Home Home > GIT Browse > vanilla
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKernel Build Daemon <kbuild@suse.de>2019-07-13 12:01:56 +0200
committerKernel Build Daemon <kbuild@suse.de>2019-07-13 12:01:56 +0200
commit599969c73a67a033a1465ac7e37d43f6ba2b7f80 (patch)
tree77adca4e02e91dc6454d25f567121042ad6264ab
parent7f45b92d43769f5ff561275afdb57365f4edcba9 (diff)
Automatically updated to 5.2-7765-g964a4eacef67
-rw-r--r--Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra2
-rw-r--r--Documentation/ABI/stable/sysfs-driver-mlxreg-io45
-rw-r--r--Documentation/ABI/testing/procfs-smaps_rollup14
-rw-r--r--Documentation/ABI/testing/pstore4
-rw-r--r--Documentation/ABI/testing/sysfs-bus-event_source-devices-format4
-rw-r--r--Documentation/ABI/testing/sysfs-bus-i2c-devices-hm635212
-rw-r--r--Documentation/ABI/testing/sysfs-bus-iio-distance-srf084
-rw-r--r--Documentation/ABI/testing/sysfs-bus-iio-proximity-as39354
-rw-r--r--Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats24
-rw-r--r--Documentation/ABI/testing/sysfs-bus-pci-devices-cciss44
-rw-r--r--Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg22
-rw-r--r--Documentation/ABI/testing/sysfs-class-backlight-driver-lm35336
-rw-r--r--Documentation/ABI/testing/sysfs-class-cxl6
-rw-r--r--Documentation/ABI/testing/sysfs-class-devfreq2
-rw-r--r--Documentation/ABI/testing/sysfs-class-led-driver-lm35338
-rw-r--r--Documentation/ABI/testing/sysfs-class-leds-gt683r4
-rw-r--r--Documentation/ABI/testing/sysfs-class-powercap2
-rw-r--r--Documentation/ABI/testing/sysfs-class-uwb_rc6
-rw-r--r--Documentation/ABI/testing/sysfs-driver-altera-cvp2
-rw-r--r--Documentation/ABI/testing/sysfs-driver-hid12
-rw-r--r--Documentation/ABI/testing/sysfs-driver-hid-roccat-kone2
-rw-r--r--Documentation/ABI/testing/sysfs-driver-ppi2
-rw-r--r--Documentation/ABI/testing/sysfs-driver-st2
-rw-r--r--Documentation/ABI/testing/sysfs-driver-wacom2
-rw-r--r--Documentation/ABI/testing/sysfs-fs-f2fs8
-rw-r--r--Documentation/ABI/testing/sysfs-kernel-fscaps2
-rw-r--r--Documentation/ABI/testing/sysfs-kernel-vmcoreinfo2
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst10
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt19
-rw-r--r--Documentation/arm64/silicon-errata.rst2
-rw-r--r--Documentation/core-api/kernel-api.rst2
-rw-r--r--Documentation/dev-tools/kmemleak.rst48
-rw-r--r--Documentation/driver-api/gpio/driver.rst2
-rw-r--r--Documentation/driver-model/binding.rst (renamed from Documentation/driver-model/binding.txt)20
-rw-r--r--Documentation/driver-model/bus.rst (renamed from Documentation/driver-model/bus.txt)69
-rw-r--r--Documentation/driver-model/class.rst (renamed from Documentation/driver-model/class.txt)74
-rw-r--r--Documentation/driver-model/design-patterns.rst (renamed from Documentation/driver-model/design-patterns.txt)106
-rw-r--r--Documentation/driver-model/device.rst (renamed from Documentation/driver-model/device.txt)57
-rw-r--r--Documentation/driver-model/devres.rst (renamed from Documentation/driver-model/devres.txt)50
-rw-r--r--Documentation/driver-model/driver.rst (renamed from Documentation/driver-model/driver.txt)114
-rw-r--r--Documentation/driver-model/index.rst26
-rw-r--r--Documentation/driver-model/overview.rst (renamed from Documentation/driver-model/overview.txt)37
-rw-r--r--Documentation/driver-model/platform.rst (renamed from Documentation/driver-model/platform.txt)30
-rw-r--r--Documentation/driver-model/porting.rst (renamed from Documentation/driver-model/porting.txt)335
-rw-r--r--Documentation/eisa.txt4
-rw-r--r--Documentation/filesystems/debugfs.txt2
-rw-r--r--Documentation/filesystems/f2fs.txt133
-rw-r--r--Documentation/filesystems/proc.txt41
-rw-r--r--Documentation/filesystems/xfs-self-describing-metadata.txt8
-rw-r--r--Documentation/hwmon/submitting-patches.rst2
-rw-r--r--Documentation/kbuild/headers_install.rst7
-rw-r--r--Documentation/kbuild/kbuild.rst9
-rw-r--r--Documentation/kbuild/makefiles.rst22
-rw-r--r--Documentation/virtual/index.rst18
-rw-r--r--Documentation/virtual/kvm/api.txt28
-rw-r--r--Documentation/virtual/kvm/arm/psci.txt31
-rw-r--r--Documentation/virtual/kvm/cpuid.rst107
-rw-r--r--Documentation/virtual/kvm/cpuid.txt83
-rw-r--r--Documentation/virtual/kvm/hypercalls.txt11
-rw-r--r--Documentation/virtual/kvm/index.rst11
-rw-r--r--Documentation/virtual/kvm/locking.txt4
-rw-r--r--Documentation/virtual/kvm/msr.txt9
-rw-r--r--Documentation/virtual/paravirt_ops.rst (renamed from Documentation/virtual/paravirt_ops.txt)19
-rw-r--r--MAINTAINERS10
-rw-r--r--Makefile117
-rw-r--r--arch/Kconfig8
-rw-r--r--arch/alpha/Makefile2
-rw-r--r--arch/alpha/include/asm/pgalloc.h40
-rw-r--r--arch/arc/Kconfig2
-rw-r--r--arch/arc/Makefile2
-rw-r--r--arch/arc/configs/tb10x_defconfig1
-rw-r--r--arch/arc/mm/dma.c71
-rw-r--r--arch/arm/Kconfig8
-rw-r--r--arch/arm/include/asm/kvm_emulate.h10
-rw-r--r--arch/arm/include/asm/kvm_host.h18
-rw-r--r--arch/arm/include/asm/kvm_hyp.h13
-rw-r--r--arch/arm/include/asm/pgalloc.h41
-rw-r--r--arch/arm/include/asm/ptdump.h9
-rw-r--r--arch/arm/include/uapi/asm/kvm.h12
-rw-r--r--arch/arm/kernel/efi.c3
-rw-r--r--arch/arm/mach-omap1/clock.c64
-rw-r--r--arch/arm/mach-omap1/pm.c7
-rw-r--r--arch/arm/mach-omap2/pm-debug.c15
-rw-r--r--arch/arm/mm/dma-mapping-nommu.c24
-rw-r--r--arch/arm/mm/dma-mapping.c23
-rw-r--r--arch/arm/mm/dump.c4
-rw-r--r--arch/arm/mm/mmu.c2
-rw-r--r--arch/arm/mm/pageattr.c3
-rw-r--r--arch/arm/mm/ptdump_debugfs.c8
-rw-r--r--arch/arm64/Kconfig4
-rw-r--r--arch/arm64/Makefile2
-rw-r--r--arch/arm64/include/asm/assembler.h4
-rw-r--r--arch/arm64/include/asm/cpufeature.h6
-rw-r--r--arch/arm64/include/asm/kvm_asm.h6
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h30
-rw-r--r--arch/arm64/include/asm/kvm_host.h23
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h50
-rw-r--r--arch/arm64/include/asm/pgalloc.h47
-rw-r--r--arch/arm64/include/asm/ptrace.h31
-rw-r--r--arch/arm64/include/asm/sysreg.h35
-rw-r--r--arch/arm64/include/uapi/asm/kvm.h10
-rw-r--r--arch/arm64/kernel/cpu_errata.c23
-rw-r--r--arch/arm64/kernel/efi.c3
-rw-r--r--arch/arm64/kernel/setup.c5
-rw-r--r--arch/arm64/kernel/smp.c5
-rw-r--r--arch/arm64/kernel/traps.c4
-rw-r--r--arch/arm64/kvm/hyp/entry.S36
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S30
-rw-r--r--arch/arm64/kvm/hyp/switch.c14
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c78
-rw-r--r--arch/arm64/kvm/hyp/tlb.c12
-rw-r--r--arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c2
-rw-r--r--arch/arm64/kvm/regmap.c4
-rw-r--r--arch/arm64/kvm/sys_regs.c60
-rw-r--r--arch/arm64/kvm/va_layout.c7
-rw-r--r--arch/arm64/mm/mmu.c2
-rw-r--r--arch/arm64/mm/pageattr.c3
-rw-r--r--arch/arm64/mm/pgd.c6
-rw-r--r--arch/csky/Makefile1
-rw-r--r--arch/csky/include/asm/pgalloc.h30
-rw-r--r--arch/m68k/include/asm/sun3_pgalloc.h41
-rw-r--r--arch/mips/Kconfig3
-rw-r--r--arch/mips/include/asm/page.h3
-rw-r--r--arch/mips/include/asm/pgalloc.h33
-rw-r--r--arch/mips/include/asm/pgtable.h3
-rw-r--r--arch/mips/include/asm/ptrace.h5
-rw-r--r--arch/mips/jazz/jazzdma.c6
-rw-r--r--arch/mips/kvm/mips.c4
-rw-r--r--arch/mips/mm/Makefile1
-rw-r--r--arch/mips/mm/cache.c2
-rw-r--r--arch/mips/mm/dma-noncoherent.c26
-rw-r--r--arch/mips/mm/gup.c303
-rw-r--r--arch/nds32/Kconfig2
-rw-r--r--arch/nds32/Makefile2
-rw-r--r--arch/nds32/configs/defconfig1
-rw-r--r--arch/nds32/include/asm/pgalloc.h31
-rw-r--r--arch/nds32/kernel/dma.c325
-rw-r--r--arch/nios2/Kconfig1
-rw-r--r--arch/nios2/Kconfig.debug3
-rw-r--r--arch/nios2/configs/10m50_defconfig1
-rw-r--r--arch/nios2/configs/3c120_defconfig1
-rw-r--r--arch/nios2/include/asm/page.h6
-rw-r--r--arch/nios2/include/asm/pgalloc.h37
-rw-r--r--arch/nios2/mm/dma-mapping.c34
-rw-r--r--arch/openrisc/kernel/dma.c22
-rw-r--r--arch/parisc/Makefile12
-rw-r--r--arch/parisc/configs/a500_defconfig1
-rw-r--r--arch/parisc/configs/b180_defconfig1
-rw-r--r--arch/parisc/configs/c3000_defconfig1
-rw-r--r--arch/parisc/configs/default_defconfig1
-rw-r--r--arch/parisc/include/asm/pgalloc.h33
-rw-r--r--arch/parisc/kernel/pci-dma.c48
-rw-r--r--arch/powerpc/Kconfig3
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig1
-rw-r--r--arch/powerpc/include/asm/pgtable.h14
-rw-r--r--arch/powerpc/include/asm/ptrace.h29
-rw-r--r--arch/powerpc/kvm/book3s_xics.c2
-rw-r--r--arch/powerpc/kvm/powerpc.c4
-rw-r--r--arch/powerpc/mm/hugetlbpage.c72
-rw-r--r--arch/powerpc/platforms/pseries/ibmebus.c4
-rw-r--r--arch/riscv/Makefile2
-rw-r--r--arch/riscv/include/asm/pgalloc.h29
-rw-r--r--arch/s390/Kconfig5
-rw-r--r--arch/s390/Makefile2
-rw-r--r--arch/s390/configs/debug_defconfig1
-rw-r--r--arch/s390/include/asm/kvm_host.h1
-rw-r--r--arch/s390/include/asm/pci_insn.h10
-rw-r--r--arch/s390/include/asm/pgtable.h8
-rw-r--r--arch/s390/include/asm/sclp.h1
-rw-r--r--arch/s390/include/uapi/asm/dasd.h154
-rw-r--r--arch/s390/kernel/early.c2
-rw-r--r--arch/s390/kernel/ipl.c7
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c2
-rw-r--r--arch/s390/kernel/unwind_bc.c2
-rw-r--r--arch/s390/kvm/kvm-s390.c9
-rw-r--r--arch/s390/pci/pci.c4
-rw-r--r--arch/s390/pci/pci_sysfs.c10
-rw-r--r--arch/sh/Kconfig2
-rw-r--r--arch/sh/configs/hp6xx_defconfig1
-rw-r--r--arch/sh/configs/sdk7786_defconfig1
-rw-r--r--arch/sh/configs/sh2007_defconfig1
-rw-r--r--arch/sh/include/asm/io.h6
-rw-r--r--arch/sh/include/asm/pgtable-3level.h3
-rw-r--r--arch/sh/include/asm/pgtable.h37
-rw-r--r--arch/sh/include/asm/ptrace.h29
-rw-r--r--arch/sh/kernel/kdebugfs.c3
-rw-r--r--arch/sh/mm/Makefile2
-rw-r--r--arch/sh/mm/asids-debugfs.c11
-rw-r--r--arch/sh/mm/cache-debugfs.c20
-rw-r--r--arch/sh/mm/gup.c277
-rw-r--r--arch/sh/mm/pmb.c9
-rw-r--r--arch/sh/mm/tlb-debugfs.c20
-rw-r--r--arch/sparc/Kconfig4
-rw-r--r--arch/sparc/include/asm/pgtable_64.h43
-rw-r--r--arch/sparc/mm/Makefile2
-rw-r--r--arch/sparc/mm/gup.c340
-rw-r--r--arch/um/Makefile2
-rw-r--r--arch/um/include/asm/pgalloc.h16
-rw-r--r--arch/um/kernel/mem.c22
-rw-r--r--arch/unicore32/Makefile3
-rw-r--r--arch/unicore32/configs/defconfig (renamed from arch/unicore32/configs/unicore32_defconfig)0
-rw-r--r--arch/unicore32/include/asm/pgalloc.h36
-rw-r--r--arch/unicore32/include/mach/regs-gpio.h2
-rw-r--r--arch/x86/Kconfig5
-rw-r--r--arch/x86/ia32/ia32_signal.c2
-rw-r--r--arch/x86/include/asm/bitops.h189
-rw-r--r--arch/x86/include/asm/kvm_host.h11
-rw-r--r--arch/x86/include/asm/mshyperv.h148
-rw-r--r--arch/x86/include/asm/pgalloc.h19
-rw-r--r--arch/x86/include/asm/pgtable-3level.h47
-rw-r--r--arch/x86/include/asm/pgtable_64.h8
-rw-r--r--arch/x86/include/asm/ptrace.h30
-rw-r--r--arch/x86/include/uapi/asm/kvm.h19
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h3
-rw-r--r--arch/x86/include/uapi/asm/vmx.h1
-rw-r--r--arch/x86/kernel/kdebugfs.c60
-rw-r--r--arch/x86/kernel/kvm.c21
-rw-r--r--arch/x86/kernel/signal.c2
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/cpuid.c247
-rw-r--r--arch/x86/kvm/emulate.c2
-rw-r--r--arch/x86/kvm/irq.h1
-rw-r--r--arch/x86/kvm/irq_comm.c2
-rw-r--r--arch/x86/kvm/lapic.c123
-rw-r--r--arch/x86/kvm/lapic.h8
-rw-r--r--arch/x86/kvm/mmu.c184
-rw-r--r--arch/x86/kvm/mmutrace.h59
-rw-r--r--arch/x86/kvm/paging_tmpl.h42
-rw-r--r--arch/x86/kvm/pmu.c63
-rw-r--r--arch/x86/kvm/pmu.h1
-rw-r--r--arch/x86/kvm/svm.c51
-rw-r--r--arch/x86/kvm/trace.h2
-rw-r--r--arch/x86/kvm/vmx/evmcs.c18
-rw-r--r--arch/x86/kvm/vmx/evmcs.h1
-rw-r--r--arch/x86/kvm/vmx/nested.c763
-rw-r--r--arch/x86/kvm/vmx/nested.h4
-rw-r--r--arch/x86/kvm/vmx/ops.h1
-rw-r--r--arch/x86/kvm/vmx/vmcs.h17
-rw-r--r--arch/x86/kvm/vmx/vmcs12.h57
-rw-r--r--arch/x86/kvm/vmx/vmcs_shadow_fields.h79
-rw-r--r--arch/x86/kvm/vmx/vmx.c449
-rw-r--r--arch/x86/kvm/vmx/vmx.h124
-rw-r--r--arch/x86/kvm/x86.c229
-rw-r--r--arch/x86/kvm/x86.h10
-rw-r--r--arch/x86/mm/debug_pagetables.c35
-rw-r--r--arch/x86/mm/pgtable.c33
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c23
-rw-r--r--arch/x86/platform/intel-quark/imr.c14
-rw-r--r--arch/x86/platform/intel/iosf_mbi.c21
-rw-r--r--arch/x86/platform/uv/tlb_uv.c15
-rw-r--r--arch/x86/xen/debugfs.c7
-rw-r--r--arch/x86/xen/mmu_pv.c3
-rw-r--r--arch/x86/xen/p2m.c3
-rw-r--r--arch/xtensa/kernel/pci-dma.c8
-rw-r--r--drivers/acpi/acpi_lpss.c4
-rw-r--r--drivers/acpi/utils.c11
-rw-r--r--drivers/amba/tegra-ahb.c4
-rw-r--r--drivers/base/arch_topology.c5
-rw-r--r--drivers/base/bus.c6
-rw-r--r--drivers/base/cacheinfo.c3
-rw-r--r--drivers/base/core.c6
-rw-r--r--drivers/base/dd.c55
-rw-r--r--drivers/base/devcon.c2
-rw-r--r--drivers/base/driver.c4
-rw-r--r--drivers/base/firmware_loader/Kconfig18
-rw-r--r--drivers/base/firmware_loader/fallback.c65
-rw-r--r--drivers/base/firmware_loader/firmware.h16
-rw-r--r--drivers/base/firmware_loader/main.c224
-rw-r--r--drivers/base/node.c5
-rw-r--r--drivers/base/platform.c2
-rw-r--r--drivers/char/ipmi/ipmi_msghandler.c8
-rw-r--r--drivers/char/ipmi/ipmi_si_platform.c2
-rw-r--r--drivers/clk/renesas/r8a77470-cpg-mssr.c2
-rw-r--r--drivers/firmware/arm_scmi/common.h2
-rw-r--r--drivers/firmware/efi/dev-path-parser.c4
-rw-r--r--drivers/firmware/ti_sci.h2
-rw-r--r--drivers/fpga/of-fpga-region.c7
-rw-r--r--drivers/gpio/gpio-cs5535.c2
-rw-r--r--drivers/gpu/drm/drm_mipi_dsi.c2
-rw-r--r--drivers/gpu/drm/i915/.gitignore1
-rw-r--r--drivers/gpu/drm/i915/Makefile.header-test12
-rw-r--r--drivers/gpu/drm/i915/i915_mm.c3
-rw-r--r--drivers/gpu/drm/tegra/dc.c4
-rw-r--r--drivers/hv/vmbus_drv.c1
-rw-r--r--drivers/hwtracing/coresight/coresight-cpu-debug.c15
-rw-r--r--drivers/hwtracing/coresight/coresight-platform.c2
-rw-r--r--drivers/hwtracing/coresight/coresight-priv.h2
-rw-r--r--drivers/hwtracing/coresight/coresight.c6
-rw-r--r--drivers/hwtracing/intel_th/core.c5
-rw-r--r--drivers/i2c/busses/i2c-amd-mp2-pci.c2
-rw-r--r--drivers/i2c/i2c-core-acpi.c4
-rw-r--r--drivers/i2c/i2c-core-of.c4
-rw-r--r--drivers/iio/inkern.c2
-rw-r--r--drivers/infiniband/core/uverbs_ioctl.c2
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v1.c2
-rw-r--r--drivers/iommu/arm-smmu-v3.c2
-rw-r--r--drivers/iommu/arm-smmu.c2
-rw-r--r--drivers/iommu/dma-iommu.c14
-rw-r--r--drivers/mailbox/bcm-flexrm-mailbox.c28
-rw-r--r--drivers/mailbox/bcm-pdc-mailbox.c8
-rw-r--r--drivers/mfd/altera-sysmgr.c4
-rw-r--r--drivers/mfd/syscon.c21
-rw-r--r--drivers/misc/cxl/cxl.h15
-rw-r--r--drivers/misc/cxl/debugfs.c36
-rw-r--r--drivers/misc/genwqe/card_base.c5
-rw-r--r--drivers/misc/genwqe/card_base.h2
-rw-r--r--drivers/misc/genwqe/card_debugfs.c165
-rw-r--r--drivers/misc/genwqe/card_dev.c6
-rw-r--r--drivers/misc/lkdtm/core.c20
-rw-r--r--drivers/misc/lkdtm/heap.c72
-rw-r--r--drivers/misc/lkdtm/lkdtm.h5
-rw-r--r--drivers/misc/mei/debugfs.c47
-rw-r--r--drivers/misc/mei/main.c8
-rw-r--r--drivers/misc/mei/mei_dev.h7
-rw-r--r--drivers/misc/mic/card/mic_debugfs.c18
-rw-r--r--drivers/misc/mic/cosm/cosm_debugfs.c4
-rw-r--r--drivers/misc/mic/host/mic_debugfs.c4
-rw-r--r--drivers/misc/mic/scif/scif_debugfs.c5
-rw-r--r--drivers/misc/mic/vop/vop_debugfs.c4
-rw-r--r--drivers/misc/ti-st/st_kim.c4
-rw-r--r--drivers/misc/vmw_balloon.c20
-rw-r--r--drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c2
-rw-r--r--drivers/net/ethernet/ti/cpsw-phy-sel.c4
-rw-r--r--drivers/net/ethernet/ti/davinci_emac.c2
-rw-r--r--drivers/net/ethernet/toshiba/tc35815.c4
-rw-r--r--drivers/net/wireless/realtek/rtlwifi/wifi.h2
-rw-r--r--drivers/nvmem/core.c2
-rw-r--r--drivers/of/of_mdio.c2
-rw-r--r--drivers/of/platform.c2
-rw-r--r--drivers/pci/probe.c2
-rw-r--r--drivers/pci/search.c4
-rw-r--r--drivers/pinctrl/devicetree.c7
-rw-r--r--drivers/s390/block/dasd.c233
-rw-r--r--drivers/s390/block/dasd_devmap.c70
-rw-r--r--drivers/s390/block/dasd_diag.c22
-rw-r--r--drivers/s390/block/dasd_eckd.c966
-rw-r--r--drivers/s390/block/dasd_eckd.h175
-rw-r--r--drivers/s390/block/dasd_eer.c1
-rw-r--r--drivers/s390/block/dasd_fba.c45
-rw-r--r--drivers/s390/block/dasd_fba.h5
-rw-r--r--drivers/s390/block/dasd_int.h33
-rw-r--r--drivers/s390/block/dasd_ioctl.c56
-rw-r--r--drivers/s390/char/sclp_early.c1
-rw-r--r--drivers/s390/cio/ccwgroup.c6
-rw-r--r--drivers/s390/cio/chsc_sch.c2
-rw-r--r--drivers/s390/cio/css.c4
-rw-r--r--drivers/s390/cio/device.c10
-rw-r--r--drivers/s390/cio/scm.c4
-rw-r--r--drivers/s390/crypto/ap_bus.c9
-rw-r--r--drivers/s390/crypto/vfio_ap_ops.c5
-rw-r--r--drivers/scsi/lpfc/lpfc_init.c2
-rw-r--r--drivers/scsi/scsi_proc.c2
-rw-r--r--drivers/spi/spi.c4
-rw-r--r--drivers/staging/most/core.c9
-rw-r--r--drivers/staging/rtl8723bs/hal/rtl8723b_phycfg.c2
-rw-r--r--drivers/thermal/broadcom/bcm2835_thermal.c2
-rw-r--r--drivers/thermal/intel/intel_powerclamp.c12
-rw-r--r--drivers/thermal/intel/x86_pkg_temp_thermal.c25
-rw-r--r--drivers/thermal/tegra/soctherm.c14
-rw-r--r--drivers/thunderbolt/switch.c4
-rw-r--r--drivers/usb/Kconfig1
-rw-r--r--drivers/usb/core/buffer.c17
-rw-r--r--drivers/usb/core/devio.c4
-rw-r--r--drivers/usb/core/hcd.c51
-rw-r--r--drivers/usb/core/usb.c4
-rw-r--r--drivers/usb/host/ehci-hcd.c2
-rw-r--r--drivers/usb/host/fotg210-hcd.c2
-rw-r--r--drivers/usb/host/ohci-hcd.c25
-rw-r--r--drivers/usb/host/ohci-mem.c37
-rw-r--r--drivers/usb/host/ohci-sm501.c50
-rw-r--r--drivers/usb/host/ohci-tmio.c15
-rw-r--r--drivers/usb/host/ohci.h2
-rw-r--r--drivers/usb/host/uhci-hcd.c2
-rw-r--r--drivers/usb/phy/phy-am335x-control.c4
-rw-r--r--drivers/usb/phy/phy-isp1301.c4
-rw-r--r--drivers/video/fbdev/au1100fb.c24
-rw-r--r--drivers/video/fbdev/au1100fb.h1
-rw-r--r--drivers/visorbus/visorbus_main.c4
-rw-r--r--drivers/watchdog/bcm_kona_wdt.c14
-rw-r--r--drivers/watchdog/mei_wdt.c30
-rw-r--r--drivers/xen/gntdev.c6
-rw-r--r--drivers/xen/privcmd.c6
-rw-r--r--drivers/xen/xlate_mmu.c3
-rw-r--r--fs/9p/vfs_addr.c6
-rw-r--r--fs/btrfs/ioctl.c30
-rw-r--r--fs/btrfs/sysfs.c18
-rw-r--r--fs/ceph/debugfs.c24
-rw-r--r--fs/ceph/super.c4
-rw-r--r--fs/ceph/super.h2
-rw-r--r--fs/debugfs/file.c14
-rw-r--r--fs/debugfs/inode.c34
-rw-r--r--fs/dlm/debug_fs.c21
-rw-r--r--fs/dlm/dlm_internal.h8
-rw-r--r--fs/dlm/lockspace.c3
-rw-r--r--fs/dlm/lowcomms.c18
-rw-r--r--fs/dlm/main.c5
-rw-r--r--fs/efivarfs/file.c26
-rw-r--r--fs/ext2/ioctl.c16
-rw-r--r--fs/ext4/ioctl.c51
-rw-r--r--fs/f2fs/checkpoint.c107
-rw-r--r--fs/f2fs/data.c249
-rw-r--r--fs/f2fs/debug.c7
-rw-r--r--fs/f2fs/dir.c16
-rw-r--r--fs/f2fs/extent_cache.c7
-rw-r--r--fs/f2fs/f2fs.h129
-rw-r--r--fs/f2fs/file.c302
-rw-r--r--fs/f2fs/gc.c196
-rw-r--r--fs/f2fs/inline.c16
-rw-r--r--fs/f2fs/inode.c78
-rw-r--r--fs/f2fs/namei.c10
-rw-r--r--fs/f2fs/node.c38
-rw-r--r--fs/f2fs/recovery.c43
-rw-r--r--fs/f2fs/segment.c170
-rw-r--r--fs/f2fs/segment.h16
-rw-r--r--fs/f2fs/super.c610
-rw-r--r--fs/f2fs/sysfs.c28
-rw-r--r--fs/f2fs/xattr.c10
-rw-r--r--fs/gfs2/file.c42
-rw-r--r--fs/gfs2/sys.c3
-rw-r--r--fs/hfsplus/ioctl.c21
-rw-r--r--fs/inode.c86
-rw-r--r--fs/jffs2/file.c4
-rw-r--r--fs/jffs2/fs.c2
-rw-r--r--fs/jffs2/os-linux.h2
-rw-r--r--fs/jfs/ioctl.c22
-rw-r--r--fs/nfsd/fault_inject.c12
-rw-r--r--fs/nfsd/nfsctl.c5
-rw-r--r--fs/nfsd/state.h4
-rw-r--r--fs/nilfs2/ioctl.c9
-rw-r--r--fs/notify/fanotify/fanotify.c5
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c8
-rw-r--r--fs/ocfs2/alloc.c10
-rw-r--r--fs/ocfs2/blockcheck.c56
-rw-r--r--fs/ocfs2/blockcheck.h7
-rw-r--r--fs/ocfs2/cluster/heartbeat.c102
-rw-r--r--fs/ocfs2/cluster/heartbeat.h2
-rw-r--r--fs/ocfs2/cluster/netdebug.c39
-rw-r--r--fs/ocfs2/cluster/nodemanager.c4
-rw-r--r--fs/ocfs2/cluster/quorum.c2
-rw-r--r--fs/ocfs2/cluster/tcp.c5
-rw-r--r--fs/ocfs2/cluster/tcp.h5
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c44
-rw-r--r--fs/ocfs2/dlm/dlmdebug.h10
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c10
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c2
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c8
-rw-r--r--fs/ocfs2/dlmglue.c96
-rw-r--r--fs/ocfs2/ioctl.c13
-rw-r--r--fs/ocfs2/localalloc.c6
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/super.c29
-rw-r--r--fs/orangefs/file.c37
-rw-r--r--fs/orangefs/orangefs-debugfs.c54
-rw-r--r--fs/orangefs/orangefs-debugfs.h2
-rw-r--r--fs/orangefs/orangefs-mod.c6
-rw-r--r--fs/proc/base.c31
-rw-r--r--fs/proc/meminfo.c2
-rw-r--r--fs/proc/task_mmu.c115
-rw-r--r--fs/proc/task_nommu.c6
-rw-r--r--fs/reiserfs/ioctl.c10
-rw-r--r--fs/ubifs/debug.c169
-rw-r--r--fs/ubifs/debug.h4
-rw-r--r--fs/ubifs/ioctl.c13
-rw-r--r--fs/ubifs/super.c9
-rw-r--r--fs/xfs/Makefile9
-rw-r--r--fs/xfs/kmem.c5
-rw-r--r--fs/xfs/kmem.h8
-rw-r--r--fs/xfs/libxfs/xfs_ag.c100
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c8
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c227
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c3
-rw-r--r--fs/xfs/libxfs/xfs_attr.c5
-rw-r--r--fs/xfs/libxfs/xfs_attr.h8
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c15
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c14
-rw-r--r--fs/xfs/libxfs/xfs_bit.c1
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c19
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c5
-rw-r--r--fs/xfs/libxfs/xfs_btree.c49
-rw-r--r--fs/xfs/libxfs/xfs_btree.h14
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c12
-rw-r--r--fs/xfs/libxfs/xfs_da_format.c3
-rw-r--r--fs/xfs/libxfs/xfs_defer.c2
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c6
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c11
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c14
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c11
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c10
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c5
-rw-r--r--fs/xfs/libxfs/xfs_dquot_buf.c10
-rw-r--r--fs/xfs/libxfs/xfs_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_fs.h124
-rw-r--r--fs/xfs/libxfs/xfs_health.h2
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c245
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h18
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c56
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.h3
-rw-r--r--fs/xfs/libxfs/xfs_iext_tree.c6
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c9
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c4
-rw-r--r--fs/xfs/libxfs/xfs_log_rlimit.c2
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c2
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c4
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c7
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c6
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c8
-rw-r--r--fs/xfs/libxfs/xfs_sb.c39
-rw-r--r--fs/xfs/libxfs/xfs_shared.h49
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c10
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c17
-rw-r--r--fs/xfs/libxfs/xfs_trans_space.h7
-rw-r--r--fs/xfs/libxfs/xfs_types.c13
-rw-r--r--fs/xfs/scrub/agheader.c11
-rw-r--r--fs/xfs/scrub/agheader_repair.c5
-rw-r--r--fs/xfs/scrub/alloc.c7
-rw-r--r--fs/xfs/scrub/attr.c122
-rw-r--r--fs/xfs/scrub/attr.h71
-rw-r--r--fs/xfs/scrub/bitmap.c5
-rw-r--r--fs/xfs/scrub/bmap.c8
-rw-r--r--fs/xfs/scrub/btree.c7
-rw-r--r--fs/xfs/scrub/common.c8
-rw-r--r--fs/xfs/scrub/dabtree.c8
-rw-r--r--fs/xfs/scrub/dir.c10
-rw-r--r--fs/xfs/scrub/fscounters.c12
-rw-r--r--fs/xfs/scrub/health.c8
-rw-r--r--fs/xfs/scrub/ialloc.c28
-rw-r--r--fs/xfs/scrub/inode.c10
-rw-r--r--fs/xfs/scrub/parent.c8
-rw-r--r--fs/xfs/scrub/quota.c13
-rw-r--r--fs/xfs/scrub/refcount.c10
-rw-r--r--fs/xfs/scrub/repair.c14
-rw-r--r--fs/xfs/scrub/rmap.c9
-rw-r--r--fs/xfs/scrub/rtbitmap.c7
-rw-r--r--fs/xfs/scrub/scrub.c20
-rw-r--r--fs/xfs/scrub/symlink.c8
-rw-r--r--fs/xfs/scrub/trace.c6
-rw-r--r--fs/xfs/xfs_acl.c4
-rw-r--r--fs/xfs/xfs_aops.c121
-rw-r--r--fs/xfs/xfs_aops.h1
-rw-r--r--fs/xfs/xfs_attr_inactive.c7
-rw-r--r--fs/xfs/xfs_attr_list.c7
-rw-r--r--fs/xfs/xfs_bio_io.c61
-rw-r--r--fs/xfs/xfs_bmap_item.c350
-rw-r--r--fs/xfs/xfs_bmap_item.h2
-rw-r--r--fs/xfs/xfs_bmap_util.c11
-rw-r--r--fs/xfs/xfs_buf.c171
-rw-r--r--fs/xfs/xfs_buf.h53
-rw-r--r--fs/xfs/xfs_buf_item.c40
-rw-r--r--fs/xfs/xfs_buf_item.h6
-rw-r--r--fs/xfs/xfs_dir2_readdir.c5
-rw-r--r--fs/xfs/xfs_discard.c4
-rw-r--r--fs/xfs/xfs_dquot.c6
-rw-r--r--fs/xfs/xfs_dquot.h1
-rw-r--r--fs/xfs/xfs_dquot_item.c118
-rw-r--r--fs/xfs/xfs_dquot_item.h4
-rw-r--r--fs/xfs/xfs_error.c3
-rw-r--r--fs/xfs/xfs_export.c4
-rw-r--r--fs/xfs/xfs_extfree_item.c410
-rw-r--r--fs/xfs/xfs_extfree_item.h6
-rw-r--r--fs/xfs/xfs_file.c23
-rw-r--r--fs/xfs/xfs_filestream.c5
-rw-r--r--fs/xfs/xfs_fsmap.c4
-rw-r--r--fs/xfs/xfs_fsops.c8
-rw-r--r--fs/xfs/xfs_globals.c4
-rw-r--r--fs/xfs/xfs_health.c6
-rw-r--r--fs/xfs/xfs_icache.c4
-rw-r--r--fs/xfs/xfs_icreate_item.c75
-rw-r--r--fs/xfs/xfs_inode.c42
-rw-r--r--fs/xfs/xfs_inode_item.c16
-rw-r--r--fs/xfs/xfs_inode_item.h2
-rw-r--r--fs/xfs/xfs_ioctl.c448
-rw-r--r--fs/xfs/xfs_ioctl.h8
-rw-r--r--fs/xfs/xfs_ioctl32.c161
-rw-r--r--fs/xfs/xfs_ioctl32.h14
-rw-r--r--fs/xfs/xfs_iomap.c5
-rw-r--r--fs/xfs/xfs_iops.c10
-rw-r--r--fs/xfs/xfs_itable.c749
-rw-r--r--fs/xfs/xfs_itable.h106
-rw-r--r--fs/xfs/xfs_iwalk.c720
-rw-r--r--fs/xfs/xfs_iwalk.h46
-rw-r--r--fs/xfs/xfs_linux.h5
-rw-r--r--fs/xfs/xfs_log.c644
-rw-r--r--fs/xfs/xfs_log.h17
-rw-r--r--fs/xfs/xfs_log_cil.c51
-rw-r--r--fs/xfs/xfs_log_priv.h36
-rw-r--r--fs/xfs/xfs_log_recover.c463
-rw-r--r--fs/xfs/xfs_message.c2
-rw-r--r--fs/xfs/xfs_mount.c102
-rw-r--r--fs/xfs/xfs_mount.h22
-rw-r--r--fs/xfs/xfs_ondisk.h5
-rw-r--r--fs/xfs/xfs_pnfs.c9
-rw-r--r--fs/xfs/xfs_pwork.c136
-rw-r--r--fs/xfs/xfs_pwork.h61
-rw-r--r--fs/xfs/xfs_qm.c68
-rw-r--r--fs/xfs/xfs_qm_bhv.c2
-rw-r--r--fs/xfs/xfs_qm_syscalls.c5
-rw-r--r--fs/xfs/xfs_quotaops.c3
-rw-r--r--fs/xfs/xfs_refcount_item.c357
-rw-r--r--fs/xfs/xfs_refcount_item.h2
-rw-r--r--fs/xfs/xfs_reflink.c15
-rw-r--r--fs/xfs/xfs_rmap_item.c380
-rw-r--r--fs/xfs/xfs_rmap_item.h2
-rw-r--r--fs/xfs/xfs_rtalloc.c6
-rw-r--r--fs/xfs/xfs_stats.c1
-rw-r--r--fs/xfs/xfs_super.c32
-rw-r--r--fs/xfs/xfs_super.h14
-rw-r--r--fs/xfs/xfs_symlink.c9
-rw-r--r--fs/xfs/xfs_sysctl.c3
-rw-r--r--fs/xfs/xfs_sysctl.h3
-rw-r--r--fs/xfs/xfs_sysfs.c42
-rw-r--r--fs/xfs/xfs_trace.c8
-rw-r--r--fs/xfs/xfs_trace.h61
-rw-r--r--fs/xfs/xfs_trans.c43
-rw-r--r--fs/xfs/xfs_trans.h70
-rw-r--r--fs/xfs/xfs_trans_ail.c53
-rw-r--r--fs/xfs/xfs_trans_bmap.c232
-rw-r--r--fs/xfs/xfs_trans_buf.c11
-rw-r--r--fs/xfs/xfs_trans_dquot.c11
-rw-r--r--fs/xfs/xfs_trans_extfree.c286
-rw-r--r--fs/xfs/xfs_trans_inode.c3
-rw-r--r--fs/xfs/xfs_trans_priv.h4
-rw-r--r--fs/xfs/xfs_trans_refcount.c240
-rw-r--r--fs/xfs/xfs_trans_rmap.c257
-rw-r--r--fs/xfs/xfs_xattr.c5
-rw-r--r--include/Kbuild1270
-rw-r--r--include/asm-generic/bitops-instrumented.h263
-rw-r--r--include/asm-generic/mshyperv.h180
-rw-r--r--include/asm-generic/pgalloc.h107
-rw-r--r--include/asm-generic/ptrace.h73
-rw-r--r--include/kvm/arm_pmu.h11
-rw-r--r--include/linux/backing-dev-defs.h1
-rw-r--r--include/linux/ceph/debugfs.h4
-rw-r--r--include/linux/cpuhotplug.h1
-rw-r--r--include/linux/debugfs.h12
-rw-r--r--include/linux/device.h11
-rw-r--r--include/linux/dma-contiguous.h19
-rw-r--r--include/linux/dma-noncoherent.h19
-rw-r--r--include/linux/dmar.h14
-rw-r--r--include/linux/fs.h12
-rw-r--r--include/linux/genalloc.h9
-rw-r--r--include/linux/hugetlb.h120
-rw-r--r--include/linux/kasan-checks.h43
-rw-r--r--include/linux/kasan.h7
-rw-r--r--include/linux/kvm_host.h5
-rw-r--r--include/linux/memcontrol.h24
-rw-r--r--include/linux/mfd/syscon.h6
-rw-r--r--include/linux/mm.h57
-rw-r--r--include/linux/mm_types.h2
-rw-r--r--include/linux/oom.h1
-rw-r--r--include/linux/page-flags.h6
-rw-r--r--include/linux/page-isolation.h2
-rw-r--r--include/linux/page_ext.h1
-rw-r--r--include/linux/pagemap.h6
-rw-r--r--include/linux/pfn_t.h7
-rw-r--r--include/linux/slab.h16
-rw-r--r--include/linux/swap.h18
-rw-r--r--include/linux/usb/hcd.h6
-rw-r--r--include/linux/vmalloc.h2
-rw-r--r--include/linux/vmpressure.h2
-rw-r--r--include/trace/events/f2fs.h11
-rw-r--r--include/uapi/Kbuild (renamed from include/uapi/linux/Kbuild)6
-rw-r--r--include/uapi/linux/kvm.h7
-rw-r--r--include/uapi/linux/kvm_para.h1
-rw-r--r--include/uapi/linux/nilfs2_ondisk.h24
-rw-r--r--init/Kconfig33
-rw-r--r--init/main.c24
-rw-r--r--kernel/dma/contiguous.c56
-rw-r--r--kernel/dma/direct.c55
-rw-r--r--kernel/dma/mapping.c12
-rw-r--r--kernel/dma/remap.c16
-rw-r--r--kernel/dma/swiotlb.c25
-rw-r--r--kernel/fail_function.c23
-rw-r--r--kernel/gcov/fs.c24
-rwxr-xr-xkernel/gen_kheaders.sh51
-rw-r--r--kernel/iomem.c2
-rw-r--r--kernel/kprobes.c25
-rw-r--r--kernel/trace/blktrace.c6
-rw-r--r--kernel/trace/trace.c4
-rw-r--r--lib/842/842_debugfs.h5
-rw-r--r--lib/Kconfig.debug25
-rw-r--r--lib/dynamic_debug.c12
-rw-r--r--lib/fault-inject.c73
-rw-r--r--lib/genalloc.c125
-rw-r--r--lib/kobject.c4
-rw-r--r--lib/notifier-error-inject.c13
-rw-r--r--lib/raid6/Makefile98
-rw-r--r--lib/test_kasan.c98
-rw-r--r--mm/Kconfig16
-rw-r--r--mm/Kconfig.debug14
-rw-r--r--mm/Makefile4
-rw-r--r--mm/backing-dev.c24
-rw-r--r--mm/cleancache.c3
-rw-r--r--mm/dmapool.c4
-rw-r--r--mm/failslab.c3
-rw-r--r--mm/filemap.c19
-rw-r--r--mm/gup.c674
-rw-r--r--mm/hwpoison-inject.c67
-rw-r--r--mm/kasan/common.c14
-rw-r--r--mm/kasan/generic.c13
-rw-r--r--mm/kasan/kasan.h15
-rw-r--r--mm/kasan/report.c165
-rw-r--r--mm/kasan/tags.c12
-rw-r--r--mm/kmemleak.c11
-rw-r--r--mm/list_lru.c3
-rw-r--r--mm/memcontrol.c461
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/memory.c15
-rw-r--r--mm/mincore.c12
-rw-r--r--mm/mmu_notifier.c2
-rw-r--r--mm/nommu.c91
-rw-r--r--mm/oom_kill.c131
-rw-r--r--mm/page-writeback.c1
-rw-r--r--mm/page_alloc.c234
-rw-r--r--mm/page_ext.c3
-rw-r--r--mm/page_io.c2
-rw-r--r--mm/page_isolation.c3
-rw-r--r--mm/slab.c79
-rw-r--r--mm/slab.h199
-rw-r--r--mm/slab_common.c269
-rw-r--r--mm/slob.c4
-rw-r--r--mm/slub.c86
-rw-r--r--mm/swap_state.c49
-rw-r--r--mm/swapfile.c291
-rw-r--r--mm/util.c47
-rw-r--r--mm/vmalloc.c108
-rw-r--r--mm/vmscan.c74
-rw-r--r--mm/z3fold.c12
-rw-r--r--mm/zsmalloc.c24
-rw-r--r--mm/zswap.c2
-rw-r--r--net/9p/trans_virtio.c8
-rw-r--r--net/9p/trans_xen.c8
-rw-r--r--net/bpfilter/Kconfig1
-rw-r--r--net/ceph/ceph_common.c5
-rw-r--r--net/ceph/debugfs.c33
-rw-r--r--net/core/sock.c2
-rw-r--r--net/sunrpc/debugfs.c66
-rw-r--r--samples/Kconfig14
-rw-r--r--samples/Makefile4
-rw-r--r--scripts/Kbuild.include28
-rw-r--r--scripts/Makefile5
-rw-r--r--scripts/Makefile.build11
-rw-r--r--scripts/Makefile.extrawarn3
-rw-r--r--scripts/Makefile.headersinst134
-rw-r--r--scripts/Makefile.host2
-rw-r--r--scripts/Makefile.lib26
-rw-r--r--scripts/Makefile.modbuiltin2
-rw-r--r--scripts/basic/fixdep.c51
-rw-r--r--scripts/coccinelle/api/kstrdup.cocci8
-rw-r--r--scripts/coccinelle/api/stream_open.cocci8
-rw-r--r--scripts/coccinelle/free/devm_free.cocci2
-rw-r--r--scripts/coccinelle/free/put_device.cocci11
-rwxr-xr-xscripts/decode_stacktrace.sh4
-rw-r--r--scripts/gdb/linux/Makefile2
-rw-r--r--scripts/genksyms/keywords.c4
-rw-r--r--scripts/genksyms/parse.y2
-rwxr-xr-xscripts/get_abi.pl468
-rwxr-xr-xscripts/headers.sh29
-rwxr-xr-xscripts/headers_install.sh48
-rw-r--r--scripts/kallsyms.c3
-rw-r--r--scripts/kconfig/Makefile8
-rw-r--r--scripts/kconfig/conf.c10
-rw-r--r--scripts/kconfig/confdata.c25
-rw-r--r--scripts/kconfig/lkc.h1
-rw-r--r--scripts/kconfig/lkc_proto.h3
-rw-r--r--scripts/kconfig/mconf.c10
-rw-r--r--scripts/kconfig/nconf.c10
-rw-r--r--scripts/kconfig/preprocess.c3
-rw-r--r--scripts/kconfig/qconf.cc2
-rw-r--r--scripts/kconfig/symbol.c2
-rwxr-xr-xscripts/package/builddeb2
-rwxr-xr-xscripts/package/mkspec2
-rw-r--r--scripts/spelling.txt36
-rwxr-xr-xscripts/tags.sh43
-rw-r--r--security/Kconfig.hardening29
-rw-r--r--sound/soc/rockchip/rk3399_gru_sound.c2
-rw-r--r--tools/firmware/Makefile2
-rw-r--r--tools/include/uapi/linux/kvm.h4
-rw-r--r--tools/testing/selftests/Makefile2
-rw-r--r--tools/testing/selftests/cgroup/test_freezer.c1
-rw-r--r--tools/testing/selftests/drivers/dma-buf/config1
-rwxr-xr-xtools/testing/selftests/firmware/fw_filesystem.sh73
-rwxr-xr-xtools/testing/selftests/firmware/fw_lib.sh7
-rwxr-xr-xtools/testing/selftests/firmware/fw_run_tests.sh1
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c3
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h4
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h3
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c50
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c9
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h2
-rw-r--r--tools/testing/selftests/kvm/lib/ucall.c19
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c5
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/kvm_create_max_vcpus.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c2
-rw-r--r--tools/testing/selftests/lib.mk4
-rw-r--r--tools/testing/selftests/networking/timestamping/timestamping.c9
-rw-r--r--tools/testing/selftests/rseq/rseq-arm.h61
-rw-r--r--tools/vm/slabinfo.c118
-rw-r--r--usr/.gitignore1
-rw-r--r--usr/Makefile2
-rw-r--r--usr/include/.gitignore3
-rw-r--r--usr/include/Makefile132
-rw-r--r--virt/kvm/arm/arch_timer.c24
-rw-r--r--virt/kvm/arm/arm.c7
-rw-r--r--virt/kvm/arm/mmu.c2
-rw-r--r--virt/kvm/arm/pmu.c350
-rw-r--r--virt/kvm/arm/psci.c149
-rw-r--r--virt/kvm/irqchip.c4
-rw-r--r--virt/kvm/kvm_main.c41
811 files changed, 18572 insertions, 14404 deletions
diff --git a/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra b/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
index 16020b31ae64..5d41ebadf15e 100644
--- a/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
+++ b/Documentation/ABI/obsolete/sysfs-driver-hid-roccat-pyra
@@ -5,7 +5,7 @@ Description: It is possible to switch the cpi setting of the mouse with the
press of a button.
