aboutsummaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/mm/fault.c2
-rw-r--r--arch/arc/Makefile4
-rw-r--r--arch/arc/include/asm/pgtable.h2
-rw-r--r--arch/arc/kernel/setup.c1
-rw-r--r--arch/arc/kernel/time.c48
-rw-r--r--arch/arc/mm/dma.c3
-rw-r--r--arch/arc/mm/fault.c2
-rw-r--r--arch/arc/mm/ioremap.c2
-rw-r--r--arch/arm/Kconfig54
-rw-r--r--arch/arm/Makefile1
-rw-r--r--arch/arm/boot/Makefile6
-rw-r--r--arch/arm/boot/dts/am33xx.dtsi3
-rw-r--r--arch/arm/boot/dts/am4372.dtsi3
-rw-r--r--arch/arm/boot/dts/am57xx-beagle-x15.dts2
-rw-r--r--arch/arm/boot/dts/dm814x.dtsi1
-rw-r--r--arch/arm/boot/dts/dra7.dtsi3
-rw-r--r--arch/arm/boot/dts/kirkwood-ns2lite.dts2
-rw-r--r--arch/arm/boot/dts/kirkwood-topkick.dts2
-rw-r--r--arch/arm/boot/dts/meson8-minix-neo-x8.dts1
-rw-r--r--arch/arm/boot/dts/rk3288.dtsi5
-rw-r--r--arch/arm/boot/dts/socfpga_arria10.dtsi16
-rw-r--r--arch/arm/boot/dts/vf610-zii-dev-rev-b.dts328
-rw-r--r--arch/arm/configs/collie_defconfig2
-rw-r--r--arch/arm/configs/ixp4xx_defconfig2
-rw-r--r--arch/arm/include/asm/assembler.h4
-rw-r--r--arch/arm/include/asm/barrier.h4
-rw-r--r--arch/arm/include/asm/delay.h6
-rw-r--r--arch/arm/include/asm/floppy.h2
-rw-r--r--arch/arm/include/asm/io.h2
-rw-r--r--arch/arm/include/asm/pgalloc.h2
-rw-r--r--arch/arm/include/asm/ptrace.h10
-rw-r--r--arch/arm/include/asm/tlb.h29
-rw-r--r--arch/arm/include/asm/uaccess.h114
-rw-r--r--arch/arm/include/asm/xen/hypercall.h1
-rw-r--r--arch/arm/include/asm/xen/xen-ops.h6
-rw-r--r--arch/arm/kernel/asm-offsets.c5
-rw-r--r--arch/arm/kernel/cpuidle.c23
-rw-r--r--arch/arm/kernel/devtree.c3
-rw-r--r--arch/arm/kernel/entry-armv.S19
-rw-r--r--arch/arm/kernel/entry-common.S2
-rw-r--r--arch/arm/kernel/entry-header.S12
-rw-r--r--arch/arm/kernel/entry-v7m.S2
-rw-r--r--arch/arm/kernel/process.c14
-rw-r--r--arch/arm/kernel/setup.c4
-rw-r--r--arch/arm/kernel/smp_tlb.c44
-rw-r--r--arch/arm/kernel/smp_twd.c31
-rw-r--r--arch/arm/kernel/vmlinux.lds.S4
-rw-r--r--arch/arm/lib/Makefile5
-rw-r--r--arch/arm/lib/delay-loop.S15
-rw-r--r--arch/arm/mach-davinci/board-dm644x-evm.c2
-rw-r--r--arch/arm/mach-mvebu/coherency.c19
-rw-r--r--arch/arm/mach-omap1/board-osk.c2
-rw-r--r--arch/arm/mach-pxa/spitz.c2
-rw-r--r--arch/arm/mm/Kconfig6
-rw-r--r--arch/arm/mm/cache-l2x0.c27
-rw-r--r--arch/arm/mm/dma-mapping.c144
-rw-r--r--arch/arm/mm/fault.c2
-rw-r--r--arch/arm/mm/pgd.c2
-rw-r--r--arch/arm/mm/proc-v7.S43
-rw-r--r--arch/arm/vfp/vfpmodule.c28
-rw-r--r--arch/arm/xen/Makefile1
-rw-r--r--arch/arm/xen/efi.c40
-rw-r--r--arch/arm/xen/enlighten.c194
-rw-r--r--arch/arm/xen/hypercall.S1
-rw-r--r--arch/arm64/Kconfig17
-rw-r--r--arch/arm64/Makefile11
-rw-r--r--arch/arm64/boot/Makefile2
-rw-r--r--arch/arm64/boot/dts/apm/apm-merlin.dts6
-rw-r--r--arch/arm64/boot/dts/apm/apm-mustang.dts12
-rw-r--r--arch/arm64/boot/dts/apm/apm-shadowcat.dtsi11
