everything is clean */
synchronize_user_stack();
- sigframe_size = NF_ALIGNEDSZ;
+ sigframe_size = SF_ALIGNEDSZ;
if (!used_math())
sigframe_size -= sizeof(__siginfo_fpu_t);
- sf = (struct new_signal_frame __user *)
+ sf = (struct signal_frame __user *)
get_sigframe(&ka->sa, regs, sigframe_size);
if (invalid_frame_pointer(sf, sigframe_size))
@@ -586,9 +369,8 @@ sigsegv:
force_sigsegv(signo, current);
}
-static inline void
-new_setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
- int signo, sigset_t *oldset, siginfo_t *info)
+static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
+ int signo, sigset_t *oldset, siginfo_t *info)
{
struct rt_signal_frame __user *sf;
int sigframe_size;
@@ -674,11 +456,9 @@ handle_signal(unsigned long signr, struct k_sigaction *ka,
siginfo_t *info, sigset_t *oldset, struct pt_regs *regs)
{
if (ka->sa.sa_flags & SA_SIGINFO)
- new_setup_rt_frame(ka, regs, signr, oldset, info);
- else if (current->thread.new_signal)
- new_setup_frame(ka, regs, signr, oldset);
+ setup_rt_frame(ka, regs, signr, oldset, info);
else
- setup_frame(&ka->sa, regs, signr, oldset, info);
+ setup_frame(ka, regs, signr, oldset);
spin_lock_irq(&current->sighand->siglock);
sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc.c
index 42bf09db9a8..f188b5dc9fd 100644
--- a/arch/sparc/kernel/sys_sparc.c
+++ b/arch/sparc/kernel/sys_sparc.c
@@ -1,5 +1,4 @@
-/* $Id: sys_sparc.c,v 1.70 2001/04/14 01:12:02 davem Exp $
- * linux/arch/sparc/kernel/sys_sparc.c
+/* linux/arch/sparc/kernel/sys_sparc.c
*
* This file contains various random system calls that
* have a non-standard calling sequence on the Linux/sparc
@@ -395,10 +394,8 @@ sparc_sigaction (int sig, const struct old_sigaction __user *act,
struct k_sigaction new_ka, old_ka;
int ret;
- if (sig < 0) {
- current->thread.new_signal = 1;
- sig = -sig;
- }
+ WARN_ON_ONCE(sig >= 0);
+ sig = -sig;
if (act) {
unsigned long mask;
@@ -446,11 +443,6 @@ sys_rt_sigaction(int sig,
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
- /* All tasks which use RT signals (effectively) use
- * new style signals.
- */
- current->thread.new_signal = 1;
-
if (act) {
new_ka.ka_restorer = restorer;
if (copy_from_user(&new_ka.sa, act, sizeof(*act)))
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index 8acc5cc3862..edbe71e3fab 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -1,9 +1,5 @@
-# $Id: config.in,v 1.158 2002/01/24 22:14:44 davem Exp $
-# For a description of the syntax of this configuration file,
-# see the Configure script.
-#
-
-mainmenu "Linux/UltraSPARC Kernel Configuration"
+# sparc64 configuration
+mainmenu "Linux Kernel Configuration for 64-bit SPARC"
config SPARC
bool
@@ -17,12 +13,6 @@ config SPARC64
default y
select HAVE_IDE
select HAVE_LMB
- help
- SPARC is a family of RISC microprocessors designed and marketed by
- Sun Microsystems, incorporated. This port covers the newer 64-bit
- UltraSPARC. The UltraLinux project maintains both the SPARC32 and
- SPARC64 ports; its web page is available at
- <http://www.ultralinux.org/>.
config GENERIC_TIME
bool
@@ -97,7 +87,7 @@ config SPARC64_PAGE_SIZE_8KB
help
This lets you select the page size of the kernel.
- 8KB and 64KB work quite well, since Sparc ELF sections
+ 8KB and 64KB work quite well, since SPARC ELF sections
provide for up to 64KB alignment.
Therefore, 512KB and 4MB are for expert hackers only.
@@ -138,7 +128,7 @@ config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
depends on SMP
select HOTPLUG
- ---help---
+ help
Say Y here to experiment with turning CPUs off and on. CPUs
can be controlled through /sys/devices/system/cpu/cpu#.
Say N if you want to disable CPU hotplug.
@@ -155,23 +145,16 @@ source "kernel/time/Kconfig"
config SMP
bool "Symmetric multi-processing support"
- ---help---
+ help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, say N. If you have a system with more than
one CPU, say Y.
If you say N here, the kernel will run on single and multiprocessor
machines, but will use only one CPU of a multiprocessor machine. If
- you say Y here, the kernel will run on many, but not all,
- singleprocessor machines. On a singleprocessor machine, the kernel
- will run faster if you say N here.
-
- People using multiprocessor machines who say Y here should also say
- Y to "Enhanced Real Time Clock Support", below. The "Advanced Power
- Management" code will be disabled if you say Y here.
-
- See also <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO
- available at <http://www.tldp.org/docs.html#howto>.
+ you say Y here, the kernel will run on single-processor machines.
+ On a single-processor machine, the kernel will run faster if you say
+ N here.
If you don't know what to do here, say N.
@@ -284,50 +267,19 @@ source "mm/Kconfig"
config ISA
bool
- help
- Find out whether you have ISA slots on your motherboard. ISA is the
- name of a bus system, i.e. the way the CPU talks to the other stuff
- inside your box. Other bus systems are PCI, EISA, MicroChannel
- (MCA) or VESA. ISA is an older system, now being displaced by PCI;
- newer boards don't support it. If you have ISA, say Y, otherwise N.
config ISAPNP
bool
- help
- Say Y here if you would like support for ISA Plug and Play devices.
- Some information is in <file:Documentation/isapnp.txt>.
-
- To compile this driver as a module, choose M here: the
- module will be called isapnp.
-
- If unsure, say Y.
config EISA
bool
- ---help---
- The Extended Industry Standard Architecture (EISA) bus was
- developed as an open alternative to the IBM MicroChannel bus.
-
- The EISA bus provided some of the features of the IBM MicroChannel
- bus while maintaining backward compatibility with cards made for
- the older ISA bus. The EISA bus saw limited use between 1988 and
- 1995 when it was made obsolete by the PCI bus.
-
- Say Y here if you are building a kernel for an EISA-based machine.
-
- Otherwise, say N.
config MCA
bool
- help
- MicroChannel Architecture is found in some IBM PS/2 machines and
- laptops. It is a bus system similar to PCI or ISA. See
- <file:Documentation/mca.txt> (and especially the web page given
- there) before attempting to build an MCA bus kernel.
config PCMCIA
tristate
- ---help---
+ help
Say Y here if you want to attach PCMCIA- or PC-cards to your Linux
computer. These are credit-card size devices such as network cards,
modems or hard drives often used with laptops computers. There are
@@ -369,10 +321,10 @@ config PCI
bool "PCI support"
select ARCH_SUPPORTS_MSI
help
- Find out whether you have a PCI motherboard. PCI is the name of a
- bus system, i.e. the way the CPU talks to the other stuff inside
- your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
- VESA. If you have PCI, say Y, otherwise N.
+ Find out whether your system includes a PCI bus. PCI is the name of
+ a bus system, i.e. the way the CPU talks to the other stuff inside
+ your box. If you say Y here, the kernel will include drivers and
+ infrastructure code to support PCI bus devices.
config PCI_DOMAINS
def_bool PCI
@@ -396,15 +348,8 @@ menu "Executable file formats"
source "fs/Kconfig.binfmt"
-config SPARC32_COMPAT
- bool "Kernel support for Linux/Sparc 32bit binary compatibility"
- help
- This allows you to run 32-bit binaries on your Ultra.
- Everybody wants this; say Y.
-
config COMPAT
bool
- depends on SPARC32_COMPAT
default y
select COMPAT_BINFMT_ELF
@@ -421,8 +366,8 @@ config SCHED_SMT
default y
help
SMT scheduler support improves the CPU scheduler's decision making
- when dealing with UltraSPARC cpus at a cost of slightly increased
- overhead in some places. If unsure say N here.
+ when dealing with SPARC cpus at a cost of slightly increased overhead
+ in some places. If unsure say N here.
config SCHED_MC
bool "Multi-core scheduler support"
diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig
index 92f79680f70..aff93c9d13f 100644
--- a/arch/sparc64/defconfig
+++ b/arch/sparc64/defconfig
@@ -1,7 +1,7 @@
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.25-numa
-# Wed Apr 23 04:49:08 2008
+# Linux kernel version: 2.6.25
+# Sat Apr 26 03:11:06 2008
#
CONFIG_SPARC=y
CONFIG_SPARC64=y
@@ -152,7 +152,9 @@ CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_HUGETLB_PAGE_SIZE_4MB=y
# CONFIG_HUGETLB_PAGE_SIZE_512K is not set
# CONFIG_HUGETLB_PAGE_SIZE_64K is not set
-# CONFIG_NUMA is not set
+CONFIG_NUMA=y
+CONFIG_NODES_SHIFT=4
+CONFIG_NODES_SPAN_OTHER_NODES=y
CONFIG_ARCH_POPULATES_NODE_MAP=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
CONFIG_ARCH_SPARSEMEM_ENABLE=y
@@ -162,12 +164,14 @@ CONFIG_SELECT_MEMORY_MODEL=y
# CONFIG_DISCONTIGMEM_MANUAL is not set
CONFIG_SPARSEMEM_MANUAL=y
CONFIG_SPARSEMEM=y
+CONFIG_NEED_MULTIPLE_NODES=y
CONFIG_HAVE_MEMORY_PRESENT=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPARSEMEM_EXTREME=y
CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
CONFIG_SPARSEMEM_VMEMMAP=y
CONFIG_SPLIT_PTLOCK_CPUS=4
+CONFIG_MIGRATION=y
CONFIG_RESOURCES_64BIT=y
CONFIG_ZONE_DMA_FLAG=0
CONFIG_NR_QUICK=1
@@ -191,7 +195,6 @@ CONFIG_SUN_OPENPROMFS=m
CONFIG_BINFMT_ELF=y
CONFIG_COMPAT_BINFMT_ELF=y
CONFIG_BINFMT_MISC=m
-CONFIG_SPARC32_COMPAT=y
CONFIG_COMPAT=y
CONFIG_SYSVIPC_COMPAT=y
CONFIG_SCHED_SMT=y
@@ -746,13 +749,7 @@ CONFIG_DEVPORT=y
CONFIG_I2C=y
CONFIG_I2C_BOARDINFO=y
# CONFIG_I2C_CHARDEV is not set
-
-#
-# I2C Algorithms
-#
CONFIG_I2C_ALGOBIT=y
-# CONFIG_I2C_ALGOPCF is not set
-# CONFIG_I2C_ALGOPCA is not set
#
# I2C Hardware Bus support
@@ -780,6 +777,7 @@ CONFIG_I2C_ALGOBIT=y
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set
# CONFIG_I2C_VOODOO3 is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
#
# Miscellaneous I2C Chip support
@@ -1026,6 +1024,7 @@ CONFIG_SND_ALI5451=m
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AW2 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CA0106 is not set
@@ -1097,10 +1096,6 @@ CONFIG_SND_SUN_CS4231=m
# CONFIG_SND_SOC is not set
#
-# SoC Audio support for SuperH
-#
-
-#
# ALSA SoC audio for Freescale SOCs
#
diff --git a/arch/sparc64/kernel/Makefile b/arch/sparc64/kernel/Makefile
index 63c6ae0dd27..2bd0340b743 100644
--- a/arch/sparc64/kernel/Makefile
+++ b/arch/sparc64/kernel/Makefile
@@ -15,17 +15,17 @@ obj-y := process.o setup.o cpu.o idprom.o \
visemul.o prom.o of_device.o hvapi.o sstate.o mdesc.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_PCI) += ebus.o isa.o pci_common.o \
+obj-$(CONFIG_PCI) += ebus.o pci_common.o \
pci_psycho.o pci_sabre.o pci_schizo.o \
pci_sun4v.o pci_sun4v_asm.o pci_fire.o
obj-$(CONFIG_PCI_MSI) += pci_msi.o
obj-$(CONFIG_SMP) += smp.o trampoline.o hvtramp.o
-obj-$(CONFIG_SPARC32_COMPAT) += sys32.o sys_sparc32.o signal32.o
+obj-$(CONFIG_COMPAT) += sys32.o sys_sparc32.o signal32.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_US3_FREQ) += us3_cpufreq.o
obj-$(CONFIG_US2E_FREQ) += us2e_cpufreq.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_SUN_LDOMS) += ldc.o vio.o viohs.o ds.o
obj-$(CONFIG_AUDIT) += audit.o
-obj-$(CONFIG_AUDIT)$(CONFIG_SPARC32_COMPAT) += compat_audit.o
+obj-$(CONFIG_AUDIT)$(CONFIG_COMPAT) += compat_audit.o
obj-y += $(obj-yy)
diff --git a/arch/sparc64/kernel/audit.c b/arch/sparc64/kernel/audit.c
index 24d7f4b4178..8fff0ac63d5 100644
--- a/arch/sparc64/kernel/audit.c
+++ b/arch/sparc64/kernel/audit.c
@@ -30,7 +30,7 @@ static unsigned signal_class[] = {
int audit_classify_arch(int arch)
{
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
if (arch == AUDIT_ARCH_SPARC)
return 1;
#endif
@@ -39,7 +39,7 @@ int audit_classify_arch(int arch)
int audit_classify_syscall(int abi, unsigned syscall)
{
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
extern int sparc32_classify_syscall(unsigned);
if (abi == AUDIT_ARCH_SPARC)
return sparc32_classify_syscall(syscall);
@@ -60,7 +60,7 @@ int audit_classify_syscall(int abi, unsigned syscall)
static int __init audit_classes_init(void)
{
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
extern __u32 sparc32_dir_class[];
extern __u32 sparc32_write_class[];
extern __u32 sparc32_read_class[];
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index eb88bd6e674..b441a26b73b 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -1,6 +1,6 @@
/* irq.c: UltraSparc IRQ handling/init/registry.
*
- * Copyright (C) 1997, 2007 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 1997, 2007, 2008 David S. Miller (davem@davemloft.net)
* Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be)
* Copyright (C) 1998 Jakub Jelinek (jj@ultra.linux.cz)
*/
@@ -308,6 +308,7 @@ static void sun4u_irq_enable(unsigned int virt_irq)
IMAP_AID_SAFARI | IMAP_NID_SAFARI);
val |= tid | IMAP_VALID;
upa_writeq(val, imap);
+ upa_writeq(ICLR_IDLE, data->iclr);
}
}
diff --git a/arch/sparc64/kernel/isa.c b/arch/sparc64/kernel/isa.c
deleted file mode 100644
index a2af5ed784c..00000000000
--- a/arch/sparc64/kernel/isa.c
+++ /dev/null
@@ -1,191 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <asm/oplib.h>
-#include <asm/prom.h>
-#include <asm/of_device.h>
-#include <asm/isa.h>
-
-struct sparc_isa_bridge *isa_chain;
-
-static void __init fatal_err(const char *reason)
-{
- prom_printf("ISA: fatal error, %s.\n", reason);
-}
-
-static void __init report_dev(struct sparc_isa_device *isa_dev, int child)
-{
- if (child)
- printk(" (%s)", isa_dev->prom_node->name);
- else
- printk(" [%s", isa_dev->prom_node->name);
-}
-
-static void __init isa_dev_get_resource(struct sparc_isa_device *isa_dev)
-{
- struct of_device *op = of_find_device_by_node(isa_dev->prom_node);
-
- memcpy(&isa_dev->resource, &op->resource[0], sizeof(struct resource));
-}
-
-static void __init isa_dev_get_irq(struct sparc_isa_device *isa_dev)
-{
- struct of_device *op = of_find_device_by_node(isa_dev->prom_node);
-
- if (!op || !op->num_irqs) {
- isa_dev->irq = PCI_IRQ_NONE;
- } else {
- isa_dev->irq = op->irqs[0];
- }
-}
-
-static void __init isa_fill_children(struct sparc_isa_device *parent_isa_dev)
-{
- struct device_node *dp = parent_isa_dev->prom_node->child;
-
- if (!dp)
- return;
-
- printk(" ->");
- while (dp) {
- struct sparc_isa_device *isa_dev;
-
- isa_dev = kzalloc(sizeof(*isa_dev), GFP_KERNEL);
- if (!isa_dev) {
- fatal_err("cannot allocate child isa_dev");
- prom_halt();
- }
-
- /* Link it in to parent. */
- isa_dev->next = parent_isa_dev->child;
- parent_isa_dev->child = isa_dev;
-
- isa_dev->bus = parent_isa_dev->bus;
- isa_dev->prom_node = dp;
-
- isa_dev_get_resource(isa_dev);
- isa_dev_get_irq(isa_dev);
-
- report_dev(isa_dev, 1);
-
- dp = dp->sibling;
- }
-}
-
-static void __init isa_fill_devices(struct sparc_isa_bridge *isa_br)
-{
- struct device_node *dp = isa_br->prom_node->child;
-
- while (dp) {
- struct sparc_isa_device *isa_dev;
- struct dev_archdata *sd;
-
- isa_dev = kzalloc(sizeof(*isa_dev), GFP_KERNEL);
- if (!isa_dev) {
- printk(KERN_DEBUG "ISA: cannot allocate isa_dev");
- return;
- }
-
- sd = &isa_dev->ofdev.dev.archdata;
- sd->prom_node = dp;
- sd->op = &isa_dev->ofdev;
- sd->iommu = isa_br->ofdev.dev.parent->archdata.iommu;
- sd->stc = isa_br->ofdev.dev.parent->archdata.stc;
- sd->numa_node = isa_br->ofdev.dev.parent->archdata.numa_node;
-
- isa_dev->ofdev.node = dp;
- isa_dev->ofdev.dev.parent = &isa_br->ofdev.dev;
- isa_dev->ofdev.dev.bus = &isa_bus_type;
- sprintf(isa_dev->ofdev.dev.bus_id, "isa[%08x]", dp->node);
-
- /* Register with core */
- if (of_device_register(&isa_dev->ofdev) != 0) {
- printk(KERN_DEBUG "isa: device registration error for %s!\n",
- dp->path_component_name);
- kfree(isa_dev);
- goto next_sibling;
- }
-
- /* Link it in. */
- isa_dev->next = NULL;
- if (isa_br->devices == NULL) {
- isa_br->devices = isa_dev;
- } else {
- struct sparc_isa_device *tmp = isa_br->devices;
-
- while (tmp->next)
- tmp = tmp->next;
-
- tmp->next = isa_dev;
- }
-
- isa_dev->bus = isa_br;
- isa_dev->prom_node = dp;
-
- isa_dev_get_resource(isa_dev);
- isa_dev_get_irq(isa_dev);
-
- report_dev(isa_dev, 0);
-
- isa_fill_children(isa_dev);
-
- printk("]");
-
- next_sibling:
- dp = dp->sibling;
- }
-}
-
-void __init isa_init(void)
-{
- struct pci_dev *pdev;
- unsigned short vendor, device;
- int index = 0;
-
- vendor = PCI_VENDOR_ID_AL;
- device = PCI_DEVICE_ID_AL_M1533;
-
- pdev = NULL;
- while ((pdev = pci_get_device(vendor, device, pdev)) != NULL) {
- struct sparc_isa_bridge *isa_br;
- struct device_node *dp;
-
- dp = pci_device_to_OF_node(pdev);
-
- isa_br = kzalloc(sizeof(*isa_br), GFP_KERNEL);
- if (!isa_br) {
- printk(KERN_DEBUG "isa: cannot allocate sparc_isa_bridge");
- pci_dev_put(pdev);
- return;
- }
-
- isa_br->ofdev.node = dp;
- isa_br->ofdev.dev.parent = &pdev->dev;
- isa_br->ofdev.dev.bus = &isa_bus_type;
- sprintf(isa_br->ofdev.dev.bus_id, "isa%d", index);
-
- /* Register with core */
- if (of_device_register(&isa_br->ofdev) != 0) {
- printk(KERN_DEBUG "isa: device registration error for %s!\n",
- dp->path_component_name);
- kfree(isa_br);
- pci_dev_put(pdev);
- return;
- }
-
- /* Link it in. */
- isa_br->next = isa_chain;
- isa_chain = isa_br;
-
- isa_br->self = pdev;
- isa_br->index = index++;
- isa_br->prom_node = dp;
-
- printk("isa%d:", isa_br->index);
-
- isa_fill_devices(isa_br);
-
- printk("\n");
- }
-}
diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc64/kernel/of_device.c
index 9e58e8cba1c..d569f60c24b 100644
--- a/arch/sparc64/kernel/of_device.c
+++ b/arch/sparc64/kernel/of_device.c
@@ -412,12 +412,6 @@ static int __init build_one_resource(struct device_node *parent,
static int __init use_1to1_mapping(struct device_node *pp)
{
- /* If this is on the PMU bus, don't try to translate it even
- * if a ranges property exists.
- */
- if (!strcmp(pp->name, "pmu"))
- return 1;
-
/* If we have a ranges property in the parent, use it. */
if (of_find_property(pp, "ranges", NULL) != NULL)
return 0;
diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc64/kernel/pci.c
index 49f91276651..dbf2fc2f4d8 100644
--- a/arch/sparc64/kernel/pci.c
+++ b/arch/sparc64/kernel/pci.c
@@ -23,7 +23,6 @@
#include <asm/pgtable.h>
#include <asm/irq.h>
#include <asm/ebus.h>
-#include <asm/isa.h>
#include <asm/prom.h>
#include <asm/apb.h>
@@ -885,7 +884,6 @@ static int __init pcibios_init(void)
pci_scan_each_controller_bus();
- isa_init();
ebus_init();
power_init();
diff --git a/arch/sparc64/kernel/process.c b/arch/sparc64/kernel/process.c
index acf8c5250aa..05601374915 100644
--- a/arch/sparc64/kernel/process.c
+++ b/arch/sparc64/kernel/process.c
@@ -1,5 +1,4 @@
-/* $Id: process.c,v 1.131 2002/02/09 19:49:30 davem Exp $
- * arch/sparc64/kernel/process.c
+/* arch/sparc64/kernel/process.c
*
* Copyright (C) 1995, 1996 David S. Miller (davem@caip.rutgers.edu)
* Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
@@ -368,9 +367,6 @@ void flush_thread(void)
if (get_thread_current_ds() != ASI_AIUS)
set_fs(USER_DS);
-
- /* Init new signal delivery disposition. */
- clear_thread_flag(TIF_NEWSIGNALS);
}
/* It's a bit more tricky when 64-bit tasks are involved... */
@@ -595,6 +591,12 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
if (clone_flags & CLONE_SETTLS)
t->kregs->u_regs[UREG_G7] = regs->u_regs[UREG_I3];
+ /* We do not want to accidently trigger system call restart
+ * handling in the new thread. Therefore, clear out the trap
+ * type, which will make pt_regs_regs_is_syscall() return false.
+ */
+ pt_regs_clear_trap_type(t->kregs);
+
return 0;
}
diff --git a/arch/sparc64/kernel/signal.c b/arch/sparc64/kernel/signal.c
index 77a3e8592cb..f2d88d8f7a4 100644
--- a/arch/sparc64/kernel/signal.c
+++ b/arch/sparc64/kernel/signal.c
@@ -8,7 +8,7 @@
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
*/
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
#include <linux/compat.h> /* for compat_old_sigset_t */
#endif
#include <linux/sched.h>
@@ -236,9 +236,6 @@ struct rt_signal_frame {
__siginfo_fpu_t fpu_state;
};
-/* Align macros */
-#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7)))
-
static long _sigpause_common(old_sigset_t set)
{
set &= _BLOCKABLE;
@@ -400,7 +397,7 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs,
synchronize_user_stack();
save_and_clear_fpu();
- sigframe_size = RT_ALIGNEDSZ;
+ sigframe_size = sizeof(struct rt_signal_frame);
if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
sigframe_size -= sizeof(__siginfo_fpu_t);
@@ -516,11 +513,10 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
struct k_sigaction ka;
sigset_t *oldset;
siginfo_t info;
- int signr, tt;
+ int signr;
- tt = regs->magic & 0x1ff;
- if (tt == 0x110 || tt == 0x111 || tt == 0x16d) {
- regs->magic &= ~0x1ff;
+ if (pt_regs_is_syscall(regs)) {
+ pt_regs_clear_trap_type(regs);
cookie.restart_syscall = 1;
} else
cookie.restart_syscall = 0;
@@ -531,7 +527,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
else
oldset = &current->blocked;
-#ifdef CONFIG_SPARC32_COMPAT
+#ifdef CONFIG_COMPAT
if (test_thread_flag(TIF_32BIT)) {
extern void do_signal32(sigset_t *, struct pt_regs *,
struct signal_deliver_cookie *);
diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc64/kernel/signal32.c
index 43cdec64d9c..91f8d0826db 100644
--- a/arch/sparc64/kernel/signal32.c
+++ b/arch/sparc64/kernel/signal32.c
@@ -1,5 +1,4 @@
-/* $Id: signal32.c,v 1.74 2002/02/09 19:49:30 davem Exp $
- * arch/sparc64/kernel/signal32.c
+/* arch/sparc64/kernel/signal32.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
@@ -31,30 +30,6 @@
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-/* Signal frames: the original one (compatible with SunOS):
- *
- * Set up a signal frame... Make the stack look the way SunOS
- * expects it to look which is basically:
- *
- * ---------------------------------- <-- %sp at signal time
- * Struct sigcontext
- * Signal address
- * Ptr to sigcontext area above
- * Signal code
- * The signal number itself
- * One register window
- * ---------------------------------- <-- New %sp
- */
-struct signal_sframe32 {
- struct reg_window32 sig_window;
- int sig_num;
- int sig_code;
- /* struct sigcontext32 * */ u32 sig_scptr;
- int sig_address;
- struct sigcontext32 sig_context;
- unsigned int extramask[_COMPAT_NSIG_WORDS - 1];
-};
-
/* This magic should be in g_upper[0] for all upper parts
* to be valid.
*/
@@ -65,12 +40,7 @@ typedef struct {
unsigned int asi;
} siginfo_extra_v8plus_t;
-/*
- * And the new one, intended to be used for Linux applications only
- * (we have enough in there to work with clone).
- * All the interesting bits are in the info field.
- */
-struct new_signal_frame32 {
+struct signal_frame32 {
struct sparc_stackf32 ss;
__siginfo32_t info;
/* __siginfo_fpu32_t * */ u32 fpu_save;
@@ -149,8 +119,7 @@ struct rt_signal_frame32 {
};
/* Align macros */
-#define SF_ALIGNEDSZ (((sizeof(struct signal_sframe32) + 7) & (~7)))
-#define NF_ALIGNEDSZ (((sizeof(struct new_signal_frame32) + 7) & (~7)))
+#define SF_ALIGNEDSZ (((sizeof(struct signal_frame32) + 7) & (~7)))
#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame32) + 7) & (~7)))
int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
@@ -241,17 +210,22 @@ static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu
return err;
}
-void do_new_sigreturn32(struct pt_regs *regs)
+void do_sigreturn32(struct pt_regs *regs)
{
- struct new_signal_frame32 __user *sf;
+ struct signal_frame32 __user *sf;
unsigned int psr;
unsigned pc, npc, fpu_save;
sigset_t set;
unsigned seta[_COMPAT_NSIG_WORDS];
int err, i;
+ /* Always make any pending restarted system calls return -EINTR */
+ current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+ synchronize_user_stack();
+
regs->u_regs[UREG_FP] &= 0x00000000ffffffffUL;
- sf = (struct new_signal_frame32 __user *) regs->u_regs[UREG_FP];
+ sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
/* 1. Make sure we are not getting garbage from the user */
if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
@@ -319,76 +293,6 @@ segv:
force_sig(SIGSEGV, current);
}
-asmlinkage void do_sigreturn32(struct pt_regs *regs)
-{
- struct sigcontext32 __user *scptr;
- unsigned int pc, npc, psr;
- sigset_t set;
- unsigned int seta[_COMPAT_NSIG_WORDS];
- int err;
-
- /* Always make any pending restarted system calls return -EINTR */
- current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
- synchronize_user_stack();
- if (test_thread_flag(TIF_NEWSIGNALS)) {
- do_new_sigreturn32(regs);
- return;
- }
-
- scptr = (struct sigcontext32 __user *)
- (regs->u_regs[UREG_I0] & 0x00000000ffffffffUL);
- /* Check sanity of the user arg. */
- if (!access_ok(VERIFY_READ, scptr, sizeof(struct sigcontext32)) ||
- (((unsigned long) scptr) & 3))
- goto segv;
-
- err = __get_user(pc, &scptr->sigc_pc);
- err |= __get_user(npc, &scptr->sigc_npc);
-
- if ((pc | npc) & 3)
- goto segv; /* Nice try. */
-
- err |= __get_user(seta[0], &scptr->sigc_mask);
- /* Note that scptr + 1 points to extramask */
- err |= copy_from_user(seta+1, scptr + 1,
- (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
- if (err)
- goto segv;
- switch (_NSIG_WORDS) {
- case 4: set.sig[3] = seta[6] + (((long)seta[7]) << 32);
- case 3: set.sig[2] = seta[4] + (((long)seta[5]) << 32);
- case 2: set.sig[1] = seta[2] + (((long)seta[3]) << 32);
- case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32);
- }
- sigdelsetmask(&set, ~_BLOCKABLE);
- spin_lock_irq(&current->sighand->siglock);
- current->blocked = set;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
-
- if (test_thread_flag(TIF_32BIT)) {
- pc &= 0xffffffff;
- npc &= 0xffffffff;
- }
- regs->tpc = pc;
- regs->tnpc = npc;
- err = __get_user(regs->u_regs[UREG_FP], &scptr->sigc_sp);
- err |= __get_user(regs->u_regs[UREG_I0], &scptr->sigc_o0);
- err |= __get_user(regs->u_regs[UREG_G1], &scptr->sigc_g1);
-
- /* User can only change condition codes in %tstate. */
- err |= __get_user(psr, &scptr->sigc_psr);
- if (err)
- goto segv;
- regs->tstate &= ~(TSTATE_ICC|TSTATE_XCC);
- regs->tstate |= psr_to_tstate_icc(psr);
- return;
-
-segv:
- force_sig(SIGSEGV, current);
-}
-
asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
{
struct rt_signal_frame32 __user *sf;
@@ -504,145 +408,6 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns
return (void __user *)(sp - framesize);
}
-static void
-setup_frame32(struct sigaction *sa, struct pt_regs *regs, int signr, sigset_t *oldset, siginfo_t *info)
-{
- struct signal_sframe32 __user *sframep;
- struct sigcontext32 __user *sc;
- unsigned int seta[_COMPAT_NSIG_WORDS];
- int err = 0;
- void __user *sig_address;
- int sig_code;
- unsigned long pc = regs->tpc;
- unsigned long npc = regs->tnpc;
- unsigned int psr;
-
- if (test_thread_flag(TIF_32BIT)) {
- pc &= 0xffffffff;
- npc &= 0xffffffff;
- }
-
- synchronize_user_stack();
- save_and_clear_fpu();
-
- sframep = (struct signal_sframe32 __user *)
- get_sigframe(sa, regs, SF_ALIGNEDSZ);
- if (invalid_frame_pointer(sframep, sizeof(*sframep))){
- /* Don't change signal code and address, so that
- * post mortem debuggers can have a look.
- */
- do_exit(SIGILL);
- }
-
- sc = &sframep->sig_context;
-
- /* We've already made sure frame pointer isn't in kernel space... */
- err = __put_user((sas_ss_flags(regs->u_regs[UREG_FP]) == SS_ONSTACK),
- &sc->sigc_onstack);
-
- switch (_NSIG_WORDS) {
- case 4: seta[7] = (oldset->sig[3] >> 32);
- seta[6] = oldset->sig[3];
- case 3: seta[5] = (oldset->sig[2] >> 32);
- seta[4] = oldset->sig[2];
- case 2: seta[3] = (oldset->sig[1] >> 32);
- seta[2] = oldset->sig[1];
- case 1: seta[1] = (oldset->sig[0] >> 32);
- seta[0] = oldset->sig[0];
- }
- err |= __put_user(seta[0], &sc->sigc_mask);
- err |= __copy_to_user(sframep->extramask, seta + 1,
- (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
- err |= __put_user(regs->u_regs[UREG_FP], &sc->sigc_sp);
- err |= __put_user(pc, &sc->sigc_pc);
- err |= __put_user(npc, &sc->sigc_npc);
- psr = tstate_to_psr(regs->tstate);
- if (current_thread_info()->fpsaved[0] & FPRS_FEF)
- psr |= PSR_EF;
- err |= __put_user(psr, &sc->sigc_psr);
- err |= __put_user(regs->u_regs[UREG_G1], &sc->sigc_g1);
- err |= __put_user(regs->u_regs[UREG_I0], &sc->sigc_o0);
- err |= __put_user(get_thread_wsaved(), &sc->sigc_oswins);
-
- err |= copy_in_user((u32 __user *)sframep,
- (u32 __user *)(regs->u_regs[UREG_FP]),
- sizeof(struct reg_window32));
-
- set_thread_wsaved(0); /* So process is allowed to execute. */
- err |= __put_user(signr, &sframep->sig_num);
- sig_address = NULL;
- sig_code = 0;
- if (SI_FROMKERNEL (info) && (info->si_code & __SI_MASK) == __SI_FAULT) {
- sig_address = info->si_addr;
- switch (signr) {
- case SIGSEGV:
- switch (info->si_code) {
- case SEGV_MAPERR: sig_code = SUBSIG_NOMAPPING; break;
- default: sig_code = SUBSIG_PROTECTION; break;
- }
- break;
- case SIGILL:
- switch (info->si_code) {
- case ILL_ILLOPC: sig_code = SUBSIG_ILLINST; break;
- case ILL_PRVOPC: sig_code = SUBSIG_PRIVINST; break;
- case ILL_ILLTRP: sig_code = SUBSIG_BADTRAP(info->si_trapno); break;
- default: sig_code = SUBSIG_STACK; break;
- }
- break;
- case SIGFPE:
- switch (info->si_code) {
- case FPE_INTDIV: sig_code = SUBSIG_IDIVZERO; break;
- case FPE_INTOVF: sig_code = SUBSIG_FPINTOVFL; break;
- case FPE_FLTDIV: sig_code = SUBSIG_FPDIVZERO; break;
- case FPE_FLTOVF: sig_code = SUBSIG_FPOVFLOW; break;
- case FPE_FLTUND: sig_code = SUBSIG_FPUNFLOW; break;
- case FPE_FLTRES: sig_code = SUBSIG_FPINEXACT; break;
- case FPE_FLTINV: sig_code = SUBSIG_FPOPERROR; break;
- default: sig_code = SUBSIG_FPERROR; break;
- }
- break;
- case SIGBUS:
- switch (info->si_code) {
- case BUS_ADRALN: sig_code = SUBSIG_ALIGNMENT; break;
- case BUS_ADRERR: sig_code = SUBSIG_MISCERROR; break;
- default: sig_code = SUBSIG_BUSTIMEOUT; break;
- }
- break;
- case SIGEMT:
- switch (info->si_code) {
- case EMT_TAGOVF: sig_code = SUBSIG_TAG; break;
- }
- break;
- case SIGSYS:
- if (info->si_code == (__SI_FAULT|0x100)) {
- /* See sys_sunos32.c */
- sig_code = info->si_trapno;
- break;
- }
- default:
- sig_address = NULL;
- }
- }
- err |= __put_user(ptr_to_compat(sig_address), &sframep->sig_address);
- err |= __put_user(sig_code, &sframep->sig_code);
- err |= __put_user(ptr_to_compat(sc), &sframep->sig_scptr);
- if (err)
- goto sigsegv;
-
- regs->u_regs[UREG_FP] = (unsigned long) sframep;
- regs->tpc = (unsigned long) sa->sa_handler;
- regs->tnpc = (regs->tpc + 4);
- if (test_thread_flag(TIF_32BIT)) {
- regs->tpc &= 0xffffffff;
- regs->tnpc &= 0xffffffff;
- }
- return;
-
-sigsegv:
- force_sigsegv(signr, current);
-}
-
-
static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
{
unsigned long *fpregs = current_thread_info()->fpregs;
@@ -663,10 +428,10 @@ static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
return err;
}
-static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
- int signo, sigset_t *oldset)
+static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
+ int signo, sigset_t *oldset)
{
- struct new_signal_frame32 __user *sf;
+ struct signal_frame32 __user *sf;
int sigframe_size;
u32 psr;
int i, err;
@@ -676,11 +441,11 @@ static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs,
synchronize_user_stack();
save_and_clear_fpu();
- sigframe_size = NF_ALIGNEDSZ;
+ sigframe_size = SF_ALIGNEDSZ;
if (!(current_thread_info()->fpsaved[0] & FPRS_FEF))
sigframe_size -= sizeof(__siginfo_fpu_t);
- sf = (struct new_signal_frame32 __user *)
+ sf = (struct signal_frame32 __user *)
get_sigframe(&ka->sa, regs, sigframe_size);
if (invalid_frame_pointer(sf, sigframe_size))
@@ -944,10 +709,9 @@ static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka,
{
if (ka->sa.sa_flags & SA_SIGINFO)
setup_rt_frame32(ka, regs, signr, oldset, info);
- else if (test_thread_flag(TIF_NEWSIGNALS))
- new_setup_frame32(ka, regs, signr, oldset);
else
- setup_frame32(&ka->sa, regs, signr, oldset, info);
+ setup_frame32(ka, regs, signr, oldset);
+
spin_lock_irq(&current->sighand->siglock);
sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NOMASK))
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index 524b8892094..409dd71f273 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -866,14 +866,21 @@ void smp_call_function_client(int irq, struct pt_regs *regs)
void *info = call_data->info;
clear_softint(1 << irq);
+
+ irq_enter();
+
+ if (!call_data->wait) {
+ /* let initiator proceed after getting data */
+ atomic_inc(&call_data->finished);
+ }
+
+ func(info);
+
+ irq_exit();
+
if (call_data->wait) {
/* let initiator proceed only after completion */
- func(info);
atomic_inc(&call_data->finished);
- } else {
- /* let initiator proceed after getting data */
- atomic_inc(&call_data->finished);
- func(info);
}
}
@@ -1032,7 +1039,9 @@ void smp_receive_signal(int cpu)
void smp_receive_signal_client(int irq, struct pt_regs *regs)
{
+ irq_enter();
clear_softint(1 << irq);
+ irq_exit();
}
void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
@@ -1040,6 +1049,8 @@ void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
struct mm_struct *mm;
unsigned long flags;
+ irq_enter();
+
clear_softint(1 << irq);
/* See if we need to allocate a new TLB context because
@@ -1059,6 +1070,8 @@ void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
load_secondary_context(mm);
__flush_tlb_mm(CTX_HWBITS(mm->context),
SECONDARY_CONTEXT);
+
+ irq_exit();
}
void smp_new_mmu_context_version(void)
@@ -1217,6 +1230,8 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs)
{
clear_softint(1 << irq);
+ irq_enter();
+
preempt_disable();
__asm__ __volatile__("flushw");
@@ -1229,6 +1244,8 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs)
prom_world(0);
preempt_enable();
+
+ irq_exit();
}
/* /proc/profile writes can call this, don't __init it please. */
diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc64/kernel/sparc64_ksyms.c
index 66336590e83..8ac0b99f2c5 100644
--- a/arch/sparc64/kernel/sparc64_ksyms.c
+++ b/arch/sparc64/kernel/sparc64_ksyms.c
@@ -49,7 +49,6 @@
#endif
#ifdef CONFIG_PCI
#include <asm/ebus.h>
-#include <asm/isa.h>
#endif
#include <asm/ns87303.h>
#include <asm/timer.h>
@@ -187,7 +186,6 @@ EXPORT_SYMBOL(insw);
EXPORT_SYMBOL(insl);
#ifdef CONFIG_PCI
EXPORT_SYMBOL(ebus_chain);
-EXPORT_SYMBOL(isa_chain);
EXPORT_SYMBOL(pci_alloc_consistent);
EXPORT_SYMBOL(pci_free_consistent);
EXPORT_SYMBOL(pci_map_single);
diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc64/kernel/sys_sparc.c
index 73ed01ba40d..8d4761f15fa 100644
--- a/arch/sparc64/kernel/sys_sparc.c
+++ b/arch/sparc64/kernel/sys_sparc.c
@@ -454,8 +454,8 @@ asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second,
err = sys_semget(first, (int)second, (int)third);
goto out;
case SEMCTL: {
- err = sys_semctl(first, third,
- (int)second | IPC_64,
+ err = sys_semctl(first, second,
+ (int)third | IPC_64,
(union semun) ptr);
goto out;
}
diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc64/kernel/sys_sparc32.c
index c1a61e98899..161ce4710fe 100644
--- a/arch/sparc64/kernel/sys_sparc32.c
+++ b/arch/sparc64/kernel/sys_sparc32.c
@@ -554,10 +554,8 @@ asmlinkage long compat_sys_sigaction(int sig, struct old_sigaction32 __user *act
struct k_sigaction new_ka, old_ka;
int ret;
- if (sig < 0) {
- set_thread_flag(TIF_NEWSIGNALS);
- sig = -sig;
- }
+ WARN_ON_ONCE(sig >= 0);
+ sig = -sig;
if (act) {
compat_old_sigset_t mask;
@@ -601,11 +599,6 @@ asmlinkage long compat_sys_rt_sigaction(int sig,
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
- /* All tasks which use RT signals (effectively) use
- * new style signals.
- */
- set_thread_flag(TIF_NEWSIGNALS);
-
if (act) {
u32 u_handler, u_restorer;
diff --git a/arch/sparc64/mm/init.c b/arch/sparc64/mm/init.c
index 177d8aaeec4..8c2b50e8abc 100644
--- a/arch/sparc64/mm/init.c
+++ b/arch/sparc64/mm/init.c
@@ -1699,9 +1699,21 @@ void __init paging_init(void)
* functions like clear_dcache_dirty_cpu use the cpu mask
* in 13-bit signed-immediate instruction fields.
*/
- BUILD_BUG_ON(FLAGS_RESERVED != 32);
+
+ /*
+ * Page flags must not reach into upper 32 bits that are used
+ * for the cpu number
+ */
+ BUILD_BUG_ON(NR_PAGEFLAGS > 32);
+
+ /*
+ * The bit fields placed in the high range must not reach below
+ * the 32 bit boundary. Otherwise we cannot place the cpu field
+ * at the 32 bit boundary.