When read, this file returns the raw number of the actual cpi
setting reported by the mouse. This number has to be further
- processed to receive the real dpi value.
+ processed to receive the real dpi value:
VALUE DPI
1 400
diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
index 156319fc5b80..3544968f43cc 100644
--- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io
+++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io
@@ -1,5 +1,4 @@
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- asic_health
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/asic_health
Date: June 2018
KernelVersion: 4.19
@@ -9,9 +8,8 @@ Description: This file shows ASIC health status. The possible values are:
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- cpld1_version
- cpld2_version
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld1_version
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/cpld2_version
Date: June 2018
KernelVersion: 4.19
Contact: Vadim Pasternak <vadimpmellanox.com>
@@ -20,8 +18,7 @@ Description: These files show with which CPLD versions have been burned
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- fan_dir
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/fan_dir
Date: December 2018
KernelVersion: 5.0
@@ -32,8 +29,7 @@ Description: This file shows the system fans direction:
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- jtag_enable
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/jtag_enable
Date: November 2018
KernelVersion: 5.0
@@ -43,8 +39,7 @@ Description: These files show with which CPLD versions have been burned
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- jtag_enable
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/jtag_enable
Date: November 2018
KernelVersion: 5.0
@@ -87,16 +82,15 @@ Description: These files allow asserting system power cycling, switching
The files are write only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- reset_aux_pwr_or_ref
- reset_asic_thermal
- reset_hotswap_or_halt
- reset_hotswap_or_wd
- reset_fw_reset
- reset_long_pb
- reset_main_pwr_fail
- reset_short_pb
- reset_sw_reset
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_aux_pwr_or_ref
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_asic_thermal
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_hotswap_or_halt
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_hotswap_or_wd
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_fw_reset
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_long_pb
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_main_pwr_fail
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_short_pb
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_sw_reset
Date: June 2018
KernelVersion: 4.19
Contact: Vadim Pasternak <vadimpmellanox.com>
@@ -110,11 +104,10 @@ Description: These files show the system reset cause, as following: power
The files are read only.
-What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/
- reset_comex_pwr_fail
- reset_from_comex
- reset_system
- reset_voltmon_upgrade_fail
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_comex_pwr_fail
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_from_comex
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_system
+What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/reset_voltmon_upgrade_fail
Date: November 2018
KernelVersion: 5.0
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup
index 0a54ed0d63c9..274df44d8b1b 100644
--- a/Documentation/ABI/testing/procfs-smaps_rollup
+++ b/Documentation/ABI/testing/procfs-smaps_rollup
@@ -3,18 +3,28 @@ Date: August 2017
Contact: Daniel Colascione <dancol@google.com>
Description:
This file provides pre-summed memory information for a
- process. The format is identical to /proc/pid/smaps,
+ process. The format is almost identical to /proc/pid/smaps,
except instead of an entry for each VMA in a process,
smaps_rollup has a single entry (tagged "[rollup]")
for which each field is the sum of the corresponding
fields from all the maps in /proc/pid/smaps.
- For more details, see the procfs man page.
+ Additionally, the fields Pss_Anon, Pss_File and Pss_Shmem
+ are not present in /proc/pid/smaps. These fields represent
+ the sum of the Pss field of each type (anon, file, shmem).
+ For more details, see Documentation/filesystems/proc.txt
+ and the procfs man page.
Typical output looks like this:
00100000-ff709000 ---p 00000000 00:00 0 [rollup]
+ Size: 1192 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
Rss: 884 kB
Pss: 385 kB
+ Pss_Anon: 301 kB
+ Pss_File: 80 kB
+ Pss_Shmem: 4 kB
Shared_Clean: 696 kB
Shared_Dirty: 0 kB
Private_Clean: 120 kB
diff --git a/Documentation/ABI/testing/pstore b/Documentation/ABI/testing/pstore
index 5fca9f5e10a3..d45209abdb1b 100644
--- a/Documentation/ABI/testing/pstore
+++ b/Documentation/ABI/testing/pstore
@@ -1,6 +1,6 @@
-Where: /sys/fs/pstore/... (or /dev/pstore/...)
+What: /sys/fs/pstore/... (or /dev/pstore/...)
Date: March 2011
-Kernel Version: 2.6.39
+KernelVersion: 2.6.39
Contact: tony.luck@intel.com
Description: Generic interface to platform dependent persistent storage.
diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
index 77f47ff5ee02..5bb793ec926c 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-format
@@ -1,6 +1,6 @@
-Where: /sys/bus/event_source/devices/<dev>/format
+What: /sys/bus/event_source/devices/<dev>/format
Date: January 2012
-Kernel Version: 3.3
+KernelVersion: 3.3
Contact: Jiri Olsa <jolsa@redhat.com>
Description:
Attribute group to describe the magic bits that go into
diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352 b/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352
index feb2e4a87075..4a251b7f11e4 100644
--- a/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352
+++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-hm6352
@@ -1,20 +1,20 @@
-Where: /sys/bus/i2c/devices/.../heading0_input
+What: /sys/bus/i2c/devices/.../heading0_input
Date: April 2010
-Kernel Version: 2.6.36?
+KernelVersion: 2.6.36?
Contact: alan.cox@intel.com
Description: Reports the current heading from the compass as a floating
point value in degrees.
-Where: /sys/bus/i2c/devices/.../power_state
+What: /sys/bus/i2c/devices/.../power_state
Date: April 2010
-Kernel Version: 2.6.36?
+KernelVersion: 2.6.36?
Contact: alan.cox@intel.com
Description: Sets the power state of the device. 0 sets the device into
sleep mode, 1 wakes it up.
-Where: /sys/bus/i2c/devices/.../calibration
+What: /sys/bus/i2c/devices/.../calibration
Date: April 2010
-Kernel Version: 2.6.36?
+KernelVersion: 2.6.36?
Contact: alan.cox@intel.com
Description: Sets the calibration on or off (1 = on, 0 = off). See the
chip data sheet.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08 b/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
index 0a1ca1487fa9..a133fd8d081a 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
+++ b/Documentation/ABI/testing/sysfs-bus-iio-distance-srf08
@@ -1,4 +1,4 @@
-What /sys/bus/iio/devices/iio:deviceX/sensor_sensitivity
+What: /sys/bus/iio/devices/iio:deviceX/sensor_sensitivity
Date: January 2017
KernelVersion: 4.11
Contact: linux-iio@vger.kernel.org
@@ -6,7 +6,7 @@ Description:
Show or set the gain boost of the amp, from 0-31 range.
default 31
-What /sys/bus/iio/devices/iio:deviceX/sensor_max_range
+What: /sys/bus/iio/devices/iio:deviceX/sensor_max_range
Date: January 2017
KernelVersion: 4.11
Contact: linux-iio@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
index 9a17ab5036a4..c59d95346341 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
+++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935
@@ -1,4 +1,4 @@
-What /sys/bus/iio/devices/iio:deviceX/in_proximity_input
+What: /sys/bus/iio/devices/iio:deviceX/in_proximity_input
Date: March 2014
KernelVersion: 3.15
Contact: Matt Ranostay <matt.ranostay@konsulko.com>
@@ -6,7 +6,7 @@ Description:
Get the current distance in meters of storm (1km steps)
1000-40000 = distance in meters
-What /sys/bus/iio/devices/iio:deviceX/sensor_sensitivity
+What: /sys/bus/iio/devices/iio:deviceX/sensor_sensitivity
Date: March 2014
KernelVersion: 3.15
Contact: Matt Ranostay <matt.ranostay@konsulko.com>
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
index 4b0318c99507..3c9a8c4a25eb 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
@@ -9,9 +9,9 @@ errors may be "seen" / reported by the link partner and not the
problematic endpoint itself (which may report all counters as 0 as it never
saw any problems).
-Where: /sys/bus/pci/devices/<dev>/aer_dev_correctable
+What: /sys/bus/pci/devices/<dev>/aer_dev_correctable
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: List of correctable errors seen and reported by this
PCI device using ERR_COR. Note that since multiple errors may
@@ -31,9 +31,9 @@ Header Log Overflow 0
TOTAL_ERR_COR 2
-------------------------------------------------------------------------
-Where: /sys/bus/pci/devices/<dev>/aer_dev_fatal
+What: /sys/bus/pci/devices/<dev>/aer_dev_fatal
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: List of uncorrectable fatal errors seen and reported by this
PCI device using ERR_FATAL. Note that since multiple errors may
@@ -62,9 +62,9 @@ TLP Prefix Blocked Error 0
TOTAL_ERR_FATAL 0
-------------------------------------------------------------------------
-Where: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal
+What: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: List of uncorrectable nonfatal errors seen and reported by this
PCI device using ERR_NONFATAL. Note that since multiple errors
@@ -103,20 +103,20 @@ collectors) that are AER capable. These indicate the number of error messages as
device, so these counters include them and are thus cumulative of all the error
messages on the PCI hierarchy originating at that root port.
-Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor
+What: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: Total number of ERR_COR messages reported to rootport.
-Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal
+What: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: Total number of ERR_FATAL messages reported to rootport.
-Where: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal
+What: /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal
Date: July 2018
-Kernel Version: 4.19.0
+KernelVersion: 4.19.0
Contact: linux-pci@vger.kernel.org, rajatja@google.com
Description: Total number of ERR_NONFATAL messages reported to rootport.
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
index 53d99edd1d75..92a94e1068c2 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-cciss
@@ -1,68 +1,68 @@
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/model
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/model
Date: March 2009
-Kernel Version: 2.6.30
+KernelVersion: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 model for logical drive
Y of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/rev
Date: March 2009
-Kernel Version: 2.6.30
+KernelVersion: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 revision for logical
drive Y of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/unique_id
Date: March 2009
-Kernel Version: 2.6.30
+KernelVersion: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 83 serial number for logical
drive Y of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/vendor
Date: March 2009
-Kernel Version: 2.6.30
+KernelVersion: 2.6.30
Contact: iss_storagedev@hp.com
Description: Displays the SCSI INQUIRY page 0 vendor for logical drive
Y of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/block:cciss!cXdY
Date: March 2009
-Kernel Version: 2.6.30
+KernelVersion: 2.6.30
Contact: iss_storagedev@hp.com
Description: A symbolic link to /sys/block/cciss!cXdY
-Where: /sys/bus/pci/devices/<dev>/ccissX/rescan
+What: /sys/bus/pci/devices/<dev>/ccissX/rescan
Date: August 2009
-Kernel Version: 2.6.31
+KernelVersion: 2.6.31
Contact: iss_storagedev@hp.com
Description: Kicks of a rescan of the controller to discover logical
drive topology changes.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/lunid
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/lunid
Date: August 2009
-Kernel Version: 2.6.31
+KernelVersion: 2.6.31
Contact: iss_storagedev@hp.com
Description: Displays the 8-byte LUN ID used to address logical
drive Y of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/raid_level
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/raid_level
Date: August 2009
-Kernel Version: 2.6.31
+KernelVersion: 2.6.31
Contact: iss_storagedev@hp.com
Description: Displays the RAID level of logical drive Y of
controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/cXdY/usage_count
+What: /sys/bus/pci/devices/<dev>/ccissX/cXdY/usage_count
Date: August 2009
-Kernel Version: 2.6.31
+KernelVersion: 2.6.31
Contact: iss_storagedev@hp.com
Description: Displays the usage count (number of opens) of logical drive Y
of controller X.
-Where: /sys/bus/pci/devices/<dev>/ccissX/resettable
+What: /sys/bus/pci/devices/<dev>/ccissX/resettable
Date: February 2011
-Kernel Version: 2.6.38
+KernelVersion: 2.6.38
Contact: iss_storagedev@hp.com
Description: Value of 1 indicates the controller can honor the reset_devices
kernel parameter. Value of 0 indicates reset_devices cannot be
@@ -71,9 +71,9 @@ Description: Value of 1 indicates the controller can honor the reset_devices
a dump device, as kdump requires resetting the device in order
to work reliably.
-Where: /sys/bus/pci/devices/<dev>/ccissX/transport_mode
+What: /sys/bus/pci/devices/<dev>/ccissX/transport_mode
Date: July 2011
-Kernel Version: 3.0
+KernelVersion: 3.0
Contact: iss_storagedev@hp.com
Description: Value of "simple" indicates that the controller has been placed
in "simple mode". Value of "performant" indicates that the
diff --git a/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
index 70d00dfa443d..9ade80f81f96 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
+++ b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
@@ -1,14 +1,14 @@
-Where: /sys/bus/usb/.../powered
+What: /sys/bus/usb/.../powered
Date: August 2008
-Kernel Version: 2.6.26
+KernelVersion: 2.6.26
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls whether the device's display will powered.
A value of 0 is off and a non-zero value is on.
-Where: /sys/bus/usb/.../mode_msb
-Where: /sys/bus/usb/.../mode_lsb
+What: /sys/bus/usb/.../mode_msb
+What: /sys/bus/usb/.../mode_lsb
Date: August 2008
-Kernel Version: 2.6.26
+KernelVersion: 2.6.26
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the devices display mode.
For a 6 character display the values are
@@ -16,24 +16,24 @@ Description: Controls the devices display mode.
for an 8 character display the values are
MSB 0x08; LSB 0xFF.
-Where: /sys/bus/usb/.../textmode
+What: /sys/bus/usb/.../textmode
Date: August 2008
-Kernel Version: 2.6.26
+KernelVersion: 2.6.26
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the way the device interprets its text buffer.
raw: each character controls its segment manually
hex: each character is between 0-15
ascii: each character is between '0'-'9' and 'A'-'F'.
-Where: /sys/bus/usb/.../text
+What: /sys/bus/usb/.../text
Date: August 2008
-Kernel Version: 2.6.26
+KernelVersion: 2.6.26
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: The text (or data) for the device to display
-Where: /sys/bus/usb/.../decimals
+What: /sys/bus/usb/.../decimals
Date: August 2008
-Kernel Version: 2.6.26
+KernelVersion: 2.6.26
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the decimal places on the device.
To set the nth decimal place, give this field
diff --git a/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533 b/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
index 77cf7ac949af..c0e0a9ae7b3d 100644
--- a/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
+++ b/Documentation/ABI/testing/sysfs-class-backlight-driver-lm3533
@@ -4,7 +4,7 @@ KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
Get the ALS output channel used as input in
- ALS-current-control mode (0, 1), where
+ ALS-current-control mode (0, 1), where:
0 - out_current0 (backlight 0)
1 - out_current1 (backlight 1)
@@ -28,7 +28,7 @@ Date: April 2012
KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
- Set the brightness-mapping mode (0, 1), where
+ Set the brightness-mapping mode (0, 1), where:
0 - exponential mode
1 - linear mode
@@ -38,7 +38,7 @@ Date: April 2012
KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
- Set the PWM-input control mask (5 bits), where
+ Set the PWM-input control mask (5 bits), where:
bit 5 - PWM-input enabled in Zone 4
bit 4 - PWM-input enabled in Zone 3
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index bbbabffc682a..7970e3713e70 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -1,6 +1,6 @@
-Note: Attributes that are shared between devices are stored in the directory
-pointed to by the symlink device/.
-Example: The real path of the attribute /sys/class/cxl/afu0.0s/irqs_max is
+Please note that attributes that are shared between devices are stored in
+the directory pointed to by the symlink device/.
+For example, the real path of the attribute /sys/class/cxl/afu0.0s/irqs_max is
/sys/class/cxl/afu0.0s/device/irqs_max, i.e. /sys/class/cxl/afu0.0/irqs_max.
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq b/Documentation/ABI/testing/sysfs-class-devfreq
index ee39acacf6f8..01196e19afca 100644
--- a/Documentation/ABI/testing/sysfs-class-devfreq
+++ b/Documentation/ABI/testing/sysfs-class-devfreq
@@ -47,7 +47,7 @@ Description:
What: /sys/class/devfreq/.../trans_stat
Date: October 2012
Contact: MyungJoo Ham <myungjoo.ham@samsung.com>
-Descrtiption:
+Description:
This ABI shows the statistics of devfreq behavior on a
specific device. It shows the time spent in each state and
the number of transitions between states.
diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-lm3533 b/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
index 620ebb3b9baa..e4c89b261546 100644
--- a/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
+++ b/Documentation/ABI/testing/sysfs-class-led-driver-lm3533
@@ -4,7 +4,7 @@ KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
Set the ALS output channel to use as input in
- ALS-current-control mode (1, 2), where
+ ALS-current-control mode (1, 2), where:
1 - out_current1
2 - out_current2
@@ -22,7 +22,7 @@ Date: April 2012
KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
- Set the pattern generator fall and rise times (0..7), where
+ Set the pattern generator fall and rise times (0..7), where:
0 - 2048 us
1 - 262 ms
@@ -45,7 +45,7 @@ Date: April 2012
KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
- Set the brightness-mapping mode (0, 1), where
+ Set the brightness-mapping mode (0, 1), where:
0 - exponential mode
1 - linear mode
@@ -55,7 +55,7 @@ Date: April 2012
KernelVersion: 3.5
Contact: Johan Hovold <jhovold@gmail.com>
Description:
- Set the PWM-input control mask (5 bits), where
+ Set the PWM-input control mask (5 bits), where:
bit 5 - PWM-input enabled in Zone 4
bit 4 - PWM-input enabled in Zone 3
diff --git a/Documentation/ABI/testing/sysfs-class-leds-gt683r b/Documentation/ABI/testing/sysfs-class-leds-gt683r
index e4fae6026e79..6adab27f646e 100644
--- a/Documentation/ABI/testing/sysfs-class-leds-gt683r
+++ b/Documentation/ABI/testing/sysfs-class-leds-gt683r
@@ -5,7 +5,7 @@ Contact: Janne Kanniainen <janne.kanniainen@gmail.com>
Description:
Set the mode of LEDs. You should notice that changing the mode
of one LED will update the mode of its two sibling devices as
- well.
+ well. Possible values are:
0 - normal
1 - audio
@@ -13,4 +13,4 @@ Description:
Normal: LEDs are fully on when enabled
Audio: LEDs brightness depends on sound level
- Breathing: LEDs brightness varies at human breathing rate \ No newline at end of file
+ Breathing: LEDs brightness varies at human breathing rate
diff --git a/Documentation/ABI/testing/sysfs-class-powercap b/Documentation/ABI/testing/sysfs-class-powercap
index db3b3ff70d84..f333a0ccc29b 100644
--- a/Documentation/ABI/testing/sysfs-class-powercap
+++ b/Documentation/ABI/testing/sysfs-class-powercap
@@ -147,6 +147,6 @@ What: /sys/class/powercap/.../<power zone>/enabled
Date: September 2013
KernelVersion: 3.13
Contact: linux-pm@vger.kernel.org
-Description
+Description:
This allows to enable/disable power capping at power zone level.
This applies to current power zone and its children.
diff --git a/Documentation/ABI/testing/sysfs-class-uwb_rc b/Documentation/ABI/testing/sysfs-class-uwb_rc
index 85f4875d16ac..a0578751c1e3 100644
--- a/Documentation/ABI/testing/sysfs-class-uwb_rc
+++ b/Documentation/ABI/testing/sysfs-class-uwb_rc
@@ -125,12 +125,6 @@ Description:
The EUI-48 of this device in colon separated hex
octets.
-What: /sys/class/uwb_rc/uwbN/<EUI-48>/BPST
-Date: July 2008
-KernelVersion: 2.6.27
-Contact: linux-usb@vger.kernel.org
-Description:
-
What: /sys/class/uwb_rc/uwbN/<EUI-48>/IEs
Date: July 2008
KernelVersion: 2.6.27
diff --git a/Documentation/ABI/testing/sysfs-driver-altera-cvp b/Documentation/ABI/testing/sysfs-driver-altera-cvp
index 8cde64a71edb..fbd8078fd7ad 100644
--- a/Documentation/ABI/testing/sysfs-driver-altera-cvp
+++ b/Documentation/ABI/testing/sysfs-driver-altera-cvp
@@ -1,6 +1,6 @@
What: /sys/bus/pci/drivers/altera-cvp/chkcfg
Date: May 2017
-Kernel Version: 4.13
+KernelVersion: 4.13
Contact: Anatolij Gustschin <agust@denx.de>
Description:
Contains either 1 or 0 and controls if configuration
diff --git a/Documentation/ABI/testing/sysfs-driver-hid b/Documentation/ABI/testing/sysfs-driver-hid
index 48942cacb0bf..a59533410871 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid
+++ b/Documentation/ABI/testing/sysfs-driver-hid
@@ -1,6 +1,6 @@
-What: For USB devices : /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/report_descriptor
- For BT devices : /sys/class/bluetooth/hci<addr>/<hid-bus>:<vendor-id>:<product-id>.<num>/report_descriptor
- Symlink : /sys/class/hidraw/hidraw<num>/device/report_descriptor
+What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/report_descriptor
+What: /sys/class/bluetooth/hci<addr>/<hid-bus>:<vendor-id>:<product-id>.<num>/report_descriptor
+What: /sys/class/hidraw/hidraw<num>/device/report_descriptor
Date: Jan 2011
KernelVersion: 2.0.39
Contact: Alan Ott <alan@signal11.us>
@@ -9,9 +9,9 @@ Description: When read, this file returns the device's raw binary HID
This file cannot be written.
Users: HIDAPI library (http://www.signal11.us/oss/hidapi)
-What: For USB devices : /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/country
- For BT devices : /sys/class/bluetooth/hci<addr>/<hid-bus>:<vendor-id>:<product-id>.<num>/country
- Symlink : /sys/class/hidraw/hidraw<num>/device/country
+What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/country
+What: /sys/class/bluetooth/hci<addr>/<hid-bus>:<vendor-id>:<product-id>.<num>/country
+What: /sys/class/hidraw/hidraw<num>/device/country
Date: February 2015
KernelVersion: 3.19
Contact: Olivier Gay <ogay@logitech.com>
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
index 3ca3971109bf..8f7982c70d72 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
+++ b/Documentation/ABI/testing/sysfs-driver-hid-roccat-kone
@@ -5,7 +5,7 @@ Description: It is possible to switch the dpi setting of the mouse with the
press of a button.
When read, this file returns the raw number of the actual dpi
setting reported by the mouse. This number has to be further
- processed to receive the real dpi value.
+ processed to receive the real dpi value:
VALUE DPI
1 800
diff --git a/Documentation/ABI/testing/sysfs-driver-ppi b/Documentation/ABI/testing/sysfs-driver-ppi
index 9921ef285899..1a56fc507689 100644
--- a/Documentation/ABI/testing/sysfs-driver-ppi
+++ b/Documentation/ABI/testing/sysfs-driver-ppi
@@ -1,6 +1,6 @@
What: /sys/class/tpm/tpmX/ppi/
Date: August 2012
-Kernel Version: 3.6
+KernelVersion: 3.6
Contact: xiaoyan.zhang@intel.com
Description:
This folder includes the attributes related with PPI (Physical
diff --git a/Documentation/ABI/testing/sysfs-driver-st b/Documentation/ABI/testing/sysfs-driver-st
index ba5d77008a85..88cab66fd77f 100644
--- a/Documentation/ABI/testing/sysfs-driver-st
+++ b/Documentation/ABI/testing/sysfs-driver-st
@@ -1,6 +1,6 @@
What: /sys/bus/scsi/drivers/st/debug_flag
Date: October 2015
-Kernel Version: ?.?
+KernelVersion: ?.?
Contact: shane.seymour@hpe.com
Description:
This file allows you to turn debug output from the st driver
diff --git a/Documentation/ABI/testing/sysfs-driver-wacom b/Documentation/ABI/testing/sysfs-driver-wacom
index 2aa5503ee200..afc48fc163b5 100644
--- a/Documentation/ABI/testing/sysfs-driver-wacom
+++ b/Documentation/ABI/testing/sysfs-driver-wacom
@@ -1,6 +1,6 @@
What: /sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/speed
Date: April 2010
-Kernel Version: 2.6.35
+KernelVersion: 2.6.35
Contact: linux-bluetooth@vger.kernel.org
Description:
The /sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/speed file
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 91822ce25831..dca326e0ee3e 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -243,3 +243,11 @@ Description:
- Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
- [h] means add/del hot file extension
- [c] means add/del cold file extension
+
+What: /sys/fs/f2fs/<disk>/unusable
+Date April 2019
+Contact: "Daniel Rosenberg" <drosen@google.com>
+Description:
+ If checkpoint=disable, it displays the number of blocks that are unusable.
+ If checkpoint=enable it displays the enumber of blocks that would be unusable
+ if checkpoint=disable were to be set.
diff --git a/Documentation/ABI/testing/sysfs-kernel-fscaps b/Documentation/ABI/testing/sysfs-kernel-fscaps
index 50a3033b5e15..bcff34665192 100644
--- a/Documentation/ABI/testing/sysfs-kernel-fscaps
+++ b/Documentation/ABI/testing/sysfs-kernel-fscaps
@@ -2,7 +2,7 @@ What: /sys/kernel/fscaps
Date: February 2011
KernelVersion: 2.6.38
Contact: Ludwig Nussel <ludwig.nussel@suse.de>
-Description
+Description:
Shows whether file system capabilities are honored
when executing a binary
diff --git a/Documentation/ABI/testing/sysfs-kernel-vmcoreinfo b/Documentation/ABI/testing/sysfs-kernel-vmcoreinfo
index 7bd81168e063..1f1087a5f075 100644
--- a/Documentation/ABI/testing/sysfs-kernel-vmcoreinfo
+++ b/Documentation/ABI/testing/sysfs-kernel-vmcoreinfo
@@ -4,7 +4,7 @@ KernelVersion: 2.6.24
Contact: Ken'ichi Ohmichi <oomichi@mxs.nes.nec.co.jp>
Kexec Mailing List <kexec@lists.infradead.org>
Vivek Goyal <vgoyal@redhat.com>
-Description
+Description:
Shows physical address and size of vmcoreinfo ELF note.
First value contains physical address of note in hex and
second value contains the size of note in hex. This ELF
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index a5c845338d6d..a9548de56ac9 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1146,6 +1146,11 @@ PAGE_SIZE multiple when read back.
otherwise, a value change in this file generates a file
modified event.
+ Note that all fields in this file are hierarchical and the
+ file modified event can be generated due to an event down the
+ hierarchy. For for the local events at the cgroup level see
+ memory.events.local.
+
low
The number of times the cgroup is reclaimed due to
high memory pressure even though its usage is under
@@ -1185,6 +1190,11 @@ PAGE_SIZE multiple when read back.
The number of processes belonging to this cgroup
killed by any kind of OOM killer.
+ memory.events.local
+ Similar to memory.events but the fields in the file are local
+ to the cgroup i.e. not hierarchical. The file modified event
+ generated on this file reflects only the local events.
+
memory.stat
A read-only flat-keyed file which exists on non-root cgroups.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1c433daef6b..099c5a4be95b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -805,12 +805,10 @@
tracking down these problems.
debug_pagealloc=
- [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
- parameter enables the feature at boot time. In
- default, it is disabled. We can avoid allocating huge
- chunk of memory for debug pagealloc if we don't enable
- it at boot time and the system will work mostly same
- with the kernel built without CONFIG_DEBUG_PAGEALLOC.
+ [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
+ enables the feature at boot time. By default, it is
+ disabled and the system will work mostly the same as a
+ kernel built without CONFIG_DEBUG_PAGEALLOC.
on: enable the feature
debugpat [X86] Enable PAT debugging
@@ -1670,6 +1668,15 @@
initrd= [BOOT] Specify the location of the initial ramdisk
+ init_on_alloc= [MM] Fill newly allocated pages and heap objects with
+ zeroes.
+ Format: 0 | 1
+ Default set by CONFIG_INIT_ON_ALLOC_DEFAULT_ON.
+
+ init_on_free= [MM] Fill freed pages and heap objects with zeroes.
+ Format: 0 | 1
+ Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
+
init_pkru= [x86] Specify the default memory protection keys rights
register contents for all processes. 0x55555554 by
default (disallow access to all but pkey 0). Can
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index c792774be59e..3e57d09246e6 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -86,6 +86,8 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Neoverse-N1 | #1349291 | N/A |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | MMU-500 | #841119,826419 | N/A |
+----------------+-----------------+-----------------+-----------------------------+
+----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 824f24ccf401..08af5caf036d 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -54,7 +54,7 @@ The Linux kernel provides more basic utility functions.
Bit Operations
--------------
-.. kernel-doc:: arch/x86/include/asm/bitops.h
+.. kernel-doc:: include/asm-generic/bitops-instrumented.h
:internal:
Bitmap Operations
diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst
index e6f51260ff32..3621cd5e1eef 100644
--- a/Documentation/dev-tools/kmemleak.rst
+++ b/Documentation/dev-tools/kmemleak.rst
@@ -2,8 +2,8 @@ Kernel Memory Leak Detector
===========================
Kmemleak provides a way of detecting possible kernel memory leaks in a
-way similar to a tracing garbage collector
-(https://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+way similar to a `tracing garbage collector
+<https://en.wikipedia.org/wiki/Tracing_garbage_collection>`_,
with the difference that the orphan objects are not freed but only
reported via /sys/kernel/debug/kmemleak. A similar method is used by the
Valgrind tool (``memcheck --leak-check``) to detect the memory leaks in
@@ -15,10 +15,13 @@ Usage
CONFIG_DEBUG_KMEMLEAK in "Kernel hacking" has to be enabled. A kernel
thread scans the memory every 10 minutes (by default) and prints the
-number of new unreferenced objects found. To display the details of all
-the possible memory leaks::
+number of new unreferenced objects found. If the ``debugfs`` isn't already
+mounted, mount with::
# mount -t debugfs nodev /sys/kernel/debug/
+
+To display the details of all the possible scanned memory leaks::
+
# cat /sys/kernel/debug/kmemleak
To trigger an intermediate memory scan::
@@ -72,6 +75,9 @@ If CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF are enabled, the kmemleak is
disabled by default. Passing ``kmemleak=on`` on the kernel command
line enables the function.
+If you are getting errors like "Error while writing to stdout" or "write_loop:
+Invalid argument", make sure kmemleak is properly enabled.
+
Basic Algorithm
---------------
@@ -218,3 +224,37 @@ the pointer is calculated by other methods than the usual container_of
macro or the pointer is stored in a location not scanned by kmemleak.
Page allocations and ioremap are not tracked.
+
+Testing with kmemleak-test
+--------------------------
+
+To check if you have all set up to use kmemleak, you can use the kmemleak-test
+module, a module that deliberately leaks memory. Set CONFIG_DEBUG_KMEMLEAK_TEST
+as module (it can't be used as bult-in) and boot the kernel with kmemleak
+enabled. Load the module and perform a scan with::
+
+ # modprobe kmemleak-test
+ # echo scan > /sys/kernel/debug/kmemleak
+
+Note that the you may not get results instantly or on the first scanning. When
+kmemleak gets results, it'll log ``kmemleak: <count of leaks> new suspected
+memory leaks``. Then read the file to see then::
+
+ # cat /sys/kernel/debug/kmemleak
+ unreferenced object 0xffff89862ca702e8 (size 32):
+ comm "modprobe", pid 2088, jiffies 4294680594 (age 375.486s)
+ hex dump (first 32 bytes):
+ 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk
+ 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkkkkkkkkkk.
+ backtrace:
+ [<00000000e0a73ec7>] 0xffffffffc01d2036
+ [<000000000c5d2a46>] do_one_initcall+0x41/0x1df
+ [<0000000046db7e0a>] do_init_module+0x55/0x200
+ [<00000000542b9814>] load_module+0x203c/0x2480
+ [<00000000c2850256>] __do_sys_finit_module+0xba/0xe0
+ [<000000006564e7ef>] do_syscall_64+0x43/0x110
+ [<000000007c873fa6>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
+ ...
+
+Removing the module with ``rmmod kmemleak_test`` should also trigger some
+kmemleak results.
diff --git a/Documentation/driver-api/gpio/driver.rst b/Documentation/driver-api/gpio/driver.rst
index 4af9aae724f0..349f2dc33029 100644
--- a/Documentation/driver-api/gpio/driver.rst
+++ b/Documentation/driver-api/gpio/driver.rst
@@ -399,7 +399,7 @@ symbol:
will pass the struct gpio_chip* for the chip to all IRQ callbacks, so the
callbacks need to embed the gpio_chip in its state container and obtain a
pointer to the container using container_of().
- (See Documentation/driver-model/design-patterns.txt)
+ (See Documentation/driver-model/design-patterns.rst)
- gpiochip_irqchip_add_nested(): adds a nested cascaded irqchip to a gpiochip,
as discussed above regarding different types of cascaded irqchips. The
diff --git a/Documentation/driver-model/binding.txt b/Documentation/driver-model/binding.rst
index abfc8e290d53..7ea1d7a41e1d 100644
--- a/Documentation/driver-model/binding.txt
+++ b/Documentation/driver-model/binding.rst
@@ -1,5 +1,6 @@
-
+==============
Driver Binding
+==============
Driver binding is the process of associating a device with a device
driver that can control it. Bus drivers have typically handled this
@@ -25,7 +26,7 @@ device_register
When a new device is added, the bus's list of drivers is iterated over
to find one that supports it. In order to determine that, the device
ID of the device must match one of the device IDs that the driver
-supports. The format and semantics for comparing IDs is bus-specific.
+supports. The format and semantics for comparing IDs is bus-specific.
Instead of trying to derive a complex state machine and matching
algorithm, it is up to the bus driver to provide a callback to compare
a device against the IDs of a driver. The bus returns 1 if a match was
@@ -36,14 +37,14 @@ int match(struct device * dev, struct device_driver * drv);
If a match is found, the device's driver field is set to the driver
and the driver's probe callback is called. This gives the driver a
chance to verify that it really does support the hardware, and that
-it's in a working state.
+it's in a working state.
Device Class
~~~~~~~~~~~~
Upon the successful completion of probe, the device is registered with
the class to which it belongs. Device drivers belong to one and only one
-class, and that is set in the driver's devclass field.
+class, and that is set in the driver's devclass field.
devclass_add_device is called to enumerate the device within the class
and actually register it with the class, which happens with the
class's register_dev callback.
@@ -53,7 +54,7 @@ Driver
~~~~~~
When a driver is attached to a device, the device is inserted into the
-driver's list of devices.
+driver's list of devices.
sysfs
@@ -67,18 +68,18 @@ to the device's directory in the physical hierarchy.
A directory for the device is created in the class's directory. A
symlink is created in that directory that points to the device's
-physical location in the sysfs tree.
+physical location in the sysfs tree.
A symlink can be created (though this isn't done yet) in the device's
physical directory to either its class directory, or the class's
top-level directory. One can also be created to point to its driver's
-directory also.
+directory also.
driver_register
~~~~~~~~~~~~~~~
-The process is almost identical for when a new driver is added.
+The process is almost identical for when a new driver is added.
The bus's list of devices is iterated over to find a match. Devices
that already have a driver are skipped. All the devices are iterated
over, to bind as many devices as possible to the driver.
@@ -94,5 +95,4 @@ of the driver is decremented. All symlinks between the two are removed.
When a driver is removed, the list of devices that it supports is
iterated over, and the driver's remove callback is called for each
-one. The device is removed from that list and the symlinks removed.
-
+one. The device is removed from that list and the symlinks removed.
diff --git a/Documentation/driver-model/bus.txt b/Documentation/driver-model/bus.rst
index c247b488a567..016b15a6e8ea 100644
--- a/Documentation/driver-model/bus.txt
+++ b/Documentation/driver-model/bus.rst
@@ -1,5 +1,6 @@
-
-Bus Types
+=========
+Bus Types
+=========
Definition
~~~~~~~~~~
@@ -13,12 +14,12 @@ Declaration
Each bus type in the kernel (PCI, USB, etc) should declare one static
object of this type. They must initialize the name field, and may
-optionally initialize the match callback.
+optionally initialize the match callback::
-struct bus_type pci_bus_type = {
- .name = "pci",
- .match = pci_bus_match,
-};
+ struct bus_type pci_bus_type = {
+ .name = "pci",
+ .match = pci_bus_match,
+ };
The structure should be exported to drivers in a header file:
@@ -30,8 +31,8 @@ Registration
When a bus driver is initialized, it calls bus_register. This
initializes the rest of the fields in the bus object and inserts it
-into a global list of bus types. Once the bus object is registered,
-the fields in it are usable by the bus driver.
+into a global list of bus types. Once the bus object is registered,
+the fields in it are usable by the bus driver.
Callbacks
@@ -43,17 +44,17 @@ match(): Attaching Drivers to Devices
The format of device ID structures and the semantics for comparing
them are inherently bus-specific. Drivers typically declare an array
of device IDs of devices they support that reside in a bus-specific
-driver structure.
+driver structure.
The purpose of the match callback is to give the bus an opportunity to
determine if a particular driver supports a particular device by
comparing the device IDs the driver supports with the device ID of a
particular device, without sacrificing bus-specific functionality or
-type-safety.
+type-safety.
When a driver is registered with the bus, the bus's list of devices is
iterated over, and the match callback is called for each device that
-does not have a driver associated with it.
+does not have a driver associated with it.
@@ -64,22 +65,23 @@ The lists of devices and drivers are intended to replace the local
lists that many buses keep. They are lists of struct devices and
struct device_drivers, respectively. Bus drivers are free to use the
lists as they please, but conversion to the bus-specific type may be
-necessary.
+necessary.
-The LDM core provides helper functions for iterating over each list.
+The LDM core provides helper functions for iterating over each list::
-int bus_for_each_dev(struct bus_type * bus, struct device * start, void * data,
- int (*fn)(struct device *, void *));
+ int bus_for_each_dev(struct bus_type * bus, struct device * start,
+ void * data,
+ int (*fn)(struct device *, void *));
-int bus_for_each_drv(struct bus_type * bus, struct device_driver * start,
- void * data, int (*fn)(struct device_driver *, void *));
+ int bus_for_each_drv(struct bus_type * bus, struct device_driver * start,
+ void * data, int (*fn)(struct device_driver *, void *));
These helpers iterate over the respective list, and call the callback
for each device or driver in the list. All list accesses are
synchronized by taking the bus's lock (read currently). The reference
count on each object in the list is incremented before the callback is
called; it is decremented after the next object has been obtained. The
-lock is not held when calling the callback.
+lock is not held when calling the callback.
sysfs
@@ -87,14 +89,14 @@ sysfs
There is a top-level directory named 'bus'.
Each bus gets a directory in the bus directory, along with two default
-directories:
+directories::
/sys/bus/pci/
|-- devices
`-- drivers
Drivers registered with the bus get a directory in the bus's drivers
-directory:
+directory::
/sys/bus/pci/
|-- devices
@@ -106,7 +108,7 @@ directory:
Each device that is discovered on a bus of that type gets a symlink in
the bus's devices directory to the device's directory in the physical
-hierarchy:
+hierarchy::
/sys/bus/pci/
|-- devices
@@ -118,26 +120,27 @@ hierarchy:
Exporting Attributes
~~~~~~~~~~~~~~~~~~~~
-struct bus_attribute {
+
+::
+
+ struct bus_attribute {
struct attribute attr;
ssize_t (*show)(struct bus_type *, char * buf);
ssize_t (*store)(struct bus_type *, const char * buf, size_t count);
-};
+ };
Bus drivers can export attributes using the BUS_ATTR_RW macro that works
similarly to the DEVICE_ATTR_RW macro for devices. For example, a
-definition like this:
+definition like this::
-static BUS_ATTR_RW(debug);
+ static BUS_ATTR_RW(debug);
-is equivalent to declaring:
+is equivalent to declaring::
-static bus_attribute bus_attr_debug;
+ static bus_attribute bus_attr_debug;
This can then be used to add and remove the attribute from the bus's
-sysfs directory using:
-
-int bus_create_file(struct bus_type *, struct bus_attribute *);
-void bus_remove_file(struct bus_type *, struct bus_attribute *);
-
+sysfs directory using::
+ int bus_create_file(struct bus_type *, struct bus_attribute *);
+ void bus_remove_file(struct bus_type *, struct bus_attribute *);
diff --git a/Documentation/driver-model/class.txt b/Documentation/driver-model/class.rst
index 1fefc480a80b..fff55b80e86a 100644
--- a/Documentation/driver-model/class.txt
+++ b/Documentation/driver-model/class.rst
@@ -1,6 +1,6 @@
-
+==============
Device Classes
-
+==============
Introduction
~~~~~~~~~~~~
@@ -13,37 +13,37 @@ device. The following device classes have been identified:
Each device class defines a set of semantics and a programming interface
that devices of that class adhere to. Device drivers are the
implementation of that programming interface for a particular device on
-a particular bus.
+a particular bus.
Device classes are agnostic with respect to what bus a device resides
-on.
+on.
Programming Interface
~~~~~~~~~~~~~~~~~~~~~
-The device class structure looks like:
+The device class structure looks like::
-typedef int (*devclass_add)(struct device *);
-typedef void (*devclass_remove)(struct device *);
+ typedef int (*devclass_add)(struct device *);
+ typedef void (*devclass_remove)(struct device *);
See the kerneldoc for the struct class.
-A typical device class definition would look like:
+A typical device class definition would look like::
-struct device_class input_devclass = {
+ struct device_class input_devclass = {
.name = "input",
.add_device = input_add_device,
.remove_device = input_remove_device,
-};
+ };
Each device class structure should be exported in a header file so it
can be used by drivers, extensions and interfaces.
-Device classes are registered and unregistered with the core using:
+Device classes are registered and unregistered with the core using::
-int devclass_register(struct device_class * cls);
-void devclass_unregister(struct device_class * cls);
+ int devclass_register(struct device_class * cls);
+ void devclass_unregister(struct device_class * cls);
Devices
@@ -52,16 +52,16 @@ As devices are bound to drivers, they are added to the device class
that the driver belongs to. Before the driver model core, this would
typically happen during the driver's probe() callback, once the device
has been initialized. It now happens after the probe() callback
-finishes from the core.
+finishes from the core.
The device is enumerated in the class. Each time a device is added to
the class, the class's devnum field is incremented and assigned to the
device. The field is never decremented, so if the device is removed
from the class and re-added, it will receive a different enumerated
-value.
+value.
The class is allowed to create a class-specific structure for the
-device and store it in the device's class_data pointer.
+device and store it in the device's class_data pointer.
There is no list of devices in the device class. Each driver has a
list of devices that it supports. The device class has a list of
@@ -73,15 +73,15 @@ Device Drivers
~~~~~~~~~~~~~~
Device drivers are added to device classes when they are registered
with the core. A driver specifies the class it belongs to by setting
-the struct device_driver::devclass field.
+the struct device_driver::devclass field.
sysfs directory structure
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-There is a top-level sysfs directory named 'class'.
+There is a top-level sysfs directory named 'class'.