-rw-r--r--arch/arm64/boot/dts/apm/apm-storm.dtsi26
-rw-r--r--arch/arm64/boot/dts/broadcom/ns2-svk.dts16
-rw-r--r--arch/arm64/boot/dts/broadcom/ns2.dtsi39
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8173.dtsi62
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/include/asm/Kbuild1
-rw-r--r--arch/arm64/include/asm/acpi.h10
-rw-r--r--arch/arm64/include/asm/alternative.h16
-rw-r--r--arch/arm64/include/asm/assembler.h12
-rw-r--r--arch/arm64/include/asm/checksum.h51
-rw-r--r--arch/arm64/include/asm/cpu.h2
-rw-r--r--arch/arm64/include/asm/cpufeature.h2
-rw-r--r--arch/arm64/include/asm/debug-monitors.h5
-rw-r--r--arch/arm64/include/asm/efi.h3
-rw-r--r--arch/arm64/include/asm/esr.h1
-rw-r--r--arch/arm64/include/asm/insn.h41
-rw-r--r--arch/arm64/include/asm/irqflags.h3
-rw-r--r--arch/arm64/include/asm/kexec.h48
-rw-r--r--arch/arm64/include/asm/kprobes.h62
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h2
-rw-r--r--arch/arm64/include/asm/mmu.h2
-rw-r--r--arch/arm64/include/asm/numa.h2
-rw-r--r--arch/arm64/include/asm/probes.h35
-rw-r--r--arch/arm64/include/asm/processor.h1
-rw-r--r--arch/arm64/include/asm/ptdump.h44
-rw-r--r--arch/arm64/include/asm/ptrace.h64
-rw-r--r--arch/arm64/include/asm/sysreg.h2
-rw-r--r--arch/arm64/include/asm/traps.h2
-rw-r--r--arch/arm64/include/asm/uaccess.h25
-rw-r--r--arch/arm64/include/asm/vdso_datapage.h8
-rw-r--r--arch/arm64/include/asm/virt.h5
-rw-r--r--arch/arm64/include/asm/xen/xen-ops.h6
-rw-r--r--arch/arm64/kernel/Makefile12
-rw-r--r--arch/arm64/kernel/acpi_numa.c112
-rw-r--r--arch/arm64/kernel/arm64ksyms.c6
-rw-r--r--arch/arm64/kernel/armv8_deprecated.c66
-rw-r--r--arch/arm64/kernel/asm-offsets.c17
-rw-r--r--arch/arm64/kernel/cpu-reset.S54
-rw-r--r--arch/arm64/kernel/cpu-reset.h34
-rw-r--r--arch/arm64/kernel/cpu_errata.c7
-rw-r--r--arch/arm64/kernel/cpufeature.c4
-rw-r--r--arch/arm64/kernel/cpuidle.c20
-rw-r--r--arch/arm64/kernel/cpuinfo.c120
-rw-r--r--arch/arm64/kernel/debug-monitors.c47
-rw-r--r--arch/arm64/kernel/efi.c50
-rw-r--r--arch/arm64/kernel/entry.S17
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c8
-rw-r--r--arch/arm64/kernel/hyp-stub.S10
-rw-r--r--arch/arm64/kernel/insn.c133
-rw-r--r--arch/arm64/kernel/kgdb.c4
-rw-r--r--arch/arm64/kernel/machine_kexec.c212
-rw-r--r--arch/arm64/kernel/probes/Makefile3
-rw-r--r--arch/arm64/kernel/probes/decode-insn.c174
-rw-r--r--arch/arm64/kernel/probes/decode-insn.h35
-rw-r--r--arch/arm64/kernel/probes/kprobes.c686
-rw-r--r--arch/arm64/kernel/probes/kprobes_trampoline.S81
-rw-r--r--arch/arm64/kernel/probes/simulate-insn.c217
-rw-r--r--arch/arm64/kernel/probes/simulate-insn.h28
-rw-r--r--arch/arm64/kernel/ptrace.c101
-rw-r--r--arch/arm64/kernel/relocate_kernel.S130
-rw-r--r--arch/arm64/kernel/setup.c11
-rw-r--r--arch/arm64/kernel/smp.c12