+ */
BUILD_BUG_ON(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH +
- ilog2(roundup_pow_of_two(NR_CPUS)) > FLAGS_RESERVED);
+ ilog2(roundup_pow_of_two(NR_CPUS)) > 32);
+
BUILD_BUG_ON(NR_CPUS > 4096);
kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
diff --git a/arch/um/Kconfig.x86_64 b/arch/um/Kconfig.x86_64
index 3fbe69e359e..5696e7b374b 100644
--- a/arch/um/Kconfig.x86_64
+++ b/arch/um/Kconfig.x86_64
@@ -1,3 +1,10 @@
+
+menu "Host processor type and features"
+
+source "arch/x86/Kconfig.cpu"
+
+endmenu
+
config UML_X86
bool
default y
diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c
index db3082b4da4..6e51424745a 100644
--- a/arch/um/drivers/chan_kern.c
+++ b/arch/um/drivers/chan_kern.c
@@ -125,7 +125,7 @@ static int open_one_chan(struct chan *chan)
return 0;
}
-int open_chan(struct list_head *chans)
+static int open_chan(struct list_head *chans)
{
struct list_head *ele;
struct chan *chan;
@@ -583,19 +583,6 @@ int parse_chan_pair(char *str, struct line *line, int device,
return 0;
}
-int chan_out_fd(struct list_head *chans)
-{
- struct list_head *ele;
- struct chan *chan;
-
- list_for_each(ele, chans) {
- chan = list_entry(ele, struct chan, list);
- if (chan->primary && chan->output)
- return chan->fd;
- }
- return -1;
-}
-
void chan_interrupt(struct list_head *chans, struct delayed_work *task,
struct tty_struct *tty, int irq)
{
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index 2c898c4d6b6..10b86e1cc65 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -304,7 +304,7 @@ int line_ioctl(struct tty_struct *tty, struct file * file,
break;
if (i == ARRAY_SIZE(tty_ioctls)) {
printk(KERN_ERR "%s: %s: unknown ioctl: 0x%x\n",
- __FUNCTION__, tty->name, cmd);
+ __func__, tty->name, cmd);
}
ret = -ENOIOCTLCMD;
break;
diff --git a/arch/um/drivers/mcast_kern.c b/arch/um/drivers/mcast_kern.c
index 822092f149b..8c4378a76d6 100644
--- a/arch/um/drivers/mcast_kern.c
+++ b/arch/um/drivers/mcast_kern.c
@@ -58,7 +58,7 @@ static const struct net_kern_info mcast_kern_info = {
.write = mcast_write,
};
-int mcast_setup(char *str, char **mac_out, void *data)
+static int mcast_setup(char *str, char **mac_out, void *data)
{
struct mcast_init *init = data;
char *port_str = NULL, *ttl_str = NULL, *remain;
diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c
index 13af2f03ed8..f8cf4c8bede 100644
--- a/arch/um/drivers/mconsole_user.c
+++ b/arch/um/drivers/mconsole_user.c
@@ -39,7 +39,7 @@ static struct mconsole_command commands[] = {
/* Initialized in mconsole_init, which is an initcall */
char mconsole_socket_name[256];
-int mconsole_reply_v0(struct mc_request *req, char *reply)
+static int mconsole_reply_v0(struct mc_request *req, char *reply)
{
struct iovec iov;
struct msghdr msg;
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 1d43bdfc20c..5b4ca8d9368 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -116,7 +116,7 @@ static void uml_dev_close(struct work_struct *work)
dev_close(lp->dev);
}
-irqreturn_t uml_net_interrupt(int irq, void *dev_id)
+static irqreturn_t uml_net_interrupt(int irq, void *dev_id)
{
struct net_device *dev = dev_id;
struct uml_net_private *lp = dev->priv;
@@ -296,7 +296,7 @@ static struct ethtool_ops uml_net_ethtool_ops = {
.get_link = ethtool_op_get_link,
};
-void uml_net_user_timer_expire(unsigned long _conn)
+static void uml_net_user_timer_expire(unsigned long _conn)
{
#ifdef undef
struct connection *conn = (struct connection *)_conn;
@@ -786,7 +786,7 @@ static int uml_inetaddr_event(struct notifier_block *this, unsigned long event,
}
/* uml_net_init shouldn't be called twice on two CPUs at the same time */
-struct notifier_block uml_inetaddr_notifier = {
+static struct notifier_block uml_inetaddr_notifier = {
.notifier_call = uml_inetaddr_event,
};
diff --git a/arch/um/drivers/port_user.c b/arch/um/drivers/port_user.c
index addd7590265..d269ca387f1 100644
--- a/arch/um/drivers/port_user.c
+++ b/arch/um/drivers/port_user.c
@@ -153,7 +153,7 @@ struct port_pre_exec_data {
int pipe_fd;
};
-void port_pre_exec(void *arg)
+static void port_pre_exec(void *arg)
{
struct port_pre_exec_data *data = arg;
diff --git a/arch/um/drivers/slip_kern.c b/arch/um/drivers/slip_kern.c
index 6b4a0f9e38d..d19faec7046 100644
--- a/arch/um/drivers/slip_kern.c
+++ b/arch/um/drivers/slip_kern.c
@@ -13,7 +13,7 @@ struct slip_init {
char *gate_addr;
};
-void slip_init(struct net_device *dev, void *data)
+static void slip_init(struct net_device *dev, void *data)
{
struct uml_net_private *private;
struct slip_data *spri;
@@ -57,7 +57,7 @@ static int slip_write(int fd, struct sk_buff *skb, struct uml_net_private *lp)
(struct slip_data *) &lp->user);
}
-const struct net_kern_info slip_kern_info = {
+static const struct net_kern_info slip_kern_info = {
.init = slip_init,
.protocol = slip_protocol,
.read = slip_read,
diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c
index cec0c33cdd3..49266f6108c 100644
--- a/arch/um/drivers/stdio_console.c
+++ b/arch/um/drivers/stdio_console.c
@@ -34,7 +34,7 @@
static struct tty_driver *console_driver;
-void stdio_announce(char *dev_name, int dev)
+static void stdio_announce(char *dev_name, int dev)
{
printk(KERN_INFO "Virtual console %d assigned device '%s'\n", dev,
dev_name);
@@ -158,7 +158,7 @@ static struct console stdiocons = {
.index = -1,
};
-int stdio_init(void)
+static int stdio_init(void)
{
char *new_title;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index be3a2797dac..5e45e39a8a8 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -72,18 +72,6 @@ struct io_thread_req {
int error;
};
-extern int open_ubd_file(char *file, struct openflags *openflags, int shared,
- char **backing_file_out, int *bitmap_offset_out,
- unsigned long *bitmap_len_out, int *data_offset_out,
- int *create_cow_out);
-extern int create_cow_file(char *cow_file, char *backing_file,
- struct openflags flags, int sectorsize,
- int alignment, int *bitmap_offset_out,
- unsigned long *bitmap_len_out,
- int *data_offset_out);
-extern int read_cow_bitmap(int fd, void *buf, int offset, int len);
-extern void do_io(struct io_thread_req *req);
-
static inline int ubd_test_bit(__u64 bit, unsigned char *data)
{
__u64 n;
@@ -200,7 +188,7 @@ struct ubd {
}
/* Protected by ubd_lock */
-struct ubd ubd_devs[MAX_DEV] = { [ 0 ... MAX_DEV - 1 ] = DEFAULT_UBD };
+static struct ubd ubd_devs[MAX_DEV] = { [0 ... MAX_DEV - 1] = DEFAULT_UBD };
/* Only changed by fake_ide_setup which is a setup */
static int fake_ide = 0;
@@ -463,7 +451,7 @@ __uml_help(udb_setup,
static void do_ubd_request(struct request_queue * q);
/* Only changed by ubd_init, which is an initcall. */
-int thread_fd = -1;
+static int thread_fd = -1;
static void ubd_end_request(struct request *req, int bytes, int error)
{
@@ -531,7 +519,7 @@ static irqreturn_t ubd_intr(int irq, void *dev)
/* Only changed by ubd_init, which is an initcall. */
static int io_pid = -1;
-void kill_io_thread(void)
+static void kill_io_thread(void)
{
if(io_pid != -1)
os_kill_process(io_pid, 1);
@@ -547,6 +535,192 @@ static inline int ubd_file_size(struct ubd *ubd_dev, __u64 *size_out)
return os_file_size(file, size_out);
}
+static int read_cow_bitmap(int fd, void *buf, int offset, int len)
+{
+ int err;
+
+ err = os_seek_file(fd, offset);
+ if (err < 0)
+ return err;
+
+ err = os_read_file(fd, buf, len);
+ if (err < 0)
+ return err;
+
+ return 0;
+}
+
+static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
+{
+ unsigned long modtime;
+ unsigned long long actual;
+ int err;
+
+ err = os_file_modtime(file, &modtime);
+ if (err < 0) {
+ printk(KERN_ERR "Failed to get modification time of backing "
+ "file \"%s\", err = %d\n", file, -err);
+ return err;
+ }
+
+ err = os_file_size(file, &actual);
+ if (err < 0) {
+ printk(KERN_ERR "Failed to get size of backing file \"%s\", "
+ "err = %d\n", file, -err);
+ return err;
+ }
+
+ if (actual != size) {
+ /*__u64 can be a long on AMD64 and with %lu GCC complains; so
+ * the typecast.*/
+ printk(KERN_ERR "Size mismatch (%llu vs %llu) of COW header "
+ "vs backing file\n", (unsigned long long) size, actual);
+ return -EINVAL;
+ }
+ if (modtime != mtime) {
+ printk(KERN_ERR "mtime mismatch (%ld vs %ld) of COW header vs "
+ "backing file\n", mtime, modtime);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int path_requires_switch(char *from_cmdline, char *from_cow, char *cow)
+{
+ struct uml_stat buf1, buf2;
+ int err;
+
+ if (from_cmdline == NULL)
+ return 0;
+ if (!strcmp(from_cmdline, from_cow))
+ return 0;
+
+ err = os_stat_file(from_cmdline, &buf1);
+ if (err < 0) {
+ printk(KERN_ERR "Couldn't stat '%s', err = %d\n", from_cmdline,
+ -err);
+ return 0;
+ }
+ err = os_stat_file(from_cow, &buf2);
+ if (err < 0) {
+ printk(KERN_ERR "Couldn't stat '%s', err = %d\n", from_cow,
+ -err);
+ return 1;
+ }
+ if ((buf1.ust_dev == buf2.ust_dev) && (buf1.ust_ino == buf2.ust_ino))
+ return 0;
+
+ printk(KERN_ERR "Backing file mismatch - \"%s\" requested, "
+ "\"%s\" specified in COW header of \"%s\"\n",
+ from_cmdline, from_cow, cow);
+ return 1;
+}
+
+static int open_ubd_file(char *file, struct openflags *openflags, int shared,
+ char **backing_file_out, int *bitmap_offset_out,
+ unsigned long *bitmap_len_out, int *data_offset_out,
+ int *create_cow_out)
+{
+ time_t mtime;
+ unsigned long long size;
+ __u32 version, align;
+ char *backing_file;
+ int fd, err, sectorsize, asked_switch, mode = 0644;
+
+ fd = os_open_file(file, *openflags, mode);
+ if (fd < 0) {
+ if ((fd == -ENOENT) && (create_cow_out != NULL))
+ *create_cow_out = 1;
+ if (!openflags->w ||
+ ((fd != -EROFS) && (fd != -EACCES)))
+ return fd;
+ openflags->w = 0;
+ fd = os_open_file(file, *openflags, mode);
+ if (fd < 0)
+ return fd;
+ }
+
+ if (shared)
+ printk(KERN_INFO "Not locking \"%s\" on the host\n", file);
+ else {
+ err = os_lock_file(fd, openflags->w);
+ if (err < 0) {
+ printk(KERN_ERR "Failed to lock '%s', err = %d\n",
+ file, -err);
+ goto out_close;
+ }
+ }
+
+ /* Successful return case! */
+ if (backing_file_out == NULL)
+ return fd;
+
+ err = read_cow_header(file_reader, &fd, &version, &backing_file, &mtime,
+ &size, &sectorsize, &align, bitmap_offset_out);
+ if (err && (*backing_file_out != NULL)) {
+ printk(KERN_ERR "Failed to read COW header from COW file "
+ "\"%s\", errno = %d\n", file, -err);
+ goto out_close;
+ }
+ if (err)
+ return fd;
+
+ asked_switch = path_requires_switch(*backing_file_out, backing_file,
+ file);
+
+ /* Allow switching only if no mismatch. */
+ if (asked_switch && !backing_file_mismatch(*backing_file_out, size,
+ mtime)) {
+ printk(KERN_ERR "Switching backing file to '%s'\n",
+ *backing_file_out);
+ err = write_cow_header(file, fd, *backing_file_out,
+ sectorsize, align, &size);
+ if (err) {
+ printk(KERN_ERR "Switch failed, errno = %d\n", -err);
+ goto out_close;
+ }
+ } else {
+ *backing_file_out = backing_file;
+ err = backing_file_mismatch(*backing_file_out, size, mtime);
+ if (err)
+ goto out_close;
+ }
+
+ cow_sizes(version, size, sectorsize, align, *bitmap_offset_out,
+ bitmap_len_out, data_offset_out);
+
+ return fd;
+ out_close:
+ os_close_file(fd);
+ return err;
+}
+
+static int create_cow_file(char *cow_file, char *backing_file,
+ struct openflags flags,
+ int sectorsize, int alignment, int *bitmap_offset_out,
+ unsigned long *bitmap_len_out, int *data_offset_out)
+{
+ int err, fd;
+
+ flags.c = 1;
+ fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL);
+ if (fd < 0) {
+ err = fd;
+ printk(KERN_ERR "Open of COW file '%s' failed, errno = %d\n",
+ cow_file, -err);
+ goto out;
+ }
+
+ err = init_cow_file(fd, cow_file, backing_file, sectorsize, alignment,
+ bitmap_offset_out, bitmap_len_out,
+ data_offset_out);
+ if (!err)
+ return fd;
+ os_close_file(fd);
+ out:
+ return err;
+}
+
static void ubd_close_dev(struct ubd *ubd_dev)
{
os_close_file(ubd_dev->fd);
@@ -1166,185 +1340,6 @@ static int ubd_ioctl(struct inode * inode, struct file * file,
return -EINVAL;
}
-static int path_requires_switch(char *from_cmdline, char *from_cow, char *cow)
-{
- struct uml_stat buf1, buf2;
- int err;
-
- if(from_cmdline == NULL)
- return 0;
- if(!strcmp(from_cmdline, from_cow))
- return 0;
-
- err = os_stat_file(from_cmdline, &buf1);
- if(err < 0){
- printk("Couldn't stat '%s', err = %d\n", from_cmdline, -err);
- return 0;
- }
- err = os_stat_file(from_cow, &buf2);
- if(err < 0){
- printk("Couldn't stat '%s', err = %d\n", from_cow, -err);
- return 1;
- }
- if((buf1.ust_dev == buf2.ust_dev) && (buf1.ust_ino == buf2.ust_ino))
- return 0;
-
- printk("Backing file mismatch - \"%s\" requested,\n"
- "\"%s\" specified in COW header of \"%s\"\n",
- from_cmdline, from_cow, cow);
- return 1;
-}
-
-static int backing_file_mismatch(char *file, __u64 size, time_t mtime)
-{
- unsigned long modtime;
- unsigned long long actual;
- int err;
-
- err = os_file_modtime(file, &modtime);
- if(err < 0){
- printk("Failed to get modification time of backing file "
- "\"%s\", err = %d\n", file, -err);
- return err;
- }
-
- err = os_file_size(file, &actual);
- if(err < 0){
- printk("Failed to get size of backing file \"%s\", "
- "err = %d\n", file, -err);
- return err;
- }
-
- if(actual != size){
- /*__u64 can be a long on AMD64 and with %lu GCC complains; so
- * the typecast.*/
- printk("Size mismatch (%llu vs %llu) of COW header vs backing "
- "file\n", (unsigned long long) size, actual);
- return -EINVAL;
- }
- if(modtime != mtime){
- printk("mtime mismatch (%ld vs %ld) of COW header vs backing "
- "file\n", mtime, modtime);
- return -EINVAL;
- }
- return 0;
-}
-
-int read_cow_bitmap(int fd, void *buf, int offset, int len)
-{
- int err;
-
- err = os_seek_file(fd, offset);
- if(err < 0)
- return err;
-
- err = os_read_file(fd, buf, len);
- if(err < 0)
- return err;
-
- return 0;
-}
-
-int open_ubd_file(char *file, struct openflags *openflags, int shared,
- char **backing_file_out, int *bitmap_offset_out,
- unsigned long *bitmap_len_out, int *data_offset_out,
- int *create_cow_out)
-{
- time_t mtime;
- unsigned long long size;
- __u32 version, align;
- char *backing_file;
- int fd, err, sectorsize, asked_switch, mode = 0644;
-
- fd = os_open_file(file, *openflags, mode);
- if (fd < 0) {
- if ((fd == -ENOENT) && (create_cow_out != NULL))
- *create_cow_out = 1;
- if (!openflags->w ||
- ((fd != -EROFS) && (fd != -EACCES)))
- return fd;
- openflags->w = 0;
- fd = os_open_file(file, *openflags, mode);
- if (fd < 0)
- return fd;
- }
-
- if(shared)
- printk("Not locking \"%s\" on the host\n", file);
- else {
- err = os_lock_file(fd, openflags->w);
- if(err < 0){
- printk("Failed to lock '%s', err = %d\n", file, -err);
- goto out_close;
- }
- }
-
- /* Successful return case! */
- if(backing_file_out == NULL)
- return fd;
-
- err = read_cow_header(file_reader, &fd, &version, &backing_file, &mtime,
- &size, &sectorsize, &align, bitmap_offset_out);
- if(err && (*backing_file_out != NULL)){
- printk("Failed to read COW header from COW file \"%s\", "
- "errno = %d\n", file, -err);
- goto out_close;
- }
- if(err)
- return fd;
-
- asked_switch = path_requires_switch(*backing_file_out, backing_file, file);
-
- /* Allow switching only if no mismatch. */
- if (asked_switch && !backing_file_mismatch(*backing_file_out, size, mtime)) {
- printk("Switching backing file to '%s'\n", *backing_file_out);
- err = write_cow_header(file, fd, *backing_file_out,
- sectorsize, align, &size);
- if (err) {
- printk("Switch failed, errno = %d\n", -err);
- goto out_close;
- }
- } else {
- *backing_file_out = backing_file;
- err = backing_file_mismatch(*backing_file_out, size, mtime);
- if (err)
- goto out_close;
- }
-
- cow_sizes(version, size, sectorsize, align, *bitmap_offset_out,
- bitmap_len_out, data_offset_out);
-
- return fd;
- out_close:
- os_close_file(fd);
- return err;
-}
-
-int create_cow_file(char *cow_file, char *backing_file, struct openflags flags,
- int sectorsize, int alignment, int *bitmap_offset_out,
- unsigned long *bitmap_len_out, int *data_offset_out)
-{
- int err, fd;
-
- flags.c = 1;
- fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL);
- if(fd < 0){
- err = fd;
- printk("Open of COW file '%s' failed, errno = %d\n", cow_file,
- -err);
- goto out;
- }
-
- err = init_cow_file(fd, cow_file, backing_file, sectorsize, alignment,
- bitmap_offset_out, bitmap_len_out,
- data_offset_out);
- if(!err)
- return fd;
- os_close_file(fd);
- out:
- return err;
-}
-
static int update_bitmap(struct io_thread_req *req)
{
int n;
@@ -1369,7 +1364,7 @@ static int update_bitmap(struct io_thread_req *req)
return 0;
}
-void do_io(struct io_thread_req *req)
+static void do_io(struct io_thread_req *req)
{
char *buf;
unsigned long len;
diff --git a/arch/um/include/chan_kern.h b/arch/um/include/chan_kern.h
index 624b5100a3c..1e651457e04 100644
--- a/arch/um/include/chan_kern.h
+++ b/arch/um/include/chan_kern.h
@@ -31,7 +31,6 @@ extern void chan_interrupt(struct list_head *chans, struct delayed_work *task,
struct tty_struct *tty, int irq);
extern int parse_chan_pair(char *str, struct line *line, int device,
const struct chan_opts *opts, char **error_out);
-extern int open_chan(struct list_head *chans);
extern int write_chan(struct list_head *chans, const char *buf, int len,
int write_irq);
extern int console_write_chan(struct list_head *chans, const char *buf,
@@ -45,7 +44,6 @@ extern void close_chan(struct list_head *chans, int delay_free_irq);
extern int chan_window_size(struct list_head *chans,
unsigned short *rows_out,
unsigned short *cols_out);
-extern int chan_out_fd(struct list_head *chans);
extern int chan_config_string(struct list_head *chans, char *str, int size,
char **error_out);
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index a6c1dd1cf5a..56deed62344 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -115,7 +115,7 @@ static int have_root __initdata = 0;
/* Set in uml_mem_setup and modified in linux_main */
long long physmem_size = 32 * 1024 * 1024;
-static char *usage_string =
+static const char *usage_string =
"User Mode Linux v%s\n"
" available at http://user-mode-linux.sourceforge.net/\n\n";
@@ -202,7 +202,7 @@ static void __init uml_checksetup(char *line, int *add)
p = &__uml_setup_start;
while (p < &__uml_setup_end) {
- int n;
+ size_t n;
n = strlen(p->str);
if (!strncmp(line, p->str, n) && p->setup_func(line + n, add))
@@ -258,7 +258,8 @@ int __init linux_main(int argc, char **argv)
{
unsigned long avail, diff;
unsigned long virtmem_size, max_physmem;
- unsigned int i, add;
+ unsigned int i;
+ int add;
char * mode;
for (i = 1; i < argc; i++) {
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index f4bd349d441..f25c29a12d0 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -14,6 +14,7 @@
#include "os.h"
#include "um_malloc.h"
#include "user.h"
+#include <linux/limits.h>
struct helper_data {
void (*pre_exec)(void*);
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index b616e15638f..997d01944f9 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -25,15 +25,15 @@
#include "registers.h"
#include "skas_ptrace.h"
-static int ptrace_child(void)
+static void ptrace_child(void)
{
int ret;
/* Calling os_getpid because some libcs cached getpid incorrectly */
int pid = os_getpid(), ppid = getppid();
int sc_result;
- change_sig(SIGWINCH, 0);
- if (ptrace(PTRACE_TRACEME, 0, 0, 0) < 0) {
+ if (change_sig(SIGWINCH, 0) < 0 ||
+ ptrace(PTRACE_TRACEME, 0, 0, 0) < 0) {
perror("ptrace");
kill(pid, SIGKILL);
}
@@ -75,9 +75,8 @@ static void fatal(char *fmt, ...)
va_list list;
va_start(list, fmt);
- vprintf(fmt, list);
+ vfprintf(stderr, fmt, list);
va_end(list);
- fflush(stdout);
exit(1);
}
@@ -87,9 +86,8 @@ static void non_fatal(char *fmt, ...)
va_list list;
va_start(list, fmt);
- vprintf(fmt, list);
+ vfprintf(stderr, fmt, list);
va_end(list);
- fflush(stdout);
}
static int start_ptraced_child(void)
@@ -495,7 +493,7 @@ int __init parse_iomem(char *str, int *add)
driver = str;
file = strchr(str,',');
if (file == NULL) {
- printf("parse_iomem : failed to parse iomem\n");
+ fprintf(stderr, "parse_iomem : failed to parse iomem\n");
goto out;
}
*file = '\0';
diff --git a/arch/um/os-Linux/sys-i386/task_size.c b/arch/um/os-Linux/sys-i386/task_size.c
index 48d211b3d9a..ccb49b0aff5 100644
--- a/arch/um/os-Linux/sys-i386/task_size.c
+++ b/arch/um/os-Linux/sys-i386/task_size.c
@@ -88,7 +88,10 @@ unsigned long os_get_task_size(void)
sa.sa_handler = segfault;
sigemptyset(&sa.sa_mask);
sa.sa_flags = SA_NODEFER;
- sigaction(SIGSEGV, &sa, &old);
+ if (sigaction(SIGSEGV, &sa, &old)) {
+ perror("os_get_task_size");
+ exit(1);
+ }
if (!page_ok(bottom)) {
fprintf(stderr, "Address 0x%x no good?\n",
@@ -110,11 +113,12 @@ unsigned long os_get_task_size(void)
out:
/* Restore the old SIGSEGV handling */
- sigaction(SIGSEGV, &old, NULL);
-
+ if (sigaction(SIGSEGV, &old, NULL)) {
+ perror("os_get_task_size");
+ exit(1);
+ }
top <<= UM_KERN_PAGE_SHIFT;
printf("0x%x\n", top);
- fflush(stdout);
return top;
}
diff --git a/arch/um/sys-i386/Makefile b/arch/um/sys-i386/Makefile
index 964dc1a04c3..598b5c1903a 100644
--- a/arch/um/sys-i386/Makefile
+++ b/arch/um/sys-i386/Makefile
@@ -6,7 +6,7 @@ obj-y = bug.o bugs.o checksum.o delay.o fault.o ksyms.o ldt.o ptrace.o \
ptrace_user.o setjmp.o signal.o stub.o stub_segv.o syscalls.o sysrq.o \
sys_call_table.o tls.o
-subarch-obj-y = lib/bitops_32.o lib/semaphore_32.o lib/string_32.o
+subarch-obj-y = lib/semaphore_32.o lib/string_32.o
subarch-obj-$(CONFIG_HIGHMEM) += mm/highmem_32.o
subarch-obj-$(CONFIG_MODULES) += kernel/module_32.o
diff --git a/arch/um/sys-x86_64/Makefile b/arch/um/sys-x86_64/Makefile
index 3c22de53208..c8b4cce9cfe 100644
--- a/arch/um/sys-x86_64/Makefile
+++ b/arch/um/sys-x86_64/Makefile
@@ -10,7 +10,7 @@ obj-y = bug.o bugs.o delay.o fault.o ldt.o mem.o ptrace.o ptrace_user.o \
obj-$(CONFIG_MODULES) += um_module.o
-subarch-obj-y = lib/bitops_64.o lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o
+subarch-obj-y = lib/csum-partial_64.o lib/memcpy_64.o lib/thunk_64.o
subarch-obj-$(CONFIG_MODULES) += kernel/module_64.o
ldt-y = ../sys-i386/ldt.o
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4d350b5cbc7..a12dbb2b93f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -86,9 +86,6 @@ config GENERIC_GPIO
config ARCH_MAY_HAVE_PC_FDC
def_bool y
-config DMI
- def_bool y
-
config RWSEM_GENERIC_SPINLOCK
def_bool !X86_XADD
@@ -114,6 +111,9 @@ config GENERIC_TIME_VSYSCALL
config ARCH_HAS_CPU_RELAX
def_bool y
+config ARCH_HAS_CACHE_LINE_SIZE
+ def_bool y
+
config HAVE_SETUP_PER_CPU_AREA
def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
@@ -142,6 +142,9 @@ config AUDIT_ARCH
config ARCH_SUPPORTS_AOUT
def_bool y
+config ARCH_SUPPORTS_OPTIMIZED_INLINING
+ def_bool y
+
# Use the generic interrupt handling code in kernel/irq/:
config GENERIC_HARDIRQS
bool
@@ -370,6 +373,25 @@ config VMI
at the moment), by linking the kernel to a GPL-ed ROM module
provided by the hypervisor.
+config KVM_CLOCK
+ bool "KVM paravirtualized clock"
+ select PARAVIRT
+ depends on !(X86_VISWS || X86_VOYAGER)
+ help
+ Turning on this option will allow you to run a paravirtualized clock
+ when running over the KVM hypervisor. Instead of relying on a PIT
+ (or probably other) emulation by the underlying device model, the host
+ provides the guest with timing infrastructure such as time of day, and
+ system time
+
+config KVM_GUEST
+ bool "KVM Guest support"
+ select PARAVIRT
+ depends on !(X86_VISWS || X86_VOYAGER)
+ help
+ This option enables various optimizations for running under the KVM
+ hypervisor.
+
source "arch/x86/lguest/Kconfig"
config PARAVIRT
@@ -460,6 +482,15 @@ config HPET_EMULATE_RTC
# Mark as embedded because too many people got it wrong.
# The code disables itself when not needed.
+config DMI
+ default y
+ bool "Enable DMI scanning" if EMBEDDED
+ help
+ Enabled scanning of DMI to identify machine quirks. Say Y
+ here unless you have verified that your setup is not
+ affected by entries in the DMI blacklist. Required by PNP
+ BIOS code.
+
config GART_IOMMU
bool "GART IOMMU support" if EMBEDDED
default y
@@ -1049,9 +1080,9 @@ config MTRR
See <file:Documentation/mtrr.txt> for more information.
config X86_PAT
- def_bool y
+ bool
prompt "x86 PAT support"
- depends on MTRR && NONPROMISC_DEVMEM
+ depends on MTRR
help
Use PAT attributes to setup page level cache control.
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 57072f2716f..7ef18b01f0b 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -21,8 +21,8 @@ config M386
Here are the settings recommended for greatest speed:
- "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI
- 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels
- will run on a 386 class machine.
+ 486DLC/DLC2, and UMC 486SX-S. Only "386" kernels will run on a 386
+ class machine.
- "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
- "586" for generic Pentium CPUs lacking the TSC
@@ -278,6 +278,11 @@ config GENERIC_CPU
endchoice
+config X86_CPU
+ def_bool y
+ select GENERIC_FIND_FIRST_BIT
+ select GENERIC_FIND_NEXT_BIT
+
config X86_GENERIC
bool "Generic x86 support"
depends on X86_32
@@ -398,7 +403,7 @@ config X86_TSC
# generates cmov.
config X86_CMOV
def_bool y
- depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7)
+ depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || X86_64)
config X86_MINIMUM_CPU_FAMILY
int
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 610aaecc19f..5b1979a45a1 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -5,6 +5,17 @@ config TRACE_IRQFLAGS_SUPPORT
source "lib/Kconfig.debug"
+config NONPROMISC_DEVMEM
+ bool "Disable promiscuous /dev/mem"
+ help
+ The /dev/mem file by default only allows userspace access to PCI
+ space and the BIOS code and data regions. This is sufficient for
+ dosemu and X and all common users of /dev/mem. With this config
+ option, you allow userspace access to all of memory, including
+ kernel and userspace memory. Accidental access to this is
+ obviously disasterous, but specific access can be used by people
+ debugging the kernel.
+
config EARLY_PRINTK
bool "Early printk" if EMBEDDED
default y
@@ -246,3 +257,16 @@ config CPA_DEBUG
Do change_page_attr() self-tests every 30 seconds.
endmenu
+
+config OPTIMIZE_INLINING
+ bool "Allow gcc to uninline functions marked 'inline'"
+ default y
+ help
+ This option determines if the kernel forces gcc to inline the functions
+ developers have marked 'inline'. Doing so takes away freedom from gcc to
+ do what it thinks is best, which is desirable for the gcc 3.x series of
+ compilers. The gcc 4.x series have a rewritten inlining algorithm and
+ disabling this option will generate a smaller kernel there. Hopefully
+ this algorithm is so good that allowing gcc4 to make the decision can
+ become the default in the future, until then this option is there to
+ test gcc for this.
diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore
index b1bdc4c6f9f..172cf8a98bd 100644
--- a/arch/x86/boot/.gitignore
+++ b/arch/x86/boot/.gitignore
@@ -1,7 +1,8 @@
bootsect
bzImage
+cpustr.h
+mkcpustr
+offsets.h
setup
setup.bin
setup.elf
-cpustr.h
-mkcpustr
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 6d2df8d61c5..af86e431acf 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -120,7 +120,7 @@ _start:
# Part 2 of the header, from the old setup.S
.ascii "HdrS" # header signature
- .word 0x0208 # header version number (>= 0x0105)
+ .word 0x0209 # header version number (>= 0x0105)
# or else old loadlin-1.5 will fail)
.globl realmode_swtch
realmode_swtch: .word 0, 0 # default_switch, SETUPSEG
@@ -227,6 +227,10 @@ hardware_subarch_data: .quad 0
payload_offset: .long input_data
payload_length: .long input_data_end-input_data
+setup_data: .quad 0 # 64-bit physical pointer to
+ # single linked list of
+ # struct setup_data
+
# End of setup header #####################################################
.section ".inittext", "ax"
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 3df340b54e5..ad7ddaaff58 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1421,6 +1421,7 @@ CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_VM is not set
# CONFIG_DEBUG_LIST is not set
# CONFIG_FRAME_POINTER is not set
+CONFIG_OPTIMIZE_INLINING=y
# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_LKDTM is not set
# CONFIG_FAULT_INJECTION is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index eef98cb00c6..2d6f5b2809d 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1346,6 +1346,7 @@ CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_VM is not set
# CONFIG_DEBUG_LIST is not set
# CONFIG_FRAME_POINTER is not set
+CONFIG_OPTIMIZE_INLINING=y
# CONFIG_RCU_TORTURE_TEST is not set
# CONFIG_LKDTM is not set
# CONFIG_FAULT_INJECTION is not set
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 05e155d3fb6..bbed3a26ce5 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -499,11 +499,6 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
- set_fs(USER_DS);
- regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
-
#if DEBUG_SIG
printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
current->comm, current->pid, frame, regs->ip, frame->pretcode);
@@ -599,11 +594,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
- set_fs(USER_DS);
- regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
-
#if DEBUG_SIG
printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
current->comm, current->pid, frame, regs->ip, frame->pretcode);
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index ae7158bce4d..b5e329da166 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -430,7 +430,7 @@ ia32_sys_call_table:
.quad sys_setuid16
.quad sys_getuid16
.quad compat_sys_stime /* stime */ /* 25 */
- .quad sys32_ptrace /* ptrace */
+ .quad compat_sys_ptrace /* ptrace */
.quad sys_alarm
.quad sys_fstat /* (old)fstat */
.quad sys_pause
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 90e092d0af0..fa19c381954 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -80,6 +80,8 @@ obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
obj-$(CONFIG_VMI) += vmi_32.o vmiclock_32.o
+obj-$(CONFIG_KVM_GUEST) += kvm.o
+obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
ifdef CONFIG_INPUT_PCSPKR
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 057ccf1d5ad..977ed5cdeaa 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -697,10 +697,6 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
#define HPET_RESOURCE_NAME_SIZE 9
hpet_res = alloc_bootmem(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE);
- if (!hpet_res)
- return 0;
-
- memset(hpet_res, 0, sizeof(*hpet_res));
hpet_res->name = (void *)&hpet_res[1];
hpet_res->flags = IORESOURCE_MEM;
snprintf((char *)hpet_res->name, HPET_RESOURCE_NAME_SIZE, "HPET %u",
diff --git a/arch/x86/kernel/acpi/realmode/.gitignore b/arch/x86/kernel/acpi/realmode/.gitignore
new file mode 100644
index 00000000000..58f1f48a58f
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/.gitignore
@@ -0,0 +1,3 @@
+wakeup.bin
+wakeup.elf
+wakeup.lds
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index df4099dc1c6..65c7857a90d 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -511,31 +511,30 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
unsigned long flags;
char *vaddr;
int nr_pages = 2;
+ struct page *pages[2];
+ int i;
- BUG_ON(len > sizeof(long));
- BUG_ON((((long)addr + len - 1) & ~(sizeof(long) - 1))
- - ((long)addr & ~(sizeof(long) - 1)));
- if (kernel_text_address((unsigned long)addr)) {
- struct page *pages[2] = { virt_to_page(addr),
- virt_to_page(addr + PAGE_SIZE) };
- if (!pages[1])
- nr_pages = 1;
- vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
- BUG_ON(!vaddr);
- local_irq_save(flags);
- memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
- local_irq_restore(flags);
- vunmap(vaddr);
+ if (!core_kernel_text((unsigned long)addr)) {
+ pages[0] = vmalloc_to_page(addr);
+ pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
} else {
- /*
- * modules are in vmalloc'ed memory, always writable.
- */
- local_irq_save(flags);
- memcpy(addr, opcode, len);
- local_irq_restore(flags);
+ pages[0] = virt_to_page(addr);
+ WARN_ON(!PageReserved(pages[0]));
+ pages[1] = virt_to_page(addr + PAGE_SIZE);
}
+ BUG_ON(!pages[0]);
+ if (!pages[1])
+ nr_pages = 1;
+ vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+ BUG_ON(!vaddr);
+ local_irq_save(flags);
+ memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
+ local_irq_restore(flags);
+ vunmap(vaddr);
sync_core();
/* Could also do a CLFLUSH here to speed up CPU recovery; but
that causes hangs on some VIA CPUs. */
+ for (i = 0; i < len; i++)
+ BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
return addr;
}
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 8317401170b..4b99b1bdeb6 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -451,7 +451,8 @@ void __init setup_boot_APIC_clock(void)
}
/* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS, 32);
+ lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
+ lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
lapic_clockevent.min_delta_ns =
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index bf83157337e..5910020c3f2 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -360,7 +360,8 @@ static void __init calibrate_APIC_clock(void)
result / 1000 / 1000, result / 1000 % 1000);
/* Calculate the scaled math multiplication factor */
- lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC, 32);
+ lapic_clockevent.mult = div_sc(result, NSEC_PER_SEC,
+ lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
lapic_clockevent.min_delta_ns =
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index f0030a0999c..e4ea362e848 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -904,6 +904,7 @@ recalc:
original_pm_idle();
else
default_idle();
+ local_irq_disable();
jiffies_since_last_check = jiffies - last_jiffies;
if (jiffies_since_last_check > idle_period)
goto recalc;
@@ -911,6 +912,8 @@ recalc:
if (apm_idle_done)
apm_do_busy();
+
+ local_irq_enable();
}
/**
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index ee7c45235e5..a0c6f819088 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -11,7 +11,6 @@ obj-$(CONFIG_X86_32) += cyrix.o
obj-$(CONFIG_X86_32) += centaur.o
obj-$(CONFIG_X86_32) += transmeta.o
obj-$(CONFIG_X86_32) += intel.o
-obj-$(CONFIG_X86_32) += nexgen.o
obj-$(CONFIG_X86_32) += umc.o
obj-$(CONFIG_X86_MCE) += mcheck/
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0173065dc3b..24586682829 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -343,10 +343,4 @@ static struct cpu_dev amd_cpu_dev __cpuinitdata = {
.c_size_cache = amd_size_cache,
};
-int __init amd_init_cpu(void)
-{
- cpu_devs[X86_VENDOR_AMD] = &amd_cpu_dev;
- return 0;
-}
-
cpu_vendor_dev_register(X86_VENDOR_AMD, &amd_cpu_dev);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index e2d870de837..8db8f73503b 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -339,6 +339,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
unsigned int freq;
+ unsigned int cached_freq;
dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
@@ -347,7 +348,16 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
return 0;
}
+ cached_freq = data->freq_table[data->acpi_data->state].frequency;
freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+ if (freq != cached_freq) {
+ /*
+ * The dreaded BIOS frequency change behind our back.
+ * Force set the frequency on next target call.
+ */
+ data->resume = 1;
+ }
+
dprintk("cur freq = %u\n", freq);
return freq;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 9a699ed0359..e07e8c068ae 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -49,7 +49,7 @@ static int banks;
static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
static unsigned long notify_user;
static int rip_msr;
-static int mce_bootlog = 1;
+static int mce_bootlog = -1;
static atomic_t mce_events;
static char trigger[128];
@@ -471,13 +471,15 @@ static void mce_init(void *dummy)
static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
{
/* This should be disabled by the BIOS, but isn't always */
- if (c->x86_vendor == X86_VENDOR_AMD && c->x86 == 15) {
- /* disable GART TBL walk error reporting, which trips off
- incorrectly with the IOMMU & 3ware & Cerberus. */
- clear_bit(10, &bank[4]);
- /* Lots of broken BIOS around that don't clear them
- by default and leave crap in there. Don't log. */
- mce_bootlog = 0;
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ if(c->x86 == 15)
+ /* disable GART TBL walk error reporting, which trips off
+ incorrectly with the IOMMU & 3ware & Cerberus. */
+ clear_bit(10, &bank[4]);
+ if(c->x86 <= 17 && mce_bootlog < 0)
+ /* Lots of broken BIOS around that don't clear them
+ by default and leave crap in there. Don't log. */
+ mce_bootlog = 0;
}
}
diff --git a/arch/x86/kernel/cpu/nexgen.c b/arch/x86/kernel/cpu/nexgen.c
deleted file mode 100644
index 5d5e1c13412..00000000000
--- a/arch/x86/kernel/cpu/nexgen.c
+++ /dev/null
@@ -1,59 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <asm/processor.h>
-
-#include "cpu.h"
-
-/*
- * Detect a NexGen CPU running without BIOS hypercode new enough
- * to have CPUID. (Thanks to Herbert Oppmann)
- */
-
-static int __cpuinit deep_magic_nexgen_probe(void)
-{
- int ret;
-
- __asm__ __volatile__ (
- " movw $0x5555, %%ax\n"
- " xorw %%dx,%%dx\n"
- " movw $2, %%cx\n"
- " divw %%cx\n"
- " movl $0, %%eax\n"
- " jnz 1f\n"
- " movl $1, %%eax\n"
- "1:\n"
- : "=a" (ret) : : "cx", "dx");
- return ret;
-}
-
-static void __cpuinit init_nexgen(struct cpuinfo_x86 *c)
-{
- c->x86_cache_size = 256; /* A few had 1 MB... */
-}
-
-static void __cpuinit nexgen_identify(struct cpuinfo_x86 *c)
-{
- /* Detect NexGen with old hypercode */
- if (deep_magic_nexgen_probe())
- strcpy(c->x86_vendor_id, "NexGenDriven");
-}
-
-static struct cpu_dev nexgen_cpu_dev __cpuinitdata = {
- .c_vendor = "Nexgen",
- .c_ident = { "NexGenDriven" },
- .c_models = {
- { .vendor = X86_VENDOR_NEXGEN,
- .family = 5,
- .model_names = { [1] = "Nx586" }
- },
- },
- .c_init = init_nexgen,
- .c_identify = nexgen_identify,
-};
-
-int __init nexgen_init_cpu(void)
-{
- cpu_devs[X86_VENDOR_NEXGEN] = &nexgen_cpu_dev;
- return 0;
-}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index b943e10ad81..f9ae93adffe 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -614,16 +614,6 @@ static struct wd_ops intel_arch_wd_ops __read_mostly = {
.evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
};
-static struct wd_ops coreduo_wd_ops = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_intel_arch_watchdog,
- .rearm = p6_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_ARCH_PERFMON_PERFCTR0,
- .evntsel = MSR_ARCH_PERFMON_EVENTSEL0,
-};
-
static void probe_nmi_watchdog(void)
{
switch (boot_cpu_data.x86_vendor) {
@@ -637,8 +627,8 @@ static void probe_nmi_watchdog(void)
/* Work around Core Duo (Yonah) errata AE49 where perfctr1
doesn't have a working enable bit. */
if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) {
- wd_ops = &coreduo_wd_ops;
- break;
+ intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
+ intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
}
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
wd_ops = &intel_arch_wd_ops;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 2251d0ae957..26855381790 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -25,6 +25,7 @@
#include <asm/hpet.h>
#include <linux/kdebug.h>
#include <asm/smp.h>
+#include <asm/reboot.h>
#include <mach_ipi.h>
@@ -117,7 +118,7 @@ static void nmi_shootdown_cpus(void)
}
#endif
-void machine_crash_shutdown(struct pt_regs *regs)
+void native_machine_crash_shutdown(struct pt_regs *regs)
{
/* This function is only called after the system
* has panicked or is otherwise in a critical state.
diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c
index cbd42e51cb0..645ee5e32a2 100644
--- a/arch/x86/kernel/e820_64.c
+++ b/arch/x86/kernel/e820_64.c
@@ -84,14 +84,41 @@ void __init reserve_early(unsigned long start, unsigned long end, char *name)
strncpy(r->name, name, sizeof(r->name) - 1);
}
-void __init early_res_to_bootmem(void)
+void __init free_early(unsigned long start, unsigned long end)
+{
+ struct early_res *r;
+ int i, j;
+
+ for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
+ r = &early_res[i];
+ if (start == r->start && end == r->end)
+ break;
+ }
+ if (i >= MAX_EARLY_RES || !early_res[i].end)
+ panic("free_early on not reserved area: %lx-%lx!", start, end);
+
+ for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
+ ;
+
+ memcpy(&early_res[i], &early_res[i + 1],
+ (j - 1 - i) * sizeof(struct early_res));
+
+ early_res[j - 1].end = 0;
+}
+
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
{
int i;
+ unsigned long final_start, final_end;
for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
struct early_res *r = &early_res[i];
- printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
- r->start, r->end - 1, r->name);
- reserve_bootmem_generic(r->start, r->end - r->start);
+ final_start = max(start, r->start);
+ final_end = min(end, r->end);
+ if (final_start >= final_end)
+ continue;
+ printk(KERN_INFO " early res: %d [%lx-%lx] %s\n", i,
+ final_start, final_end - 1, r->name);
+ reserve_bootmem_generic(final_start, final_end - final_start);
}
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index f0f8934fc30..2a609dc3271 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -409,7 +409,7 @@ restore_nocheck_notrace:
irq_return:
INTERRUPT_RETURN
.section .fixup,"ax"
-iret_exc:
+ENTRY(iret_exc)
pushl $0 # no error code
pushl $do_iret_error
jmp error_code
@@ -1017,6 +1017,13 @@ ENTRY(kernel_thread_helper)
ENDPROC(kernel_thread_helper)
#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 */
+ jmp sysenter_past_esp
+
ENTRY(xen_hypervisor_callback)
CFI_STARTPROC
pushl $0
@@ -1035,8 +1042,9 @@ ENTRY(xen_hypervisor_callback)
cmpl $xen_iret_end_crit,%eax
jae 1f
- call xen_iret_crit_fixup
+ jmp xen_iret_crit_fixup
+ENTRY(xen_do_upcall)
1: mov %esp, %eax
call xen_evtchn_do_upcall
jmp ret_from_intr
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 9546ef408b9..021624c8358 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -51,7 +51,7 @@ void __init setup_apic_routing(void)
else
#endif
- if (cpus_weight(cpu_possible_map) <= 8)
+ if (num_possible_cpus() <= 8)
genapic = &apic_flat;
else
genapic = &apic_physflat;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 993c7677325..e25c57b8aa8 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -11,6 +11,7 @@
#include <linux/string.h>
#include <linux/percpu.h>
#include <linux/start_kernel.h>
+#include <linux/io.h>
#include <asm/processor.h>
#include <asm/proto.h>
@@ -22,6 +23,7 @@
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/e820.h>
+#include <asm/bios_ebda.h>
static void __init zap_identity_mappings(void)
{
@@ -49,7 +51,6 @@ static void __init copy_bootdata(char *real_mode_data)
}
}
-#define BIOS_EBDA_SEGMENT 0x40E
#define BIOS_LOWMEM_KILOBYTES 0x413
/*
@@ -80,8 +81,7 @@ static void __init reserve_ebda_region(void)
lowmem <<= 10;
/* start of EBDA area */
- ebda_addr = *(unsigned short *)__va(BIOS_EBDA_SEGMENT);
- ebda_addr <<= 4;
+ ebda_addr = get_bios_ebda();
/* Fixup: bios puts an EBDA in the top 64K segment */
/* of conventional memory, but does not adjust lowmem. */
@@ -101,6 +101,24 @@ static void __init reserve_ebda_region(void)
reserve_early(lowmem, 0x100000, "BIOS reserved");
}
+static void __init reserve_setup_data(void)
+{
+ struct setup_data *data;
+ unsigned long pa_data;
+ char buf[32];
+
+ if (boot_params.hdr.version < 0x0209)
+ return;
+ pa_data = boot_params.hdr.setup_data;
+ while (pa_data) {
+ data = early_ioremap(pa_data, sizeof(*data));
+ sprintf(buf, "setup data %x", data->type);
+ reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+ pa_data = data->next;
+ early_iounmap(data, sizeof(*data));
+ }
+}
+
void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
@@ -157,6 +175,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
#endif
reserve_ebda_region();
+ reserve_setup_data();
/*
* At this point everything still needed from the boot loader
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 36652ea1a26..9007f9ea64e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -218,7 +218,7 @@ static void hpet_legacy_clockevent_register(void)
hpet_freq = 1000000000000000ULL;
do_div(hpet_freq, hpet_period);
hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
- NSEC_PER_SEC, 32);
+ NSEC_PER_SEC, hpet_clockevent.shift);
/* Calculate the min / max delta */
hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
&hpet_clockevent);
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 8540abe86ad..c1b5e3ece1f 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -115,7 +115,8 @@ void __init setup_pit_timer(void)
* IO_APIC has been initialized.
*/
pit_clockevent.cpumask = cpumask_of_cpu(smp_processor_id());
- pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, 32);
+ pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC,
+ pit_clockevent.shift);
pit_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFF, &pit_clockevent);
pit_clockevent.min_delta_ns =
@@ -224,7 +225,8 @@ static int __init init_pit_clocksource(void)
pit_clockevent.mode != CLOCK_EVT_MODE_PERIODIC)
return 0;
- clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20);
+ clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE,
+ clocksource_pit.shift);
return clocksource_register(&clocksource_pit);
}
arch_initcall(init_pit_clocksource);
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 2e2f42074e1..a40d54fc1fd 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -2068,7 +2068,7 @@ static void __init setup_nmi(void)
* cycles as some i82489DX-based boards have glue logic that keeps the
* 8259A interrupt line asserted until INTA. --macro
*/
-static inline void unlock_ExtINT_logic(void)
+static inline void __init unlock_ExtINT_logic(void)
{
int apic, pin, i;
struct IO_APIC_route_entry entry0, entry1;
@@ -2444,6 +2444,7 @@ void destroy_irq(unsigned int irq)
dynamic_irq_cleanup(irq);
spin_lock_irqsave(&vector_lock, flags);
+ clear_bit(irq_vector[irq], used_vectors);
irq_vector[irq] = 0;
spin_unlock_irqrestore(&vector_lock, flags);
}
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 9ba11d07920..ef1a8dfcc52 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1599,7 +1599,7 @@ static void __init setup_nmi(void)
* cycles as some i82489DX-based boards have glue logic that keeps the
* 8259A interrupt line asserted until INTA. --macro
*/
-static inline void unlock_ExtINT_logic(void)
+static inline void __init unlock_ExtINT_logic(void)
{
int apic, pin, i;
struct IO_APIC_route_entry entry0, entry1;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 6ea67b76a21..00bda7bcda6 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -134,7 +134,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
: "=a" (arg1), "=d" (arg2), "=b" (bx)
: "0" (irq), "1" (desc), "2" (isp),
"D" (desc->handle_irq)
- : "memory", "cc"
+ : "memory", "cc", "ecx"
);
} else
#endif
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 73354302fda..c0320599171 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -6,23 +6,171 @@
*
* This file is released under the GPLv2.