Each class gets a directory in the class directory, along with two
-default subdirectories:
+default subdirectories::
class/
`-- input
@@ -89,8 +89,8 @@ default subdirectories:
`-- drivers
-Drivers registered with the class get a symlink in the drivers/ directory
-that points to the driver's directory (under its bus directory):
+Drivers registered with the class get a symlink in the drivers/ directory
+that points to the driver's directory (under its bus directory)::
class/
`-- input
@@ -99,8 +99,8 @@ that points to the driver's directory (under its bus directory):
`-- usb:usb_mouse -> ../../../bus/drivers/usb_mouse/
-Each device gets a symlink in the devices/ directory that points to the
-device's directory in the physical hierarchy:
+Each device gets a symlink in the devices/ directory that points to the
+device's directory in the physical hierarchy::
class/
`-- input
@@ -111,37 +111,39 @@ device's directory in the physical hierarchy:
Exporting Attributes
~~~~~~~~~~~~~~~~~~~~
-struct devclass_attribute {
+
+::
+
+ struct devclass_attribute {
struct attribute attr;
ssize_t (*show)(struct device_class *, char * buf, size_t count, loff_t off);
ssize_t (*store)(struct device_class *, const char * buf, size_t count, loff_t off);
-};
+ };
Class drivers can export attributes using the DEVCLASS_ATTR macro that works
-similarly to the DEVICE_ATTR macro for devices. For example, a definition
-like this:
+similarly to the DEVICE_ATTR macro for devices. For example, a definition
+like this::
-static DEVCLASS_ATTR(debug,0644,show_debug,store_debug);
+ static DEVCLASS_ATTR(debug,0644,show_debug,store_debug);
-is equivalent to declaring:
+is equivalent to declaring::
-static devclass_attribute devclass_attr_debug;
+ static devclass_attribute devclass_attr_debug;
The bus driver can add and remove the attribute from the class's
-sysfs directory using:
+sysfs directory using::
-int devclass_create_file(struct device_class *, struct devclass_attribute *);
-void devclass_remove_file(struct device_class *, struct devclass_attribute *);
+ int devclass_create_file(struct device_class *, struct devclass_attribute *);
+ void devclass_remove_file(struct device_class *, struct devclass_attribute *);
In the example above, the file will be named 'debug' in placed in the
-class's directory in sysfs.
+class's directory in sysfs.
Interfaces
~~~~~~~~~~
There may exist multiple mechanisms for accessing the same device of a
-particular class type. Device interfaces describe these mechanisms.
+particular class type. Device interfaces describe these mechanisms.
When a device is added to a device class, the core attempts to add it
to every interface that is registered with the device class.
-
diff --git a/Documentation/driver-model/design-patterns.txt b/Documentation/driver-model/design-patterns.rst
index ba7b2df64904..41eb8f41f7dd 100644
--- a/Documentation/driver-model/design-patterns.txt
+++ b/Documentation/driver-model/design-patterns.rst
@@ -1,6 +1,6 @@
-
+=============================
Device Driver Design Patterns
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+=============================
This document describes a few common design patterns found in device drivers.
It is likely that subsystem maintainers will ask driver developers to
@@ -19,23 +19,23 @@ that the device the driver binds to will appear in several instances. This
means that the probe() function and all callbacks need to be reentrant.
The most common way to achieve this is to use the state container design
-pattern. It usually has this form:
+pattern. It usually has this form::
-struct foo {
- spinlock_t lock; /* Example member */
- (...)
-};
+ struct foo {
+ spinlock_t lock; /* Example member */
+ (...)
+ };
-static int foo_probe(...)
-{
- struct foo *foo;
+ static int foo_probe(...)
+ {
+ struct foo *foo;
- foo = devm_kzalloc(dev, sizeof(*foo), GFP_KERNEL);
- if (!foo)
- return -ENOMEM;
- spin_lock_init(&foo->lock);
- (...)
-}
+ foo = devm_kzalloc(dev, sizeof(*foo), GFP_KERNEL);
+ if (!foo)
+ return -ENOMEM;
+ spin_lock_init(&foo->lock);
+ (...)
+ }
This will create an instance of struct foo in memory every time probe() is
called. This is our state container for this instance of the device driver.
@@ -43,21 +43,21 @@ Of course it is then necessary to always pass this instance of the
state around to all functions that need access to the state and its members.
For example, if the driver is registering an interrupt handler, you would
-pass around a pointer to struct foo like this:
+pass around a pointer to struct foo like this::
-static irqreturn_t foo_handler(int irq, void *arg)
-{
- struct foo *foo = arg;
- (...)
-}
+ static irqreturn_t foo_handler(int irq, void *arg)
+ {
+ struct foo *foo = arg;
+ (...)
+ }
-static int foo_probe(...)
-{
- struct foo *foo;
+ static int foo_probe(...)
+ {
+ struct foo *foo;
- (...)
- ret = request_irq(irq, foo_handler, 0, "foo", foo);
-}
+ (...)
+ ret = request_irq(irq, foo_handler, 0, "foo", foo);
+ }
This way you always get a pointer back to the correct instance of foo in
your interrupt handler.
@@ -66,38 +66,38 @@ your interrupt handler.
2. container_of()
~~~~~~~~~~~~~~~~~
-Continuing on the above example we add an offloaded work:
+Continuing on the above example we add an offloaded work::
-struct foo {
- spinlock_t lock;
- struct workqueue_struct *wq;
- struct work_struct offload;
- (...)
-};
+ struct foo {
+ spinlock_t lock;
+ struct workqueue_struct *wq;
+ struct work_struct offload;
+ (...)
+ };
-static void foo_work(struct work_struct *work)
-{
- struct foo *foo = container_of(work, struct foo, offload);
+ static void foo_work(struct work_struct *work)
+ {
+ struct foo *foo = container_of(work, struct foo, offload);
- (...)
-}
+ (...)
+ }
-static irqreturn_t foo_handler(int irq, void *arg)
-{
- struct foo *foo = arg;
+ static irqreturn_t foo_handler(int irq, void *arg)
+ {
+ struct foo *foo = arg;
- queue_work(foo->wq, &foo->offload);
- (...)
-}
+ queue_work(foo->wq, &foo->offload);
+ (...)
+ }
-static int foo_probe(...)
-{
- struct foo *foo;
+ static int foo_probe(...)
+ {
+ struct foo *foo;
- foo->wq = create_singlethread_workqueue("foo-wq");
- INIT_WORK(&foo->offload, foo_work);
- (...)
-}
+ foo->wq = create_singlethread_workqueue("foo-wq");
+ INIT_WORK(&foo->offload, foo_work);
+ (...)
+ }
The design pattern is the same for an hrtimer or something similar that will
return a single argument which is a pointer to a struct member in the
diff --git a/Documentation/driver-model/device.txt b/Documentation/driver-model/device.rst
index 2403eb856187..2b868d49d349 100644
--- a/Documentation/driver-model/device.txt
+++ b/Documentation/driver-model/device.rst
@@ -1,6 +1,6 @@
-
+==========================
The Basic Device Structure
-~~~~~~~~~~~~~~~~~~~~~~~~~~
+==========================
See the kerneldoc for the struct device.
@@ -8,9 +8,9 @@ See the kerneldoc for the struct device.
Programming Interface
~~~~~~~~~~~~~~~~~~~~~
The bus driver that discovers the device uses this to register the
-device with the core:
+device with the core::
-int device_register(struct device * dev);
+ int device_register(struct device * dev);
The bus should initialize the following fields:
@@ -20,30 +20,33 @@ The bus should initialize the following fields:
- bus
A device is removed from the core when its reference count goes to
-0. The reference count can be adjusted using:
+0. The reference count can be adjusted using::
-struct device * get_device(struct device * dev);
-void put_device(struct device * dev);
+ struct device * get_device(struct device * dev);
+ void put_device(struct device * dev);
get_device() will return a pointer to the struct device passed to it
if the reference is not already 0 (if it's in the process of being
removed already).
-A driver can access the lock in the device structure using:
+A driver can access the lock in the device structure using::
-void lock_device(struct device * dev);
-void unlock_device(struct device * dev);
+ void lock_device(struct device * dev);
+ void unlock_device(struct device * dev);
Attributes
~~~~~~~~~~
-struct device_attribute {
+
+::
+
+ struct device_attribute {
struct attribute attr;
ssize_t (*show)(struct device *dev, struct device_attribute *attr,
char *buf);
ssize_t (*store)(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count);
-};
+ };
Attributes of devices can be exported by a device driver through sysfs.
@@ -54,39 +57,39 @@ As explained in Documentation/kobject.txt, device attributes must be
created before the KOBJ_ADD uevent is generated. The only way to realize
that is by defining an attribute group.
-Attributes are declared using a macro called DEVICE_ATTR:
+Attributes are declared using a macro called DEVICE_ATTR::
-#define DEVICE_ATTR(name,mode,show,store)
+ #define DEVICE_ATTR(name,mode,show,store)
-Example:
+Example:::
-static DEVICE_ATTR(type, 0444, show_type, NULL);
-static DEVICE_ATTR(power, 0644, show_power, store_power);
+ static DEVICE_ATTR(type, 0444, show_type, NULL);
+ static DEVICE_ATTR(power, 0644, show_power, store_power);
This declares two structures of type struct device_attribute with respective
names 'dev_attr_type' and 'dev_attr_power'. These two attributes can be
-organized as follows into a group:
+organized as follows into a group::
-static struct attribute *dev_attrs[] = {
+ static struct attribute *dev_attrs[] = {
&dev_attr_type.attr,
&dev_attr_power.attr,
NULL,
-};
+ };
-static struct attribute_group dev_attr_group = {
+ static struct attribute_group dev_attr_group = {
.attrs = dev_attrs,
-};
+ };
-static const struct attribute_group *dev_attr_groups[] = {
+ static const struct attribute_group *dev_attr_groups[] = {
&dev_attr_group,
NULL,
-};
+ };
This array of groups can then be associated with a device by setting the
-group pointer in struct device before device_register() is invoked:
+group pointer in struct device before device_register() is invoked::
- dev->groups = dev_attr_groups;
- device_register(dev);
+ dev->groups = dev_attr_groups;
+ device_register(dev);
The device_register() function will use the 'groups' pointer to create the
device attributes and the device_unregister() function will use this pointer
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.rst
index 69c7fa7f616c..4ac99122b5f1 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.rst
@@ -1,3 +1,4 @@
+================================
Devres - Managed Device Resource
================================
@@ -5,17 +6,18 @@ Tejun Heo <teheo@suse.de>
First draft 10 January 2007
+.. contents
-1. Intro : Huh? Devres?
-2. Devres : Devres in a nutshell
-3. Devres Group : Group devres'es and release them together
-4. Details : Life time rules, calling context, ...
-5. Overhead : How much do we have to pay for this?
-6. List of managed interfaces : Currently implemented managed interfaces
+ 1. Intro : Huh? Devres?
+ 2. Devres : Devres in a nutshell
+ 3. Devres Group : Group devres'es and release them together
+ 4. Details : Life time rules, calling context, ...
+ 5. Overhead : How much do we have to pay for this?
+ 6. List of managed interfaces: Currently implemented managed interfaces
- 1. Intro
- --------
+1. Intro
+--------
devres came up while trying to convert libata to use iomap. Each
iomapped address should be kept and unmapped on driver detach. For
@@ -42,8 +44,8 @@ would leak resources or even cause oops when failure occurs. iomap
adds more to this mix. So do msi and msix.
- 2. Devres
- ---------
+2. Devres
+---------
devres is basically linked list of arbitrarily sized memory areas
associated with a struct device. Each devres entry is associated with
@@ -58,7 +60,7 @@ using dma_alloc_coherent(). The managed version is called
dmam_alloc_coherent(). It is identical to dma_alloc_coherent() except
for the DMA memory allocated using it is managed and will be
automatically released on driver detach. Implementation looks like
-the following.
+the following::
struct dma_devres {
size_t size;
@@ -98,7 +100,7 @@ If a driver uses dmam_alloc_coherent(), the area is guaranteed to be
freed whether initialization fails half-way or the device gets
detached. If most resources are acquired using managed interface, a
driver can have much simpler init and exit code. Init path basically
-looks like the following.
+looks like the following::
my_init_one()
{
@@ -119,7 +121,7 @@ looks like the following.
return register_to_upper_layer(d);
}
-And exit path,
+And exit path::
my_remove_one()
{
@@ -140,13 +142,13 @@ on you. In some cases this may mean introducing checks that were not
necessary before moving to the managed devm_* calls.
- 3. Devres group
- ---------------
+3. Devres group
+---------------
Devres entries can be grouped using devres group. When a group is
released, all contained normal devres entries and properly nested
groups are released. One usage is to rollback series of acquired
-resources on failure. For example,
+resources on failure. For example::
if (!devres_open_group(dev, NULL, GFP_KERNEL))
return -ENOMEM;
@@ -172,7 +174,7 @@ like above are usually useful in midlayer driver (e.g. libata core
layer) where interface function shouldn't have side effect on failure.
For LLDs, just returning error code suffices in most cases.
-Each group is identified by void *id. It can either be explicitly
+Each group is identified by `void *id`. It can either be explicitly
specified by @id argument to devres_open_group() or automatically
created by passing NULL as @id as in the above example. In both
cases, devres_open_group() returns the group's id. The returned id
@@ -180,7 +182,7 @@ can be passed to other devres functions to select the target group.
If NULL is given to those functions, the latest open group is
selected.
-For example, you can do something like the following.
+For example, you can do something like the following::
int my_midlayer_create_something()
{
@@ -199,8 +201,8 @@ For example, you can do something like the following.
}
- 4. Details
- ----------
+4. Details
+----------
Lifetime of a devres entry begins on devres allocation and finishes
when it is released or destroyed (removed and freed) - no reference
@@ -220,8 +222,8 @@ All devres interface functions can be called without context if the
right gfp mask is given.
- 5. Overhead
- -----------
+5. Overhead
+-----------
Each devres bookkeeping info is allocated together with requested data
area. With debug option turned off, bookkeeping info occupies 16
@@ -237,8 +239,8 @@ and 400 bytes on 32bit machine after naive conversion (we can
certainly invest a bit more effort into libata core layer).
- 6. List of managed interfaces
- -----------------------------
+6. List of managed interfaces
+-----------------------------
CLOCK
devm_clk_get()
diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.rst
index d661e6f7e6a0..11d281506a04 100644
--- a/Documentation/driver-model/driver.txt
+++ b/Documentation/driver-model/driver.rst
@@ -1,5 +1,6 @@
-
+==============
Device Drivers
+==============
See the kerneldoc for the struct device_driver.
@@ -26,50 +27,50 @@ Declaration
As stated above, struct device_driver objects are statically
allocated. Below is an example declaration of the eepro100
driver. This declaration is hypothetical only; it relies on the driver
-being converted completely to the new model.
-
-static struct device_driver eepro100_driver = {
- .name = "eepro100",
- .bus = &pci_bus_type,
-
- .probe = eepro100_probe,
- .remove = eepro100_remove,
- .suspend = eepro100_suspend,
- .resume = eepro100_resume,
-};
+being converted completely to the new model::
+
+ static struct device_driver eepro100_driver = {
+ .name = "eepro100",
+ .bus = &pci_bus_type,
+
+ .probe = eepro100_probe,
+ .remove = eepro100_remove,
+ .suspend = eepro100_suspend,
+ .resume = eepro100_resume,
+ };
Most drivers will not be able to be converted completely to the new
model because the bus they belong to has a bus-specific structure with
-bus-specific fields that cannot be generalized.
+bus-specific fields that cannot be generalized.
The most common example of this are device ID structures. A driver
typically defines an array of device IDs that it supports. The format
of these structures and the semantics for comparing device IDs are
completely bus-specific. Defining them as bus-specific entities would
-sacrifice type-safety, so we keep bus-specific structures around.
+sacrifice type-safety, so we keep bus-specific structures around.
Bus-specific drivers should include a generic struct device_driver in
-the definition of the bus-specific driver. Like this:
+the definition of the bus-specific driver. Like this::
-struct pci_driver {
- const struct pci_device_id *id_table;
- struct device_driver driver;
-};
+ struct pci_driver {
+ const struct pci_device_id *id_table;
+ struct device_driver driver;
+ };
A definition that included bus-specific fields would look like
-(using the eepro100 driver again):
+(using the eepro100 driver again)::
-static struct pci_driver eepro100_driver = {
- .id_table = eepro100_pci_tbl,
- .driver = {
+ static struct pci_driver eepro100_driver = {
+ .id_table = eepro100_pci_tbl,
+ .driver = {
.name = "eepro100",
.bus = &pci_bus_type,
.probe = eepro100_probe,
.remove = eepro100_remove,
.suspend = eepro100_suspend,
.resume = eepro100_resume,
- },
-};
+ },
+ };
Some may find the syntax of embedded struct initialization awkward or
even a bit ugly. So far, it's the best way we've found to do what we want...
@@ -77,12 +78,14 @@ even a bit ugly. So far, it's the best way we've found to do what we want...
Registration
~~~~~~~~~~~~
-int driver_register(struct device_driver * drv);
+::
+
+ int driver_register(struct device_driver *drv);
The driver registers the structure on startup. For drivers that have
no bus-specific fields (i.e. don't have a bus-specific driver
structure), they would use driver_register and pass a pointer to their
-struct device_driver object.
+struct device_driver object.
Most drivers, however, will have a bus-specific structure and will
need to register with the bus using something like pci_driver_register.
@@ -101,7 +104,7 @@ By defining wrapper functions, the transition to the new model can be
made easier. Drivers can ignore the generic structure altogether and
let the bus wrapper fill in the fields. For the callbacks, the bus can
define generic callbacks that forward the call to the bus-specific
-callbacks of the drivers.
+callbacks of the drivers.
This solution is intended to be only temporary. In order to get class
information in the driver, the drivers must be modified anyway. Since
@@ -113,16 +116,16 @@ Access
~~~~~~
Once the object has been registered, it may access the common fields of
-the object, like the lock and the list of devices.
+the object, like the lock and the list of devices::
-int driver_for_each_dev(struct device_driver * drv, void * data,
- int (*callback)(struct device * dev, void * data));
+ int driver_for_each_dev(struct device_driver *drv, void *data,
+ int (*callback)(struct device *dev, void *data));
The devices field is a list of all the devices that have been bound to
the driver. The LDM core provides a helper function to operate on all
the devices a driver controls. This helper locks the driver on each
node access, and does proper reference counting on each device as it
-accesses it.
+accesses it.
sysfs
@@ -142,7 +145,9 @@ supports.
Callbacks
~~~~~~~~~
- int (*probe) (struct device * dev);
+::
+
+ int (*probe) (struct device *dev);
The probe() entry is called in task context, with the bus's rwsem locked
and the driver partially bound to the device. Drivers commonly use
@@ -162,9 +167,9 @@ the driver to that device.
A driver's probe() may return a negative errno value to indicate that
the driver did not bind to this device, in which case it should have
-released all resources it allocated.
+released all resources it allocated::
- int (*remove) (struct device * dev);
+ int (*remove) (struct device *dev);
remove is called to unbind a driver from a device. This may be
called if a device is physically removed from the system, if the
@@ -173,43 +178,46 @@ in other cases.
It is up to the driver to determine if the device is present or
not. It should free any resources allocated specifically for the
-device; i.e. anything in the device's driver_data field.
+device; i.e. anything in the device's driver_data field.
If the device is still present, it should quiesce the device and place
-it into a supported low-power state.
+it into a supported low-power state::
- int (*suspend) (struct device * dev, pm_message_t state);
+ int (*suspend) (struct device *dev, pm_message_t state);
-suspend is called to put the device in a low power state.
+suspend is called to put the device in a low power state::
- int (*resume) (struct device * dev);
+ int (*resume) (struct device *dev);
Resume is used to bring a device back from a low power state.
Attributes
~~~~~~~~~~
-struct driver_attribute {
- struct attribute attr;
- ssize_t (*show)(struct device_driver *driver, char *buf);
- ssize_t (*store)(struct device_driver *, const char * buf, size_t count);
-};
-Device drivers can export attributes via their sysfs directories.
+::
+
+ struct driver_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct device_driver *driver, char *buf);
+ ssize_t (*store)(struct device_driver *, const char *buf, size_t count);
+ };
+
+Device drivers can export attributes via their sysfs directories.
Drivers can declare attributes using a DRIVER_ATTR_RW and DRIVER_ATTR_RO
macro that works identically to the DEVICE_ATTR_RW and DEVICE_ATTR_RO
macros.
-Example:
+Example::
-DRIVER_ATTR_RW(debug);
+ DRIVER_ATTR_RW(debug);
-This is equivalent to declaring:
+This is equivalent to declaring::
-struct driver_attribute driver_attr_debug;
+ struct driver_attribute driver_attr_debug;
This can then be used to add and remove the attribute from the
-driver's directory using:
+driver's directory using::
-int driver_create_file(struct device_driver *, const struct driver_attribute *);
-void driver_remove_file(struct device_driver *, const struct driver_attribute *);
+ int driver_create_file(struct device_driver *, const struct driver_attribute *);
+ void driver_remove_file(struct device_driver *, const struct driver_attribute *);
diff --git a/Documentation/driver-model/index.rst b/Documentation/driver-model/index.rst
new file mode 100644
index 000000000000..9f85d579ce56
--- /dev/null
+++ b/Documentation/driver-model/index.rst
@@ -0,0 +1,26 @@
+:orphan:
+
+============
+Driver Model
+============
+
+.. toctree::
+ :maxdepth: 1
+
+ binding
+ bus
+ class
+ design-patterns
+ device
+ devres
+ driver
+ overview
+ platform
+ porting
+
+.. only:: subproject and html
+
+ Indices
+ =======
+
+ * :ref:`genindex`
diff --git a/Documentation/driver-model/overview.txt b/Documentation/driver-model/overview.rst
index 6a8f9a8075d8..d4d1e9b40e0c 100644
--- a/Documentation/driver-model/overview.txt
+++ b/Documentation/driver-model/overview.rst
@@ -1,4 +1,6 @@
+=============================
The Linux Kernel Device Model
+=============================
Patrick Mochel <mochel@digitalimplant.org>
@@ -41,14 +43,14 @@ data structure. These fields must still be accessed by the bus layers,
and sometimes by the device-specific drivers.
Other bus layers are encouraged to do what has been done for the PCI layer.
-struct pci_dev now looks like this:
+struct pci_dev now looks like this::
-struct pci_dev {
+ struct pci_dev {
...
struct device dev; /* Generic device interface */
...
-};
+ };
Note first that the struct device dev within the struct pci_dev is
statically allocated. This means only one allocation on device discovery.
@@ -80,26 +82,26 @@ easy. This has been accomplished by implementing a special purpose virtual
file system named sysfs.
Almost all mainstream Linux distros mount this filesystem automatically; you
-can see some variation of the following in the output of the "mount" command:
+can see some variation of the following in the output of the "mount" command::
-$ mount
-...
-none on /sys type sysfs (rw,noexec,nosuid,nodev)
-...
-$
+ $ mount
+ ...
+ none on /sys type sysfs (rw,noexec,nosuid,nodev)
+ ...
+ $
The auto-mounting of sysfs is typically accomplished by an entry similar to
-the following in the /etc/fstab file:
+the following in the /etc/fstab file::
-none /sys sysfs defaults 0 0
+ none /sys sysfs defaults 0 0
-or something similar in the /lib/init/fstab file on Debian-based systems:
+or something similar in the /lib/init/fstab file on Debian-based systems::
-none /sys sysfs nodev,noexec,nosuid 0 0
+ none /sys sysfs nodev,noexec,nosuid 0 0
-If sysfs is not automatically mounted, you can always do it manually with:
+If sysfs is not automatically mounted, you can always do it manually with::
-# mount -t sysfs sysfs /sys
+ # mount -t sysfs sysfs /sys
Whenever a device is inserted into the tree, a directory is created for it.
This directory may be populated at each layer of discovery - the global layer,
@@ -108,7 +110,7 @@ the bus layer, or the device layer.
The global layer currently creates two files - 'name' and 'power'. The
former only reports the name of the device. The latter reports the
current power state of the device. It will also be used to set the current
-power state.
+power state.
The bus layer may also create files for the devices it finds while probing the
bus. For example, the PCI layer currently creates 'irq' and 'resource' files
@@ -118,6 +120,5 @@ A device-specific driver may also export files in its directory to expose
device-specific data or tunable interfaces.
More information about the sysfs directory layout can be found in
-the other documents in this directory and in the file
+the other documents in this directory and in the file
Documentation/filesystems/sysfs.txt.
-
diff --git a/Documentation/driver-model/platform.txt b/Documentation/driver-model/platform.rst
index 9d9e47dfc013..334dd4071ae4 100644
--- a/Documentation/driver-model/platform.txt
+++ b/Documentation/driver-model/platform.rst
@@ -1,5 +1,7 @@
+============================
Platform Devices and Drivers
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+============================
+
See <linux/platform_device.h> for the driver model interface to the
platform bus: platform_device, and platform_driver. This pseudo-bus
is used to connect devices on busses with minimal infrastructure,
@@ -19,15 +21,15 @@ be connected through a segment of some other kind of bus; but its
registers will still be directly addressable.
Platform devices are given a name, used in driver binding, and a
-list of resources such as addresses and IRQs.
+list of resources such as addresses and IRQs::
-struct platform_device {
+ struct platform_device {
const char *name;
u32 id;
struct device dev;
u32 num_resources;
struct resource *resource;
-};
+ };
Platform drivers
@@ -35,9 +37,9 @@ Platform drivers
Platform drivers follow the standard driver model convention, where
discovery/enumeration is handled outside the drivers, and drivers
provide probe() and remove() methods. They support power management
-and shutdown notifications using the standard conventions.
+and shutdown notifications using the standard conventions::
-struct platform_driver {
+ struct platform_driver {
int (*probe)(struct platform_device *);
int (*remove)(struct platform_device *);
void (*shutdown)(struct platform_device *);
@@ -46,25 +48,25 @@ struct platform_driver {
int (*resume_early)(struct platform_device *);
int (*resume)(struct platform_device *);
struct device_driver driver;
-};
+ };
Note that probe() should in general verify that the specified device hardware
actually exists; sometimes platform setup code can't be sure. The probing
can use device resources, including clocks, and device platform_data.
-Platform drivers register themselves the normal way:
+Platform drivers register themselves the normal way::
int platform_driver_register(struct platform_driver *drv);
Or, in common situations where the device is known not to be hot-pluggable,
the probe() routine can live in an init section to reduce the driver's
-runtime memory footprint:
+runtime memory footprint::
int platform_driver_probe(struct platform_driver *drv,
int (*probe)(struct platform_device *))
Kernel modules can be composed of several platform drivers. The platform core
-provides helpers to register and unregister an array of drivers:
+provides helpers to register and unregister an array of drivers::
int __platform_register_drivers(struct platform_driver * const *drivers,
unsigned int count, struct module *owner);
@@ -73,7 +75,7 @@ provides helpers to register and unregister an array of drivers:
If one of the drivers fails to register, all drivers registered up to that
point will be unregistered in reverse order. Note that there is a convenience
-macro that passes THIS_MODULE as owner parameter:
+macro that passes THIS_MODULE as owner parameter::
#define platform_register_drivers(drivers, count)
@@ -81,7 +83,7 @@ macro that passes THIS_MODULE as owner parameter:
Device Enumeration
~~~~~~~~~~~~~~~~~~
As a rule, platform specific (and often board-specific) setup code will
-register platform devices:
+register platform devices::
int platform_device_register(struct platform_device *pdev);
@@ -133,14 +135,14 @@ tend to already have "normal" modes, such as ones using device nodes that
were created by PNP or by platform device setup.
None the less, there are some APIs to support such legacy drivers. Avoid
-using these calls except with such hotplug-deficient drivers.
+using these calls except with such hotplug-deficient drivers::
struct platform_device *platform_device_alloc(
const char *name, int id);
You can use platform_device_alloc() to dynamically allocate a device, which
you will then initialize with resources and platform_device_register().
-A better solution is usually:
+A better solution is usually::
struct platform_device *platform_device_register_simple(
const char *name, int id,
diff --git a/Documentation/driver-model/porting.txt b/Documentation/driver-model/porting.rst
index 453053f1661f..ae4bf843c1d6 100644
--- a/Documentation/driver-model/porting.txt
+++ b/Documentation/driver-model/porting.rst
@@ -1,5 +1,6 @@
-
+=======================================
Porting Drivers to the New Driver Model
+=======================================
Patrick Mochel
@@ -8,8 +9,8 @@ Patrick Mochel
Overview
-Please refer to Documentation/driver-model/*.txt for definitions of
-various driver types and concepts.
+Please refer to `Documentation/driver-model/*.rst` for definitions of
+various driver types and concepts.
Most of the work of porting devices drivers to the new model happens
at the bus driver layer. This was intentional, to minimize the
@@ -18,11 +19,11 @@ of bus drivers.
In a nutshell, the driver model consists of a set of objects that can
be embedded in larger, bus-specific objects. Fields in these generic
-objects can replace fields in the bus-specific objects.
+objects can replace fields in the bus-specific objects.
The generic objects must be registered with the driver model core. By
doing so, they will exported via the sysfs filesystem. sysfs can be
-mounted by doing
+mounted by doing::
# mount -t sysfs sysfs /sys
@@ -30,108 +31,109 @@ mounted by doing
The Process
-Step 0: Read include/linux/device.h for object and function definitions.
+Step 0: Read include/linux/device.h for object and function definitions.
-Step 1: Registering the bus driver.
+Step 1: Registering the bus driver.
-- Define a struct bus_type for the bus driver.
+- Define a struct bus_type for the bus driver::
-struct bus_type pci_bus_type = {
- .name = "pci",
-};
+ struct bus_type pci_bus_type = {
+ .name = "pci",
+ };
- Register the bus type.
+
This should be done in the initialization function for the bus type,
- which is usually the module_init(), or equivalent, function.
+ which is usually the module_init(), or equivalent, function::
-static int __init pci_driver_init(void)
-{
- return bus_register(&pci_bus_type);
-}
+ static int __init pci_driver_init(void)
+ {
+ return bus_register(&pci_bus_type);
+ }
-subsys_initcall(pci_driver_init);
+ subsys_initcall(pci_driver_init);
The bus type may be unregistered (if the bus driver may be compiled
- as a module) by doing:
+ as a module) by doing::
bus_unregister(&pci_bus_type);
-- Export the bus type for others to use.
+- Export the bus type for others to use.
- Other code may wish to reference the bus type, so declare it in a
+ Other code may wish to reference the bus type, so declare it in a
shared header file and export the symbol.
-From include/linux/pci.h:
+From include/linux/pci.h::
-extern struct bus_type pci_bus_type;
+ extern struct bus_type pci_bus_type;
-From file the above code appears in:
+From file the above code appears in::
-EXPORT_SYMBOL(pci_bus_type);
+ EXPORT_SYMBOL(pci_bus_type);
- This will cause the bus to show up in /sys/bus/pci/ with two
- subdirectories: 'devices' and 'drivers'.
+ subdirectories: 'devices' and 'drivers'::
-# tree -d /sys/bus/pci/
-/sys/bus/pci/
-|-- devices
-`-- drivers
+ # tree -d /sys/bus/pci/
+ /sys/bus/pci/
+ |-- devices
+ `-- drivers
-Step 2: Registering Devices.
+Step 2: Registering Devices.
struct device represents a single device. It mainly contains metadata
-describing the relationship the device has to other entities.
+describing the relationship the device has to other entities.
-- Embed a struct device in the bus-specific device type.
+- Embed a struct device in the bus-specific device type::
-struct pci_dev {
- ...
- struct device dev; /* Generic device interface */
- ...
-};
+ struct pci_dev {
+ ...
+ struct device dev; /* Generic device interface */
+ ...
+ };
- It is recommended that the generic device not be the first item in
+ It is recommended that the generic device not be the first item in
the struct to discourage programmers from doing mindless casts
between the object types. Instead macros, or inline functions,
- should be created to convert from the generic object type.
+ should be created to convert from the generic object type::
-#define to_pci_dev(n) container_of(n, struct pci_dev, dev)
+ #define to_pci_dev(n) container_of(n, struct pci_dev, dev)
-or
+ or
-static inline struct pci_dev * to_pci_dev(struct kobject * kobj)
-{
+ static inline struct pci_dev * to_pci_dev(struct kobject * kobj)
+ {
return container_of(n, struct pci_dev, dev);
-}
+ }
- This allows the compiler to verify type-safety of the operations
+ This allows the compiler to verify type-safety of the operations
that are performed (which is Good).
- Initialize the device on registration.
- When devices are discovered or registered with the bus type, the
+ When devices are discovered or registered with the bus type, the
bus driver should initialize the generic device. The most important
things to initialize are the bus_id, parent, and bus fields.
The bus_id is an ASCII string that contains the device's address on
the bus. The format of this string is bus-specific. This is
- necessary for representing devices in sysfs.
+ necessary for representing devices in sysfs.
parent is the physical parent of the device. It is important that
- the bus driver sets this field correctly.
+ the bus driver sets this field correctly.
The driver model maintains an ordered list of devices that it uses
for power management. This list must be in order to guarantee that
@@ -140,13 +142,13 @@ static inline struct pci_dev * to_pci_dev(struct kobject * kobj)
devices.
Also, the location of the device's sysfs directory depends on a
- device's parent. sysfs exports a directory structure that mirrors
+ device's parent. sysfs exports a directory structure that mirrors
the device hierarchy. Accurately setting the parent guarantees that
sysfs will accurately represent the hierarchy.
The device's bus field is a pointer to the bus type the device
belongs to. This should be set to the bus_type that was declared
- and initialized before.
+ and initialized before.
Optionally, the bus driver may set the device's name and release
fields.
@@ -155,107 +157,107 @@ static inline struct pci_dev * to_pci_dev(struct kobject * kobj)
"ATI Technologies Inc Radeon QD"
- The release field is a callback that the driver model core calls
- when the device has been removed, and all references to it have
+ The release field is a callback that the driver model core calls
+ when the device has been removed, and all references to it have
been released. More on this in a moment.
-- Register the device.
+- Register the device.
Once the generic device has been initialized, it can be registered
- with the driver model core by doing:
+ with the driver model core by doing::
device_register(&dev->dev);
- It can later be unregistered by doing:
+ It can later be unregistered by doing::
device_unregister(&dev->dev);
- This should happen on buses that support hotpluggable devices.
+ This should happen on buses that support hotpluggable devices.
If a bus driver unregisters a device, it should not immediately free
- it. It should instead wait for the driver model core to call the
- device's release method, then free the bus-specific object.
+ it. It should instead wait for the driver model core to call the
+ device's release method, then free the bus-specific object.
(There may be other code that is currently referencing the device
- structure, and it would be rude to free the device while that is
+ structure, and it would be rude to free the device while that is
happening).
- When the device is registered, a directory in sysfs is created.
- The PCI tree in sysfs looks like:
-
-/sys/devices/pci0/
-|-- 00:00.0
-|-- 00:01.0
-| `-- 01:00.0
-|-- 00:02.0
-| `-- 02:1f.0
-| `-- 03:00.0
-|-- 00:1e.0
-| `-- 04:04.0
-|-- 00:1f.0
-|-- 00:1f.1
-| |-- ide0
-| | |-- 0.0
-| | `-- 0.1
-| `-- ide1
-| `-- 1.0
-|-- 00:1f.2
-|-- 00:1f.3
-`-- 00:1f.5
+ When the device is registered, a directory in sysfs is created.
+ The PCI tree in sysfs looks like::
+
+ /sys/devices/pci0/
+ |-- 00:00.0
+ |-- 00:01.0
+ | `-- 01:00.0
+ |-- 00:02.0
+ | `-- 02:1f.0
+ | `-- 03:00.0
+ |-- 00:1e.0
+ | `-- 04:04.0
+ |-- 00:1f.0
+ |-- 00:1f.1
+ | |-- ide0
+ | | |-- 0.0
+ | | `-- 0.1
+ | `-- ide1
+ | `-- 1.0
+ |-- 00:1f.2
+ |-- 00:1f.3
+ `-- 00:1f.5
Also, symlinks are created in the bus's 'devices' directory
- that point to the device's directory in the physical hierarchy.
+ that point to the device's directory in the physical hierarchy::
-/sys/bus/pci/devices/
-|-- 00:00.0 -> ../../../devices/pci0/00:00.0
-|-- 00:01.0 -> ../../../devices/pci0/00:01.0
-|-- 00:02.0 -> ../../../devices/pci0/00:02.0
-|-- 00:1e.0 -> ../../../devices/pci0/00:1e.0
-|-- 00:1f.0 -> ../../../devices/pci0/00:1f.0
-|-- 00:1f.1 -> ../../../devices/pci0/00:1f.1
-|-- 00:1f.2 -> ../../../devices/pci0/00:1f.2
-|-- 00:1f.3 -> ../../../devices/pci0/00:1f.3
-|-- 00:1f.5 -> ../../../devices/pci0/00:1f.5
-|-- 01:00.0 -> ../../../devices/pci0/00:01.0/01:00.0
-|-- 02:1f.0 -> ../../../devices/pci0/00:02.0/02:1f.0
-|-- 03:00.0 -> ../../../devices/pci0/00:02.0/02:1f.0/03:00.0
-`-- 04:04.0 -> ../../../devices/pci0/00:1e.0/04:04.0
+ /sys/bus/pci/devices/
+ |-- 00:00.0 -> ../../../devices/pci0/00:00.0
+ |-- 00:01.0 -> ../../../devices/pci0/00:01.0
+ |-- 00:02.0 -> ../../../devices/pci0/00:02.0
+ |-- 00:1e.0 -> ../../../devices/pci0/00:1e.0
+ |-- 00:1f.0 -> ../../../devices/pci0/00:1f.0
+ |-- 00:1f.1 -> ../../../devices/pci0/00:1f.1
+ |-- 00:1f.2 -> ../../../devices/pci0/00:1f.2
+ |-- 00:1f.3 -> ../../../devices/pci0/00:1f.3
+ |-- 00:1f.5 -> ../../../devices/pci0/00:1f.5
+ |-- 01:00.0 -> ../../../devices/pci0/00:01.0/01:00.0
+ |-- 02:1f.0 -> ../../../devices/pci0/00:02.0/02:1f.0
+ |-- 03:00.0 -> ../../../devices/pci0/00:02.0/02:1f.0/03:00.0
+ `-- 04:04.0 -> ../../../devices/pci0/00:1e.0/04:04.0
Step 3: Registering Drivers.
struct device_driver is a simple driver structure that contains a set
-of operations that the driver model core may call.
+of operations that the driver model core may call.
-- Embed a struct device_driver in the bus-specific driver.
+- Embed a struct device_driver in the bus-specific driver.
- Just like with devices, do something like:
+ Just like with devices, do something like::
-struct pci_driver {
- ...
- struct device_driver driver;
-};
+ struct pci_driver {
+ ...
+ struct device_driver driver;
+ };
-- Initialize the generic driver structure.
+- Initialize the generic driver structure.
When the driver registers with the bus (e.g. doing pci_register_driver()),
initialize the necessary fields of the driver: the name and bus
- fields.
+ fields.
- Register the driver.
- After the generic driver has been initialized, call
+ After the generic driver has been initialized, call::
driver_register(&drv->driver);
to register the driver with the core.
When the driver is unregistered from the bus, unregister it from the
- core by doing:
+ core by doing::
driver_unregister(&drv->driver);
@@ -265,15 +267,15 @@ struct pci_driver {
- Sysfs representation.
- Drivers are exported via sysfs in their bus's 'driver's directory.
- For example:
+ Drivers are exported via sysfs in their bus's 'driver's directory.
+ For example::
-/sys/bus/pci/drivers/
-|-- 3c59x
-|-- Ensoniq AudioPCI
-|-- agpgart-amdk7
-|-- e100
-`-- serial
+ /sys/bus/pci/drivers/
+ |-- 3c59x
+ |-- Ensoniq AudioPCI
+ |-- agpgart-amdk7
+ |-- e100
+ `-- serial
Step 4: Define Generic Methods for Drivers.
@@ -281,30 +283,30 @@ Step 4: Define Generic Methods for Drivers.
struct device_driver defines a set of operations that the driver model
core calls. Most of these operations are probably similar to
operations the bus already defines for drivers, but taking different
-parameters.
+parameters.
It would be difficult and tedious to force every driver on a bus to
simultaneously convert their drivers to generic format. Instead, the
bus driver should define single instances of the generic methods that
-forward call to the bus-specific drivers. For instance:
+forward call to the bus-specific drivers. For instance::
-static int pci_device_remove(struct device * dev)
-{
- struct pci_dev * pci_dev = to_pci_dev(dev);
- struct pci_driver * drv = pci_dev->driver;
+ static int pci_device_remove(struct device * dev)
+ {
+ struct pci_dev * pci_dev = to_pci_dev(dev);
+ struct pci_driver * drv = pci_dev->driver;
- if (drv) {
- if (drv->remove)
- drv->remove(pci_dev);
- pci_dev->driver = NULL;
- }
- return 0;
-}
+ if (drv) {
+ if (drv->remove)
+ drv->remove(pci_dev);
+ pci_dev->driver = NULL;
+ }
+ return 0;
+ }
The generic driver should be initialized with these methods before it
-is registered.
+is registered::
/* initialize common driver fields */
drv->driver.name = drv->name;
@@ -320,23 +322,23 @@ is registered.
Ideally, the bus should only initialize the fields if they are not
already set. This allows the drivers to implement their own generic
-methods.
+methods.
-Step 5: Support generic driver binding.
+Step 5: Support generic driver binding.
The model assumes that a device or driver can be dynamically
registered with the bus at any time. When registration happens,
devices must be bound to a driver, or drivers must be bound to all
-devices that it supports.
+devices that it supports.
A driver typically contains a list of device IDs that it supports. The
-bus driver compares these IDs to the IDs of devices registered with it.
+bus driver compares these IDs to the IDs of devices registered with it.
The format of the device IDs, and the semantics for comparing them are
-bus-specific, so the generic model does attempt to generalize them.
+bus-specific, so the generic model does attempt to generalize them.
Instead, a bus may supply a method in struct bus_type that does the
-comparison:
+comparison::
int (*match)(struct device * dev, struct device_driver * drv);
@@ -346,59 +348,59 @@ and zero otherwise. It may also return error code (for example
not possible.
When a device is registered, the bus's list of drivers is iterated
-over. bus->match() is called for each one until a match is found.
+over. bus->match() is called for each one until a match is found.
When a driver is registered, the bus's list of devices is iterated
over. bus->match() is called for each device that is not already
-claimed by a driver.
+claimed by a driver.
When a device is successfully bound to a driver, device->driver is
set, the device is added to a per-driver list of devices, and a
symlink is created in the driver's sysfs directory that points to the
-device's physical directory:
+device's physical directory::
-/sys/bus/pci/drivers/
-|-- 3c59x
-| `-- 00:0b.0 -> ../../../../devices/pci0/00:0b.0
-|-- Ensoniq AudioPCI
-|-- agpgart-amdk7
-| `-- 00:00.0 -> ../../../../devices/pci0/00:00.0
-|-- e100
-| `-- 00:0c.0 -> ../../../../devices/pci0/00:0c.0
-`-- serial
+ /sys/bus/pci/drivers/
+ |-- 3c59x
+ | `-- 00:0b.0 -> ../../../../devices/pci0/00:0b.0
+ |-- Ensoniq AudioPCI
+ |-- agpgart-amdk7
+ | `-- 00:00.0 -> ../../../../devices/pci0/00:00.0
+ |-- e100
+ | `-- 00:0c.0 -> ../../../../devices/pci0/00:0c.0
+ `-- serial
This driver binding should replace the existing driver binding
-mechanism the bus currently uses.
+mechanism the bus currently uses.
Step 6: Supply a hotplug callback.
Whenever a device is registered with the driver model core, the
-userspace program /sbin/hotplug is called to notify userspace.
+userspace program /sbin/hotplug is called to notify userspace.
Users can define actions to perform when a device is inserted or
-removed.
+removed.
The driver model core passes several arguments to userspace via
environment variables, including
- ACTION: set to 'add' or 'remove'
-- DEVPATH: set to the device's physical path in sysfs.
+- DEVPATH: set to the device's physical path in sysfs.
A bus driver may also supply additional parameters for userspace to
consume. To do this, a bus must implement the 'hotplug' method in
-struct bus_type:
+struct bus_type::
- int (*hotplug) (struct device *dev, char **envp,
+ int (*hotplug) (struct device *dev, char **envp,
int num_envp, char *buffer, int buffer_size);
-This is called immediately before /sbin/hotplug is executed.
+This is called immediately before /sbin/hotplug is executed.
Step 7: Cleaning up the bus driver.
The generic bus, device, and driver structures provide several fields
-that can replace those defined privately to the bus driver.
+that can replace those defined privately to the bus driver.
- Device list.
@@ -407,36 +409,36 @@ type. This includes all devices on all instances of that bus type.
An internal list that the bus uses may be removed, in favor of using
this one.
-The core provides an iterator to access these devices.
+The core provides an iterator to access these devices::
-int bus_for_each_dev(struct bus_type * bus, struct device * start,
- void * data, int (*fn)(struct device *, void *));
+ int bus_for_each_dev(struct bus_type * bus, struct device * start,
+ void * data, int (*fn)(struct device *, void *));
- Driver list.
struct bus_type also contains a list of all drivers registered with
-it. An internal list of drivers that the bus driver maintains may
-be removed in favor of using the generic one.
+it. An internal list of drivers that the bus driver maintains may
+be removed in favor of using the generic one.