-rw-r--r--arch/arm64/kernel/traps.c152
-rw-r--r--arch/arm64/kernel/vdso.c8
-rw-r--r--arch/arm64/kernel/vdso/Makefile7
-rw-r--r--arch/arm64/kernel/vdso/gettimeofday.S331
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S9
-rw-r--r--arch/arm64/kvm/handle_exit.c4
-rw-r--r--arch/arm64/kvm/hyp/Makefile4
-rw-r--r--arch/arm64/kvm/hyp/switch.c2
-rw-r--r--arch/arm64/lib/copy_from_user.S4
-rw-r--r--arch/arm64/lib/copy_to_user.S4
-rw-r--r--arch/arm64/mm/cache.S2
-rw-r--r--arch/arm64/mm/dma-mapping.c37
-rw-r--r--arch/arm64/mm/dump.c32
-rw-r--r--arch/arm64/mm/fault.c43
-rw-r--r--arch/arm64/mm/init.c15
-rw-r--r--arch/arm64/mm/mmu.c154
-rw-r--r--arch/arm64/mm/numa.c28
-rw-r--r--arch/arm64/mm/proc.S2
-rw-r--r--arch/arm64/net/bpf_jit.h3
-rw-r--r--arch/arm64/net/bpf_jit_comp.c111
-rw-r--r--arch/arm64/xen/Makefile1
-rw-r--r--arch/arm64/xen/hypercall.S1
-rw-r--r--arch/avr32/include/uapi/asm/unistd.h646
-rw-r--r--arch/avr32/kernel/syscall-stubs.S18
-rw-r--r--arch/avr32/kernel/syscall_table.S662
-rw-r--r--arch/avr32/mach-at32ap/pio.c2
-rw-r--r--arch/avr32/mm/fault.c2
-rw-r--r--arch/blackfin/kernel/perf_event.c26
-rw-r--r--arch/blackfin/mach-bf609/boards/ezkit.c2
-rw-r--r--arch/cris/mm/fault.c2
-rw-r--r--arch/frv/mm/fault.c2
-rw-r--r--arch/hexagon/Kconfig3
-rw-r--r--arch/hexagon/mm/vm_fault.c2
-rw-r--r--arch/ia64/Kconfig1
-rw-r--r--arch/ia64/include/asm/acpi.h3
-rw-r--r--arch/ia64/include/asm/tlb.h31
-rw-r--r--arch/ia64/kernel/acpi.c2
-rw-r--r--arch/ia64/kernel/setup.c1
-rw-r--r--arch/ia64/mm/fault.c2
-rw-r--r--arch/m32r/kernel/m32r_ksyms.c3
-rw-r--r--arch/m32r/lib/Makefile4
-rw-r--r--arch/m32r/lib/libgcc.h23
-rw-r--r--arch/m32r/lib/ucmpdi2.c17
-rw-r--r--arch/m32r/mm/fault.c2
-rw-r--r--arch/m68k/mm/fault.c2
-rw-r--r--arch/metag/kernel/perf/perf_event.c26
-rw-r--r--arch/metag/mm/fault.c2
-rw-r--r--arch/microblaze/Kconfig1
-rw-r--r--arch/microblaze/mm/fault.c2
-rw-r--r--arch/mips/configs/malta_qemu_32r6_defconfig2
-rw-r--r--arch/mips/configs/maltaaprp_defconfig2
-rw-r--r--arch/mips/configs/maltasmvp_eva_defconfig2
-rw-r--r--arch/mips/configs/maltaup_defconfig2
-rw-r--r--arch/mips/configs/rbtx49xx_defconfig2
-rw-r--r--arch/mips/include/asm/octeon/cvmx-mpi-defs.h328
-rw-r--r--arch/mips/mm/fault.c2
-rw-r--r--arch/mips/oprofile/op_model_loongson3.c35
-rw-r--r--arch/mips/txx9/generic/setup.c2
-rw-r--r--arch/mips/txx9/rbtx4939/setup.c2
-rw-r--r--arch/mn10300/mm/fault.c2
-rw-r--r--arch/nios2/mm/fault.c2
-rw-r--r--arch/openrisc/Kconfig2
-rw-r--r--arch/openrisc/mm/fault.c2
-rw-r--r--arch/parisc/configs/generic-32bit_defconfig2
-rw-r--r--arch/parisc/configs/generic-64bit_defconfig2
-rw-r--r--arch/parisc/mm/fault.c2
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/boot/dts/mpc8315erdb.dts2
-rw-r--r--arch/powerpc/boot/dts/mpc8377_rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/mpc8378_rdb.dts2