*/
-
#include <linux/debugfs.h>
+#include <linux/uaccess.h>
#include <linux/stat.h>
#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/mm.h>
#include <asm/setup.h>
#ifdef CONFIG_DEBUG_BOOT_PARAMS
+struct setup_data_node {
+ u64 paddr;
+ u32 type;
+ u32 len;
+};
+
+static ssize_t
+setup_data_read(struct file *file, char __user *user_buf, size_t count,
+ loff_t *ppos)
+{
+ struct setup_data_node *node = file->private_data;
+ unsigned long remain;
+ loff_t pos = *ppos;
+ struct page *pg;
+ void *p;
+ u64 pa;
+
+ if (pos < 0)
+ return -EINVAL;
+ if (pos >= node->len)
+ return 0;
+
+ if (count > node->len - pos)
+ count = node->len - pos;
+ pa = node->paddr + sizeof(struct setup_data) + pos;
+ pg = pfn_to_page((pa + count - 1) >> PAGE_SHIFT);
+ if (PageHighMem(pg)) {
+ p = ioremap_cache(pa, count);
+ if (!p)
+ return -ENXIO;
+ } else {
+ p = __va(pa);
+ }
+
+ remain = copy_to_user(user_buf, p, count);
+
+ if (PageHighMem(pg))
+ iounmap(p);
+
+ if (remain)
+ return -EFAULT;
+
+ *ppos = pos + count;
+
+ return count;
+}
+
+static int setup_data_open(struct inode *inode, struct file *file)
+{
+ file->private_data = inode->i_private;
+ return 0;
+}
+
+static const struct file_operations fops_setup_data = {
+ .read = setup_data_read,
+ .open = setup_data_open,
+};
+
+static int __init
+create_setup_data_node(struct dentry *parent, int no,
+ struct setup_data_node *node)
+{
+ struct dentry *d, *type, *data;
+ char buf[16];
+ int error;
+
+ sprintf(buf, "%d", no);
+ d = debugfs_create_dir(buf, parent);
+ if (!d) {
+ error = -ENOMEM;
+ goto err_return;
+ }
+ type = debugfs_create_x32("type", S_IRUGO, d, &node->type);
+ if (!type) {
+ error = -ENOMEM;
+ goto err_dir;
+ }
+ data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
+ if (!data) {
+ error = -ENOMEM;
+ goto err_type;
+ }
+ return 0;
+
+err_type:
+ debugfs_remove(type);
+err_dir:
+ debugfs_remove(d);
+err_return:
+ return error;
+}
+
+static int __init create_setup_data_nodes(struct dentry *parent)
+{
+ struct setup_data_node *node;
+ struct setup_data *data;
+ int error, no = 0;
+ struct dentry *d;
+ struct page *pg;
+ u64 pa_data;
+
+ d = debugfs_create_dir("setup_data", parent);
+ if (!d) {
+ error = -ENOMEM;
+ goto err_return;
+ }
+
+ pa_data = boot_params.hdr.setup_data;
+
+ while (pa_data) {
+ node = kmalloc(sizeof(*node), GFP_KERNEL);
+ if (!node) {
+ error = -ENOMEM;
+ goto err_dir;
+ }
+ pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT);
+ if (PageHighMem(pg)) {
+ data = ioremap_cache(pa_data, sizeof(*data));
+ if (!data) {
+ error = -ENXIO;
+ goto err_dir;
+ }
+ } else {
+ data = __va(pa_data);
+ }
+
+ node->paddr = pa_data;
+ node->type = data->type;
+ node->len = data->len;
+ error = create_setup_data_node(d, no, node);
+ pa_data = data->next;
+
+ if (PageHighMem(pg))
+ iounmap(data);
+ if (error)
+ goto err_dir;
+ no++;
+ }
+ return 0;
+
+err_dir:
+ debugfs_remove(d);
+err_return:
+ return error;
+}
+
static struct debugfs_blob_wrapper boot_params_blob = {
- .data = &boot_params,
- .size = sizeof(boot_params),
+ .data = &boot_params,
+ .size = sizeof(boot_params),
};
static int __init boot_params_kdebugfs_init(void)
{
- int error;
struct dentry *dbp, *version, *data;
+ int error;
dbp = debugfs_create_dir("boot_params", NULL);
if (!dbp) {
@@ -41,7 +189,13 @@ static int __init boot_params_kdebugfs_init(void)
error = -ENOMEM;
goto err_version;
}
+ error = create_setup_data_nodes(dbp);
+ if (error)
+ goto err_data;
return 0;
+
+err_data:
+ debugfs_remove(data);
err_version:
debugfs_remove(version);
err_dir:
@@ -61,5 +215,4 @@ static int __init arch_kdebugfs_init(void)
return error;
}
-
arch_initcall(arch_kdebugfs_init);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
new file mode 100644
index 00000000000..8b7a3cf37d2
--- /dev/null
+++ b/arch/x86/kernel/kvm.c
@@ -0,0 +1,248 @@
+/*
+ * KVM paravirt_ops implementation
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ * Copyright IBM Corporation, 2007
+ * Authors: Anthony Liguori <aliguori@us.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kvm_para.h>
+#include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/hardirq.h>
+
+#define MMU_QUEUE_SIZE 1024
+
+struct kvm_para_state {
+ u8 mmu_queue[MMU_QUEUE_SIZE];
+ int mmu_queue_len;
+ enum paravirt_lazy_mode mode;
+};
+
+static DEFINE_PER_CPU(struct kvm_para_state, para_state);
+
+static struct kvm_para_state *kvm_para_state(void)
+{
+ return &per_cpu(para_state, raw_smp_processor_id());
+}
+
+/*
+ * No need for any "IO delay" on KVM
+ */
+static void kvm_io_delay(void)
+{
+}
+
+static void kvm_mmu_op(void *buffer, unsigned len)
+{
+ int r;
+ unsigned long a1, a2;
+
+ do {
+ a1 = __pa(buffer);
+ a2 = 0; /* on i386 __pa() always returns <4G */
+ r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
+ buffer += r;
+ len -= r;
+ } while (len);
+}
+
+static void mmu_queue_flush(struct kvm_para_state *state)
+{
+ if (state->mmu_queue_len) {
+ kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
+ state->mmu_queue_len = 0;
+ }
+}
+
+static void kvm_deferred_mmu_op(void *buffer, int len)
+{
+ struct kvm_para_state *state = kvm_para_state();
+
+ if (state->mode != PARAVIRT_LAZY_MMU) {
+ kvm_mmu_op(buffer, len);
+ return;
+ }
+ if (state->mmu_queue_len + len > sizeof state->mmu_queue)
+ mmu_queue_flush(state);
+ memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
+ state->mmu_queue_len += len;
+}
+
+static void kvm_mmu_write(void *dest, u64 val)
+{
+ __u64 pte_phys;
+ struct kvm_mmu_op_write_pte wpte;
+
+#ifdef CONFIG_HIGHPTE
+ struct page *page;
+ unsigned long dst = (unsigned long) dest;
+
+ page = kmap_atomic_to_page(dest);
+ pte_phys = page_to_pfn(page);
+ pte_phys <<= PAGE_SHIFT;
+ pte_phys += (dst & ~(PAGE_MASK));
+#else
+ pte_phys = (unsigned long)__pa(dest);
+#endif
+ wpte.header.op = KVM_MMU_OP_WRITE_PTE;
+ wpte.pte_val = val;
+ wpte.pte_phys = pte_phys;
+
+ kvm_deferred_mmu_op(&wpte, sizeof wpte);
+}
+
+/*
+ * We only need to hook operations that are MMU writes. We hook these so that
+ * we can use lazy MMU mode to batch these operations. We could probably
+ * improve the performance of the host code if we used some of the information
+ * here to simplify processing of batched writes.
+ */
+static void kvm_set_pte(pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+ kvm_mmu_write(pmdp, pmd_val(pmd));
+}
+
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ kvm_mmu_write(ptep, pte_val(pte));
+}
+
+static void kvm_pte_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ kvm_mmu_write(ptep, 0);
+}
+
+static void kvm_pmd_clear(pmd_t *pmdp)
+{
+ kvm_mmu_write(pmdp, 0);
+}
+#endif
+
+static void kvm_set_pud(pud_t *pudp, pud_t pud)
+{
+ kvm_mmu_write(pudp, pud_val(pud));
+}
+
+#if PAGETABLE_LEVELS == 4
+static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ kvm_mmu_write(pgdp, pgd_val(pgd));
+}
+#endif
+#endif /* PAGETABLE_LEVELS >= 3 */
+
+static void kvm_flush_tlb(void)
+{
+ struct kvm_mmu_op_flush_tlb ftlb = {
+ .header.op = KVM_MMU_OP_FLUSH_TLB,
+ };
+
+ kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
+}
+
+static void kvm_release_pt(u32 pfn)
+{
+ struct kvm_mmu_op_release_pt rpt = {
+ .header.op = KVM_MMU_OP_RELEASE_PT,
+ .pt_phys = (u64)pfn << PAGE_SHIFT,
+ };
+
+ kvm_mmu_op(&rpt, sizeof rpt);
+}
+
+static void kvm_enter_lazy_mmu(void)
+{
+ struct kvm_para_state *state = kvm_para_state();
+
+ paravirt_enter_lazy_mmu();
+ state->mode = paravirt_get_lazy_mode();
+}
+
+static void kvm_leave_lazy_mmu(void)
+{
+ struct kvm_para_state *state = kvm_para_state();
+
+ mmu_queue_flush(state);
+ paravirt_leave_lazy(paravirt_get_lazy_mode());
+ state->mode = paravirt_get_lazy_mode();
+}
+
+static void paravirt_ops_setup(void)
+{
+ pv_info.name = "KVM";
+ pv_info.paravirt_enabled = 1;
+
+ if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
+ pv_cpu_ops.io_delay = kvm_io_delay;
+
+ if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
+ pv_mmu_ops.set_pte = kvm_set_pte;
+ pv_mmu_ops.set_pte_at = kvm_set_pte_at;
+ pv_mmu_ops.set_pmd = kvm_set_pmd;
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+ pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
+ pv_mmu_ops.set_pte_present = kvm_set_pte_present;
+ pv_mmu_ops.pte_clear = kvm_pte_clear;
+ pv_mmu_ops.pmd_clear = kvm_pmd_clear;
+#endif
+ pv_mmu_ops.set_pud = kvm_set_pud;
+#if PAGETABLE_LEVELS == 4
+ pv_mmu_ops.set_pgd = kvm_set_pgd;
+#endif
+#endif
+ pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
+ pv_mmu_ops.release_pte = kvm_release_pt;
+ pv_mmu_ops.release_pmd = kvm_release_pt;
+ pv_mmu_ops.release_pud = kvm_release_pt;
+
+ pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
+ pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
+ }
+}
+
+void __init kvm_guest_init(void)
+{
+ if (!kvm_para_available())
+ return;
+
+ paravirt_ops_setup();
+}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
new file mode 100644
index 00000000000..ddee04043ae
--- /dev/null
+++ b/arch/x86/kernel/kvmclock.c
@@ -0,0 +1,187 @@
+/* KVM paravirtual clock driver. A clocksource implementation
+ Copyright (C) 2008 Glauber de Oliveira Costa, Red Hat Inc.
+
+ 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+*/
+
+#include <linux/clocksource.h>
+#include <linux/kvm_para.h>
+#include <asm/arch_hooks.h>
+#include <asm/msr.h>
+#include <asm/apic.h>
+#include <linux/percpu.h>
+#include <asm/reboot.h>
+
+#define KVM_SCALE 22
+
+static int kvmclock = 1;
+
+static int parse_no_kvmclock(char *arg)
+{
+ kvmclock = 0;
+ return 0;
+}
+early_param("no-kvmclock", parse_no_kvmclock);
+
+/* The hypervisor will put information about time periodically here */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
+#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+
+static inline u64 kvm_get_delta(u64 last_tsc)
+{
+ int cpu = smp_processor_id();
+ u64 delta = native_read_tsc() - last_tsc;
+ return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
+}
+
+static struct kvm_wall_clock wall_clock;
+static cycle_t kvm_clock_read(void);
+/*
+ * The wallclock is the time of day when we booted. Since then, some time may
+ * have elapsed since the hypervisor wrote the data. So we try to account for
+ * that with system time
+ */
+unsigned long kvm_get_wallclock(void)
+{
+ u32 wc_sec, wc_nsec;
+ u64 delta;
+ struct timespec ts;
+ int version, nsec;
+ int low, high;
+
+ low = (int)__pa(&wall_clock);
+ high = ((u64)__pa(&wall_clock) >> 32);
+
+ delta = kvm_clock_read();
+
+ native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+ do {
+ version = wall_clock.wc_version;
+ rmb();
+ wc_sec = wall_clock.wc_sec;
+ wc_nsec = wall_clock.wc_nsec;
+ rmb();
+ } while ((wall_clock.wc_version != version) || (version & 1));
+
+ delta = kvm_clock_read() - delta;
+ delta += wc_nsec;
+ nsec = do_div(delta, NSEC_PER_SEC);
+ set_normalized_timespec(&ts, wc_sec + delta, nsec);
+ /*
+ * Of all mechanisms of time adjustment I've tested, this one
+ * was the champion!
+ */
+ return ts.tv_sec + 1;
+}
+
+int kvm_set_wallclock(unsigned long now)
+{
+ return 0;
+}
+
+/*
+ * This is our read_clock function. The host puts an tsc timestamp each time
+ * it updates a new time. Without the tsc adjustment, we can have a situation
+ * in which a vcpu starts to run earlier (smaller system_time), but probes
+ * time later (compared to another vcpu), leading to backwards time
+ */
+static cycle_t kvm_clock_read(void)
+{
+ u64 last_tsc, now;
+ int cpu;
+
+ preempt_disable();
+ cpu = smp_processor_id();
+
+ last_tsc = get_clock(cpu, tsc_timestamp);
+ now = get_clock(cpu, system_time);
+
+ now += kvm_get_delta(last_tsc);
+ preempt_enable();
+
+ return now;
+}
+static struct clocksource kvm_clock = {
+ .name = "kvm-clock",
+ .read = kvm_clock_read,
+ .rating = 400,
+ .mask = CLOCKSOURCE_MASK(64),
+ .mult = 1 << KVM_SCALE,
+ .shift = KVM_SCALE,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int kvm_register_clock(void)
+{
+ int cpu = smp_processor_id();
+ int low, high;
+ low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
+ high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
+
+ return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+}
+
+static void kvm_setup_secondary_clock(void)
+{
+ /*
+ * Now that the first cpu already had this clocksource initialized,
+ * we shouldn't fail.
+ */
+ WARN_ON(kvm_register_clock());
+ /* ok, done with our trickery, call native */
+ setup_secondary_APIC_clock();
+}
+
+/*
+ * After the clock is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written. So before any
+ * kind of shutdown from our side, we unregister the clock by writting anything
+ * that does not have the 'enable' bit set in the msr
+ */
+#ifdef CONFIG_KEXEC
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+ native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+ native_machine_crash_shutdown(regs);
+}
+#endif
+
+static void kvm_shutdown(void)
+{
+ native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+ native_machine_shutdown();
+}
+
+void __init kvmclock_init(void)
+{
+ if (!kvm_para_available())
+ return;
+
+ if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
+ if (kvm_register_clock())
+ return;
+ pv_time_ops.get_wallclock = kvm_get_wallclock;
+ pv_time_ops.set_wallclock = kvm_set_wallclock;
+ pv_time_ops.sched_clock = kvm_clock_read;
+ pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+ machine_ops.shutdown = kvm_shutdown;
+#ifdef CONFIG_KEXEC
+ machine_ops.crash_shutdown = kvm_crash_shutdown;
+#endif
+ clocksource_register(&kvm_clock);
+ }
+}
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index b402c0f3f19..3cad17fe026 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -63,7 +63,7 @@ static int __init mfgpt_fix(char *s)
/* The following udocumented bit resets the MFGPT timers */
val = 0xFF; dummy = 0;
- wrmsr(0x5140002B, val, dummy);
+ wrmsr(MSR_MFGPT_SETUP, val, dummy);
return 1;
}
__setup("mfgptfix", mfgpt_fix);
@@ -127,17 +127,17 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable)
* 6; that is, resets for 7 and 8 will be ignored. Is this
* a problem? -dilinger
*/
- msr = MFGPT_NR_MSR;
+ msr = MSR_MFGPT_NR;
mask = 1 << (timer + 24);
break;
case MFGPT_EVENT_NMI:
- msr = MFGPT_NR_MSR;
+ msr = MSR_MFGPT_NR;
mask = 1 << (timer + shift);
break;
case MFGPT_EVENT_IRQ:
- msr = MFGPT_IRQ_MSR;
+ msr = MSR_MFGPT_IRQ;
mask = 1 << (timer + shift);
break;
@@ -364,7 +364,8 @@ int __init mfgpt_timer_setup(void)
geode_mfgpt_write(mfgpt_event_clock, MFGPT_REG_SETUP, val);
/* Set up the clock event */
- mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC, 32);
+ mfgpt_clockevent.mult = div_sc(MFGPT_HZ, NSEC_PER_SEC,
+ mfgpt_clockevent.shift);
mfgpt_clockevent.min_delta_ns = clockevent_delta2ns(0xF,
&mfgpt_clockevent);
mfgpt_clockevent.max_delta_ns = clockevent_delta2ns(0xFFFE,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 70744e344fa..3e2c54dc8b2 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -686,13 +686,11 @@ void __init get_smp_config(void)
static int __init smp_scan_config(unsigned long base, unsigned long length,
unsigned reserve)
{
- extern void __bad_mpf_size(void);
unsigned int *bp = phys_to_virt(base);
struct intel_mp_floating *mpf;
Dprintk("Scan SMP from %p for %ld bytes.\n", bp, length);
- if (sizeof(*mpf) != 16)
- __bad_mpf_size();
+ BUILD_BUG_ON(sizeof(*mpf) != 16);
while (length > 0) {
mpf = (struct intel_mp_floating *)bp;
@@ -801,7 +799,6 @@ void __init find_smp_config(void)
#ifdef CONFIG_X86_IO_APIC
#define MP_ISA_BUS 0
-#define MP_MAX_IOAPIC_PIN 127
extern struct mp_ioapic_routing mp_ioapic_routing[MAX_IO_APICS];
@@ -820,7 +817,7 @@ static int mp_find_ioapic(int gsi)
return -1;
}
-static u8 uniq_ioapic_id(u8 id)
+static u8 __init uniq_ioapic_id(u8 id)
{
#ifdef CONFIG_X86_32
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
@@ -909,14 +906,7 @@ void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi)
intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */
intsrc.mpc_dstirq = pin; /* INTIN# */
- Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n",
- intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
- (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
- intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq);
-
- mp_irqs[mp_irq_entries] = intsrc;
- if (++mp_irq_entries == MAX_IRQ_SOURCES)
- panic("Max # of irq sources exceeded!\n");
+ MP_intsrc_info(&intsrc);
}
int es7000_plat;
@@ -985,23 +975,14 @@ void __init mp_config_acpi_legacy_irqs(void)
intsrc.mpc_srcbusirq = i; /* Identity mapped */
intsrc.mpc_dstirq = i;
- Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, "
- "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3,
- (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus,
- intsrc.mpc_srcbusirq, intsrc.mpc_dstapic,
- intsrc.mpc_dstirq);
-
- mp_irqs[mp_irq_entries] = intsrc;
- if (++mp_irq_entries == MAX_IRQ_SOURCES)
- panic("Max # of irq sources exceeded!\n");
+ MP_intsrc_info(&intsrc);
}
}
int mp_register_gsi(u32 gsi, int triggering, int polarity)
{
- int ioapic = -1;
- int ioapic_pin = 0;
- int idx, bit = 0;
+ int ioapic;
+ int ioapic_pin;
#ifdef CONFIG_X86_32
#define MAX_GSI_NUM 4096
#define IRQ_COMPRESSION_START 64
@@ -1041,15 +1022,13 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
* with redundant pin->gsi mappings (but unique PCI devices);
* we only program the IOAPIC on the first.
*/
- bit = ioapic_pin % 32;
- idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32);
- if (idx > 3) {
+ if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
printk(KERN_ERR "Invalid reference to IOAPIC pin "
"%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
ioapic_pin);
return gsi;
}
- if ((1 << bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) {
+ if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n",
mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
#ifdef CONFIG_X86_32
@@ -1059,7 +1038,7 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
#endif
}
- mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1 << bit);
+ set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
#ifdef CONFIG_X86_32
/*
* For GSI >= 64, use IRQ compression
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 3733412d135..74f0c5ea2a0 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -366,11 +366,13 @@ struct pv_mmu_ops pv_mmu_ops = {
.flush_tlb_single = native_flush_tlb_single,
.flush_tlb_others = native_flush_tlb_others,
- .alloc_pt = paravirt_nop,
- .alloc_pd = paravirt_nop,
- .alloc_pd_clone = paravirt_nop,
- .release_pt = paravirt_nop,
- .release_pd = paravirt_nop,
+ .alloc_pte = paravirt_nop,
+ .alloc_pmd = paravirt_nop,
+ .alloc_pmd_clone = paravirt_nop,
+ .alloc_pud = paravirt_nop,
+ .release_pte = paravirt_nop,
+ .release_pmd = paravirt_nop,
+ .release_pud = paravirt_nop,
.set_pte = native_set_pte,
.set_pte_at = native_set_pte_at,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 2edee22e9c3..e28ec497e14 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -43,6 +43,7 @@
#include <asm/system.h>
#include <asm/dma.h>
#include <asm/rio.h>
+#include <asm/bios_ebda.h>
#ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
int use_calgary __read_mostly = 1;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3004d716539..67e9b4a1e89 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -4,6 +4,8 @@
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/pm.h>
struct kmem_cache *task_xstate_cachep;
@@ -42,3 +44,118 @@ void arch_task_cache_init(void)
__alignof__(union thread_xstate),
SLAB_PANIC, NULL);
}
+
+static void do_nothing(void *unused)
+{
+}
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
+void cpu_idle_wait(void)
+{
+ smp_mb();
+ /* kick all the CPUs so that they exit out of pm_idle */
+ smp_call_function(do_nothing, NULL, 0, 1);
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
+/*
+ * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
+ * which can obviate IPI to trigger checking of need_resched.
+ * We execute MONITOR against need_resched and enter optimized wait state
+ * through MWAIT. Whenever someone changes need_resched, we would be woken
+ * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
+ */
+void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
+{
+ if (!need_resched()) {
+ __monitor((void *)&current_thread_info()->flags, 0, 0);
+ smp_mb();
+ if (!need_resched())
+ __mwait(ax, cx);
+ }
+}
+
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+ if (!need_resched()) {
+ __monitor((void *)&current_thread_info()->flags, 0, 0);
+ smp_mb();
+ if (!need_resched())
+ __sti_mwait(0, 0);
+ else
+ local_irq_enable();
+ } else
+ local_irq_enable();
+}
+
+
+static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
+{
+ if (force_mwait)
+ return 1;
+ /* Any C1 states supported? */
+ return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
+}
+
+/*
+ * On SMP it's slightly faster (but much more power-consuming!)
+ * to poll the ->work.need_resched flag instead of waiting for the
+ * cross-CPU IPI to arrive. Use this option with caution.
+ */
+static void poll_idle(void)
+{
+ local_irq_enable();
+ cpu_relax();
+}
+
+void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+{
+ static int selected;
+
+ if (selected)
+ return;
+#ifdef CONFIG_X86_SMP
+ if (pm_idle == poll_idle && smp_num_siblings > 1) {
+ printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
+ " performance may degrade.\n");
+ }
+#endif
+ if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
+ /*
+ * Skip, if setup has overridden idle.
+ * One CPU supports mwait => All CPUs supports mwait
+ */
+ if (!pm_idle) {
+ printk(KERN_INFO "using mwait in idle threads.\n");
+ pm_idle = mwait_idle;
+ }
+ }
+ selected = 1;
+}
+
+static int __init idle_setup(char *str)
+{
+ if (!strcmp(str, "poll")) {
+ printk("using polling idle threads.\n");
+ pm_idle = poll_idle;
+ } else if (!strcmp(str, "mwait"))
+ force_mwait = 1;
+ else
+ return -1;
+
+ boot_option_idle_override = 1;
+ return 0;
+}
+early_param("idle", idle_setup);
+
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 77de848bd1f..f8476dfbb60 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -111,12 +111,10 @@ void default_idle(void)
*/
smp_mb();
- local_irq_disable();
- if (!need_resched()) {
+ if (!need_resched())
safe_halt(); /* enables interrupts racelessly */
- local_irq_disable();
- }
- local_irq_enable();
+ else
+ local_irq_enable();
current_thread_info()->status |= TS_POLLING;
} else {
local_irq_enable();
@@ -128,17 +126,6 @@ void default_idle(void)
EXPORT_SYMBOL(default_idle);
#endif
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->work.need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
- local_irq_enable();
- cpu_relax();
-}
-
#ifdef CONFIG_HOTPLUG_CPU
#include <asm/nmi.h>
/* We don't actually take CPU down, just spin without interrupts. */
@@ -196,6 +183,7 @@ void cpu_idle(void)
if (cpu_is_offline(cpu))
play_dead();
+ local_irq_disable();
__get_cpu_var(irq_stat).idle_timestamp = jiffies;
idle();
}
@@ -206,104 +194,6 @@ void cpu_idle(void)
}
}
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
- smp_mb();
- /* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
- if (!need_resched()) {
- __monitor((void *)&current_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __sti_mwait(ax, cx);
- else
- local_irq_enable();
- } else
- local_irq_enable();
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
- local_irq_enable();
- mwait_idle_with_hints(0, 0);
-}
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
- if (force_mwait)
- return 1;
- /* Any C1 states supported? */
- return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
- static int selected;
-
- if (selected)
- return;
-#ifdef CONFIG_X86_SMP
- if (pm_idle == poll_idle && smp_num_siblings > 1) {
- printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
- " performance may degrade.\n");
- }
-#endif
- if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
- /*
- * Skip, if setup has overridden idle.
- * One CPU supports mwait => All CPUs supports mwait
- */
- if (!pm_idle) {
- printk(KERN_INFO "using mwait in idle threads.\n");
- pm_idle = mwait_idle;
- }
- }
- selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
- if (!strcmp(str, "poll")) {
- printk("using polling idle threads.\n");
- pm_idle = poll_idle;
- } else if (!strcmp(str, "mwait"))
- force_mwait = 1;
- else
- return -1;
-
- boot_option_idle_override = 1;
- return 0;
-}
-early_param("idle", idle_setup);
-
void __show_registers(struct pt_regs *regs, int all)
{
unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 131c2ee7ac5..e2319f39988 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -106,26 +106,13 @@ void default_idle(void)
* test NEED_RESCHED:
*/
smp_mb();
- local_irq_disable();
- if (!need_resched()) {
+ if (!need_resched())
safe_halt(); /* enables interrupts racelessly */
- local_irq_disable();
- }
- local_irq_enable();
+ else
+ local_irq_enable();
current_thread_info()->status |= TS_POLLING;
}
-/*
- * On SMP it's slightly faster (but much more power-consuming!)
- * to poll the ->need_resched flag instead of waiting for the
- * cross-CPU IPI to arrive. Use this option with caution.
- */
-static void poll_idle(void)
-{
- local_irq_enable();
- cpu_relax();
-}
-
#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);
@@ -192,110 +179,6 @@ void cpu_idle(void)
}
}
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
- smp_mb();
- /* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 0, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
- if (!need_resched()) {
- __monitor((void *)&current_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __mwait(ax, cx);
- }
-}
-
-/* Default MONITOR/MWAIT with no hints, used for default C1 state */
-static void mwait_idle(void)
-{
- if (!need_resched()) {
- __monitor((void *)&current_thread_info()->flags, 0, 0);
- smp_mb();
- if (!need_resched())
- __sti_mwait(0, 0);
- else
- local_irq_enable();
- } else {
- local_irq_enable();
- }
-}
-
-
-static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
-{
- if (force_mwait)
- return 1;
- /* Any C1 states supported? */
- return c->cpuid_level >= 5 && ((cpuid_edx(5) >> 4) & 0xf) > 0;
-}
-
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
-{
- static int selected;
-
- if (selected)
- return;
-#ifdef CONFIG_X86_SMP
- if (pm_idle == poll_idle && smp_num_siblings > 1) {
- printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
- " performance may degrade.\n");
- }
-#endif
- if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
- /*
- * Skip, if setup has overridden idle.
- * One CPU supports mwait => All CPUs supports mwait
- */
- if (!pm_idle) {
- printk(KERN_INFO "using mwait in idle threads.\n");
- pm_idle = mwait_idle;
- }
- }
- selected = 1;
-}
-
-static int __init idle_setup(char *str)
-{
- if (!strcmp(str, "poll")) {
- printk("using polling idle threads.\n");
- pm_idle = poll_idle;
- } else if (!strcmp(str, "mwait"))
- force_mwait = 1;
- else
- return -1;
-
- boot_option_idle_override = 1;
- return 0;
-}
-early_param("idle", idle_setup);
-
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs * regs)
{
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 559c1b02741..fb03ef380f0 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1207,97 +1207,16 @@ static int genregs32_set(struct task_struct *target,
return ret;
}
-static long ptrace32_siginfo(unsigned request, u32 pid, u32 addr, u32 data)
+long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
+ compat_ulong_t caddr, compat_ulong_t cdata)
{
- siginfo_t __user *si = compat_alloc_user_space(sizeof(siginfo_t));
- compat_siginfo_t __user *si32 = compat_ptr(data);
- siginfo_t ssi;
- int ret;
-
- if (request == PTRACE_SETSIGINFO) {
- memset(&ssi, 0, sizeof(siginfo_t));
- ret = copy_siginfo_from_user32(&ssi, si32);
- if (ret)
- return ret;
- if (copy_to_user(si, &ssi, sizeof(siginfo_t)))
- return -EFAULT;
- }
- ret = sys_ptrace(request, pid, addr, (unsigned long)si);
- if (ret)
- return ret;
- if (request == PTRACE_GETSIGINFO) {
- if (copy_from_user(&ssi, si, sizeof(siginfo_t)))
- return -EFAULT;
- ret = copy_siginfo_to_user32(si32, &ssi);
- }
- return ret;
-}
-
-asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
-{
- struct task_struct *child;
- struct pt_regs *childregs;
+ unsigned long addr = caddr;
+ unsigned long data = cdata;
void __user *datap = compat_ptr(data);
int ret;
__u32 val;
switch (request) {
- case PTRACE_TRACEME:
- case PTRACE_ATTACH:
- case PTRACE_KILL:
- case PTRACE_CONT:
- case PTRACE_SINGLESTEP:
- case PTRACE_SINGLEBLOCK:
- case PTRACE_DETACH:
- case PTRACE_SYSCALL:
- case PTRACE_OLDSETOPTIONS:
- case PTRACE_SETOPTIONS:
- case PTRACE_SET_THREAD_AREA:
- case PTRACE_GET_THREAD_AREA:
-#ifdef X86_BTS
- case PTRACE_BTS_CONFIG:
- case PTRACE_BTS_STATUS:
- case PTRACE_BTS_SIZE:
- case PTRACE_BTS_GET:
- case PTRACE_BTS_CLEAR:
- case PTRACE_BTS_DRAIN:
-#endif
- return sys_ptrace(request, pid, addr, data);
-
- default:
- return -EINVAL;
-
- case PTRACE_PEEKTEXT:
- case PTRACE_PEEKDATA:
- case PTRACE_POKEDATA:
- case PTRACE_POKETEXT:
- case PTRACE_POKEUSR:
- case PTRACE_PEEKUSR:
- case PTRACE_GETREGS:
- case PTRACE_SETREGS:
- case PTRACE_SETFPREGS:
- case PTRACE_GETFPREGS:
- case PTRACE_SETFPXREGS:
- case PTRACE_GETFPXREGS:
- case PTRACE_GETEVENTMSG:
- break;
-
- case PTRACE_SETSIGINFO:
- case PTRACE_GETSIGINFO:
- return ptrace32_siginfo(request, pid, addr, data);
- }
-
- child = ptrace_get_task_struct(pid);
- if (IS_ERR(child))
- return PTR_ERR(child);
-
- ret = ptrace_check_attach(child, request == PTRACE_KILL);
- if (ret < 0)
- goto out;
-
- childregs = task_pt_regs(child);
-
- switch (request) {
case PTRACE_PEEKUSR:
ret = getreg32(child, addr, &val);
if (ret == 0)
@@ -1343,12 +1262,14 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
sizeof(struct user32_fxsr_struct),
datap);
+ case PTRACE_GET_THREAD_AREA:
+ case PTRACE_SET_THREAD_AREA:
+ return arch_ptrace(child, request, addr, data);
+
default:
return compat_ptrace_request(child, request, addr, data);
}
- out:
- put_task_struct(child);
return ret;
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 19c9386ac11..a4a838306b2 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -8,6 +8,7 @@
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
+#include <asm/pgtable.h>
#include <asm/reboot_fixups.h>
#include <asm/reboot.h>
@@ -15,7 +16,6 @@
# include <linux/dmi.h>
# include <linux/ctype.h>
# include <linux/mc146818rtc.h>
-# include <asm/pgtable.h>
#else
# include <asm/iommu.h>
#endif
@@ -275,7 +275,7 @@ void machine_real_restart(unsigned char *code, int length)
/* Remap the kernel at virtual address zero, as well as offset zero
from the kernel segment. This assumes the kernel segment starts at
virtual address PAGE_OFFSET. */
- memcpy(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
+ memcpy(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
sizeof(swapper_pg_dir [0]) * KERNEL_PGD_PTRS);
/*
@@ -399,7 +399,7 @@ static void native_machine_emergency_restart(void)
}
}
-static void native_machine_shutdown(void)
+void native_machine_shutdown(void)
{
/* Stop the cpus and apics */
#ifdef CONFIG_SMP
@@ -470,7 +470,10 @@ struct machine_ops machine_ops = {
.shutdown = native_machine_shutdown,
.emergency_restart = native_machine_emergency_restart,
.restart = native_machine_restart,
- .halt = native_machine_halt
+ .halt = native_machine_halt,
+#ifdef CONFIG_KEXEC
+ .crash_shutdown = native_machine_crash_shutdown,
+#endif
};
void machine_power_off(void)
@@ -498,3 +501,9 @@ void machine_halt(void)
machine_ops.halt();
}
+#ifdef CONFIG_KEXEC
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+ machine_ops.crash_shutdown(regs);
+}
+#endif
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 455d3c80960..2283422af79 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -47,6 +47,7 @@
#include <linux/pfn.h>
#include <linux/pci.h>
#include <linux/init_ohci1394_dma.h>
+#include <linux/kvm_para.h>
#include <video/edid.h>
@@ -389,7 +390,6 @@ unsigned long __init find_max_low_pfn(void)
return max_low_pfn;
}
-#define BIOS_EBDA_SEGMENT 0x40E
#define BIOS_LOWMEM_KILOBYTES 0x413
/*
@@ -420,8 +420,7 @@ static void __init reserve_ebda_region(void)
lowmem <<= 10;
/* start of EBDA area */
- ebda_addr = *(unsigned short *)__va(BIOS_EBDA_SEGMENT);
- ebda_addr <<= 4;
+ ebda_addr = get_bios_ebda();
/* Fixup: bios puts an EBDA in the top 64K segment */
/* of conventional memory, but does not adjust lowmem. */
@@ -822,6 +821,10 @@ void __init setup_arch(char **cmdline_p)
max_low_pfn = setup_memory();
+#ifdef CONFIG_KVM_CLOCK
+ kvmclock_init();
+#endif
+
#ifdef CONFIG_VMI
/*
* Must be after max_low_pfn is determined, and before kernel
@@ -829,6 +832,7 @@ void __init setup_arch(char **cmdline_p)
*/
vmi_init();
#endif
+ kvm_guest_init();
/*
* NOTE: before this point _nobody_ is allowed to allocate
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index c2ec3dcb6b9..a94fb959a87 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -42,6 +42,7 @@
#include <linux/ctype.h>
#include <linux/uaccess.h>
#include <linux/init_ohci1394_dma.h>
+#include <linux/kvm_para.h>
#include <asm/mtrr.h>
#include <asm/uaccess.h>
@@ -116,7 +117,7 @@ extern int root_mountflags;
char __initdata command_line[COMMAND_LINE_SIZE];
-struct resource standard_io_resources[] = {
+static struct resource standard_io_resources[] = {
{ .name = "dma1", .start = 0x00, .end = 0x1f,
.flags = IORESOURCE_BUSY | IORESOURCE_IO },
{ .name = "pic1", .start = 0x20, .end = 0x21,
@@ -190,6 +191,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
e820_register_active_regions(0, start_pfn, end_pfn);
free_bootmem_with_active_regions(0, end_pfn);
+ early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
}
#endif
@@ -264,6 +266,28 @@ void __attribute__((weak)) __init memory_setup(void)
machine_specific_memory_setup();
}
+static void __init parse_setup_data(void)
+{
+ struct setup_data *data;
+ unsigned long pa_data;
+
+ if (boot_params.hdr.version < 0x0209)
+ return;
+ pa_data = boot_params.hdr.setup_data;
+ while (pa_data) {
+ data = early_ioremap(pa_data, PAGE_SIZE);
+ switch (data->type) {
+ default:
+ break;
+ }
+#ifndef CONFIG_DEBUG_BOOT_PARAMS
+ free_early(pa_data, pa_data+sizeof(*data)+data->len);
+#endif
+ pa_data = data->next;
+ early_iounmap(data, PAGE_SIZE);
+ }
+}
+
/*
* setup_arch - architecture-specific boot-time initializations
*
@@ -316,6 +340,8 @@ void __init setup_arch(char **cmdline_p)
strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
+ parse_setup_data();
+
parse_early_param();
#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
@@ -359,6 +385,10 @@ void __init setup_arch(char **cmdline_p)
io_delay_init();
+#ifdef CONFIG_KVM_CLOCK
+ kvmclock_init();
+#endif
+
#ifdef CONFIG_SMP
/* setup to use the early static init tables during kernel startup */
x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
@@ -397,8 +427,6 @@ void __init setup_arch(char **cmdline_p)
contig_initmem_init(0, end_pfn);
#endif
- early_res_to_bootmem();
-
dma32_reserve_bootmem();
#ifdef CONFIG_ACPI_SLEEP
@@ -465,6 +493,8 @@ void __init setup_arch(char **cmdline_p)
init_apic_mappings();
ioapic_init_mappings();
+ kvm_guest_init();
+
/*
* We trust e820 completely. No explicit ROM probing in memory.
*/
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index f1b11793083..8e05e7f7bd4 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -413,16 +413,6 @@ setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
regs->ss = __USER_DS;
regs->cs = __USER_CS;
- /*
- * Clear TF when entering the signal handler, but
- * notify any tracer that was single-stepping it.
- * The tracer may want to single-step inside the
- * handler too.
- */
- regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
-
return 0;
give_sigsegv:
@@ -501,16 +491,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
regs->ss = __USER_DS;
regs->cs = __USER_CS;
- /*
- * Clear TF when entering the signal handler, but
- * notify any tracer that was single-stepping it.
- * The tracer may want to single-step inside the
- * handler too.
- */
- regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
-
return 0;
give_sigsegv:
@@ -566,6 +546,21 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
if (ret)
return ret;
+ /*
+ * Clear the direction flag as per the ABI for function entry.
+ */
+ regs->flags &= ~X86_EFLAGS_DF;
+
+ /*
+ * Clear TF when entering the signal handler, but
+ * notify any tracer that was single-stepping it.
+ * The tracer may want to single-step inside the
+ * handler too.
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
+ if (test_thread_flag(TIF_SINGLESTEP))
+ ptrace_notify(SIGTRAP);
+
spin_lock_irq(&current->sighand->siglock);
sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 827179c5b32..ccb2a4560c2 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -285,14 +285,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
even if the handler happens to be interrupting 32-bit code. */
regs->cs = __USER_CS;
- /* This, by contrast, has nothing to do with segment registers -
- see include/asm-x86_64/uaccess.h for details. */
- set_fs(USER_DS);
-
- regs->flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_DF);
- if (test_thread_flag(TIF_SINGLESTEP))
- ptrace_notify(SIGTRAP);
-
return 0;
give_sigsegv:
@@ -380,6 +372,28 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
ret = setup_rt_frame(sig, ka, info, oldset, regs);
if (ret == 0) {
+ /*
+ * This has nothing to do with segment registers,
+ * despite the name. This magic affects uaccess.h
+ * macros' behavior. Reset it to the normal setting.
+ */
+ set_fs(USER_DS);
+
+ /*
+ * Clear the direction flag as per the ABI for function entry.
+ */
+ regs->flags &= ~X86_EFLAGS_DF;
+
+ /*
+ * Clear TF when entering the signal handler, but
+ * notify any tracer that was single-stepping it.
+ * The tracer may want to single-step inside the
+ * handler too.
+ */
+ regs->flags &= ~X86_EFLAGS_TF;
+ if (test_thread_flag(TIF_SINGLESTEP))
+ ptrace_notify(SIGTRAP);
+
spin_lock_irq(&current->sighand->siglock);
sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ade371f9663..04c662ba18f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1039,8 +1039,8 @@ int __cpuinit native_cpu_up(unsigned int cpu)
#ifdef CONFIG_X86_32
/* init low mem mapping */
- clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
- min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS));
+ clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
flush_tlb_all();
#endif
@@ -1058,7 +1058,7 @@ int __cpuinit native_cpu_up(unsigned int cpu)
check_tsc_sync_source(cpu);
local_irq_restore(flags);
- while (!cpu_isset(cpu, cpu_online_map)) {
+ while (!cpu_online(cpu)) {
cpu_relax();
touch_nmi_watchdog();
}
@@ -1168,7 +1168,7 @@ static void __init smp_cpu_index_default(void)
int i;
struct cpuinfo_x86 *c;
- for_each_cpu_mask(i, cpu_possible_map) {
+ for_each_possible_cpu(i) {
c = &cpu_data(i);
/* mark all to hotplug */
c->cpu_index = NR_CPUS;
diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c
index 6878a9c2df5..ae751094eba 100644
--- a/arch/x86/kernel/summit_32.c
+++ b/arch/x86/kernel/summit_32.c
@@ -29,6 +29,7 @@
#include <linux/mm.h>
#include <linux/init.h>
#include <asm/io.h>
+#include <asm/bios_ebda.h>
#include <asm/mach-summit/mach_mpparse.h>
static struct rio_table_hdr *rio_table_hdr __initdata;
@@ -140,8 +141,8 @@ void __init setup_summit(void)
int i, next_wpeg, next_bus = 0;
/* The pointer to the EBDA is stored in the word @ phys 0x40E(40:0E) */
- ptr = *(unsigned short *)phys_to_virt(0x40Eul);
- ptr = (unsigned long)phys_to_virt(ptr << 4);
+ ptr = get_bios_ebda();
+ ptr = (unsigned long)phys_to_virt(ptr);
rio_table_hdr = NULL;
offset = 0x180;
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index df224a8774c..a1f07d79320 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -195,9 +195,9 @@ static int __cpuinit init_smp_flush(void)
{
int i;
- for_each_cpu_mask(i, cpu_possible_map) {
+ for_each_possible_cpu(i)
spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);
- }
+
return 0;
}
core_initcall(init_smp_flush);
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
index 64580679861..d8ccc3c6552 100644
--- a/arch/x86/kernel/trampoline_32.S
+++ b/arch/x86/kernel/trampoline_32.S
@@ -33,7 +33,7 @@
/* We can free up trampoline after bootup if cpu hotplug is not supported. */
#ifndef CONFIG_HOTPLUG_CPU
-.section ".init.data","aw",@progbits
+.section ".cpuinit.data","aw",@progbits
#else
.section .rodata,"a",@progbits
#endif
diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c
index 471e694d671..bde6f63e15d 100644
--- a/arch/x86/kernel/traps_32.c
+++ b/arch/x86/kernel/traps_32.c
@@ -602,7 +602,7 @@ DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0, 0)
-DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1)
+DO_ERROR_INFO(32, SIGILL, "iret exception", iret_error, ILL_BADSTK, 0, 1)
void __kprobes do_general_protection(struct pt_regs *regs, long error_code)
{
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 12affe1f9bc..956f38927aa 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -320,7 +320,7 @@ static void check_zeroed_page(u32 pfn, int type, struct page *page)
* pdes need to be zeroed.
*/
if (type & VMI_PAGE_CLONE)
- limit = USER_PTRS_PER_PGD;
+ limit = KERNEL_PGD_BOUNDARY;
for (i = 0; i < limit; i++)
BUG_ON(ptr[i]);
}
@@ -392,13 +392,13 @@ static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)
}
#endif
-static void vmi_allocate_pt(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pte(struct mm_struct *mm, u32 pfn)
{
vmi_set_page_type(pfn, VMI_PAGE_L1);
vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
}
-static void vmi_allocate_pd(struct mm_struct *mm, u32 pfn)
+static void vmi_allocate_pmd(struct mm_struct *mm, u32 pfn)
{
/*
* This call comes in very early, before mem_map is setup.
@@ -409,20 +409,20 @@ static void vmi_allocate_pd(struct mm_struct *mm, u32 pfn)
vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
}
-static void vmi_allocate_pd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count)
+static void vmi_allocate_pmd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count)
{
vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE);
vmi_check_page_type(clonepfn, VMI_PAGE_L2);
vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
}
-static void vmi_release_pt(u32 pfn)
+static void vmi_release_pte(u32 pfn)
{
vmi_ops.release_page(pfn, VMI_PAGE_L1);
vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
}
-static void vmi_release_pd(u32 pfn)
+static void vmi_release_pmd(u32 pfn)
{
vmi_ops.release_page(pfn, VMI_PAGE_L2);
vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
@@ -871,15 +871,15 @@ static inline int __init activate_vmi(void)
vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
if (vmi_ops.allocate_page) {
- pv_mmu_ops.alloc_pt = vmi_allocate_pt;
- pv_mmu_ops.alloc_pd = vmi_allocate_pd;
- pv_mmu_ops.alloc_pd_clone = vmi_allocate_pd_clone;
+ pv_mmu_ops.alloc_pte = vmi_allocate_pte;
+ pv_mmu_ops.alloc_pmd = vmi_allocate_pmd;
+ pv_mmu_ops.alloc_pmd_clone = vmi_allocate_pmd_clone;
}
vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
if (vmi_ops.release_page) {
- pv_mmu_ops.release_pt = vmi_release_pt;
- pv_mmu_ops.release_pd = vmi_release_pd;
+ pv_mmu_ops.release_pte = vmi_release_pte;
+ pv_mmu_ops.release_pmd = vmi_release_pmd;
}
/* Set linear is needed in all cases */
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index b7ab3c335fa..fad3674b06a 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -209,12 +209,6 @@ SECTIONS
EXIT_DATA
}
-/* vdso blob that is mapped into user space */
- vdso_start = . ;
- .vdso : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) }
- . = ALIGN(PAGE_SIZE);
- vdso_end = .;
-
#ifdef CONFIG_BLK_DEV_INITRD
. = ALIGN(PAGE_SIZE);
__initramfs_start = .;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 41962e793c0..8d45fabc5f3 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -19,7 +19,7 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
- depends on HAVE_KVM && EXPERIMENTAL
+ depends on HAVE_KVM
select PREEMPT_NOTIFIERS
select ANON_INODES
---help---
@@ -50,6 +50,17 @@ config KVM_AMD
Provides support for KVM on AMD processors equipped with the AMD-V
(SVM) extensions.
+config KVM_TRACE
+ bool "KVM trace support"
+ depends on KVM && MARKERS && SYSFS
+ select RELAY
+ select DEBUG_FS
+ default n
+ ---help---
+ This option allows reading a trace of kvm-related events through
+ relayfs. Note the ABI is not considered stable and will be
+ modified in future updates.
+
# OK, it's a little counter-intuitive to do this, but it puts it neatly under
# the virtualization menu.
source drivers/lguest/Kconfig
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index ffdd0b31078..c97d35c218d 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -3,10 +3,14 @@
#
common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o)
+ifeq ($(CONFIG_KVM_TRACE),y)
+common-objs += $(addprefix ../../../virt/kvm/, kvm_trace.o)
+endif
EXTRA_CFLAGS += -Ivirt/kvm -Iarch/x86/kvm
-kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o
+kvm-objs := $(common-objs) x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \
+ i8254.o
obj-$(CONFIG_KVM) += kvm.o
kvm-intel-objs = vmx.o
obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
new file mode 100644
index 00000000000..361e3161127
--- /dev/null
+++ b/arch/x86/kvm/i8254.c
@@ -0,0 +1,611 @@
+/*
+ * 8253/8254 interval timer emulation
+ *
+ * Copyright (c) 2003-2004 Fabrice Bellard
+ * Copyright (c) 2006 Intel Corporation
+ * Copyright (c) 2007 Keir Fraser, XenSource Inc
+ * Copyright (c) 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * Authors:
+ * Sheng Yang <sheng.yang@intel.com>
+ * Based on QEMU and Xen.