-The drivers may be iterated over, like devices:
+The drivers may be iterated over, like devices::
-int bus_for_each_drv(struct bus_type * bus, struct device_driver * start,
- void * data, int (*fn)(struct device_driver *, void *));
+ int bus_for_each_drv(struct bus_type * bus, struct device_driver * start,
+ void * data, int (*fn)(struct device_driver *, void *));
Please see drivers/base/bus.c for more information.
-- rwsem
+- rwsem
struct bus_type contains an rwsem that protects all core accesses to
the device and driver lists. This can be used by the bus driver
internally, and should be used when accessing the device or driver
-lists the bus maintains.
+lists the bus maintains.
-- Device and driver fields.
+- Device and driver fields.
Some of the fields in struct device and struct device_driver duplicate
fields in the bus-specific representations of these objects. Feel free
@@ -444,4 +446,3 @@ to remove the bus-specific ones and favor the generic ones. Note
though, that this will likely mean fixing up all the drivers that
reference the bus-specific fields (though those should all be 1-line
changes).
-
diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt
index 2806e5544e43..f388545a85a7 100644
--- a/Documentation/eisa.txt
+++ b/Documentation/eisa.txt
@@ -103,7 +103,7 @@ id_table an array of NULL terminated EISA id strings,
(driver_data).
driver a generic driver, such as described in
- Documentation/driver-model/driver.txt. Only .name,
+ Documentation/driver-model/driver.rst. Only .name,
.probe and .remove members are mandatory.
=============== ====================================================
@@ -152,7 +152,7 @@ state set of flags indicating the state of the device. Current
flags are EISA_CONFIG_ENABLED and EISA_CONFIG_FORCED.
res set of four 256 bytes I/O regions allocated to this device
dma_mask DMA mask set from the parent device.
-dev generic device (see Documentation/driver-model/device.txt)
+dev generic device (see Documentation/driver-model/device.rst)
======== ============================================================
You can get the 'struct eisa_device' from 'struct device' using the
diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt
index 4a0a9c3f4af6..9e27c843d00e 100644
--- a/Documentation/filesystems/debugfs.txt
+++ b/Documentation/filesystems/debugfs.txt
@@ -169,7 +169,7 @@ byte offsets over a base for the register block.
If you want to dump an u32 array in debugfs, you can create file with:
- struct dentry *debugfs_create_u32_array(const char *name, umode_t mode,
+ void debugfs_create_u32_array(const char *name, umode_t mode,
struct dentry *parent,
u32 *array, u32 elements);
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index f7b5e4ff0de3..496fa28b2492 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -214,11 +214,22 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix",
non-atomic files likewise "nobarrier" mount option.
test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt
context. The fake fscrypt context is used by xfstests.
-checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable"
+checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable"
to reenable checkpointing. Is enabled by default. While
disabled, any unmounting or unexpected shutdowns will cause
the filesystem contents to appear as they did when the
filesystem was mounted with that option.
+ While mounting with checkpoint=disabled, the filesystem must
+ run garbage collection to ensure that all available space can
+ be used. If this takes too much time, the mount may return
+ EAGAIN. You may optionally add a value to indicate how much
+ of the disk you would be willing to temporarily give up to
+ avoid additional garbage collection. This can be given as a
+ number of blocks, or as a percent. For instance, mounting
+ with checkpoint=disable:100% would always succeed, but it may
+ hide up to all remaining free space. The actual space that
+ would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable
+ This space is reclaimed once checkpoint=enable.
================================================================================
DEBUGFS ENTRIES
@@ -246,11 +257,14 @@ Files in /sys/fs/f2fs/<devname>
..............................................................................
File Content
- gc_max_sleep_time This tuning parameter controls the maximum sleep
+ gc_urgent_sleep_time This parameter controls sleep time for gc_urgent.
+ 500 ms is set by default. See above gc_urgent.
+
+ gc_min_sleep_time This tuning parameter controls the minimum sleep
time for the garbage collection thread. Time is
in milliseconds.
- gc_min_sleep_time This tuning parameter controls the minimum sleep
+ gc_max_sleep_time This tuning parameter controls the maximum sleep
time for the garbage collection thread. Time is
in milliseconds.
@@ -270,9 +284,6 @@ Files in /sys/fs/f2fs/<devname>
to 1, background thread starts to do GC by given
gc_urgent_sleep_time interval.
- gc_urgent_sleep_time This parameter controls sleep time for gc_urgent.
- 500 ms is set by default. See above gc_urgent.
-
reclaim_segments This parameter controls the number of prefree
segments to be reclaimed. If the number of prefree
segments is larger than the number of segments
@@ -287,7 +298,16 @@ Files in /sys/fs/f2fs/<devname>
checkpoint is triggered, and issued during the
checkpoint. By default, it is disabled with 0.
- trim_sections This parameter controls the number of sections
+ discard_granularity This parameter controls the granularity of discard
+ command size. It will issue discard commands iif
+ the size is larger than given granularity. Its
+ unit size is 4KB, and 4 (=16KB) is set by default.
+ The maximum value is 128 (=512KB).
+
+ reserved_blocks This parameter indicates the number of blocks that
+ f2fs reserves internally for root.
+
+ batched_trim_sections This parameter controls the number of sections
to be trimmed out in batch mode when FITRIM
conducts. 32 sections is set by default.
@@ -309,11 +329,35 @@ Files in /sys/fs/f2fs/<devname>
the number is less than this value, it triggers
in-place-updates.
+ min_seq_blocks This parameter controls the threshold to serialize
+ write IOs issued by multiple threads in parallel.
+
+ min_hot_blocks This parameter controls the threshold to allocate
+ a hot data log for pending data blocks to write.
+
+ min_ssr_sections This parameter adds the threshold when deciding
+ SSR block allocation. If this is large, SSR mode
+ will be enabled early.
+
+ ram_thresh This parameter controls the memory footprint used
+ by free nids and cached nat entries. By default,
+ 10 is set, which indicates 10 MB / 1 GB RAM.
+
+ ra_nid_pages When building free nids, F2FS reads NAT blocks
+ ahead for speed up. Default is 0.
+
+ dirty_nats_ratio Given dirty ratio of cached nat entries, F2FS
+ determines flushing them in background.
+
max_victim_search This parameter controls the number of trials to
find a victim segment when conducting SSR and
cleaning operations. The default value is 4096
which covers 8GB block address range.
+ migration_granularity For large-sized sections, F2FS can stop GC given
+ this granularity instead of reclaiming entire
+ section.
+
dir_level This parameter controls the directory level to
support large directory. If a directory has a
number of files, it can reduce the file lookup
@@ -321,9 +365,53 @@ Files in /sys/fs/f2fs/<devname>
Otherwise, it needs to decrease this value to
reduce the space overhead. The default value is 0.
- ram_thresh This parameter controls the memory footprint used
- by free nids and cached nat entries. By default,
- 10 is set, which indicates 10 MB / 1 GB RAM.
+ cp_interval F2FS tries to do checkpoint periodically, 60 secs
+ by default.
+
+ idle_interval F2FS detects system is idle, if there's no F2FS
+ operations during given interval, 5 secs by
+ default.
+
+ discard_idle_interval F2FS detects the discard thread is idle, given
+ time interval. Default is 5 secs.
+
+ gc_idle_interval F2FS detects the GC thread is idle, given time
+ interval. Default is 5 secs.
+
+ umount_discard_timeout When unmounting the disk, F2FS waits for finishing
+ queued discard commands which can take huge time.
+ This gives time out for it, 5 secs by default.
+
+ iostat_enable This controls to enable/disable iostat in F2FS.
+
+ readdir_ra This enables/disabled readahead of inode blocks
+ in readdir, and default is enabled.
+
+ gc_pin_file_thresh This indicates how many GC can be failed for the
+ pinned file. If it exceeds this, F2FS doesn't
+ guarantee its pinning state. 2048 trials is set
+ by default.
+
+ extension_list This enables to change extension_list for hot/cold
+ files in runtime.
+
+ inject_rate This controls injection rate of arbitrary faults.
+
+ inject_type This controls injection type of arbitrary faults.
+
+ dirty_segments This shows # of dirty segments.
+
+ lifetime_write_kbytes This shows # of data written to the disk.
+
+ features This shows current features enabled on F2FS.
+
+ current_reserved_blocks This shows # of blocks currently reserved.
+
+ unusable If checkpoint=disable, this shows the number of
+ blocks that are unusable.
+ If checkpoint=enable it shows the number of blocks
+ that would be unusable if checkpoint=disable were
+ to be set.
================================================================================
USAGE
@@ -716,3 +804,28 @@ WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
WRITE_LIFE_NONE " WRITE_LIFE_NONE
WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
WRITE_LIFE_LONG " WRITE_LIFE_LONG
+
+Fallocate(2) Policy
+-------------------
+
+The default policy follows the below posix rule.
+
+Allocating disk space
+ The default operation (i.e., mode is zero) of fallocate() allocates
+ the disk space within the range specified by offset and len. The
+ file size (as reported by stat(2)) will be changed if offset+len is
+ greater than the file size. Any subregion within the range specified
+ by offset and len that did not contain data before the call will be
+ initialized to zero. This default behavior closely resembles the
+ behavior of the posix_fallocate(3) library function, and is intended
+ as a method of optimally implementing that function.
+
+However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to
+fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having
+zero or random data, which is useful to the below scenario where:
+ 1. create(fd)
+ 2. ioctl(fd, F2FS_IOC_SET_PIN_FILE)
+ 3. fallocate(fd, 0, 0, size)
+ 4. address = fibmap(fd, offset)
+ 5. open(blkdev)
+ 6. write(blkdev, address)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a226061fa109..d750b6926899 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -154,9 +154,11 @@ Table 1-1: Process specific entries in /proc
symbol the task is blocked in - or "0" if not blocked.
pagemap Page table
stack Report full stack trace, enable via CONFIG_STACKTRACE
- smaps an extension based on maps, showing the memory consumption of
+ smaps An extension based on maps, showing the memory consumption of
each mapping and flags associated with it
- numa_maps an extension based on maps, showing the memory locality and
+ smaps_rollup Accumulated smaps stats for all mappings of the process. This
+ can be derived from smaps, but is faster and more convenient
+ numa_maps An extension based on maps, showing the memory locality and
binding policy as well as mem usage (in pages) of each mapping.
..............................................................................
@@ -366,7 +368,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
exit_code the thread's exit_code in the form reported by the waitpid system call
..............................................................................
-The /proc/PID/maps file containing the currently mapped memory regions and
+The /proc/PID/maps file contains the currently mapped memory regions and
their access permissions.
The format is:
@@ -417,11 +419,14 @@ is not associated with a file:
or if empty, the mapping is anonymous.
The /proc/PID/smaps is an extension based on maps, showing the memory
-consumption for each of the process's mappings. For each of mappings there
-is a series of lines such as the following:
+consumption for each of the process's mappings. For each mapping (aka Virtual
+Memory Area, or VMA) there is a series of lines such as the following:
08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
+
Size: 1084 kB
+KernelPageSize: 4 kB
+MMUPageSize: 4 kB
Rss: 892 kB
Pss: 374 kB
Shared_Clean: 892 kB
@@ -443,11 +448,14 @@ Locked: 0 kB
THPeligible: 0
VmFlags: rd ex mr mw me dw
-the first of these lines shows the same information as is displayed for the
-mapping in /proc/PID/maps. The remaining lines show the size of the mapping
-(size), the amount of the mapping that is currently resident in RAM (RSS), the
-process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping.
+The first of these lines shows the same information as is displayed for the
+mapping in /proc/PID/maps. Following lines show the size of the mapping
+(size); the size of each page allocated when backing a VMA (KernelPageSize),
+which is usually the same as the size in the page table entries; the page size
+used by the MMU when backing a VMA (in most cases, the same as KernelPageSize);
+the amount of the mapping that is currently resident in RAM (RSS); the
+process' proportional share of this mapping (PSS); and the number of clean and
+dirty shared and private pages in the mapping.
The "proportional set size" (PSS) of a process is the count of pages it has
in memory, where each page is divided by the number of processes sharing it.
@@ -532,6 +540,19 @@ guarantees:
2) If there is something at a given vaddr during the entirety of the
life of the smaps/maps walk, there will be some output for it.
+The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps,
+but their values are the sums of the corresponding values for all mappings of
+the process. Additionally, it contains these fields:
+
+Pss_Anon
+Pss_File
+Pss_Shmem
+
+They represent the proportional shares of anonymous, file, and shmem pages, as
+described for smaps above. These fields are omitted in smaps since each
+mapping identifies the type (anon, file, or shmem) of all pages it contains.
+Thus all information in smaps_rollup can be derived from smaps, but at a
+significantly higher cost.
The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
bits on both physical and virtual pages associated with a process, and the
diff --git a/Documentation/filesystems/xfs-self-describing-metadata.txt b/Documentation/filesystems/xfs-self-describing-metadata.txt
index 68604e67a495..8db0121d0980 100644
--- a/Documentation/filesystems/xfs-self-describing-metadata.txt
+++ b/Documentation/filesystems/xfs-self-describing-metadata.txt
@@ -222,7 +222,7 @@ static void
xfs_foo_read_verify(
struct xfs_buf *bp)
{
- struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_mount *mp = bp->b_mount;
if ((xfs_sb_version_hascrc(&mp->m_sb) &&
!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
@@ -245,7 +245,7 @@ static bool
xfs_foo_verify(
struct xfs_buf *bp)
{
- struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_mount *mp = bp->b_mount;
struct xfs_ondisk_hdr *hdr = bp->b_addr;
if (hdr->magic != cpu_to_be32(XFS_FOO_MAGIC))
@@ -272,7 +272,7 @@ static bool
xfs_foo_verify(
struct xfs_buf *bp)
{
- struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_mount *mp = bp->b_mount;
struct xfs_ondisk_hdr *hdr = bp->b_addr;
if (hdr->magic == cpu_to_be32(XFS_FOO_CRC_MAGIC)) {
@@ -297,7 +297,7 @@ static void
xfs_foo_write_verify(
struct xfs_buf *bp)
{
- struct xfs_mount *mp = bp->b_target->bt_mount;
+ struct xfs_mount *mp = bp->b_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
if (!xfs_foo_verify(bp)) {
diff --git a/Documentation/hwmon/submitting-patches.rst b/Documentation/hwmon/submitting-patches.rst
index f9796b9d9db6..d5b05d3e54ba 100644
--- a/Documentation/hwmon/submitting-patches.rst
+++ b/Documentation/hwmon/submitting-patches.rst
@@ -89,7 +89,7 @@ increase the chances of your change being accepted.
console. Excessive logging can seriously affect system performance.
* Use devres functions whenever possible to allocate resources. For rationale
- and supported functions, please see Documentation/driver-model/devres.txt.
+ and supported functions, please see Documentation/driver-model/devres.rst.
If a function is not supported by devres, consider using devm_add_action().
* If the driver has a detect function, make sure it is silent. Debug messages
diff --git a/Documentation/kbuild/headers_install.rst b/Documentation/kbuild/headers_install.rst
index 1ab7294e41ac..f6c6b74a609c 100644
--- a/Documentation/kbuild/headers_install.rst
+++ b/Documentation/kbuild/headers_install.rst
@@ -40,12 +40,5 @@ INSTALL_HDR_PATH indicates where to install the headers. It defaults to
An 'include' directory is automatically created inside INSTALL_HDR_PATH and
headers are installed in 'INSTALL_HDR_PATH/include'.
-The command "make headers_install_all" exports headers for all architectures
-simultaneously. (This is mostly of interest to distribution maintainers,
-who create an architecture-independent tarball from the resulting include
-directory.) You also can use HDR_ARCH_LIST to specify list of architectures.
-Remember to provide the appropriate linux/asm directory via "mv" or "ln -s"
-before building a C library with headers exported this way.
-
The kernel header export infrastructure is maintained by David Woodhouse
<dwmw2@infradead.org>.
diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
index e774e760522d..b25548963d70 100644
--- a/Documentation/kbuild/kbuild.rst
+++ b/Documentation/kbuild/kbuild.rst
@@ -200,6 +200,15 @@ The output directory is often set using "O=..." on the commandline.
The value can be overridden in which case the default value is ignored.
+KBUILD_ABS_SRCTREE
+--------------------------------------------------
+Kbuild uses a relative path to point to the tree when possible. For instance,
+when building in the source tree, the source tree path is '.'
+
+Setting this flag requests Kbuild to use absolute path to the source tree.
+There are some useful cases to do so, like when generating tag files with
+absolute path entries etc.
+
KBUILD_SIGN_PIN
---------------
This variable allows a passphrase or PIN to be passed to the sign-file
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 9274cdcc9bd2..093f2d79ab95 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -999,11 +999,7 @@ When kbuild executes, the following steps are followed (roughly):
------------------------------------
The archheaders: rule is used to generate header files that
- may be installed into user space by "make header_install" or
- "make headers_install_all". In order to support
- "make headers_install_all", this target has to be able to run
- on an unconfigured tree, or a tree configured for another
- architecture.
+ may be installed into user space by "make header_install".
It is run before "make archprepare" when run on the
architecture itself.
@@ -1140,6 +1136,22 @@ When kbuild executes, the following steps are followed (roughly):
In this example, extra-y is used to list object files that
shall be built, but shall not be linked as part of built-in.a.
+ header-test-y
+
+ header-test-y specifies headers (*.h) in the current directory that
+ should be compile tested to ensure they are self-contained,
+ i.e. compilable as standalone units. If CONFIG_HEADER_TEST is enabled,
+ this builds them as part of extra-y.
+
+ header-test-pattern-y
+
+ This works as a weaker version of header-test-y, and accepts wildcard
+ patterns. The typical usage is:
+
+ header-test-pattern-y += *.h
+
+ This specifies all the files that matches to '*.h' in the current
+ directory, but the files in 'header-test-' are excluded.
6.7 Commands useful for building a boot image
---------------------------------------------
diff --git a/Documentation/virtual/index.rst b/Documentation/virtual/index.rst
new file mode 100644
index 000000000000..062ffb527043
--- /dev/null
+++ b/Documentation/virtual/index.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Linux Virtualization Support
+============================
+
+.. toctree::
+ :maxdepth: 2
+
+ kvm/index
+ paravirt_ops
+
+.. only:: html and subproject
+
+ Indices
+ =======
+
+ * :ref:`genindex`
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 383b292966fa..2cd6250b2896 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4081,6 +4081,32 @@ KVM_ARM_VCPU_FINALIZE call.
See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
using this ioctl.
+4.120 KVM_SET_PMU_EVENT_FILTER
+
+Capability: KVM_CAP_PMU_EVENT_FILTER
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pmu_event_filter (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_pmu_event_filter {
+ __u32 action;
+ __u32 nevents;
+ __u64 events[0];
+};
+
+This ioctl restricts the set of PMU events that the guest can program.
+The argument holds a list of events which will be allowed or denied.
+The eventsel+umask of each event the guest attempts to program is compared
+against the events field to determine whether the guest should have access.
+This only affects general purpose counters; fixed purpose counters can
+be disabled by changing the perfmon CPUID leaf.
+
+Valid values for 'action':
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+
5. The kvm_run structure
------------------------
@@ -4909,6 +4935,8 @@ Valid bits in args[0] are
#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
Enabling this capability on a VM provides userspace with a way to no
longer intercept some instructions for improved latency in some
diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virtual/kvm/arm/psci.txt
index aafdab887b04..559586fc9d37 100644
--- a/Documentation/virtual/kvm/arm/psci.txt
+++ b/Documentation/virtual/kvm/arm/psci.txt
@@ -28,3 +28,34 @@ The following register is defined:
- Allows any PSCI version implemented by KVM and compatible with
v0.2 to be set with SET_ONE_REG
- Affects the whole VM (even if the register view is per-vcpu)
+
+* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+ Holds the state of the firmware support to mitigate CVE-2017-5715, as
+ offered by KVM to the guest via a HVC call. The workaround is described
+ under SMCCC_ARCH_WORKAROUND_1 in [1].
+ Accepted values are:
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer
+ firmware support for the workaround. The mitigation status for the
+ guest is unknown.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is
+ available to the guest and required for the mitigation.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call
+ is available to the guest, but it is not needed on this VCPU.
+
+* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+ Holds the state of the firmware support to mitigate CVE-2018-3639, as
+ offered by KVM to the guest via a HVC call. The workaround is described
+ under SMCCC_ARCH_WORKAROUND_2 in [1].
+ Accepted values are:
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not
+ available. KVM does not offer firmware support for the workaround.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is
+ unknown. KVM does not offer firmware support for the workaround.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available,
+ and can be disabled by a vCPU. If
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for
+ this vCPU.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is
+ always active on this vCPU or it is not needed.
+
+[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf
diff --git a/Documentation/virtual/kvm/cpuid.rst b/Documentation/virtual/kvm/cpuid.rst
new file mode 100644
index 000000000000..01b081f6e7ea
--- /dev/null
+++ b/Documentation/virtual/kvm/cpuid.rst
@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+KVM CPUID bits
+==============
+
+:Author: Glauber Costa <glommer@gmail.com>
+
+A guest running on a kvm host, can check some of its features using
+cpuid. This is not always guaranteed to work, since userspace can
+mask-out some, or even all KVM-related cpuid features before launching
+a guest.
+
+KVM cpuid functions are:
+
+function: KVM_CPUID_SIGNATURE (0x40000000)
+
+returns::
+
+ eax = 0x40000001
+ ebx = 0x4b4d564b
+ ecx = 0x564b4d56
+ edx = 0x4d
+
+Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
+The value in eax corresponds to the maximum cpuid function present in this leaf,
+and will be updated if more functions are added in the future.
+Note also that old hosts set eax value to 0x0. This should
+be interpreted as if the value was 0x40000001.
+This function queries the presence of KVM cpuid leafs.
+
+function: define KVM_CPUID_FEATURES (0x40000001)
+
+returns::
+
+ ebx, ecx
+ eax = an OR'ed group of (1 << flag)
+
+where ``flag`` is defined as below:
+
+================================= =========== ================================
+flag value meaning
+================================= =========== ================================
+KVM_FEATURE_CLOCKSOURCE 0 kvmclock available at msrs
+ 0x11 and 0x12
+
+KVM_FEATURE_NOP_IO_DELAY 1 not necessary to perform delays
+ on PIO operations
+
+KVM_FEATURE_MMU_OP 2 deprecated
+
+KVM_FEATURE_CLOCKSOURCE2 3 kvmclock available at msrs
+
+ 0x4b564d00 and 0x4b564d01
+KVM_FEATURE_ASYNC_PF 4 async pf can be enabled by
+ writing to msr 0x4b564d02
+
+KVM_FEATURE_STEAL_TIME 5 steal time can be enabled by
+ writing to msr 0x4b564d03
+
+KVM_FEATURE_PV_EOI 6 paravirtualized end of interrupt
+ handler can be enabled by
+ writing to msr 0x4b564d04
+
+KVM_FEATURE_PV_UNHAULT 7 guest checks this feature bit
+ before enabling paravirtualized
+ spinlock support
+
+KVM_FEATURE_PV_TLB_FLUSH 9 guest checks this feature bit
+ before enabling paravirtualized
+ tlb flush
+
+KVM_FEATURE_ASYNC_PF_VMEXIT 10 paravirtualized async PF VM EXIT
+ can be enabled by setting bit 2
+ when writing to msr 0x4b564d02
+
+KVM_FEATURE_PV_SEND_IPI 11 guest checks this feature bit
+ before enabling paravirtualized
+ sebd IPIs
+
+KVM_FEATURE_PV_POLL_CONTROL 12 host-side polling on HLT can
+ be disabled by writing
+ to msr 0x4b564d05.
+
+KVM_FEATURE_PV_SCHED_YIELD 13 guest checks this feature bit
+ before using paravirtualized
+ sched yield.
+
+KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24 host will warn if no guest-side
+ per-cpu warps are expeced in
+ kvmclock
+================================= =========== ================================
+
+::
+
+ edx = an OR'ed group of (1 << flag)
+
+Where ``flag`` here is defined as below:
+
+================== ============ =================================
+flag value meaning
+================== ============ =================================
+KVM_HINTS_REALTIME 0 guest checks this feature bit to
+ determine that vCPUs are never
+ preempted for an unlimited time
+ allowing optimizations
+================== ============ =================================
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
deleted file mode 100644
index 97ca1940a0dc..000000000000
--- a/Documentation/virtual/kvm/cpuid.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-KVM CPUID bits
-Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
-=====================================================
-
-A guest running on a kvm host, can check some of its features using
-cpuid. This is not always guaranteed to work, since userspace can
-mask-out some, or even all KVM-related cpuid features before launching
-a guest.
-
-KVM cpuid functions are:
-
-function: KVM_CPUID_SIGNATURE (0x40000000)
-returns : eax = 0x40000001,
- ebx = 0x4b4d564b,
- ecx = 0x564b4d56,
- edx = 0x4d.
-Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
-The value in eax corresponds to the maximum cpuid function present in this leaf,
-and will be updated if more functions are added in the future.
-Note also that old hosts set eax value to 0x0. This should
-be interpreted as if the value was 0x40000001.
-This function queries the presence of KVM cpuid leafs.
-
-
-function: define KVM_CPUID_FEATURES (0x40000001)
-returns : ebx, ecx
- eax = an OR'ed group of (1 << flag), where each flags is:
-
-
-flag || value || meaning
-=============================================================================
-KVM_FEATURE_CLOCKSOURCE || 0 || kvmclock available at msrs
- || || 0x11 and 0x12.
-------------------------------------------------------------------------------
-KVM_FEATURE_NOP_IO_DELAY || 1 || not necessary to perform delays
- || || on PIO operations.
-------------------------------------------------------------------------------
-KVM_FEATURE_MMU_OP || 2 || deprecated.
-------------------------------------------------------------------------------
-KVM_FEATURE_CLOCKSOURCE2 || 3 || kvmclock available at msrs
- || || 0x4b564d00 and 0x4b564d01
-------------------------------------------------------------------------------
-KVM_FEATURE_ASYNC_PF || 4 || async pf can be enabled by
- || || writing to msr 0x4b564d02
-------------------------------------------------------------------------------
-KVM_FEATURE_STEAL_TIME || 5 || steal time can be enabled by
- || || writing to msr 0x4b564d03.
-------------------------------------------------------------------------------
-KVM_FEATURE_PV_EOI || 6 || paravirtualized end of interrupt
- || || handler can be enabled by writing
- || || to msr 0x4b564d04.
-------------------------------------------------------------------------------
-KVM_FEATURE_PV_UNHALT || 7 || guest checks this feature bit
- || || before enabling paravirtualized
- || || spinlock support.
-------------------------------------------------------------------------------
-KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit
- || || before enabling paravirtualized
- || || tlb flush.
-------------------------------------------------------------------------------
-KVM_FEATURE_ASYNC_PF_VMEXIT || 10 || paravirtualized async PF VM exit
- || || can be enabled by setting bit 2
- || || when writing to msr 0x4b564d02
-------------------------------------------------------------------------------
-KVM_FEATURE_PV_SEND_IPI || 11 || guest checks this feature bit
- || || before using paravirtualized
- || || send IPIs.
-------------------------------------------------------------------------------
-KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side
- || || per-cpu warps are expected in
- || || kvmclock.
-------------------------------------------------------------------------------
-
- edx = an OR'ed group of (1 << flag), where each flags is:
-
-
-flag || value || meaning
-==================================================================================
-KVM_HINTS_REALTIME || 0 || guest checks this feature bit to
- || || determine that vCPUs are never
- || || preempted for an unlimited time,
- || || allowing optimizations
-----------------------------------------------------------------------------------
diff --git a/Documentation/virtual/kvm/hypercalls.txt b/Documentation/virtual/kvm/hypercalls.txt
index da24c138c8d1..da210651f714 100644
--- a/Documentation/virtual/kvm/hypercalls.txt
+++ b/Documentation/virtual/kvm/hypercalls.txt
@@ -141,3 +141,14 @@ a0 corresponds to the APIC ID in the third argument (a2), bit 1
corresponds to the APIC ID a2+1, and so on.
Returns the number of CPUs to which the IPIs were delivered successfully.
+
+7. KVM_HC_SCHED_YIELD
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to yield if the IPI target vCPU is preempted
+
+a0: destination APIC ID
+
+Usage example: When sending a call-function IPI-many to vCPUs, yield if
+any of the IPI target vCPUs was preempted.
diff --git a/Documentation/virtual/kvm/index.rst b/Documentation/virtual/kvm/index.rst
new file mode 100644
index 000000000000..0b206a06f5be
--- /dev/null
+++ b/Documentation/virtual/kvm/index.rst
@@ -0,0 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===
+KVM
+===
+
+.. toctree::
+ :maxdepth: 2
+
+ amd-memory-encryption
+ cpuid
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 1bb8bcaf8497..635cd6eaf714 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -15,8 +15,6 @@ The acquisition orders for mutexes are as follows:
On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
-For spinlocks, kvm_lock is taken outside kvm->mmu_lock.
-
Everything else is a leaf: no other lock is taken inside the critical
sections.
@@ -169,7 +167,7 @@ which time it will be set using the Dirty tracking mechanism described above.
------------
Name: kvm_lock
-Type: spinlock_t
+Type: mutex
Arch: any
Protects: - vm_list
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index f3f0d57ced8e..df1f4338b3ca 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -273,3 +273,12 @@ MSR_KVM_EOI_EN: 0x4b564d04
guest must both read the least significant bit in the memory area and
clear it using a single CPU instruction, such as test and clear, or
compare and exchange.
+
+MSR_KVM_POLL_CONTROL: 0x4b564d05
+ Control host-side polling.
+
+ data: Bit 0 enables (1) or disables (0) host-side HLT polling logic.
+
+ KVM guests can request the host not to poll on HLT, for example if
+ they are performing polling themselves.
+
diff --git a/Documentation/virtual/paravirt_ops.txt b/Documentation/virtual/paravirt_ops.rst
index d4881c00e339..6b789d27cead 100644
--- a/Documentation/virtual/paravirt_ops.txt
+++ b/Documentation/virtual/paravirt_ops.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
Paravirt_ops
============
@@ -18,15 +21,15 @@ at boot time.
pv_ops operations are classified into three categories:
- simple indirect call
- These operations correspond to high level functionality where it is
- known that the overhead of indirect call isn't very important.
+ These operations correspond to high level functionality where it is
+ known that the overhead of indirect call isn't very important.
- indirect call which allows optimization with binary patch
- Usually these operations correspond to low level critical instructions. They
- are called frequently and are performance critical. The overhead is
- very important.
+ Usually these operations correspond to low level critical instructions. They
+ are called frequently and are performance critical. The overhead is
+ very important.
- a set of macros for hand written assembly code
- Hand written assembly codes (.S files) also need paravirtualization
- because they include sensitive instructions or some of code paths in
- them are very performance critical.
+ Hand written assembly codes (.S files) also need paravirtualization
+ because they include sensitive instructions or some of code paths in
+ them are very performance critical.
diff --git a/MAINTAINERS b/MAINTAINERS
index 133ec3cc11ae..1be025959be9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7422,6 +7422,7 @@ F: net/vmw_vsock/hyperv_transport.c
F: include/clocksource/hyperv_timer.h
F: include/linux/hyperv.h
F: include/uapi/linux/hyperv.h
+F: include/asm-generic/mshyperv.h
F: tools/hv/
F: Documentation/ABI/stable/sysfs-bus-vmbus
@@ -11260,7 +11261,7 @@ F: include/uapi/linux/nfs*
F: include/uapi/linux/sunrpc/
NILFS2 FILESYSTEM
-M: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
+M: Ryusuke Konishi <konishi.ryusuke@gmail.com>
L: linux-nilfs@vger.kernel.org
W: https://nilfs.sourceforge.io/
W: https://nilfs.osdn.jp/
@@ -12929,7 +12930,6 @@ F: include/linux/regset.h
F: include/linux/tracehook.h
F: include/uapi/linux/ptrace.h
F: include/uapi/linux/ptrace.h
-F: include/asm-generic/ptrace.h
F: kernel/ptrace.c
F: arch/*/ptrace*.c
F: arch/*/*/ptrace*.c
@@ -17544,7 +17544,13 @@ W: http://xfs.org/
T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
S: Supported
F: Documentation/filesystems/xfs.txt
+F: Documentation/ABI/testing/sysfs-fs-xfs
+F: Documentation/filesystems/xfs.txt
+F: Documentation/filesystems/xfs-delayed-logging-design.txt
+F: Documentation/filesystems/xfs-self-describing-metadata.txt
F: fs/xfs/
+F: include/uapi/linux/dqblk_xfs.h
+F: include/uapi/linux/fsmap.h
XILINX AXI ETHERNET DRIVER
M: Anirudha Sarangi <anirudh@xilinx.com>
diff --git a/Makefile b/Makefile
index 3e4868a6498b..2c5d00ba537e 100644
--- a/Makefile
+++ b/Makefile
@@ -212,6 +212,13 @@ endif
ifdef SUBDIRS
$(warning ================= WARNING ================)
$(warning 'SUBDIRS' will be removed after Linux 5.3)
+ $(warning )
+ $(warning If you are building an individual subdirectory)
+ $(warning in the kernel tree, you can do like this:)
+ $(warning $$ make path/to/dir/you/want/to/build/)
+ $(warning (Do not forget the trailing slash))
+ $(warning )
+ $(warning If you are building an external module,)
$(warning Please use 'M=' or 'KBUILD_EXTMOD' instead)
$(warning ==========================================)
KBUILD_EXTMOD ?= $(SUBDIRS)
@@ -221,9 +228,12 @@ ifeq ("$(origin M)", "command line")
KBUILD_EXTMOD := $(M)
endif
+export KBUILD_CHECKSRC KBUILD_EXTMOD
+
ifeq ($(abs_srctree),$(abs_objtree))
# building in the source tree
srctree := .
+ building_out_of_srctree :=
else
ifeq ($(abs_srctree)/,$(dir $(abs_objtree)))
# building in a subdirectory of the source tree
@@ -231,22 +241,17 @@ else
else
srctree := $(abs_srctree)
endif
-
- # TODO:
- # KBUILD_SRC is only used to distinguish in-tree/out-of-tree build.
- # Replace it with $(srctree) or something.
- KBUILD_SRC := $(abs_srctree)
+ building_out_of_srctree := 1
endif
-export KBUILD_CHECKSRC KBUILD_EXTMOD KBUILD_SRC
+ifneq ($(KBUILD_ABS_SRCTREE),)
+srctree := $(abs_srctree)
+endif
objtree := .
-src := $(srctree)
-obj := $(objtree)
-
VPATH := $(srctree)
-export srctree objtree VPATH
+export building_out_of_srctree srctree objtree VPATH
# To make sure we do not include .config for any of the *config targets
# catch them early, and hand them over to scripts/kconfig/Makefile
@@ -262,7 +267,7 @@ old_version_h := include/linux/version.h
clean-targets := %clean mrproper cleandocs
no-dot-config-targets := $(clean-targets) \
cscope gtags TAGS tags help% %docs check% coccicheck \
- $(version_h) headers_% archheaders archscripts \
+ $(version_h) headers headers_% archheaders archscripts \
%asm-generic kernelversion %src-pkg
no-sync-config-targets := $(no-dot-config-targets) install %install \
kernelrelease
@@ -449,7 +454,7 @@ USERINCLUDE := \
LINUXINCLUDE := \
-I$(srctree)/arch/$(SRCARCH)/include \
-I$(objtree)/arch/$(SRCARCH)/include/generated \
- $(if $(filter .,$(srctree)),,-I$(srctree)/include) \
+ $(if $(building_out_of_srctree),-I$(srctree)/include) \
-I$(objtree)/include \
$(USERINCLUDE)
@@ -510,7 +515,7 @@ PHONY += outputmakefile
# At the same time when output Makefile generated, generate .gitignore to
# ignore whole output directory
outputmakefile:
-ifneq ($(srctree),.)
+ifdef building_out_of_srctree
$(Q)ln -fsn $(srctree) source
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkmakefile $(srctree)
$(Q)test -e .gitignore || \
@@ -527,7 +532,10 @@ endif
ifneq ($(GCC_TOOLCHAIN),)
CLANG_FLAGS += --gcc-toolchain=$(GCC_TOOLCHAIN)
endif
+ifeq ($(shell $(AS) --version 2>&1 | head -n 1 | grep clang),)
CLANG_FLAGS += -no-integrated-as
+endif
+CLANG_FLAGS += -Werror=unknown-warning-option
KBUILD_CFLAGS += $(CLANG_FLAGS)
KBUILD_AFLAGS += $(CLANG_FLAGS)
export CLANG_FLAGS
@@ -608,6 +616,7 @@ ifeq ($(KBUILD_EXTMOD),)
init-y := init/
drivers-y := drivers/ sound/
drivers-$(CONFIG_SAMPLES) += samples/
+drivers-$(CONFIG_KERNEL_HEADER_TEST) += include/
net-y := net/
libs-y := lib/
core-y := usr/
@@ -1053,9 +1062,6 @@ vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) FORCE
targets := vmlinux
-# Some samples need headers_install.
-samples: headers_install
-
# The actual objects are generated when descending,
# make sure no implicit rule kicks in
$(sort $(vmlinux-deps)): $(vmlinux-dirs) ;
@@ -1096,12 +1102,12 @@ PHONY += prepare archprepare prepare1 prepare3
# and if so do:
# 1) Check that make has not been executed in the kernel src $(srctree)
prepare3: include/config/kernel.release
-ifneq ($(srctree),.)
+ifdef building_out_of_srctree
@$(kecho) ' Using $(srctree) as source for kernel'
$(Q)if [ -f $(srctree)/.config -o \
-d $(srctree)/include/config -o \
-d $(srctree)/arch/$(SRCARCH)/include/generated ]; then \
- echo >&2 " $(srctree) is not clean, please run 'make mrproper'"; \
+ echo >&2 " $(srctree) is not clean, please run 'make ARCH=$(ARCH) mrproper'"; \
echo >&2 " in the '$(srctree)' directory.";\
/bin/false; \
fi;
@@ -1181,39 +1187,44 @@ headerdep:
#Default location for installed headers
export INSTALL_HDR_PATH = $(objtree)/usr
-# If we do an all arch process set dst to include/arch-$(SRCARCH)
-hdr-dst = $(if $(KBUILD_HEADERS), dst=include/arch-$(SRCARCH), dst=include)
+quiet_cmd_headers_install = INSTALL $(INSTALL_HDR_PATH)/include
+ cmd_headers_install = \
+ mkdir -p $(INSTALL_HDR_PATH); \
+ rsync -mrl --include='*/' --include='*\.h' --exclude='*' \
+ usr/include $(INSTALL_HDR_PATH)
-PHONY += archheaders archscripts
+PHONY += headers_install
+headers_install: headers
+ $(call cmd,headers_install)
-PHONY += __headers
-__headers: $(version_h) scripts_basic uapi-asm-generic archheaders archscripts
- $(Q)$(MAKE) $(build)=scripts build_unifdef
+PHONY += archheaders archscripts
-PHONY += headers_install_all
-headers_install_all:
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/headers.sh install
+hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
-PHONY += headers_install
-headers_install: __headers
+PHONY += headers
+headers: $(version_h) scripts_unifdef uapi-asm-generic archheaders archscripts
$(if $(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/Kbuild),, \
$(error Headers not exportable for the $(SRCARCH) architecture))
- $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include
- $(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi $(hdr-dst)
-
-PHONY += headers_check_all
-headers_check_all: headers_install_all
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/headers.sh check
+ $(Q)$(MAKE) $(hdr-inst)=include/uapi
+ $(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
PHONY += headers_check
-headers_check: headers_install
- $(Q)$(MAKE) $(hdr-inst)=include/uapi dst=include HDRCHECK=1
- $(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi $(hdr-dst) HDRCHECK=1
+headers_check: headers
+ $(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1
+ $(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi HDRCHECK=1
+
+ifdef CONFIG_HEADERS_INSTALL
+prepare: headers
+endif
ifdef CONFIG_HEADERS_CHECK
all: headers_check
endif
+PHONY += scripts_unifdef
+scripts_unifdef: scripts_basic
+ $(Q)$(MAKE) $(build)=scripts scripts/unifdef
+
# ---------------------------------------------------------------------------
# Kernel selftest
@@ -1283,18 +1294,24 @@ all: modules
# using awk while concatenating to the final file.
PHONY += modules
-modules: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) modules.builtin
- $(Q)$(AWK) '!x[$$0]++' $(vmlinux-dirs:%=$(objtree)/%/modules.order) > $(objtree)/modules.order
+modules: $(if $(KBUILD_BUILTIN),vmlinux) modules.order modules.builtin
@$(kecho) ' Building modules, stage 2.';
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/modules-check.sh
-modules.builtin: $(vmlinux-dirs:%=%/modules.builtin)
- $(Q)$(AWK) '!x[$$0]++' $^ > $(objtree)/modules.builtin
+modules.order: $(vmlinux-dirs)
+ $(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(vmlinux-dirs)) > $@
+
+modbuiltin-dirs := $(addprefix _modbuiltin_, $(vmlinux-dirs))
-%/modules.builtin: include/config/auto.conf include/config/tristate.conf
- $(Q)$(MAKE) $(modbuiltin)=$*
+modules.builtin: $(modbuiltin-dirs)
+ $(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(vmlinux-dirs)) > $@
+PHONY += $(modbuiltin-dirs)
+# tristate.conf is not included from this Makefile. Add it as a prerequisite
+# here to make it self-healing in case somebody accidentally removes it.
+$(modbuiltin-dirs): include/config/tristate.conf
+ $(Q)$(MAKE) $(modbuiltin)=$(patsubst _modbuiltin_%,%,$@)
# Target to prepare building external modules
PHONY += modules_prepare
@@ -1360,7 +1377,7 @@ CLEAN_DIRS += $(MODVERDIR) include/ksym
CLEAN_FILES += modules.builtin.modinfo
# Directories & files removed with 'make mrproper'
-MRPROPER_DIRS += include/config usr/include include/generated \
+MRPROPER_DIRS += include/config include/generated \
arch/$(SRCARCH)/include/generated .tmp_objdiff
MRPROPER_FILES += .config .config.old .version \
Module.symvers tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS \
@@ -1551,7 +1568,7 @@ $(DOC_TARGETS): scripts_basic FORCE
# ---------------------------------------------------------------------------
PHONY += scripts_gdb
-scripts_gdb: prepare
+scripts_gdb: prepare0
$(Q)$(MAKE) $(build)=scripts/gdb
$(Q)ln -fsn $(abspath $(srctree)/scripts/gdb/vmlinux-gdb.py)
@@ -1698,7 +1715,7 @@ CHECKSTACK_ARCH := $(ARCH)
endif
checkstack:
$(OBJDUMP) -d vmlinux $$(find . -name '*.ko') | \
- $(PERL) $(src)/scripts/checkstack.pl $(CHECKSTACK_ARCH)
+ $(PERL) $(srctree)/scripts/checkstack.pl $(CHECKSTACK_ARCH)
kernelrelease:
@echo "$(KERNELVERSION)$$($(CONFIG_SHELL) $(srctree)/scripts/setlocalversion $(srctree))"
@@ -1717,11 +1734,11 @@ endif
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(src)/tools/
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(src)/tools/ $*
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------
@@ -1755,8 +1772,6 @@ build-dir = $(patsubst %/,%,$(dir $(build-target)))
PHONY += /
/: ./
-# Make sure the latest headers are built for Documentation
-Documentation/ samples/: headers_install
%/: prepare FORCE
$(Q)$(MAKE) KBUILD_MODULES=1 $(build)=$(build-dir)
diff --git a/arch/Kconfig b/arch/Kconfig
index c47b328eada0..e8d19c3cb91f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -260,6 +260,14 @@ config ARCH_HAS_SET_MEMORY
config ARCH_HAS_SET_DIRECT_MAP
bool
+#
+# Select if arch has an uncached kernel segment and provides the
+# uncached_kernel_address / cached_kernel_address symbols to use it
+#
+config ARCH_HAS_UNCACHED_SEGMENT
+ select ARCH_HAS_DMA_PREP_COHERENT
+ bool
+
# Select if arch init_task must go in the __init_task_data section
config ARCH_TASK_STRUCT_ON_STACK
bool
diff --git a/arch/alpha/Makefile b/arch/alpha/Makefile
index b3314e0dcb6f..12dee59b011c 100644
--- a/arch/alpha/Makefile
+++ b/arch/alpha/Makefile
@@ -8,8 +8,6 @@
# Copyright (C) 1994 by Linus Torvalds
#
-KBUILD_DEFCONFIG := defconfig
-
NM := $(NM) -B
LDFLAGS_vmlinux := -static -N #-relax
diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h
index 02f9f91bb4f0..71ded3b7d82d 100644
--- a/arch/alpha/include/asm/pgalloc.h
+++ b/arch/alpha/include/asm/pgalloc.h
@@ -5,6 +5,8 @@
#include <linux/mm.h>
#include <linux/mmzone.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
/*
* Allocate and free page tables. The xxx_kernel() versions are
* used to allocate a kernel page table - this turns on ASN bits
@@ -41,7 +43,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd)
static inline pmd_t *
pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
- pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+ pmd_t *ret = (pmd_t *)__get_free_page(GFP_PGTABLE_USER);
return ret;
}
@@ -51,42 +53,6 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd)
free_page((unsigned long)pmd);
}
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm)
-{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
- return pte;
-}
-
-static inline void
-pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long)pte);
-}
-
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm)
-{
- pte_t *pte = pte_alloc_one_kernel(mm);
- struct page *page;
-
- if (!pte)
- return NULL;
- page = virt_to_page(pte);
- if (!pgtable_page_ctor(page)) {
- __free_page(page);
- return NULL;
- }
- return page;
-}
-
-static inline void
-pte_free(struct mm_struct *mm, pgtable_t page)
-{
- pgtable_page_dtor(page);
- __free_page(page);
-}
-
#define check_pgt_cache() do { } while (0)
#endif /* _ALPHA_PGALLOC_H */
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 1c8137e7247b..8383155c8c82 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -7,6 +7,7 @@ config ARC
def_bool y
select ARC_TIMERS
select ARCH_HAS_DMA_COHERENT_TO_PFN
+ select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SETUP_DMA_OPS
select ARCH_HAS_SYNC_DMA_FOR_CPU
@@ -16,6 +17,7 @@ config ARC
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_DIRECT_REMAP
select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC)
select GENERIC_CLOCKEVENTS
select GENERIC_FIND_FIRST_BIT
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 03a0b19c92cd..ee6d1184c2b1 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -19,7 +19,7 @@ ifdef CONFIG_ARC_CURR_IN_REG
# any kernel headers, and missing the r25 global register
# Can't do unconditionally because of recursive include issues
# due to <linux/thread_info.h>
-LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h
+LINUXINCLUDE += -include $(srctree)/arch/arc/include/asm/current.h
endif
cflags-y += -fsection-anchors
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 5b5119d2b5d5..dc739bd093e3 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -94,6 +94,7 @@ CONFIG_CONFIGFS_FS=y
CONFIG_DEBUG_INFO=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 0bf1468c35a3..62c210e7ee4c 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -8,51 +8,15 @@
#include <asm/cacheflush.h>
/*
- * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c)
+ * ARCH specific callbacks for generic noncoherent DMA ops
* - hardware IOC not available (or "dma-coherent" not set for device in DT)
* - But still handle both coherent and non-coherent requests from caller
*
* For DMA coherent hardware (IOC) generic code suffices
*/
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
-{
- unsigned long order = get_order(size);
- struct page *page;
- phys_addr_t paddr;
- void *kvaddr;
- bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT);
-
- /*
- * __GFP_HIGHMEM flag is cleared by upper layer functions
- * (in include/linux/dma-mapping.h) so we should never get a
- * __GFP_HIGHMEM here.