-rw-r--r--arch/powerpc/boot/dts/mpc8379_rdb.dts2
-rw-r--r--arch/powerpc/configs/pmac32_defconfig2
-rw-r--r--arch/powerpc/configs/ppc6xx_defconfig2
-rw-r--r--arch/powerpc/include/asm/pgtable.h6
-rw-r--r--arch/powerpc/kernel/nvram_64.c4
-rw-r--r--arch/powerpc/mm/copro_fault.c2
-rw-r--r--arch/powerpc/mm/fault.c2
-rw-r--r--arch/powerpc/mm/numa.c48
-rw-r--r--arch/powerpc/perf/core-book3s.c30
-rw-r--r--arch/powerpc/platforms/40x/Kconfig2
-rw-r--r--arch/powerpc/platforms/44x/Kconfig2
-rw-r--r--arch/powerpc/platforms/512x/Kconfig1
-rw-r--r--arch/powerpc/platforms/83xx/Kconfig3
-rw-r--r--arch/powerpc/platforms/85xx/Kconfig4
-rw-r--r--arch/powerpc/platforms/86xx/Kconfig7
-rw-r--r--arch/powerpc/platforms/8xx/Kconfig2
-rw-r--r--arch/powerpc/platforms/Kconfig8
-rw-r--r--arch/powerpc/sysdev/axonram.c4
-rw-r--r--arch/s390/appldata/appldata_mem.c2
-rw-r--r--arch/s390/include/asm/tlb.h22
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c46
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c54
-rw-r--r--arch/s390/mm/fault.c2
-rw-r--r--arch/score/mm/fault.c2
-rw-r--r--arch/sh/Kconfig11
-rw-r--r--arch/sh/boards/Kconfig17
-rw-r--r--arch/sh/boards/mach-highlander/Kconfig2
-rw-r--r--arch/sh/boards/mach-rsk/Kconfig6
-rw-r--r--arch/sh/include/asm/tlb.h20
-rw-r--r--arch/sh/kernel/perf_event.c23
-rw-r--r--arch/sh/mm/fault.c2
-rw-r--r--arch/sparc/include/asm/hugetlb.h12
-rw-r--r--arch/sparc/include/asm/mmu_64.h3
-rw-r--r--arch/sparc/include/asm/pgtable_64.h7
-rw-r--r--arch/sparc/include/asm/tsb.h2
-rw-r--r--arch/sparc/kernel/dtlb_prot.S4
-rw-r--r--arch/sparc/kernel/irq_32.c4
-rw-r--r--arch/sparc/kernel/ktlb.S12
-rw-r--r--arch/sparc/kernel/tsb.S12
-rw-r--r--arch/sparc/mm/fault_32.c4
-rw-r--r--arch/sparc/mm/fault_64.c12
-rw-r--r--arch/sparc/mm/hugetlbpage.c170
-rw-r--r--arch/sparc/mm/init_64.c7
-rw-r--r--arch/sparc/mm/tlb.c4
-rw-r--r--arch/sparc/mm/tsb.c14
-rw-r--r--arch/tile/include/asm/elf.h1
-rw-r--r--arch/tile/include/asm/setup.h5
-rw-r--r--arch/tile/include/uapi/asm/auxvec.h2
-rw-r--r--arch/tile/kernel/compat.c35
-rw-r--r--arch/tile/kernel/sys.c13
-rw-r--r--arch/tile/lib/exports.c6
-rw-r--r--arch/tile/mm/fault.c2
-rw-r--r--arch/tile/mm/pgtable.c18
-rw-r--r--arch/um/include/asm/tlb.h20
-rw-r--r--arch/um/kernel/trap.c2
-rw-r--r--arch/unicore32/Kconfig2
-rw-r--r--arch/unicore32/configs/unicore32_defconfig2
-rw-r--r--arch/unicore32/kernel/gpio.c2
-rw-r--r--arch/unicore32/mm/fault.c2
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/entry/vdso/vma.c20
-rw-r--r--arch/x86/events/amd/core.c6
-rw-r--r--arch/x86/events/amd/ibs.c72
-rw-r--r--arch/x86/events/amd/power.c60
-rw-r--r--arch/x86/events/amd/uncore.c122
-rw-r--r--arch/x86/events/core.c103
-rw-r--r--arch/x86/events/intel/core.c4
-rw-r--r--arch/x86/events/intel/cqm.c49