+ */
+
+#include <linux/kvm_host.h>
+
+#include "irq.h"
+#include "i8254.h"
+
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
+#define RW_STATE_LSB 1
+#define RW_STATE_MSB 2
+#define RW_STATE_WORD0 3
+#define RW_STATE_WORD1 4
+
+/* Compute with 96 bit intermediate result: (a*b)/c */
+static u64 muldiv64(u64 a, u32 b, u32 c)
+{
+ union {
+ u64 ll;
+ struct {
+ u32 low, high;
+ } l;
+ } u, res;
+ u64 rl, rh;
+
+ u.ll = a;
+ rl = (u64)u.l.low * (u64)b;
+ rh = (u64)u.l.high * (u64)b;
+ rh += (rl >> 32);
+ res.l.high = div64_64(rh, c);
+ res.l.low = div64_64(((mod_64(rh, c) << 32) + (rl & 0xffffffff)), c);
+ return res.ll;
+}
+
+static void pit_set_gate(struct kvm *kvm, int channel, u32 val)
+{
+ struct kvm_kpit_channel_state *c =
+ &kvm->arch.vpit->pit_state.channels[channel];
+
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ switch (c->mode) {
+ default:
+ case 0:
+ case 4:
+ /* XXX: just disable/enable counting */
+ break;
+ case 1:
+ case 2:
+ case 3:
+ case 5:
+ /* Restart counting on rising edge. */
+ if (c->gate < val)
+ c->count_load_time = ktime_get();
+ break;
+ }
+
+ c->gate = val;
+}
+
+int pit_get_gate(struct kvm *kvm, int channel)
+{
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ return kvm->arch.vpit->pit_state.channels[channel].gate;
+}
+
+static int pit_get_count(struct kvm *kvm, int channel)
+{
+ struct kvm_kpit_channel_state *c =
+ &kvm->arch.vpit->pit_state.channels[channel];
+ s64 d, t;
+ int counter;
+
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+ d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+ switch (c->mode) {
+ case 0:
+ case 1:
+ case 4:
+ case 5:
+ counter = (c->count - d) & 0xffff;
+ break;
+ case 3:
+ /* XXX: may be incorrect for odd counts */
+ counter = c->count - (mod_64((2 * d), c->count));
+ break;
+ default:
+ counter = c->count - mod_64(d, c->count);
+ break;
+ }
+ return counter;
+}
+
+static int pit_get_out(struct kvm *kvm, int channel)
+{
+ struct kvm_kpit_channel_state *c =
+ &kvm->arch.vpit->pit_state.channels[channel];
+ s64 d, t;
+ int out;
+
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ t = ktime_to_ns(ktime_sub(ktime_get(), c->count_load_time));
+ d = muldiv64(t, KVM_PIT_FREQ, NSEC_PER_SEC);
+
+ switch (c->mode) {
+ default:
+ case 0:
+ out = (d >= c->count);
+ break;
+ case 1:
+ out = (d < c->count);
+ break;
+ case 2:
+ out = ((mod_64(d, c->count) == 0) && (d != 0));
+ break;
+ case 3:
+ out = (mod_64(d, c->count) < ((c->count + 1) >> 1));
+ break;
+ case 4:
+ case 5:
+ out = (d == c->count);
+ break;
+ }
+
+ return out;
+}
+
+static void pit_latch_count(struct kvm *kvm, int channel)
+{
+ struct kvm_kpit_channel_state *c =
+ &kvm->arch.vpit->pit_state.channels[channel];
+
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ if (!c->count_latched) {
+ c->latched_count = pit_get_count(kvm, channel);
+ c->count_latched = c->rw_mode;
+ }
+}
+
+static void pit_latch_status(struct kvm *kvm, int channel)
+{
+ struct kvm_kpit_channel_state *c =
+ &kvm->arch.vpit->pit_state.channels[channel];
+
+ WARN_ON(!mutex_is_locked(&kvm->arch.vpit->pit_state.lock));
+
+ if (!c->status_latched) {
+ /* TODO: Return NULL COUNT (bit 6). */
+ c->status = ((pit_get_out(kvm, channel) << 7) |
+ (c->rw_mode << 4) |
+ (c->mode << 1) |
+ c->bcd);
+ c->status_latched = 1;
+ }
+}
+
+int __pit_timer_fn(struct kvm_kpit_state *ps)
+{
+ struct kvm_vcpu *vcpu0 = ps->pit->kvm->vcpus[0];
+ struct kvm_kpit_timer *pt = &ps->pit_timer;
+
+ atomic_inc(&pt->pending);
+ smp_mb__after_atomic_inc();
+ /* FIXME: handle case where the guest is in guest mode */
+ if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
+ vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ wake_up_interruptible(&vcpu0->wq);
+ }
+
+ pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
+ pt->scheduled = ktime_to_ns(pt->timer.expires);
+
+ return (pt->period == 0 ? 0 : 1);
+}
+
+int pit_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+
+ if (pit && vcpu->vcpu_id == 0)
+ return atomic_read(&pit->pit_state.pit_timer.pending);
+
+ return 0;
+}
+
+static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
+{
+ struct kvm_kpit_state *ps;
+ int restart_timer = 0;
+
+ ps = container_of(data, struct kvm_kpit_state, pit_timer.timer);
+
+ restart_timer = __pit_timer_fn(ps);
+
+ if (restart_timer)
+ return HRTIMER_RESTART;
+ else
+ return HRTIMER_NORESTART;
+}
+
+static void destroy_pit_timer(struct kvm_kpit_timer *pt)
+{
+ pr_debug("pit: execute del timer!\n");
+ hrtimer_cancel(&pt->timer);
+}
+
+static void create_pit_timer(struct kvm_kpit_timer *pt, u32 val, int is_period)
+{
+ s64 interval;
+
+ interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ);
+
+ pr_debug("pit: create pit timer, interval is %llu nsec\n", interval);
+
+ /* TODO The new value only affected after the retriggered */
+ hrtimer_cancel(&pt->timer);
+ pt->period = (is_period == 0) ? 0 : interval;
+ pt->timer.function = pit_timer_fn;
+ atomic_set(&pt->pending, 0);
+
+ hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+ HRTIMER_MODE_ABS);
+}
+
+static void pit_load_count(struct kvm *kvm, int channel, u32 val)
+{
+ struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
+
+ WARN_ON(!mutex_is_locked(&ps->lock));
+
+ pr_debug("pit: load_count val is %d, channel is %d\n", val, channel);
+
+ /*
+ * Though spec said the state of 8254 is undefined after power-up,
+ * seems some tricky OS like Windows XP depends on IRQ0 interrupt
+ * when booting up.
+ * So here setting initialize rate for it, and not a specific number
+ */
+ if (val == 0)
+ val = 0x10000;
+
+ ps->channels[channel].count_load_time = ktime_get();
+ ps->channels[channel].count = val;
+
+ if (channel != 0)
+ return;
+
+ /* Two types of timer
+ * mode 1 is one shot, mode 2 is period, otherwise del timer */
+ switch (ps->channels[0].mode) {
+ case 1:
+ create_pit_timer(&ps->pit_timer, val, 0);
+ break;
+ case 2:
+ create_pit_timer(&ps->pit_timer, val, 1);
+ break;
+ default:
+ destroy_pit_timer(&ps->pit_timer);
+ }
+}
+
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
+{
+ mutex_lock(&kvm->arch.vpit->pit_state.lock);
+ pit_load_count(kvm, channel, val);
+ mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+}
+
+static void pit_ioport_write(struct kvm_io_device *this,
+ gpa_t addr, int len, const void *data)
+{
+ struct kvm_pit *pit = (struct kvm_pit *)this->private;
+ struct kvm_kpit_state *pit_state = &pit->pit_state;
+ struct kvm *kvm = pit->kvm;
+ int channel, access;
+ struct kvm_kpit_channel_state *s;
+ u32 val = *(u32 *) data;
+
+ val &= 0xff;
+ addr &= KVM_PIT_CHANNEL_MASK;
+
+ mutex_lock(&pit_state->lock);
+
+ if (val != 0)
+ pr_debug("pit: write addr is 0x%x, len is %d, val is 0x%x\n",
+ (unsigned int)addr, len, val);
+
+ if (addr == 3) {
+ channel = val >> 6;
+ if (channel == 3) {
+ /* Read-Back Command. */
+ for (channel = 0; channel < 3; channel++) {
+ s = &pit_state->channels[channel];
+ if (val & (2 << channel)) {
+ if (!(val & 0x20))
+ pit_latch_count(kvm, channel);
+ if (!(val & 0x10))
+ pit_latch_status(kvm, channel);
+ }
+ }
+ } else {
+ /* Select Counter <channel>. */
+ s = &pit_state->channels[channel];
+ access = (val >> 4) & KVM_PIT_CHANNEL_MASK;
+ if (access == 0) {
+ pit_latch_count(kvm, channel);
+ } else {
+ s->rw_mode = access;
+ s->read_state = access;
+ s->write_state = access;
+ s->mode = (val >> 1) & 7;
+ if (s->mode > 5)
+ s->mode -= 4;
+ s->bcd = val & 1;
+ }
+ }
+ } else {
+ /* Write Count. */
+ s = &pit_state->channels[addr];
+ switch (s->write_state) {
+ default:
+ case RW_STATE_LSB:
+ pit_load_count(kvm, addr, val);
+ break;
+ case RW_STATE_MSB:
+ pit_load_count(kvm, addr, val << 8);
+ break;
+ case RW_STATE_WORD0:
+ s->write_latch = val;
+ s->write_state = RW_STATE_WORD1;
+ break;
+ case RW_STATE_WORD1:
+ pit_load_count(kvm, addr, s->write_latch | (val << 8));
+ s->write_state = RW_STATE_WORD0;
+ break;
+ }
+ }
+
+ mutex_unlock(&pit_state->lock);
+}
+
+static void pit_ioport_read(struct kvm_io_device *this,
+ gpa_t addr, int len, void *data)
+{
+ struct kvm_pit *pit = (struct kvm_pit *)this->private;
+ struct kvm_kpit_state *pit_state = &pit->pit_state;
+ struct kvm *kvm = pit->kvm;
+ int ret, count;
+ struct kvm_kpit_channel_state *s;
+
+ addr &= KVM_PIT_CHANNEL_MASK;
+ s = &pit_state->channels[addr];
+
+ mutex_lock(&pit_state->lock);
+
+ if (s->status_latched) {
+ s->status_latched = 0;
+ ret = s->status;
+ } else if (s->count_latched) {
+ switch (s->count_latched) {
+ default:
+ case RW_STATE_LSB:
+ ret = s->latched_count & 0xff;
+ s->count_latched = 0;
+ break;
+ case RW_STATE_MSB:
+ ret = s->latched_count >> 8;
+ s->count_latched = 0;
+ break;
+ case RW_STATE_WORD0:
+ ret = s->latched_count & 0xff;
+ s->count_latched = RW_STATE_MSB;
+ break;
+ }
+ } else {
+ switch (s->read_state) {
+ default:
+ case RW_STATE_LSB:
+ count = pit_get_count(kvm, addr);
+ ret = count & 0xff;
+ break;
+ case RW_STATE_MSB:
+ count = pit_get_count(kvm, addr);
+ ret = (count >> 8) & 0xff;
+ break;
+ case RW_STATE_WORD0:
+ count = pit_get_count(kvm, addr);
+ ret = count & 0xff;
+ s->read_state = RW_STATE_WORD1;
+ break;
+ case RW_STATE_WORD1:
+ count = pit_get_count(kvm, addr);
+ ret = (count >> 8) & 0xff;
+ s->read_state = RW_STATE_WORD0;
+ break;
+ }
+ }
+
+ if (len > sizeof(ret))
+ len = sizeof(ret);
+ memcpy(data, (char *)&ret, len);
+
+ mutex_unlock(&pit_state->lock);
+}
+
+static int pit_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+ return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+ (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static void speaker_ioport_write(struct kvm_io_device *this,
+ gpa_t addr, int len, const void *data)
+{
+ struct kvm_pit *pit = (struct kvm_pit *)this->private;
+ struct kvm_kpit_state *pit_state = &pit->pit_state;
+ struct kvm *kvm = pit->kvm;
+ u32 val = *(u32 *) data;
+
+ mutex_lock(&pit_state->lock);
+ pit_state->speaker_data_on = (val >> 1) & 1;
+ pit_set_gate(kvm, 2, val & 1);
+ mutex_unlock(&pit_state->lock);
+}
+
+static void speaker_ioport_read(struct kvm_io_device *this,
+ gpa_t addr, int len, void *data)
+{
+ struct kvm_pit *pit = (struct kvm_pit *)this->private;
+ struct kvm_kpit_state *pit_state = &pit->pit_state;
+ struct kvm *kvm = pit->kvm;
+ unsigned int refresh_clock;
+ int ret;
+
+ /* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
+ refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
+
+ mutex_lock(&pit_state->lock);
+ ret = ((pit_state->speaker_data_on << 1) | pit_get_gate(kvm, 2) |
+ (pit_get_out(kvm, 2) << 5) | (refresh_clock << 4));
+ if (len > sizeof(ret))
+ len = sizeof(ret);
+ memcpy(data, (char *)&ret, len);
+ mutex_unlock(&pit_state->lock);
+}
+
+static int speaker_in_range(struct kvm_io_device *this, gpa_t addr)
+{
+ return (addr == KVM_SPEAKER_BASE_ADDRESS);
+}
+
+void kvm_pit_reset(struct kvm_pit *pit)
+{
+ int i;
+ struct kvm_kpit_channel_state *c;
+
+ mutex_lock(&pit->pit_state.lock);
+ for (i = 0; i < 3; i++) {
+ c = &pit->pit_state.channels[i];
+ c->mode = 0xff;
+ c->gate = (i != 2);
+ pit_load_count(pit->kvm, i, 0);
+ }
+ mutex_unlock(&pit->pit_state.lock);
+
+ atomic_set(&pit->pit_state.pit_timer.pending, 0);
+ pit->pit_state.inject_pending = 1;
+}
+
+struct kvm_pit *kvm_create_pit(struct kvm *kvm)
+{
+ struct kvm_pit *pit;
+ struct kvm_kpit_state *pit_state;
+
+ pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
+ if (!pit)
+ return NULL;
+
+ mutex_init(&pit->pit_state.lock);
+ mutex_lock(&pit->pit_state.lock);
+
+ /* Initialize PIO device */
+ pit->dev.read = pit_ioport_read;
+ pit->dev.write = pit_ioport_write;
+ pit->dev.in_range = pit_in_range;
+ pit->dev.private = pit;
+ kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+
+ pit->speaker_dev.read = speaker_ioport_read;
+ pit->speaker_dev.write = speaker_ioport_write;
+ pit->speaker_dev.in_range = speaker_in_range;
+ pit->speaker_dev.private = pit;
+ kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+
+ kvm->arch.vpit = pit;
+ pit->kvm = kvm;
+
+ pit_state = &pit->pit_state;
+ pit_state->pit = pit;
+ hrtimer_init(&pit_state->pit_timer.timer,
+ CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ mutex_unlock(&pit->pit_state.lock);
+
+ kvm_pit_reset(pit);
+
+ return pit;
+}
+
+void kvm_free_pit(struct kvm *kvm)
+{
+ struct hrtimer *timer;
+
+ if (kvm->arch.vpit) {
+ mutex_lock(&kvm->arch.vpit->pit_state.lock);
+ timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+ hrtimer_cancel(timer);
+ mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ kfree(kvm->arch.vpit);
+ }
+}
+
+void __inject_pit_timer_intr(struct kvm *kvm)
+{
+ mutex_lock(&kvm->lock);
+ kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 1);
+ kvm_ioapic_set_irq(kvm->arch.vioapic, 0, 0);
+ kvm_pic_set_irq(pic_irqchip(kvm), 0, 1);
+ kvm_pic_set_irq(pic_irqchip(kvm), 0, 0);
+ mutex_unlock(&kvm->lock);
+}
+
+void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pit *pit = vcpu->kvm->arch.vpit;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_kpit_state *ps;
+
+ if (vcpu && pit) {
+ ps = &pit->pit_state;
+
+ /* Try to inject pending interrupts when:
+ * 1. Pending exists
+ * 2. Last interrupt was accepted or waited for too long time*/
+ if (atomic_read(&ps->pit_timer.pending) &&
+ (ps->inject_pending ||
+ (jiffies - ps->last_injected_time
+ >= KVM_MAX_PIT_INTR_INTERVAL))) {
+ ps->inject_pending = 0;
+ __inject_pit_timer_intr(kvm);
+ ps->last_injected_time = jiffies;
+ }
+ }
+}
+
+void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
+{
+ struct kvm_arch *arch = &vcpu->kvm->arch;
+ struct kvm_kpit_state *ps;
+
+ if (vcpu && arch->vpit) {
+ ps = &arch->vpit->pit_state;
+ if (atomic_read(&ps->pit_timer.pending) &&
+ (((arch->vpic->pics[0].imr & 1) == 0 &&
+ arch->vpic->pics[0].irq_base == vec) ||
+ (arch->vioapic->redirtbl[0].fields.vector == vec &&
+ arch->vioapic->redirtbl[0].fields.mask != 1))) {
+ ps->inject_pending = 1;
+ atomic_dec(&ps->pit_timer.pending);
+ ps->channels[0].count_load_time = ktime_get();
+ }
+ }
+}
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
new file mode 100644
index 00000000000..db25c2a6c8c
--- /dev/null
+++ b/arch/x86/kvm/i8254.h
@@ -0,0 +1,63 @@
+#ifndef __I8254_H
+#define __I8254_H
+
+#include "iodev.h"
+
+struct kvm_kpit_timer {
+ struct hrtimer timer;
+ int irq;
+ s64 period; /* unit: ns */
+ s64 scheduled;
+ ktime_t last_update;
+ atomic_t pending;
+};
+
+struct kvm_kpit_channel_state {
+ u32 count; /* can be 65536 */
+ u16 latched_count;
+ u8 count_latched;
+ u8 status_latched;
+ u8 status;
+ u8 read_state;
+ u8 write_state;
+ u8 write_latch;
+ u8 rw_mode;
+ u8 mode;
+ u8 bcd; /* not supported */
+ u8 gate; /* timer start */
+ ktime_t count_load_time;
+};
+
+struct kvm_kpit_state {
+ struct kvm_kpit_channel_state channels[3];
+ struct kvm_kpit_timer pit_timer;
+ u32 speaker_data_on;
+ struct mutex lock;
+ struct kvm_pit *pit;
+ bool inject_pending; /* if inject pending interrupts */
+ unsigned long last_injected_time;
+};
+
+struct kvm_pit {
+ unsigned long base_addresss;
+ struct kvm_io_device dev;
+ struct kvm_io_device speaker_dev;
+ struct kvm *kvm;
+ struct kvm_kpit_state pit_state;
+};
+
+#define KVM_PIT_BASE_ADDRESS 0x40
+#define KVM_SPEAKER_BASE_ADDRESS 0x61
+#define KVM_PIT_MEM_LENGTH 4
+#define KVM_PIT_FREQ 1193181
+#define KVM_MAX_PIT_INTR_INTERVAL HZ / 100
+#define KVM_PIT_CHANNEL_MASK 0x3
+
+void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu);
+void kvm_pit_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
+void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val);
+struct kvm_pit *kvm_create_pit(struct kvm *kvm);
+void kvm_free_pit(struct kvm *kvm);
+void kvm_pit_reset(struct kvm_pit *pit);
+
+#endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index e5714759e97..ce1f583459b 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -23,6 +23,22 @@
#include <linux/kvm_host.h>
#include "irq.h"
+#include "i8254.h"
+
+/*
+ * check if there are pending timer events
+ * to be processed.
+ */
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ int ret;
+
+ ret = pit_has_pending_timer(vcpu);
+ ret |= apic_has_pending_timer(vcpu);
+
+ return ret;
+}
+EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
/*
* check if there is pending interrupt without
@@ -66,6 +82,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
{
kvm_inject_apic_timer_irqs(vcpu);
+ kvm_inject_pit_timer_irqs(vcpu);
/* TODO: PIT, RTC etc. */
}
EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
@@ -73,6 +90,7 @@ EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
{
kvm_apic_timer_intr_post(vcpu, vec);
+ kvm_pit_timer_intr_post(vcpu, vec);
/* TODO: PIT, RTC etc. */
}
EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index fa5ed5d59b5..1802134b836 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -85,4 +85,7 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
+int pit_has_pending_timer(struct kvm_vcpu *vcpu);
+int apic_has_pending_timer(struct kvm_vcpu *vcpu);
+
#endif
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index ecdfe97e463..65ef0fc2c03 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -39,6 +39,8 @@ struct vcpu_svm {
unsigned long host_db_regs[NUM_DB_REGS];
unsigned long host_dr6;
unsigned long host_dr7;
+
+ u32 *msrpm;
};
#endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 68a6b151193..57ac4e4c556 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -338,10 +338,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
} else
apic_clear_vector(vector, apic->regs + APIC_TMR);
- if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
+ if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
kvm_vcpu_kick(vcpu);
- else if (vcpu->arch.mp_state == VCPU_MP_STATE_HALTED) {
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ else if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) {
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
}
@@ -362,11 +362,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
case APIC_DM_INIT:
if (level) {
- if (vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE)
+ if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
printk(KERN_DEBUG
"INIT on a runnable vcpu %d\n",
vcpu->vcpu_id);
- vcpu->arch.mp_state = VCPU_MP_STATE_INIT_RECEIVED;
+ vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
kvm_vcpu_kick(vcpu);
} else {
printk(KERN_DEBUG
@@ -379,9 +379,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
case APIC_DM_STARTUP:
printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n",
vcpu->vcpu_id, vector);
- if (vcpu->arch.mp_state == VCPU_MP_STATE_INIT_RECEIVED) {
+ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
vcpu->arch.sipi_vector = vector;
- vcpu->arch.mp_state = VCPU_MP_STATE_SIPI_RECEIVED;
+ vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
}
@@ -658,7 +658,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
PRIx64 ", "
"timer initial count 0x%x, period %lldns, "
- "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__,
+ "expire @ 0x%016" PRIx64 ".\n", __func__,
APIC_BUS_CYCLE_NS, ktime_to_ns(now),
apic_get_reg(apic, APIC_TMICT),
apic->timer.period,
@@ -691,7 +691,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
/* too common printing */
if (offset != APIC_EOI)
apic_debug("%s: offset 0x%x with length 0x%x, and value is "
- "0x%x\n", __FUNCTION__, offset, len, val);
+ "0x%x\n", __func__, offset, len, val);
offset &= 0xff0;
@@ -822,6 +822,7 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
| (apic_get_reg(apic, APIC_TASKPRI) & 4));
}
+EXPORT_SYMBOL_GPL(kvm_lapic_set_tpr);
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
{
@@ -869,7 +870,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic;
int i;
- apic_debug("%s\n", __FUNCTION__);
+ apic_debug("%s\n", __func__);
ASSERT(vcpu);
apic = vcpu->arch.apic;
@@ -907,7 +908,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
apic_update_ppr(apic);
apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
- "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__,
+ "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
vcpu, kvm_apic_id(apic),
vcpu->arch.apic_base, apic->base_address);
}
@@ -940,7 +941,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
atomic_inc(&apic->timer.pending);
if (waitqueue_active(q)) {
- apic->vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
wake_up_interruptible(q);
}
if (apic_lvtt_period(apic)) {
@@ -952,6 +953,16 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
return result;
}
+int apic_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+ struct kvm_lapic *lapic = vcpu->arch.apic;
+
+ if (lapic)
+ return atomic_read(&lapic->timer.pending);
+
+ return 0;
+}
+
static int __inject_apic_timer_irq(struct kvm_lapic *apic)
{
int vector;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e55af12e11b..2ad6f548167 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -27,11 +27,22 @@
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/swap.h>
+#include <linux/hugetlb.h>
+#include <linux/compiler.h>
#include <asm/page.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
+/*
+ * When setting this variable to true it enables Two-Dimensional-Paging
+ * where the hardware walks 2 page tables:
+ * 1. the guest-virtual to guest-physical
+ * 2. while doing 1. it walks guest-physical to host-physical
+ * If the hardware supports that we don't need to do shadow paging.
+ */
+bool tdp_enabled = false;
+
#undef MMU_DEBUG
#undef AUDIT
@@ -101,8 +112,6 @@ static int dbg = 1;
#define PT_FIRST_AVAIL_BITS_SHIFT 9
#define PT64_SECOND_AVAIL_BITS_SHIFT 52
-#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
-
#define VALID_PAGE(x) ((x) != INVALID_PAGE)
#define PT64_LEVEL_BITS 9
@@ -159,6 +168,13 @@ static int dbg = 1;
#define ACC_USER_MASK PT_USER_MASK
#define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK)
+struct kvm_pv_mmu_op_buffer {
+ void *ptr;
+ unsigned len;
+ unsigned processed;
+ char buf[512] __aligned(sizeof(long));
+};
+
struct kvm_rmap_desc {
u64 *shadow_ptes[RMAP_EXT];
struct kvm_rmap_desc *more;
@@ -200,11 +216,15 @@ static int is_present_pte(unsigned long pte)
static int is_shadow_present_pte(u64 pte)
{
- pte &= ~PT_SHADOW_IO_MARK;
return pte != shadow_trap_nonpresent_pte
&& pte != shadow_notrap_nonpresent_pte;
}
+static int is_large_pte(u64 pte)
+{
+ return pte & PT_PAGE_SIZE_MASK;
+}
+
static int is_writeble_pte(unsigned long pte)
{
return pte & PT_WRITABLE_MASK;
@@ -215,14 +235,14 @@ static int is_dirty_pte(unsigned long pte)
return pte & PT_DIRTY_MASK;
}
-static int is_io_pte(unsigned long pte)
+static int is_rmap_pte(u64 pte)
{
- return pte & PT_SHADOW_IO_MARK;
+ return is_shadow_present_pte(pte);
}
-static int is_rmap_pte(u64 pte)
+static pfn_t spte_to_pfn(u64 pte)
{
- return is_shadow_present_pte(pte);
+ return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
}
static gfn_t pse36_gfn_delta(u32 gpte)
@@ -349,16 +369,100 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd)
}
/*
+ * Return the pointer to the largepage write count for a given
+ * gfn, handling slots that are not large page aligned.
+ */
+static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot)
+{
+ unsigned long idx;
+
+ idx = (gfn / KVM_PAGES_PER_HPAGE) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+ return &slot->lpage_info[idx].write_count;
+}
+
+static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+ int *write_count;
+
+ write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+ *write_count += 1;
+ WARN_ON(*write_count > KVM_PAGES_PER_HPAGE);
+}
+
+static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+{
+ int *write_count;
+
+ write_count = slot_largepage_idx(gfn, gfn_to_memslot(kvm, gfn));
+ *write_count -= 1;
+ WARN_ON(*write_count < 0);
+}
+
+static int has_wrprotected_page(struct kvm *kvm, gfn_t gfn)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+ int *largepage_idx;
+
+ if (slot) {
+ largepage_idx = slot_largepage_idx(gfn, slot);
+ return *largepage_idx;
+ }
+
+ return 1;
+}
+
+static int host_largepage_backed(struct kvm *kvm, gfn_t gfn)
+{
+ struct vm_area_struct *vma;
+ unsigned long addr;
+
+ addr = gfn_to_hva(kvm, gfn);
+ if (kvm_is_error_hva(addr))
+ return 0;
+
+ vma = find_vma(current->mm, addr);
+ if (vma && is_vm_hugetlb_page(vma))
+ return 1;
+
+ return 0;
+}
+
+static int is_largepage_backed(struct kvm_vcpu *vcpu, gfn_t large_gfn)
+{
+ struct kvm_memory_slot *slot;
+
+ if (has_wrprotected_page(vcpu->kvm, large_gfn))
+ return 0;
+
+ if (!host_largepage_backed(vcpu->kvm, large_gfn))
+ return 0;
+
+ slot = gfn_to_memslot(vcpu->kvm, large_gfn);
+ if (slot && slot->dirty_bitmap)
+ return 0;
+
+ return 1;
+}
+
+/*
* Take gfn and return the reverse mapping to it.
* Note: gfn must be unaliased before this function get called
*/
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
{
struct kvm_memory_slot *slot;
+ unsigned long idx;
slot = gfn_to_memslot(kvm, gfn);
- return &slot->rmap[gfn - slot->base_gfn];
+ if (!lpage)
+ return &slot->rmap[gfn - slot->base_gfn];
+
+ idx = (gfn / KVM_PAGES_PER_HPAGE) -
+ (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+
+ return &slot->lpage_info[idx].rmap_pde;
}
/*
@@ -370,7 +474,7 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn)
* If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
* containing more mappings.
*/
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
+static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
{
struct kvm_mmu_page *sp;
struct kvm_rmap_desc *desc;
@@ -382,7 +486,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
gfn = unalias_gfn(vcpu->kvm, gfn);
sp = page_header(__pa(spte));
sp->gfns[spte - sp->spt] = gfn;
- rmapp = gfn_to_rmap(vcpu->kvm, gfn);
+ rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
if (!*rmapp) {
rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte);
*rmapp = (unsigned long)spte;
@@ -435,20 +539,21 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
struct kvm_rmap_desc *desc;
struct kvm_rmap_desc *prev_desc;
struct kvm_mmu_page *sp;
- struct page *page;
+ pfn_t pfn;
unsigned long *rmapp;
int i;
if (!is_rmap_pte(*spte))
return;
sp = page_header(__pa(spte));
- page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT);
- mark_page_accessed(page);
+ pfn = spte_to_pfn(*spte);
+ if (*spte & PT_ACCESSED_MASK)
+ kvm_set_pfn_accessed(pfn);
if (is_writeble_pte(*spte))
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
- rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt]);
+ kvm_release_pfn_clean(pfn);
+ rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], is_large_pte(*spte));
if (!*rmapp) {
printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte);
BUG();
@@ -514,7 +619,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
int write_protected = 0;
gfn = unalias_gfn(kvm, gfn);
- rmapp = gfn_to_rmap(kvm, gfn);
+ rmapp = gfn_to_rmap(kvm, gfn, 0);
spte = rmap_next(kvm, rmapp, NULL);
while (spte) {
@@ -527,8 +632,35 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
}
spte = rmap_next(kvm, rmapp, spte);
}
+ if (write_protected) {
+ pfn_t pfn;
+
+ spte = rmap_next(kvm, rmapp, NULL);
+ pfn = spte_to_pfn(*spte);
+ kvm_set_pfn_dirty(pfn);
+ }
+
+ /* check for huge page mappings */
+ rmapp = gfn_to_rmap(kvm, gfn, 1);
+ spte = rmap_next(kvm, rmapp, NULL);
+ while (spte) {
+ BUG_ON(!spte);
+ BUG_ON(!(*spte & PT_PRESENT_MASK));
+ BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK));
+ pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
+ if (is_writeble_pte(*spte)) {
+ rmap_remove(kvm, spte);
+ --kvm->stat.lpages;
+ set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ write_protected = 1;
+ }
+ spte = rmap_next(kvm, rmapp, spte);
+ }
+
if (write_protected)
kvm_flush_remote_tlbs(kvm);
+
+ account_shadowed(kvm, gfn);
}
#ifdef MMU_DEBUG
@@ -538,8 +670,8 @@ static int is_empty_shadow_page(u64 *spt)
u64 *end;
for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
- if ((*pos & ~PT_SHADOW_IO_MARK) != shadow_trap_nonpresent_pte) {
- printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__,
+ if (*pos != shadow_trap_nonpresent_pte) {
+ printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
return 0;
}
@@ -559,7 +691,7 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp)
static unsigned kvm_page_table_hashfn(gfn_t gfn)
{
- return gfn;
+ return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1);
}
static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
@@ -662,13 +794,14 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
struct kvm_mmu_page *sp;
struct hlist_node *node;
- pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
- index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+ pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
+ index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
hlist_for_each_entry(sp, node, bucket, hash_link)
- if (sp->gfn == gfn && !sp->role.metaphysical) {
+ if (sp->gfn == gfn && !sp->role.metaphysical
+ && !sp->role.invalid) {
pgprintk("%s: found role %x\n",
- __FUNCTION__, sp->role.word);
+ __func__, sp->role.word);
return sp;
}
return NULL;
@@ -699,27 +832,27 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
}
- pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__,
+ pgprintk("%s: looking gfn %lx role %x\n", __func__,
gfn, role.word);
- index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+ index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
hlist_for_each_entry(sp, node, bucket, hash_link)
if (sp->gfn == gfn && sp->role.word == role.word) {
mmu_page_add_parent_pte(vcpu, sp, parent_pte);
- pgprintk("%s: found\n", __FUNCTION__);
+ pgprintk("%s: found\n", __func__);
return sp;
}
++vcpu->kvm->stat.mmu_cache_miss;
sp = kvm_mmu_alloc_page(vcpu, parent_pte);
if (!sp)
return sp;
- pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word);
+ pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word);
sp->gfn = gfn;
sp->role = role;
hlist_add_head(&sp->hash_link, bucket);
- vcpu->arch.mmu.prefetch_page(vcpu, sp);
if (!metaphysical)
rmap_write_protect(vcpu->kvm, gfn);
+ vcpu->arch.mmu.prefetch_page(vcpu, sp);
return sp;
}
@@ -745,11 +878,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm,
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
ent = pt[i];
+ if (is_shadow_present_pte(ent)) {
+ if (!is_large_pte(ent)) {
+ ent &= PT64_BASE_ADDR_MASK;
+ mmu_page_remove_parent_pte(page_header(ent),
+ &pt[i]);
+ } else {
+ --kvm->stat.lpages;
+ rmap_remove(kvm, &pt[i]);
+ }
+ }
pt[i] = shadow_trap_nonpresent_pte;
- if (!is_shadow_present_pte(ent))
- continue;
- ent &= PT64_BASE_ADDR_MASK;
- mmu_page_remove_parent_pte(page_header(ent), &pt[i]);
}
kvm_flush_remote_tlbs(kvm);
}
@@ -789,10 +928,15 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
}
kvm_mmu_page_unlink_children(kvm, sp);
if (!sp->root_count) {
+ if (!sp->role.metaphysical)
+ unaccount_shadowed(kvm, sp->gfn);
hlist_del(&sp->hash_link);
kvm_mmu_free_page(kvm, sp);
- } else
+ } else {
list_move(&sp->link, &kvm->arch.active_mmu_pages);
+ sp->role.invalid = 1;
+ kvm_reload_remote_mmus(kvm);
+ }
kvm_mmu_reset_last_pte_updated(kvm);
}
@@ -838,13 +982,13 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
struct hlist_node *node, *n;
int r;
- pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn);
+ pgprintk("%s: looking for gfn %lx\n", __func__, gfn);
r = 0;
- index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+ index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
if (sp->gfn == gfn && !sp->role.metaphysical) {
- pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn,
+ pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
sp->role.word);
kvm_mmu_zap_page(kvm, sp);
r = 1;
@@ -857,7 +1001,7 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
struct kvm_mmu_page *sp;
while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) {
- pgprintk("%s: zap %lx %x\n", __FUNCTION__, gfn, sp->role.word);
+ pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word);
kvm_mmu_zap_page(kvm, sp);
}
}
@@ -889,26 +1033,39 @@ struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
unsigned pt_access, unsigned pte_access,
int user_fault, int write_fault, int dirty,
- int *ptwrite, gfn_t gfn, struct page *page)
+ int *ptwrite, int largepage, gfn_t gfn,
+ pfn_t pfn, bool speculative)
{
u64 spte;
int was_rmapped = 0;
int was_writeble = is_writeble_pte(*shadow_pte);
- hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
pgprintk("%s: spte %llx access %x write_fault %d"
" user_fault %d gfn %lx\n",
- __FUNCTION__, *shadow_pte, pt_access,
+ __func__, *shadow_pte, pt_access,
write_fault, user_fault, gfn);
if (is_rmap_pte(*shadow_pte)) {
- if (host_pfn != page_to_pfn(page)) {
+ /*
+ * If we overwrite a PTE page pointer with a 2MB PMD, unlink
+ * the parent of the now unreachable PTE.
+ */
+ if (largepage && !is_large_pte(*shadow_pte)) {
+ struct kvm_mmu_page *child;
+ u64 pte = *shadow_pte;
+
+ child = page_header(pte & PT64_BASE_ADDR_MASK);
+ mmu_page_remove_parent_pte(child, shadow_pte);
+ } else if (pfn != spte_to_pfn(*shadow_pte)) {
pgprintk("hfn old %lx new %lx\n",
- host_pfn, page_to_pfn(page));
+ spte_to_pfn(*shadow_pte), pfn);
rmap_remove(vcpu->kvm, shadow_pte);
+ } else {
+ if (largepage)
+ was_rmapped = is_large_pte(*shadow_pte);
+ else
+ was_rmapped = 1;
}
- else
- was_rmapped = 1;
}
/*
@@ -917,6 +1074,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
* demand paging).
*/
spte = PT_PRESENT_MASK | PT_DIRTY_MASK;
+ if (!speculative)
+ pte_access |= PT_ACCESSED_MASK;
if (!dirty)
pte_access &= ~ACC_WRITE_MASK;
if (!(pte_access & ACC_EXEC_MASK))
@@ -925,15 +1084,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
spte |= PT_PRESENT_MASK;
if (pte_access & ACC_USER_MASK)
spte |= PT_USER_MASK;
+ if (largepage)
+ spte |= PT_PAGE_SIZE_MASK;
- if (is_error_page(page)) {
- set_shadow_pte(shadow_pte,
- shadow_trap_nonpresent_pte | PT_SHADOW_IO_MARK);
- kvm_release_page_clean(page);
- return;
- }
-
- spte |= page_to_phys(page);
+ spte |= (u64)pfn << PAGE_SHIFT;
if ((pte_access & ACC_WRITE_MASK)
|| (write_fault && !is_write_protection(vcpu) && !user_fault)) {
@@ -946,9 +1100,10 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
}
shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
- if (shadow) {
+ if (shadow ||
+ (largepage && has_wrprotected_page(vcpu->kvm, gfn))) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
- __FUNCTION__, gfn);
+ __func__, gfn);
pte_access &= ~ACC_WRITE_MASK;
if (is_writeble_pte(spte)) {
spte &= ~PT_WRITABLE_MASK;
@@ -964,18 +1119,25 @@ unshadowed:
if (pte_access & ACC_WRITE_MASK)
mark_page_dirty(vcpu->kvm, gfn);
- pgprintk("%s: setting spte %llx\n", __FUNCTION__, spte);
+ pgprintk("%s: setting spte %llx\n", __func__, spte);
+ pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n",
+ (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB",
+ (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte);
set_shadow_pte(shadow_pte, spte);
+ if (!was_rmapped && (spte & PT_PAGE_SIZE_MASK)
+ && (spte & PT_PRESENT_MASK))
+ ++vcpu->kvm->stat.lpages;
+
page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
if (!was_rmapped) {
- rmap_add(vcpu, shadow_pte, gfn);
+ rmap_add(vcpu, shadow_pte, gfn, largepage);
if (!is_rmap_pte(*shadow_pte))
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
} else {
if (was_writeble)
- kvm_release_page_dirty(page);
+ kvm_release_pfn_dirty(pfn);
else
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
if (!ptwrite || !*ptwrite)
vcpu->arch.last_pte_updated = shadow_pte;
@@ -985,10 +1147,10 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
{
}
-static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
- gfn_t gfn, struct page *page)
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
+ int largepage, gfn_t gfn, pfn_t pfn,
+ int level)
{
- int level = PT32E_ROOT_LEVEL;
hpa_t table_addr = vcpu->arch.mmu.root_hpa;
int pt_write = 0;
@@ -1001,8 +1163,14 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
if (level == 1) {
mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
- 0, write, 1, &pt_write, gfn, page);
- return pt_write || is_io_pte(table[index]);
+ 0, write, 1, &pt_write, 0, gfn, pfn, false);
+ return pt_write;
+ }
+
+ if (largepage && level == 2) {
+ mmu_set_spte(vcpu, &table[index], ACC_ALL, ACC_ALL,
+ 0, write, 1, &pt_write, 1, gfn, pfn, false);
+ return pt_write;
}
if (table[index] == shadow_trap_nonpresent_pte) {
@@ -1016,7 +1184,7 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
1, ACC_ALL, &table[index]);
if (!new_table) {
pgprintk("nonpaging_map: ENOMEM\n");
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
return -ENOMEM;
}
@@ -1030,21 +1198,30 @@ static int __nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write,
static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
{
int r;
-
- struct page *page;
-
- down_read(&vcpu->kvm->slots_lock);
+ int largepage = 0;
+ pfn_t pfn;
down_read(&current->mm->mmap_sem);
- page = gfn_to_page(vcpu->kvm, gfn);
+ if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+ gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+ largepage = 1;
+ }
+
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
up_read(&current->mm->mmap_sem);
+ /* mmio */
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
+ return 1;
+ }
+
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
- r = __nonpaging_map(vcpu, v, write, gfn, page);
+ r = __direct_map(vcpu, v, write, largepage, gfn, pfn,
+ PT32E_ROOT_LEVEL);
spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(&vcpu->kvm->slots_lock);
return r;
}
@@ -1073,6 +1250,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
sp = page_header(root);
--sp->root_count;
+ if (!sp->root_count && sp->role.invalid)
+ kvm_mmu_zap_page(vcpu->kvm, sp);
vcpu->arch.mmu.root_hpa = INVALID_PAGE;
spin_unlock(&vcpu->kvm->mmu_lock);
return;
@@ -1085,6 +1264,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
root &= PT64_BASE_ADDR_MASK;
sp = page_header(root);
--sp->root_count;
+ if (!sp->root_count && sp->role.invalid)
+ kvm_mmu_zap_page(vcpu->kvm, sp);
}
vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
}
@@ -1097,6 +1278,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
int i;
gfn_t root_gfn;
struct kvm_mmu_page *sp;
+ int metaphysical = 0;
root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
@@ -1105,14 +1287,20 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
hpa_t root = vcpu->arch.mmu.root_hpa;
ASSERT(!VALID_PAGE(root));
+ if (tdp_enabled)
+ metaphysical = 1;
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- PT64_ROOT_LEVEL, 0, ACC_ALL, NULL);
+ PT64_ROOT_LEVEL, metaphysical,
+ ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
vcpu->arch.mmu.root_hpa = root;
return;
}
#endif
+ metaphysical = !is_paging(vcpu);
+ if (tdp_enabled)
+ metaphysical = 1;
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
@@ -1126,7 +1314,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu)
} else if (vcpu->arch.mmu.root_level == 0)
root_gfn = 0;
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
- PT32_ROOT_LEVEL, !is_paging(vcpu),
+ PT32_ROOT_LEVEL, metaphysical,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
@@ -1146,7 +1334,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
gfn_t gfn;
int r;
- pgprintk("%s: gva %lx error %x\n", __FUNCTION__, gva, error_code);
+ pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
@@ -1160,6 +1348,41 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
error_code & PFERR_WRITE_MASK, gfn);
}
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
+ u32 error_code)
+{
+ pfn_t pfn;
+ int r;
+ int largepage = 0;
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+
+ ASSERT(vcpu);
+ ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+ r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ return r;
+
+ down_read(&current->mm->mmap_sem);
+ if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
+ gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+ largepage = 1;
+ }
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
+ up_read(&current->mm->mmap_sem);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
+ return 1;
+ }
+ spin_lock(&vcpu->kvm->mmu_lock);
+ kvm_mmu_free_some_pages(vcpu);
+ r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
+ largepage, gfn, pfn, TDP_ROOT_LEVEL);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+
+ return r;
+}
+
static void nonpaging_free(struct kvm_vcpu *vcpu)
{
mmu_free_roots(vcpu);
@@ -1188,7 +1411,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
- pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->arch.cr3);
+ pgprintk("%s: cr3 %lx\n", __func__, vcpu->arch.cr3);
mmu_free_roots(vcpu);
}
@@ -1253,7 +1476,35 @@ static int paging32E_init_context(struct kvm_vcpu *vcpu)
return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL);
}
-static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu *context = &vcpu->arch.mmu;
+
+ context->new_cr3 = nonpaging_new_cr3;
+ context->page_fault = tdp_page_fault;
+ context->free = nonpaging_free;
+ context->prefetch_page = nonpaging_prefetch_page;
+ context->shadow_root_level = TDP_ROOT_LEVEL;
+ context->root_hpa = INVALID_PAGE;
+
+ if (!is_paging(vcpu)) {
+ context->gva_to_gpa = nonpaging_gva_to_gpa;
+ context->root_level = 0;
+ } else if (is_long_mode(vcpu)) {
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ context->root_level = PT64_ROOT_LEVEL;
+ } else if (is_pae(vcpu)) {
+ context->gva_to_gpa = paging64_gva_to_gpa;
+ context->root_level = PT32E_ROOT_LEVEL;
+ } else {
+ context->gva_to_gpa = paging32_gva_to_gpa;
+ context->root_level = PT32_ROOT_LEVEL;
+ }
+
+ return 0;
+}
+
+static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
ASSERT(vcpu);
ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
@@ -1268,6 +1519,16 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu)
return paging32_init_context(vcpu);
}
+static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.update_pte.pfn = bad_pfn;
+
+ if (tdp_enabled)
+ return init_kvm_tdp_mmu(vcpu);
+ else
+ return init_kvm_softmmu(vcpu);
+}
+
static void destroy_kvm_mmu(struct kvm_vcpu *vcpu)
{
ASSERT(vcpu);
@@ -1316,7 +1577,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
pte = *spte;
if (is_shadow_present_pte(pte)) {
- if (sp->role.level == PT_PAGE_TABLE_LEVEL)
+ if (sp->role.level == PT_PAGE_TABLE_LEVEL ||
+ is_large_pte(pte))
rmap_remove(vcpu->kvm, spte);
else {
child = page_header(pte & PT64_BASE_ADDR_MASK);
@@ -1324,24 +1586,26 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
}
}
set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+ if (is_large_pte(pte))
+ --vcpu->kvm->stat.lpages;
}
static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp,
u64 *spte,
- const void *new, int bytes,
- int offset_in_pte)
+ const void *new)
{
- if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+ if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
+ && !vcpu->arch.update_pte.largepage) {
++vcpu->kvm->stat.mmu_pde_zapped;
return;
}
++vcpu->kvm->stat.mmu_pte_updated;
if (sp->role.glevels == PT32_ROOT_LEVEL)
- paging32_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+ paging32_update_pte(vcpu, sp, spte, new);
else
- paging64_update_pte(vcpu, sp, spte, new, bytes, offset_in_pte);
+ paging64_update_pte(vcpu, sp, spte, new);
}
static bool need_remote_flush(u64 old, u64 new)
@@ -1378,7 +1642,9 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
gfn_t gfn;
int r;
u64 gpte = 0;
- struct page *page;
+ pfn_t pfn;
+
+ vcpu->arch.update_pte.largepage = 0;
if (bytes != 4 && bytes != 8)
return;
@@ -1408,11 +1674,19 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
down_read(&current->mm->mmap_sem);
- page = gfn_to_page(vcpu->kvm, gfn);
+ if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) {
+ gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+ vcpu->arch.update_pte.largepage = 1;
+ }
+ pfn = gfn_to_pfn(vcpu->kvm, gfn);
up_read(&current->mm->mmap_sem);
+ if (is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
+ return;
+ }
vcpu->arch.update_pte.gfn = gfn;
- vcpu->arch.update_pte.page = page;
+ vcpu->arch.update_pte.pfn = pfn;
}
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -1423,7 +1697,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
struct hlist_node *node, *n;
struct hlist_head *bucket;
unsigned index;
- u64 entry;
+ u64 entry, gentry;
u64 *spte;
unsigned offset = offset_in_page(gpa);
unsigned pte_size;
@@ -1433,8 +1707,9 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
int level;
int flooded = 0;
int npte;
+ int r;
- pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
+ pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
@@ -1450,7 +1725,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
vcpu->arch.last_pt_write_count = 1;
vcpu->arch.last_pte_updated = NULL;
}
- index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES;
+ index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
if (sp->gfn != gfn || sp->role.metaphysical)
@@ -1496,20 +1771,29 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
continue;
}
spte = &sp->spt[page_offset / sizeof(*spte)];
+ if ((gpa & (pte_size - 1)) || (bytes < pte_size)) {
+ gentry = 0;
+ r = kvm_read_guest_atomic(vcpu->kvm,
+ gpa & ~(u64)(pte_size - 1),
+ &gentry, pte_size);
+ new = (const void *)&gentry;
+ if (r < 0)
+ new = NULL;
+ }
while (npte--) {
entry = *spte;
mmu_pte_write_zap_pte(vcpu, sp, spte);
- mmu_pte_write_new_pte(vcpu, sp, spte, new, bytes,
- page_offset & (pte_size - 1));
+ if (new)
+ mmu_pte_write_new_pte(vcpu, sp, spte, new);
mmu_pte_write_flush_tlb(vcpu, entry, *spte);
++spte;
}
}
kvm_mmu_audit(vcpu, "post pte write");
spin_unlock(&vcpu->kvm->mmu_lock);
- if (vcpu->arch.update_pte.page) {
- kvm_release_page_clean(vcpu->arch.update_pte.page);
- vcpu->arch.update_pte.page = NULL;
+ if (!is_error_pfn(vcpu->arch.update_pte.pfn)) {
+ kvm_release_pfn_clean(vcpu->arch.update_pte.pfn);
+ vcpu->arch.update_pte.pfn = bad_pfn;
}
}
@@ -1518,9 +1802,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
gpa_t gpa;
int r;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gva);
- up_read(&vcpu->kvm->slots_lock);
spin_lock(&vcpu->kvm->mmu_lock);
r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
@@ -1577,6 +1859,12 @@ out:
}
EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
+void kvm_enable_tdp(void)
+{
+ tdp_enabled = true;
+}
+EXPORT_SYMBOL_GPL(kvm_enable_tdp);
+
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
struct kvm_mmu_page *sp;
@@ -1677,7 +1965,53 @@ void kvm_mmu_zap_all(struct kvm *kvm)
kvm_flush_remote_tlbs(kvm);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+{
+ struct kvm_mmu_page *page;
+
+ page = container_of(kvm->arch.active_mmu_pages.prev,
+ struct kvm_mmu_page, link);
+ kvm_mmu_zap_page(kvm, page);
+}
+
+static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+{
+ struct kvm *kvm;
+ struct kvm *kvm_freed = NULL;
+ int cache_count = 0;
+
+ spin_lock(&kvm_lock);
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ int npages;
+
+ spin_lock(&kvm->mmu_lock);
+ npages = kvm->arch.n_alloc_mmu_pages -
+ kvm->arch.n_free_mmu_pages;
+ cache_count += npages;
+ if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
+ kvm_mmu_remove_one_alloc_mmu_page(kvm);
+ cache_count--;
+ kvm_freed = kvm;
+ }
+ nr_to_scan--;
+
+ spin_unlock(&kvm->mmu_lock);
+ }
+ if (kvm_freed)
+ list_move_tail(&kvm_freed->vm_list, &vm_list);
+
+ spin_unlock(&kvm_lock);
+
+ return cache_count;
+}
+
+static struct shrinker mmu_shrinker = {
+ .shrink = mmu_shrink,
+ .seeks = DEFAULT_SEEKS * 10,
+};
+
+void mmu_destroy_caches(void)
{
if (pte_chain_cache)
kmem_cache_destroy(pte_chain_cache);
@@ -1687,6 +2021,12 @@ void kvm_mmu_module_exit(void)
kmem_cache_destroy(mmu_page_header_cache);
}
+void kvm_mmu_module_exit(void)
+{
+ mmu_destroy_caches();
+ unregister_shrinker(&mmu_shrinker);
+}
+
int kvm_mmu_module_init(void)
{
pte_chain_cache = kmem_cache_create("kvm_pte_chain",
@@ -1706,10 +2046,12 @@ int kvm_mmu_module_init(void)
if (!mmu_page_header_cache)
goto nomem;
+ register_shrinker(&mmu_shrinker);
+
return 0;
nomem:
- kvm_mmu_module_exit();
+ mmu_destroy_caches();
return -ENOMEM;
}
@@ -1732,6 +2074,127 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
return nr_mmu_pages;
}
+static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+ unsigned len)
+{
+ if (len > buffer->len)
+ return NULL;
+ return buffer->ptr;
+}
+
+static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer,
+ unsigned len)
+{
+ void *ret;
+
+ ret = pv_mmu_peek_buffer(buffer, len);
+ if (!ret)
+ return ret;
+ buffer->ptr += len;
+ buffer->len -= len;
+ buffer->processed += len;
+ return ret;
+}
+
+static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
+ gpa_t addr, gpa_t value)
+{
+ int bytes = 8;
+ int r;
+
+ if (!is_long_mode(vcpu) && !is_pae(vcpu))
+ bytes = 4;
+
+ r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ return r;
+
+ if (!emulator_write_phys(vcpu, addr, &value, bytes))
+ return -EFAULT;
+
+ return 1;
+}
+
+static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->tlb_flush(vcpu);
+ return 1;
+}
+
+static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
+{
+ spin_lock(&vcpu->kvm->mmu_lock);
+ mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT);
+ spin_unlock(&vcpu->kvm->mmu_lock);
+ return 1;
+}
+
+static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu,
+ struct kvm_pv_mmu_op_buffer *buffer)
+{
+ struct kvm_mmu_op_header *header;
+
+ header = pv_mmu_peek_buffer(buffer, sizeof *header);
+ if (!header)
+ return 0;
+ switch (header->op) {
+ case KVM_MMU_OP_WRITE_PTE: {
+ struct kvm_mmu_op_write_pte *wpte;
+
+ wpte = pv_mmu_read_buffer(buffer, sizeof *wpte);
+ if (!wpte)
+ return 0;
+ return kvm_pv_mmu_write(vcpu, wpte->pte_phys,
+ wpte->pte_val);
+ }
+ case KVM_MMU_OP_FLUSH_TLB: {
+ struct kvm_mmu_op_flush_tlb *ftlb;
+
+ ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb);
+ if (!ftlb)
+ return 0;
+ return kvm_pv_mmu_flush_tlb(vcpu);
+ }
+ case KVM_MMU_OP_RELEASE_PT: {
+ struct kvm_mmu_op_release_pt *rpt;
+
+ rpt = pv_mmu_read_buffer(buffer, sizeof *rpt);
+ if (!rpt)
+ return 0;
+ return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys);
+ }
+ default: return 0;
+ }
+}
+
+int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
+ gpa_t addr, unsigned long *ret)
+{
+ int r;
+ struct kvm_pv_mmu_op_buffer buffer;
+
+ buffer.ptr = buffer.buf;
+ buffer.len = min_t(unsigned long, bytes, sizeof buffer.buf);
+ buffer.processed = 0;
+
+ r = kvm_read_guest(vcpu->kvm, addr, buffer.buf, buffer.len);
+ if (r)
+ goto out;
+
+ while (buffer.len) {
+ r = kvm_pv_mmu_op_one(vcpu, &buffer);
+ if (r < 0)
+ goto out;
+ if (r == 0)
+ break;
+ }
+
+ r = 1;
+out:
+ *ret = buffer.processed;
+ return r;
+}
+
#ifdef AUDIT
static const char *audit_msg;
@@ -1768,8 +2231,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
audit_mappings_page(vcpu, ent, va, level - 1);
} else {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
- struct page *page = gpa_to_page(vcpu, gpa);
- hpa_t hpa = page_to_phys(page);
+ hpa_t hpa = (hpa_t)gpa_to_pfn(vcpu, gpa) << PAGE_SHIFT;
if (is_shadow_present_pte(ent)
&& (ent & PT64_BASE_ADDR_MASK) != hpa)
@@ -1782,7 +2244,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
&& !is_error_hpa(hpa))
printk(KERN_ERR "audit: (%s) notrap shadow,"
" valid guest gva %lx\n", audit_msg, va);
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
}
}
@@ -1867,7 +2329,7 @@ static void audit_rmap(struct kvm_vcpu *vcpu)
if (n_rmap != n_actual)
printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
- __FUNCTION__, audit_msg, n_rmap, n_actual);
+ __func__, audit_msg, n_rmap, n_actual);
}
static void audit_write_protection(struct kvm_vcpu *vcpu)
@@ -1887,7 +2349,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
if (*rmapp)
printk(KERN_ERR "%s: (%s) shadow page has writable"
" mappings: gfn %lx role %x\n",
- __FUNCTION__, audit_msg, sp->gfn,
+ __func__, audit_msg, sp->gfn,
sp->role.word);
}
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1fce19ec7a2..e64e9f56a65 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -3,6 +3,12 @@
#include <linux/kvm_host.h>
+#ifdef CONFIG_X86_64
+#define TDP_ROOT_LEVEL PT64_ROOT_LEVEL
+#else
+#define TDP_ROOT_LEVEL PT32E_ROOT_LEVEL
+#endif
+
static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
{
if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index ecc0856268c..156fe10288a 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -130,7 +130,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
unsigned index, pt_access, pte_access;
gpa_t pte_gpa;
- pgprintk("%s: addr %lx\n", __FUNCTION__, addr);
+ pgprintk("%s: addr %lx\n", __func__, addr);
walk:
walker->level = vcpu->arch.mmu.root_level;
pte = vcpu->arch.cr3;
@@ -155,7 +155,7 @@ walk:
pte_gpa += index * sizeof(pt_element_t);
walker->table_gfn[walker->level - 1] = table_gfn;
walker->pte_gpa[walker->level - 1] = pte_gpa;
- pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__,
+ pgprintk("%s: table_gfn[%d] %lx\n", __func__,
walker->level - 1, table_gfn);
kvm_read_guest(vcpu->kvm, pte_gpa, &pte, sizeof(pte));
@@ -222,7 +222,7 @@ walk:
walker->pt_access = pt_access;
walker->pte_access = pte_access;
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
- __FUNCTION__, (u64)pte, pt_access, pte_access);
+ __func__, (u64)pte, pt_access, pte_access);
return 1;
not_present:
@@ -243,31 +243,30 @@ err:
}
static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
- u64 *spte, const void *pte, int bytes,
- int offset_in_pte)
+ u64 *spte, const void *pte)
{
pt_element_t gpte;
unsigned pte_access;
- struct page *npage;
+ pfn_t pfn;
+ int largepage = vcpu->arch.update_pte.largepage;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
- if (!offset_in_pte && !is_present_pte(gpte))
+ if (!is_present_pte(gpte))
set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
return;
}
- if (bytes < sizeof(pt_element_t))
- return;
- pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
+ pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte);
if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn)
return;
- npage = vcpu->arch.update_pte.page;
- if (!npage)
+ pfn = vcpu->arch.update_pte.pfn;
+ if (is_error_pfn(pfn))
return;
- get_page(npage);
+ kvm_get_pfn(pfn);
mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
- gpte & PT_DIRTY_MASK, NULL, gpte_to_gfn(gpte), npage);
+ gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
+ pfn, true);
}
/*
@@ -275,8 +274,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
*/
static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *walker,
- int user_fault, int write_fault, int *ptwrite,
- struct page *page)
+ int user_fault, int write_fault, int largepage,
+ int *ptwrite, pfn_t pfn)
{
hpa_t shadow_addr;
int level;
@@ -304,11 +303,19 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
shadow_ent = ((u64 *)__va(shadow_addr)) + index;
if (level == PT_PAGE_TABLE_LEVEL)
break;
- if (is_shadow_present_pte(*shadow_ent)) {
+
+ if (largepage && level == PT_DIRECTORY_LEVEL)
+ break;
+
+ if (is_shadow_present_pte(*shadow_ent)
+ && !is_large_pte(*shadow_ent)) {
shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
continue;
}
+ if (is_large_pte(*shadow_ent))
+ rmap_remove(vcpu->kvm, shadow_ent);
+
if (level - 1 == PT_PAGE_TABLE_LEVEL
&& walker->level == PT_DIRECTORY_LEVEL) {
metaphysical = 1;
@@ -329,7 +336,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
walker->pte_gpa[level - 2],
&curr_pte, sizeof(curr_pte));
if (r || curr_pte != walker->ptes[level - 2]) {
- kvm_release_page_clean(page);
+ kvm_release_pfn_clean(pfn);
return NULL;
}
}
@@ -342,7 +349,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
mmu_set_spte(vcpu, shadow_ent, access, walker->pte_access & access,
user_fault, write_fault,
walker->ptes[walker->level-1] & PT_DIRTY_MASK,
- ptwrite, walker->gfn, page);
+ ptwrite, largepage, walker->gfn, pfn, false);
return shadow_ent;
}
@@ -371,16 +378,16 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
u64 *shadow_pte;
int write_pt = 0;
int r;
- struct page *page;
+ pfn_t pfn;
+ int largepage = 0;
- pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code);
+ pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
kvm_mmu_audit(vcpu, "pre page fault");
r = mmu_topup_memory_caches(vcpu);
if (r)
return r;
- down_read(&vcpu->kvm->slots_lock);
/*
* Look up the shadow pte for the faulting address.