- */
- BUG_ON(gfp & __GFP_HIGHMEM);
-
- page = alloc_pages(gfp | __GFP_ZERO, order);
- if (!page)
- return NULL;
-
- /* This is linear addr (0x8000_0000 based) */
- paddr = page_to_phys(page);
-
- *dma_handle = paddr;
-
- /*
- * A coherent buffer needs MMU mapping to enforce non-cachability.
- * kvaddr is kernel Virtual address (0x7000_0000 based).
- */
- if (need_coh) {
- kvaddr = ioremap_nocache(paddr, size);
- if (kvaddr == NULL) {
- __free_pages(page, order);
- return NULL;
- }
- } else {
- kvaddr = (void *)(u32)paddr;
- }
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
/*
* Evict any existing L1 and/or L2 lines for the backing page
* in case it was used earlier as a normal "cached" page.
@@ -63,28 +27,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
* Currently flush_cache_vmap nukes the L1 cache completely which
* will be optimized as a separate commit
*/
- if (need_coh)
- dma_cache_wback_inv(paddr, size);
-
- return kvaddr;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- phys_addr_t paddr = dma_handle;
- struct page *page = virt_to_page(paddr);
-
- if (!(attrs & DMA_ATTR_NON_CONSISTENT))
- iounmap((void __force __iomem *)vaddr);
-
- __free_pages(page, get_order(size));
-}
-
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr)
-{
- return __phys_to_pfn(dma_addr);
+ dma_cache_wback_inv(page_to_phys(page), size);
}
/*
@@ -161,3 +104,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
dev_info(dev, "use %sncoherent DMA ops\n",
dev->dma_coherent ? "" : "non");
}
+
+static int __init atomic_pool_init(void)
+{
+ return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL));
+}
+postcore_initcall(atomic_pool_init);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d850feb5cc0a..2bf1ce39a96d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -75,6 +75,7 @@ config ARM
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP if ARM_LPAE
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
@@ -1622,16 +1623,9 @@ config ARCH_SPARSEMEM_ENABLE
config ARCH_SPARSEMEM_DEFAULT
def_bool ARCH_SPARSEMEM_ENABLE
-config ARCH_SELECT_MEMORY_MODEL
- def_bool ARCH_SPARSEMEM_ENABLE
-
config HAVE_ARCH_PFN_VALID
def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
-config HAVE_GENERIC_GUP
- def_bool y
- depends on ARM_LPAE
-
config HIGHMEM
bool "High Memory Support"
depends on MMU
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 6b7644a383f6..40002416efec 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -271,6 +271,16 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
return vcpu_cp15(vcpu, c0_MPIDR) & MPIDR_HWID_BITMASK;
}
+static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
+static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
+ bool flag)
+{
+}
+
static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
{
*vcpu_cpsr(vcpu) |= PSR_E_BIT;
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index f80418ddeb60..8a37c8e89777 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -15,7 +15,6 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_mmio.h>
#include <asm/fpstate.h>
-#include <asm/smp_plat.h>
#include <kvm/arm_arch_timer.h>
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -147,11 +146,10 @@ struct kvm_host_data {
typedef struct kvm_host_data kvm_host_data_t;
-static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt,
- int cpu)
+static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
{
/* The host's MPIDR is immutable, so let's set it up at boot time */
- cpu_ctxt->cp15[c0_MPIDR] = cpu_logical_map(cpu);
+ cpu_ctxt->cp15[c0_MPIDR] = read_cpuid_mpidr();
}
struct vcpu_reset_state {
@@ -362,7 +360,11 @@ static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
static inline void kvm_arm_vhe_guest_enter(void) {}
static inline void kvm_arm_vhe_guest_exit(void) {}
-static inline bool kvm_arm_harden_branch_predictor(void)
+#define KVM_BP_HARDEN_UNKNOWN -1
+#define KVM_BP_HARDEN_WA_NEEDED 0
+#define KVM_BP_HARDEN_NOT_REQUIRED 1
+
+static inline int kvm_arm_harden_branch_predictor(void)
{
switch(read_cpuid_part()) {
#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
@@ -370,10 +372,12 @@ static inline bool kvm_arm_harden_branch_predictor(void)
case ARM_CPU_PART_CORTEX_A12:
case ARM_CPU_PART_CORTEX_A15:
case ARM_CPU_PART_CORTEX_A17:
- return true;
+ return KVM_BP_HARDEN_WA_NEEDED;
#endif
+ case ARM_CPU_PART_CORTEX_A7:
+ return KVM_BP_HARDEN_NOT_REQUIRED;
default:
- return false;
+ return KVM_BP_HARDEN_UNKNOWN;
}
}
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index 71ac1c8d101c..40e9034db601 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -82,13 +82,14 @@
#define VFP_FPEXC __ACCESS_VFP(FPEXC)
/* AArch64 compatibility macros, only for the timer so far */
-#define read_sysreg_el0(r) read_sysreg(r##_el0)
-#define write_sysreg_el0(v, r) write_sysreg(v, r##_el0)
+#define read_sysreg_el0(r) read_sysreg(r##_EL0)
+#define write_sysreg_el0(v, r) write_sysreg(v, r##_EL0)
+
+#define SYS_CNTP_CTL_EL0 CNTP_CTL
+#define SYS_CNTP_CVAL_EL0 CNTP_CVAL
+#define SYS_CNTV_CTL_EL0 CNTV_CTL
+#define SYS_CNTV_CVAL_EL0 CNTV_CVAL
-#define cntp_ctl_el0 CNTP_CTL
-#define cntp_cval_el0 CNTP_CVAL
-#define cntv_ctl_el0 CNTV_CTL
-#define cntv_cval_el0 CNTV_CVAL
#define cntvoff_el2 CNTVOFF
#define cnthctl_el2 CNTHCTL
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index c038cff6fdd3..a2a68b751971 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -54,8 +54,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
extern pgd_t *pgd_alloc(struct mm_struct *mm);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
-
static inline void clean_pte_table(pte_t *pte)
{
clean_dcache_area(pte + PTE_HWTABLE_PTRS, PTE_HWTABLE_SIZE);
@@ -77,54 +75,41 @@ static inline void clean_pte_table(pte_t *pte)
* | h/w pt 1 |
* +------------+
*/
+
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+#define __HAVE_ARCH_PTE_ALLOC_ONE
+#include <asm-generic/pgalloc.h>
+
static inline pte_t *
pte_alloc_one_kernel(struct mm_struct *mm)
{
- pte_t *pte;
+ pte_t *pte = __pte_alloc_one_kernel(mm);
- pte = (pte_t *)__get_free_page(PGALLOC_GFP);
if (pte)
clean_pte_table(pte);
return pte;
}
+#ifdef CONFIG_HIGHPTE
+#define PGTABLE_HIGHMEM __GFP_HIGHMEM
+#else
+#define PGTABLE_HIGHMEM 0
+#endif
+
static inline pgtable_t
pte_alloc_one(struct mm_struct *mm)
{
struct page *pte;
-#ifdef CONFIG_HIGHPTE
- pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
-#else
- pte = alloc_pages(PGALLOC_GFP, 0);
-#endif
+ pte = __pte_alloc_one(mm, GFP_PGTABLE_USER | PGTABLE_HIGHMEM);
if (!pte)
return NULL;
if (!PageHighMem(pte))
clean_pte_table(page_address(pte));
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
return pte;
}
-/*
- * Free one PTE table.
- */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- if (pte)
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
pmdval_t prot)
{
diff --git a/arch/arm/include/asm/ptdump.h b/arch/arm/include/asm/ptdump.h
index 3ebf9718288d..0c2d3d0d4cc6 100644
--- a/arch/arm/include/asm/ptdump.h
+++ b/arch/arm/include/asm/ptdump.h
@@ -21,13 +21,10 @@ struct ptdump_info {
void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
#ifdef CONFIG_ARM_PTDUMP_DEBUGFS
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name);
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name);
#else
-static inline int ptdump_debugfs_register(struct ptdump_info *info,
- const char *name)
-{
- return 0;
-}
+static inline void ptdump_debugfs_register(struct ptdump_info *info,
+ const char *name) { }
#endif /* CONFIG_ARM_PTDUMP_DEBUGFS */
void ptdump_check_wx(void);
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 4602464ebdfb..a4217c1a5d01 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -214,6 +214,18 @@ struct kvm_vcpu_events {
#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
KVM_REG_ARM_FW | ((r) & 0xffff))
#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c
index ed005870671a..e57dbcc89123 100644
--- a/arch/arm/kernel/efi.c
+++ b/arch/arm/kernel/efi.c
@@ -8,8 +8,7 @@
#include <asm/mach/map.h>
#include <asm/mmu_context.h>
-static int __init set_permissions(pte_t *ptep, pgtable_t token,
- unsigned long addr, void *data)
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
{
efi_memory_desc_t *md = data;
pte_t pte = *ptep;
diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c
index 406fd2a9a88f..bd5be82101f3 100644
--- a/arch/arm/mach-omap1/clock.c
+++ b/arch/arm/mach-omap1/clock.c
@@ -987,84 +987,44 @@ static int debug_clock_show(struct seq_file *s, void *unused)
DEFINE_SHOW_ATTRIBUTE(debug_clock);
-static int clk_debugfs_register_one(struct clk *c)
+static void clk_debugfs_register_one(struct clk *c)
{
- int err;
struct dentry *d;
struct clk *pa = c->parent;
d = debugfs_create_dir(c->name, pa ? pa->dent : clk_debugfs_root);
- if (!d)
- return -ENOMEM;
c->dent = d;
- d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount);
- if (!d) {
- err = -ENOMEM;
- goto err_out;
- }
- d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate);
- if (!d) {
- err = -ENOMEM;
- goto err_out;
- }
- d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags);
- if (!d) {
- err = -ENOMEM;
- goto err_out;
- }
- return 0;
-
-err_out:
- debugfs_remove_recursive(c->dent);
- return err;
+ debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount);
+ debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate);
+ debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags);
}
-static int clk_debugfs_register(struct clk *c)
+static void clk_debugfs_register(struct clk *c)
{
- int err;
struct clk *pa = c->parent;
- if (pa && !pa->dent) {
- err = clk_debugfs_register(pa);
- if (err)
- return err;
- }
+ if (pa && !pa->dent)
+ clk_debugfs_register(pa);
- if (!c->dent) {
- err = clk_debugfs_register_one(c);
- if (err)
- return err;
- }
- return 0;
+ if (!c->dent)
+ clk_debugfs_register_one(c);
}
static int __init clk_debugfs_init(void)
{
struct clk *c;
struct dentry *d;
- int err;
d = debugfs_create_dir("clock", NULL);
- if (!d)
- return -ENOMEM;
clk_debugfs_root = d;
- list_for_each_entry(c, &clocks, node) {
- err = clk_debugfs_register(c);
- if (err)
- goto err_out;
- }
+ list_for_each_entry(c, &clocks, node)
+ clk_debugfs_register(c);
- d = debugfs_create_file("summary", S_IRUGO,
- d, NULL, &debug_clock_fops);
- if (!d)
- return -ENOMEM;
+ debugfs_create_file("summary", S_IRUGO, d, NULL, &debug_clock_fops);
return 0;
-err_out:
- debugfs_remove_recursive(clk_debugfs_root);
- return err;
}
late_initcall(clk_debugfs_init);
diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c
index 998075d3ef86..d068958d6f8a 100644
--- a/arch/arm/mach-omap1/pm.c
+++ b/arch/arm/mach-omap1/pm.c
@@ -539,11 +539,8 @@ static void omap_pm_init_debugfs(void)
struct dentry *d;
d = debugfs_create_dir("pm_debug", NULL);
- if (!d)
- return;
-
- (void) debugfs_create_file("omap_pm", S_IWUSR | S_IRUGO,
- d, NULL, &omap_pm_debug_fops);
+ debugfs_create_file("omap_pm", S_IWUSR | S_IRUGO, d, NULL,
+ &omap_pm_debug_fops);
}
#endif /* CONFIG_DEBUG_FS */
diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c
index fe6ec9b580b9..fceb1e525d26 100644
--- a/arch/arm/mach-omap2/pm-debug.c
+++ b/arch/arm/mach-omap2/pm-debug.c
@@ -190,9 +190,8 @@ static int __init pwrdms_setup(struct powerdomain *pwrdm, void *dir)
return 0;
d = debugfs_create_dir(pwrdm->name, (struct dentry *)dir);
- if (d)
- (void) debugfs_create_file("suspend", S_IRUGO|S_IWUSR, d,
- (void *)pwrdm, &pwrdm_suspend_fops);
+ debugfs_create_file("suspend", S_IRUGO|S_IWUSR, d, pwrdm,
+ &pwrdm_suspend_fops);
return 0;
}
@@ -230,16 +229,14 @@ static int __init pm_dbg_init(void)
return 0;
d = debugfs_create_dir("pm_debug", NULL);
- if (!d)
- return -EINVAL;
- (void) debugfs_create_file("count", 0444, d, NULL, &pm_dbg_counters_fops);
- (void) debugfs_create_file("time", 0444, d, NULL, &pm_dbg_timers_fops);
+ debugfs_create_file("count", 0444, d, NULL, &pm_dbg_counters_fops);
+ debugfs_create_file("time", 0444, d, NULL, &pm_dbg_timers_fops);
pwrdm_for_each(pwrdms_setup, (void *)d);
- (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d,
- &enable_off_mode, &pm_dbg_option_fops);
+ debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d,
+ &enable_off_mode, &pm_dbg_option_fops);
pm_dbg_init_done = 1;
return 0;
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 1aea01ba1262..52b82559d99b 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -35,18 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
unsigned long attrs)
{
- void *ret;
-
- /*
- * Try generic allocator first if we are advertised that
- * consistency is not required.
- */
-
- if (attrs & DMA_ATTR_NON_CONSISTENT)
- return dma_direct_alloc_pages(dev, size, dma_handle, gfp,
- attrs);
-
- ret = dma_alloc_from_global_coherent(size, dma_handle);
+ void *ret = dma_alloc_from_global_coherent(size, dma_handle);
/*
* dma_alloc_from_global_coherent() may fail because:
@@ -66,16 +55,9 @@ static void arm_nommu_dma_free(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_addr,
unsigned long attrs)
{
- if (attrs & DMA_ATTR_NON_CONSISTENT) {
- dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
- } else {
- int ret = dma_release_from_global_coherent(get_order(size),
- cpu_addr);
-
- WARN_ON_ONCE(ret == 0);
- }
+ int ret = dma_release_from_global_coherent(get_order(size), cpu_addr);
- return;
+ WARN_ON_ONCE(ret == 0);
}
static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 439bb6a59a04..4789c60a86e3 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -216,25 +216,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops);
static int __dma_supported(struct device *dev, u64 mask, bool warn)
{
- unsigned long max_dma_pfn;
-
- /*
- * If the mask allows for more memory than we can address,
- * and we actually have that much memory, then we must
- * indicate that DMA to this device is not supported.
- */
- if (sizeof(mask) != sizeof(dma_addr_t) &&
- mask > (dma_addr_t)~0 &&
- dma_to_pfn(dev, ~0) < max_pfn - 1) {
- if (warn) {
- dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
- mask);
- dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
- }
- return 0;
- }
-
- max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+ unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
/*
* Translate the device's DMA mask to a PFN limit. This
@@ -493,8 +475,7 @@ void __init dma_contiguous_remap(void)
}
}
-static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
- void *data)
+static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data)
{
struct page *page = virt_to_page(addr);
pgprot_t prot = *(pgprot_t *)data;
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 006d27ee4fc6..7d6291f23251 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -446,7 +446,7 @@ void ptdump_check_wx(void)
static int ptdump_init(void)
{
ptdump_initialize();
- return ptdump_debugfs_register(&kernel_ptdump_info,
- "kernel_page_tables");
+ ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
+ return 0;
}
__initcall(ptdump_init);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 1aa2586fa597..d9a0038774a6 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -729,7 +729,7 @@ static void __init *early_alloc(unsigned long sz)
static void *__init late_alloc(unsigned long sz)
{
- void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
+ void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz));
if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
BUG();
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index 0f5faf30d9bf..d546efad7e97 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -14,8 +14,7 @@ struct page_change_data {
pgprot_t clear_mask;
};
-static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
- void *data)
+static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
{
struct page_change_data *cdata = data;
pte_t pte = *ptep;
diff --git a/arch/arm/mm/ptdump_debugfs.c b/arch/arm/mm/ptdump_debugfs.c
index be8d87be4b93..598b636615a2 100644
--- a/arch/arm/mm/ptdump_debugfs.c
+++ b/arch/arm/mm/ptdump_debugfs.c
@@ -24,11 +24,7 @@ static const struct file_operations ptdump_fops = {
.release = single_release,
};
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name)
{
- struct dentry *pe;
-
- pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
- return pe ? 0 : -ENOMEM;
-
+ debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c085aec9459b..a36ff61321ce 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -143,6 +143,7 @@ config ARM64
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
@@ -267,9 +268,6 @@ config ZONE_DMA32
bool "Support DMA32 zone" if EXPERT
default y
-config HAVE_GENERIC_GUP
- def_bool y
-
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index e3d3fd0a4268..bb1f1dbb34e8 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -30,8 +30,6 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419
endif
endif
-KBUILD_DEFCONFIG := defconfig
-
# Check for binutils support for specific extensions
lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 570d195a184d..e3a15c751b13 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -96,7 +96,11 @@
* RAS Error Synchronization barrier
*/
.macro esb
+#ifdef CONFIG_ARM64_RAS_EXTN
hint #16
+#else
+ nop
+#endif
.endm
/*
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 3d8db50d9ae2..407e2bf23676 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -620,6 +620,12 @@ static inline bool system_has_prio_mask_debugging(void)
system_uses_irq_prio_masking();
}
+#define ARM64_BP_HARDEN_UNKNOWN -1
+#define ARM64_BP_HARDEN_WA_NEEDED 0
+#define ARM64_BP_HARDEN_NOT_REQUIRED 1
+
+int get_spectre_v2_workaround_state(void);
+
#define ARM64_SSBD_UNKNOWN -1
#define ARM64_SSBD_FORCE_DISABLE 0
#define ARM64_SSBD_KERNEL 1
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 2ca437ef59fa..44a243754c1b 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -30,6 +30,12 @@
{ARM_EXCEPTION_TRAP, "TRAP" }, \
{ARM_EXCEPTION_HYP_GONE, "HYP_GONE" }
+/*
+ * Size of the HYP vectors preamble. kvm_patch_vector_branch() generates code
+ * that jumps over this.
+ */
+#define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE)
+
#ifndef __ASSEMBLY__
#include <linux/mm.h>
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 034dadec7168..d69c1efc63e7 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -126,7 +126,7 @@ static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu)
static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
{
if (vcpu->arch.sysregs_loaded_on_cpu)
- return read_sysreg_el1(elr);
+ return read_sysreg_el1(SYS_ELR);
else
return *__vcpu_elr_el1(vcpu);
}
@@ -134,7 +134,7 @@ static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu)
static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v)
{
if (vcpu->arch.sysregs_loaded_on_cpu)
- write_sysreg_el1(v, elr);
+ write_sysreg_el1(v, SYS_ELR);
else
*__vcpu_elr_el1(vcpu) = v;
}
@@ -186,7 +186,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
return vcpu_read_spsr32(vcpu);
if (vcpu->arch.sysregs_loaded_on_cpu)
- return read_sysreg_el1(spsr);
+ return read_sysreg_el1(SYS_SPSR);
else
return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
}
@@ -199,7 +199,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
}
if (vcpu->arch.sysregs_loaded_on_cpu)
- write_sysreg_el1(v, spsr);
+ write_sysreg_el1(v, SYS_SPSR);
else
vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
}
@@ -353,6 +353,20 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
}
+static inline bool kvm_arm_get_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG;
+}
+
+static inline void kvm_arm_set_vcpu_workaround_2_flag(struct kvm_vcpu *vcpu,
+ bool flag)
+{
+ if (flag)
+ vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
+ else
+ vcpu->arch.workaround_flags &= ~VCPU_WORKAROUND_2_FLAG;
+}
+
static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
{
if (vcpu_mode_is_32bit(vcpu)) {
@@ -451,13 +465,13 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
*/
static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu)
{
- *vcpu_pc(vcpu) = read_sysreg_el2(elr);
- vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr);
+ *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+ vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
- write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr);
- write_sysreg_el2(*vcpu_pc(vcpu), elr);
+ write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR);
+ write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
}
#endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 9f19c354b165..f656169db8c3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -19,12 +19,12 @@
#include <asm/arch_gicv3.h>
#include <asm/barrier.h>
#include <asm/cpufeature.h>
+#include <asm/cputype.h>
#include <asm/daifflags.h>
#include <asm/fpsimd.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmio.h>
-#include <asm/smp_plat.h>
#include <asm/thread_info.h>
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -484,11 +484,10 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data);
-static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt,
- int cpu)
+static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
{
/* The host's MPIDR is immutable, so let's set it up at boot time */
- cpu_ctxt->sys_regs[MPIDR_EL1] = cpu_logical_map(cpu);
+ cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr();
}
void __kvm_enable_ssbs(void);
@@ -621,9 +620,21 @@ static inline void kvm_arm_vhe_guest_exit(void)
isb();
}
-static inline bool kvm_arm_harden_branch_predictor(void)
+#define KVM_BP_HARDEN_UNKNOWN -1
+#define KVM_BP_HARDEN_WA_NEEDED 0
+#define KVM_BP_HARDEN_NOT_REQUIRED 1
+
+static inline int kvm_arm_harden_branch_predictor(void)
{
- return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
+ switch (get_spectre_v2_workaround_state()) {
+ case ARM64_BP_HARDEN_WA_NEEDED:
+ return KVM_BP_HARDEN_WA_NEEDED;
+ case ARM64_BP_HARDEN_NOT_REQUIRED:
+ return KVM_BP_HARDEN_NOT_REQUIRED;
+ case ARM64_BP_HARDEN_UNKNOWN:
+ default:
+ return KVM_BP_HARDEN_UNKNOWN;
+ }
}
#define KVM_SSBD_UNKNOWN -1
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 286f7e7e1be4..86825aa20852 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -18,7 +18,7 @@
#define read_sysreg_elx(r,nvh,vh) \
({ \
u64 reg; \
- asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
+ asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh), \
__mrs_s("%0", r##vh), \
ARM64_HAS_VIRT_HOST_EXTN) \
: "=r" (reg)); \
@@ -28,7 +28,7 @@
#define write_sysreg_elx(v,r,nvh,vh) \
do { \
u64 __val = (u64)(v); \
- asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
+ asm volatile(ALTERNATIVE(__msr_s(r##nvh, "%x0"), \
__msr_s(r##vh, "%x0"), \
ARM64_HAS_VIRT_HOST_EXTN) \
: : "rZ" (__val)); \
@@ -37,55 +37,15 @@
/*
* Unified accessors for registers that have a different encoding
* between VHE and non-VHE. They must be specified without their "ELx"
- * encoding.
+ * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h.
*/
-#define read_sysreg_el2(r) \
- ({ \
- u64 reg; \
- asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##_EL2),\
- "mrs %0, " __stringify(r##_EL1),\
- ARM64_HAS_VIRT_HOST_EXTN) \
- : "=r" (reg)); \
- reg; \
- })
-
-#define write_sysreg_el2(v,r) \
- do { \
- u64 __val = (u64)(v); \
- asm volatile(ALTERNATIVE("msr " __stringify(r##_EL2) ", %x0",\
- "msr " __stringify(r##_EL1) ", %x0",\
- ARM64_HAS_VIRT_HOST_EXTN) \
- : : "rZ" (__val)); \
- } while (0)
#define read_sysreg_el0(r) read_sysreg_elx(r, _EL0, _EL02)
#define write_sysreg_el0(v,r) write_sysreg_elx(v, r, _EL0, _EL02)
#define read_sysreg_el1(r) read_sysreg_elx(r, _EL1, _EL12)
#define write_sysreg_el1(v,r) write_sysreg_elx(v, r, _EL1, _EL12)
-
-/* The VHE specific system registers and their encoding */
-#define sctlr_EL12 sys_reg(3, 5, 1, 0, 0)
-#define cpacr_EL12 sys_reg(3, 5, 1, 0, 2)
-#define ttbr0_EL12 sys_reg(3, 5, 2, 0, 0)
-#define ttbr1_EL12 sys_reg(3, 5, 2, 0, 1)
-#define tcr_EL12 sys_reg(3, 5, 2, 0, 2)
-#define afsr0_EL12 sys_reg(3, 5, 5, 1, 0)
-#define afsr1_EL12 sys_reg(3, 5, 5, 1, 1)
-#define esr_EL12 sys_reg(3, 5, 5, 2, 0)
-#define far_EL12 sys_reg(3, 5, 6, 0, 0)
-#define mair_EL12 sys_reg(3, 5, 10, 2, 0)
-#define amair_EL12 sys_reg(3, 5, 10, 3, 0)
-#define vbar_EL12 sys_reg(3, 5, 12, 0, 0)
-#define contextidr_EL12 sys_reg(3, 5, 13, 0, 1)
-#define cntkctl_EL12 sys_reg(3, 5, 14, 1, 0)
-#define cntp_tval_EL02 sys_reg(3, 5, 14, 2, 0)
-#define cntp_ctl_EL02 sys_reg(3, 5, 14, 2, 1)
-#define cntp_cval_EL02 sys_reg(3, 5, 14, 2, 2)
-#define cntv_tval_EL02 sys_reg(3, 5, 14, 3, 0)
-#define cntv_ctl_EL02 sys_reg(3, 5, 14, 3, 1)
-#define cntv_cval_EL02 sys_reg(3, 5, 14, 3, 2)
-#define spsr_EL12 sys_reg(3, 5, 4, 0, 0)
-#define elr_EL12 sys_reg(3, 5, 4, 0, 1)
+#define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1)
+#define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1)
/**
* hyp_alternate_select - Generates patchable code sequences that are
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index cdced518378d..14d0bc44d451 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -13,18 +13,23 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
#define check_pgt_cache() do { } while (0)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
#if CONFIG_PGTABLE_LEVELS > 2
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
+ gfp_t gfp = GFP_PGTABLE_USER;
struct page *page;
- page = alloc_page(PGALLOC_GFP);
+ if (mm == &init_mm)
+ gfp = GFP_PGTABLE_KERNEL;
+
+ page = alloc_page(gfp);
if (!page)
return NULL;
if (!pgtable_pmd_page_ctor(page)) {
@@ -61,7 +66,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pud_t *)__get_free_page(PGALLOC_GFP);
+ return (pud_t *)__get_free_page(GFP_PGTABLE_USER);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pudp)
@@ -89,42 +94,6 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
extern pgd_t *pgd_alloc(struct mm_struct *mm);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp);
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)__get_free_page(PGALLOC_GFP);
-}
-
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_pages(PGALLOC_GFP, 0);
- if (!pte)
- return NULL;
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
- return pte;
-}
-
-/*
- * Free a PTE table.
- */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep)
-{
- if (ptep)
- free_page((unsigned long)ptep);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
pmdval_t prot)
{
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 81693244f58d..b1dd039023ef 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -223,11 +223,12 @@ static inline void forget_syscall(struct pt_regs *regs)
#define fast_interrupts_enabled(regs) \
(!((regs)->pstate & PSR_F_BIT))
-#define GET_USP(regs) \
- (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
-
-#define SET_USP(ptregs, value) \
- (!compat_user_mode(regs) ? ((regs)->sp = value) : ((regs)->compat_sp = value))
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ if (compat_user_mode(regs))
+ return regs->compat_sp;
+ return regs->sp;
+}
extern int regs_query_register_offset(const char *name);
extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
@@ -326,13 +327,20 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
struct task_struct;
int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
-#define GET_IP(regs) ((unsigned long)(regs)->pc)
-#define SET_IP(regs, value) ((regs)->pc = ((u64) (value)))
-
-#define GET_FP(ptregs) ((unsigned long)(ptregs)->regs[29])
-#define SET_FP(ptregs, value) ((ptregs)->regs[29] = ((u64) (value)))
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return regs->pc;
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->pc = val;
+}
-#include <asm-generic/ptrace.h>
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return regs->regs[29];
+}
#define procedure_link_pointer(regs) ((regs)->regs[30])
@@ -342,7 +350,6 @@ static inline void procedure_link_pointer_set(struct pt_regs *regs,
procedure_link_pointer(regs) = val;
}
-#undef profile_pc
extern unsigned long profile_pc(struct pt_regs *regs);
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index d0bd4ffcf2c4..a7522fca1105 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -191,6 +191,9 @@
#define SYS_APGAKEYLO_EL1 sys_reg(3, 0, 2, 3, 0)
#define SYS_APGAKEYHI_EL1 sys_reg(3, 0, 2, 3, 1)
+#define SYS_SPSR_EL1 sys_reg(3, 0, 4, 0, 0)
+#define SYS_ELR_EL1 sys_reg(3, 0, 4, 0, 1)
+
#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
#define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0)
@@ -382,6 +385,9 @@
#define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1)
#define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2)
+#define SYS_CNTV_CTL_EL0 sys_reg(3, 3, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL0 sys_reg(3, 3, 14, 3, 2)
+
#define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0)
#define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1)
#define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0)
@@ -392,14 +398,17 @@
#define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3))
#define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
-#define SYS_PMCCFILTR_EL0 sys_reg (3, 3, 14, 15, 7)
+#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7)
#define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0)
-
#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0)
+#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0)
+#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1)
#define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1)
+#define SYS_ESR_EL2 sys_reg(3, 4, 5, 2, 0)
#define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3)
#define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0)
+#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0)
#define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1)
#define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
@@ -444,7 +453,29 @@
#define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7)
/* VHE encodings for architectural EL0/1 system registers */
+#define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0)
+#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2)
#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0)
+#define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0)
+#define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1)
+#define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2)
+#define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0)
+#define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1)
+#define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0)
+#define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1)
+#define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0)
+#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0)
+#define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0)
+#define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0)
+#define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0)
+#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1)
+#define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0)
+#define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0)
+#define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL02 sys_reg(3, 5, 14, 2, 2)
+#define SYS_CNTV_TVAL_EL02 sys_reg(3, 5, 14, 3, 0)
+#define SYS_CNTV_CTL_EL02 sys_reg(3, 5, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2)
/* Common SCTLR_ELx flags. */
#define SCTLR_ELx_DSSBS (_BITUL(44))
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index d819a3e8b552..9a507716ae2f 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -229,6 +229,16 @@ struct kvm_vcpu_events {
#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
KVM_REG_ARM_FW | ((r) & 0xffff))
#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
/* SVE registers */
#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ca11ff7bf55e..1e43ba5c79b7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -554,6 +554,17 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
static bool __hardenbp_enab = true;
static bool __spectrev2_safe = true;
+int get_spectre_v2_workaround_state(void)
+{
+ if (__spectrev2_safe)
+ return ARM64_BP_HARDEN_NOT_REQUIRED;
+
+ if (!__hardenbp_enab)
+ return ARM64_BP_HARDEN_UNKNOWN;
+
+ return ARM64_BP_HARDEN_WA_NEEDED;
+}
+
/*
* List of CPUs that do not need any Spectre-v2 mitigation at all.
*/
@@ -854,13 +865,15 @@ ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
char *buf)
{
- if (__spectrev2_safe)
+ switch (get_spectre_v2_workaround_state()) {
+ case ARM64_BP_HARDEN_NOT_REQUIRED:
return sprintf(buf, "Not affected\n");
-
- if (__hardenbp_enab)
+ case ARM64_BP_HARDEN_WA_NEEDED:
return sprintf(buf, "Mitigation: Branch predictor hardening\n");
-
- return sprintf(buf, "Vulnerable\n");
+ case ARM64_BP_HARDEN_UNKNOWN:
+ default:
+ return sprintf(buf, "Vulnerable\n");
+ }
}
ssize_t cpu_show_spec_store_bypass(struct device *dev,
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 3c33d0dd8e0e..d0cf596db82c 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -82,8 +82,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
return 0;
}
-static int __init set_permissions(pte_t *ptep, pgtable_t token,
- unsigned long addr, void *data)
+static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
{
efi_memory_desc_t *md = data;
pte_t pte = READ_ONCE(*ptep);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 7e541f947b4c..9c4bad7d7131 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -283,6 +283,11 @@ void __init setup_arch(char **cmdline_p)
setup_machine_fdt(__fdt_pointer);
+ /*
+ * Initialise the static keys early as they may be enabled by the
+ * cpufeature code and early parameters.
+ */
+ jump_label_init();
parse_early_param();
/*
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 9286ee6749e8..ea90d3bd9253 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -420,11 +420,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
void __init smp_prepare_boot_cpu(void)
{
set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
- /*
- * Initialise the static keys early as they may be enabled by the
- * cpufeature code.
- */
- jump_label_init();
cpuinfo_store_boot_cpu();
/*
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 678af745d881..8c03456dade6 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -871,6 +871,10 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
/*
* The CPU can't make progress. The exception may have
* been imprecise.
+ *
+ * Neoverse-N1 #1349291 means a non-KVM SError reported as
+ * Unrecoverable should be treated as Uncontainable. We
+ * call arm64_serror_panic() in both cases.
*/
return true;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index bd34016354ba..e5cc8d66bf53 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -6,6 +6,7 @@
#include <linux/linkage.h>
+#include <asm/alternative.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
#include <asm/fpsimdmacros.h>
@@ -52,6 +53,20 @@ ENTRY(__guest_enter)
// Store the host regs
save_callee_saved_regs x1
+ // Now the host state is stored if we have a pending RAS SError it must
+ // affect the host. If any asynchronous exception is pending we defer
+ // the guest entry. The DSB isn't necessary before v8.2 as any SError
+ // would be fatal.
+alternative_if ARM64_HAS_RAS_EXTN
+ dsb nshst
+ isb
+alternative_else_nop_endif
+ mrs x1, isr_el1
+ cbz x1, 1f
+ mov x0, #ARM_EXCEPTION_IRQ
+ ret
+
+1:
add x18, x0, #VCPU_CONTEXT
// Macro ptrauth_switch_to_guest format:
@@ -127,8 +142,8 @@ ENTRY(__guest_exit)
alternative_if ARM64_HAS_RAS_EXTN
// If we have the RAS extensions we can consume a pending error
- // without an unmask-SError and isb.
- esb
+ // without an unmask-SError and isb. The ESB-instruction consumed any
+ // pending guest error when we took the exception from the guest.
mrs_s x2, SYS_DISR_EL1
str x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)]
cbz x2, 1f
@@ -136,8 +151,16 @@ alternative_if ARM64_HAS_RAS_EXTN
orr x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT)
1: ret
alternative_else
- // If we have a pending asynchronous abort, now is the
- // time to find out. From your VAXorcist book, page 666:
+ dsb sy // Synchronize against in-flight ld/st
+ isb // Prevent an early read of side-effect free ISR
+ mrs x2, isr_el1
+ tbnz x2, #8, 2f // ISR_EL1.A
+ ret
+ nop
+2:
+alternative_endif
+ // We know we have a pending asynchronous abort, now is the
+ // time to flush it out. From your VAXorcist book, page 666:
// "Threaten me not, oh Evil one! For I speak with
// the power of DEC, and I command thee to show thyself!"
mrs x2, elr_el2
@@ -145,10 +168,7 @@ alternative_else
mrs x4, spsr_el2
mov x5, x0
- dsb sy // Synchronize against in-flight ld/st
- nop
msr daifclr, #4 // Unmask aborts
-alternative_endif
// This is our single instruction exception window. A pending
// SError is guaranteed to occur at the earliest when we unmask
@@ -161,6 +181,8 @@ abort_guest_exit_start:
.global abort_guest_exit_end
abort_guest_exit_end:
+ msr daifset, #4 // Mask aborts
+
// If the exception took place, restore the EL1 exception
// context so that we can report some information.
// Merge the exception code with the SError pending bit.
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index b8e045615961..ffa68d5713f1 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -216,17 +216,34 @@ ENDPROC(\label)
.align 11
+.macro check_preamble_length start, end
+/* kvm_patch_vector_branch() generates code that jumps over the preamble. */
+.if ((\end-\start) != KVM_VECTOR_PREAMBLE)
+ .error "KVM vector preamble length mismatch"
+.endif
+.endm
+
.macro valid_vect target
.align 7
+661:
+ esb
stp x0, x1, [sp, #-16]!
+662:
b \target
+
+check_preamble_length 661b, 662b
.endm
.macro invalid_vect target
.align 7
+661:
b \target
+ nop
+662:
ldp x0, x1, [sp], #16
b \target
+
+check_preamble_length 661b, 662b
.endm
ENTRY(__kvm_hyp_vector)
@@ -254,13 +271,14 @@ ENDPROC(__kvm_hyp_vector)
#ifdef CONFIG_KVM_INDIRECT_VECTORS
.macro hyp_ventry
.align 7
-1: .rept 27
+1: esb
+ .rept 26
nop
.endr
/*
* The default sequence is to directly branch to the KVM vectors,
* using the computed offset. This applies for VHE as well as
- * !ARM64_HARDEN_EL2_VECTORS.
+ * !ARM64_HARDEN_EL2_VECTORS. The first vector must always run the preamble.
*
* For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced
* with:
@@ -271,12 +289,13 @@ ENDPROC(__kvm_hyp_vector)
* movk x0, #((addr >> 32) & 0xffff), lsl #32
* br x0
*
- * Where addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + 4.
+ * Where:
+ * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE.
* See kvm_patch_vector_branch for details.
*/
alternative_cb kvm_patch_vector_branch
- b __kvm_hyp_vector + (1b - 0b)
- nop
+ stp x0, x1, [sp, #-16]!
+ b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE)
nop
nop
nop
@@ -301,6 +320,7 @@ ENTRY(__bp_harden_hyp_vecs_end)
.popsection
ENTRY(__smccc_workaround_1_smc_start)
+ esb
sub sp, sp, #(8 * 4)
stp x2, x3, [sp, #(8 * 0)]
stp x0, x1, [sp, #(8 * 2)]
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 58f281b6ca4a..adaf266d8de8 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -284,7 +284,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
return true;
- far = read_sysreg_el2(far);
+ far = read_sysreg_el2(SYS_FAR);
/*
* The HPFAR can be invalid if the stage 2 fault did not
@@ -401,7 +401,7 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
{
if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
- vcpu->arch.fault.esr_el2 = read_sysreg_el2(esr);
+ vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
/*
* We're using the raw exception code in order to only process
@@ -697,8 +697,8 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par,
asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va));
__hyp_do_panic(str_va,
- spsr, elr,
- read_sysreg(esr_el2), read_sysreg_el2(far),
+ spsr, elr,
+ read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR),
read_sysreg(hpfar_el2), par, vcpu);
}
@@ -713,15 +713,15 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par,
panic(__hyp_panic_string,
spsr, elr,
- read_sysreg_el2(esr), read_sysreg_el2(far),
+ read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR),
read_sysreg(hpfar_el2), par, vcpu);
}
NOKPROBE_SYMBOL(__hyp_call_panic_vhe);
void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt)
{
- u64 spsr = read_sysreg_el2(spsr);
- u64 elr = read_sysreg_el2(elr);
+ u64 spsr = read_sysreg_el2(SYS_SPSR);
+ u64 elr = read_sysreg_el2(SYS_ELR);
u64 par = read_sysreg(par_el1);
if (!has_vhe())
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index c283f7cbc702..7ddbc849b580 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -43,33 +43,33 @@ static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
{
ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1);
- ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(sctlr);
+ ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(SYS_SCTLR);
ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1);
- ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(cpacr);
- ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(ttbr0);
- ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(ttbr1);
- ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(tcr);
- ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(esr);
- ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(afsr0);
- ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(afsr1);
- ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(far);
- ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(mair);
- ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(vbar);
- ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(contextidr);
- ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair);
- ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl);
+ ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(SYS_CPACR);
+ ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(SYS_TTBR0);
+ ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(SYS_TTBR1);
+ ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(SYS_TCR);
+ ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(SYS_ESR);
+ ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(SYS_AFSR0);
+ ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(SYS_AFSR1);
+ ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(SYS_FAR);
+ ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(SYS_MAIR);
+ ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(SYS_VBAR);
+ ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(SYS_CONTEXTIDR);
+ ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(SYS_AMAIR);
+ ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(SYS_CNTKCTL);
ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1);
ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1);
ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1);
- ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr);
- ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(spsr);
+ ctxt->gp_regs.elr_el1 = read_sysreg_el1(SYS_ELR);
+ ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR);
}
static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
{
- ctxt->gp_regs.regs.pc = read_sysreg_el2(elr);
- ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr);
+ ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR);
+ ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
@@ -109,35 +109,35 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
{
- write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0);
- write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
+ write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0);
+ write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
}
static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
{
write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2);
write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1);
- write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], sctlr);
- write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1);
- write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], cpacr);
- write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], ttbr0);
- write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], ttbr1);
- write_sysreg_el1(ctxt->sys_regs[TCR_EL1], tcr);
- write_sysreg_el1(ctxt->sys_regs[ESR_EL1], esr);
- write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], afsr0);
- write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], afsr1);
- write_sysreg_el1(ctxt->sys_regs[FAR_EL1], far);
- write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], mair);
- write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], vbar);
- write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],contextidr);
- write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair);
- write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl);
+ write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR);
+ write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1);
+ write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR);
+ write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0);
+ write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1);
+ write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR);
+ write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR);
+ write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0);
+ write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1);
+ write_sysreg_el1(ctxt->sys_regs[FAR_EL1], SYS_FAR);
+ write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], SYS_MAIR);
+ write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], SYS_VBAR);
+ write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR);
+ write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], SYS_AMAIR);
+ write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], SYS_CNTKCTL);
write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1);
write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1);
write_sysreg(ctxt->gp_regs.sp_el1, sp_el1);
- write_sysreg_el1(ctxt->gp_regs.elr_el1, elr);
- write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],spsr);
+ write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR);
+ write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR);
}
static void __hyp_text
@@ -160,8 +160,8 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
pstate = PSR_MODE_EL2h | PSR_IL_BIT;
- write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
- write_sysreg_el2(pstate, spsr);
+ write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR);
+ write_sysreg_el2(pstate, SYS_SPSR);
if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 32078b767f63..d49a14497715 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -33,12 +33,12 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
* in the TCR_EL1 register. We also need to prevent it to
* allocate IPA->PA walks, so we enable the S1 MMU...