-rw-r--r--arch/x86/events/intel/cstate.c51
-rw-r--r--arch/x86/events/intel/rapl.c84
-rw-r--r--arch/x86/events/intel/uncore.c133
-rw-r--r--arch/x86/include/asm/acpi.h3
-rw-r--r--arch/x86/include/asm/cpu.h1
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/pgalloc.h12
-rw-r--r--arch/x86/include/asm/pmem.h77
-rw-r--r--arch/x86/include/asm/smp.h2
-rw-r--r--arch/x86/include/asm/special_insns.h46
-rw-r--r--arch/x86/include/asm/vmx.h1
-rw-r--r--arch/x86/include/asm/xen/cpuid.h5
-rw-r--r--arch/x86/include/uapi/asm/vmx.h4
-rw-r--r--arch/x86/kernel/acpi/boot.c16
-rw-r--r--arch/x86/kernel/apb_timer.c29
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c80
-rw-r--r--arch/x86/kernel/hpet.c69
-rw-r--r--arch/x86/kernel/setup.c9
-rw-r--r--arch/x86/kernel/setup_percpu.c3
-rw-r--r--arch/x86/kernel/tboot.c25
-rw-r--r--arch/x86/kvm/cpuid.c2
-rw-r--r--arch/x86/kvm/cpuid.h8
-rw-r--r--arch/x86/kvm/vmx.c32
-rw-r--r--arch/x86/kvm/x86.c35
-rw-r--r--arch/x86/lib/x86-opcode-map.txt2
-rw-r--r--arch/x86/mm/fault.c2
-rw-r--r--arch/x86/mm/numa.c2
-rw-r--r--arch/x86/mm/pgtable.c10
-rw-r--r--arch/x86/mm/srat.c116
-rw-r--r--arch/x86/xen/efi.c111
-rw-r--r--arch/x86/xen/enlighten.c49
-rw-r--r--arch/x86/xen/grant-table.c57
-rw-r--r--arch/x86/xen/irq.c3
-rw-r--r--arch/x86/xen/pmu.c2
-rw-r--r--arch/x86/xen/smp.c18
-rw-r--r--arch/x86/xen/time.c63
-rw-r--r--arch/x86/xen/xen-ops.h1
-rw-r--r--arch/xtensa/kernel/perf_event.c26
-rw-r--r--arch/xtensa/mm/fault.c2
311 files changed, 6228 insertions, 3413 deletions
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 4a905bd667e2..83e9eee57a55 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -147,7 +147,7 @@ retry:
/* If for any reason at all we couldn't handle the fault,
make sure we exit gracefully rather than endlessly redo
the fault. */
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 85814e74677d..601ed173080b 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -74,9 +74,7 @@ endif
ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
# Generic build system uses -O2, we want -O3
# Note: No need to add to cflags-y as that happens anyways
-#
-# Disable the false maybe-uninitialized warings gcc spits out at -O3
-ARCH_CFLAGS += -O3 $(call cc-disable-warning,maybe-uninitialized,)
+ARCH_CFLAGS += -O3
endif
# small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 858f98ef7f1b..0f92d97432a2 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -110,7 +110,7 @@
#define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
/* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL)
/* More Abbrevaited helpers */
#define PAGE_U_NONE __pgprot(___DEF)
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 2ee7a4d758a8..5f8c0b47045a 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/of_fdt.h>
+#include <linux/of.h>
#include <linux/of_platform.h>