*/
@@ -391,40 +398,45 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
* The page is not mapped by the guest. Let the guest handle it.
*/
if (!r) {
- pgprintk("%s: guest page fault\n", __FUNCTION__);
+ pgprintk("%s: guest page fault\n", __func__);
inject_page_fault(vcpu, addr, walker.error_code);
vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
- up_read(&vcpu->kvm->slots_lock);
return 0;
}
down_read(&current->mm->mmap_sem);
- page = gfn_to_page(vcpu->kvm, walker.gfn);
+ if (walker.level == PT_DIRECTORY_LEVEL) {
+ gfn_t large_gfn;
+ large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
+ if (is_largepage_backed(vcpu, large_gfn)) {
+ walker.gfn = large_gfn;
+ largepage = 1;
+ }
+ }
+ pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
up_read(&current->mm->mmap_sem);
+ /* mmio */
+ if (is_error_pfn(pfn)) {
+ pgprintk("gfn %x is mmio\n", walker.gfn);
+ kvm_release_pfn_clean(pfn);
+ return 1;
+ }
+
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
- &write_pt, page);
- pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__,
+ largepage, &write_pt, pfn);
+
+ pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __func__,
shadow_pte, *shadow_pte, write_pt);
if (!write_pt)
vcpu->arch.last_pt_write_count = 0; /* reset fork detector */
- /*
- * mmio: emulate if accessible, otherwise its a guest fault.
- */
- if (shadow_pte && is_io_pte(*shadow_pte)) {
- spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(&vcpu->kvm->slots_lock);
- return 1;
- }
-
++vcpu->stat.pf_fixed;
kvm_mmu_audit(vcpu, "post page fault (fixed)");
spin_unlock(&vcpu->kvm->mmu_lock);
- up_read(&vcpu->kvm->slots_lock);
return write_pt;
}
diff --git a/arch/x86/kvm/segment_descriptor.h b/arch/x86/kvm/segment_descriptor.h
deleted file mode 100644
index 56fc4c87338..00000000000
--- a/arch/x86/kvm/segment_descriptor.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __SEGMENT_DESCRIPTOR_H
-#define __SEGMENT_DESCRIPTOR_H
-
-struct segment_descriptor {
- u16 limit_low;
- u16 base_low;
- u8 base_mid;
- u8 type : 4;
- u8 system : 1;
- u8 dpl : 2;
- u8 present : 1;
- u8 limit_high : 4;
- u8 avl : 1;
- u8 long_mode : 1;
- u8 default_op : 1;
- u8 granularity : 1;
- u8 base_high;
-} __attribute__((packed));
-
-#ifdef CONFIG_X86_64
-/* LDT or TSS descriptor in the GDT. 16 bytes. */
-struct segment_descriptor_64 {
- struct segment_descriptor s;
- u32 base_higher;
- u32 pad_zero;
-};
-
-#endif
-#endif
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1a582f1090e..89e0be2c10d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -47,6 +47,18 @@ MODULE_LICENSE("GPL");
#define SVM_FEATURE_LBRV (1 << 1)
#define SVM_DEATURE_SVML (1 << 2)
+#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+
+/* enable NPT for AMD64 and X86 with PAE */
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static bool npt_enabled = true;
+#else
+static bool npt_enabled = false;
+#endif
+static int npt = 1;
+
+module_param(npt, int, S_IRUGO);
+
static void kvm_reput_irq(struct vcpu_svm *svm);
static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
@@ -54,8 +66,7 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
return container_of(vcpu, struct vcpu_svm, vcpu);
}
-unsigned long iopm_base;
-unsigned long msrpm_base;
+static unsigned long iopm_base;
struct kvm_ldttss_desc {
u16 limit0;
@@ -182,7 +193,7 @@ static inline void flush_guest_tlb(struct kvm_vcpu *vcpu)
static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (!(efer & EFER_LMA))
+ if (!npt_enabled && !(efer & EFER_LMA))
efer &= ~EFER_LME;
to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK;
@@ -219,12 +230,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
if (!svm->next_rip) {
- printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__);
+ printk(KERN_DEBUG "%s: NOP\n", __func__);
return;
}
if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE)
printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n",
- __FUNCTION__,
+ __func__,
svm->vmcb->save.rip,
svm->next_rip);
@@ -279,11 +290,7 @@ static void svm_hardware_enable(void *garbage)
struct svm_cpu_data *svm_data;
uint64_t efer;
-#ifdef CONFIG_X86_64
- struct desc_ptr gdt_descr;
-#else
struct desc_ptr gdt_descr;
-#endif
struct desc_struct *gdt;
int me = raw_smp_processor_id();
@@ -302,7 +309,6 @@ static void svm_hardware_enable(void *garbage)
svm_data->asid_generation = 1;
svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
svm_data->next_asid = svm_data->max_asid + 1;
- svm_features = cpuid_edx(SVM_CPUID_FUNC);
asm volatile ("sgdt %0" : "=m"(gdt_descr));
gdt = (struct desc_struct *)gdt_descr.address;
@@ -361,12 +367,51 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
BUG();
}
+static void svm_vcpu_init_msrpm(u32 *msrpm)
+{
+ memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+#ifdef CONFIG_X86_64
+ set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
+ set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
+ set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
+ set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
+ set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
+ set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
+#endif
+ set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_SYSENTER_ESP, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_SYSENTER_EIP, 1, 1);
+}
+
+static void svm_enable_lbrv(struct vcpu_svm *svm)
+{
+ u32 *msrpm = svm->msrpm;
+
+ svm->vmcb->control.lbr_ctl = 1;
+ set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
+ set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+}
+
+static void svm_disable_lbrv(struct vcpu_svm *svm)
+{
+ u32 *msrpm = svm->msrpm;
+
+ svm->vmcb->control.lbr_ctl = 0;
+ set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
+ set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
+ set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
+ set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+}
+
static __init int svm_hardware_setup(void)
{
int cpu;
struct page *iopm_pages;
- struct page *msrpm_pages;
- void *iopm_va, *msrpm_va;
+ void *iopm_va;
int r;
iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER);
@@ -379,41 +424,33 @@ static __init int svm_hardware_setup(void)
clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */
iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+ if (boot_cpu_has(X86_FEATURE_NX))
+ kvm_enable_efer_bits(EFER_NX);
- msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+ for_each_online_cpu(cpu) {
+ r = svm_cpu_init(cpu);
+ if (r)
+ goto err;
+ }
- r = -ENOMEM;
- if (!msrpm_pages)
- goto err_1;
+ svm_features = cpuid_edx(SVM_CPUID_FUNC);
- msrpm_va = page_address(msrpm_pages);
- memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
- msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT;
+ if (!svm_has(SVM_FEATURE_NPT))
+ npt_enabled = false;
-#ifdef CONFIG_X86_64
- set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1);
- set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1);
- set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1);
- set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1);
- set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1);
- set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1);
-#endif
- set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1);
- set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1);
- set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1);
- set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1);
+ if (npt_enabled && !npt) {
+ printk(KERN_INFO "kvm: Nested Paging disabled\n");
+ npt_enabled = false;
+ }
- for_each_online_cpu(cpu) {
- r = svm_cpu_init(cpu);
- if (r)
- goto err_2;
+ if (npt_enabled) {
+ printk(KERN_INFO "kvm: Nested Paging enabled\n");
+ kvm_enable_tdp();
}
+
return 0;
-err_2:
- __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
- msrpm_base = 0;
-err_1:
+err:
__free_pages(iopm_pages, IOPM_ALLOC_ORDER);
iopm_base = 0;
return r;
@@ -421,9 +458,8 @@ err_1:
static __exit void svm_hardware_unsetup(void)
{
- __free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER);
__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
- iopm_base = msrpm_base = 0;
+ iopm_base = 0;
}
static void init_seg(struct vmcb_seg *seg)
@@ -443,15 +479,14 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
seg->base = 0;
}
-static void init_vmcb(struct vmcb *vmcb)
+static void init_vmcb(struct vcpu_svm *svm)
{
- struct vmcb_control_area *control = &vmcb->control;
- struct vmcb_save_area *save = &vmcb->save;
+ struct vmcb_control_area *control = &svm->vmcb->control;
+ struct vmcb_save_area *save = &svm->vmcb->save;
control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
- INTERCEPT_CR4_MASK |
- INTERCEPT_CR8_MASK;
+ INTERCEPT_CR4_MASK;
control->intercept_cr_write = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
@@ -471,23 +506,13 @@ static void init_vmcb(struct vmcb *vmcb)
INTERCEPT_DR7_MASK;
control->intercept_exceptions = (1 << PF_VECTOR) |
- (1 << UD_VECTOR);
+ (1 << UD_VECTOR) |
+ (1 << MC_VECTOR);
control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
- /*
- * selective cr0 intercept bug?
- * 0: 0f 22 d8 mov %eax,%cr3
- * 3: 0f 20 c0 mov %cr0,%eax
- * 6: 0d 00 00 00 80 or $0x80000000,%eax
- * b: 0f 22 c0 mov %eax,%cr0
- * set cr3 ->interception
- * get cr0 ->interception
- * set cr0 -> no interception
- */
- /* (1ULL << INTERCEPT_SELECTIVE_CR0) | */
(1ULL << INTERCEPT_CPUID) |
(1ULL << INTERCEPT_INVD) |
(1ULL << INTERCEPT_HLT) |
@@ -508,7 +533,7 @@ static void init_vmcb(struct vmcb *vmcb)
(1ULL << INTERCEPT_MWAIT);
control->iopm_base_pa = iopm_base;
- control->msrpm_base_pa = msrpm_base;
+ control->msrpm_base_pa = __pa(svm->msrpm);
control->tsc_offset = 0;
control->int_ctl = V_INTR_MASKING_MASK;
@@ -550,13 +575,30 @@ static void init_vmcb(struct vmcb *vmcb)
save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
+
+ if (npt_enabled) {
+ /* Setup VMCB for Nested Paging */
+ control->nested_ctl = 1;
+ control->intercept &= ~(1ULL << INTERCEPT_TASK_SWITCH);
+ control->intercept_exceptions &= ~(1 << PF_VECTOR);
+ control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK|
+ INTERCEPT_CR3_MASK);
+ control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
+ INTERCEPT_CR3_MASK);
+ save->g_pat = 0x0007040600070406ULL;
+ /* enable caching because the QEMU Bios doesn't enable it */
+ save->cr0 = X86_CR0_ET;
+ save->cr3 = 0;
+ save->cr4 = 0;
+ }
+ force_new_asid(&svm->vcpu);
}
static int svm_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- init_vmcb(svm->vmcb);
+ init_vmcb(svm);
if (vcpu->vcpu_id != 0) {
svm->vmcb->save.rip = 0;
@@ -571,6 +613,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
{
struct vcpu_svm *svm;
struct page *page;
+ struct page *msrpm_pages;
int err;
svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
@@ -589,12 +632,19 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
goto uninit;
}
+ err = -ENOMEM;
+ msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
+ if (!msrpm_pages)
+ goto uninit;
+ svm->msrpm = page_address(msrpm_pages);
+ svm_vcpu_init_msrpm(svm->msrpm);
+
svm->vmcb = page_address(page);
clear_page(svm->vmcb);
svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
svm->asid_generation = 0;
memset(svm->db_regs, 0, sizeof(svm->db_regs));
- init_vmcb(svm->vmcb);
+ init_vmcb(svm);
fx_init(&svm->vcpu);
svm->vcpu.fpu_active = 1;
@@ -617,6 +667,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
+ __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, svm);
}
@@ -731,6 +782,13 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
var->unusable = !var->present;
}
+static int svm_get_cpl(struct kvm_vcpu *vcpu)
+{
+ struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save;
+
+ return save->cpl;
+}
+
static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -784,6 +842,9 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
}
#endif
+ if (npt_enabled)
+ goto set;
+
if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
vcpu->fpu_active = 1;
@@ -791,18 +852,29 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
vcpu->arch.cr0 = cr0;
cr0 |= X86_CR0_PG | X86_CR0_WP;
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
if (!vcpu->fpu_active) {
svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
cr0 |= X86_CR0_TS;
}
+set:
+ /*
+ * re-enable caching here because the QEMU bios
+ * does not do it - this results in some delay at
+ * reboot
+ */
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
}
static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
- vcpu->arch.cr4 = cr4;
- to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE;
+ unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+
+ vcpu->arch.cr4 = cr4;
+ if (!npt_enabled)
+ cr4 |= X86_CR4_PAE;
+ cr4 |= host_cr4_mce;
+ to_svm(vcpu)->vmcb->save.cr4 = cr4;
}
static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -833,13 +905,6 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
}
-/* FIXME:
-
- svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK;
- svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK);
-
-*/
-
static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
{
return -EOPNOTSUPP;
@@ -920,7 +985,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
}
default:
printk(KERN_DEBUG "%s: unexpected dr %u\n",
- __FUNCTION__, dr);
+ __func__, dr);
*exception = UD_VECTOR;
return;
}
@@ -962,6 +1027,19 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
return 1;
}
+static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+ /*
+ * On an #MC intercept the MCE handler is not called automatically in
+ * the host. So do it by hand here.
+ */
+ asm volatile (
+ "int $0x12\n");
+ /* not sure if we ever come back to this point */
+
+ return 1;
+}
+
static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
{
/*
@@ -969,7 +1047,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
* so reinitialize it.
*/
clear_page(svm->vmcb);
- init_vmcb(svm->vmcb);
+ init_vmcb(svm);
kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
return 0;
@@ -1033,9 +1111,18 @@ static int invalid_op_interception(struct vcpu_svm *svm,
static int task_switch_interception(struct vcpu_svm *svm,
struct kvm_run *kvm_run)
{
- pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__);
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- return 0;
+ u16 tss_selector;
+
+ tss_selector = (u16)svm->vmcb->control.exit_info_1;
+ if (svm->vmcb->control.exit_info_2 &
+ (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET))
+ return kvm_task_switch(&svm->vcpu, tss_selector,
+ TASK_SWITCH_IRET);
+ if (svm->vmcb->control.exit_info_2 &
+ (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP))
+ return kvm_task_switch(&svm->vcpu, tss_selector,
+ TASK_SWITCH_JMP);
+ return kvm_task_switch(&svm->vcpu, tss_selector, TASK_SWITCH_CALL);
}
static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
@@ -1049,7 +1136,7 @@ static int emulate_on_interception(struct vcpu_svm *svm,
struct kvm_run *kvm_run)
{
if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
- pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__);
+ pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
return 1;
}
@@ -1179,8 +1266,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
svm->vmcb->save.sysenter_esp = data;
break;
case MSR_IA32_DEBUGCTLMSR:
- pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
- __FUNCTION__, data);
+ if (!svm_has(SVM_FEATURE_LBRV)) {
+ pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n",
+ __func__, data);
+ break;
+ }
+ if (data & DEBUGCTL_RESERVED_BITS)
+ return 1;
+
+ svm->vmcb->save.dbgctl = data;
+ if (data & (1ULL<<0))
+ svm_enable_lbrv(svm);
+ else
+ svm_disable_lbrv(svm);
break;
case MSR_K7_EVNTSEL0:
case MSR_K7_EVNTSEL1:
@@ -1265,6 +1363,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
[SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
[SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
+ [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
[SVM_EXIT_INTR] = nop_on_interception,
[SVM_EXIT_NMI] = nop_on_interception,
[SVM_EXIT_SMI] = nop_on_interception,
@@ -1290,14 +1389,34 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
[SVM_EXIT_WBINVD] = emulate_on_interception,
[SVM_EXIT_MONITOR] = invalid_op_interception,
[SVM_EXIT_MWAIT] = invalid_op_interception,
+ [SVM_EXIT_NPF] = pf_interception,
};
-
static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u32 exit_code = svm->vmcb->control.exit_code;
+ if (npt_enabled) {
+ int mmu_reload = 0;
+ if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
+ svm_set_cr0(vcpu, svm->vmcb->save.cr0);
+ mmu_reload = 1;
+ }
+ vcpu->arch.cr0 = svm->vmcb->save.cr0;
+ vcpu->arch.cr3 = svm->vmcb->save.cr3;
+ if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
+ if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ }
+ if (mmu_reload) {
+ kvm_mmu_reset_context(vcpu);
+ kvm_mmu_load(vcpu);
+ }
+ }
+
kvm_reput_irq(svm);
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
@@ -1308,10 +1427,11 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
}
if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
- exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR)
+ exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
+ exit_code != SVM_EXIT_NPF)
printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x "
"exit_code 0x%x\n",
- __FUNCTION__, svm->vmcb->control.exit_int_info,
+ __func__, svm->vmcb->control.exit_int_info,
exit_code);
if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
@@ -1364,6 +1484,27 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq)
svm_inject_irq(svm, irq);
}
+static void update_cr8_intercept(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct vmcb *vmcb = svm->vmcb;
+ int max_irr, tpr;
+
+ if (!irqchip_in_kernel(vcpu->kvm) || vcpu->arch.apic->vapic_addr)
+ return;
+
+ vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+
+ max_irr = kvm_lapic_find_highest_irr(vcpu);
+ if (max_irr == -1)
+ return;
+
+ tpr = kvm_lapic_get_cr8(vcpu) << 4;
+
+ if (tpr >= (max_irr & 0xf0))
+ vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK;
+}
+
static void svm_intr_assist(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1376,14 +1517,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
SVM_EVTINJ_VEC_MASK;
vmcb->control.exit_int_info = 0;
svm_inject_irq(svm, intr_vector);
- return;
+ goto out;
}
if (vmcb->control.int_ctl & V_IRQ_MASK)
- return;
+ goto out;
if (!kvm_cpu_has_interrupt(vcpu))
- return;
+ goto out;
if (!(vmcb->save.rflags & X86_EFLAGS_IF) ||
(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) ||
@@ -1391,12 +1532,14 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
/* unable to deliver irq, set pending irq */
vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR);
svm_inject_irq(svm, 0x0);
- return;
+ goto out;
}
/* Okay, we can deliver the interrupt: grab it and update PIC state. */
intr_vector = kvm_cpu_get_interrupt(vcpu);
svm_inject_irq(svm, intr_vector);
kvm_timer_intr_post(vcpu, intr_vector);
+out:
+ update_cr8_intercept(vcpu);
}
static void kvm_reput_irq(struct vcpu_svm *svm)
@@ -1482,6 +1625,29 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
{
}
+static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
+ int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
+ kvm_lapic_set_tpr(vcpu, cr8);
+ }
+}
+
+static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ u64 cr8;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return;
+
+ cr8 = kvm_get_cr8(vcpu);
+ svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
+ svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
+}
+
static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1491,6 +1657,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
pre_svm_run(svm);
+ sync_lapic_to_cr8(vcpu);
+
save_host_msrs(vcpu);
fs_selector = read_fs();
gs_selector = read_gs();
@@ -1499,6 +1667,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
svm->host_dr6 = read_dr6();
svm->host_dr7 = read_dr7();
svm->vmcb->save.cr2 = vcpu->arch.cr2;
+ /* required for live migration with NPT */
+ if (npt_enabled)
+ svm->vmcb->save.cr3 = vcpu->arch.cr3;
if (svm->vmcb->save.dr7 & 0xff) {
write_dr7(0);
@@ -1635,6 +1806,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
stgi();
+ sync_cr8_to_lapic(vcpu);
+
svm->next_rip = 0;
}
@@ -1642,6 +1815,12 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (npt_enabled) {
+ svm->vmcb->control.nested_cr3 = root;
+ force_new_asid(vcpu);
+ return;
+ }
+
svm->vmcb->save.cr3 = root;
force_new_asid(vcpu);
@@ -1709,6 +1888,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.get_segment_base = svm_get_segment_base,
.get_segment = svm_get_segment,
.set_segment = svm_set_segment,
+ .get_cpl = svm_get_cpl,
.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
.set_cr0 = svm_set_cr0,
diff --git a/arch/x86/kvm/svm.h b/arch/x86/kvm/svm.h
index 5fd50491b55..1b8afa78e86 100644
--- a/arch/x86/kvm/svm.h
+++ b/arch/x86/kvm/svm.h
@@ -238,6 +238,9 @@ struct __attribute__ ((__packed__)) vmcb {
#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID
#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR
+#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
+#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+
#define SVM_EXIT_READ_CR0 0x000
#define SVM_EXIT_READ_CR3 0x003
#define SVM_EXIT_READ_CR4 0x004
diff --git a/arch/x86/kvm/tss.h b/arch/x86/kvm/tss.h
new file mode 100644
index 00000000000..622aa10f692
--- /dev/null
+++ b/arch/x86/kvm/tss.h
@@ -0,0 +1,59 @@
+#ifndef __TSS_SEGMENT_H
+#define __TSS_SEGMENT_H
+
+struct tss_segment_32 {
+ u32 prev_task_link;
+ u32 esp0;
+ u32 ss0;
+ u32 esp1;
+ u32 ss1;
+ u32 esp2;
+ u32 ss2;
+ u32 cr3;
+ u32 eip;
+ u32 eflags;
+ u32 eax;
+ u32 ecx;
+ u32 edx;
+ u32 ebx;
+ u32 esp;
+ u32 ebp;
+ u32 esi;
+ u32 edi;
+ u32 es;
+ u32 cs;
+ u32 ss;
+ u32 ds;
+ u32 fs;
+ u32 gs;
+ u32 ldt_selector;
+ u16 t;
+ u16 io_map;
+};
+
+struct tss_segment_16 {
+ u16 prev_task_link;
+ u16 sp0;
+ u16 ss0;
+ u16 sp1;
+ u16 ss1;
+ u16 sp2;
+ u16 ss2;
+ u16 ip;
+ u16 flag;
+ u16 ax;
+ u16 cx;
+ u16 dx;
+ u16 bx;
+ u16 sp;
+ u16 bp;
+ u16 si;
+ u16 di;
+ u16 es;
+ u16 cs;
+ u16 ss;
+ u16 ds;
+ u16 ldt;
+};
+
+#endif
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8e1462880d1..8e5d6645b90 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -17,7 +17,6 @@
#include "irq.h"
#include "vmx.h"
-#include "segment_descriptor.h"
#include "mmu.h"
#include <linux/kvm_host.h>
@@ -37,6 +36,12 @@ MODULE_LICENSE("GPL");
static int bypass_guest_pf = 1;
module_param(bypass_guest_pf, bool, 0);
+static int enable_vpid = 1;
+module_param(enable_vpid, bool, 0);
+
+static int flexpriority_enabled = 1;
+module_param(flexpriority_enabled, bool, 0);
+
struct vmcs {
u32 revision_id;
u32 abort;
@@ -71,6 +76,7 @@ struct vcpu_vmx {
unsigned rip;
} irq;
} rmode;
+ int vpid;
};
static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
@@ -85,6 +91,10 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
static struct page *vmx_io_bitmap_a;
static struct page *vmx_io_bitmap_b;
+static struct page *vmx_msr_bitmap;
+
+static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
+static DEFINE_SPINLOCK(vmx_vpid_lock);
static struct vmcs_config {
int size;
@@ -176,6 +186,11 @@ static inline int is_external_interrupt(u32 intr_info)
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
+static inline int cpu_has_vmx_msr_bitmap(void)
+{
+ return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS);
+}
+
static inline int cpu_has_vmx_tpr_shadow(void)
{
return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW);
@@ -194,8 +209,9 @@ static inline int cpu_has_secondary_exec_ctrls(void)
static inline bool cpu_has_vmx_virtualize_apic_accesses(void)
{
- return (vmcs_config.cpu_based_2nd_exec_ctrl &
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+ return flexpriority_enabled
+ && (vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
}
static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
@@ -204,6 +220,12 @@ static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
(irqchip_in_kernel(kvm)));
}
+static inline int cpu_has_vmx_vpid(void)
+{
+ return (vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_ENABLE_VPID);
+}
+
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
int i;
@@ -214,6 +236,20 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
return -1;
}
+static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+{
+ struct {
+ u64 vpid : 16;
+ u64 rsvd : 48;
+ u64 gva;
+ } operand = { vpid, 0, gva };
+
+ asm volatile (ASM_VMX_INVVPID
+ /* CF==1 or ZF==1 --> rc = -1 */
+ "; ja 1f ; ud2 ; 1:"
+ : : "a"(&operand), "c"(ext) : "cc", "memory");
+}
+
static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
{
int i;
@@ -257,6 +293,14 @@ static void vcpu_clear(struct vcpu_vmx *vmx)
vmx->launched = 0;
}
+static inline void vpid_sync_vcpu_all(struct vcpu_vmx *vmx)
+{
+ if (vmx->vpid == 0)
+ return;
+
+ __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0);
+}
+
static unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
@@ -353,7 +397,7 @@ static void reload_tss(void)
* VT restores TR but not its size. Useless.
*/
struct descriptor_table gdt;
- struct segment_descriptor *descs;
+ struct desc_struct *descs;
get_gdt(&gdt);
descs = (void *)gdt.base;
@@ -485,11 +529,12 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u64 phys_addr = __pa(vmx->vmcs);
- u64 tsc_this, delta;
+ u64 tsc_this, delta, new_offset;
if (vcpu->cpu != cpu) {
vcpu_clear(vmx);
kvm_migrate_apic_timer(vcpu);
+ vpid_sync_vcpu_all(vmx);
}
if (per_cpu(current_vmcs, cpu) != vmx->vmcs) {
@@ -524,8 +569,11 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
* Make sure the time stamp counter is monotonous.
*/
rdtscll(tsc_this);
- delta = vcpu->arch.host_tsc - tsc_this;
- vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta);
+ if (tsc_this < vcpu->arch.host_tsc) {
+ delta = vcpu->arch.host_tsc - tsc_this;
+ new_offset = vmcs_read64(TSC_OFFSET) + delta;
+ vmcs_write64(TSC_OFFSET, new_offset);
+ }
}
}
@@ -596,7 +644,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
{
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
nr | INTR_TYPE_EXCEPTION
- | (has_error_code ? INTR_INFO_DELIEVER_CODE_MASK : 0)
+ | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
| INTR_INFO_VALID_MASK);
if (has_error_code)
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
@@ -959,6 +1007,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING;
opt = CPU_BASED_TPR_SHADOW |
+ CPU_BASED_USE_MSR_BITMAPS |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS,
&_cpu_based_exec_control) < 0)
@@ -971,7 +1020,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
if (_cpu_based_exec_control & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) {
min = 0;
opt = SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
- SECONDARY_EXEC_WBINVD_EXITING;
+ SECONDARY_EXEC_WBINVD_EXITING |
+ SECONDARY_EXEC_ENABLE_VPID;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
return -EIO;
@@ -1080,6 +1130,10 @@ static __init int hardware_setup(void)
{
if (setup_vmcs_config(&vmcs_config) < 0)
return -EIO;
+
+ if (boot_cpu_has(X86_FEATURE_NX))
+ kvm_enable_efer_bits(EFER_NX);
+
return alloc_kvm_area();
}
@@ -1214,7 +1268,7 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
printk(KERN_DEBUG "%s: tss fixup for long mode. \n",
- __FUNCTION__);
+ __func__);
vmcs_write32(GUEST_TR_AR_BYTES,
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
@@ -1239,6 +1293,11 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
#endif
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ vpid_sync_vcpu_all(to_vmx(vcpu));
+}
+
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
vcpu->arch.cr4 &= KVM_GUEST_CR4_MASK;
@@ -1275,6 +1334,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
+ vmx_flush_tlb(vcpu);
vmcs_writel(GUEST_CR3, cr3);
if (vcpu->arch.cr0 & X86_CR0_PE)
vmx_fpu_deactivate(vcpu);
@@ -1288,14 +1348,14 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
vcpu->arch.cr4 = cr4;
}
-#ifdef CONFIG_X86_64
-
static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
vcpu->arch.shadow_efer = efer;
+ if (!msr)
+ return;
if (efer & EFER_LMA) {
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS) |
@@ -1312,8 +1372,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
setup_msrs(vmx);
}
-#endif
-
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1344,6 +1402,20 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
var->unusable = (ar >> 16) & 1;
}
+static int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment kvm_seg;
+
+ if (!(vcpu->arch.cr0 & X86_CR0_PE)) /* if real mode */
+ return 0;
+
+ if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
+ return 3;
+
+ vmx_get_segment(vcpu, &kvm_seg, VCPU_SREG_CS);
+ return kvm_seg.selector & 3;
+}
+
static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
u32 ar;
@@ -1433,7 +1505,6 @@ static int init_rmode_tss(struct kvm *kvm)
int ret = 0;
int r;
- down_read(&kvm->slots_lock);
r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
if (r < 0)
goto out;
@@ -1456,7 +1527,6 @@ static int init_rmode_tss(struct kvm *kvm)
ret = 1;
out:
- up_read(&kvm->slots_lock);
return ret;
}
@@ -1494,6 +1564,46 @@ out:
return r;
}
+static void allocate_vpid(struct vcpu_vmx *vmx)
+{
+ int vpid;
+
+ vmx->vpid = 0;
+ if (!enable_vpid || !cpu_has_vmx_vpid())
+ return;
+ spin_lock(&vmx_vpid_lock);
+ vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS);
+ if (vpid < VMX_NR_VPIDS) {
+ vmx->vpid = vpid;
+ __set_bit(vpid, vmx_vpid_bitmap);
+ }
+ spin_unlock(&vmx_vpid_lock);
+}
+
+void vmx_disable_intercept_for_msr(struct page *msr_bitmap, u32 msr)
+{
+ void *va;
+
+ if (!cpu_has_vmx_msr_bitmap())
+ return;
+
+ /*
+ * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+ * have the write-low and read-high bitmap offsets the wrong way round.
+ * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+ */
+ va = kmap(msr_bitmap);
+ if (msr <= 0x1fff) {
+ __clear_bit(msr, va + 0x000); /* read-low */
+ __clear_bit(msr, va + 0x800); /* write-low */
+ } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+ msr &= 0x1fff;
+ __clear_bit(msr, va + 0x400); /* read-high */
+ __clear_bit(msr, va + 0xc00); /* write-high */
+ }
+ kunmap(msr_bitmap);
+}
+
/*
* Sets up the vmcs for emulated real mode.
*/
@@ -1511,6 +1621,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a));
vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b));
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, page_to_phys(vmx_msr_bitmap));
+
vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
/* Control */
@@ -1532,6 +1645,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
exec_control &=
~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ if (vmx->vpid == 0)
+ exec_control &= ~SECONDARY_EXEC_ENABLE_VPID;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
@@ -1613,6 +1728,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
u64 msr;
int ret;
+ down_read(&vcpu->kvm->slots_lock);
if (!init_rmode_tss(vmx->vcpu.kvm)) {
ret = -ENOMEM;
goto out;
@@ -1621,7 +1737,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.rmode.active = 0;
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
- set_cr8(&vmx->vcpu, 0);
+ kvm_set_cr8(&vmx->vcpu, 0);
msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
if (vmx->vcpu.vcpu_id == 0)
msr |= MSR_IA32_APICBASE_BSP;
@@ -1704,18 +1820,22 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write64(APIC_ACCESS_ADDR,
page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
+ if (vmx->vpid != 0)
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
vmx->vcpu.arch.cr0 = 0x60000010;
vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */
vmx_set_cr4(&vmx->vcpu, 0);
-#ifdef CONFIG_X86_64
vmx_set_efer(&vmx->vcpu, 0);
-#endif
vmx_fpu_activate(&vmx->vcpu);
update_exception_bitmap(&vmx->vcpu);
- return 0;
+ vpid_sync_vcpu_all(vmx);
+
+ ret = 0;
out:
+ up_read(&vcpu->kvm->slots_lock);
return ret;
}
@@ -1723,6 +1843,8 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ KVMTRACE_1D(INJ_VIRQ, vcpu, (u32)irq, handler);
+
if (vcpu->arch.rmode.active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = irq;
@@ -1844,7 +1966,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if ((vect_info & VECTORING_INFO_VALID_MASK) &&
!is_page_fault(intr_info))
printk(KERN_ERR "%s: unexpected, vectoring info 0x%x "
- "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info);
+ "intr info 0x%x\n", __func__, vect_info, intr_info);
if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) {
int irq = vect_info & VECTORING_INFO_VECTOR_MASK;
@@ -1869,10 +1991,12 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
error_code = 0;
rip = vmcs_readl(GUEST_RIP);
- if (intr_info & INTR_INFO_DELIEVER_CODE_MASK)
+ if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
if (is_page_fault(intr_info)) {
cr2 = vmcs_readl(EXIT_QUALIFICATION);
+ KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
+ (u32)((u64)cr2 >> 32), handler);
return kvm_mmu_page_fault(vcpu, cr2, error_code);
}
@@ -1901,6 +2025,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
++vcpu->stat.irq_exits;
+ KVMTRACE_1D(INTR, vcpu, vmcs_read32(VM_EXIT_INTR_INFO), handler);
return 1;
}
@@ -1958,25 +2083,27 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
reg = (exit_qualification >> 8) & 15;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
+ KVMTRACE_3D(CR_WRITE, vcpu, (u32)cr, (u32)vcpu->arch.regs[reg],
+ (u32)((u64)vcpu->arch.regs[reg] >> 32), handler);
switch (cr) {
case 0:
vcpu_load_rsp_rip(vcpu);
- set_cr0(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr0(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 3:
vcpu_load_rsp_rip(vcpu);
- set_cr3(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr3(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 4:
vcpu_load_rsp_rip(vcpu);
- set_cr4(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr4(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
case 8:
vcpu_load_rsp_rip(vcpu);
- set_cr8(vcpu, vcpu->arch.regs[reg]);
+ kvm_set_cr8(vcpu, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
if (irqchip_in_kernel(vcpu->kvm))
return 1;
@@ -1990,6 +2117,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.cr0 &= ~X86_CR0_TS;
vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
vmx_fpu_activate(vcpu);
+ KVMTRACE_0D(CLTS, vcpu, handler);
skip_emulated_instruction(vcpu);
return 1;
case 1: /*mov from cr*/
@@ -1998,18 +2126,24 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu_load_rsp_rip(vcpu);
vcpu->arch.regs[reg] = vcpu->arch.cr3;
vcpu_put_rsp_rip(vcpu);
+ KVMTRACE_3D(CR_READ, vcpu, (u32)cr,
+ (u32)vcpu->arch.regs[reg],
+ (u32)((u64)vcpu->arch.regs[reg] >> 32),
+ handler);
skip_emulated_instruction(vcpu);
return 1;
case 8:
vcpu_load_rsp_rip(vcpu);
- vcpu->arch.regs[reg] = get_cr8(vcpu);
+ vcpu->arch.regs[reg] = kvm_get_cr8(vcpu);
vcpu_put_rsp_rip(vcpu);
+ KVMTRACE_2D(CR_READ, vcpu, (u32)cr,
+ (u32)vcpu->arch.regs[reg], handler);
skip_emulated_instruction(vcpu);
return 1;
}
break;
case 3: /* lmsw */
- lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
+ kvm_lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f);
skip_emulated_instruction(vcpu);
return 1;
@@ -2049,6 +2183,7 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
val = 0;
}
vcpu->arch.regs[reg] = val;
+ KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
} else {
/* mov to dr */
}
@@ -2073,6 +2208,9 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
+ KVMTRACE_3D(MSR_READ, vcpu, ecx, (u32)data, (u32)(data >> 32),
+ handler);
+
/* 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;
@@ -2086,6 +2224,9 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u)
| ((u64)(vcpu->arch.regs[VCPU_REGS_RDX] & -1u) << 32);
+ KVMTRACE_3D(MSR_WRITE, vcpu, ecx, (u32)data, (u32)(data >> 32),
+ handler);
+
if (vmx_set_msr(vcpu, ecx, data) != 0) {
kvm_inject_gp(vcpu, 0);
return 1;
@@ -2110,6 +2251,9 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu,
cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+
+ KVMTRACE_0D(PEND_INTR, vcpu, handler);
+
/*
* If the user space waits to inject interrupts, exit as soon as
* possible
@@ -2152,6 +2296,8 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
offset = exit_qualification & 0xffful;
+ KVMTRACE_1D(APIC_ACCESS, vcpu, (u32)offset, handler);
+
er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
if (er != EMULATE_DONE) {
@@ -2163,6 +2309,20 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
+static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ unsigned long exit_qualification;
+ u16 tss_selector;
+ int reason;
+
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+ reason = (u32)exit_qualification >> 30;
+ tss_selector = exit_qualification;
+
+ return kvm_task_switch(vcpu, tss_selector, reason);
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -2185,6 +2345,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
[EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
[EXIT_REASON_APIC_ACCESS] = handle_apic_access,
[EXIT_REASON_WBINVD] = handle_wbinvd,
+ [EXIT_REASON_TASK_SWITCH] = handle_task_switch,
};
static const int kvm_vmx_max_exit_handlers =
@@ -2200,6 +2361,9 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 vectoring_info = vmx->idt_vectoring_info;
+ KVMTRACE_3D(VMEXIT, vcpu, exit_reason, (u32)vmcs_readl(GUEST_RIP),
+ (u32)((u64)vmcs_readl(GUEST_RIP) >> 32), entryexit);
+
if (unlikely(vmx->fail)) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
@@ -2210,7 +2374,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
exit_reason != EXIT_REASON_EXCEPTION_NMI)
printk(KERN_WARNING "%s: unexpected, valid vectoring info and "
- "exit reason is 0x%x\n", __FUNCTION__, exit_reason);
+ "exit reason is 0x%x\n", __func__, exit_reason);
if (exit_reason < kvm_vmx_max_exit_handlers
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run);
@@ -2221,10 +2385,6 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
return 0;
}
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
-{
-}
-
static void update_tpr_threshold(struct kvm_vcpu *vcpu)
{
int max_irr, tpr;
@@ -2285,11 +2445,13 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
return;
}
+ KVMTRACE_1D(REDELIVER_EVT, vcpu, idtv_info_field, handler);
+
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
- if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK))
+ if (unlikely(idtv_info_field & INTR_INFO_DELIVER_CODE_MASK))
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
vmcs_read32(IDT_VECTORING_ERROR_CODE));
if (unlikely(has_ext_irq))
@@ -2470,8 +2632,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
/* We need to handle NMIs before interrupts are enabled */
- if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */
+ if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) { /* nmi */
+ KVMTRACE_0D(NMI, vcpu, handler);
asm("int $2");
+ }
}
static void vmx_free_vmcs(struct kvm_vcpu *vcpu)
@@ -2489,6 +2653,10 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ spin_lock(&vmx_vpid_lock);
+ if (vmx->vpid != 0)
+ __clear_bit(vmx->vpid, vmx_vpid_bitmap);
+ spin_unlock(&vmx_vpid_lock);
vmx_free_vmcs(vcpu);
kfree(vmx->host_msrs);
kfree(vmx->guest_msrs);
@@ -2505,6 +2673,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!vmx)
return ERR_PTR(-ENOMEM);
+ allocate_vpid(vmx);
+
err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
if (err)
goto free_vcpu;
@@ -2591,14 +2761,13 @@ static struct kvm_x86_ops vmx_x86_ops = {
.get_segment_base = vmx_get_segment_base,
.get_segment = vmx_get_segment,
.set_segment = vmx_set_segment,
+ .get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr3 = vmx_set_cr3,
.set_cr4 = vmx_set_cr4,
-#ifdef CONFIG_X86_64
.set_efer = vmx_set_efer,
-#endif
.get_idt = vmx_get_idt,
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
@@ -2626,7 +2795,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
static int __init vmx_init(void)
{
- void *iova;
+ void *va;
int r;
vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
@@ -2639,28 +2808,48 @@ static int __init vmx_init(void)
goto out;
}
+ vmx_msr_bitmap = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+ if (!vmx_msr_bitmap) {
+ r = -ENOMEM;
+ goto out1;
+ }
+
/*
* Allow direct access to the PC debug port (it is often used for I/O
* delays, but the vmexits simply slow things down).