*/
- val = cxt->tcr = read_sysreg_el1(tcr);
+ val = cxt->tcr = read_sysreg_el1(SYS_TCR);
val |= TCR_EPD1_MASK | TCR_EPD0_MASK;
- write_sysreg_el1(val, tcr);
- val = cxt->sctlr = read_sysreg_el1(sctlr);
+ write_sysreg_el1(val, SYS_TCR);
+ val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR);
val |= SCTLR_ELx_M;
- write_sysreg_el1(val, sctlr);
+ write_sysreg_el1(val, SYS_SCTLR);
}
/*
@@ -85,8 +85,8 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) {
/* Restore the registers to what they were */
- write_sysreg_el1(cxt->tcr, tcr);
- write_sysreg_el1(cxt->sctlr, sctlr);
+ write_sysreg_el1(cxt->tcr, SYS_TCR);
+ write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
}
local_irq_restore(cxt->flags);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index ba2aaeb84c6c..29ee1feba4eb 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -16,7 +16,7 @@
static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
{
if (vcpu_mode_is_32bit(vcpu))
- return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT);
+ return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
}
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index d66613e6ad08..0d60e4f0af66 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -152,7 +152,7 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
switch (spsr_idx) {
case KVM_SPSR_SVC:
- return read_sysreg_el1(spsr);
+ return read_sysreg_el1(SYS_SPSR);
case KVM_SPSR_ABT:
return read_sysreg(spsr_abt);
case KVM_SPSR_UND:
@@ -177,7 +177,7 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
switch (spsr_idx) {
case KVM_SPSR_SVC:
- write_sysreg_el1(v, spsr);
+ write_sysreg_el1(v, SYS_SPSR);
case KVM_SPSR_ABT:
write_sysreg(v, spsr_abt);
case KVM_SPSR_UND:
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ce933f296049..f26e181d881c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -81,24 +81,24 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
*/
switch (reg) {
case CSSELR_EL1: return read_sysreg_s(SYS_CSSELR_EL1);
- case SCTLR_EL1: return read_sysreg_s(sctlr_EL12);
+ case SCTLR_EL1: return read_sysreg_s(SYS_SCTLR_EL12);
case ACTLR_EL1: return read_sysreg_s(SYS_ACTLR_EL1);
- case CPACR_EL1: return read_sysreg_s(cpacr_EL12);
- case TTBR0_EL1: return read_sysreg_s(ttbr0_EL12);
- case TTBR1_EL1: return read_sysreg_s(ttbr1_EL12);
- case TCR_EL1: return read_sysreg_s(tcr_EL12);
- case ESR_EL1: return read_sysreg_s(esr_EL12);
- case AFSR0_EL1: return read_sysreg_s(afsr0_EL12);
- case AFSR1_EL1: return read_sysreg_s(afsr1_EL12);
- case FAR_EL1: return read_sysreg_s(far_EL12);
- case MAIR_EL1: return read_sysreg_s(mair_EL12);
- case VBAR_EL1: return read_sysreg_s(vbar_EL12);
- case CONTEXTIDR_EL1: return read_sysreg_s(contextidr_EL12);
+ case CPACR_EL1: return read_sysreg_s(SYS_CPACR_EL12);
+ case TTBR0_EL1: return read_sysreg_s(SYS_TTBR0_EL12);
+ case TTBR1_EL1: return read_sysreg_s(SYS_TTBR1_EL12);
+ case TCR_EL1: return read_sysreg_s(SYS_TCR_EL12);
+ case ESR_EL1: return read_sysreg_s(SYS_ESR_EL12);
+ case AFSR0_EL1: return read_sysreg_s(SYS_AFSR0_EL12);
+ case AFSR1_EL1: return read_sysreg_s(SYS_AFSR1_EL12);
+ case FAR_EL1: return read_sysreg_s(SYS_FAR_EL12);
+ case MAIR_EL1: return read_sysreg_s(SYS_MAIR_EL12);
+ case VBAR_EL1: return read_sysreg_s(SYS_VBAR_EL12);
+ case CONTEXTIDR_EL1: return read_sysreg_s(SYS_CONTEXTIDR_EL12);
case TPIDR_EL0: return read_sysreg_s(SYS_TPIDR_EL0);
case TPIDRRO_EL0: return read_sysreg_s(SYS_TPIDRRO_EL0);
case TPIDR_EL1: return read_sysreg_s(SYS_TPIDR_EL1);
- case AMAIR_EL1: return read_sysreg_s(amair_EL12);
- case CNTKCTL_EL1: return read_sysreg_s(cntkctl_EL12);
+ case AMAIR_EL1: return read_sysreg_s(SYS_AMAIR_EL12);
+ case CNTKCTL_EL1: return read_sysreg_s(SYS_CNTKCTL_EL12);
case PAR_EL1: return read_sysreg_s(SYS_PAR_EL1);
case DACR32_EL2: return read_sysreg_s(SYS_DACR32_EL2);
case IFSR32_EL2: return read_sysreg_s(SYS_IFSR32_EL2);
@@ -124,24 +124,24 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
*/
switch (reg) {
case CSSELR_EL1: write_sysreg_s(val, SYS_CSSELR_EL1); return;
- case SCTLR_EL1: write_sysreg_s(val, sctlr_EL12); return;
+ case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); return;
case ACTLR_EL1: write_sysreg_s(val, SYS_ACTLR_EL1); return;
- case CPACR_EL1: write_sysreg_s(val, cpacr_EL12); return;
- case TTBR0_EL1: write_sysreg_s(val, ttbr0_EL12); return;
- case TTBR1_EL1: write_sysreg_s(val, ttbr1_EL12); return;
- case TCR_EL1: write_sysreg_s(val, tcr_EL12); return;
- case ESR_EL1: write_sysreg_s(val, esr_EL12); return;
- case AFSR0_EL1: write_sysreg_s(val, afsr0_EL12); return;
- case AFSR1_EL1: write_sysreg_s(val, afsr1_EL12); return;
- case FAR_EL1: write_sysreg_s(val, far_EL12); return;
- case MAIR_EL1: write_sysreg_s(val, mair_EL12); return;
- case VBAR_EL1: write_sysreg_s(val, vbar_EL12); return;
- case CONTEXTIDR_EL1: write_sysreg_s(val, contextidr_EL12); return;
+ case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); return;
+ case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); return;
+ case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); return;
+ case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); return;
+ case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); return;
+ case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); return;
+ case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); return;
+ case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); return;
+ case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); return;
+ case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); return;
+ case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12); return;
case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); return;
case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); return;
case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); return;
- case AMAIR_EL1: write_sysreg_s(val, amair_EL12); return;
- case CNTKCTL_EL1: write_sysreg_s(val, cntkctl_EL12); return;
+ case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); return;
+ case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); return;
case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); return;
case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); return;
case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); return;
@@ -865,12 +865,12 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (r->Op2 & 0x1) {
/* accessing PMCNTENSET_EL0 */
__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
- kvm_pmu_enable_counter(vcpu, val);
+ kvm_pmu_enable_counter_mask(vcpu, val);
kvm_vcpu_pmu_restore_guest(vcpu);
} else {
/* accessing PMCNTENCLR_EL0 */
__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
- kvm_pmu_disable_counter(vcpu, val);
+ kvm_pmu_disable_counter_mask(vcpu, val);
}
} else {
p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 2947ab1b0fa5..acd8084f1f2c 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -170,11 +170,10 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
addr |= ((u64)origptr & GENMASK_ULL(10, 7));
/*
- * Branch to the second instruction in the vectors in order to
- * avoid the initial store on the stack (which we already
- * perform in the hardening vectors).
+ * Branch over the preamble in order to avoid the initial store on
+ * the stack (which we already perform in the hardening vectors).
*/
- addr += AARCH64_INSN_SIZE;
+ addr += KVM_VECTOR_PREAMBLE;
/* stp x0, x1, [sp, #-16]! */
insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 3645f29bd814..1b49c08dfa2b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -362,7 +362,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
static phys_addr_t __pgd_pgtable_alloc(int shift)
{
- void *ptr = (void *)__get_free_page(PGALLOC_GFP);
+ void *ptr = (void *)__get_free_page(GFP_PGTABLE_KERNEL);
BUG_ON(!ptr);
/* Ensure the zeroed page is visible to the page table walker */
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index fcdcf6cd7677..03c53f16ee77 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -19,8 +19,7 @@ struct page_change_data {
bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED);
-static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
- void *data)
+static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
{
struct page_change_data *cdata = data;
pte_t pte = READ_ONCE(*ptep);
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 9a0c7d5090d6..7548f9ca1f11 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -19,10 +19,12 @@ static struct kmem_cache *pgd_cache __ro_after_init;
pgd_t *pgd_alloc(struct mm_struct *mm)
{
+ gfp_t gfp = GFP_PGTABLE_USER;
+
if (PGD_SIZE == PAGE_SIZE)
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ return (pgd_t *)__get_free_page(gfp);
else
- return kmem_cache_alloc(pgd_cache, PGALLOC_GFP);
+ return kmem_cache_alloc(pgd_cache, gfp);
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/csky/Makefile b/arch/csky/Makefile
index f9aab9157c4a..fb1bbbd91954 100644
--- a/arch/csky/Makefile
+++ b/arch/csky/Makefile
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
OBJCOPYFLAGS :=-O binary
GZFLAGS :=-9
-KBUILD_DEFCONFIG := defconfig
ifdef CONFIG_CPU_HAS_FPU
FPUEXT = f
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index d213bb47b717..98c5716708d6 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -8,6 +8,9 @@
#include <linux/mm.h>
#include <linux/sched.h>
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pte_t *pte)
{
@@ -39,33 +42,6 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
return pte;
}
-static inline struct page *pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
- if (!pte)
- return NULL;
-
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
-
- return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_pages((unsigned long)pte, PTE_ORDER);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_pages(pte, PTE_ORDER);
-}
-
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
free_pages((unsigned long)pgd, PGD_ORDER);
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 1456c5eecbd9..1a8ddbd0d23c 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -13,55 +13,18 @@
#include <asm/tlb.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
extern const char bad_pmd_string[];
#define pmd_alloc_one(mm,address) ({ BUG(); ((pmd_t *)2); })
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long) pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t page)
-{
- pgtable_page_dtor(page);
- __free_page(page);
-}
-
#define __pte_free_tlb(tlb,pte,addr) \
do { \
pgtable_page_dtor(pte); \
tlb_remove_page((tlb), pte); \
} while (0)
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- unsigned long page = __get_free_page(GFP_KERNEL);
-
- if (!page)
- return NULL;
-
- memset((void *)page, 0, PAGE_SIZE);
- return (pte_t *) (page);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- struct page *page = alloc_pages(GFP_KERNEL, 0);
-
- if (page == NULL)
- return NULL;
-
- clear_highpage(page);
- if (!pgtable_page_ctor(page)) {
- __free_page(page);
- return NULL;
- }
- return page;
-
-}
-
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
{
pmd_val(*pmd) = __pa((unsigned long)pte);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 70d3200476bf..d50fafd7bf3a 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -34,6 +34,7 @@ config MIPS
select GENERIC_SCHED_CLOCK if !CAVIUM_OCTEON_SOC
select GENERIC_SMP_IDLE_THREAD
select GENERIC_TIME_VSYSCALL
+ select GUP_GET_PTE_LOW_HIGH if CPU_MIPS32 && PHYS_ADDR_T_64BIT
select HANDLE_DOMAIN_IRQ
select HAVE_ARCH_COMPILER_H
select HAVE_ARCH_JUMP_LABEL
@@ -52,6 +53,7 @@ config MIPS
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
@@ -1119,6 +1121,7 @@ config DMA_NONCOHERENT
bool
select ARCH_HAS_DMA_MMAP_PGPROT
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select ARCH_HAS_UNCACHED_SEGMENT
select NEED_DMA_MAP_STATE
select ARCH_HAS_DMA_COHERENT_TO_PFN
select DMA_NONCOHERENT_CACHE_SYNC
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index a25643d258cb..0ba4ce6e2bf3 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -258,9 +258,6 @@ extern bool __virt_addr_valid(const volatile void *kaddr);
((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define UNCAC_ADDR(addr) (UNCAC_BASE + __pa(addr))
-#define CAC_ADDR(addr) ((unsigned long)__va((addr) - UNCAC_BASE))
-
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index 27808d9461f4..aa16b85ddffc 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -13,6 +13,8 @@
#include <linux/mm.h>
#include <linux/sched.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pte_t *pte)
{
@@ -50,37 +52,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
free_pages((unsigned long)pgd, PGD_ORDER);
}
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, PTE_ORDER);
-}
-
-static inline struct page *pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
- if (!pte)
- return NULL;
- clear_highpage(pte);
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
- return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_pages((unsigned long)pte, PTE_ORDER);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_pages(pte, PTE_ORDER);
-}
-
#define __pte_free_tlb(tlb,pte,address) \
do { \
pgtable_page_dtor(pte); \
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 4ccb465ef3f2..7d27194e3b45 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -20,6 +20,7 @@
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/pgtable-bits.h>
+#include <asm/cpu-features.h>
struct mm_struct;
struct vm_area_struct;
@@ -626,6 +627,8 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define gup_fast_permitted(start, end) (!cpu_has_dc_aliases)
+
#include <asm-generic/pgtable.h>
/*
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index b6578611dddb..1e76774b36dd 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -56,11 +56,6 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
return regs->regs[31];
}
-/*
- * Don't use asm-generic/ptrace.h it defines FP accessors that don't make
- * sense on MIPS. We rather want an error if they get invoked.
- */
-
static inline void instruction_pointer_set(struct pt_regs *regs,
unsigned long val)
{
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index bedb5047aff3..1804dc9d8136 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -575,10 +575,6 @@ static void *jazz_dma_alloc(struct device *dev, size_t size,
return NULL;
}
- if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
- dma_cache_wback_inv((unsigned long)ret, size);
- ret = (void *)UNCAC_ADDR(ret);
- }
return ret;
}
@@ -586,8 +582,6 @@ static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
vdma_free(dma_handle);
- if (!(attrs & DMA_ATTR_NON_CONSISTENT))
- vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
dma_direct_free_pages(dev, size, vaddr, dma_handle, attrs);
}
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 0369f26ab96d..2cfe839f0b3a 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -123,9 +123,9 @@ int kvm_arch_hardware_setup(void)
return 0;
}
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
{
- *(int *)rtn = 0;
+ return 0;
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index f34d7ff5eb60..1e8d335025d7 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -7,7 +7,6 @@ obj-y += cache.o
obj-y += context.o
obj-y += extable.o
obj-y += fault.o
-obj-y += gup.o
obj-y += init.o
obj-y += mmap.o
obj-y += page.o
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 3da216988672..33b409391ddb 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -62,8 +62,6 @@ void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
void (*_dma_cache_wback)(unsigned long start, unsigned long size);
void (*_dma_cache_inv)(unsigned long start, unsigned long size);
-EXPORT_SYMBOL(_dma_cache_wback_inv);
-
#endif /* CONFIG_DMA_NONCOHERENT */
/*
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index f9549d2fbea3..ed56c6fa7be2 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -44,33 +44,25 @@ static inline bool cpu_needs_post_dma_flush(struct device *dev)
}
}
-void *arch_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void arch_dma_prep_coherent(struct page *page, size_t size)
{
- void *ret;
-
- ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
- if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
- dma_cache_wback_inv((unsigned long) ret, size);
- ret = (void *)UNCAC_ADDR(ret);
- }
+ dma_cache_wback_inv((unsigned long)page_address(page), size);
+}
- return ret;
+void *uncached_kernel_address(void *addr)
+{
+ return (void *)(__pa(addr) + UNCAC_BASE);
}
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t dma_addr, unsigned long attrs)
+void *cached_kernel_address(void *addr)
{
- if (!(attrs & DMA_ATTR_NON_CONSISTENT))
- cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
- dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
+ return __va(addr) - UNCAC_BASE;
}
long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
dma_addr_t dma_addr)
{
- unsigned long addr = CAC_ADDR((unsigned long)cpu_addr);
- return page_to_pfn(virt_to_page((void *)addr));
+ return page_to_pfn(virt_to_page(cached_kernel_address(cpu_addr)));
}
pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
deleted file mode 100644
index 4c2b4483683c..000000000000
--- a/arch/mips/mm/gup.c
+++ /dev/null
@@ -1,303 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lockless get_user_pages_fast for MIPS
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- * Copyright (C) 2011 Ralf Baechle
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/vmstat.h>
-#include <linux/highmem.h>
-#include <linux/swap.h>
-#include <linux/hugetlb.h>
-
-#include <asm/cpu-features.h>
-#include <asm/pgtable.h>
-
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
-#if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
- pte_t pte;
-
-retry:
- pte.pte_low = ptep->pte_low;
- smp_rmb();
- pte.pte_high = ptep->pte_high;
- smp_rmb();
- if (unlikely(pte.pte_low != ptep->pte_low))
- goto retry;
-
- return pte;
-#else
- return READ_ONCE(*ptep);
-#endif
-}
-
-static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- pte_t *ptep = pte_offset_map(&pmd, addr);
- do {
- pte_t pte = gup_get_pte(ptep);
- struct page *page;
-
- if (!pte_present(pte) ||
- pte_special(pte) || (write && !pte_write(pte))) {
- pte_unmap(ptep);
- return 0;
- }
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- page = pte_page(pte);
- get_page(page);
- SetPageReferenced(page);
- pages[*nr] = page;
- (*nr)++;
-
- } while (ptep++, addr += PAGE_SIZE, addr != end);
-
- pte_unmap(ptep - 1);
- return 1;
-}
-
-static inline void get_head_page_multiple(struct page *page, int nr)
-{
- VM_BUG_ON(page != compound_head(page));
- VM_BUG_ON(page_count(page) == 0);
- page_ref_add(page, nr);
- SetPageReferenced(page);
-}
-
-static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- pte_t pte = *(pte_t *)&pmd;
- struct page *head, *page;
- int refs;
-
- if (write && !pte_write(pte))
- return 0;
- /* hugepages are never "special" */
- VM_BUG_ON(pte_special(pte));
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- refs = 0;
- head = pte_page(pte);
- page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- get_head_page_multiple(head, refs);
- return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pmd_t *pmdp;
-
- pmdp = pmd_offset(&pud, addr);
- do {
- pmd_t pmd = *pmdp;
-
- next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
- return 0;
- if (unlikely(pmd_huge(pmd))) {
- if (!gup_huge_pmd(pmd, addr, next, write, pages,nr))
- return 0;
- } else {
- if (!gup_pte_range(pmd, addr, next, write, pages,nr))
- return 0;
- }
- } while (pmdp++, addr = next, addr != end);
-
- return 1;
-}
-
-static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- pte_t pte = *(pte_t *)&pud;
- struct page *head, *page;
- int refs;
-
- if (write && !pte_write(pte))
- return 0;
- /* hugepages are never "special" */
- VM_BUG_ON(pte_special(pte));
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- refs = 0;
- head = pte_page(pte);
- page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- get_head_page_multiple(head, refs);
- return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pud_t *pudp;
-
- pudp = pud_offset(&pgd, addr);
- do {
- pud_t pud = *pudp;
-
- next = pud_addr_end(addr, end);
- if (pud_none(pud))
- return 0;
- if (unlikely(pud_huge(pud))) {
- if (!gup_huge_pud(pud, addr, next, write, pages,nr))
- return 0;
- } else {
- if (!gup_pmd_range(pud, addr, next, write, pages,nr))
- return 0;
- }
- } while (pudp++, addr = next, addr != end);
-
- return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- unsigned long flags;
- pgd_t *pgdp;
- int nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- if (unlikely(!access_ok((void __user *)start, len)))
- return 0;
-
- /*
- * XXX: batch / limit 'nr', to avoid large irq off latency
- * needs some instrumenting to determine the common sizes used by
- * important workloads (eg. DB2), and whether limiting the batch
- * size will decrease performance.
- *
- * It seems like we're in the clear for the moment. Direct-IO is
- * the main guy that batches up lots of get_user_pages, and even
- * they are limited to 64-at-a-time which is not so many.
- */
- /*
- * This doesn't prevent pagetable teardown, but does prevent
- * the pagetables and pages from being freed.
- *
- * So long as we atomically load page table pointers versus teardown,
- * we can follow the address down to the page and take a ref on it.
- */
- local_irq_save(flags);
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- break;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
- break;
- } while (pgdp++, addr = next, addr != end);
- local_irq_restore(flags);
-
- return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying pin behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages,
- unsigned int gup_flags, struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- pgd_t *pgdp;
- int ret, nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
-
- end = start + len;
- if (end < start || cpu_has_dc_aliases)
- goto slow_irqon;
-
- /* XXX: batch / limit 'nr' */
- local_irq_disable();
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- goto slow;
- if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
- pages, &nr))
- goto slow;
- } while (pgdp++, addr = next, addr != end);
- local_irq_enable();
-
- VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
- return nr;
-slow:
- local_irq_enable();
-
-slow_irqon:
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
-
- ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
- pages, gup_flags);
-
- /* Have to be a bit careful with return values */
- if (nr > 0) {
- if (ret < 0)
- ret = nr;
- else
- ret += nr;
- }
- return ret;
-}
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index fd0d0639454f..fbd68329737f 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -7,12 +7,14 @@
config NDS32
def_bool y
select ARCH_32BIT_OFF_T
+ select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_WANT_FRAME_POINTERS if FTRACE
select CLKSRC_MMIO
select CLONE_BACKWARDS
select COMMON_CLK
+ select DMA_DIRECT_REMAP
select GENERIC_ATOMIC64
select GENERIC_CPU_DEVICES
select GENERIC_CLOCKEVENTS
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 14dab5ad88ef..ccdca7142020 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -2,8 +2,6 @@
LDFLAGS_vmlinux := --no-undefined -X
OBJCOPYFLAGS := -O binary -R .note -R .note.gnu.build-id -R .comment -S
-KBUILD_DEFCONFIG := defconfig
-
ifdef CONFIG_FUNCTION_TRACER
arch-y += -malways-save-lp -mno-relax
endif
diff --git a/arch/nds32/configs/defconfig b/arch/nds32/configs/defconfig
index 65ce9259081b..40313a635075 100644
--- a/arch/nds32/configs/defconfig
+++ b/arch/nds32/configs/defconfig
@@ -92,6 +92,7 @@ CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
CONFIG_READABLE_ASM=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/nds32/include/asm/pgalloc.h b/arch/nds32/include/asm/pgalloc.h
index 3cbc749c79aa..e78b43d8389f 100644
--- a/arch/nds32/include/asm/pgalloc.h
+++ b/arch/nds32/include/asm/pgalloc.h
@@ -9,6 +9,9 @@
#include <asm/tlbflush.h>
#include <asm/proc-fns.h>
+#define __HAVE_ARCH_PTE_ALLOC_ONE
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
/*
* Since we have only two-level page tables, these are trivial
*/
@@ -22,22 +25,11 @@ extern void pgd_free(struct mm_struct *mm, pgd_t * pgd);
#define check_pgt_cache() do { } while (0)
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- pte_t *pte;
-
- pte =
- (pte_t *) __get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL |
- __GFP_ZERO);
-
- return pte;
-}
-
static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
{
pgtable_t pte;
- pte = alloc_pages(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO, 0);
+ pte = __pte_alloc_one(mm, GFP_PGTABLE_USER);
if (pte)
cpu_dcache_wb_page((unsigned long)page_address(pte));
@@ -45,21 +37,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
}
/*
- * Free one PTE table.
- */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t * pte)
-{
- if (pte) {
- free_page((unsigned long)pte);
- }
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- __free_page(pte);
-}
-
-/*
* Populate the pmdp entry with a pointer to the pte. This pmd is part
* of the mm address space.
*
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index d0dbd4fe9645..490e3720d694 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,327 +3,13 @@
#include <linux/types.h>
#include <linux/mm.h>
-#include <linux/string.h>
#include <linux/dma-noncoherent.h>
-#include <linux/io.h>
#include <linux/cache.h>
#include <linux/highmem.h>
-#include <linux/slab.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/proc-fns.h>
-/*
- * This is the page table (2MB) covering uncached, DMA consistent allocations
- */
-static pte_t *consistent_pte;
-static DEFINE_RAW_SPINLOCK(consistent_lock);
-
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- * struct vm_struct {
- * struct vm_region region;
- * unsigned long flags;
- * struct page **pages;
- * unsigned int nr_pages;
- * unsigned long phys_addr;
- * };
- *
- * get_vm_area() would then call vm_region_alloc with an appropriate
- * struct vm_region head (eg):
- *
- * struct vm_region vmalloc_head = {
- * .vm_list = LIST_HEAD_INIT(vmalloc_head.vm_list),
- * .vm_start = VMALLOC_START,
- * .vm_end = VMALLOC_END,
- * };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.) I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vm_region_alloc().
- */
-struct arch_vm_region {
- struct list_head vm_list;
- unsigned long vm_start;
- unsigned long vm_end;
- struct page *vm_pages;
-};
-
-static struct arch_vm_region consistent_head = {
- .vm_list = LIST_HEAD_INIT(consistent_head.vm_list),
- .vm_start = CONSISTENT_BASE,
- .vm_end = CONSISTENT_END,
-};
-
-static struct arch_vm_region *vm_region_alloc(struct arch_vm_region *head,
- size_t size, int gfp)
-{
- unsigned long addr = head->vm_start, end = head->vm_end - size;
- unsigned long flags;
- struct arch_vm_region *c, *new;
-
- new = kmalloc(sizeof(struct arch_vm_region), gfp);
- if (!new)
- goto out;
-
- raw_spin_lock_irqsave(&consistent_lock, flags);
-
- list_for_each_entry(c, &head->vm_list, vm_list) {
- if ((addr + size) < addr)
- goto nospc;
- if ((addr + size) <= c->vm_start)
- goto found;
- addr = c->vm_end;
- if (addr > end)
- goto nospc;
- }
-
-found:
- /*
- * Insert this entry _before_ the one we found.
- */
- list_add_tail(&new->vm_list, &c->vm_list);
- new->vm_start = addr;
- new->vm_end = addr + size;
-
- raw_spin_unlock_irqrestore(&consistent_lock, flags);
- return new;
-
-nospc:
- raw_spin_unlock_irqrestore(&consistent_lock, flags);
- kfree(new);
-out:
- return NULL;
-}
-
-static struct arch_vm_region *vm_region_find(struct arch_vm_region *head,
- unsigned long addr)
-{
- struct arch_vm_region *c;
-
- list_for_each_entry(c, &head->vm_list, vm_list) {
- if (c->vm_start == addr)
- goto out;
- }
- c = NULL;
-out:
- return c;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
- gfp_t gfp, unsigned long attrs)
-{
- struct page *page;
- struct arch_vm_region *c;
- unsigned long order;
- u64 mask = ~0ULL, limit;
- pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
-
- if (!consistent_pte) {
- pr_err("%s: not initialized\n", __func__);
- dump_stack();
- return NULL;
- }
-
- if (dev) {
- mask = dev->coherent_dma_mask;
-
- /*
- * Sanity check the DMA mask - it must be non-zero, and
- * must be able to be satisfied by a DMA allocation.
- */
- if (mask == 0) {
- dev_warn(dev, "coherent DMA mask is unset\n");
- goto no_page;
- }
-
- }
-
- /*
- * Sanity check the allocation size.
- */
- size = PAGE_ALIGN(size);
- limit = (mask + 1) & ~mask;
- if ((limit && size >= limit) ||
- size >= (CONSISTENT_END - CONSISTENT_BASE)) {
- pr_warn("coherent allocation too big "
- "(requested %#x mask %#llx)\n", size, mask);
- goto no_page;
- }
-
- order = get_order(size);
-
- if (mask != 0xffffffff)
- gfp |= GFP_DMA;
-
- page = alloc_pages(gfp, order);
- if (!page)
- goto no_page;
-
- /*
- * Invalidate any data that might be lurking in the
- * kernel direct-mapped region for device DMA.
- */
- {
- unsigned long kaddr = (unsigned long)page_address(page);
- memset(page_address(page), 0, size);
- cpu_dma_wbinval_range(kaddr, kaddr + size);
- }
-
- /*
- * Allocate a virtual address in the consistent mapping region.
- */
- c = vm_region_alloc(&consistent_head, size,
- gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
- if (c) {
- pte_t *pte = consistent_pte + CONSISTENT_OFFSET(c->vm_start);
- struct page *end = page + (1 << order);
-
- c->vm_pages = page;
-
- /*
- * Set the "dma handle"
- */
- *handle = page_to_phys(page);
-
- do {
- BUG_ON(!pte_none(*pte));
-
- /*
- * x86 does not mark the pages reserved...
- */
- SetPageReserved(page);
- set_pte(pte, mk_pte(page, prot));
- page++;
- pte++;
- } while (size -= PAGE_SIZE);
-
- /*
- * Free the otherwise unused pages.
- */
- while (page < end) {
- __free_page(page);
- page++;
- }
-
- return (void *)c->vm_start;
- }
-
- if (page)
- __free_pages(page, order);
-no_page:
- *handle = ~0;
- return NULL;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t handle, unsigned long attrs)
-{
- struct arch_vm_region *c;
- unsigned long flags, addr;
- pte_t *ptep;
-
- size = PAGE_ALIGN(size);
-
- raw_spin_lock_irqsave(&consistent_lock, flags);
-
- c = vm_region_find(&consistent_head, (unsigned long)cpu_addr);
- if (!c)
- goto no_area;
-
- if ((c->vm_end - c->vm_start) != size) {
- pr_err("%s: freeing wrong coherent size (%ld != %d)\n",
- __func__, c->vm_end - c->vm_start, size);
- dump_stack();
- size = c->vm_end - c->vm_start;
- }
-
- ptep = consistent_pte + CONSISTENT_OFFSET(c->vm_start);
- addr = c->vm_start;
- do {
- pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
- unsigned long pfn;
-
- ptep++;
- addr += PAGE_SIZE;
-
- if (!pte_none(pte) && pte_present(pte)) {
- pfn = pte_pfn(pte);
-
- if (pfn_valid(pfn)) {
- struct page *page = pfn_to_page(pfn);
-
- /*
- * x86 does not mark the pages reserved...
- */
- ClearPageReserved(page);
-
- __free_page(page);
- continue;
- }
- }
-
- pr_crit("%s: bad page in kernel page table\n", __func__);
- } while (size -= PAGE_SIZE);
-
- flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
- list_del(&c->vm_list);
-
- raw_spin_unlock_irqrestore(&consistent_lock, flags);
-
- kfree(c);
- return;
-
-no_area:
- raw_spin_unlock_irqrestore(&consistent_lock, flags);
- pr_err("%s: trying to free invalid coherent area: %p\n",
- __func__, cpu_addr);
- dump_stack();
-}
-
-/*
- * Initialise the consistent memory allocation.
- */
-static int __init consistent_init(void)
-{
- pgd_t *pgd;
- pmd_t *pmd;
- pte_t *pte;
- int ret = 0;
-
- do {
- pgd = pgd_offset(&init_mm, CONSISTENT_BASE);
- pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE);
- if (!pmd) {
- pr_err("%s: no pmd tables\n", __func__);
- ret = -ENOMEM;
- break;
- }
- /* The first level mapping may be created in somewhere.
- * It's not necessary to warn here. */
- /* WARN_ON(!pmd_none(*pmd)); */
-
- pte = pte_alloc_kernel(pmd, CONSISTENT_BASE);
- if (!pte) {
- ret = -ENOMEM;
- break;
- }
-
- consistent_pte = pte;
- } while (0);
-
- return ret;
-}
-
-core_initcall(consistent_init);
-
static inline void cache_op(phys_addr_t paddr, size_t size,
void (*fn)(unsigned long start, unsigned long end))
{
@@ -389,3 +75,14 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
BUG();
}
}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+ cache_op(page_to_phys(page), size, cpu_dma_wbinval_range);
+}
+
+static int __init atomic_pool_init(void)
+{
+ return dma_atomic_pool_init(GFP_KERNEL, pgprot_noncached(PAGE_KERNEL));
+}
+postcore_initcall(atomic_pool_init);
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 26a9c760a98b..44b5da37e8bd 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -4,6 +4,7 @@ config NIOS2
select ARCH_32BIT_OFF_T
select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select ARCH_HAS_UNCACHED_SEGMENT
select ARCH_NO_SWAP
select TIMER_OF
select GENERIC_ATOMIC64
diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug
index f1da8a7b17ff..a8bc06e96ef5 100644
--- a/arch/nios2/Kconfig.debug
+++ b/arch/nios2/Kconfig.debug
@@ -1,8 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-config TRACE_IRQFLAGS_SUPPORT
- def_bool y
-
config EARLY_PRINTK
bool "Activate early kernel debugging"
default y
diff --git a/arch/nios2/configs/10m50_defconfig b/arch/nios2/configs/10m50_defconfig
index 7977ab7e2ca6..1137ef2ed3b0 100644
--- a/arch/nios2/configs/10m50_defconfig
+++ b/arch/nios2/configs/10m50_defconfig
@@ -35,7 +35,6 @@ CONFIG_IP_PNP_RARP=y
# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
# CONFIG_FW_LOADER is not set
diff --git a/arch/nios2/configs/3c120_defconfig b/arch/nios2/configs/3c120_defconfig
index ceb97cd85ac1..a0f160ba7598 100644
--- a/arch/nios2/configs/3c120_defconfig
+++ b/arch/nios2/configs/3c120_defconfig
@@ -37,7 +37,6 @@ CONFIG_IP_PNP_RARP=y
# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
# CONFIG_FW_LOADER is not set
diff --git a/arch/nios2/include/asm/page.h b/arch/nios2/include/asm/page.h
index f1fbdc47bdaf..79fcac61f6ef 100644
--- a/arch/nios2/include/asm/page.h
+++ b/arch/nios2/include/asm/page.h
@@ -101,12 +101,6 @@ static inline bool pfn_valid(unsigned long pfn)
# define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-# define UNCAC_ADDR(addr) \
- ((void *)((unsigned)(addr) | CONFIG_NIOS2_IO_REGION_BASE))
-# define CAC_ADDR(addr) \
- ((void *)(((unsigned)(addr) & ~CONFIG_NIOS2_IO_REGION_BASE) | \
- CONFIG_NIOS2_KERNEL_REGION_BASE))
-
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index 3a149ead1207..4bc8cf72067e 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -12,6 +12,8 @@
#include <linux/mm.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pte_t *pte)
{
@@ -37,41 +39,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
free_pages((unsigned long)pgd, PGD_ORDER);
}
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- pte_t *pte;
-
- pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER);
-
- return pte;
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_pages(GFP_KERNEL, PTE_ORDER);
- if (pte) {
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
- clear_highpage(pte);
- }
- return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_pages((unsigned long)pte, PTE_ORDER);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
- pgtable_page_dtor(pte);
- __free_pages(pte, PTE_ORDER);
-}
-
#define __pte_free_tlb(tlb, pte, addr) \
do { \
pgtable_page_dtor(pte); \
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 4af9e5b5ba1c..9cb238664584 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -60,32 +60,28 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
}
}
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp, unsigned long attrs)
+void arch_dma_prep_coherent(struct page *page, size_t size)
{
- void *ret;
+ unsigned long start = (unsigned long)page_address(page);
- /* optimized page clearing */
- gfp |= __GFP_ZERO;
+ flush_dcache_range(start, start + size);
+}
- if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
- gfp |= GFP_DMA;
+void *uncached_kernel_address(void *ptr)
+{
+ unsigned long addr = (unsigned long)ptr;
- ret = (void *) __get_free_pages(gfp, get_order(size));
- if (ret != NULL) {
- *dma_handle = virt_to_phys(ret);
- flush_dcache_range((unsigned long) ret,
- (unsigned long) ret + size);
- ret = UNCAC_ADDR(ret);
- }
+ addr |= CONFIG_NIOS2_IO_REGION_BASE;
- return ret;
+ return (void *)ptr;
}
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
+void *cached_kernel_address(void *ptr)
{
- unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr);
+ unsigned long addr = (unsigned long)ptr;
+
+ addr &= ~CONFIG_NIOS2_IO_REGION_BASE;
+ addr |= CONFIG_NIOS2_KERNEL_REGION_BASE;
- free_pages(addr, get_order(size));
+ return (void *)ptr;
}
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 43e340c4cd9c..b41a79fcdbd9 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -94,15 +94,13 @@ arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
va = (unsigned long)page;
- if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) {
- /*
- * We need to iterate through the pages, clearing the dcache for
- * them and setting the cache-inhibit bit.
- */
- if (walk_page_range(va, va + size, &walk)) {
- free_pages_exact(page, size);
- return NULL;
- }
+ /*
+ * We need to iterate through the pages, clearing the dcache for
+ * them and setting the cache-inhibit bit.
+ */
+ if (walk_page_range(va, va + size, &walk)) {
+ free_pages_exact(page, size);
+ return NULL;
}
return (void *)va;
@@ -118,10 +116,8 @@ arch_dma_free(struct device *dev, size_t size, void *vaddr,
.mm = &init_mm
};
- if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) {
- /* walk_page_range shouldn't be able to fail here */
- WARN_ON(walk_page_range(va, va + size, &walk));
- }
+ /* walk_page_range shouldn't be able to fail here */
+ WARN_ON(walk_page_range(va, va + size, &walk));
free_pages_exact(vaddr, size);
}
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 58d46665cad9..8acb8fa1f8d6 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -120,8 +120,8 @@ PALO := $(shell if (which palo 2>&1); then : ; \
elif [ -x /sbin/palo ]; then echo /sbin/palo; \
fi)
-PALOCONF := $(shell if [ -f $(src)/palo.conf ]; then echo $(src)/palo.conf; \
- else echo $(obj)/palo.conf; \
+PALOCONF := $(shell if [ -f $(srctree)/palo.conf ]; then echo $(srctree)/palo.conf; \
+ else echo $(objtree)/palo.conf; \
fi)
palo lifimage: vmlinuz
@@ -131,8 +131,8 @@ palo lifimage: vmlinuz
false; \
fi
@if test ! -f "$(PALOCONF)"; then \
- cp $(src)/arch/parisc/defpalo.conf $(obj)/palo.conf; \
- echo 'A generic palo config file ($(obj)/palo.conf) has been created for you.'; \
+ cp $(srctree)/arch/parisc/defpalo.conf $(objtree)/palo.conf; \
+ echo 'A generic palo config file ($(objree)/palo.conf) has been created for you.'; \
echo 'You should check it and re-run "make palo".'; \
echo 'WARNING: the "lifimage" file is now placed in this directory by default!'; \
false; \
@@ -162,10 +162,10 @@ vmlinuz: vmlinux
endif
install:
- $(CONFIG_SHELL) $(src)/arch/parisc/install.sh \
+ $(CONFIG_SHELL) $(srctree)/arch/parisc/install.sh \
$(KERNELRELEASE) vmlinux System.map "$(INSTALL_PATH)"
zinstall:
- $(CONFIG_SHELL) $(src)/arch/parisc/install.sh \
+ $(CONFIG_SHELL) $(srctree)/arch/parisc/install.sh \
$(KERNELRELEASE) vmlinuz System.map "$(INSTALL_PATH)"
CLEAN_FILES += lifimage
diff --git a/arch/parisc/configs/a500_defconfig b/arch/parisc/configs/a500_defconfig
index a8859496b0b9..3335734bfadd 100644
--- a/arch/parisc/configs/a500_defconfig
+++ b/arch/parisc/configs/a500_defconfig
@@ -166,6 +166,7 @@ CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_MAGIC_SYSRQ=y
# CONFIG_DEBUG_BUGVERBOSE is not set
diff --git a/arch/parisc/configs/b180_defconfig b/arch/parisc/configs/b180_defconfig
index 0cae9664bf67..07fde5bd6974 100644
--- a/arch/parisc/configs/b180_defconfig
+++ b/arch/parisc/configs/b180_defconfig
@@ -90,6 +90,7 @@ CONFIG_NLS_ASCII=m
CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig
index 6c29b841735c..64d45a8b6ca0 100644
--- a/arch/parisc/configs/c3000_defconfig
+++ b/arch/parisc/configs/c3000_defconfig
@@ -139,6 +139,7 @@ CONFIG_NLS_ISO8859_1=m
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MUTEXES=y
diff --git a/arch/parisc/configs/default_defconfig b/arch/parisc/configs/default_defconfig
index 6a91cc2623e8..5b877ca34ebf 100644
--- a/arch/parisc/configs/default_defconfig
+++ b/arch/parisc/configs/default_defconfig
@@ -183,6 +183,7 @@ CONFIG_NLS_KOI8_R=m
CONFIG_NLS_KOI8_U=m
CONFIG_NLS_UTF8=y
CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index ea75cc966dae..4f2059a50fae 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -10,6 +10,8 @@
#include <asm/cache.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
/* Allocate the top level pgd (page directory)
*
* Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
@@ -122,37 +124,6 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
pmd_populate_kernel(mm, pmd, page_address(pte_page))
#define pmd_pgtable(pmd) pmd_page(pmd)
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm)
-{
- struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
- if (!page)
- return NULL;
- if (!pgtable_page_ctor(page)) {
- __free_page(page);
- return NULL;
- }
- return page;
-}
-
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm)
-{
- pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
- return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
- pgtable_page_dtor(pte);
- pte_free_kernel(mm, page_address(pte));
-}
-
#define check_pgt_cache() do { } while (0)
#endif
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 239162355b58..ca35d9a76e50 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -394,17 +394,20 @@ pcxl_dma_init(void)
__initcall(pcxl_dma_init);
-static void *pcxl_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
unsigned long vaddr;
unsigned long paddr;
int order;
+ if (boot_cpu_data.cpu_type != pcxl2 && boot_cpu_data.cpu_type != pcxl)
+ return NULL;
+
order = get_order(size);
size = 1 << (order + PAGE_SHIFT);
vaddr = pcxl_alloc_range(size);
- paddr = __get_free_pages(flag | __GFP_ZERO, order);
+ paddr = __get_free_pages(gfp | __GFP_ZERO, order);
flush_kernel_dcache_range(paddr, size);
paddr = __pa(paddr);
map_uncached_pages(vaddr, size, paddr);
@@ -421,44 +424,19 @@ static void *pcxl_dma_alloc(struct device *dev, size_t size,
return (void *)vaddr;
}
-static void *pcx_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
- void *addr;
-
- if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
- return NULL;
-
- addr = (void *)__get_free_pages(flag | __GFP_ZERO, get_order(size));
- if (addr)
- *dma_handle = (dma_addr_t)virt_to_phys(addr);
-
- return addr;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-
- if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl)
- return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs);
- else
- return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
-}
-
void arch_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
int order = get_order(size);
- if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
- size = 1 << (order + PAGE_SHIFT);
- unmap_uncached_pages((unsigned long)vaddr, size);
- pcxl_free_range((unsigned long)vaddr, size);
+ WARN_ON_ONCE(boot_cpu_data.cpu_type != pcxl2 &&
+ boot_cpu_data.cpu_type != pcxl);
- vaddr = __va(dma_handle);
- }
- free_pages((unsigned long)vaddr, get_order(size));
+ size = 1 << (order + PAGE_SHIFT);
+ unmap_uncached_pages((unsigned long)vaddr, size);
+ pcxl_free_range((unsigned long)vaddr, size);
+
+ free_pages((unsigned long)__va(dma_handle), order);
}
void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3b795a0cab62..24a41f919309 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -125,6 +125,7 @@ config PPC
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV
+ select ARCH_HAS_HUGEPD if HUGETLB_PAGE
select ARCH_HAS_MMIOWB if PPC64
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_PMEM_API if PPC64
@@ -185,12 +186,12 @@ config PPC
select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
select HAVE_EBPF_JIT if PPC64
select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ERROR_INJECTION
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
- select HAVE_GENERIC_GUP
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IDE
select HAVE_IOREMAP_PROT
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index aa51b9b66fa2..1c074fb95df2 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -1123,6 +1123,7 @@ CONFIG_NLS_KOI8_R=m
CONFIG_NLS_KOI8_U=m
CONFIG_DEBUG_INFO=y
CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 3f53be60fb01..64145751b2fd 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -140,6 +140,20 @@ static inline void pte_frag_set(mm_context_t *ctx, void *p)
}
#endif
+#ifdef CONFIG_PPC64
+#define is_ioremap_addr is_ioremap_addr
+static inline bool is_ioremap_addr(const void *x)
+{
+#ifdef CONFIG_MMU
+ unsigned long addr = (unsigned long)x;
+
+ return addr >= IOREMAP_BASE && addr < IOREMAP_END;
+#else
+ return false;
+#endif
+}
+#endif /* CONFIG_PPC64 */
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index faa5a338ac5a..feee1b21bbd5 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -111,18 +111,33 @@ struct pt_regs
#ifndef __ASSEMBLY__
-#define GET_IP(regs) ((regs)->nip)
-#define GET_USP(regs) ((regs)->gpr[1])
-#define GET_FP(regs) (0)
-#define SET_FP(regs, val)
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return regs->nip;
+}
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->nip = val;
+}
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return regs->gpr[1];
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return 0;
+}
#ifdef CONFIG_SMP
extern unsigned long profile_pc(struct pt_regs *regs);
-#define profile_pc profile_pc
+#else
+#define profile_pc(regs) instruction_pointer(regs)
#endif
-#include <asm-generic/ptrace.h>
-
#define kernel_stack_pointer(regs) ((regs)->gpr[1])
static inline int is_syscall_success(struct pt_regs *regs)
{
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index e8276161872e..381bf8dea193 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -827,7 +827,7 @@ static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
*
* Note: If EOI is incorrectly used by SW to lower the CPPR
* value (ie more favored), we do not check for rejection of
- * a pending interrupt, this is a SW error and PAPR sepcifies
+ * a pending interrupt, this is a SW error and PAPR specifies
* that we don't have to deal with it.