#include <linux/cache.h>
#include <asm/sections.h>
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 98f22d2eb563..f927b8dc6edd 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -296,30 +296,23 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id)
return IRQ_HANDLED;
}
-static int arc_timer_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+
+static int arc_timer_starting_cpu(unsigned int cpu)
{
struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
evt->cpumask = cpumask_of(smp_processor_id());
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- clockevents_config_and_register(evt, arc_timer_freq,
- 0, ULONG_MAX);
- enable_percpu_irq(arc_timer_irq, 0);
- break;
- case CPU_DYING:
- disable_percpu_irq(arc_timer_irq);
- break;
- }
-
- return NOTIFY_OK;
+ clockevents_config_and_register(evt, arc_timer_freq, 0, ARC_TIMER_MAX);
+ enable_percpu_irq(arc_timer_irq, 0);
+ return 0;
}
-static struct notifier_block arc_timer_cpu_nb = {
- .notifier_call = arc_timer_cpu_notify,
-};
+static int arc_timer_dying_cpu(unsigned int cpu)
+{
+ disable_percpu_irq(arc_timer_irq);
+ return 0;
+}
/*
* clockevent setup for boot CPU
@@ -329,12 +322,6 @@ static int __init arc_clockevent_setup(struct device_node *node)
struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
int ret;
- ret = register_cpu_notifier(&arc_timer_cpu_nb);
- if (ret) {
- pr_err("Failed to register cpu notifier");
- return ret;
- }
-
arc_timer_irq = irq_of_parse_and_map(node, 0);
if (arc_timer_irq <= 0) {
pr_err("clockevent: missing irq");
@@ -347,11 +334,6 @@ static int __init arc_clockevent_setup(struct device_node *node)
return ret;
}
- evt->irq = arc_timer_irq;
- evt->cpumask = cpumask_of(smp_processor_id());
- clockevents_config_and_register(evt, arc_timer_freq,
- 0, ARC_TIMER_MAX);
-
/* Needs apriori irq_set_percpu_devid() done in intc map function */
ret = request_percpu_irq(arc_timer_irq, timer_irq_handler,
"Timer0 (per-cpu-tick)", evt);
@@ -360,8 +342,14 @@ static int __init arc_clockevent_setup(struct device_node *node)
return ret;
}
- enable_percpu_irq(arc_timer_irq, 0);
-
+ ret = cpuhp_setup_state(CPUHP_AP_ARC_TIMER_STARTING,
+ "AP_ARC_TIMER_STARTING",
+ arc_timer_starting_cpu,
+ arc_timer_dying_cpu);
+ if (ret) {
+ pr_err("Failed to setup hotplug state");
+ return ret;
+ }
return 0;
}
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 73d7e4c75b7d..ab74b5d9186c 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -92,7 +92,8 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, struct dma_attrs *attrs)
{
- struct page *page = virt_to_page(dma_handle);
+ phys_addr_t paddr = plat_dma_to_phys(dev, dma_handle);
+ struct page *page = virt_to_page(paddr);
int is_non_coh = 1;
is_non_coh = dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) ||