*/
- iova = kmap(vmx_io_bitmap_a);
- memset(iova, 0xff, PAGE_SIZE);
- clear_bit(0x80, iova);
+ va = kmap(vmx_io_bitmap_a);
+ memset(va, 0xff, PAGE_SIZE);
+ clear_bit(0x80, va);
kunmap(vmx_io_bitmap_a);
- iova = kmap(vmx_io_bitmap_b);
- memset(iova, 0xff, PAGE_SIZE);
+ va = kmap(vmx_io_bitmap_b);
+ memset(va, 0xff, PAGE_SIZE);
kunmap(vmx_io_bitmap_b);
+ va = kmap(vmx_msr_bitmap);
+ memset(va, 0xff, PAGE_SIZE);
+ kunmap(vmx_msr_bitmap);
+
+ set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
if (r)
- goto out1;
+ goto out2;
+
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_FS_BASE);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_GS_BASE);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_CS);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
+ vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
if (bypass_guest_pf)
kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
return 0;
+out2:
+ __free_page(vmx_msr_bitmap);
out1:
__free_page(vmx_io_bitmap_b);
out:
@@ -2670,6 +2859,7 @@ out:
static void __exit vmx_exit(void)
{
+ __free_page(vmx_msr_bitmap);
__free_page(vmx_io_bitmap_b);
__free_page(vmx_io_bitmap_a);
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index d52ae8d7303..5dff4606b98 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -49,6 +49,7 @@
* Definitions of Secondary Processor-Based VM-Execution Controls.
*/
#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
@@ -65,6 +66,7 @@
/* VMCS Encodings */
enum vmcs_field {
+ VIRTUAL_PROCESSOR_ID = 0x00000000,
GUEST_ES_SELECTOR = 0x00000800,
GUEST_CS_SELECTOR = 0x00000802,
GUEST_SS_SELECTOR = 0x00000804,
@@ -231,12 +233,12 @@ enum vmcs_field {
*/
#define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */
#define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */
-#define INTR_INFO_DELIEVER_CODE_MASK 0x800 /* 11 */
+#define INTR_INFO_DELIVER_CODE_MASK 0x800 /* 11 */
#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */
#define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK
#define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK
-#define VECTORING_INFO_DELIEVER_CODE_MASK INTR_INFO_DELIEVER_CODE_MASK
+#define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK
#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK
#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */
@@ -321,4 +323,8 @@ enum vmcs_field {
#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT 9
+#define VMX_NR_VPIDS (1 << 16)
+#define VMX_VPID_EXTENT_SINGLE_CONTEXT 1
+#define VMX_VPID_EXTENT_ALL_CONTEXT 2
+
#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6b01552bd1f..0ce556372a4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -15,10 +15,12 @@
*/
#include <linux/kvm_host.h>
-#include "segment_descriptor.h"
#include "irq.h"
#include "mmu.h"
+#include "i8254.h"
+#include "tss.h"
+#include <linux/clocksource.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
@@ -28,6 +30,7 @@
#include <asm/uaccess.h>
#include <asm/msr.h>
+#include <asm/desc.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
@@ -41,7 +44,15 @@
| X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
-#define EFER_RESERVED_BITS 0xfffffffffffff2fe
+/* EFER defaults:
+ * - enable syscall per default because its emulated by KVM
+ * - enable LME and LMA per default on 64 bit KVM
+ */
+#ifdef CONFIG_X86_64
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL;
+#else
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
+#endif
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@@ -63,6 +74,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "irq_window", VCPU_STAT(irq_window_exits) },
{ "halt_exits", VCPU_STAT(halt_exits) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+ { "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
{ "irq_exits", VCPU_STAT(irq_exits) },
{ "host_state_reload", VCPU_STAT(host_state_reload) },
@@ -78,6 +90,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_recycled", VM_STAT(mmu_recycled) },
{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
+ { "largepages", VM_STAT(lpages) },
{ NULL }
};
@@ -85,7 +98,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
unsigned long segment_base(u16 selector)
{
struct descriptor_table gdt;
- struct segment_descriptor *d;
+ struct desc_struct *d;
unsigned long table_base;
unsigned long v;
@@ -101,13 +114,12 @@ unsigned long segment_base(u16 selector)
asm("sldt %0" : "=g"(ldt_selector));
table_base = segment_base(ldt_selector);
}
- d = (struct segment_descriptor *)(table_base + (selector & ~7));
- v = d->base_low | ((unsigned long)d->base_mid << 16) |
- ((unsigned long)d->base_high << 24);
+ d = (struct desc_struct *)(table_base + (selector & ~7));
+ v = d->base0 | ((unsigned long)d->base1 << 16) |
+ ((unsigned long)d->base2 << 24);
#ifdef CONFIG_X86_64
- if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
- v |= ((unsigned long) \
- ((struct segment_descriptor_64 *)d)->base_higher) << 32;
+ if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
#endif
return v;
}
@@ -145,11 +157,16 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
u32 error_code)
{
++vcpu->stat.pf_guest;
- if (vcpu->arch.exception.pending && vcpu->arch.exception.nr == PF_VECTOR) {
- printk(KERN_DEBUG "kvm: inject_page_fault:"
- " double fault 0x%lx\n", addr);
- vcpu->arch.exception.nr = DF_VECTOR;
- vcpu->arch.exception.error_code = 0;
+ if (vcpu->arch.exception.pending) {
+ if (vcpu->arch.exception.nr == PF_VECTOR) {
+ printk(KERN_DEBUG "kvm: inject_page_fault:"
+ " double fault 0x%lx\n", addr);
+ vcpu->arch.exception.nr = DF_VECTOR;
+ vcpu->arch.exception.error_code = 0;
+ } else if (vcpu->arch.exception.nr == DF_VECTOR) {
+ /* triple fault -> shutdown */
+ set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+ }
return;
}
vcpu->arch.cr2 = addr;
@@ -184,7 +201,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
int ret;
u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
- down_read(&vcpu->kvm->slots_lock);
ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
offset * sizeof(u64), sizeof(pdpte));
if (ret < 0) {
@@ -201,10 +217,10 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
out:
- up_read(&vcpu->kvm->slots_lock);
return ret;
}
+EXPORT_SYMBOL_GPL(load_pdptrs);
static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
@@ -215,18 +231,16 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
if (is_long_mode(vcpu) || !is_pae(vcpu))
return false;
- down_read(&vcpu->kvm->slots_lock);
r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
if (r < 0)
goto out;
changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
out:
- up_read(&vcpu->kvm->slots_lock);
return changed;
}
-void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
if (cr0 & CR0_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
@@ -284,15 +298,18 @@ void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
kvm_mmu_reset_context(vcpu);
return;
}
-EXPORT_SYMBOL_GPL(set_cr0);
+EXPORT_SYMBOL_GPL(kvm_set_cr0);
-void lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
+void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+ kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+ KVMTRACE_1D(LMSW, vcpu,
+ (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)),
+ handler);
}
-EXPORT_SYMBOL_GPL(lmsw);
+EXPORT_SYMBOL_GPL(kvm_lmsw);
-void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
if (cr4 & CR4_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
@@ -323,9 +340,9 @@ void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
vcpu->arch.cr4 = cr4;
kvm_mmu_reset_context(vcpu);
}
-EXPORT_SYMBOL_GPL(set_cr4);
+EXPORT_SYMBOL_GPL(kvm_set_cr4);
-void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
kvm_mmu_flush_tlb(vcpu);
@@ -359,7 +376,6 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
*/
}
- down_read(&vcpu->kvm->slots_lock);
/*
* Does the new cr3 value map to physical memory? (Note, we
* catch an invalid cr3 even in real-mode, because it would
@@ -375,11 +391,10 @@ void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
vcpu->arch.cr3 = cr3;
vcpu->arch.mmu.new_cr3(vcpu);
}
- up_read(&vcpu->kvm->slots_lock);
}
-EXPORT_SYMBOL_GPL(set_cr3);
+EXPORT_SYMBOL_GPL(kvm_set_cr3);
-void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
+void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
if (cr8 & CR8_RESERVED_BITS) {
printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
@@ -391,16 +406,16 @@ void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
else
vcpu->arch.cr8 = cr8;
}
-EXPORT_SYMBOL_GPL(set_cr8);
+EXPORT_SYMBOL_GPL(kvm_set_cr8);
-unsigned long get_cr8(struct kvm_vcpu *vcpu)
+unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
{
if (irqchip_in_kernel(vcpu->kvm))
return kvm_lapic_get_cr8(vcpu);
else
return vcpu->arch.cr8;
}
-EXPORT_SYMBOL_GPL(get_cr8);
+EXPORT_SYMBOL_GPL(kvm_get_cr8);
/*
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
@@ -415,7 +430,8 @@ static u32 msrs_to_save[] = {
#ifdef CONFIG_X86_64
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
- MSR_IA32_TIME_STAMP_COUNTER,
+ MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ MSR_IA32_PERF_STATUS,
};
static unsigned num_msrs_to_save;
@@ -424,11 +440,9 @@ static u32 emulated_msrs[] = {
MSR_IA32_MISC_ENABLE,
};
-#ifdef CONFIG_X86_64
-
static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (efer & EFER_RESERVED_BITS) {
+ if (efer & efer_reserved_bits) {
printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
efer);
kvm_inject_gp(vcpu, 0);
@@ -450,7 +464,12 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
vcpu->arch.shadow_efer = efer;
}
-#endif
+void kvm_enable_efer_bits(u64 mask)
+{
+ efer_reserved_bits &= ~mask;
+}
+EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
+
/*
* Writes msr value into into the appropriate "register".
@@ -470,26 +489,86 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
return kvm_set_msr(vcpu, index, *data);
}
+static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
+{
+ static int version;
+ struct kvm_wall_clock wc;
+ struct timespec wc_ts;
+
+ if (!wall_clock)
+ return;
+
+ version++;
+
+ kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+
+ wc_ts = current_kernel_time();
+ wc.wc_sec = wc_ts.tv_sec;
+ wc.wc_nsec = wc_ts.tv_nsec;
+ wc.wc_version = version;
+
+ kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
+
+ version++;
+ kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+}
+
+static void kvm_write_guest_time(struct kvm_vcpu *v)
+{
+ struct timespec ts;
+ unsigned long flags;
+ struct kvm_vcpu_arch *vcpu = &v->arch;
+ void *shared_kaddr;
+
+ if ((!vcpu->time_page))
+ return;
+
+ /* Keep irq disabled to prevent changes to the clock */
+ local_irq_save(flags);
+ kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
+ &vcpu->hv_clock.tsc_timestamp);
+ ktime_get_ts(&ts);
+ local_irq_restore(flags);
+
+ /* With all the info we got, fill in the values */
+
+ vcpu->hv_clock.system_time = ts.tv_nsec +
+ (NSEC_PER_SEC * (u64)ts.tv_sec);
+ /*
+ * The interface expects us to write an even number signaling that the
+ * update is finished. Since the guest won't see the intermediate
+ * state, we just write "2" at the end
+ */
+ vcpu->hv_clock.version = 2;
+
+ shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
+
+ memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
+
+ kunmap_atomic(shared_kaddr, KM_USER0);
+
+ mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+}
+
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
switch (msr) {
-#ifdef CONFIG_X86_64
case MSR_EFER:
set_efer(vcpu, data);
break;
-#endif
case MSR_IA32_MC0_STATUS:
pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
- __FUNCTION__, data);
+ __func__, data);
break;
case MSR_IA32_MCG_STATUS:
pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n",
- __FUNCTION__, data);
+ __func__, data);
break;
case MSR_IA32_MCG_CTL:
pr_unimpl(vcpu, "%s: MSR_IA32_MCG_CTL 0x%llx, nop\n",
- __FUNCTION__, data);
+ __func__, data);
break;
case MSR_IA32_UCODE_REV:
case MSR_IA32_UCODE_WRITE:
@@ -501,6 +580,42 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
+ case MSR_KVM_WALL_CLOCK:
+ vcpu->kvm->arch.wall_clock = data;
+ kvm_write_wall_clock(vcpu->kvm, data);
+ break;
+ case MSR_KVM_SYSTEM_TIME: {
+ if (vcpu->arch.time_page) {
+ kvm_release_page_dirty(vcpu->arch.time_page);
+ vcpu->arch.time_page = NULL;
+ }
+
+ vcpu->arch.time = data;
+
+ /* we verify if the enable bit is set... */
+ if (!(data & 1))
+ break;
+
+ /* ...but clean it before doing the actual write */
+ vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+
+ vcpu->arch.hv_clock.tsc_to_system_mul =
+ clocksource_khz2mult(tsc_khz, 22);
+ vcpu->arch.hv_clock.tsc_shift = 22;
+
+ down_read(&current->mm->mmap_sem);
+ vcpu->arch.time_page =
+ gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+ up_read(&current->mm->mmap_sem);
+
+ if (is_error_page(vcpu->arch.time_page)) {
+ kvm_release_page_clean(vcpu->arch.time_page);
+ vcpu->arch.time_page = NULL;
+ }
+
+ kvm_write_guest_time(vcpu);
+ break;
+ }
default:
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
return 1;
@@ -540,7 +655,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_IA32_MC0_MISC+12:
case MSR_IA32_MC0_MISC+16:
case MSR_IA32_UCODE_REV:
- case MSR_IA32_PERF_STATUS:
case MSR_IA32_EBL_CR_POWERON:
/* MTRR registers */
case 0xfe:
@@ -556,11 +670,21 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_IA32_MISC_ENABLE:
data = vcpu->arch.ia32_misc_enable_msr;
break;
-#ifdef CONFIG_X86_64
+ case MSR_IA32_PERF_STATUS:
+ /* TSC increment by tick */
+ data = 1000ULL;
+ /* CPU multiplier */
+ data |= (((uint64_t)4ULL) << 40);
+ break;
case MSR_EFER:
data = vcpu->arch.shadow_efer;
break;
-#endif
+ case MSR_KVM_WALL_CLOCK:
+ data = vcpu->kvm->arch.wall_clock;
+ break;
+ case MSR_KVM_SYSTEM_TIME:
+ data = vcpu->arch.time;
+ break;
default:
pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
return 1;
@@ -584,9 +708,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
vcpu_load(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
+ up_read(&vcpu->kvm->slots_lock);
vcpu_put(vcpu);
@@ -688,11 +814,24 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_USER_MEMORY:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
+ case KVM_CAP_CLOCKSOURCE:
+ case KVM_CAP_PIT:
+ case KVM_CAP_NOP_IO_DELAY:
+ case KVM_CAP_MP_STATE:
r = 1;
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
break;
+ case KVM_CAP_NR_VCPUS:
+ r = KVM_MAX_VCPUS;
+ break;
+ case KVM_CAP_NR_MEMSLOTS:
+ r = KVM_MEMORY_SLOTS;
+ break;
+ case KVM_CAP_PV_MMU:
+ r = !tdp_enabled;
+ break;
default:
r = 0;
break;
@@ -763,6 +902,7 @@ out:
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
kvm_x86_ops->vcpu_load(vcpu, cpu);
+ kvm_write_guest_time(vcpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -958,32 +1098,32 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
/* function 4 and 0xb have additional index. */
case 4: {
- int index, cache_type;
+ int i, cache_type;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until cache_type is zero */
- for (index = 1; *nent < maxnent; ++index) {
- cache_type = entry[index - 1].eax & 0x1f;
+ for (i = 1; *nent < maxnent; ++i) {
+ cache_type = entry[i - 1].eax & 0x1f;
if (!cache_type)
break;
- do_cpuid_1_ent(&entry[index], function, index);
- entry[index].flags |=
+ do_cpuid_1_ent(&entry[i], function, i);
+ entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
}
break;
}
case 0xb: {
- int index, level_type;
+ int i, level_type;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until level_type is zero */
- for (index = 1; *nent < maxnent; ++index) {
- level_type = entry[index - 1].ecx & 0xff;
+ for (i = 1; *nent < maxnent; ++i) {
+ level_type = entry[i - 1].ecx & 0xff;
if (!level_type)
break;
- do_cpuid_1_ent(&entry[index], function, index);
- entry[index].flags |=
+ do_cpuid_1_ent(&entry[i], function, i);
+ entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
}
@@ -1365,6 +1505,23 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
return r;
}
+static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+ int r = 0;
+
+ memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
+ return r;
+}
+
+static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+ int r = 0;
+
+ memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
+ kvm_pit_load_count(kvm, 0, ps->channels[0].count);
+ return r;
+}
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
@@ -1457,6 +1614,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
} else
goto out;
break;
+ case KVM_CREATE_PIT:
+ r = -ENOMEM;
+ kvm->arch.vpit = kvm_create_pit(kvm);
+ if (kvm->arch.vpit)
+ r = 0;
+ break;
case KVM_IRQ_LINE: {
struct kvm_irq_level irq_event;
@@ -1512,6 +1675,37 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = 0;
break;
}
+ case KVM_GET_PIT: {
+ struct kvm_pit_state ps;
+ r = -EFAULT;
+ if (copy_from_user(&ps, argp, sizeof ps))
+ goto out;
+ r = -ENXIO;
+ if (!kvm->arch.vpit)
+ goto out;
+ r = kvm_vm_ioctl_get_pit(kvm, &ps);
+ if (r)
+ goto out;
+ r = -EFAULT;
+ if (copy_to_user(argp, &ps, sizeof ps))
+ goto out;
+ r = 0;
+ break;
+ }
+ case KVM_SET_PIT: {
+ struct kvm_pit_state ps;
+ r = -EFAULT;
+ if (copy_from_user(&ps, argp, sizeof ps))
+ goto out;
+ r = -ENXIO;
+ if (!kvm->arch.vpit)
+ goto out;
+ r = kvm_vm_ioctl_set_pit(kvm, &ps);
+ if (r)
+ goto out;
+ r = 0;
+ break;
+ }
default:
;
}
@@ -1570,7 +1764,6 @@ int emulator_read_std(unsigned long addr,
void *data = val;
int r = X86EMUL_CONTINUE;
- down_read(&vcpu->kvm->slots_lock);
while (bytes) {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
unsigned offset = addr & (PAGE_SIZE-1);
@@ -1592,7 +1785,6 @@ int emulator_read_std(unsigned long addr,
addr += tocopy;
}
out:
- up_read(&vcpu->kvm->slots_lock);
return r;
}
EXPORT_SYMBOL_GPL(emulator_read_std);
@@ -1611,9 +1803,7 @@ static int emulator_read_emulated(unsigned long addr,
return X86EMUL_CONTINUE;
}
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
- up_read(&vcpu->kvm->slots_lock);
/* For APIC access vmexit */
if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
@@ -1646,19 +1836,15 @@ mmio:
return X86EMUL_UNHANDLEABLE;
}
-static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
- const void *val, int bytes)
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const void *val, int bytes)
{
int ret;
- down_read(&vcpu->kvm->slots_lock);
ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
- if (ret < 0) {
- up_read(&vcpu->kvm->slots_lock);
+ if (ret < 0)
return 0;
- }
kvm_mmu_pte_write(vcpu, gpa, val, bytes);
- up_read(&vcpu->kvm->slots_lock);
return 1;
}
@@ -1670,9 +1856,7 @@ static int emulator_write_emulated_onepage(unsigned long addr,
struct kvm_io_device *mmio_dev;
gpa_t gpa;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
- up_read(&vcpu->kvm->slots_lock);
if (gpa == UNMAPPED_GVA) {
kvm_inject_page_fault(vcpu, addr, 2);
@@ -1749,7 +1933,6 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
char *kaddr;
u64 val;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
if (gpa == UNMAPPED_GVA ||
@@ -1769,9 +1952,8 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
kunmap_atomic(kaddr, KM_USER0);
kvm_release_page_dirty(page);
- emul_write:
- up_read(&vcpu->kvm->slots_lock);
}
+emul_write:
#endif
return emulator_write_emulated(addr, new, bytes, vcpu);
@@ -1802,7 +1984,7 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
*dest = kvm_x86_ops->get_dr(vcpu, dr);
return X86EMUL_CONTINUE;
default:
- pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr);
+ pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
return X86EMUL_UNHANDLEABLE;
}
}
@@ -1840,7 +2022,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
-struct x86_emulate_ops emulate_ops = {
+static struct x86_emulate_ops emulate_ops = {
.read_std = emulator_read_std,
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
@@ -2091,6 +2273,13 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
vcpu->arch.pio.guest_page_offset = 0;
vcpu->arch.pio.rep = 0;
+ if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+ KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+ else
+ KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+
kvm_x86_ops->cache_regs(vcpu);
memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4);
kvm_x86_ops->decache_regs(vcpu);
@@ -2129,6 +2318,13 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
vcpu->arch.pio.guest_page_offset = offset_in_page(address);
vcpu->arch.pio.rep = rep;
+ if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+ KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+ else
+ KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+
if (!count) {
kvm_x86_ops->skip_emulated_instruction(vcpu);
return 1;
@@ -2163,10 +2359,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
kvm_x86_ops->skip_emulated_instruction(vcpu);
for (i = 0; i < nr_pages; ++i) {
- down_read(&vcpu->kvm->slots_lock);
page = gva_to_page(vcpu, address + i * PAGE_SIZE);
vcpu->arch.pio.guest_pages[i] = page;
- up_read(&vcpu->kvm->slots_lock);
if (!page) {
kvm_inject_gp(vcpu, 0);
free_pio_guest_pages(vcpu);
@@ -2238,10 +2432,13 @@ void kvm_arch_exit(void)
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
++vcpu->stat.halt_exits;
+ KVMTRACE_0D(HLT, vcpu, handler);
if (irqchip_in_kernel(vcpu->kvm)) {
- vcpu->arch.mp_state = VCPU_MP_STATE_HALTED;
+ vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+ up_read(&vcpu->kvm->slots_lock);
kvm_vcpu_block(vcpu);
- if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE)
+ down_read(&vcpu->kvm->slots_lock);
+ if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
return -EINTR;
return 1;
} else {
@@ -2251,9 +2448,19 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
+static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
+ unsigned long a1)
+{
+ if (is_long_mode(vcpu))
+ return a0;
+ else
+ return a0 | ((gpa_t)a1 << 32);
+}
+
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
+ int r = 1;
kvm_x86_ops->cache_regs(vcpu);
@@ -2263,6 +2470,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
a2 = vcpu->arch.regs[VCPU_REGS_RDX];
a3 = vcpu->arch.regs[VCPU_REGS_RSI];
+ KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler);
+
if (!is_long_mode(vcpu)) {
nr &= 0xFFFFFFFF;
a0 &= 0xFFFFFFFF;
@@ -2275,13 +2484,17 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
case KVM_HC_VAPIC_POLL_IRQ:
ret = 0;
break;
+ case KVM_HC_MMU_OP:
+ r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
+ break;
default:
ret = -KVM_ENOSYS;
break;
}
vcpu->arch.regs[VCPU_REGS_RAX] = ret;
kvm_x86_ops->decache_regs(vcpu);
- return 0;
+ ++vcpu->stat.hypercalls;
+ return r;
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -2329,7 +2542,7 @@ void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
unsigned long *rflags)
{
- lmsw(vcpu, msw);
+ kvm_lmsw(vcpu, msw);
*rflags = kvm_x86_ops->get_rflags(vcpu);
}
@@ -2346,9 +2559,9 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
case 4:
return vcpu->arch.cr4;
case 8:
- return get_cr8(vcpu);
+ return kvm_get_cr8(vcpu);
default:
- vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
+ vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
return 0;
}
}
@@ -2358,23 +2571,23 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
{
switch (cr) {
case 0:
- set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+ kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
*rflags = kvm_x86_ops->get_rflags(vcpu);
break;
case 2:
vcpu->arch.cr2 = val;
break;
case 3:
- set_cr3(vcpu, val);
+ kvm_set_cr3(vcpu, val);
break;
case 4:
- set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
+ kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val));
break;
case 8:
- set_cr8(vcpu, val & 0xfUL);
+ kvm_set_cr8(vcpu, val & 0xfUL);
break;
default:
- vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr);
+ vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
}
}
@@ -2447,6 +2660,11 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
}
kvm_x86_ops->decache_regs(vcpu);
kvm_x86_ops->skip_emulated_instruction(vcpu);
+ KVMTRACE_5D(CPUID, vcpu, function,
+ (u32)vcpu->arch.regs[VCPU_REGS_RAX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RBX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RCX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RDX], handler);
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
@@ -2469,7 +2687,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
- kvm_run->cr8 = get_cr8(vcpu);
+ kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
if (irqchip_in_kernel(vcpu->kvm))
kvm_run->ready_for_interrupt_injection = 1;
@@ -2509,16 +2727,17 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
- if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
+ if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
pr_debug("vcpu %d received sipi with vector # %x\n",
vcpu->vcpu_id, vcpu->arch.sipi_vector);
kvm_lapic_reset(vcpu);
r = kvm_x86_ops->vcpu_reset(vcpu);
if (r)
return r;
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
+ down_read(&vcpu->kvm->slots_lock);
vapic_enter(vcpu);
preempted:
@@ -2526,6 +2745,10 @@ preempted:
kvm_x86_ops->guest_debug_pre(vcpu);
again:
+ if (vcpu->requests)
+ if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+ kvm_mmu_unload(vcpu);
+
r = kvm_mmu_reload(vcpu);
if (unlikely(r))
goto out;
@@ -2539,6 +2762,11 @@ again:
r = 0;
goto out;
}
+ if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
+ kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+ r = 0;
+ goto out;
+ }
}
kvm_inject_pending_timer_irqs(vcpu);
@@ -2557,6 +2785,14 @@ again:
goto out;
}
+ if (vcpu->requests)
+ if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
+ local_irq_enable();
+ preempt_enable();
+ r = 1;
+ goto out;
+ }
+
if (signal_pending(current)) {
local_irq_enable();
preempt_enable();
@@ -2566,6 +2802,13 @@ again:
goto out;
}
+ vcpu->guest_mode = 1;
+ /*
+ * Make sure that guest_mode assignment won't happen after
+ * testing the pending IRQ vector bitmap.
+ */
+ smp_wmb();
+
if (vcpu->arch.exception.pending)
__queue_exception(vcpu);
else if (irqchip_in_kernel(vcpu->kvm))
@@ -2575,13 +2818,15 @@ again:
kvm_lapic_sync_to_vapic(vcpu);
- vcpu->guest_mode = 1;
+ up_read(&vcpu->kvm->slots_lock);
+
kvm_guest_enter();
if (vcpu->requests)
if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
kvm_x86_ops->tlb_flush(vcpu);
+ KVMTRACE_0D(VMENTRY, vcpu, entryexit);
kvm_x86_ops->run(vcpu, kvm_run);
vcpu->guest_mode = 0;
@@ -2601,6 +2846,8 @@ again:
preempt_enable();
+ down_read(&vcpu->kvm->slots_lock);
+
/*
* Profile KVM exit RIPs:
*/
@@ -2628,14 +2875,18 @@ again:
}
out:
+ up_read(&vcpu->kvm->slots_lock);
if (r > 0) {
kvm_resched(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
goto preempted;
}
post_kvm_run_save(vcpu, kvm_run);
+ down_read(&vcpu->kvm->slots_lock);
vapic_exit(vcpu);
+ up_read(&vcpu->kvm->slots_lock);
return r;
}
@@ -2647,7 +2898,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu_load(vcpu);
- if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+ if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
vcpu_put(vcpu);
return -EAGAIN;
@@ -2658,7 +2909,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
/* re-sync apic's tpr */
if (!irqchip_in_kernel(vcpu->kvm))
- set_cr8(vcpu, kvm_run->cr8);
+ kvm_set_cr8(vcpu, kvm_run->cr8);
if (vcpu->arch.pio.cur_count) {
r = complete_pio(vcpu);
@@ -2670,9 +2921,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
+
+ down_read(&vcpu->kvm->slots_lock);
r = emulate_instruction(vcpu, kvm_run,
vcpu->arch.mmio_fault_cr2, 0,
EMULTYPE_NO_DECODE);
+ up_read(&vcpu->kvm->slots_lock);
if (r == EMULATE_DO_MMIO) {
/*
* Read-modify-write. Back to userspace.
@@ -2773,7 +3027,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
static void get_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- return kvm_x86_ops->get_segment(vcpu, var, seg);
+ kvm_x86_ops->get_segment(vcpu, var, seg);
}
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -2816,7 +3070,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
sregs->cr2 = vcpu->arch.cr2;
sregs->cr3 = vcpu->arch.cr3;
sregs->cr4 = vcpu->arch.cr4;
- sregs->cr8 = get_cr8(vcpu);
+ sregs->cr8 = kvm_get_cr8(vcpu);
sregs->efer = vcpu->arch.shadow_efer;
sregs->apic_base = kvm_get_apic_base(vcpu);
@@ -2836,12 +3090,438 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
return 0;
}
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_load(vcpu);
+ mp_state->mp_state = vcpu->arch.mp_state;
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_load(vcpu);
+ vcpu->arch.mp_state = mp_state->mp_state;
+ vcpu_put(vcpu);
+ return 0;
+}
+
static void set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- return kvm_x86_ops->set_segment(vcpu, var, seg);
+ kvm_x86_ops->set_segment(vcpu, var, seg);
+}
+
+static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
+ struct kvm_segment *kvm_desct)
+{
+ kvm_desct->base = seg_desc->base0;
+ kvm_desct->base |= seg_desc->base1 << 16;
+ kvm_desct->base |= seg_desc->base2 << 24;
+ kvm_desct->limit = seg_desc->limit0;
+ kvm_desct->limit |= seg_desc->limit << 16;
+ kvm_desct->selector = selector;
+ kvm_desct->type = seg_desc->type;
+ kvm_desct->present = seg_desc->p;
+ kvm_desct->dpl = seg_desc->dpl;
+ kvm_desct->db = seg_desc->d;
+ kvm_desct->s = seg_desc->s;
+ kvm_desct->l = seg_desc->l;
+ kvm_desct->g = seg_desc->g;
+ kvm_desct->avl = seg_desc->avl;
+ if (!selector)
+ kvm_desct->unusable = 1;
+ else
+ kvm_desct->unusable = 0;
+ kvm_desct->padding = 0;
+}
+
+static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu,
+ u16 selector,
+ struct descriptor_table *dtable)
+{
+ if (selector & 1 << 2) {
+ struct kvm_segment kvm_seg;
+
+ get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
+
+ if (kvm_seg.unusable)
+ dtable->limit = 0;
+ else
+ dtable->limit = kvm_seg.limit;
+ dtable->base = kvm_seg.base;
+ }
+ else
+ kvm_x86_ops->get_gdt(vcpu, dtable);
+}
+
+/* allowed just for 8 bytes segments */
+static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+ struct desc_struct *seg_desc)
+{
+ struct descriptor_table dtable;
+ u16 index = selector >> 3;
+
+ get_segment_descritptor_dtable(vcpu, selector, &dtable);
+
+ if (dtable.limit < index * 8 + 7) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
+ return 1;
+ }
+ return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+}
+
+/* allowed just for 8 bytes segments */
+static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+ struct desc_struct *seg_desc)
+{
+ struct descriptor_table dtable;
+ u16 index = selector >> 3;
+
+ get_segment_descritptor_dtable(vcpu, selector, &dtable);
+
+ if (dtable.limit < index * 8 + 7)
+ return 1;
+ return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+}
+
+static u32 get_tss_base_addr(struct kvm_vcpu *vcpu,
+ struct desc_struct *seg_desc)
+{
+ u32 base_addr;
+
+ base_addr = seg_desc->base0;
+ base_addr |= (seg_desc->base1 << 16);
+ base_addr |= (seg_desc->base2 << 24);
+
+ return base_addr;
+}
+
+static int load_tss_segment32(struct kvm_vcpu *vcpu,
+ struct desc_struct *seg_desc,
+ struct tss_segment_32 *tss)
+{
+ u32 base_addr;
+
+ base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+ return kvm_read_guest(vcpu->kvm, base_addr, tss,
+ sizeof(struct tss_segment_32));
+}
+
+static int save_tss_segment32(struct kvm_vcpu *vcpu,
+ struct desc_struct *seg_desc,
+ struct tss_segment_32 *tss)
+{
+ u32 base_addr;
+
+ base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+ return kvm_write_guest(vcpu->kvm, base_addr, tss,
+ sizeof(struct tss_segment_32));
+}
+
+static int load_tss_segment16(struct kvm_vcpu *vcpu,
+ struct desc_struct *seg_desc,
+ struct tss_segment_16 *tss)
+{
+ u32 base_addr;
+
+ base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+ return kvm_read_guest(vcpu->kvm, base_addr, tss,
+ sizeof(struct tss_segment_16));
+}
+
+static int save_tss_segment16(struct kvm_vcpu *vcpu,
+ struct desc_struct *seg_desc,
+ struct tss_segment_16 *tss)
+{
+ u32 base_addr;
+
+ base_addr = get_tss_base_addr(vcpu, seg_desc);
+
+ return kvm_write_guest(vcpu->kvm, base_addr, tss,
+ sizeof(struct tss_segment_16));
+}
+
+static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
+{
+ struct kvm_segment kvm_seg;
+
+ get_segment(vcpu, &kvm_seg, seg);
+ return kvm_seg.selector;
+}
+
+static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu,
+ u16 selector,
+ struct kvm_segment *kvm_seg)
+{
+ struct desc_struct seg_desc;
+
+ if (load_guest_segment_descriptor(vcpu, selector, &seg_desc))
+ return 1;
+ seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg);
+ return 0;
+}
+
+static int load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+ int type_bits, int seg)
+{
+ struct kvm_segment kvm_seg;
+
+ if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
+ return 1;
+ kvm_seg.type |= type_bits;
+
+ if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS &&
+ seg != VCPU_SREG_LDTR)
+ if (!kvm_seg.s)
+ kvm_seg.unusable = 1;
+
+ set_segment(vcpu, &kvm_seg, seg);
+ return 0;
+}
+
+static void save_state_to_tss32(struct kvm_vcpu *vcpu,
+ struct tss_segment_32 *tss)
+{
+ tss->cr3 = vcpu->arch.cr3;
+ tss->eip = vcpu->arch.rip;
+ tss->eflags = kvm_x86_ops->get_rflags(vcpu);
+ tss->eax = vcpu->arch.regs[VCPU_REGS_RAX];
+ tss->ecx = vcpu->arch.regs[VCPU_REGS_RCX];
+ tss->edx = vcpu->arch.regs[VCPU_REGS_RDX];
+ tss->ebx = vcpu->arch.regs[VCPU_REGS_RBX];
+ tss->esp = vcpu->arch.regs[VCPU_REGS_RSP];
+ tss->ebp = vcpu->arch.regs[VCPU_REGS_RBP];
+ tss->esi = vcpu->arch.regs[VCPU_REGS_RSI];
+ tss->edi = vcpu->arch.regs[VCPU_REGS_RDI];
+
+ tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
+ tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
+ tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
+ tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
+ tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
+ tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
+ tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
+ tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
+}
+
+static int load_state_from_tss32(struct kvm_vcpu *vcpu,
+ struct tss_segment_32 *tss)
+{
+ kvm_set_cr3(vcpu, tss->cr3);
+
+ vcpu->arch.rip = tss->eip;
+ kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2);
+
+ vcpu->arch.regs[VCPU_REGS_RAX] = tss->eax;
+ vcpu->arch.regs[VCPU_REGS_RCX] = tss->ecx;
+ vcpu->arch.regs[VCPU_REGS_RDX] = tss->edx;
+ vcpu->arch.regs[VCPU_REGS_RBX] = tss->ebx;
+ vcpu->arch.regs[VCPU_REGS_RSP] = tss->esp;
+ vcpu->arch.regs[VCPU_REGS_RBP] = tss->ebp;
+ vcpu->arch.regs[VCPU_REGS_RSI] = tss->esi;
+ vcpu->arch.regs[VCPU_REGS_RDI] = tss->edi;
+
+ if (load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS))
+ return 1;
+ return 0;
+}
+
+static void save_state_to_tss16(struct kvm_vcpu *vcpu,
+ struct tss_segment_16 *tss)
+{
+ tss->ip = vcpu->arch.rip;
+ tss->flag = kvm_x86_ops->get_rflags(vcpu);
+ tss->ax = vcpu->arch.regs[VCPU_REGS_RAX];
+ tss->cx = vcpu->arch.regs[VCPU_REGS_RCX];
+ tss->dx = vcpu->arch.regs[VCPU_REGS_RDX];
+ tss->bx = vcpu->arch.regs[VCPU_REGS_RBX];
+ tss->sp = vcpu->arch.regs[VCPU_REGS_RSP];
+ tss->bp = vcpu->arch.regs[VCPU_REGS_RBP];
+ tss->si = vcpu->arch.regs[VCPU_REGS_RSI];
+ tss->di = vcpu->arch.regs[VCPU_REGS_RDI];
+
+ tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
+ tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
+ tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
+ tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
+ tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
+ tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
+}
+
+static int load_state_from_tss16(struct kvm_vcpu *vcpu,
+ struct tss_segment_16 *tss)
+{
+ vcpu->arch.rip = tss->ip;
+ kvm_x86_ops->set_rflags(vcpu, tss->flag | 2);
+ vcpu->arch.regs[VCPU_REGS_RAX] = tss->ax;
+ vcpu->arch.regs[VCPU_REGS_RCX] = tss->cx;
+ vcpu->arch.regs[VCPU_REGS_RDX] = tss->dx;
+ vcpu->arch.regs[VCPU_REGS_RBX] = tss->bx;
+ vcpu->arch.regs[VCPU_REGS_RSP] = tss->sp;
+ vcpu->arch.regs[VCPU_REGS_RBP] = tss->bp;
+ vcpu->arch.regs[VCPU_REGS_RSI] = tss->si;
+ vcpu->arch.regs[VCPU_REGS_RDI] = tss->di;
+
+ if (load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS))
+ return 1;
+
+ if (load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS))
+ return 1;
+ return 0;
+}
+
+int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
+ struct desc_struct *cseg_desc,
+ struct desc_struct *nseg_desc)
+{
+ struct tss_segment_16 tss_segment_16;
+ int ret = 0;
+
+ if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16))
+ goto out;
+
+ save_state_to_tss16(vcpu, &tss_segment_16);
+ save_tss_segment16(vcpu, cseg_desc, &tss_segment_16);
+
+ if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16))
+ goto out;
+ if (load_state_from_tss16(vcpu, &tss_segment_16))
+ goto out;
+
+ ret = 1;
+out:
+ return ret;
+}
+
+int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
+ struct desc_struct *cseg_desc,
+ struct desc_struct *nseg_desc)
+{
+ struct tss_segment_32 tss_segment_32;
+ int ret = 0;
+
+ if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32))
+ goto out;
+
+ save_state_to_tss32(vcpu, &tss_segment_32);
+ save_tss_segment32(vcpu, cseg_desc, &tss_segment_32);
+
+ if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32))
+ goto out;
+ if (load_state_from_tss32(vcpu, &tss_segment_32))
+ goto out;
+
+ ret = 1;
+out:
+ return ret;
}
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
+{
+ struct kvm_segment tr_seg;
+ struct desc_struct cseg_desc;
+ struct desc_struct nseg_desc;
+ int ret = 0;
+
+ get_segment(vcpu, &tr_seg, VCPU_SREG_TR);
+
+ if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
+ goto out;
+
+ if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc))
+ goto out;
+
+
+ if (reason != TASK_SWITCH_IRET) {
+ int cpl;
+
+ cpl = kvm_x86_ops->get_cpl(vcpu);
+ if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
+ }
+
+ if (!nseg_desc.p || (nseg_desc.limit0 | nseg_desc.limit << 16) < 0x67) {
+ kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
+ return 1;
+ }
+
+ if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
+ cseg_desc.type &= ~(1 << 8); //clear the B flag
+ save_guest_segment_descriptor(vcpu, tr_seg.selector,
+ &cseg_desc);
+ }
+
+ if (reason == TASK_SWITCH_IRET) {
+ u32 eflags = kvm_x86_ops->get_rflags(vcpu);
+ kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
+ }
+
+ kvm_x86_ops->skip_emulated_instruction(vcpu);
+ kvm_x86_ops->cache_regs(vcpu);
+
+ if (nseg_desc.type & 8)
+ ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc,
+ &nseg_desc);
+ else
+ ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc,
+ &nseg_desc);
+
+ if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
+ u32 eflags = kvm_x86_ops->get_rflags(vcpu);
+ kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT);
+ }
+
+ if (reason != TASK_SWITCH_IRET) {
+ nseg_desc.type |= (1 << 8);
+ save_guest_segment_descriptor(vcpu, tss_selector,
+ &nseg_desc);
+ }
+
+ kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+ seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
+ tr_seg.type = 11;
+ set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
+out:
+ kvm_x86_ops->decache_regs(vcpu);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_task_switch);
+
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
@@ -2862,12 +3542,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
vcpu->arch.cr3 = sregs->cr3;
- set_cr8(vcpu, sregs->cr8);
+ kvm_set_cr8(vcpu, sregs->cr8);
mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
-#ifdef CONFIG_X86_64
kvm_x86_ops->set_efer(vcpu, sregs->efer);
-#endif
kvm_set_apic_base(vcpu, sregs->apic_base);
kvm_x86_ops->decache_cr4_guest_bits(vcpu);
@@ -3141,9 +3819,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
vcpu->arch.mmu.root_hpa = INVALID_PAGE;
if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
- vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED;
+ vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page) {
@@ -3175,7 +3853,9 @@ fail:
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
kvm_free_lapic(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
kvm_mmu_destroy(vcpu);
+ up_read(&vcpu->kvm->slots_lock);
free_page((unsigned long)vcpu->arch.pio_data);
}
@@ -3219,10 +3899,13 @@ static void kvm_free_vcpus(struct kvm *kvm)
void kvm_arch_destroy_vm(struct kvm *kvm)
{
+ kvm_free_pit(kvm);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
+ if (kvm->arch.apic_access_page)
+ put_page(kvm->arch.apic_access_page);
kfree(kvm);
}
@@ -3278,8 +3961,8 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE
- || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED;
+ return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
+ || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED;
}
static void vcpu_kick_intr(void *info)
@@ -3293,11 +3976,17 @@ static void vcpu_kick_intr(void *info)
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int ipi_pcpu = vcpu->cpu;
+ int cpu = get_cpu();
if (waitqueue_active(&vcpu->wq)) {
wake_up_interruptible(&vcpu->wq);
++vcpu->stat.halt_wakeup;
}
- if (vcpu->guest_mode)
+ /*
+ * We may be called synchronously with irqs disabled in guest mode,
+ * So need not to call smp_call_function_single() in that case.