*
* The sending of an EOI to the ICS is handled after the
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6d704ad2472b..0dba7eb24f92 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -414,9 +414,9 @@ int kvm_arch_hardware_setup(void)
return 0;
}
-void kvm_arch_check_processor_compat(void *rtn)
+int kvm_arch_check_processor_compat(void)
{
- *(int *)rtn = kvmppc_core_check_processor_compat();
+ return kvmppc_core_check_processor_compat();
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index b5d92dc32844..51716c11d0fb 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -511,13 +511,6 @@ retry:
return page;
}
-static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
- unsigned long sz)
-{
- unsigned long __boundary = (addr + sz) & ~(sz-1);
- return (__boundary - 1 < end - 1) ? __boundary : end;
-}
-
#ifdef CONFIG_PPC_MM_SLICES
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
@@ -665,68 +658,3 @@ void flush_dcache_icache_hugepage(struct page *page)
}
}
}
-
-static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long pte_end;
- struct page *head, *page;
- pte_t pte;
- int refs;
-
- pte_end = (addr + sz) & ~(sz-1);
- if (pte_end < end)
- end = pte_end;
-
- pte = READ_ONCE(*ptep);
-
- if (!pte_access_permitted(pte, write))
- return 0;
-
- /* hugepages are never "special" */
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- refs = 0;
- head = pte_page(pte);
-
- page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- /* Could be optimized better */
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- pte_t *ptep;
- unsigned long sz = 1UL << hugepd_shift(hugepd);
- unsigned long next;
-
- ptep = hugepte_offset(hugepd, addr, pdshift);
- do {
- next = hugepte_addr_end(addr, end, sz);
- if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
- return 0;
- } while (ptep++, addr = next, addr != end);
-
- return 1;
-}
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index 84e8ec4011ba..b91eb0929ed1 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -147,13 +147,13 @@ static const struct dma_map_ops ibmebus_dma_ops = {
.unmap_page = ibmebus_unmap_page,
};
-static int ibmebus_match_path(struct device *dev, void *data)
+static int ibmebus_match_path(struct device *dev, const void *data)
{
struct device_node *dn = to_platform_device(dev)->dev.of_node;
return (of_find_node_by_path(data) == dn);
}
-static int ibmebus_match_node(struct device *dev, void *data)
+static int ibmebus_match_node(struct device *dev, const void *data)
{
return to_platform_device(dev)->dev.of_node == data;
}
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 6b0741c9f348..f8b3b07e4247 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -16,8 +16,6 @@ endif
KBUILD_AFLAGS_MODULE += -fPIC
KBUILD_CFLAGS_MODULE += -fPIC
-KBUILD_DEFCONFIG = defconfig
-
export BITS
ifeq ($(CONFIG_ARCH_RV64I),y)
BITS := 64
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index eb8b0195f27f..56a67d66f72f 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -10,6 +10,8 @@
#include <linux/mm.h>
#include <asm/tlb.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
static inline void pmd_populate_kernel(struct mm_struct *mm,
pmd_t *pmd, pte_t *pte)
{
@@ -74,33 +76,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
#endif /* __PAGETABLE_PMD_FOLDED */
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)__get_free_page(
- GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO);
-}
-
-static inline struct page *pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO);
- if (likely(pte != NULL))
- pgtable_page_ctor(pte);
- return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
#define __pte_free_tlb(tlb, pte, buf) \
do { \
pgtable_page_dtor(pte); \
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index fdb4246265a5..5d8570ed6cab 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -139,6 +139,7 @@ config S390
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select HAVE_FAST_GUP
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FENTRY
select HAVE_FTRACE_MCOUNT_RECORD
@@ -146,7 +147,6 @@ config S390
select HAVE_FUNCTION_TRACER
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_GCC_PLUGINS
- select HAVE_GENERIC_GUP
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
@@ -641,9 +641,6 @@ config ARCH_SPARSEMEM_ENABLE
config ARCH_SPARSEMEM_DEFAULT
def_bool y
-config ARCH_SELECT_MEMORY_MODEL
- def_bool y
-
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y if SPARSEMEM
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index e48013cf50a2..e0bab7ed4123 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -10,8 +10,6 @@
# Copyright (C) 1994 by Linus Torvalds
#
-KBUILD_DEFCONFIG := defconfig
-
LD_BFD := elf64-s390
KBUILD_LDFLAGS := -m elf64_s390
KBUILD_AFLAGS_MODULE += -fPIC
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index a6dc01a22048..e26d4413d34c 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -588,6 +588,7 @@ CONFIG_GDB_SCRIPTS=y
CONFIG_FRAME_WARN=1024
CONFIG_READABLE_ASM=y
CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 4a928e2c667b..abe60268335d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -912,7 +912,6 @@ extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc);
extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
static inline void kvm_arch_hardware_disable(void) {}
-static inline void kvm_arch_check_processor_compat(void *rtn) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index ff81ed19c506..61cf9531f68f 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -143,14 +143,4 @@ static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
return __zpci_set_irq_ctrl(ctl, isc, &iib);
}
-#ifdef CONFIG_PCI
-static inline void enable_mio_ctl(void)
-{
- if (static_branch_likely(&have_mio))
- __ctl_set_bit(2, 5);
-}
-#else /* CONFIG_PCI */
-static inline void enable_mio_ctl(void) {}
-#endif /* CONFIG_PCI */
-
#endif
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 9f0195d5fa16..9b274fcaacb6 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1270,14 +1270,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
#define pte_unmap(pte) do { } while (0)
-static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
{
- unsigned long len, end;
-
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- if (end < start)
- return false;
return end <= current->mm->context.asce_limit;
}
#define gup_fast_permitted gup_fast_permitted
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index f577c5f6031a..c563f8368b19 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -80,7 +80,6 @@ struct sclp_info {
unsigned char has_gisaf : 1;
unsigned char has_diag318 : 1;
unsigned char has_sipl : 1;
- unsigned char has_sipl_g2 : 1;
unsigned char has_dirq : 1;
unsigned int ibc;
unsigned int mtid;
diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h
index 832be5c2584f..9ec86fae9980 100644
--- a/arch/s390/include/uapi/asm/dasd.h
+++ b/arch/s390/include/uapi/asm/dasd.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
+/*
* Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
* Bugreports.to..: <Linux390@de.ibm.com>
* Copyright IBM Corp. 1999, 2000
@@ -21,40 +21,40 @@
#define DASD_API_VERSION 6
-/*
+/*
* struct dasd_information2_t
* represents any data about the device, which is visible to userspace.
* including foramt and featueres.
*/
typedef struct dasd_information2_t {
- unsigned int devno; /* S/390 devno */
- unsigned int real_devno; /* for aliases */
- unsigned int schid; /* S/390 subchannel identifier */
- unsigned int cu_type : 16; /* from SenseID */
- unsigned int cu_model : 8; /* from SenseID */
- unsigned int dev_type : 16; /* from SenseID */
- unsigned int dev_model : 8; /* from SenseID */
- unsigned int open_count;
- unsigned int req_queue_len;
- unsigned int chanq_len; /* length of chanq */
- char type[4]; /* from discipline.name, 'none' for unknown */
- unsigned int status; /* current device level */
- unsigned int label_block; /* where to find the VOLSER */
- unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
- unsigned int characteristics_size;
- unsigned int confdata_size;
- char characteristics[64]; /* from read_device_characteristics */
- char configuration_data[256]; /* from read_configuration_data */
- unsigned int format; /* format info like formatted/cdl/ldl/... */
- unsigned int features; /* dasd features like 'ro',... */
- unsigned int reserved0; /* reserved for further use ,... */
- unsigned int reserved1; /* reserved for further use ,... */
- unsigned int reserved2; /* reserved for further use ,... */
- unsigned int reserved3; /* reserved for further use ,... */
- unsigned int reserved4; /* reserved for further use ,... */
- unsigned int reserved5; /* reserved for further use ,... */
- unsigned int reserved6; /* reserved for further use ,... */
- unsigned int reserved7; /* reserved for further use ,... */
+ unsigned int devno; /* S/390 devno */
+ unsigned int real_devno; /* for aliases */
+ unsigned int schid; /* S/390 subchannel identifier */
+ unsigned int cu_type : 16; /* from SenseID */
+ unsigned int cu_model : 8; /* from SenseID */
+ unsigned int dev_type : 16; /* from SenseID */
+ unsigned int dev_model : 8; /* from SenseID */
+ unsigned int open_count;
+ unsigned int req_queue_len;
+ unsigned int chanq_len; /* length of chanq */
+ char type[4]; /* from discipline.name, 'none' for unknown */
+ unsigned int status; /* current device level */
+ unsigned int label_block; /* where to find the VOLSER */
+ unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
+ unsigned int characteristics_size;
+ unsigned int confdata_size;
+ char characteristics[64]; /* from read_device_characteristics */
+ char configuration_data[256]; /* from read_configuration_data */
+ unsigned int format; /* format info like formatted/cdl/ldl/... */
+ unsigned int features; /* dasd features like 'ro',... */
+ unsigned int reserved0; /* reserved for further use ,... */
+ unsigned int reserved1; /* reserved for further use ,... */
+ unsigned int reserved2; /* reserved for further use ,... */
+ unsigned int reserved3; /* reserved for further use ,... */
+ unsigned int reserved4; /* reserved for further use ,... */
+ unsigned int reserved5; /* reserved for further use ,... */
+ unsigned int reserved6; /* reserved for further use ,... */
+ unsigned int reserved7; /* reserved for further use ,... */
} dasd_information2_t;
/*
@@ -92,34 +92,34 @@ typedef struct dasd_information2_t {
#define DASD_PARTN_BITS 2
-/*
+/*
* struct dasd_information_t
* represents any data about the data, which is visible to userspace
*/
typedef struct dasd_information_t {
- unsigned int devno; /* S/390 devno */
- unsigned int real_devno; /* for aliases */
- unsigned int schid; /* S/390 subchannel identifier */
- unsigned int cu_type : 16; /* from SenseID */
- unsigned int cu_model : 8; /* from SenseID */
- unsigned int dev_type : 16; /* from SenseID */
- unsigned int dev_model : 8; /* from SenseID */
- unsigned int open_count;
- unsigned int req_queue_len;
- unsigned int chanq_len; /* length of chanq */
- char type[4]; /* from discipline.name, 'none' for unknown */
- unsigned int status; /* current device level */
- unsigned int label_block; /* where to find the VOLSER */
- unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
- unsigned int characteristics_size;
- unsigned int confdata_size;
- char characteristics[64]; /* from read_device_characteristics */
- char configuration_data[256]; /* from read_configuration_data */
+ unsigned int devno; /* S/390 devno */
+ unsigned int real_devno; /* for aliases */
+ unsigned int schid; /* S/390 subchannel identifier */
+ unsigned int cu_type : 16; /* from SenseID */
+ unsigned int cu_model : 8; /* from SenseID */
+ unsigned int dev_type : 16; /* from SenseID */
+ unsigned int dev_model : 8; /* from SenseID */
+ unsigned int open_count;
+ unsigned int req_queue_len;
+ unsigned int chanq_len; /* length of chanq */
+ char type[4]; /* from discipline.name, 'none' for unknown */
+ unsigned int status; /* current device level */
+ unsigned int label_block; /* where to find the VOLSER */
+ unsigned int FBA_layout; /* fixed block size (like AIXVOL) */
+ unsigned int characteristics_size;
+ unsigned int confdata_size;
+ char characteristics[64]; /* from read_device_characteristics */
+ char configuration_data[256]; /* from read_configuration_data */
} dasd_information_t;
/*
* Read Subsystem Data - Performance Statistics
- */
+ */
typedef struct dasd_rssd_perf_stats_t {
unsigned char invalid:1;
unsigned char format:3;
@@ -154,21 +154,21 @@ typedef struct dasd_rssd_perf_stats_t {
unsigned char reseved2[96];
} __attribute__((packed)) dasd_rssd_perf_stats_t;
-/*
+/*
* struct profile_info_t
- * holds the profinling information
+ * holds the profinling information
*/
typedef struct dasd_profile_info_t {
- unsigned int dasd_io_reqs; /* number of requests processed at all */
- unsigned int dasd_io_sects; /* number of sectors processed at all */
- unsigned int dasd_io_secs[32]; /* histogram of request's sizes */
- unsigned int dasd_io_times[32]; /* histogram of requests's times */
- unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */
- unsigned int dasd_io_time1[32]; /* histogram of time from build to start */
- unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */
- unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */
- unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */
- unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */
+ unsigned int dasd_io_reqs; /* number of requests processed at all */
+ unsigned int dasd_io_sects; /* number of sectors processed at all */
+ unsigned int dasd_io_secs[32]; /* histogram of request's sizes */
+ unsigned int dasd_io_times[32]; /* histogram of requests's times */
+ unsigned int dasd_io_timps[32]; /* histogram of requests's times per sector */
+ unsigned int dasd_io_time1[32]; /* histogram of time from build to start */
+ unsigned int dasd_io_time2[32]; /* histogram of time from start to irq */
+ unsigned int dasd_io_time2ps[32]; /* histogram of time from start to irq */
+ unsigned int dasd_io_time3[32]; /* histogram of time from irq to end */
+ unsigned int dasd_io_nr_req[32]; /* histogram of # of requests in chanq */
} dasd_profile_info_t;
/*
@@ -189,10 +189,12 @@ typedef struct format_data_t {
* 3/11: also write home address
* 4/12: invalidate track
*/
-#define DASD_FMT_INT_FMT_R0 1 /* write record zero */
-#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */
-#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */
-#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */
+#define DASD_FMT_INT_FMT_R0 1 /* write record zero */
+#define DASD_FMT_INT_FMT_HA 2 /* write home address, also set FMT_R0 ! */
+#define DASD_FMT_INT_INVAL 4 /* invalidate tracks */
+#define DASD_FMT_INT_COMPAT 8 /* use OS/390 compatible disk layout */
+#define DASD_FMT_INT_FMT_NOR0 16 /* remove permission to write record zero */
+#define DASD_FMT_INT_ESE_FULL 32 /* release space for entire volume */
/*
* struct format_check_t
@@ -225,7 +227,7 @@ typedef struct format_check_t {
/* If key-length was != 0 */
#define DASD_FMT_ERR_KEY_LENGTH 5
-/*
+/*
* struct attrib_data_t
* represents the operation (cache) bits for the device.
* Used in DE to influence caching of the DASD.
@@ -281,13 +283,13 @@ struct dasd_snid_ioctl_data {
* Here ist how the ioctl-nr should be used:
* 0 - 31 DASD driver itself
* 32 - 239 still open
- * 240 - 255 reserved for EMC
+ * 240 - 255 reserved for EMC
*******************************************************************************/
/* Disable the volume (for Linux) */
-#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0)
+#define BIODASDDISABLE _IO(DASD_IOCTL_LETTER,0)
/* Enable the volume (for Linux) */
-#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1)
+#define BIODASDENABLE _IO(DASD_IOCTL_LETTER,1)
/* Issue a reserve/release command, rsp. */
#define BIODASDRSRV _IO(DASD_IOCTL_LETTER,2) /* reserve */
#define BIODASDRLSE _IO(DASD_IOCTL_LETTER,3) /* release */
@@ -295,9 +297,9 @@ struct dasd_snid_ioctl_data {
/* reset profiling information of a device */
#define BIODASDPRRST _IO(DASD_IOCTL_LETTER,5)
/* Quiesce IO on device */
-#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6)
+#define BIODASDQUIESCE _IO(DASD_IOCTL_LETTER,6)
/* Resume IO on device */
-#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7)
+#define BIODASDRESUME _IO(DASD_IOCTL_LETTER,7)
/* Abort all I/O on a device */
#define BIODASDABORTIO _IO(DASD_IOCTL_LETTER, 240)
/* Allow I/O on a device */
@@ -315,13 +317,15 @@ struct dasd_snid_ioctl_data {
/* Performance Statistics Read */
#define BIODASDPSRD _IOR(DASD_IOCTL_LETTER,4,dasd_rssd_perf_stats_t)
/* Get Attributes (cache operations) */
-#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t)
+#define BIODASDGATTR _IOR(DASD_IOCTL_LETTER,5,attrib_data_t)
/* #define BIODASDFORMAT _IOW(IOCTL_LETTER,0,format_data_t) , deprecated */
-#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t)
+#define BIODASDFMT _IOW(DASD_IOCTL_LETTER,1,format_data_t)
/* Set Attributes (cache operations) */
-#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t)
+#define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t)
+/* Release Allocated Space */
+#define BIODASDRAS _IOW(DASD_IOCTL_LETTER, 3, format_data_t)
/* Get Sense Path Group ID (SNID) data */
#define BIODASDSNID _IOWR(DASD_IOCTL_LETTER, 1, struct dasd_snid_ioctl_data)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 629f173f60cd..6312fed48530 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,7 +30,6 @@
#include <asm/sclp.h>
#include <asm/facility.h>
#include <asm/boot_data.h>
-#include <asm/pci_insn.h>
#include "entry.h"
/*
@@ -236,7 +235,6 @@ static __init void detect_machine_facilities(void)
clock_comparator_max = -1ULL >> 1;
__ctl_set_bit(0, 53);
}
- enable_mio_ctl();
}
static inline void save_vector_registers(void)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index d836af3ccc38..2c0a515428d6 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -286,12 +286,7 @@ static struct kobj_attribute sys_ipl_secure_attr =
static ssize_t ipl_has_secure_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- if (MACHINE_IS_LPAR)
- return sprintf(page, "%i\n", !!sclp.has_sipl);
- else if (MACHINE_IS_VM)
- return sprintf(page, "%i\n", !!sclp.has_sipl_g2);
- else
- return sprintf(page, "%i\n", 0);
+ return sprintf(page, "%i\n", !!sclp.has_sipl);
}
static struct kobj_attribute sys_ipl_has_secure_attr =
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 34cc96449b30..8b33e03e47b8 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -624,6 +624,8 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
break;
case 0x3906:
case 0x3907:
+ case 0x8561:
+ case 0x8562:
model = cpumcf_z14_pmu_event_attr;
break;
default:
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index 3ce8a0808059..8fc9daae47a2 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -20,7 +20,7 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address);
static bool outside_of_stack(struct unwind_state *state, unsigned long sp)
{
return (sp <= state->sp) ||
- (sp + sizeof(struct stack_frame) > state->stack_info.end);
+ (sp > state->stack_info.end - sizeof(struct stack_frame));
}
static bool update_stack_info(struct unwind_state *state, unsigned long sp)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1c4113f0f2a8..3f520cd837fb 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -227,6 +227,11 @@ int kvm_arch_hardware_enable(void)
return 0;
}
+int kvm_arch_check_processor_compat(void)
+{
+ return 0;
+}
+
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
@@ -2418,13 +2423,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
if (!kvm->arch.sca)
goto out_err;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
sca_offset += 16;
if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
kvm->arch.sca = (struct bsca_block *)
((char *) kvm->arch.sca + sca_offset);
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index b8a64cbb5dea..b0e3b9a0e488 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -890,8 +890,10 @@ static int __init pci_base_init(void)
if (!test_facility(69) || !test_facility(71))
return 0;
- if (test_facility(153) && !s390_pci_no_mio)
+ if (test_facility(153) && !s390_pci_no_mio) {
static_branch_enable(&have_mio);
+ ctl_set_bit(2, 5);
+ }
rc = zpci_debug_init();
if (rc)
diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c
index 430c14b006d1..a433ba01a317 100644
--- a/arch/s390/pci/pci_sysfs.c
+++ b/arch/s390/pci/pci_sysfs.c
@@ -37,6 +37,15 @@ zpci_attr(segment1, "0x%02x\n", pfip[1]);
zpci_attr(segment2, "0x%02x\n", pfip[2]);
zpci_attr(segment3, "0x%02x\n", pfip[3]);
+static ssize_t mio_enabled_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
+
+ return sprintf(buf, zpci_use_mio(zdev) ? "1\n" : "0\n");
+}
+static DEVICE_ATTR_RO(mio_enabled);
+
static ssize_t recover_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
@@ -115,6 +124,7 @@ static struct attribute *zpci_dev_attrs[] = {
&dev_attr_vfn.attr,
&dev_attr_uid.attr,
&dev_attr_recover.attr,
+ &dev_attr_mio_enabled.attr,
NULL,
};
static struct attribute_group zpci_attr_group = {
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index c7c99e18d5ff..31a7d12db705 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -15,6 +15,7 @@ config SUPERH
select HAVE_ARCH_TRACEHOOK
select HAVE_PERF_EVENTS
select HAVE_DEBUG_BUGVERBOSE
+ select HAVE_FAST_GUP if MMU
select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
select ARCH_HAS_GCOV_PROFILE_ALL
@@ -64,6 +65,7 @@ config SUPERH
config SUPERH32
def_bool "$(ARCH)" = "sh"
select ARCH_32BIT_OFF_T
+ select GUP_GET_PTE_LOW_HIGH if X2TLB
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_IOREMAP_PROT if MMU && !X2TLB
diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig
index 4dcf7f552582..91d43e2bffea 100644
--- a/arch/sh/configs/hp6xx_defconfig
+++ b/arch/sh/configs/hp6xx_defconfig
@@ -40,7 +40,6 @@ CONFIG_FB=y
CONFIG_FIRMWARE_EDID=y
CONFIG_FB_HIT=y
CONFIG_FB_SH_MOBILE_LCDC=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FONTS=y
CONFIG_FONT_PEARL_8x8=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index 5209889765ad..49a29338789b 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -191,7 +191,6 @@ CONFIG_CONFIGFS_FS=y
CONFIG_JFFS2_FS=m
CONFIG_JFFS2_FS_XATTR=y
CONFIG_UBIFS_FS=m
-CONFIG_LOGFS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
CONFIG_ROMFS_FS=m
diff --git a/arch/sh/configs/sh2007_defconfig b/arch/sh/configs/sh2007_defconfig
index a1cf6447dbb1..cbd6742eb423 100644
--- a/arch/sh/configs/sh2007_defconfig
+++ b/arch/sh/configs/sh2007_defconfig
@@ -85,7 +85,6 @@ CONFIG_WATCHDOG=y
CONFIG_SH_WDT=y
CONFIG_SSB=y
CONFIG_FB=y
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index c28e37a344ad..ac0561960c52 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -369,7 +369,11 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
#define ioremap_nocache ioremap
#define ioremap_uc ioremap
-#define iounmap __iounmap
+
+static inline void iounmap(void __iomem *addr)
+{
+ __iounmap(addr);
+}
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index 7d8587eb65ff..779260b721ca 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -38,6 +38,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
return pud_val(pud);
}
+/* only used by the stubbed out hugetlb gup code, should never be called */
+#define pud_page(pud) NULL
+
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index 3587103afe59..9085d1142fa3 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -149,6 +149,43 @@ extern void paging_init(void);
extern void page_table_range_init(unsigned long start, unsigned long end,
pgd_t *pgd);
+static inline bool __pte_access_permitted(pte_t pte, u64 prot)
+{
+ return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot;
+}
+
+#ifdef CONFIG_X2TLB
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ u64 prot = _PAGE_PRESENT;
+
+ prot |= _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ);
+ if (write)
+ prot |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE);
+ return __pte_access_permitted(pte, prot);
+}
+#elif defined(CONFIG_SUPERH64)
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ u64 prot = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ;
+
+ if (write)
+ prot |= _PAGE_WRITE;
+ return __pte_access_permitted(pte, prot);
+}
+#else
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ u64 prot = _PAGE_PRESENT | _PAGE_USER;
+
+ if (write)
+ prot |= _PAGE_RW;
+ return __pte_access_permitted(pte, prot);
+}
+#endif
+
+#define pte_access_permitted pte_access_permitted
+
/* arch/sh/mm/mmap.c */
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 9143c7babcbe..6c89e3e04cee 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -16,8 +16,31 @@
#define user_mode(regs) (((regs)->sr & 0x40000000)==0)
#define kernel_stack_pointer(_regs) ((unsigned long)(_regs)->regs[15])
-#define GET_FP(regs) ((regs)->regs[14])
-#define GET_USP(regs) ((regs)->regs[15])
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return regs->pc;
+}
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->pc = val;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return regs->regs[14];
+}
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return regs->regs[15];
+}
+
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->regs[15] = val;
+}
#define arch_has_single_step() (1)
@@ -112,7 +135,5 @@ static inline unsigned long profile_pc(struct pt_regs *regs)
return pc;
}
-#define profile_pc profile_pc
-#include <asm-generic/ptrace.h>
#endif /* __ASM_SH_PTRACE_H */
diff --git a/arch/sh/kernel/kdebugfs.c b/arch/sh/kernel/kdebugfs.c
index 95428e05d212..8b505e1556a5 100644
--- a/arch/sh/kernel/kdebugfs.c
+++ b/arch/sh/kernel/kdebugfs.c
@@ -9,9 +9,6 @@ EXPORT_SYMBOL(arch_debugfs_dir);
static int __init arch_kdebugfs_init(void)
{
arch_debugfs_dir = debugfs_create_dir("sh", NULL);
- if (!arch_debugfs_dir)
- return -ENOMEM;
-
return 0;
}
arch_initcall(arch_kdebugfs_init);
diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile
index fbe5e79751b3..5051b38fd5b6 100644
--- a/arch/sh/mm/Makefile
+++ b/arch/sh/mm/Makefile
@@ -17,7 +17,7 @@ cacheops-$(CONFIG_CPU_SHX3) += cache-shx3.o
obj-y += $(cacheops-y)
mmu-y := nommu.o extable_32.o
-mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o gup.o ioremap.o kmap.o \
+mmu-$(CONFIG_MMU) := extable_$(BITS).o fault.o ioremap.o kmap.o \
pgtable.o tlbex_$(BITS).o tlbflush_$(BITS).o
obj-y += $(mmu-y)
diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c
index e5539e0f8e3b..4c1ca197e9c5 100644
--- a/arch/sh/mm/asids-debugfs.c
+++ b/arch/sh/mm/asids-debugfs.c
@@ -63,13 +63,8 @@ static const struct file_operations asids_debugfs_fops = {
static int __init asids_debugfs_init(void)
{
- struct dentry *asids_dentry;
-
- asids_dentry = debugfs_create_file("asids", S_IRUSR, arch_debugfs_dir,
- NULL, &asids_debugfs_fops);
- if (!asids_dentry)
- return -ENOMEM;
-
- return PTR_ERR_OR_ZERO(asids_dentry);
+ debugfs_create_file("asids", S_IRUSR, arch_debugfs_dir, NULL,
+ &asids_debugfs_fops);
+ return 0;
}
device_initcall(asids_debugfs_init);
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 4eb9d43578b4..17d780794497 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -109,22 +109,10 @@ static const struct file_operations cache_debugfs_fops = {
static int __init cache_debugfs_init(void)
{
- struct dentry *dcache_dentry, *icache_dentry;
-
- dcache_dentry = debugfs_create_file("dcache", S_IRUSR, arch_debugfs_dir,
- (unsigned int *)CACHE_TYPE_DCACHE,
- &cache_debugfs_fops);
- if (!dcache_dentry)
- return -ENOMEM;
-
- icache_dentry = debugfs_create_file("icache", S_IRUSR, arch_debugfs_dir,
- (unsigned int *)CACHE_TYPE_ICACHE,
- &cache_debugfs_fops);
- if (!icache_dentry) {
- debugfs_remove(dcache_dentry);
- return -ENOMEM;
- }
-
+ debugfs_create_file("dcache", S_IRUSR, arch_debugfs_dir,
+ (void *)CACHE_TYPE_DCACHE, &cache_debugfs_fops);
+ debugfs_create_file("icache", S_IRUSR, arch_debugfs_dir,
+ (void *)CACHE_TYPE_ICACHE, &cache_debugfs_fops);
return 0;
}
module_init(cache_debugfs_init);
diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
deleted file mode 100644
index 277c882f7489..000000000000
--- a/arch/sh/mm/gup.c
+++ /dev/null
@@ -1,277 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lockless get_user_pages_fast for SuperH
- *
- * Copyright (C) 2009 - 2010 Paul Mundt
- *
- * Cloned from the x86 and PowerPC versions, by:
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/vmstat.h>
-#include <linux/highmem.h>
-#include <asm/pgtable.h>
-
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
-#ifndef CONFIG_X2TLB
- return READ_ONCE(*ptep);
-#else
- /*
- * With get_user_pages_fast, we walk down the pagetables without
- * taking any locks. For this we would like to load the pointers
- * atomically, but that is not possible with 64-bit PTEs. What
- * we do have is the guarantee that a pte will only either go
- * from not present to present, or present to not present or both
- * -- it will not switch to a completely different present page
- * without a TLB flush in between; something that we are blocking
- * by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- * ptep->pte_high = h;
- * smp_wmb();
- * ptep->pte_low = l;
- *
- * And present to not present goes:
- * ptep->pte_low = 0;
- * smp_wmb();
- * ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees l iff pte_high
- * sees h. We load pte_high *after* loading pte_low, which ensures we
- * don't see an older value of pte_high. *Then* we recheck pte_low,
- * which ensures that we haven't picked up a changed pte high. We might
- * have got rubbish values from pte_low and pte_high, but we are
- * guaranteed that pte_low will not have the present bit set *unless*
- * it is 'l'. And get_user_pages_fast only operates on present ptes, so
- * we're safe.
- *
- * gup_get_pte should not be used or copied outside gup.c without being
- * very careful -- it does not atomically load the pte or anything that
- * is likely to be useful for you.
- */
- pte_t pte;
-
-retry:
- pte.pte_low = ptep->pte_low;
- smp_rmb();
- pte.pte_high = ptep->pte_high;
- smp_rmb();
- if (unlikely(pte.pte_low != ptep->pte_low))
- goto retry;
-
- return pte;
-#endif
-}
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- u64 mask, result;
- pte_t *ptep;
-
-#ifdef CONFIG_X2TLB
- result = _PAGE_PRESENT | _PAGE_EXT(_PAGE_EXT_KERN_READ | _PAGE_EXT_USER_READ);
- if (write)
- result |= _PAGE_EXT(_PAGE_EXT_KERN_WRITE | _PAGE_EXT_USER_WRITE);
-#elif defined(CONFIG_SUPERH64)
- result = _PAGE_PRESENT | _PAGE_USER | _PAGE_READ;
- if (write)
- result |= _PAGE_WRITE;
-#else
- result = _PAGE_PRESENT | _PAGE_USER;
- if (write)
- result |= _PAGE_RW;
-#endif
-
- mask = result | _PAGE_SPECIAL;
-
- ptep = pte_offset_map(&pmd, addr);
- do {
- pte_t pte = gup_get_pte(ptep);
- struct page *page;
-
- if ((pte_val(pte) & mask) != result) {
- pte_unmap(ptep);
- return 0;
- }
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- page = pte_page(pte);
- get_page(page);
- __flush_anon_page(page, addr);
- flush_dcache_page(page);
- pages[*nr] = page;
- (*nr)++;
-
- } while (ptep++, addr += PAGE_SIZE, addr != end);
- pte_unmap(ptep - 1);
-
- return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pmd_t *pmdp;
-
- pmdp = pmd_offset(&pud, addr);
- do {
- pmd_t pmd = *pmdp;
-
- next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
- return 0;
- if (!gup_pte_range(pmd, addr, next, write, pages, nr))
- return 0;
- } while (pmdp++, addr = next, addr != end);
-
- return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pud_t *pudp;
-
- pudp = pud_offset(&pgd, addr);
- do {
- pud_t pud = *pudp;
-
- next = pud_addr_end(addr, end);
- if (pud_none(pud))
- return 0;
- if (!gup_pmd_range(pud, addr, next, write, pages, nr))
- return 0;
- } while (pudp++, addr = next, addr != end);
-
- return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- unsigned long flags;
- pgd_t *pgdp;
- int nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
- if (unlikely(!access_ok((void __user *)start, len)))
- return 0;
-
- /*
- * This doesn't prevent pagetable teardown, but does prevent
- * the pagetables and pages from being freed.
- */
- local_irq_save(flags);
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- break;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
- break;
- } while (pgdp++, addr = next, addr != end);
- local_irq_restore(flags);
-
- return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying pin behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages,
- unsigned int gup_flags, struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- pgd_t *pgdp;
- int nr = 0;
-
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
-
- end = start + len;
- if (end < start)
- goto slow_irqon;
-
- local_irq_disable();
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- goto slow;
- if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
- pages, &nr))
- goto slow;
- } while (pgdp++, addr = next, addr != end);
- local_irq_enable();
-
- VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
- return nr;
-
- {
- int ret;
-
-slow:
- local_irq_enable();
-slow_irqon:
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
-
- ret = get_user_pages_unlocked(start,
- (end - start) >> PAGE_SHIFT, pages,
- gup_flags);
-
- /* Have to be a bit careful with return values */
- if (nr > 0) {
- if (ret < 0)
- ret = nr;
- else
- ret += nr;
- }
-
- return ret;
- }
-}
diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c
index a53a040d0054..b59bad86b31e 100644
--- a/arch/sh/mm/pmb.c
+++ b/arch/sh/mm/pmb.c
@@ -861,13 +861,8 @@ static const struct file_operations pmb_debugfs_fops = {
static int __init pmb_debugfs_init(void)
{
- struct dentry *dentry;
-
- dentry = debugfs_create_file("pmb", S_IFREG | S_IRUGO,
- arch_debugfs_dir, NULL, &pmb_debugfs_fops);
- if (!dentry)
- return -ENOMEM;
-
+ debugfs_create_file("pmb", S_IFREG | S_IRUGO, arch_debugfs_dir, NULL,
+ &pmb_debugfs_fops);
return 0;
}
subsys_initcall(pmb_debugfs_init);
diff --git a/arch/sh/mm/tlb-debugfs.c b/arch/sh/mm/tlb-debugfs.c
index dea637a09246..11c6148283f3 100644
--- a/arch/sh/mm/tlb-debugfs.c
+++ b/arch/sh/mm/tlb-debugfs.c
@@ -149,22 +149,10 @@ static const struct file_operations tlb_debugfs_fops = {
static int __init tlb_debugfs_init(void)
{
- struct dentry *itlb, *utlb;
-
- itlb = debugfs_create_file("itlb", S_IRUSR, arch_debugfs_dir,
- (unsigned int *)TLB_TYPE_ITLB,
- &tlb_debugfs_fops);
- if (unlikely(!itlb))
- return -ENOMEM;
-
- utlb = debugfs_create_file("utlb", S_IRUSR, arch_debugfs_dir,
- (unsigned int *)TLB_TYPE_UTLB,
- &tlb_debugfs_fops);
- if (unlikely(!utlb)) {
- debugfs_remove(itlb);
- return -ENOMEM;
- }
-
+ debugfs_create_file("itlb", S_IRUSR, arch_debugfs_dir,
+ (void *)TLB_TYPE_ITLB, &tlb_debugfs_fops);
+ debugfs_create_file("utlb", S_IRUSR, arch_debugfs_dir,
+ (void *)TLB_TYPE_UTLB, &tlb_debugfs_fops);
return 0;
}
module_init(tlb_debugfs_init);
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 26ab6f5bbaaf..e9f5d62e9817 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -28,6 +28,7 @@ config SPARC
select RTC_DRV_M48T59
select RTC_SYSTOHC
select HAVE_ARCH_JUMP_LABEL if SPARC64
+ select HAVE_FAST_GUP if SPARC64
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select GENERIC_PCI_IOMAP
@@ -300,9 +301,6 @@ config NODES_SPAN_OTHER_NODES
def_bool y
depends on NEED_MULTIPLE_NODES
-config ARCH_SELECT_MEMORY_MODEL
- def_bool y if SPARC64
-
config ARCH_SPARSEMEM_ENABLE
def_bool y if SPARC64
select SPARSEMEM_VMEMMAP_ENABLE
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 22500c3be7a9..1599de730532 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -864,6 +864,9 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
#define pgd_present(pgd) (pgd_val(pgd) != 0U)
#define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0UL)
+/* only used by the stubbed out hugetlb gup code, should never be called */
+#define pgd_page(pgd) NULL
+
static inline unsigned long pud_large(pud_t pud)
{
pte_t pte = __pte(pud_val(pud));
@@ -1075,6 +1078,46 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
}
#define io_remap_pfn_range io_remap_pfn_range
+static inline unsigned long untagged_addr(unsigned long start)
+{
+ if (adi_capable()) {
+ long addr = start;
+
+ /* If userspace has passed a versioned address, kernel
+ * will not find it in the VMAs since it does not store
+ * the version tags in the list of VMAs. Storing version
+ * tags in list of VMAs is impractical since they can be
+ * changed any time from userspace without dropping into
+ * kernel. Any address search in VMAs will be done with
+ * non-versioned addresses. Ensure the ADI version bits
+ * are dropped here by sign extending the last bit before
+ * ADI bits. IOMMU does not implement version tags.
+ */
+ return (addr << (long)adi_nbits()) >> (long)adi_nbits();
+ }
+
+ return start;
+}
+#define untagged_addr untagged_addr
+
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ u64 prot;
+
+ if (tlb_type == hypervisor) {
+ prot = _PAGE_PRESENT_4V | _PAGE_P_4V;
+ if (write)
+ prot |= _PAGE_WRITE_4V;
+ } else {
+ prot = _PAGE_PRESENT_4U | _PAGE_P_4U;
+ if (write)
+ prot |= _PAGE_WRITE_4U;
+ }
+
+ return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot;
+}
+#define pte_access_permitted pte_access_permitted
+
#include <asm/tlbflush.h>
#include <asm-generic/pgtable.h>
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index d39075b1e3b7..b078205b70e0 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -5,7 +5,7 @@
asflags-y := -ansi
ccflags-y := -Werror
-obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o
+obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
deleted file mode 100644
index 1e770a517d4a..000000000000
--- a/arch/sparc/mm/gup.c
+++ /dev/null
@@ -1,340 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lockless get_user_pages_fast for sparc, cribbed from powerpc
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-#include <asm/adi.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long mask, result;
- pte_t *ptep;
-
- if (tlb_type == hypervisor) {
- result = _PAGE_PRESENT_4V|_PAGE_P_4V;
- if (write)
- result |= _PAGE_WRITE_4V;
- } else {
- result = _PAGE_PRESENT_4U|_PAGE_P_4U;
- if (write)
- result |= _PAGE_WRITE_4U;
- }
- mask = result | _PAGE_SPECIAL;
-
- ptep = pte_offset_kernel(&pmd, addr);
- do {
- struct page *page, *head;
- pte_t pte = *ptep;
-
- if ((pte_val(pte) & mask) != result)
- return 0;
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- /* The hugepage case is simplified on sparc64 because
- * we encode the sub-page pfn offsets into the
- * hugepage PTEs. We could optimize this in the future
- * use page_cache_add_speculative() for the hugepage case.
- */
- page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- return 0;
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_page(head);
- return 0;
- }
-
- pages[*nr] = page;
- (*nr)++;
- } while (ptep++, addr += PAGE_SIZE, addr != end);
-
- return 1;
-}
-
-static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages,
- int *nr)
-{
- struct page *head, *page;
- int refs;
-
- if (!(pmd_val(pmd) & _PAGE_VALID))
- return 0;
-
- if (write && !pmd_write(pmd))
- return 0;
-
- refs = 0;
- page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- head = compound_head(page);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
- unsigned long end, int write, struct page **pages,
- int *nr)
-{
- struct page *head, *page;
- int refs;
-
- if (!(pud_val(pud) & _PAGE_VALID))
- return 0;
-
- if (write && !pud_write(pud))
- return 0;
-
- refs = 0;
- page = pud_page(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- head = compound_head(page);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pud_val(pud) != pud_val(*pudp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pmd_t *pmdp;
-
- pmdp = pmd_offset(&pud, addr);
- do {
- pmd_t pmd = *pmdp;
-
- next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
- return 0;
- if (unlikely(pmd_large(pmd))) {
- if (!gup_huge_pmd(pmdp, pmd, addr, next,
- write, pages, nr))
- return 0;
- } else if (!gup_pte_range(pmd, addr, next, write,
- pages, nr))
- return 0;
- } while (pmdp++, addr = next, addr != end);
-
- return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pud_t *pudp;
-
- pudp = pud_offset(&pgd, addr);
- do {
- pud_t pud = *pudp;
-
- next = pud_addr_end(addr, end);
- if (pud_none(pud))
- return 0;
- if (unlikely(pud_large(pud))) {
- if (!gup_huge_pud(pudp, pud, addr, next,
- write, pages, nr))
- return 0;
- } else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
- return 0;
- } while (pudp++, addr = next, addr != end);
-
- return 1;
-}
-
-/*
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next, flags;
- pgd_t *pgdp;
- int nr = 0;
-
-#ifdef CONFIG_SPARC64
- if (adi_capable()) {
- long addr = start;
-
- /* If userspace has passed a versioned address, kernel
- * will not find it in the VMAs since it does not store
- * the version tags in the list of VMAs. Storing version
- * tags in list of VMAs is impractical since they can be
- * changed any time from userspace without dropping into
- * kernel. Any address search in VMAs will be done with
- * non-versioned addresses. Ensure the ADI version bits
- * are dropped here by sign extending the last bit before
- * ADI bits. IOMMU does not implement version tags.
- */
- addr = (addr << (long)adi_nbits()) >> (long)adi_nbits();
- start = addr;
- }
-#endif
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- local_irq_save(flags);
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- break;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
- break;
- } while (pgdp++, addr = next, addr != end);
- local_irq_restore(flags);
-
- return nr;
-}
-
-int get_user_pages_fast(unsigned long start, int nr_pages,
- unsigned int gup_flags, struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- pgd_t *pgdp;
- int nr = 0;
-
-#ifdef CONFIG_SPARC64
- if (adi_capable()) {
- long addr = start;
-
- /* If userspace has passed a versioned address, kernel
- * will not find it in the VMAs since it does not store
- * the version tags in the list of VMAs. Storing version
- * tags in list of VMAs is impractical since they can be
- * changed any time from userspace without dropping into
- * kernel. Any address search in VMAs will be done with
- * non-versioned addresses. Ensure the ADI version bits
- * are dropped here by sign extending the last bit before
- * ADI bits. IOMMU does not implements version tags,
- */
- addr = (addr << (long)adi_nbits()) >> (long)adi_nbits();
- start = addr;
- }
-#endif
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- /*
- * XXX: batch / limit 'nr', to avoid large irq off latency
- * needs some instrumenting to determine the common sizes used by
- * important workloads (eg. DB2), and whether limiting the batch size
- * will decrease performance.
- *
- * It seems like we're in the clear for the moment. Direct-IO is
- * the main guy that batches up lots of get_user_pages, and even
- * they are limited to 64-at-a-time which is not so many.
- */
- /*
- * This doesn't prevent pagetable teardown, but does prevent
- * the pagetables from being freed on sparc.
- *
- * So long as we atomically load page table pointers versus teardown,
- * we can follow the address down to the the page and take a ref on it.
- */
- local_irq_disable();
-
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- goto slow;
- if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
- pages, &nr))
- goto slow;
- } while (pgdp++, addr = next, addr != end);
-
- local_irq_enable();
-
- VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
- return nr;
-
- {
- int ret;
-
-slow:
- local_irq_enable();
-
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
-
- ret = get_user_pages_unlocked(start,
- (end - start) >> PAGE_SHIFT, pages,
- gup_flags);
-
- /* Have to be a bit careful with return values */
- if (nr > 0) {
- if (ret < 0)
- ret = nr;
- else
- ret += nr;
- }
-
- return ret;
- }
-}
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 273130cf91d1..d2daa206872d 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -73,7 +73,7 @@ KBUILD_AFLAGS += $(ARCH_INCLUDE)
USER_CFLAGS = $(patsubst $(KERNEL_DEFINES),,$(patsubst -I%,,$(KBUILD_CFLAGS))) \
$(ARCH_INCLUDE) $(MODE_INCLUDE) $(filter -I%,$(CFLAGS)) \
-D_FILE_OFFSET_BITS=64 -idirafter $(srctree)/include \
- -idirafter $(obj)/include -D__KERNEL__ -D__UM_HOST__
+ -idirafter $(objtree)/include -D__KERNEL__ -D__UM_HOST__
#This will adjust *FLAGS accordingly to the platform.
include $(ARCH_DIR)/Makefile-os-$(OS)
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index 99eb5682792a..d7b282e9c4d5 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -10,6 +10,8 @@
#include <linux/mm.h>
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
#define pmd_populate_kernel(mm, pmd, pte) \
set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte)))
@@ -25,20 +27,6 @@
extern pgd_t *pgd_alloc(struct mm_struct *);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *);
-extern pgtable_t pte_alloc_one(struct mm_struct *);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- free_page((unsigned long) pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
#define __pte_free_tlb(tlb,pte, address) \
do { \
pgtable_page_dtor(pte); \
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index a9c9a94c096f..de58e976b9bc 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -208,28 +208,6 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
free_page((unsigned long) pgd);
}
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- pte_t *pte;
-
- pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
- return pte;
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- struct page *pte;
-
- pte = alloc_page(GFP_KERNEL|__GFP_ZERO);
- if (!pte)
- return NULL;
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- return NULL;
- }
- return pte;
-}
-
#ifdef CONFIG_3_LEVEL_PGTABLES
pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
diff --git a/arch/unicore32/Makefile b/arch/unicore32/Makefile
index 98a5ca43ae87..390819947c37 100644
--- a/arch/unicore32/Makefile
+++ b/arch/unicore32/Makefile
@@ -41,8 +41,7 @@ libs-y += arch/unicore32/lib/
boot := arch/unicore32/boot
-# Default defconfig and target when executing plain make
-KBUILD_DEFCONFIG := $(ARCH)_defconfig
+# Default target when executing plain make
KBUILD_IMAGE := $(boot)/zImage
all: zImage
diff --git a/arch/unicore32/configs/unicore32_defconfig b/arch/unicore32/configs/defconfig
index 360cc9abcdb0..360cc9abcdb0 100644
--- a/arch/unicore32/configs/unicore32_defconfig
+++ b/arch/unicore32/configs/defconfig
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
index ec64834b1c6a..3f0903bd98e9 100644
--- a/arch/unicore32/include/asm/pgalloc.h
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -14,6 +14,10 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+#define __HAVE_ARCH_PTE_ALLOC_ONE
+#include <asm-generic/pgalloc.h>
+
#define check_pgt_cache() do { } while (0)
#define _PAGE_USER_TABLE (PMD_TYPE_TABLE | PMD_PRESENT)
@@ -25,17 +29,14 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
#define pgd_alloc(mm) get_pgd_slow(mm)
#define pgd_free(mm, pgd) free_pgd_slow(mm, pgd)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
-
/*
* Allocate one PTE table.
*/
static inline pte_t *
pte_alloc_one_kernel(struct mm_struct *mm)
{
- pte_t *pte;
+ pte_t *pte = __pte_alloc_one_kernel(mm);
- pte = (pte_t *)__get_free_page(PGALLOC_GFP);
if (pte)
clean_dcache_area(pte, PTRS_PER_PTE * sizeof(pte_t));
@@ -47,35 +48,14 @@ pte_alloc_one(struct mm_struct *mm)
{
struct page *pte;
- pte = alloc_pages(PGALLOC_GFP, 0);
+ pte = __pte_alloc_one(mm, GFP_PGTABLE_USER);
if (!pte)
return NULL;
- if (!PageHighMem(pte)) {
- void *page = page_address(pte);
- clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t));
- }
- if (!pgtable_page_ctor(pte)) {
- __free_page(pte);
- }
-
+ if (!PageHighMem(pte))
+ clean_pte_table(page_address(pte));
return pte;
}
-/*
- * Free one PTE table.
- */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- if (pte)
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval)
{
set_pmd(pmdp, __pmd(pmdval));
diff --git a/arch/unicore32/include/mach/regs-gpio.h b/arch/unicore32/include/mach/regs-gpio.h
index 806350e1ccb6..5fc701ee33e3 100644
--- a/arch/unicore32/include/mach/regs-gpio.h
+++ b/arch/unicore32/include/mach/regs-gpio.h
@@ -32,7 +32,7 @@
*/
#define GPIO_GEDR (PKUNITY_GPIO_BASE + 0x0018)
/*
- * Sepcial Voltage Detect Reg GPIO_GPIR.
+ * Special Voltage Detect Reg GPIO_GPIR.
*/
#define GPIO_GPIR (PKUNITY_GPIO_BASE + 0x0020)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index dce10b18f4bc..9df2d1cb7a9e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -123,6 +123,7 @@ config X86
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
select GENERIC_GETTIMEOFDAY
+ select GUP_GET_PTE_LOW_HIGH if X86_PAE
select HARDLOCKUP_CHECK_TIMESTAMP if X86_64
select HAVE_ACPI_APEI if ACPI
select HAVE_ACPI_APEI_NMI if ACPI
@@ -158,6 +159,7 @@ config X86
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EISA
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
@@ -2906,9 +2908,6 @@ config HAVE_ATOMIC_IOMAP
config X86_DEV_DMA_OPS
bool
-config HAVE_GENERIC_GUP
- def_bool y
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 629d1ee05599..1cee10091b9f 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -358,7 +358,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
/* Create the ucontext. */
- if (boot_cpu_has(X86_FEATURE_XSAVE))
+ if (static_cpu_has(X86_FEATURE_XSAVE))
put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
else
put_user_ex(0, &frame->uc.uc_flags);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 8e790ec219a5..ba15d53c1ca7 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -49,23 +49,8 @@
#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3))
#define CONST_MASK(nr) (1 << ((nr) & 7))
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered. See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
static __always_inline void
-set_bit(long nr, volatile unsigned long *addr)
+arch_set_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -78,32 +63,14 @@ set_bit(long nr, volatile unsigned long *addr)
}
}
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered. However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
static __always_inline void
-clear_bit(long nr, volatile unsigned long *addr)
+arch_clear_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -115,26 +82,21 @@ clear_bit(long nr, volatile unsigned long *addr)
}
}
-/*
- * clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and implies release semantics before the memory
- * operation. It can be used for an unlock.
- */
-static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
{
barrier();
- clear_bit(nr, addr);
+ arch_clear_bit(nr, addr);
}
-static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
-static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
{
bool negative;
asm volatile(LOCK_PREFIX "andb %2,%1"
@@ -143,48 +105,23 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
: "ir" ((char) ~(1 << nr)) : "memory");
return negative;
}
+#define arch_clear_bit_unlock_is_negative_byte \
+ arch_clear_bit_unlock_is_negative_byte
-// Let everybody know we have it
-#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
-
-/*
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * __clear_bit() is non-atomic and implies release semantics before the memory
- * operation. It can be used for an unlock if no other CPUs can concurrently
- * modify other bits in the word.
- */
-static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
{
- __clear_bit(nr, addr);
+ arch___clear_bit(nr, addr);
}
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(long nr, volatile unsigned long *addr)
{
asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static __always_inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch_change_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -196,42 +133,20 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
}
}
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_set_bit(long nr, volatile unsigned long *addr)
{
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr);
}
-/**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
static __always_inline bool
-test_and_set_bit_lock(long nr, volatile unsigned long *addr)
+arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
{
- return test_and_set_bit(nr, addr);
+ return arch_test_and_set_bit(nr, addr);
}
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail. You must protect multiple accesses with a lock.
- */
-static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_set_bit(long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -242,28 +157,13 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
return oldbit;
}
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
{
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr);
}
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail. You must protect multiple accesses with a lock.
- *
+/*
* Note: the operation is performed atomically with respect to
* the local CPU, but not other CPUs. Portable code should not
* rely on this behaviour.
@@ -271,7 +171,8 @@ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *
* accessed from a hypervisor on the same CPU if running in a VM: don't change
* this without also updating arch/x86/kernel/kvm.c
*/
-static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -282,8 +183,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
return oldbit;
}
-/* WARNING: non atomic and it can be reordered! */
-static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_change_bit(long nr, volatile unsigned long *addr)
{
bool oldbit;
@@ -295,15 +196,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
return oldbit;
}
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_change_bit(long nr, volatile unsigned long *addr)
{
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
}
@@ -326,16 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
return oldbit;
}
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static bool test_bit(int nr, const volatile unsigned long *addr);
-#endif
-
-#define test_bit(nr, addr) \
+#define arch_test_bit(nr, addr) \
(__builtin_constant_p((nr)) \
? constant_test_bit((nr), (addr)) \
: variable_test_bit((nr), (addr)))
@@ -504,6 +389,8 @@ static __always_inline int fls64(__u64 x)
#include <asm-generic/bitops/const_hweight.h>
+#include <asm-generic/bitops-instrumented.h>
+
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 26d1eb83f72a..0cc5b611a113 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -686,6 +686,7 @@ struct kvm_vcpu_arch {
u32 virtual_tsc_mult;
u32 virtual_tsc_khz;
s64 ia32_tsc_adjust_msr;
+ u64 msr_ia32_power_ctl;
u64 tsc_scaling_ratio;
atomic_t nmi_queued; /* unprocessed asynchronous NMIs */
@@ -752,6 +753,8 @@ struct kvm_vcpu_arch {
struct gfn_to_hva_cache data;
} pv_eoi;
+ u64 msr_kvm_poll_control;
+
/*
* Indicate whether the access faults on its page table in guest
* which is set when fix page fault and used to detect unhandeable
@@ -879,6 +882,7 @@ struct kvm_arch {
bool mwait_in_guest;
bool hlt_in_guest;
bool pause_in_guest;
+ bool cstate_in_guest;
unsigned long irq_sources_bitmap;
s64 kvmclock_offset;
@@ -926,6 +930,8 @@ struct kvm_arch {
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
+
+ struct kvm_pmu_event_filter *pmu_event_filter;
};
struct kvm_vm_stat {
@@ -996,7 +1002,7 @@ struct kvm_x86_ops {
int (*disabled_by_bios)(void); /* __init */
int (*hardware_enable)(void);
void (*hardware_disable)(void);
- void (*check_processor_compatibility)(void *rtn);
+ int (*check_processor_compatibility)(void);/* __init */
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
bool (*cpu_has_accelerated_tpr)(void);
@@ -1110,7 +1116,7 @@ struct kvm_x86_ops {
int (*check_intercept)(struct kvm_vcpu *vcpu,
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
- void (*handle_external_intr)(struct kvm_vcpu *vcpu);
+ void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
bool (*mpx_supported)(void);
bool (*xsaves_supported)(void);
bool (*umip_emulated)(void);
@@ -1529,7 +1535,6 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
unsigned long ipi_bitmap_high, u32 min,
unsigned long icr, int op_64_bit);
-u64 kvm_get_arch_capabilities(void);
void kvm_define_shared_msr(unsigned index, u32 msr);
int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f4fa8a9d5d0b..2ef31cc8c529 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -3,84 +3,15 @@
#define _ASM_X86_MSHYPER_H
#include <linux/types.h>
-#include <linux/atomic.h>
#include <linux/nmi.h>
#include <asm/io.h>
#include <asm/hyperv-tlfs.h>
#include <asm/nospec-branch.h>
-#define VP_INVAL U32_MAX
-
-struct ms_hyperv_info {
- u32 features;
- u32 misc_features;
- u32 hints;
- u32 nested_features;
- u32 max_vp_index;
- u32 max_lp_index;
-};
-
-extern struct ms_hyperv_info ms_hyperv;
-
-
typedef int (*hyperv_fill_flush_list_func)(
struct hv_guest_mapping_flush_list *flush,
void *data);
-/*
- * Generate the guest ID.
- */
-
-static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
- __u64 d_info2)
-{
- __u64 guest_id = 0;
-
- guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
- guest_id |= (d_info1 << 48);
- guest_id |= (kernel_version << 16);
- guest_id |= d_info2;
-
- return guest_id;
-}
-
-
-/* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
-{
- /*
- * On crash we're reading some other CPU's message page and we need
- * to be careful: this other CPU may already had cleared the header
- * and the host may already had delivered some other message there.
- * In case we blindly write msg->header.message_type we're going
- * to lose it. We can still lose a message of the same type but
- * we count on the fact that there can only be one
- * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
- * on crash.
- */
- if (cmpxchg(&msg->header.message_type, old_msg_type,
- HVMSG_NONE) != old_msg_type)
- return;
-
- /*
- * Make sure the write to MessageType (ie set to
- * HVMSG_NONE) happens before we read the
- * MessagePending and EOMing. Otherwise, the EOMing
- * will not deliver any more messages since there is
- * no empty slot
- */
- mb();
-
- if (msg->header.message_flags.msg_pending) {
- /*
- * This will cause message queue rescan to
- * possibly deliver another msg from the
- * hypervisor
- */
- wrmsrl(HV_X64_MSR_EOM, 0);
- }
-}
-
#define hv_init_timer(timer, tick) \
wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick)
#define hv_init_timer_config(timer, val) \
@@ -97,6 +28,8 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
+#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0)
+
#define hv_get_synint_state(int_num, val) \
rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
#define hv_set_synint_state(int_num, val) \
@@ -122,13 +55,6 @@ void hyperv_reenlightenment_vector(void);
#define trace_hyperv_callback_vector hyperv_callback_vector
#endif
void hyperv_vector_handler(struct pt_regs *regs);
-void hv_setup_vmbus_irq(void (*handler)(void));
-void hv_remove_vmbus_irq(void);
-
-void hv_setup_kexec_handler(void (*handler)(void));
-void hv_remove_kexec_handler(void);
-void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
-void hv_remove_crash_handler(void);
/*
* Routines for stimer0 Direct Mode handling.
@@ -136,8 +62,6 @@ void hv_remove_crash_handler(void);
*/
void hv_stimer0_vector_handler(struct pt_regs *regs);
void hv_stimer0_callback_vector(void);
-int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void));
-void hv_remove_stimer0_irq(int irq);
static inline void hv_enable_stimer0_percpu_irq(int irq) {}
static inline void hv_disable_stimer0_percpu_irq(int irq) {}
@@ -282,14 +206,6 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
return status;
}
-/*
- * Hypervisor's notion of virtual processor ID is different from
- * Linux' notion of CPU ID. This information can only be retrieved
- * in the context of the calling CPU. Setup a map for easy access
- * to this information.
- */
-extern u32 *hv_vp_index;
-extern u32 hv_max_vp_index;
extern struct hv_vp_assist_page **hv_vp_assist_page;
static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -300,63 +216,8 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
return hv_vp_assist_page[cpu];
}
-/**
- * hv_cpu_number_to_vp_number() - Map CPU to VP.
- * @cpu_number: CPU number in Linux terms
- *
- * This function returns the mapping between the Linux processor
- * number and the hypervisor's virtual processor number, useful
- * in making hypercalls and such that talk about specific
- * processors.
- *
- * Return: Virtual processor number in Hyper-V terms
- */
-static inline int hv_cpu_number_to_vp_number(int cpu_number)
-{
- return hv_vp_index[cpu_number];
-}
-
-static inline int cpumask_to_vpset(struct hv_vpset *vpset,
- const struct cpumask *cpus)
-{
- int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
-
- /* valid_bank_mask can represent up to 64 banks */
- if (hv_max_vp_index / 64 >= 64)
- return 0;
-
- /*
- * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
- * structs are not cleared between calls, we risk flushing unneeded
- * vCPUs otherwise.
- */
- for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
- vpset->bank_contents[vcpu_bank] = 0;
-
- /*
- * Some banks may end up being empty but this is acceptable.
- */
- for_each_cpu(cpu, cpus) {
- vcpu = hv_cpu_number_to_vp_number(cpu);
- if (vcpu == VP_INVAL)
- return -1;
- vcpu_bank = vcpu / 64;
- vcpu_offset = vcpu % 64;
- __set_bit(vcpu_offset, (unsigned long *)
- &vpset->bank_contents[vcpu_bank]);
- if (vcpu_bank >= nr_bank)
- nr_bank = vcpu_bank + 1;
- }
- vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
- return nr_bank;
-}
-
void __init hyperv_init(void);
void hyperv_setup_mmu_ops(void);
-void hyperv_report_panic(struct pt_regs *regs, long err);
-void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
-bool hv_is_hyperv_initialized(void);
-void hyperv_cleanup(void);
void hyperv_reenlightenment_intr(struct pt_regs *regs);
void set_hv_tscchange_cb(void (*cb)(void));
@@ -379,8 +240,6 @@ static inline void hv_apic_init(void) {}
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
-static inline bool hv_is_hyperv_initialized(void) { return false; }
-static inline void hyperv_cleanup(void) {}
static inline void hyperv_setup_mmu_ops(void) {}
static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
static inline void clear_hv_tscchange_cb(void) {}
@@ -397,4 +256,7 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
}
#endif /* CONFIG_HYPERV */
+
+#include <asm-generic/mshyperv.h>
+
#endif
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a281e61ec60c..29aa7859bdee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,9 @@
#include <linux/mm.h> /* for struct page */
#include <linux/pagemap.h>
+#define __HAVE_ARCH_PTE_ALLOC_ONE
+#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */
+
static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
#ifdef CONFIG_PARAVIRT_XXL
@@ -47,24 +50,8 @@ extern gfp_t __userpte_alloc_gfp;
extern pgd_t *pgd_alloc(struct mm_struct *);
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *);
extern pgtable_t pte_alloc_one(struct mm_struct *);
-/* Should really implement gc for free page table pages. This could be
- done with a reference count in struct page. */
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
- free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
- pgtable_page_dtor(pte);
- __free_page(pte);
-}
-
extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte,
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f8b1ad2c3828..e3633795fb22 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \
__pteval_swp_offset(pte)))
-#define gup_get_pte gup_get_pte
-/*
- * WARNING: only to be used in the get_user_pages_fast() implementation.
- *
- * With get_user_pages_fast(), we walk down the pagetables without taking
- * any locks. For this we would like to load the pointers atomically,
- * but that is not possible (without expensive cmpxchg8b) on PAE. What
- * we do have is the guarantee that a PTE will only either go from not
- * present to present, or present to not present or both -- it will not
- * switch to a completely different present page without a TLB flush in
- * between; something that we are blocking by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- *
- * ptep->pte_high = h;
- * smp_wmb();
- * ptep->pte_low = l;
- *
- * And present to not present goes:
- *
- * ptep->pte_low = 0;
- * smp_wmb();
- * ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees 'l' iff pte_high
- * sees 'h'. We load pte_high *after* loading pte_low, which ensures we
- * don't see an older value of pte_high. *Then* we recheck pte_low,
- * which ensures that we haven't picked up a changed pte high. We might
- * have gotten rubbish values from pte_low and pte_high, but we are
- * guaranteed that pte_low will not have the present bit set *unless*
- * it is 'l'. Because get_user_pages_fast() only operates on present ptes
- * we're safe.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
- pte_t pte;
-
- do {
- pte.pte_low = ptep->pte_low;
- smp_rmb();
- pte.pte_high = ptep->pte_high;
- smp_rmb();
- } while (unlikely(pte.pte_low != ptep->pte_low));
-
- return pte;
-}
-
#include <asm/pgtable-invert.h>
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0bb566315621..4990d26dfc73 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -259,14 +259,8 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
#define gup_fast_permitted gup_fast_permitted
-static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
{
- unsigned long len, end;
-
- len = (unsigned long)nr_pages << PAGE_SHIFT;
- end = start + len;
- if (end < start)
- return false;
if (end >> __VIRTUAL_MASK_SHIFT)
return false;
return true;
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 78cf265c5b58..332eb3525867 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -98,7 +98,6 @@ struct cpuinfo_x86;
struct task_struct;
extern unsigned long profile_pc(struct pt_regs *regs);
-#define profile_pc profile_pc
extern unsigned long
convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
@@ -170,11 +169,32 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
return regs->sp;
}
-#define GET_IP(regs) ((regs)->ip)
-#define GET_FP(regs) ((regs)->bp)
-#define GET_USP(regs) ((regs)->sp)
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+ return regs->ip;
+}
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->ip = val;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+ return regs->bp;
+}
-#include <asm-generic/ptrace.h>
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+ return regs->sp;
+}
+
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+ unsigned long val)
+{
+ regs->sp = val;
+}
/* Query offset/name of register from its name/offset */
extern int regs_query_register_offset(const char *name);
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d6ab5b4d15e5..e901b0ab116f 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -378,10 +378,11 @@ struct kvm_sync_regs {
struct kvm_vcpu_events events;
};
-#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
-#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
-#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
-#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
@@ -432,4 +433,14 @@ struct kvm_nested_state {
} data;
};
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+ __u32 action;
+ __u32 nevents;
+ __u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 19980ec1a316..2a8e0b6b9805 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -29,6 +29,8 @@
#define KVM_FEATURE_PV_TLB_FLUSH 9
#define KVM_FEATURE_ASYNC_PF_VMEXIT 10
#define KVM_FEATURE_PV_SEND_IPI 11
+#define KVM_FEATURE_POLL_CONTROL 12
+#define KVM_FEATURE_PV_SCHED_YIELD 13
#define KVM_HINTS_REALTIME 0
@@ -47,6 +49,7 @@
#define MSR_KVM_ASYNC_PF_EN 0x4b564d02
#define MSR_KVM_STEAL_TIME 0x4b564d03
#define MSR_KVM_PV_EOI_EN 0x4b564d04
+#define MSR_KVM_POLL_CONTROL 0x4b564d05
struct kvm_steal_time {
__u64 steal;
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d213ec5c3766..f0b0c90dd398 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,7 +146,6 @@
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
-#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 7670ac2bda3a..edaa30b20841 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -67,33 +67,18 @@ static const struct file_operations fops_setup_data = {
.llseek = default_llseek,
};
-static int __init
+static void __init
create_setup_data_node(struct dentry *parent, int no,
struct setup_data_node *node)
{
- struct dentry *d, *type, *data;
+ struct dentry *d;
char buf[16];
sprintf(buf, "%d", no);
d = debugfs_create_dir(buf, parent);
- if (!d)
- return -ENOMEM;
-
- type = debugfs_create_x32("type", S_IRUGO, d, &node->type);
- if (!type)
- goto err_dir;
-
- data = debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
- if (!data)
- goto err_type;
- return 0;
-
-err_type:
- debugfs_remove(type);
-err_dir:
- debugfs_remove(d);
- return -ENOMEM;
+ debugfs_create_x32("type", S_IRUGO, d, &node->type);
+ debugfs_create_file("data", S_IRUGO, d, node, &fops_setup_data);
}
static int __init create_setup_data_nodes(struct dentry *parent)
@@ -106,8 +91,6 @@ static int __init create_setup_data_nodes(struct dentry *parent)
int no = 0;
d = debugfs_create_dir("setup_data", parent);
- if (!d)
- return -ENOMEM;
pa_data = boot_params.hdr.setup_data;
@@ -128,19 +111,17 @@ static int __init create_setup_data_nodes(struct dentry *parent)
node->paddr = pa_data;
node->type = data->type;
node->len = data->len;
- error = create_setup_data_node(d, no, node);
+ create_setup_data_node(d, no, node);
pa_data = data->next;
memunmap(data);
- if (error)
- goto err_dir;
no++;
}
return 0;
err_dir:
- debugfs_remove(d);
+ debugfs_remove_recursive(d);
return error;
}
@@ -151,35 +132,18 @@ static struct debugfs_blob_wrapper boot_params_blob = {
static int __init boot_params_kdebugfs_init(void)
{
- struct dentry *dbp, *version, *data;
- int error = -ENOMEM;
+ struct dentry *dbp;
+ int error;
dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
- if (!dbp)
- return -ENOMEM;
-
- version = debugfs_create_x16("version", S_IRUGO, dbp,
- &boot_params.hdr.version);
- if (!version)
- goto err_dir;
- data = debugfs_create_blob("data", S_IRUGO, dbp,
- &boot_params_blob);
- if (!data)
- goto err_version;
+ debugfs_create_x16("version", S_IRUGO, dbp, &boot_params.hdr.version);
+ debugfs_create_blob("data", S_IRUGO, dbp, &boot_params_blob);
error = create_setup_data_nodes(dbp);
if (error)
- goto err_data;
+ debugfs_remove_recursive(dbp);
- return 0;
-
-err_data:
- debugfs_remove(data);
-err_version:
- debugfs_remove(version);
-err_dir:
- debugfs_remove(dbp);
return error;
}
#endif /* CONFIG_DEBUG_BOOT_PARAMS */
@@ -189,8 +153,6 @@ static int __init arch_kdebugfs_init(void)
int error = 0;
arch_debugfs_dir = debugfs_create_dir("x86", NULL);
- if (!arch_debugfs_dir)
- return -ENOMEM;
#ifdef CONFIG_DEBUG_BOOT_PARAMS
error = boot_params_kdebugfs_init();
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5169b8cc35bb..82caf01b63dd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -527,6 +527,21 @@ static void kvm_setup_pv_ipi(void)
pr_info("KVM setup pv IPIs\n");
}
+static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
+{
+ int cpu;
+
+ native_send_call_func_ipi(mask);
+
+ /* Make sure other vCPUs get a chance to run if they need to. */
+ for_each_cpu(cpu, mask) {
+ if (vcpu_is_preempted(cpu)) {
+ kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
+ break;
+ }
+ }
+}
+
static void __init kvm_smp_prepare_cpus(unsigned int max_cpus)
{
native_smp_prepare_cpus(max_cpus);
@@ -638,6 +653,12 @@ static void __init kvm_guest_init(void)
#ifdef CONFIG_SMP
smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+ if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
+ !kvm_para_has_hint(KVM_HINTS_REALTIME) &&
+ kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi;
+ pr_info("KVM setup pv sched yield\n");
+ }
if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
kvm_cpu_online, kvm_cpu_down_prepare) < 0)
pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 7cf508f78c8c..8eb7193e158d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -391,7 +391,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
put_user_ex(&frame->uc, &frame->puc);
/* Create the ucontext. */
- if (boot_cpu_has(X86_FEATURE_XSAVE))
+ if (static_cpu_has(X86_FEATURE_XSAVE))
put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
else
put_user_ex(0, &frame->uc.uc_flags);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index fc042419e670..840e12583b85 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -41,6 +41,7 @@ config KVM
select PERF_EVENTS
select HAVE_KVM_MSI
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select HAVE_KVM_NO_POLL
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select KVM_VFIO
select SRCU
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 4992e7c99588..ead681210306 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -134,6 +134,16 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
+ if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
+ best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+ if (best) {
+ if (vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT)
+ best->ecx |= F(MWAIT);
+ else
+ best->ecx &= ~F(MWAIT);
+ }
+ }
+
/* Update physical-address width */
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -276,19 +286,38 @@ static void cpuid_mask(u32 *word, int wordnum)
*word &= boot_cpu_data.x86_capability[wordnum];
}
-static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+static void do_host_cpuid(struct kvm_cpuid_entry2 *entry, u32 function,
u32 index)
{
entry->function = function;
entry->index = index;
+ entry->flags = 0;
+
cpuid_count(entry->function, entry->index,
&entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
- entry->flags = 0;
+
+ switch (function) {
+ case 2:
+ entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+ break;
+ case 4:
+ case 7:
+ case 0xb:
+ case 0xd:
+ case 0x14:
+ case 0x8000001d:
+ entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ break;
+ }
}
-static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
- u32 func, u32 index, int *nent, int maxnent)
+static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry,
+ u32 func, int *nent, int maxnent)
{
+ entry->function = func;
+ entry->index = 0;
+ entry->flags = 0;
+
switch (func) {
case 0:
entry->eax = 7;
@@ -300,21 +329,83 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
break;
case 7:
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- if (index == 0)
- entry->ecx = F(RDPID);
+ entry->eax = 0;
+ entry->ecx = F(RDPID);
++*nent;
default:
break;
}
- entry->function = func;
- entry->index = index;
-
return 0;
}
-static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index, int *nent, int maxnent)
+static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
+{
+ unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
+ unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
+ unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
+ unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
+ unsigned f_la57;
+
+ /* cpuid 7.0.ebx */
+ const u32 kvm_cpuid_7_0_ebx_x86_features =
+ F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
+ F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
+ F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
+ F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
+ F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt;
+
+ /* cpuid 7.0.ecx*/
+ const u32 kvm_cpuid_7_0_ecx_x86_features =
+ F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+ F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
+ F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
+ F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B);
+
+ /* cpuid 7.0.edx*/
+ const u32 kvm_cpuid_7_0_edx_x86_features =
+ F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
+ F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
+ F(MD_CLEAR);
+
+ switch (index) {
+ case 0:
+ entry->eax = 0;
+ entry->ebx &= kvm_cpuid_7_0_ebx_x86_features;
+ cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
+ /* TSC_ADJUST is emulated */
+ entry->ebx |= F(TSC_ADJUST);
+
+ entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
+ f_la57 = entry->ecx & F(LA57);
+ cpuid_mask(&entry->ecx, CPUID_7_ECX);
+ /* Set LA57 based on hardware capability. */
+ entry->ecx |= f_la57;
+ entry->ecx |= f_umip;
+ /* PKU is not yet implemented for shadow paging. */
+ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
+ entry->ecx &= ~F(PKU);
+
+ entry->edx &= kvm_cpuid_7_0_edx_x86_features;
+ cpuid_mask(&entry->edx, CPUID_7_EDX);
+ /*
+ * We emulate ARCH_CAPABILITIES in software even
+ * if the host doesn't support it.
+ */
+ entry->edx |= F(ARCH_CAPABILITIES);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ entry->eax = 0;
+ entry->ebx = 0;
+ entry->ecx = 0;
+ entry->edx = 0;
+ break;
+ }
+}
+
+static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
+ int *nent, int maxnent)
{
int r;
unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -327,12 +418,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
unsigned f_lm = 0;
#endif
unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
- unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
- unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
- unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
- unsigned f_la57 = 0;
/* cpuid 1.edx */
const u32 kvm_cpuid_1_edx_x86_features =
@@ -377,7 +464,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
- F(AMD_SSB_NO) | F(AMD_STIBP);
+ F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
/* cpuid 0xC0000001.edx */
const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -385,31 +472,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
F(PMM) | F(PMM_EN);
- /* cpuid 7.0.ebx */
- const u32 kvm_cpuid_7_0_ebx_x86_features =
- F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
- F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
- F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
- F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
- F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | f_intel_pt;
-
/* cpuid 0xD.1.eax */
const u32 kvm_cpuid_D_1_eax_x86_features =
F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
- /* cpuid 7.0.ecx*/
- const u32 kvm_cpuid_7_0_ecx_x86_features =
- F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
- F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
- F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
- F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B);
-
- /* cpuid 7.0.edx*/
- const u32 kvm_cpuid_7_0_edx_x86_features =
- F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
- F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
- F(MD_CLEAR);
-
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -418,12 +484,13 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
if (*nent >= maxnent)
goto out;
- do_cpuid_1_ent(entry, function, index);
+ do_host_cpuid(entry, function, 0);
++*nent;
switch (function) {
case 0:
- entry->eax = min(entry->eax, (u32)(f_intel_pt ? 0x14 : 0xd));
+ /* Limited to the highest leaf implemented in KVM. */
+ entry->eax = min(entry->eax, 0x1fU);
break;
case 1:
entry->edx &= kvm_cpuid_1_edx_x86_features;
@@ -441,14 +508,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
case 2: {
int t, times = entry->eax & 0xff;
- entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
for (t = 1; t < times; ++t) {
if (*nent >= maxnent)
goto out;
- do_cpuid_1_ent(&entry[t], function, 0);
- entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
+ do_host_cpuid(&entry[t], function, 0);
++*nent;
}
break;
@@ -458,7 +523,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
case 0x8000001d: {
int i, cache_type;
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until cache_type is zero */
for (i = 1; ; ++i) {
if (*nent >= maxnent)
@@ -467,9 +531,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
cache_type = entry[i - 1].eax & 0x1f;
if (!cache_type)
break;
- do_cpuid_1_ent(&entry[i], function, i);
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ do_host_cpuid(&entry[i], function, i);
++*nent;
}
break;
@@ -480,36 +542,21 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ecx = 0;
entry->edx = 0;
break;
+ /* function 7 has additional index. */
case 7: {
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- /* Mask ebx against host capability word 9 */
- if (index == 0) {
- entry->ebx &= kvm_cpuid_7_0_ebx_x86_features;
- cpuid_mask(&entry->ebx, CPUID_7_0_EBX);
- // TSC_ADJUST is emulated
- entry->ebx |= F(TSC_ADJUST);
- entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
- f_la57 = entry->ecx & F(LA57);
- cpuid_mask(&entry->ecx, CPUID_7_ECX);
- /* Set LA57 based on hardware capability. */
- entry->ecx |= f_la57;
- entry->ecx |= f_umip;
- /* PKU is not yet implemented for shadow paging. */
- if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
- entry->ecx &= ~F(PKU);
- entry->edx &= kvm_cpuid_7_0_edx_x86_features;
- cpuid_mask(&entry->edx, CPUID_7_EDX);
- /*
- * We emulate ARCH_CAPABILITIES in software even
- * if the host doesn't support it.
- */
- entry->edx |= F(ARCH_CAPABILITIES);
- } else {
- entry->ebx = 0;
- entry->ecx = 0;
- entry->edx = 0;
+ int i;
+
+ for (i = 0; ; ) {
+ do_cpuid_7_mask(&entry[i], i);
+ if (i == entry->eax)
+ break;
+ if (*nent >= maxnent)
+ goto out;
+
+ ++i;
+ do_host_cpuid(&entry[i], function, i);
+ ++*nent;
}
- entry->eax = 0;
break;
}
case 9:
@@ -543,11 +590,14 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->edx = edx.full;
break;
}
- /* function 0xb has additional index. */
+ /*
+ * Per Intel's SDM, the 0x1f is a superset of 0xb,
+ * thus they can be handled by common code.
+ */
+ case 0x1f:
case 0xb: {
int i, level_type;
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until level_type is zero */
for (i = 1; ; ++i) {
if (*nent >= maxnent)
@@ -556,9 +606,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
level_type = entry[i - 1].ecx & 0xff00;
if (!level_type)
break;
- do_cpuid_1_ent(&entry[i], function, i);
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ do_host_cpuid(&entry[i], function, i);
++*nent;
}
break;
@@ -571,7 +619,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ebx = xstate_required_size(supported, false);
entry->ecx = entry->ebx;
entry->edx &= supported >> 32;
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
if (!supported)
break;
@@ -580,7 +627,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
if (*nent >= maxnent)
goto out;
- do_cpuid_1_ent(&entry[i], function, idx);
+ do_host_cpuid(&entry[i], function, idx);
if (idx == 1) {
entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
@@ -597,8 +644,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
entry[i].ecx = 0;
entry[i].edx = 0;
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
++i;
}
@@ -611,12 +656,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
if (!f_intel_pt)
break;
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
for (t = 1; t <= times; ++t) {
if (*nent >= maxnent)
goto out;
- do_cpuid_1_ent(&entry[t], function, t);
- entry[t].flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ do_host_cpuid(&entry[t], function, t);
++*nent;
}
break;
@@ -640,7 +683,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
(1 << KVM_FEATURE_PV_UNHALT) |
(1 << KVM_FEATURE_PV_TLB_FLUSH) |
(1 << KVM_FEATURE_ASYNC_PF_VMEXIT) |
- (1 << KVM_FEATURE_PV_SEND_IPI);
+ (1 << KVM_FEATURE_PV_SEND_IPI) |
+ (1 << KVM_FEATURE_POLL_CONTROL) |
+ (1 << KVM_FEATURE_PV_SCHED_YIELD);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
@@ -730,21 +775,19 @@ out:
return r;
}
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
- u32 idx, int *nent, int maxnent, unsigned int type)
+static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
+ int *nent, int maxnent, unsigned int type)
{
if (type == KVM_GET_EMULATED_CPUID)
- return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+ return __do_cpuid_func_emulated(entry, func, nent, maxnent);
- return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+ return __do_cpuid_func(entry, func, nent, maxnent);
}
#undef F
struct kvm_cpuid_param {
u32 func;
- u32 idx;
- bool has_leaf_count;
bool (*qualifier)(const struct kvm_cpuid_param *param);
};
@@ -788,11 +831,10 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
int limit, nent = 0, r = -E2BIG, i;
u32 func;
static const struct kvm_cpuid_param param[] = {
- { .func = 0, .has_leaf_count = true },
- { .func = 0x80000000, .has_leaf_count = true },
- { .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true },
+ { .func = 0 },
+ { .func = 0x80000000 },
+ { .func = 0xC0000000, .qualifier = is_centaur_cpu },
{ .func = KVM_CPUID_SIGNATURE },
- { .func = KVM_CPUID_FEATURES },
};
if (cpuid->nent < 1)
@@ -816,19 +858,16 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
if (ent->qualifier && !ent->qualifier(ent))
continue;
- r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
- &nent, cpuid->nent, type);
+ r = do_cpuid_func(&cpuid_entries[nent], ent->func,
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
- if (!ent->has_leaf_count)
- continue;
-
limit = cpuid_entries[nent - 1].eax;
for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
- r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
- &nent, cpuid->nent, type);
+ r = do_cpuid_func(&cpuid_entries[nent], func,
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4a387a235424..8e409ad448f9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4258,7 +4258,7 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt)
ulong dr6;
ctxt->ops->get_dr(ctxt, 6, &dr6);
- dr6 &= ~15;
+ dr6 &= ~DR_TRAP_BITS;
dr6 |= DR6_BD | DR6_RTM;
ctxt->ops->set_dr(ctxt, 6, dr6);
return emulate_db(ctxt);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index d6519a3aa959..7c6233d37c64 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -102,7 +102,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
return mode != KVM_IRQCHIP_NONE;
}
-bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 924b3bd5a7b7..8ecd48d31800 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -75,7 +75,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
if (r < 0)
r = 0;
r += kvm_apic_set_irq(vcpu, irq, dest_map);
- } else if (kvm_lapic_enabled(vcpu)) {
+ } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) {
if (!kvm_vector_hashing_enabled()) {
if (!lowest)
lowest = vcpu;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4dabc318adb8..a232e76d8f23 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -69,6 +69,7 @@
#define X2APIC_BROADCAST 0xFFFFFFFFul
#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
+#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000
/* step-by-step approximation to mitigate fluctuation */
#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
@@ -85,11 +86,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector)
apic_test_vector(vector, apic->regs + APIC_IRR);
}
-static inline void apic_clear_vector(int vec, void *bitmap)
-{
- clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
static inline int __apic_test_and_set_vector(int vec, void *bitmap)
{
return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -443,12 +439,12 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
if (unlikely(vcpu->arch.apicv_active)) {
/* need to update RVI */
- apic_clear_vector(vec, apic->regs + APIC_IRR);
+ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
kvm_x86_ops->hwapic_irr_update(vcpu,
apic_find_highest_irr(apic));
} else {
apic->irr_pending = false;
- apic_clear_vector(vec, apic->regs + APIC_IRR);
+ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
if (apic_search_irr(apic) != -1)
apic->irr_pending = true;
}
@@ -1053,9 +1049,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
if (trig_mode)
- kvm_lapic_set_vector(vector, apic->regs + APIC_TMR);
+ kvm_lapic_set_vector(vector,
+ apic->regs + APIC_TMR);
else
- apic_clear_vector(vector, apic->regs + APIC_TMR);
+ kvm_lapic_clear_vector(vector,
+ apic->regs + APIC_TMR);
}
if (vcpu->arch.apicv_active)
@@ -1313,21 +1311,45 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
return container_of(dev, struct kvm_lapic, dev);
}
+#define APIC_REG_MASK(reg) (1ull << ((reg) >> 4))
+#define APIC_REGS_MASK(first, count) \
+ (APIC_REG_MASK(first) * ((1ull << (count)) - 1))
+
int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
void *data)
{
unsigned char alignment = offset & 0xf;
u32 result;
/* this bitmask has a bit cleared for each reserved register */
- static const u64 rmask = 0x43ff01ffffffe70cULL;
-
- if ((alignment + len) > 4) {
- apic_debug("KVM_APIC_READ: alignment error %x %d\n",
- offset, len);
- return 1;
- }
+ u64 valid_reg_mask =
+ APIC_REG_MASK(APIC_ID) |
+ APIC_REG_MASK(APIC_LVR) |
+ APIC_REG_MASK(APIC_TASKPRI) |
+ APIC_REG_MASK(APIC_PROCPRI) |
+ APIC_REG_MASK(APIC_LDR) |
+ APIC_REG_MASK(APIC_DFR) |
+ APIC_REG_MASK(APIC_SPIV) |
+ APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) |
+ APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) |
+ APIC_REGS_MASK(APIC_IRR, APIC_ISR_NR) |
+ APIC_REG_MASK(APIC_ESR) |
+ APIC_REG_MASK(APIC_ICR) |
+ APIC_REG_MASK(APIC_ICR2) |
+ APIC_REG_MASK(APIC_LVTT) |
+ APIC_REG_MASK(APIC_LVTTHMR) |
+ APIC_REG_MASK(APIC_LVTPC) |
+ APIC_REG_MASK(APIC_LVT0) |
+ APIC_REG_MASK(APIC_LVT1) |
+ APIC_REG_MASK(APIC_LVTERR) |
+ APIC_REG_MASK(APIC_TMICT) |
+ APIC_REG_MASK(APIC_TMCCT) |
+ APIC_REG_MASK(APIC_TDCR);
+
+ /* ARBPRI is not valid on x2APIC */
+ if (!apic_x2apic_mode(apic))
+ valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI);
- if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) {
+ if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset))) {
apic_debug("KVM_APIC_READ: read reserved register %x\n",
offset);
return 1;
@@ -1499,11 +1521,40 @@ static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
}
}
-void wait_lapic_expire(struct kvm_vcpu *vcpu)
+static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
+ s64 advance_expire_delta)
{
struct kvm_lapic *apic = vcpu->arch.apic;
u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
- u64 guest_tsc, tsc_deadline, ns;
+ u64 ns;
+
+ /* too early */
+ if (advance_expire_delta < 0) {
+ ns = -advance_expire_delta * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ timer_advance_ns -= min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ } else {
+ /* too late */
+ ns = advance_expire_delta * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ timer_advance_ns += min((u32)ns,
+ timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ }
+
+ if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
+ apic->lapic_timer.timer_advance_adjust_done = true;
+ if (unlikely(timer_advance_ns > 5000)) {
+ timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+ apic->lapic_timer.timer_advance_adjust_done = false;
+ }
+ apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+}
+
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
+{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u64 guest_tsc, tsc_deadline;
if (apic->lapic_timer.expired_tscdeadline == 0)
return;
@@ -1514,34 +1565,15 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
tsc_deadline = apic->lapic_timer.expired_tscdeadline;
apic->lapic_timer.expired_tscdeadline = 0;
guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
- trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
+ apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;
if (guest_tsc < tsc_deadline)
__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
- if (!apic->lapic_timer.timer_advance_adjust_done) {
- /* too early */
- if (guest_tsc < tsc_deadline) {
- ns = (tsc_deadline - guest_tsc) * 1000000ULL;
- do_div(ns, vcpu->arch.virtual_tsc_khz);
- timer_advance_ns -= min((u32)ns,
- timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
- } else {
- /* too late */
- ns = (guest_tsc - tsc_deadline) * 1000000ULL;
- do_div(ns, vcpu->arch.virtual_tsc_khz);
- timer_advance_ns += min((u32)ns,
- timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
- }
- if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
- apic->lapic_timer.timer_advance_adjust_done = true;
- if (unlikely(timer_advance_ns > 5000)) {
- timer_advance_ns = 0;
- apic->lapic_timer.timer_advance_adjust_done = true;
- }
- apic->lapic_timer.timer_advance_ns = timer_advance_ns;
- }
+ if (unlikely(!apic->lapic_timer.timer_advance_adjust_done))
+ adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
}
+EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire);
static void start_sw_tscdeadline(struct kvm_lapic *apic)
{
@@ -2014,7 +2046,7 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
apic_debug("%s: offset 0x%x with length 0x%x, and value is "
"0x%x\n", __func__, offset, len, val);
- kvm_lapic_reg_write(apic, offset & 0xff0, val);
+ kvm_lapic_reg_write(apic, offset, val);
return 0;
}
@@ -2311,7 +2343,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
HRTIMER_MODE_ABS_PINNED);
apic->lapic_timer.timer.function = apic_timer_fn;
if (timer_advance_ns == -1) {
- apic->lapic_timer.timer_advance_ns = 1000;
+ apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
apic->lapic_timer.timer_advance_adjust_done = false;
} else {
apic->lapic_timer.timer_advance_ns = timer_advance_ns;
@@ -2321,7 +2353,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
/*
* APIC is created enabled. This will prevent kvm_lapic_set_base from
- * thinking that APIC satet has changed.
+ * thinking that APIC state has changed.
*/
vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
@@ -2330,6 +2362,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
return 0;
nomem_free_apic:
kfree(apic);
+ vcpu->arch.apic = NULL;
nomem:
return -ENOMEM;
}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index d6d049ba3045..36747174e4a8 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -32,6 +32,7 @@ struct kvm_timer {
u64 tscdeadline;
u64 expired_tscdeadline;
u32 timer_advance_ns;
+ s64 advance_expire_delta;
atomic_t pending; /* accumulated triggered timers */
bool hv_timer_in_use;
bool timer_advance_adjust_done;
@@ -129,6 +130,11 @@ void kvm_lapic_exit(void);
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
+static inline void kvm_lapic_clear_vector(int vec, void *bitmap)
+{
+ clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
static inline void kvm_lapic_set_vector(int vec, void *bitmap)
{
set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -219,7 +225,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
-void wait_lapic_expire(struct kvm_vcpu *vcpu);
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 98f6e4f88b04..9a5814d8d194 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -140,9 +140,6 @@ module_param(dbg, bool, 0644);
#include <trace/events/kvm.h>
-#define CREATE_TRACE_POINTS
-#include "mmutrace.h"
-
#define SPTE_HOST_WRITEABLE (1ULL << PT_FIRST_AVAIL_BITS_SHIFT)
#define SPTE_MMU_WRITEABLE (1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
@@ -259,11 +256,20 @@ static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
*/
static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+/*
+ * The number of non-reserved physical address bits irrespective of features
+ * that repurpose legal bits, e.g. MKTME.
+ */
+static u8 __read_mostly shadow_phys_bits;
static void mmu_spte_set(u64 *sptep, u64 spte);
+static bool is_executable_pte(u64 spte);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
+#define CREATE_TRACE_POINTS
+#include "mmutrace.h"
+
static inline bool kvm_available_flush_tlb_with_range(void)
{
@@ -468,6 +474,21 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
+static u8 kvm_get_shadow_phys_bits(void)
+{
+ /*
+ * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
+ * in CPU detection code, but MKTME treats those reduced bits as
+ * 'keyID' thus they are not reserved bits. Therefore for MKTME
+ * we should still return physical address bits reported by CPUID.
+ */
+ if (!boot_cpu_has(X86_FEATURE_TME) ||
+ WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
+ return boot_cpu_data.x86_phys_bits;
+
+ return cpuid_eax(0x80000008) & 0xff;
+}
+
static void kvm_mmu_reset_all_pte_masks(void)
{
u8 low_phys_bits;
@@ -481,6 +502,8 @@ static void kvm_mmu_reset_all_pte_masks(void)
shadow_present_mask = 0;
shadow_acc_track_mask = 0;
+ shadow_phys_bits = kvm_get_shadow_phys_bits();
+
/*
* If the CPU has 46 or less physical address bits, then set an
* appropriate mask to guard against L1TF attacks. Otherwise, it is
@@ -650,7 +673,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
/*
* The idea using the light way get the spte on x86_32 guest is from
- * gup_get_pte(arch/x86/mm/gup.c).
+ * gup_get_pte (mm/gup.c).
*
* An spte tlb flush may be pending, because kvm_set_pte_rmapp
* coalesces them and we are running out of the MMU lock. Therefore
@@ -1073,10 +1096,16 @@ static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index)
static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn)
{
- if (sp->role.direct)
- BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index));
- else
+ if (!sp->role.direct) {
sp->gfns[index] = gfn;
+ return;
+ }
+
+ if (WARN_ON(gfn != kvm_mmu_page_get_gfn(sp, index)))
+ pr_err_ratelimited("gfn mismatch under direct page %llx "
+