+ */
+ if (vcpu->guest_mode && vcpu->cpu != cpu)
smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+ put_cpu();
}
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index 79586003397..2ca08386f99 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -65,6 +65,14 @@
#define MemAbs (1<<9) /* Memory operand is absolute displacement */
#define String (1<<10) /* String instruction (rep capable) */
#define Stack (1<<11) /* Stack instruction (push/pop) */
+#define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */
+#define GroupDual (1<<15) /* Alternate decoding of mod == 3 */
+#define GroupMask 0xff /* Group number stored in bits 0:7 */
+
+enum {
+ Group1_80, Group1_81, Group1_82, Group1_83,
+ Group1A, Group3_Byte, Group3, Group4, Group5, Group7,
+};
static u16 opcode_table[256] = {
/* 0x00 - 0x07 */
@@ -123,14 +131,14 @@ static u16 opcode_table[256] = {
ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
/* 0x80 - 0x87 */
- ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
- ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM,
+ Group | Group1_80, Group | Group1_81,
+ Group | Group1_82, Group | Group1_83,
ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
/* 0x88 - 0x8F */
ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov,
ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
- 0, ModRM | DstReg, 0, DstMem | SrcNone | ModRM | Mov | Stack,
+ 0, ModRM | DstReg, 0, Group | Group1A,
/* 0x90 - 0x9F */
0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0,
@@ -164,16 +172,15 @@ static u16 opcode_table[256] = {
0, 0, 0, 0,
/* 0xF0 - 0xF7 */
0, 0, 0, 0,
- ImplicitOps, ImplicitOps,
- ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
+ ImplicitOps, ImplicitOps, Group | Group3_Byte, Group | Group3,
/* 0xF8 - 0xFF */
ImplicitOps, 0, ImplicitOps, ImplicitOps,
- 0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM
+ 0, 0, Group | Group4, Group | Group5,
};
static u16 twobyte_table[256] = {
/* 0x00 - 0x0F */
- 0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0,
+ 0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
/* 0x10 - 0x1F */
0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,
@@ -229,6 +236,56 @@ static u16 twobyte_table[256] = {
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
};
+static u16 group_table[] = {
+ [Group1_80*8] =
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ [Group1_81*8] =
+ DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+ DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+ DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+ DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+ [Group1_82*8] =
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+ [Group1_83*8] =
+ DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+ DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+ DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+ DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+ [Group1A*8] =
+ DstMem | SrcNone | ModRM | Mov | Stack, 0, 0, 0, 0, 0, 0, 0,
+ [Group3_Byte*8] =
+ ByteOp | SrcImm | DstMem | ModRM, 0,
+ ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+ 0, 0, 0, 0,
+ [Group3*8] =
+ DstMem | SrcImm | ModRM | SrcImm, 0,
+ DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+ 0, 0, 0, 0,
+ [Group4*8] =
+ ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM,
+ 0, 0, 0, 0, 0, 0,
+ [Group5*8] =
+ DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, 0, 0,
+ SrcMem | ModRM, 0, SrcMem | ModRM | Stack, 0,
+ [Group7*8] =
+ 0, 0, ModRM | SrcMem, ModRM | SrcMem,
+ SrcNone | ModRM | DstMem | Mov, 0,
+ SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp,
+};
+
+static u16 group2_table[] = {
+ [Group7*8] =
+ SrcNone | ModRM, 0, 0, 0,
+ SrcNone | ModRM | DstMem | Mov, 0,
+ SrcMem16 | ModRM | Mov, 0,
+};
+
/* EFLAGS bit definitions. */
#define EFLG_OF (1<<11)
#define EFLG_DF (1<<10)
@@ -317,7 +374,7 @@ static u16 twobyte_table[256] = {
#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \
do { \
- unsigned long _tmp; \
+ unsigned long __tmp; \
switch ((_dst).bytes) { \
case 1: \
__asm__ __volatile__ ( \
@@ -325,7 +382,7 @@ static u16 twobyte_table[256] = {
_op"b %"_bx"3,%1; " \
_POST_EFLAGS("0", "4", "2") \
: "=m" (_eflags), "=m" ((_dst).val), \
- "=&r" (_tmp) \
+ "=&r" (__tmp) \
: _by ((_src).val), "i" (EFLAGS_MASK)); \
break; \
default: \
@@ -426,29 +483,40 @@ static u16 twobyte_table[256] = {
(_type)_x; \
})
+static inline unsigned long ad_mask(struct decode_cache *c)
+{
+ return (1UL << (c->ad_bytes << 3)) - 1;
+}
+
/* Access/update address held in a register, based on addressing mode. */
-#define address_mask(reg) \
- ((c->ad_bytes == sizeof(unsigned long)) ? \
- (reg) : ((reg) & ((1UL << (c->ad_bytes << 3)) - 1)))
-#define register_address(base, reg) \
- ((base) + address_mask(reg))
-#define register_address_increment(reg, inc) \
- do { \
- /* signed type ensures sign extension to long */ \
- int _inc = (inc); \
- if (c->ad_bytes == sizeof(unsigned long)) \
- (reg) += _inc; \
- else \
- (reg) = ((reg) & \
- ~((1UL << (c->ad_bytes << 3)) - 1)) | \
- (((reg) + _inc) & \
- ((1UL << (c->ad_bytes << 3)) - 1)); \
- } while (0)
+static inline unsigned long
+address_mask(struct decode_cache *c, unsigned long reg)
+{
+ if (c->ad_bytes == sizeof(unsigned long))
+ return reg;
+ else
+ return reg & ad_mask(c);
+}
-#define JMP_REL(rel) \
- do { \
- register_address_increment(c->eip, rel); \
- } while (0)
+static inline unsigned long
+register_address(struct decode_cache *c, unsigned long base, unsigned long reg)
+{
+ return base + address_mask(c, reg);
+}
+
+static inline void
+register_address_increment(struct decode_cache *c, unsigned long *reg, int inc)
+{
+ if (c->ad_bytes == sizeof(unsigned long))
+ *reg += inc;
+ else
+ *reg = (*reg & ~ad_mask(c)) | ((*reg + inc) & ad_mask(c));
+}
+
+static inline void jmp_rel(struct decode_cache *c, int rel)
+{
+ register_address_increment(c, &c->eip, rel);
+}
static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops,
@@ -763,7 +831,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
struct decode_cache *c = &ctxt->decode;
int rc = 0;
int mode = ctxt->mode;
- int def_op_bytes, def_ad_bytes;
+ int def_op_bytes, def_ad_bytes, group;
/* Shadow copy of register state. Committed on successful emulation. */
@@ -864,12 +932,24 @@ done_prefixes:
c->b = insn_fetch(u8, 1, c->eip);
c->d = twobyte_table[c->b];
}
+ }
- /* Unrecognised? */
- if (c->d == 0) {
- DPRINTF("Cannot emulate %02x\n", c->b);
- return -1;
- }
+ if (c->d & Group) {
+ group = c->d & GroupMask;
+ c->modrm = insn_fetch(u8, 1, c->eip);
+ --c->eip;
+
+ group = (group << 3) + ((c->modrm >> 3) & 7);
+ if ((c->d & GroupDual) && (c->modrm >> 6) == 3)
+ c->d = group2_table[group];
+ else
+ c->d = group_table[group];
+ }
+
+ /* Unrecognised? */
+ if (c->d == 0) {
+ DPRINTF("Cannot emulate %02x\n", c->b);
+ return -1;
}
if (mode == X86EMUL_MODE_PROT64 && (c->d & Stack))
@@ -924,6 +1004,7 @@ done_prefixes:
*/
if ((c->d & ModRM) && c->modrm_mod == 3) {
c->src.type = OP_REG;
+ c->src.val = c->modrm_val;
break;
}
c->src.type = OP_MEM;
@@ -967,6 +1048,7 @@ done_prefixes:
case DstMem:
if ((c->d & ModRM) && c->modrm_mod == 3) {
c->dst.type = OP_REG;
+ c->dst.val = c->dst.orig_val = c->modrm_val;
break;
}
c->dst.type = OP_MEM;
@@ -984,8 +1066,8 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
c->dst.type = OP_MEM;
c->dst.bytes = c->op_bytes;
c->dst.val = c->src.val;
- register_address_increment(c->regs[VCPU_REGS_RSP], -c->op_bytes);
- c->dst.ptr = (void *) register_address(ctxt->ss_base,
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP], -c->op_bytes);
+ c->dst.ptr = (void *) register_address(c, ctxt->ss_base,
c->regs[VCPU_REGS_RSP]);
}
@@ -995,13 +1077,13 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
struct decode_cache *c = &ctxt->decode;
int rc;
- rc = ops->read_std(register_address(ctxt->ss_base,
+ rc = ops->read_std(register_address(c, ctxt->ss_base,
c->regs[VCPU_REGS_RSP]),
&c->dst.val, c->dst.bytes, ctxt->vcpu);
if (rc != 0)
return rc;
- register_address_increment(c->regs[VCPU_REGS_RSP], c->dst.bytes);
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->dst.bytes);
return 0;
}
@@ -1043,26 +1125,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
switch (c->modrm_reg) {
case 0 ... 1: /* test */
- /*
- * Special case in Grp3: test has an immediate
- * source operand.
- */
- c->src.type = OP_IMM;
- c->src.ptr = (unsigned long *)c->eip;
- c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- if (c->src.bytes == 8)
- c->src.bytes = 4;
- switch (c->src.bytes) {
- case 1:
- c->src.val = insn_fetch(s8, 1, c->eip);
- break;
- case 2:
- c->src.val = insn_fetch(s16, 2, c->eip);
- break;
- case 4:
- c->src.val = insn_fetch(s32, 4, c->eip);
- break;
- }
emulate_2op_SrcV("test", c->src, c->dst, ctxt->eflags);
break;
case 2: /* not */
@@ -1076,7 +1138,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
rc = X86EMUL_UNHANDLEABLE;
break;
}
-done:
return rc;
}
@@ -1084,7 +1145,6 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops)
{
struct decode_cache *c = &ctxt->decode;
- int rc;
switch (c->modrm_reg) {
case 0: /* inc */
@@ -1094,36 +1154,11 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
emulate_1op("dec", c->dst, ctxt->eflags);
break;
case 4: /* jmp abs */
- if (c->b == 0xff)
- c->eip = c->dst.val;
- else {
- DPRINTF("Cannot emulate %02x\n", c->b);
- return X86EMUL_UNHANDLEABLE;
- }
+ c->eip = c->src.val;
break;
case 6: /* push */
-
- /* 64-bit mode: PUSH always pushes a 64-bit operand. */
-
- if (ctxt->mode == X86EMUL_MODE_PROT64) {
- c->dst.bytes = 8;
- rc = ops->read_std((unsigned long)c->dst.ptr,
- &c->dst.val, 8, ctxt->vcpu);
- if (rc != 0)
- return rc;
- }
- register_address_increment(c->regs[VCPU_REGS_RSP],
- -c->dst.bytes);
- rc = ops->write_emulated(register_address(ctxt->ss_base,
- c->regs[VCPU_REGS_RSP]), &c->dst.val,
- c->dst.bytes, ctxt->vcpu);
- if (rc != 0)
- return rc;
- c->dst.type = OP_NONE;
+ emulate_push(ctxt);
break;
- default:
- DPRINTF("Cannot emulate %02x\n", c->b);
- return X86EMUL_UNHANDLEABLE;
}
return 0;
}
@@ -1361,19 +1396,19 @@ special_insn:
c->dst.type = OP_MEM;
c->dst.bytes = c->op_bytes;
c->dst.val = c->src.val;
- register_address_increment(c->regs[VCPU_REGS_RSP],
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP],
-c->op_bytes);
c->dst.ptr = (void *) register_address(
- ctxt->ss_base, c->regs[VCPU_REGS_RSP]);
+ c, ctxt->ss_base, c->regs[VCPU_REGS_RSP]);
break;
case 0x58 ... 0x5f: /* pop reg */
pop_instruction:
- if ((rc = ops->read_std(register_address(ctxt->ss_base,
+ if ((rc = ops->read_std(register_address(c, ctxt->ss_base,
c->regs[VCPU_REGS_RSP]), c->dst.ptr,
c->op_bytes, ctxt->vcpu)) != 0)
goto done;
- register_address_increment(c->regs[VCPU_REGS_RSP],
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP],
c->op_bytes);
c->dst.type = OP_NONE; /* Disable writeback. */
break;
@@ -1393,9 +1428,9 @@ special_insn:
1,
(c->d & ByteOp) ? 1 : c->op_bytes,
c->rep_prefix ?
- address_mask(c->regs[VCPU_REGS_RCX]) : 1,
+ address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
(ctxt->eflags & EFLG_DF),
- register_address(ctxt->es_base,
+ register_address(c, ctxt->es_base,
c->regs[VCPU_REGS_RDI]),
c->rep_prefix,
c->regs[VCPU_REGS_RDX]) == 0) {
@@ -1409,9 +1444,9 @@ special_insn:
0,
(c->d & ByteOp) ? 1 : c->op_bytes,
c->rep_prefix ?
- address_mask(c->regs[VCPU_REGS_RCX]) : 1,
+ address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
(ctxt->eflags & EFLG_DF),
- register_address(c->override_base ?
+ register_address(c, c->override_base ?
*c->override_base :
ctxt->ds_base,
c->regs[VCPU_REGS_RSI]),
@@ -1425,7 +1460,7 @@ special_insn:
int rel = insn_fetch(s8, 1, c->eip);
if (test_cc(c->b, ctxt->eflags))
- JMP_REL(rel);
+ jmp_rel(c, rel);
break;
}
case 0x80 ... 0x83: /* Grp1 */
@@ -1477,7 +1512,7 @@ special_insn:
case 0x88 ... 0x8b: /* mov */
goto mov;
case 0x8d: /* lea r16/r32, m */
- c->dst.val = c->modrm_val;
+ c->dst.val = c->modrm_ea;
break;
case 0x8f: /* pop (sole member of Grp1a) */
rc = emulate_grp1a(ctxt, ops);
@@ -1501,27 +1536,27 @@ special_insn:
case 0xa4 ... 0xa5: /* movs */
c->dst.type = OP_MEM;
c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- c->dst.ptr = (unsigned long *)register_address(
+ c->dst.ptr = (unsigned long *)register_address(c,
ctxt->es_base,
c->regs[VCPU_REGS_RDI]);
- if ((rc = ops->read_emulated(register_address(
+ if ((rc = ops->read_emulated(register_address(c,
c->override_base ? *c->override_base :
ctxt->ds_base,
c->regs[VCPU_REGS_RSI]),
&c->dst.val,
c->dst.bytes, ctxt->vcpu)) != 0)
goto done;
- register_address_increment(c->regs[VCPU_REGS_RSI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RSI],
(ctxt->eflags & EFLG_DF) ? -c->dst.bytes
: c->dst.bytes);
- register_address_increment(c->regs[VCPU_REGS_RDI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RDI],
(ctxt->eflags & EFLG_DF) ? -c->dst.bytes
: c->dst.bytes);
break;
case 0xa6 ... 0xa7: /* cmps */
c->src.type = OP_NONE; /* Disable writeback. */
c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- c->src.ptr = (unsigned long *)register_address(
+ c->src.ptr = (unsigned long *)register_address(c,
c->override_base ? *c->override_base :
ctxt->ds_base,
c->regs[VCPU_REGS_RSI]);
@@ -1533,7 +1568,7 @@ special_insn:
c->dst.type = OP_NONE; /* Disable writeback. */
c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- c->dst.ptr = (unsigned long *)register_address(
+ c->dst.ptr = (unsigned long *)register_address(c,
ctxt->es_base,
c->regs[VCPU_REGS_RDI]);
if ((rc = ops->read_emulated((unsigned long)c->dst.ptr,
@@ -1546,10 +1581,10 @@ special_insn:
emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags);
- register_address_increment(c->regs[VCPU_REGS_RSI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RSI],
(ctxt->eflags & EFLG_DF) ? -c->src.bytes
: c->src.bytes);
- register_address_increment(c->regs[VCPU_REGS_RDI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RDI],
(ctxt->eflags & EFLG_DF) ? -c->dst.bytes
: c->dst.bytes);
@@ -1557,11 +1592,11 @@ special_insn:
case 0xaa ... 0xab: /* stos */
c->dst.type = OP_MEM;
c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- c->dst.ptr = (unsigned long *)register_address(
+ c->dst.ptr = (unsigned long *)register_address(c,
ctxt->es_base,
c->regs[VCPU_REGS_RDI]);
c->dst.val = c->regs[VCPU_REGS_RAX];
- register_address_increment(c->regs[VCPU_REGS_RDI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RDI],
(ctxt->eflags & EFLG_DF) ? -c->dst.bytes
: c->dst.bytes);
break;
@@ -1569,7 +1604,7 @@ special_insn:
c->dst.type = OP_REG;
c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX];
- if ((rc = ops->read_emulated(register_address(
+ if ((rc = ops->read_emulated(register_address(c,
c->override_base ? *c->override_base :
ctxt->ds_base,
c->regs[VCPU_REGS_RSI]),
@@ -1577,7 +1612,7 @@ special_insn:
c->dst.bytes,
ctxt->vcpu)) != 0)
goto done;
- register_address_increment(c->regs[VCPU_REGS_RSI],
+ register_address_increment(c, &c->regs[VCPU_REGS_RSI],
(ctxt->eflags & EFLG_DF) ? -c->dst.bytes
: c->dst.bytes);
break;
@@ -1616,14 +1651,14 @@ special_insn:
goto cannot_emulate;
}
c->src.val = (unsigned long) c->eip;
- JMP_REL(rel);
+ jmp_rel(c, rel);
c->op_bytes = c->ad_bytes;
emulate_push(ctxt);
break;
}
case 0xe9: /* jmp rel */
case 0xeb: /* jmp rel short */
- JMP_REL(c->src.val);
+ jmp_rel(c, c->src.val);
c->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf4: /* hlt */
@@ -1690,6 +1725,8 @@ twobyte_insn:
goto done;
kvm_emulate_hypercall(ctxt->vcpu);
+ /* Disable writeback. */
+ c->dst.type = OP_NONE;
break;
case 2: /* lgdt */
rc = read_descriptor(ctxt, ops, c->src.ptr,
@@ -1697,6 +1734,8 @@ twobyte_insn:
if (rc)
goto done;
realmode_lgdt(ctxt->vcpu, size, address);
+ /* Disable writeback. */
+ c->dst.type = OP_NONE;
break;
case 3: /* lidt/vmmcall */
if (c->modrm_mod == 3 && c->modrm_rm == 1) {
@@ -1712,27 +1751,25 @@ twobyte_insn:
goto done;
realmode_lidt(ctxt->vcpu, size, address);
}
+ /* Disable writeback. */
+ c->dst.type = OP_NONE;
break;
case 4: /* smsw */
- if (c->modrm_mod != 3)
- goto cannot_emulate;
- *(u16 *)&c->regs[c->modrm_rm]
- = realmode_get_cr(ctxt->vcpu, 0);
+ c->dst.bytes = 2;
+ c->dst.val = realmode_get_cr(ctxt->vcpu, 0);
break;
case 6: /* lmsw */
- if (c->modrm_mod != 3)
- goto cannot_emulate;
- realmode_lmsw(ctxt->vcpu, (u16)c->modrm_val,
- &ctxt->eflags);
+ realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
+ &ctxt->eflags);
break;
case 7: /* invlpg*/
emulate_invlpg(ctxt->vcpu, memop);
+ /* Disable writeback. */
+ c->dst.type = OP_NONE;
break;
default:
goto cannot_emulate;
}
- /* Disable writeback. */
- c->dst.type = OP_NONE;
break;
case 0x06:
emulate_clts(ctxt->vcpu);
@@ -1823,7 +1860,7 @@ twobyte_insn:
goto cannot_emulate;
}
if (test_cc(c->b, ctxt->eflags))
- JMP_REL(rel);
+ jmp_rel(c, rel);
c->dst.type = OP_NONE;
break;
}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 25df1c1989f..76f60f52a88 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -11,7 +11,7 @@ lib-y += memcpy_$(BITS).o
ifeq ($(CONFIG_X86_32),y)
lib-y += checksum_32.o
lib-y += strstr_32.o
- lib-y += bitops_32.o semaphore_32.o string_32.o
+ lib-y += semaphore_32.o string_32.o
lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
else
@@ -21,7 +21,6 @@ else
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
lib-y += thunk_64.o clear_page_64.o copy_page_64.o
- lib-y += bitops_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
endif
diff --git a/arch/x86/lib/bitops_32.c b/arch/x86/lib/bitops_32.c
deleted file mode 100644
index b6544045985..00000000000
--- a/arch/x86/lib/bitops_32.c
+++ /dev/null
@@ -1,70 +0,0 @@
-#include <linux/bitops.h>
-#include <linux/module.h>
-
-/**
- * find_next_bit - find the next set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-int find_next_bit(const unsigned long *addr, int size, int offset)
-{
- const unsigned long *p = addr + (offset >> 5);
- int set = 0, bit = offset & 31, res;
-
- if (bit) {
- /*
- * Look for nonzero in the first 32 bits:
- */
- __asm__("bsfl %1,%0\n\t"
- "jne 1f\n\t"
- "movl $32, %0\n"
- "1:"
- : "=r" (set)
- : "r" (*p >> bit));
- if (set < (32 - bit))
- return set + offset;
- set = 32 - bit;
- p++;
- }
- /*
- * No set bit yet, search remaining full words for a bit
- */
- res = find_first_bit (p, size - 32 * (p - addr));
- return (offset + set + res);
-}
-EXPORT_SYMBOL(find_next_bit);
-
-/**
- * find_next_zero_bit - find the first zero bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-int find_next_zero_bit(const unsigned long *addr, int size, int offset)
-{
- const unsigned long *p = addr + (offset >> 5);
- int set = 0, bit = offset & 31, res;
-
- if (bit) {
- /*
- * Look for zero in the first 32 bits.
- */
- __asm__("bsfl %1,%0\n\t"
- "jne 1f\n\t"
- "movl $32, %0\n"
- "1:"
- : "=r" (set)
- : "r" (~(*p >> bit)));
- if (set < (32 - bit))
- return set + offset;
- set = 32 - bit;
- p++;
- }
- /*
- * No zero yet, search remaining full bytes for a zero
- */
- res = find_first_zero_bit(p, size - 32 * (p - addr));
- return (offset + set + res);
-}
-EXPORT_SYMBOL(find_next_zero_bit);
diff --git a/arch/x86/lib/bitops_64.c b/arch/x86/lib/bitops_64.c
deleted file mode 100644
index 0e8f491e6cc..00000000000
--- a/arch/x86/lib/bitops_64.c
+++ /dev/null
@@ -1,175 +0,0 @@
-#include <linux/bitops.h>
-
-#undef find_first_zero_bit
-#undef find_next_zero_bit
-#undef find_first_bit
-#undef find_next_bit
-
-static inline long
-__find_first_zero_bit(const unsigned long * addr, unsigned long size)
-{
- long d0, d1, d2;
- long res;
-
- /*
- * We must test the size in words, not in bits, because
- * otherwise incoming sizes in the range -63..-1 will not run
- * any scasq instructions, and then the flags used by the je
- * instruction will have whatever random value was in place
- * before. Nobody should call us like that, but
- * find_next_zero_bit() does when offset and size are at the
- * same word and it fails to find a zero itself.
- */
- size += 63;
- size >>= 6;
- if (!size)
- return 0;
- asm volatile(
- " repe; scasq\n"
- " je 1f\n"
- " xorq -8(%%rdi),%%rax\n"
- " subq $8,%%rdi\n"
- " bsfq %%rax,%%rdx\n"
- "1: subq %[addr],%%rdi\n"
- " shlq $3,%%rdi\n"
- " addq %%rdi,%%rdx"
- :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
- :"0" (0ULL), "1" (size), "2" (addr), "3" (-1ULL),
- [addr] "S" (addr) : "memory");
- /*
- * Any register would do for [addr] above, but GCC tends to
- * prefer rbx over rsi, even though rsi is readily available
- * and doesn't have to be saved.
- */
- return res;
-}
-
-/**
- * find_first_zero_bit - find the first zero bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit-number of the first zero bit, not the number of the byte
- * containing a bit.
- */
-long find_first_zero_bit(const unsigned long * addr, unsigned long size)
-{
- return __find_first_zero_bit (addr, size);
-}
-
-/**
- * find_next_zero_bit - find the next zero bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-long find_next_zero_bit (const unsigned long * addr, long size, long offset)
-{
- const unsigned long * p = addr + (offset >> 6);
- unsigned long set = 0;
- unsigned long res, bit = offset&63;
-
- if (bit) {
- /*
- * Look for zero in first word
- */
- asm("bsfq %1,%0\n\t"
- "cmoveq %2,%0"
- : "=r" (set)
- : "r" (~(*p >> bit)), "r"(64L));
- if (set < (64 - bit))
- return set + offset;
- set = 64 - bit;
- p++;
- }
- /*
- * No zero yet, search remaining full words for a zero
- */
- res = __find_first_zero_bit (p, size - 64 * (p - addr));
-
- return (offset + set + res);
-}
-
-static inline long
-__find_first_bit(const unsigned long * addr, unsigned long size)
-{
- long d0, d1;
- long res;
-
- /*
- * We must test the size in words, not in bits, because
- * otherwise incoming sizes in the range -63..-1 will not run
- * any scasq instructions, and then the flags used by the jz
- * instruction will have whatever random value was in place
- * before. Nobody should call us like that, but
- * find_next_bit() does when offset and size are at the same
- * word and it fails to find a one itself.
- */
- size += 63;
- size >>= 6;
- if (!size)
- return 0;
- asm volatile(
- " repe; scasq\n"
- " jz 1f\n"
- " subq $8,%%rdi\n"
- " bsfq (%%rdi),%%rax\n"
- "1: subq %[addr],%%rdi\n"
- " shlq $3,%%rdi\n"
- " addq %%rdi,%%rax"
- :"=a" (res), "=&c" (d0), "=&D" (d1)
- :"0" (0ULL), "1" (size), "2" (addr),
- [addr] "r" (addr) : "memory");
- return res;
-}
-
-/**
- * find_first_bit - find the first set bit in a memory region
- * @addr: The address to start the search at
- * @size: The maximum size to search
- *
- * Returns the bit-number of the first set bit, not the number of the byte
- * containing a bit.
- */
-long find_first_bit(const unsigned long * addr, unsigned long size)
-{
- return __find_first_bit(addr,size);
-}
-
-/**
- * find_next_bit - find the first set bit in a memory region
- * @addr: The address to base the search on
- * @offset: The bitnumber to start searching at
- * @size: The maximum size to search
- */
-long find_next_bit(const unsigned long * addr, long size, long offset)
-{
- const unsigned long * p = addr + (offset >> 6);
- unsigned long set = 0, bit = offset & 63, res;
-
- if (bit) {
- /*
- * Look for nonzero in the first 64 bits:
- */
- asm("bsfq %1,%0\n\t"
- "cmoveq %2,%0\n\t"
- : "=r" (set)
- : "r" (*p >> bit), "r" (64L));
- if (set < (64 - bit))
- return set + offset;
- set = 64 - bit;
- p++;
- }
- /*
- * No set bit yet, search remaining full words for a bit
- */
- res = __find_first_bit (p, size - 64 * (p - addr));
- return (offset + set + res);
-}
-
-#include <linux/module.h>
-
-EXPORT_SYMBOL(find_next_bit);
-EXPORT_SYMBOL(find_first_bit);
-EXPORT_SYMBOL(find_first_zero_bit);
-EXPORT_SYMBOL(find_next_zero_bit);
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index d05722121d2..8acbf0cdf1a 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -113,7 +113,7 @@ static inline void send_QIC_CPI(__u32 cpuset, __u8 cpi)
for_each_online_cpu(cpu) {
if (cpuset & (1 << cpu)) {
#ifdef VOYAGER_DEBUG
- if (!cpu_isset(cpu, cpu_online_map))
+ if (!cpu_online(cpu))
VDEBUG(("CPU%d sending cpi %d to CPU%d not in "
"cpu_online_map\n",
hard_smp_processor_id(), cpi, cpu));
@@ -543,8 +543,8 @@ static void __init do_boot_cpu(__u8 cpu)
hijack_source.idt.Offset, stack_start.sp));
/* init lowmem identity mapping */
- clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
- min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS));
+ clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
flush_tlb_all();
if (quad_boot) {
@@ -683,9 +683,9 @@ void __init smp_boot_cpus(void)
* Code added from smpboot.c */
{
unsigned long bogosum = 0;
- for (i = 0; i < NR_CPUS; i++)
- if (cpu_isset(i, cpu_online_map))
- bogosum += cpu_data(i).loops_per_jiffy;
+
+ for_each_online_cpu(i)
+ bogosum += cpu_data(i).loops_per_jiffy;
printk(KERN_INFO "Total of %d processors activated "
"(%lu.%02lu BogoMIPS).\n",
cpucount + 1, bogosum / (500000 / HZ),
@@ -1838,7 +1838,7 @@ static int __cpuinit voyager_cpu_up(unsigned int cpu)
return -EIO;
/* Unleash the CPU! */
cpu_set(cpu, smp_commenced_mask);
- while (!cpu_isset(cpu, cpu_online_map))
+ while (!cpu_online(cpu))
mb();
return 0;
}
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 20941d2954e..b7b3e4c7cfc 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,5 @@
obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
- pat.o
+ pat.o pgtable.o
obj-$(CONFIG_X86_32) += pgtable_32.o
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9ec62da85fd..de236e419cb 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -71,7 +71,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
- paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
+ paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
pud = pud_offset(pgd, 0);
BUG_ON(pmd_table != pmd_offset(pud, 0));
@@ -100,7 +100,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
}
- paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
+ paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
BUG_ON(page_table != pte_offset_kernel(pmd, 0));
}
@@ -227,6 +227,25 @@ static inline int page_kills_ppro(unsigned long pagenr)
return 0;
}
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number.
+ *
+ *
+ * On x86, access has to be given to the first megabyte of ram because that area
+ * contains bios code and data regions used by X and dosemu and similar apps.
+ * Access has to be given to non-kernel-ram areas as well, these contain the PCI
+ * mmio resources as well as potential bios/acpi data regions.
+ */
+int devmem_is_allowed(unsigned long pagenr)
+{
+ if (pagenr <= 256)
+ return 1;
+ if (!page_is_ram(pagenr))
+ return 1;
+ return 0;
+}
+
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
@@ -268,47 +287,17 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
pkmap_page_table = pte;
}
-static void __meminit free_new_highpage(struct page *page)
-{
- init_page_count(page);
- __free_page(page);
- totalhigh_pages++;
-}
-
void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro)
{
if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
ClearPageReserved(page);
- free_new_highpage(page);
+ init_page_count(page);
+ __free_page(page);
+ totalhigh_pages++;
} else
SetPageReserved(page);
}
-static int __meminit
-add_one_highpage_hotplug(struct page *page, unsigned long pfn)
-{
- free_new_highpage(page);
- totalram_pages++;
-#ifdef CONFIG_FLATMEM
- max_mapnr = max(pfn, max_mapnr);
-#endif
- num_physpages++;
-
- return 0;
-}
-
-/*
- * Not currently handling the NUMA case.
- * Assuming single node and all memory that
- * has been added dynamically that would be
- * onlined here is in HIGHMEM.
- */
-void __meminit online_page(struct page *page)
-{
- ClearPageReserved(page);
- add_one_highpage_hotplug(page, page_to_pfn(page));
-}
-
#ifndef CONFIG_NUMA
static void __init set_highmem_pages_init(int bad_ppro)
{
@@ -365,7 +354,7 @@ void __init native_pagetable_setup_start(pgd_t *base)
pte_clear(NULL, va, pte);
}
- paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT);
+ paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
}
void __init native_pagetable_setup_done(pgd_t *base)
@@ -457,7 +446,7 @@ void zap_low_mappings(void)
* Note that "pgd_clear()" doesn't do it for
* us, because pgd_clear() is a no-op on i386.
*/
- for (i = 0; i < USER_PTRS_PER_PGD; i++) {
+ for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
#ifdef CONFIG_X86_PAE
set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
@@ -547,9 +536,9 @@ void __init paging_init(void)
/*
* Test if the WP bit works in supervisor mode. It isn't supported on 386's
- * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This
- * used to involve black magic jumps to work around some nasty CPU bugs,
- * but fortunately the switch to using exceptions got rid of all that.
+ * and also on some strange 486's. All 586+'s are OK. This used to involve
+ * black magic jumps to work around some nasty CPU bugs, but fortunately the
+ * switch to using exceptions got rid of all that.
*/
static void __init test_wp_bit(void)
{
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1ff7906a9a4..32ba13b0f81 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -135,7 +135,7 @@ static __init void *spp_getpage(void)
return ptr;
}
-static __init void
+static void
set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
{
pgd_t *pgd;
@@ -173,7 +173,7 @@ set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
pte = pte_offset_kernel(pmd, vaddr);
- if (!pte_none(*pte) &&
+ if (!pte_none(*pte) && pte_val(new_pte) &&
pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
pte_ERROR(*pte);
set_pte(pte, new_pte);
@@ -214,8 +214,7 @@ void __init cleanup_highmap(void)
}
/* NOTE: this is meant to be run only at boot */
-void __init
-__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
unsigned long address = __fix_to_virt(idx);
@@ -621,15 +620,6 @@ void __init paging_init(void)
/*
* Memory hotplug specific functions
*/
-void online_page(struct page *page)
-{
- ClearPageReserved(page);
- init_page_count(page);
- __free_page(page);
- totalram_pages++;
- num_physpages++;
-}
-
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory is added always to NORMAL zone. This means you will never get
@@ -664,6 +654,26 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif /* CONFIG_MEMORY_HOTPLUG */
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number.
+ *
+ *
+ * On x86, access has to be given to the first megabyte of ram because that area
+ * contains bios code and data regions used by X and dosemu and similar apps.
+ * Access has to be given to non-kernel-ram areas as well, these contain the PCI
+ * mmio resources as well as potential bios/acpi data regions.
+ */
+int devmem_is_allowed(unsigned long pagenr)
+{
+ if (pagenr <= 256)
+ return 1;
+ if (!page_is_ram(pagenr))
+ return 1;
+ return 0;
+}
+
+
static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
kcore_modules, kcore_vsyscall;
@@ -791,7 +801,7 @@ void free_initrd_mem(unsigned long start, unsigned long end)
void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
{
#ifdef CONFIG_NUMA
- int nid = phys_to_nid(phys);
+ int nid, next_nid;
#endif
unsigned long pfn = phys >> PAGE_SHIFT;
@@ -810,10 +820,16 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
/* Should check here against the e820 map to avoid double free */
#ifdef CONFIG_NUMA
- reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+ nid = phys_to_nid(phys);
+ next_nid = phys_to_nid(phys + len - 1);
+ if (nid == next_nid)
+ reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
+ else
+ reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
#else
reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
#endif
+
if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
dma_reserve += len / PAGE_SIZE;
set_dma_reserve(dma_reserve);
@@ -907,6 +923,10 @@ const char *arch_vma_name(struct vm_area_struct *vma)
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
*/
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
int __meminit
vmemmap_populate(struct page *start_page, unsigned long size, int node)
{
@@ -941,12 +961,32 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
PAGE_KERNEL_LARGE);
set_pmd(pmd, __pmd(pte_val(entry)));
- printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
- addr, addr + PMD_SIZE - 1, p, node);
+ /* check to see if we have contiguous blocks */
+ if (p_end != p || node_start != node) {
+ if (p_start)
+ printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+ addr_start, addr_end-1, p_start, p_end-1, node_start);
+ addr_start = addr;
+ node_start = node;
+ p_start = p;
+ }
+ addr_end = addr + PMD_SIZE;
+ p_end = p + PMD_SIZE;
} else {
vmemmap_verify((pte_t *)pmd, node, addr, next);
}
}
return 0;
}
+
+void __meminit vmemmap_populate_print_last(void)
+{
+ if (p_start) {
+ printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+ addr_start, addr_end-1, p_start, p_end-1, node_start);
+ p_start = NULL;
+ p_end = NULL;
+ node_start = 0;
+ }
+}
#endif
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 3a4baf95e24..804de18abcc 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -117,8 +117,8 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
* have to convert them into an offset in a page-aligned mapping, but the
* caller shouldn't need to know that small detail.
*/
-static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
- unsigned long prot_val)
+static void __iomem *__ioremap_caller(resource_size_t phys_addr,
+ unsigned long size, unsigned long prot_val, void *caller)
{
unsigned long pfn, offset, vaddr;
resource_size_t last_addr;
@@ -212,7 +212,7 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
/*
* Ok, go for it..
*/
- area = get_vm_area(size, VM_IOREMAP);
+ area = get_vm_area_caller(size, VM_IOREMAP, caller);
if (!area)
return NULL;
area->phys_addr = phys_addr;
@@ -255,7 +255,8 @@ static void __iomem *__ioremap(resource_size_t phys_addr, unsigned long size,
*/
void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
{
- return __ioremap(phys_addr, size, _PAGE_CACHE_UC);
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_UC,
+ __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_nocache);
@@ -272,7 +273,8 @@ EXPORT_SYMBOL(ioremap_nocache);
void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size)
{
if (pat_wc_enabled)
- return __ioremap(phys_addr, size, _PAGE_CACHE_WC);
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
+ __builtin_return_address(0));
else
return ioremap_nocache(phys_addr, size);
}
@@ -280,7 +282,8 @@ EXPORT_SYMBOL(ioremap_wc);
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
- return __ioremap(phys_addr, size, _PAGE_CACHE_WB);
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB,
+ __builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_cache);
@@ -336,6 +339,35 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+void *xlate_dev_mem_ptr(unsigned long phys)
+{
+ void *addr;
+ unsigned long start = phys & PAGE_MASK;
+
+ /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
+ if (page_is_ram(start >> PAGE_SHIFT))
+ return __va(phys);
+
+ addr = (void *)ioremap(start, PAGE_SIZE);
+ if (addr)
+ addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
+
+ return addr;
+}
+
+void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+{
+ if (page_is_ram(phys >> PAGE_SHIFT))
+ return;
+
+ iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
+ return;
+}
+
#ifdef CONFIG_X86_32
int __initdata early_ioremap_debug;
@@ -407,7 +439,7 @@ void __init early_ioremap_clear(void)
pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
pmd_clear(pmd);
- paravirt_release_pt(__pa(bm_pte) >> PAGE_SHIFT);
+ paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT);
__flush_tlb_all();
}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9a6892200b2..c5066d519e5 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -196,6 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
unsigned long bootmap_start, nodedata_phys;
void *bootmap;
const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+ int nid;
start = round_up(start, ZONE_ALIGN);
@@ -218,9 +219,19 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
NODE_DATA(nodeid)->node_start_pfn = start_pfn;
NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn;
- /* Find a place for the bootmem map */
+ /*
+ * Find a place for the bootmem map
+ * nodedata_phys could be on other nodes by alloc_bootmem,
+ * so need to sure bootmap_start not to be small, otherwise
+ * early_node_mem will get that with find_e820_area instead
+ * of alloc_bootmem, that could clash with reserved range
+ */
bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
- bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+ nid = phys_to_nid(nodedata_phys);
+ if (nid == nodeid)
+ bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+ else
+ bootmap_start = round_up(start, PAGE_SIZE);
/*
* SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
* to use that to align to PAGE_SIZE
@@ -245,10 +256,29 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
free_bootmem_with_active_regions(nodeid, end);
- reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size,
- BOOTMEM_DEFAULT);
- reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
- bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+ /*
+ * convert early reserve to bootmem reserve earlier
+ * otherwise early_node_mem could use early reserved mem
+ * on previous node
+ */
+ early_res_to_bootmem(start, end);
+
+ /*
+ * in some case early_node_mem could use alloc_bootmem
+ * to get range on other node, don't reserve that again
+ */
+ if (nid != nodeid)
+ printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid);
+ else
+ reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
+ pgdat_size, BOOTMEM_DEFAULT);
+ nid = phys_to_nid(bootmap_start);
+ if (nid != nodeid)
+ printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid);
+ else
+ reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
+ bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
#ifdef CONFIG_ACPI_NUMA
srat_reserve_add_area(nodeid);
#endif
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index c29ebd03725..bd5e05c654d 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -483,9 +483,7 @@ static int split_large_page(pte_t *kpte, unsigned long address)
goto out_unlock;
pbase = (pte_t *)page_address(base);
-#ifdef CONFIG_X86_32
- paravirt_alloc_pt(&init_mm, page_to_pfn(base));
-#endif
+ paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
#ifdef CONFIG_X86_64
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 72c0f609740..277446cd30b 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -11,16 +11,19 @@
#include <linux/kernel.h>
#include <linux/gfp.h>
#include <linux/fs.h>
+#include <linux/bootmem.h>
#include <asm/msr.h>
#include <asm/tlbflush.h>
#include <asm/processor.h>
+#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/pat.h>
#include <asm/e820.h>
#include <asm/cacheflush.h>
#include <asm/fcntl.h>
#include <asm/mtrr.h>
+#include <asm/io.h>
int pat_wc_enabled = 1;
@@ -190,6 +193,21 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
return 0;
}
+/*
+ * req_type typically has one of the:
+ * - _PAGE_CACHE_WB
+ * - _PAGE_CACHE_WC
+ * - _PAGE_CACHE_UC_MINUS
+ * - _PAGE_CACHE_UC
+ *
+ * req_type will have a special case value '-1', when requester want to inherit
+ * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS.
+ *
+ * If ret_type is NULL, function will return an error if it cannot reserve the
+ * region with req_type. If ret_type is non-null, function will return
+ * available type in ret_type in case of no error. In case of any error
+ * it will return a negative return value.
+ */
int reserve_memtype(u64 start, u64 end, unsigned long req_type,
unsigned long *ret_type)
{
@@ -200,9 +218,14 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
/* Only track when pat_wc_enabled */
if (!pat_wc_enabled) {
- if (ret_type)
- *ret_type = req_type;
-
+ /* This is identical to page table setting without PAT */
+ if (ret_type) {
+ if (req_type == -1) {
+ *ret_type = _PAGE_CACHE_WB;
+ } else {
+ *ret_type = req_type;
+ }
+ }
return 0;
}
@@ -214,8 +237,29 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
return 0;
}
- req_type &= _PAGE_CACHE_MASK;
- err = pat_x_mtrr_type(start, end, req_type, &actual_type);
+ if (req_type == -1) {
+ /*
+ * Special case where caller wants to inherit from mtrr or
+ * existing pat mapping, defaulting to UC_MINUS in case of
+ * no match.
+ */
+ u8 mtrr_type = mtrr_type_lookup(start, end);
+ if (mtrr_type == 0xFE) { /* MTRR match error */
+ err = -1;
+ }
+
+ if (mtrr_type == MTRR_TYPE_WRBACK) {
+ req_type = _PAGE_CACHE_WB;
+ actual_type = _PAGE_CACHE_WB;
+ } else {
+ req_type = _PAGE_CACHE_UC_MINUS;
+ actual_type = _PAGE_CACHE_UC_MINUS;
+ }
+ } else {
+ req_type &= _PAGE_CACHE_MASK;
+ err = pat_x_mtrr_type(start, end, req_type, &actual_type);
+ }
+
if (err) {
if (ret_type)
*ret_type = actual_type;
@@ -241,7 +285,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
struct memtype *saved_ptr;
if (parse->start >= end) {
- printk("New Entry\n");
+ pr_debug("New Entry\n");
list_add(&new_entry->nd, parse->nd.prev);
new_entry = NULL;
break;
@@ -291,7 +335,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
break;
}
- printk("Overlap at 0x%Lx-0x%Lx\n",
+ pr_debug("Overlap at 0x%Lx-0x%Lx\n",
saved_ptr->start, saved_ptr->end);
/* No conflict. Go ahead and add this new entry */
list_add(&new_entry->nd, saved_ptr->nd.prev);
@@ -343,8 +387,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
break;
}
- printk("Overlap at 0x%Lx-0x%Lx\n",
- saved_ptr->start, saved_ptr->end);
+ pr_debug(KERN_INFO "Overlap at 0x%Lx-0x%Lx\n",
+ saved_ptr->start, saved_ptr->end);
/* No conflict. Go ahead and add this new entry */
list_add(&new_entry->nd, &saved_ptr->nd);
new_entry = NULL;
@@ -353,7 +397,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
}
if (err) {
- printk(
+ printk(KERN_INFO
"reserve_memtype failed 0x%Lx-0x%Lx, track %s, req %s\n",
start, end, cattr_name(new_entry->type),
cattr_name(req_type));
@@ -365,16 +409,16 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
if (new_entry) {
/* No conflict. Not yet added to the list. Add to the tail */
list_add_tail(&new_entry->nd, &memtype_list);
- printk("New Entry\n");
- }
+ pr_debug("New Entry\n");
+ }
if (ret_type) {
- printk(
+ pr_debug(
"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
start, end, cattr_name(actual_type),
cattr_name(req_type), cattr_name(*ret_type));
} else {
- printk(
+ pr_debug(
"reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s\n",
start, end, cattr_name(actual_type),
cattr_name(req_type));
@@ -411,11 +455,142 @@ int free_memtype(u64 start, u64 end)
spin_unlock(&memtype_lock);
if (err) {
- printk(KERN_DEBUG "%s:%d freeing invalid memtype %Lx-%Lx\n",
+ printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
current->comm, current->pid, start, end);
}
- printk( "free_memtype request 0x%Lx-0x%Lx\n", start, end);
+ pr_debug("free_memtype request 0x%Lx-0x%Lx\n", start, end);
return err;
}
+
+/*
+ * /dev/mem mmap interface. The memtype used for mapping varies:
+ * - Use UC for mappings with O_SYNC flag
+ * - Without O_SYNC flag, if there is any conflict in reserve_memtype,
+ * inherit the memtype from existing mapping.
+ * - Else use UC_MINUS memtype (for backward compatibility with existing
+ * X drivers.
+ */
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+ unsigned long size, pgprot_t vma_prot)
+{
+ return vma_prot;
+}
+
+#ifdef CONFIG_NONPROMISC_DEVMEM
+/* This check is done in drivers/char/mem.c in case of NONPROMISC_DEVMEM*/
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+ return 1;
+}
+#else
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+ u64 from = ((u64)pfn) << PAGE_SHIFT;
+ u64 to = from + size;
+ u64 cursor = from;
+
+ while (cursor < to) {
+ if (!devmem_is_allowed(pfn)) {
+ printk(KERN_INFO
+ "Program %s tried to access /dev/mem between %Lx->%Lx.\n",
+ current->comm, from, to);
+ return 0;
+ }
+ cursor += PAGE_SIZE;
+ pfn++;
+ }
+ return 1;
+}
+#endif /* CONFIG_NONPROMISC_DEVMEM */
+
+int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
+ unsigned long size, pgprot_t *vma_prot)
+{
+ u64 offset = ((u64) pfn) << PAGE_SHIFT;
+ unsigned long flags = _PAGE_CACHE_UC_MINUS;
+ int retval;
+
+ if (!range_is_allowed(pfn, size))
+ return 0;
+
+ if (file->f_flags & O_SYNC) {
+ flags = _PAGE_CACHE_UC;
+ }
+
+#ifdef CONFIG_X86_32
+ /*
+ * On the PPro and successors, the MTRRs are used to set
+ * memory types for physical addresses outside main memory,
+ * so blindly setting UC or PWT on those pages is wrong.
+ * For Pentiums and earlier, the surround logic should disable
+ * caching for the high addresses through the KEN pin, but
+ * we maintain the tradition of paranoia in this code.
+ */
+ if (!pat_wc_enabled &&
+ ! ( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) ||
+ test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability)) &&
+ (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
+ flags = _PAGE_CACHE_UC;
+ }
+#endif
+
+ /*
+ * With O_SYNC, we can only take UC mapping. Fail if we cannot.
+ * Without O_SYNC, we want to get
+ * - WB for WB-able memory and no other conflicting mappings
+ * - UC_MINUS for non-WB-able memory with no other conflicting mappings
+ * - Inherit from confliting mappings otherwise
+ */
+ if (flags != _PAGE_CACHE_UC_MINUS) {
+ retval = reserve_memtype(offset, offset + size, flags, NULL);
+ } else {
+ retval = reserve_memtype(offset, offset + size, -1, &flags);
+ }
+
+ if (retval < 0)
+ return 0;
+
+ if (pfn <= max_pfn_mapped &&
+ ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
+ free_memtype(offset, offset + size);
+ printk(KERN_INFO
+ "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
+ current->comm, current->pid,
+ cattr_name(flags),
+ offset, offset + size);
+ return 0;
+ }
+
+ *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
+ flags);
+ return 1;
+}
+
+void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
+{
+ u64 addr = (u64)pfn << PAGE_SHIFT;
+ unsigned long flags;
+ unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+
+ reserve_memtype(addr, addr + size, want_flags, &flags);
+ if (flags != want_flags) {
+ printk(KERN_INFO
+ "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
+ current->comm, current->pid,
+ cattr_name(want_flags),
+ addr, addr + size,
+ cattr_name(flags));
+ }
+}
+
+void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
+{
+ u64 addr = (u64)pfn << PAGE_SHIFT;
+
+ free_memtype(addr, addr + size);
+}
+
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
new file mode 100644
index 00000000000..50159764f69
--- /dev/null
+++ b/arch/x86/mm/pgtable.c
@@ -0,0 +1,276 @@
+#include <linux/mm.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+{
+ return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+}
+
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+ struct page *pte;
+
+#ifdef CONFIG_HIGHPTE
+ pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
+#else
+ pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+#endif
+ if (pte)
+ pgtable_page_ctor(pte);
+ return pte;
+}
+
+void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
+{
+ pgtable_page_dtor(pte);
+ paravirt_release_pte(page_to_pfn(pte));
+ tlb_remove_page(tlb, pte);
+}
+
+#if PAGETABLE_LEVELS > 2
+void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
+{
+ paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+ tlb_remove_page(tlb, virt_to_page(pmd));
+}
+
+#if PAGETABLE_LEVELS > 3
+void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
+{
+ paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
+ tlb_remove_page(tlb, virt_to_page(pud));
+}
+#endif /* PAGETABLE_LEVELS > 3 */
+#endif /* PAGETABLE_LEVELS > 2 */
+
+static inline void pgd_list_add(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ list_add(&page->lru, &pgd_list);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+ struct page *page = virt_to_page(pgd);
+
+ list_del(&page->lru);
+}
+
+#define UNSHARED_PTRS_PER_PGD \
+ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
+
+static void pgd_ctor(void *p)
+{
+ pgd_t *pgd = p;
+ unsigned long flags;
+
+ /* Clear usermode parts of PGD */
+ memset(pgd, 0, KERNEL_PGD_BOUNDARY*sizeof(pgd_t));
+
+ spin_lock_irqsave(&pgd_lock, flags);
+
+ /* If the pgd points to a shared pagetable level (either the
+ ptes in non-PAE, or shared PMD in PAE), then just copy the
+ references from swapper_pg_dir. */
+ if (PAGETABLE_LEVELS == 2 ||
+ (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
+ PAGETABLE_LEVELS == 4) {
+ clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
+ swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ KERNEL_PGD_PTRS);
+ paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
+ __pa(swapper_pg_dir) >> PAGE_SHIFT,
+ KERNEL_PGD_BOUNDARY,
+ KERNEL_PGD_PTRS);
+ }
+
+ /* list required to sync kernel mapping updates */
+ if (!SHARED_KERNEL_PMD)
+ pgd_list_add(pgd);
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void pgd_dtor(void *pgd)
+{
+ unsigned long flags; /* can be called from interrupt context */
+
+ if (SHARED_KERNEL_PMD)
+ return;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ pgd_list_del(pgd);
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+/*
+ * List of all pgd's needed for non-PAE so it can invalidate entries
+ * in both cached and uncached pgd's; not needed for PAE since the
+ * kernel pmd is shared. If PAE were not to share the pmd a similar
+ * tactic would be needed. This is essentially codepath-based locking
+ * against pageattr.c; it is the unique case in which a valid change
+ * of kernel pagetables can't be lazily synchronized by vmalloc faults.
+ * vmalloc faults work because attached pagetables are never freed.
+ * -- wli
+ */
+
+#ifdef CONFIG_X86_PAE
+/*
+ * Mop up any pmd pages which may still be attached to the pgd.
+ * Normally they will be freed by munmap/exit_mmap, but any pmd we
+ * preallocate which never got a corresponding vma will need to be
+ * freed manually.
+ */
+static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
+{
+ int i;
+
+ for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
+ pgd_t pgd = pgdp[i];
+
+ if (pgd_val(pgd) != 0) {
+ pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+ pgdp[i] = native_make_pgd(0);
+
+ paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+ pmd_free(mm, pmd);
+ }
+ }
+}
+
+/*
+ * In PAE mode, we need to do a cr3 reload (=tlb flush) when
+ * updating the top-level pagetable entries to guarantee the
+ * processor notices the update. Since this is expensive, and
+ * all 4 top-level entries are used almost immediately in a
+ * new process's life, we just pre-populate them here.
+ *
+ * Also, if we're in a paravirt environment where the kernel pmd is
+ * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
+ * and initialize the kernel pmds here.
+ */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+ pud_t *pud;
+ unsigned long addr;
+ int i;
+
+ pud = pud_offset(pgd, 0);
+ for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
+ i++, pud++, addr += PUD_SIZE) {
+ pmd_t *pmd = pmd_alloc_one(mm, addr);
+
+ if (!pmd) {
+ pgd_mop_up_pmds(mm, pgd);
+ return 0;
+ }
+
+ if (i >= KERNEL_PGD_BOUNDARY)
+ memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
+ sizeof(pmd_t) * PTRS_PER_PMD);
+
+ pud_populate(mm, pud, pmd);
+ }
+
+ return 1;
+}
+
+void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
+{
+ paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
+
+ /* Note: almost everything apart from _PAGE_PRESENT is
+ reserved at the pmd (PDPT) level. */
+ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
+
+ /*
+ * According to Intel App note "TLBs, Paging-Structure Caches,
+ * and Their Invalidation", April 2007, document 317080-001,
+ * section 8.1: in PAE mode we explicitly have to flush the
+ * TLB via cr3 if the top-level pgd is changed...
+ */
+ if (mm == current->active_mm)
+ write_cr3(read_cr3());
+}
+#else /* !CONFIG_X86_PAE */
+/* No need to prepopulate any pagetable entries in non-PAE modes. */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+ return 1;
+}
+
+static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd)
+{
+}
+#endif /* CONFIG_X86_PAE */
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+
+ /* so that alloc_pmd can use it */
+ mm->pgd = pgd;
+ if (pgd)
+ pgd_ctor(pgd);
+
+ if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
+ pgd_dtor(pgd);
+ free_page((unsigned long)pgd);
+ pgd = NULL;
+ }
+
+ return pgd;
+}
+
+void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ pgd_mop_up_pmds(mm, pgd);
+ pgd_dtor(pgd);
+ free_page((unsigned long)pgd);
+}
+
+int ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep,
+ pte_t entry, int dirty)
+{
+ int changed = !pte_same(*ptep, entry);
+
+ if (changed && dirty) {
+ *ptep = entry;
+ pte_update_defer(vma->vm_mm, address, ptep);
+ flush_tlb_page(vma, address);
+ }
+
+ return changed;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
+{
+ int ret = 0;
+
+ if (pte_young(*ptep))
+ ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+ &ptep->pte);
+
+ if (ret)
+ pte_update(vma->vm_mm, addr, ptep);
+
+ return ret;
+}
+
+int ptep_clear_flush_young(struct vm_area_struct *vma,
+ unsigned long address, pte_t *ptep)
+{
+ int young;
+
+ young = ptep_test_and_clear_young(vma, address, ptep);
+ if (young)
+ flush_tlb_page(vma, address);
+
+ return young;
+}
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6fb9e7c6893..9ee007be914 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -173,210 +173,6 @@ void reserve_top_address(unsigned long reserve)
__VMALLOC_RESERVE += reserve;
}
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
- return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
- struct page *pte;
-
-#ifdef CONFIG_HIGHPTE
- pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
-#else
- pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
-#endif
- if (pte)
- pgtable_page_ctor(pte);
- return pte;
-}
-
-/*
- * List of all pgd's needed for non-PAE so it can invalidate entries
- * in both cached and uncached pgd's; not needed for PAE since the
- * kernel pmd is shared. If PAE were not to share the pmd a similar
- * tactic would be needed. This is essentially codepath-based locking
- * against pageattr.c; it is the unique case in which a valid change
- * of kernel pagetables can't be lazily synchronized by vmalloc faults.
- * vmalloc faults work because attached pagetables are never freed.
- * -- wli
- */
-static inline void pgd_list_add(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- list_add(&page->lru, &pgd_list);
-}
-
-static inline void pgd_list_del(pgd_t *pgd)
-{
- struct page *page = virt_to_page(pgd);
-
- list_del(&page->lru);
-}
-
-#define UNSHARED_PTRS_PER_PGD \
- (SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
-
-static void pgd_ctor(void *p)
-{
- pgd_t *pgd = p;
- unsigned long flags;
-
- /* Clear usermode parts of PGD */
- memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
-
- spin_lock_irqsave(&pgd_lock, flags);
-
- /* If the pgd points to a shared pagetable level (either the
- ptes in non-PAE, or shared PMD in PAE), then just copy the
- references from swapper_pg_dir. */
- if (PAGETABLE_LEVELS == 2 ||
- (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) {
- clone_pgd_range(pgd + USER_PTRS_PER_PGD,
- swapper_pg_dir + USER_PTRS_PER_PGD,
- KERNEL_PGD_PTRS);
- paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
- __pa(swapper_pg_dir) >> PAGE_SHIFT,
- USER_PTRS_PER_PGD,
- KERNEL_PGD_PTRS);
- }
-
- /* list required to sync kernel mapping updates */
- if (!SHARED_KERNEL_PMD)
- pgd_list_add(pgd);
-
- spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-static void pgd_dtor(void *pgd)
-{
- unsigned long flags; /* can be called from interrupt context */
-
- if (SHARED_KERNEL_PMD)
- return;
-
- spin_lock_irqsave(&pgd_lock, flags);
- pgd_list_del(pgd);
- spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-#ifdef CONFIG_X86_PAE
-/*
- * Mop up any pmd pages which may still be attached to the pgd.
- * Normally they will be freed by munmap/exit_mmap, but any pmd we
- * preallocate which never got a corresponding vma will need to be
- * freed manually.
- */
-static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
-{
- int i;
-
- for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
- pgd_t pgd = pgdp[i];
-
- if (pgd_val(pgd) != 0) {
- pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
-
- pgdp[i] = native_make_pgd(0);
-
- paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT);
- pmd_free(mm, pmd);
- }
- }
-}
-
-/*
- * In PAE mode, we need to do a cr3 reload (=tlb flush) when
- * updating the top-level pagetable entries to guarantee the
- * processor notices the update. Since this is expensive, and
- * all 4 top-level entries are used almost immediately in a
- * new process's life, we just pre-populate them here.
- *
- * Also, if we're in a paravirt environment where the kernel pmd is
- * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
- * and initialize the kernel pmds here.
- */
-static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
-{
- pud_t *pud;
- unsigned long addr;
- int i;
-
- pud = pud_offset(pgd, 0);
- for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
- i++, pud++, addr += PUD_SIZE) {
- pmd_t *pmd = pmd_alloc_one(mm, addr);
-
- if (!pmd) {
- pgd_mop_up_pmds(mm, pgd);
- return 0;
- }
-
- if (i >= USER_PTRS_PER_PGD)
- memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
- sizeof(pmd_t) * PTRS_PER_PMD);
-
- pud_populate(mm, pud, pmd);
- }
-
- return 1;
-}
-#else /* !CONFIG_X86_PAE */
-/* No need to prepopulate any pagetable entries in non-PAE modes. */
-static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
-{
- return 1;
-}
-
-static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
-{
-}
-#endif /* CONFIG_X86_PAE */
-
-pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-
- /* so that alloc_pd can use it */
- mm->pgd = pgd;
- if (pgd)
- pgd_ctor(pgd);
-
- if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
- pgd_dtor(pgd);
- free_page((unsigned long)pgd);
- pgd = NULL;
- }
-
- return pgd;
-}
-
-void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
- pgd_mop_up_pmds(mm, pgd);
- pgd_dtor(pgd);
- free_page((unsigned long)pgd);
-}
-
-void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
-{
- pgtable_page_dtor(pte);
- paravirt_release_pt(page_to_pfn(pte));
- tlb_remove_page(tlb, pte);
-}
-
-#ifdef CONFIG_X86_PAE
-
-void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
-{
- paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
- tlb_remove_page(tlb, virt_to_page(pmd));
-}
-
-#endif
-
int pmd_bad(pmd_t pmd)
{
WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd));
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 4b1620a1529..1d3aa6b8718 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -1,2 +1,10 @@
- .section ".vdso","a"
+#include <linux/init.h>
+
+__INITDATA
+
+ .globl vdso_start, vdso_end
+vdso_start:
.incbin "arch/x86/vdso/vdso.so"
+vdso_end:
+
+__FINIT
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 4d5f2649bee..2e641be2737 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -6,7 +6,7 @@ config XEN
bool "Xen guest support"
select PARAVIRT
depends on X86_32
- depends on X86_CMPXCHG && X86_TSC && !NEED_MULTIPLE_NODES && !(X86_VISWS || X86_VOYAGER)
+ depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
help
This is the Linux Xen port. Enabling this will allow the
kernel to boot in a paravirtualized environment under the
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 343df246bd3..3d8df981d5f 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
-obj-y := enlighten.o setup.o features.o multicalls.o mmu.o \
- events.o time.o manage.o xen-asm.o
+obj-y := enlighten.o setup.o multicalls.o mmu.o \
+ time.o manage.o xen-asm.o grant-table.o
obj-$(CONFIG_SMP) += smp.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0388220cf9..c8a56e457d6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -155,7 +155,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
if (*ax == 1)
maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */
(1 << X86_FEATURE_ACPI) | /* disable ACPI */
- (1 << X86_FEATURE_SEP) | /* disable SEP */
+ (1 << X86_FEATURE_MCE) | /* disable MCE */
+ (1 << X86_FEATURE_MCA) | /* disable MCA */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
asm(XEN_EMULATE_PREFIX "cpuid"
@@ -531,26 +532,37 @@ static void xen_apic_write(unsigned long reg, u32 val)
static void xen_flush_tlb(void)
{
struct mmuext_op *op;
- struct multicall_space mcs = xen_mc_entry(sizeof(*op));
+ struct multicall_space mcs;
+
+ preempt_disable();
+
+ mcs = xen_mc_entry(sizeof(*op));
op = mcs.args;
op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
}
static void xen_flush_tlb_single(unsigned long addr)
{
struct mmuext_op *op;
- struct multicall_space mcs = xen_mc_entry(sizeof(*op));
+ struct multicall_space mcs;
+
+ preempt_disable();
+ mcs = xen_mc_entry(sizeof(*op));
op = mcs.args;
op->cmd = MMUEXT_INVLPG_LOCAL;
op->arg1.linear_addr = addr & PAGE_MASK;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
}
static void xen_flush_tlb_others(const cpumask_t *cpus, struct mm_struct *mm,
@@ -655,15 +667,17 @@ static void xen_write_cr3(unsigned long cr3)
/* Early in boot, while setting up the initial pagetable, assume
everything is pinned. */
-static __init void xen_alloc_pt_init(struct mm_struct *mm, u32 pfn)
+static __init void xen_alloc_pte_init(struct mm_struct *mm, u32 pfn)
{
+#ifdef CONFIG_FLATMEM
BUG_ON(mem_map); /* should only be used early */
+#endif
make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
}
-/* Early release_pt assumes that all pts are pinned, since there's
+/* Early release_pte assumes that all pts are pinned, since there's
only init_mm and anything attached to that is pinned. */
-static void xen_release_pt_init(u32 pfn)
+static void xen_release_pte_init(u32 pfn)
{
make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}
@@ -697,12 +711,12 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
}
}
-static void xen_alloc_pt(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pte(struct mm_struct *mm, u32 pfn)
{
xen_alloc_ptpage(mm, pfn, PT_PTE);
}
-static void xen_alloc_pd(struct mm_struct *mm, u32 pfn)
+static void xen_alloc_pmd(struct mm_struct *mm, u32 pfn)
{
xen_alloc_ptpage(mm, pfn, PT_PMD);
}
@@ -722,12 +736,12 @@ static void xen_release_ptpage(u32 pfn, unsigned level)
}
}
-static void xen_release_pt(u32 pfn)
+static void xen_release_pte(u32 pfn)
{
xen_release_ptpage(pfn, PT_PTE);
}
-static void xen_release_pd(u32 pfn)
+static void xen_release_pmd(u32 pfn)
{
xen_release_ptpage(pfn, PT_PMD);
}
@@ -849,10 +863,10 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
{
/* This will work as long as patching hasn't happened yet
(which it hasn't) */
- pv_mmu_ops.alloc_pt = xen_alloc_pt;
- pv_mmu_ops.alloc_pd = xen_alloc_pd;
- pv_mmu_ops.release_pt = xen_release_pt;
- pv_mmu_ops.release_pd = xen_release_pd;
+ pv_mmu_ops.alloc_pte = xen_alloc_pte;
+ pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
+ pv_mmu_ops.release_pte = xen_release_pte;
+ pv_mmu_ops.release_pmd = xen_release_pmd;
pv_mmu_ops.set_pte = xen_set_pte;
setup_shared_info();
@@ -994,7 +1008,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
.read_pmc = native_read_pmc,
.iret = xen_iret,
- .irq_enable_syscall_ret = NULL, /* never called */
+ .irq_enable_syscall_ret = xen_sysexit,
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
@@ -1059,11 +1073,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
- .alloc_pt = xen_alloc_pt_init,
- .release_pt = xen_release_pt_init,
- .alloc_pd = xen_alloc_pt_init,
- .alloc_pd_clone = paravirt_nop,
- .release_pd = xen_release_pt_init,
+ .alloc_pte = xen_alloc_pte_init,
+ .release_pte = xen_release_pte_init,
+ .alloc_pmd = xen_alloc_pte_init,
+ .alloc_pmd_clone = paravirt_nop,
+ .release_pmd = xen_release_pte_init,
#ifdef CONFIG_HIGHPTE
.kmap_atomic_pte = xen_kmap_atomic_pte,
diff --git a/arch/x86/xen/events.c b/arch/x86/xen/events.c
deleted file mode 100644
index dcf613e1758..00000000000
--- a/arch/x86/xen/events.c
+++ /dev/null
@@ -1,591 +0,0 @@
-/*
- * Xen event channels
- *
- * Xen models interrupts with abstract event channels. Because each
- * domain gets 1024 event channels, but NR_IRQ is not that large, we
- * must dynamically map irqs<->event channels. The event channels
- * interface with the rest of the kernel by defining a xen interrupt
- * chip. When an event is recieved, it is mapped to an irq and sent
- * through the normal interrupt processing path.
- *
- * There are four kinds of events which can be mapped to an event
- * channel:
- *
- * 1. Inter-domain notifications. This includes all the virtual
- * device events, since they're driven by front-ends in another domain
- * (typically dom0).
- * 2. VIRQs, typically used for timers. These are per-cpu events.
- * 3. IPIs.
- * 4. Hardware interrupts. Not supported at present.
- *
- * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
- */
-
-#include <linux/linkage.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/string.h>
-
-#include <asm/ptrace.h>
-#include <asm/irq.h>
-#include <asm/sync_bitops.h>
-#include <asm/xen/hypercall.h>
-#include <asm/xen/hypervisor.h>
-
-#include <xen/events.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/event_channel.h>
-
-#include "xen-ops.h"
-
-/*
- * This lock protects updates to the following mapping and reference-count
- * arrays. The lock does not need to be acquired to read the mapping tables.
- */
-static DEFINE_SPINLOCK(irq_mapping_update_lock);
-
-/* IRQ <-> VIRQ mapping. */
-static DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]) = {[0 ... NR_VIRQS-1] = -1};
-
-/* IRQ <-> IPI mapping */
-static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1};
-
-/* Packed IRQ information: binding type, sub-type index, and event channel. */
-struct packed_irq
-{
- unsigned short evtchn;
- unsigned char index;
- unsigned char type;
-};
-
-static struct packed_irq irq_info[NR_IRQS];
-
-/* Binding types. */
-enum {
- IRQT_UNBOUND,
- IRQT_PIRQ,
- IRQT_VIRQ,
- IRQT_IPI,
- IRQT_EVTCHN
-};
-
-/* Convenient shorthand for packed representation of an unbound IRQ. */
-#define IRQ_UNBOUND mk_irq_info(IRQT_UNBOUND, 0, 0)
-
-static int evtchn_to_irq[NR_EVENT_CHANNELS] = {
- [0 ... NR_EVENT_CHANNELS-1] = -1
-};
-static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG];
-static u8 cpu_evtchn[NR_EVENT_CHANNELS];
-
-/* Reference counts for bindings to IRQs. */
-static int irq_bindcount[NR_IRQS];
-
-/* Xen will never allocate port zero for any purpose. */
-#define VALID_EVTCHN(chn) ((chn) != 0)
-
-/*
- * Force a proper event-channel callback from Xen after clearing the
- * callback mask. We do this in a very simple manner, by making a call
- * down into Xen. The pending flag will be checked by Xen on return.
- */
-void force_evtchn_callback(void)
-{
- (void)HYPERVISOR_xen_version(0, NULL);
-}
-EXPORT_SYMBOL_GPL(force_evtchn_callback);
-
-static struct irq_chip xen_dynamic_chip;
-
-/* Constructor for packed IRQ information. */
-static inline struct packed_irq mk_irq_info(u32 type, u32 index, u32 evtchn)
-{
- return (struct packed_irq) { evtchn, index, type };
-}
-
-/*
- * Accessors for packed IRQ information.
- */
-static inline unsigned int evtchn_from_irq(int irq)
-{
- return irq_info[irq].evtchn;
-}
-
-static inline unsigned int index_from_irq(int irq)
-{
- return irq_info[irq].index;
-}
-
-static inline unsigned int type_from_irq(int irq)
-{
- return irq_info[irq].type;
-}
-
-static inline unsigned long active_evtchns(unsigned int cpu,
- struct shared_info *sh,
- unsigned int idx)
-{
- return (sh->evtchn_pending[idx] &
- cpu_evtchn_mask[cpu][idx] &
- ~sh->evtchn_mask[idx]);
-}
-
-static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
-{
- int irq = evtchn_to_irq[chn];
-
- BUG_ON(irq == -1);
-#ifdef CONFIG_SMP
- irq_desc[irq].affinity = cpumask_of_cpu(cpu);
-#endif
-
- __clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
- __set_bit(chn, cpu_evtchn_mask[cpu]);
-
- cpu_evtchn[chn] = cpu;
-}
-
-static void init_evtchn_cpu_bindings(void)
-{
-#ifdef CONFIG_SMP
- int i;
- /* By default all event channels notify CPU#0. */
- for (i = 0; i < NR_IRQS; i++)
- irq_desc[i].affinity = cpumask_of_cpu(0);
-#endif
-
- memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
- memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0]));
-}
-
-static inline unsigned int cpu_from_evtchn(unsigned int evtchn)
-{
- return cpu_evtchn[evtchn];
-}
-
-static inline void clear_evtchn(int port)
-{
- struct shared_info *s = HYPERVISOR_shared_info;
- sync_clear_bit(port, &s->evtchn_pending[0]);
-}
-
-static inline void set_evtchn(int port)
-{
- struct shared_info *s = HYPERVISOR_shared_info;
- sync_set_bit(port, &s->evtchn_pending[0]);
-}
-
-
-/**
- * notify_remote_via_irq - send event to remote end of event channel via irq
- * @irq: irq of event channel to send event to
- *
- * Unlike notify_remote_via_evtchn(), this is safe to use across
- * save/restore. Notifications on a broken connection are silently
- * dropped.
- */
-void notify_remote_via_irq(int irq)
-{
- int evtchn = evtchn_from_irq(irq);
-
- if (VALID_EVTCHN(evtchn))
- notify_remote_via_evtchn(evtchn);
-}
-EXPORT_SYMBOL_GPL(notify_remote_via_irq);
-
-static void mask_evtchn(int port)
-{
- struct shared_info *s = HYPERVISOR_shared_info;
- sync_set_bit(port, &s->evtchn_mask[0]);
-}
-
-static void unmask_evtchn(int port)
-{
- struct shared_info *s = HYPERVISOR_shared_info;
- unsigned int cpu = get_cpu();
-
- BUG_ON(!irqs_disabled());
-
- /* Slow path (hypercall) if this is a non-local port. */
- if (unlikely(cpu != cpu_from_evtchn(port))) {
- struct evtchn_unmask unmask = { .port = port };
- (void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
- } else {
- struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
-
- sync_clear_bit(port, &s->evtchn_mask[0]);
-
- /*
- * The following is basically the equivalent of
- * 'hw_resend_irq'. Just like a real IO-APIC we 'lose
- * the interrupt edge' if the channel is masked.
- */
- if (sync_test_bit(port, &s->evtchn_pending[0]) &&
- !sync_test_and_set_bit(port / BITS_PER_LONG,
- &vcpu_info->evtchn_pending_sel))
- vcpu_info->evtchn_upcall_pending = 1;
- }
-
- put_cpu();
-}
-
-static int find_unbound_irq(void)
-{
- int irq;
-
- /* Only allocate from dynirq range */
- for (irq = 0; irq < NR_IRQS; irq++)
- if (irq_bindcount[irq] == 0)
- break;
-
- if (irq == NR_IRQS)
- panic("No available IRQ to bind to: increase NR_IRQS!\n");
-
- return irq;
-}
-
-int bind_evtchn_to_irq(unsigned int evtchn)
-{
- int irq;
-
- spin_lock(&irq_mapping_update_lock);
-
- irq = evtchn_to_irq[evtchn];
-
- if (irq == -1) {
- irq = find_unbound_irq();
-
- dynamic_irq_init(irq);
- set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
- handle_level_irq, "event");
-
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn);
- }
-
- irq_bindcount[irq]++;
-
- spin_unlock(&irq_mapping_update_lock);
-
- return irq;
-}
-EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
-
-static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
-{
- struct evtchn_bind_ipi bind_ipi;
- int evtchn, irq;
-
- spin_lock(&irq_mapping_update_lock);
-
- irq = per_cpu(ipi_to_irq, cpu)[ipi];
- if (irq == -1) {
- irq = find_unbound_irq();
- if (irq < 0)
- goto out;
-
- dynamic_irq_init(irq);
- set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
- handle_level_irq, "ipi");
-
- bind_ipi.vcpu = cpu;
- if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_ipi,
- &bind_ipi) != 0)
- BUG();
- evtchn = bind_ipi.port;
-
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn);
-
- per_cpu(ipi_to_irq, cpu)[ipi] = irq;
-
- bind_evtchn_to_cpu(evtchn, cpu);
- }
-
- irq_bindcount[irq]++;
-
- out:
- spin_unlock(&irq_mapping_update_lock);
- return irq;
-}
-
-
-static int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
-{
- struct evtchn_bind_virq bind_virq;
- int evtchn, irq;
-
- spin_lock(&irq_mapping_update_lock);
-
- irq = per_cpu(virq_to_irq, cpu)[virq];
-
- if (irq == -1) {
- bind_virq.virq = virq;
- bind_virq.vcpu = cpu;
- if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
- &bind_virq) != 0)
- BUG();
- evtchn = bind_virq.port;
-
- irq = find_unbound_irq();
-
- dynamic_irq_init(irq);
- set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
- handle_level_irq, "virq");
-
- evtchn_to_irq[evtchn] = irq;
- irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn);
-
- per_cpu(virq_to_irq, cpu)[virq] = irq;
-
- bind_evtchn_to_cpu(evtchn, cpu);
- }
-
- irq_bindcount[irq]++;
-
- spin_unlock(&irq_mapping_update_lock);
-
- return irq;
-}
-
-static void unbind_from_irq(unsigned int irq)
-{
- struct evtchn_close close;
- int evtchn = evtchn_from_irq(irq);
-
- spin_lock(&irq_mapping_update_lock);
-
- if (VALID_EVTCHN(evtchn) && (--irq_bindcount[irq] == 0)) {
- close.port = evtchn;
- if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
- BUG();
-
- switch (type_from_irq(irq)) {
- case IRQT_VIRQ:
- per_cpu(virq_to_irq, cpu_from_evtchn(evtchn))
- [index_from_irq(irq)] = -1;
- break;
- default:
- break;
- }
-
- /* Closed ports are implicitly re-bound to VCPU0. */
- bind_evtchn_to_cpu(evtchn, 0);
-
- evtchn_to_irq[evtchn] = -1;
- irq_info[irq] = IRQ_UNBOUND;
-
- dynamic_irq_init(irq);
- }
-
- spin_unlock(&irq_mapping_update_lock);
-}
-
-int bind_evtchn_to_irqhandler(unsigned int evtchn,
- irq_handler_t handler,
- unsigned long irqflags,
- const char *devname, void *dev_id)
-{
- unsigned int irq;
- int retval;
-
- irq = bind_evtchn_to_irq(evtchn);
- retval = request_irq(irq, handler, irqflags, devname, dev_id);
- if (retval != 0) {
- unbind_from_irq(irq);
- return retval;
- }
-
- return irq;
-}
-EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
-
-int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
- irq_handler_t handler,
- unsigned long irqflags, const char *devname, void *dev_id)
-{
- unsigned int irq;
- int retval;
-
- irq = bind_virq_to_irq(virq, cpu);
- retval = request_irq(irq, handler, irqflags, devname, dev_id);
- if (retval != 0) {
- unbind_from_irq(irq);
- return retval;
- }
-
- return irq;
-}
-EXPORT_SYMBOL_GPL(bind_virq_to_irqhandler);
-
-int bind_ipi_to_irqhandler(enum ipi_vector ipi,
- unsigned int cpu,
- irq_handler_t handler,
- unsigned long irqflags,
- const char *devname,
- void *dev_id)
-{
- int irq, retval;
-
- irq = bind_ipi_to_irq(ipi, cpu);
- if (irq < 0)
- return irq;
-
- retval = request_irq(irq, handler, irqflags, devname, dev_id);
- if (retval != 0) {
- unbind_from_irq(irq);
- return retval;
- }
-
- return irq;
-}
-
-void unbind_from_irqhandler(unsigned int irq, void *dev_id)
-{
- free_irq(irq, dev_id);
- unbind_from_irq(irq);
-}
-EXPORT_SYMBOL_GPL(unbind_from_irqhandler);
-
-void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector)
-{
- int irq = per_cpu(ipi_to_irq, cpu)[vector];
- BUG_ON(irq < 0);
- notify_remote_via_irq(irq);
-}
-
-
-/*
- * Search the CPUs pending events bitmasks. For each one found, map
- * the event number to an irq, and feed it into do_IRQ() for
- * handling.
- *
- * Xen uses a two-level bitmap to speed searching. The first level is
- * a bitset of words which contain pending event bits. The second
- * level is a bitset of pending events themselves.
- */
-void xen_evtchn_do_upcall(struct pt_regs *regs)
-{
- int cpu = get_cpu();
- struct shared_info *s = HYPERVISOR_shared_info;
- struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu);
- unsigned long pending_words;
-
- vcpu_info->evtchn_upcall_pending = 0;
-
- /* NB. No need for a barrier here -- XCHG is a barrier on x86. */
- pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
- while (pending_words != 0) {
- unsigned long pending_bits;
- int word_idx = __ffs(pending_words);
- pending_words &= ~(1UL << word_idx);
-
- while ((pending_bits = active_evtchns(cpu, s, word_idx)) != 0) {
- int bit_idx = __ffs(pending_bits);
- int port = (word_idx * BITS_PER_LONG) + bit_idx;
- int irq = evtchn_to_irq[port];
-
- if (irq != -1) {
- regs->orig_ax = ~irq;
- do_IRQ(regs);
- }
- }
- }
-
- put_cpu();
-}
-
-/* Rebind an evtchn so that it gets delivered to a specific cpu */
-static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
-{
- struct evtchn_bind_vcpu bind_vcpu;
- int evtchn = evtchn_from_irq(irq);
-
- if (!VALID_EVTCHN(evtchn))
- return;
-
- /* Send future instances of this interrupt to other vcpu. */
- bind_vcpu.port = evtchn;
- bind_vcpu.vcpu = tcpu;
-
- /*
- * If this fails, it usually just indicates that we're dealing with a
- * virq or IPI channel, which don't actually need to be rebound. Ignore
- * it, but don't do the xenlinux-level rebind in that case.
- */
- if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
- bind_evtchn_to_cpu(evtchn, tcpu);
-}
-
-
-static void set_affinity_irq(unsigned irq, cpumask_t dest)
-{
- unsigned tcpu = first_cpu(dest);
- rebind_irq_to_cpu(irq, tcpu);
-}
-
-static void enable_dynirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
-
- if (VALID_EVTCHN(evtchn))
- unmask_evtchn(evtchn);
-}
-
-static void disable_dynirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
-
- if (VALID_EVTCHN(evtchn))
- mask_evtchn(evtchn);
-}
-
-static void ack_dynirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
-
- move_native_irq(irq);
-
- if (VALID_EVTCHN(evtchn))
- clear_evtchn(evtchn);
-}
-
-static int retrigger_dynirq(unsigned int irq)
-{
- int evtchn = evtchn_from_irq(irq);
- int ret = 0;
-
- if (VALID_EVTCHN(evtchn)) {
- set_evtchn(evtchn);
- ret = 1;
- }
-
- return ret;
-}
-
-static struct irq_chip xen_dynamic_chip __read_mostly = {
- .name = "xen-dyn",
- .mask = disable_dynirq,
- .unmask = enable_dynirq,
- .ack = ack_dynirq,
- .set_affinity = set_affinity_irq,
- .retrigger = retrigger_dynirq,
-};
-
-void __init xen_init_IRQ(void)
-{
- int i;
-
- init_evtchn_cpu_bindings();
-
- /* No event channels are 'live' right now. */
- for (i = 0; i < NR_EVENT_CHANNELS; i++)
- mask_evtchn(i);
-
- /* Dynamic IRQ space is currently unbound. Zero the refcnts. */
- for (i = 0; i < NR_IRQS; i++)
- irq_bindcount[i] = 0;
-
- irq_ctx_init(smp_processor_id());
-}
diff --git a/arch/x86/xen/features.c b/arch/x86/xen/features.c
deleted file mode 100644
index 0707714e40d..00000000000
--- a/arch/x86/xen/features.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/******************************************************************************
- * features.c
- *
- * Xen feature flags.
- *
- * Copyright (c) 2006, Ian Campbell, XenSource Inc.
- */
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <linux/module.h>
-#include <asm/xen/hypervisor.h>
-#include <xen/features.h>
-
-u8 xen_features[XENFEAT_NR_SUBMAPS * 32] __read_mostly;
-EXPORT_SYMBOL_GPL(xen_features);
-
-void xen_setup_features(void)
-{
- struct xen_feature_info fi;
- int i, j;
-
- for (i = 0; i < XENFEAT_NR_SUBMAPS; i++) {
- fi.submap_idx = i;
- if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0)
- break;
- for (j = 0; j < 32; j++)
- xen_features[i * 32 + j] = !!(fi.submap & 1<<j);
- }
-}
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
new file mode 100644
index 00000000000..49ba9b5224d
--- /dev/null
+++ b/arch/x86/xen/grant-table.c
@@ -0,0 +1,91 @@
+/******************************************************************************
+ * grant_table.c
+ * x86 specific part
+ *
+ * Granting foreign access to our memory reservation.
+ *
+ * Copyright (c) 2005-2006, Christopher Clark
+ * Copyright (c) 2004-2005, K A Fraser
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ * VA Linux Systems Japan. Split out x86 specific part.
+ *
+ * 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; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+
+#include <xen/interface/xen.h>
+#include <xen/page.h>
+#include <xen/grant_table.h>
+
+#include <asm/pgtable.h>
+
+static int map_pte_fn(pte_t *pte, struct page *pmd_page,
+ unsigned long addr, void *data)
+{
+ unsigned long **frames = (unsigned long **)data;
+
+ set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
+ (*frames)++;
+ return 0;
+}
+
+static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
+ unsigned long addr, void *data)
+{
+
+ set_pte_at(&init_mm, addr, pte, __pte(0));
+ return 0;
+}
+
+int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
+ unsigned long max_nr_gframes,
+ struct grant_entry **__shared)
+{
+ int rc;
+ struct grant_entry *shared = *__shared;
+
+ if (shared == NULL) {
+ struct vm_struct *area =
+ xen_alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+ BUG_ON(area == NULL);
+ shared = area->addr;
+ *__shared = shared;
+ }
+
+ rc = apply_to_page_range(&init_mm, (unsigned long)shared,
+ PAGE_SIZE * nr_gframes,
+ map_pte_fn, &frames);
+ return rc;
+}
+
+void arch_gnttab_unmap_shared(struct grant_entry *shared,
+ unsigned long nr_gframes)
+{
+ apply_to_page_range(&init_mm, (unsigned long)shared,
+ PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
+}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2a054ef2a3d..126766d43ae 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -156,6 +156,10 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
+ /* updates to init_mm may be done without lock */
+ if (mm == &init_mm)
+ preempt_disable();
+
if (mm == current->mm || mm == &init_mm) {
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
struct multicall_space mcs;
@@ -163,14 +167,61 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
MULTI_update_va_mapping(mcs.mc, addr, pteval, 0);
xen_mc_issue(PARAVIRT_LAZY_MMU);
- return;
+ goto out;
} else
if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0)
- return;
+ goto out;
}
xen_set_pte(ptep, pteval);
+
+out:
+ if (mm == &init_mm)
+ preempt_enable();
+}
+
+pteval_t xen_pte_val(pte_t pte)
+{
+ pteval_t ret = pte.pte;
+
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+
+ return ret;
+}
+
+pgdval_t xen_pgd_val(pgd_t pgd)
+{
+ pgdval_t ret = pgd.pgd;
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+ return ret;
+}
+
+pte_t xen_make_pte(pteval_t pte)
+{
+ if (pte & _PAGE_PRESENT) {
+ pte = phys_to_machine(XPADDR(pte)).maddr;
+ pte &= ~(_PAGE_PCD | _PAGE_PWT);
+ }
+
+ return (pte_t){ .pte = pte };
}
+pgd_t xen_make_pgd(pgdval_t pgd)
+{
+ if (pgd & _PAGE_PRESENT)
+ pgd = phys_to_machine(XPADDR(pgd)).maddr;
+
+ return (pgd_t){ pgd };
+}
+
+pmdval_t xen_pmd_val(pmd_t pmd)
+{
+ pmdval_t ret = native_pmd_val(pmd);
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+ return ret;
+}
#ifdef CONFIG_X86_PAE
void xen_set_pud(pud_t *ptr, pud_t val)
{
@@ -214,100 +265,18 @@ void xen_pmd_clear(pmd_t *pmdp)
xen_set_pmd(pmdp, __pmd(0));
}
-unsigned long long xen_pte_val(pte_t pte)
+pmd_t xen_make_pmd(pmdval_t pmd)
{
- unsigned long long ret = 0;
-
- if (pte.pte_low) {
- ret = ((unsigned long long)pte.pte_high << 32) | pte.pte_low;
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- }
-
- return ret;
-}
-
-unsigned long long xen_pmd_val(pmd_t pmd)
-{
- unsigned long long ret = pmd.pmd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- return ret;
-}
-
-unsigned long long xen_pgd_val(pgd_t pgd)
-{
- unsigned long long ret = pgd.pgd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- return ret;
-}
-
-pte_t xen_make_pte(unsigned long long pte)
-{
- if (pte & _PAGE_PRESENT) {
- pte = phys_to_machine(XPADDR(pte)).maddr;
- pte &= ~(_PAGE_PCD | _PAGE_PWT);
- }
-
- return (pte_t){ .pte = pte };
-}
-
-pmd_t xen_make_pmd(unsigned long long pmd)
-{
- if (pmd & 1)
+ if (pmd & _PAGE_PRESENT)
pmd = phys_to_machine(XPADDR(pmd)).maddr;
- return (pmd_t){ pmd };
-}
-
-pgd_t xen_make_pgd(unsigned long long pgd)
-{
- if (pgd & _PAGE_PRESENT)
- pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
- return (pgd_t){ pgd };
+ return native_make_pmd(pmd);
}
#else /* !PAE */
void xen_set_pte(pte_t *ptep, pte_t pte)
{
*ptep = pte;
}
-
-unsigned long xen_pte_val(pte_t pte)
-{
- unsigned long ret = pte.pte_low;
-
- if (ret & _PAGE_PRESENT)
- ret = machine_to_phys(XMADDR(ret)).paddr;
-
- return ret;
-}
-
-unsigned long xen_pgd_val(pgd_t pgd)
-{
- unsigned long ret = pgd.pgd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- return ret;
-}
-
-pte_t xen_make_pte(unsigned long pte)
-{
- if (pte & _PAGE_PRESENT) {
- pte = phys_to_machine(XPADDR(pte)).maddr;
- pte &= ~(_PAGE_PCD | _PAGE_PWT);
- }
-
- return (pte_t){ pte };
-}
-
-pgd_t xen_make_pgd(unsigned long pgd)
-{
- if (pgd & _PAGE_PRESENT)
- pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
- return (pgd_t){ pgd };
-}
#endif /* CONFIG_X86_PAE */
/*
@@ -418,7 +387,7 @@ static void xen_do_pin(unsigned level, unsigned long pfn)
static int pin_page(struct page *page, enum pt_level level)
{
- unsigned pgfl = test_and_set_bit(PG_pinned, &page->flags);
+ unsigned pgfl = TestSetPagePinned(page);
int flush;
if (pgfl)
@@ -499,7 +468,7 @@ void __init xen_mark_init_mm_pinned(void)
static int unpin_page(struct page *page, enum pt_level level)
{
- unsigned pgfl = test_and_clear_bit(PG_pinned, &page->flags);
+ unsigned pgfl = TestClearPagePinned(page);
if (pgfl && !PageHighMem(page)) {
void *pt = lowmem_page_address(page);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 2341492bf7a..82517e4a752 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -16,6 +16,7 @@
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#include <xen/interface/callback.h>
#include <xen/interface/physdev.h>
#include <xen/features.h>
@@ -68,6 +69,24 @@ static void __init fiddle_vdso(void)
*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
}
+void xen_enable_sysenter(void)
+{
+ int cpu = smp_processor_id();
+ extern void xen_sysenter_target(void);
+ /* Mask events on entry, even though they get enabled immediately */
+ static struct callback_register sysenter = {
+ .type = CALLBACKTYPE_sysenter,
+ .address = { __KERNEL_CS, (unsigned long)xen_sysenter_target },
+ .flags = CALLBACKF_mask_events,
+ };
+
+ if (!boot_cpu_has(X86_FEATURE_SEP) ||
+ HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) != 0) {
+ clear_cpu_cap(&cpu_data(cpu), X86_FEATURE_SEP);
+ clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP);
+ }
+}
+
void __init xen_arch_setup(void)
{
struct physdev_set_iopl set_iopl;
@@ -82,6 +101,8 @@ void __init xen_arch_setup(void)
HYPERVISOR_set_callbacks(__KERNEL_CS, (unsigned long)xen_hypervisor_callback,
__KERNEL_CS, (unsigned long)xen_failsafe_callback);
+ xen_enable_sysenter();
+
set_iopl.iopl = 1;
rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
if (rc != 0)
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index e340ff92f6b..94e69000f98 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -36,8 +36,9 @@
#include "mmu.h"
static cpumask_t xen_cpu_initialized_map;
-static DEFINE_PER_CPU(int, resched_irq);
-static DEFINE_PER_CPU(int, callfunc_irq);
+static DEFINE_PER_CPU(int, resched_irq) = -1;
+static DEFINE_PER_CPU(int, callfunc_irq) = -1;
+static DEFINE_PER_CPU(int, debug_irq) = -1;
/*
* Structure and data for smp_call_function(). This is designed to minimise
@@ -72,6 +73,7 @@ static __cpuinit void cpu_bringup_and_idle(void)
int cpu = smp_processor_id();
cpu_init();
+ xen_enable_sysenter();
preempt_disable();
per_cpu(cpu_state, cpu) = CPU_ONLINE;
@@ -88,9 +90,7 @@ static __cpuinit void cpu_bringup_and_idle(void)
static int xen_smp_intr_init(unsigned int cpu)
{
int rc;
- const char *resched_name, *callfunc_name;
-
- per_cpu(resched_irq, cpu) = per_cpu(callfunc_irq, cpu) = -1;
+ const char *resched_name, *callfunc_name, *debug_name;
resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
@@ -114,6 +114,14 @@ static int xen_smp_intr_init(unsigned int cpu)
goto fail;
per_cpu(callfunc_irq, cpu) = rc;
+ debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+ rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
+ IRQF_DISABLED | IRQF_PERCPU | IRQF_NOBALANCING,
+ debug_name, NULL);
+ if (rc < 0)
+ goto fail;
+ per_cpu(debug_irq, cpu) = rc;
+
return 0;
fail:
@@ -121,6 +129,8 @@ static int xen_smp_intr_init(unsigned int cpu)
unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
if (per_cpu(callfunc_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
+ if (per_cpu(debug_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
return rc;
}
@@ -183,7 +193,7 @@ void __init xen_smp_prepare_cpus(unsigned int max_cpus)
/* Restrict the possible_map according to max_cpus. */
while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
- for (cpu = NR_CPUS-1; !cpu_isset(cpu, cpu_possible_map); cpu--)
+ for (cpu = NR_CPUS - 1; !cpu_possible(cpu); cpu--)
continue;
cpu_clear(cpu, cpu_possible_map);
}
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index fe161ed4b01..2497a30f41d 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -108,6 +108,20 @@ ENDPATCH(xen_restore_fl_direct)
RELOC(xen_restore_fl_direct, 2b+1)
/*
+ We can't use sysexit directly, because we're not running in ring0.
+ But we can easily fake it up using iret. Assuming xen_sysexit
+ is jumped to with a standard stack frame, we can just strip it
+ back to a standard iret frame and use iret.
+ */
+ENTRY(xen_sysexit)
+ movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */
+ orl $X86_EFLAGS_IF, PT_EFLAGS(%esp)
+ lea PT_EIP(%esp), %esp
+
+ jmp xen_iret
+ENDPROC(xen_sysexit)
+
+/*
This is run where a normal iret would be run, with the same stack setup:
8: eflags
4: cs
@@ -184,8 +198,12 @@ iret_restore_end:
region is OK. */
je xen_hypervisor_callback
- iret
+1: iret
xen_iret_end_crit:
+.section __ex_table,"a"
+ .align 4
+ .long 1b,iret_exc
+.previous
hyper_iret:
/* put this out of line since its very rarely used */
@@ -219,9 +237,7 @@ hyper_iret:
ds } SAVE_ALL state
eax }
: :
- ebx }
- ----------------
- return addr <- esp
+ ebx }<- esp
----------------
In order to deliver the nested exception properly, we need to shift
@@ -236,10 +252,8 @@ hyper_iret:
it's usermode state which we eventually need to restore.
*/
ENTRY(xen_iret_crit_fixup)
- /* offsets +4 for return address */
-
/*
- Paranoia: Make sure we're really coming from userspace.
+ Paranoia: Make sure we're really coming from kernel space.
One could imagine a case where userspace jumps into the
critical range address, but just before the CPU delivers a GP,
it decides to deliver an interrupt instead. Unlikely?
@@ -248,32 +262,32 @@ ENTRY(xen_iret_crit_fixup)
jump instruction itself, not the destination, but some virtual
environments get this wrong.
*/
- movl PT_CS+4(%esp), %ecx
+ movl PT_CS(%esp), %ecx
andl $SEGMENT_RPL_MASK, %ecx
cmpl $USER_RPL, %ecx
je 2f
- lea PT_ORIG_EAX+4(%esp), %esi
- lea PT_EFLAGS+4(%esp), %edi
+ lea PT_ORIG_EAX(%esp), %esi
+ lea PT_EFLAGS(%esp), %edi
/* If eip is before iret_restore_end then stack
hasn't been restored yet. */
cmp $iret_restore_end, %eax
jae 1f
- movl 0+4(%edi),%eax /* copy EAX */
- movl %eax, PT_EAX+4(%esp)
+ movl 0+4(%edi),%eax /* copy EAX (just above top of frame) */
+ movl %eax, PT_EAX(%esp)
lea ESP_OFFSET(%edi),%edi /* move dest up over saved regs */
/* set up the copy */
1: std
- mov $(PT_EIP+4) / 4, %ecx /* copy ret+saved regs up to orig_eax */
+ mov $PT_EIP / 4, %ecx /* saved regs up to orig_eax */
rep movsl
cld
lea 4(%edi),%esp /* point esp to new frame */
-2: ret
+2: jmp xen_do_upcall
/*
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 956a491ea99..f1063ae0803 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -2,6 +2,8 @@
#define XEN_OPS_H
#include <linux/init.h>
+#include <linux/irqreturn.h>
+#include <xen/xen-ops.h>
/* These are code, but not functions. Defined in entry.S */
extern const char xen_hypervisor_callback[];
@@ -9,7 +11,6 @@ extern const char xen_failsafe_callback[];
void xen_copy_trap_info(struct trap_info *traps);
-DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
DECLARE_PER_CPU(unsigned long, xen_cr3);
DECLARE_PER_CPU(unsigned long, xen_current_cr3);
@@ -19,6 +20,7 @@ extern struct shared_info *HYPERVISOR_shared_info;
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
void __init xen_init_IRQ(void);
+void xen_enable_sysenter(void);
void xen_setup_timer(int cpu);
void xen_setup_cpu_clockevents(void);
@@ -28,6 +30,8 @@ unsigned long xen_get_wallclock(void);
int xen_set_wallclock(unsigned long time);
unsigned long long xen_sched_clock(void);
+irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
+
bool xen_vcpu_stolen(int vcpu);
void xen_mark_init_mm_pinned(void);
@@ -64,4 +68,6 @@ DECL_ASM(unsigned long, xen_save_fl_direct, void);
DECL_ASM(void, xen_restore_fl_direct, unsigned long);
void xen_iret(void);
+void xen_sysexit(void);
+
#endif /* XEN_OPS_H */