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index af63f4a13e60..e94e5aa33985 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -137,7 +137,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
if (unlikely(fatal_signal_pending(current))) {
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index 49b8abd1115c..f52b7db67fd3 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -49,7 +49,7 @@ EXPORT_SYMBOL(ioremap);
/*
* ioremap with access flags
* Cache semantics wise it is same as ioremap - "forced" uncached.
- * However unline vanilla ioremap which bypasses ARC MMU for addresses in
+ * However unlike vanilla ioremap which bypasses ARC MMU for addresses in
* ARC hardware uncached region, this one still goes thru the MMU as caller
* might need finer access control (R/W/X)
*/
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f0636ec94903..4c445fb9c189 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1186,6 +1186,60 @@ config ARM_ERRATA_773022
loop buffer may deliver incorrect instructions. This
workaround disables the loop buffer to avoid the erratum.
+config ARM_ERRATA_818325_852422
+ bool "ARM errata: A12: some seqs of opposed cond code instrs => deadlock or corruption"
+ depends on CPU_V7
+ help
+ This option enables the workaround for:
+ - Cortex-A12 818325: Execution of an UNPREDICTABLE STR or STM
+ instruction might deadlock. Fixed in r0p1.
+ - Cortex-A12 852422: Execution of a sequence of instructions might
+ lead to either a data corruption or a CPU deadlock. Not fixed in
+ any Cortex-A12 cores yet.
+ This workaround for all both errata involves setting bit[12] of the
+ Feature Register. This bit disables an optimisation applied to a
+ sequence of 2 instructions that use opposing condition codes.
+
+config ARM_ERRATA_821420
+ bool "ARM errata: A12: sequence of VMOV to core registers might lead to a dead lock"
+ depends on CPU_V7
+ help
+ This option enables the workaround for the 821420 Cortex-A12
+ (all revs) erratum. In very rare timing conditions, a sequence
+ of VMOV to Core registers instructions, for which the second
+ one is in the shadow of a branch or abort, can lead to a
+ deadlock when the VMOV instructions are issued out-of-order.
+
+config ARM_ERRATA_825619
+ bool "ARM errata: A12: DMB NSHST/ISHST mixed ... might cause deadlock"
+ depends on CPU_V7
+ help
+ This option enables the workaround for the 825619 Cortex-A12
+ (all revs) erratum. Within rare timing constraints, executing a
+ DMB NSHST or DMB ISHST instruction followed by a mix of Cacheable
+ and Device/Strongly-Ordered loads and stores might cause deadlock
+
+config ARM_ERRATA_852421
+ bool "ARM errata: A17: DMB ST might fail to create order between stores"
+ depends on CPU_V7
+ help
+ This option enables the workaround for the 852421 Cortex-A17
+ (r1p0, r1p1, r1p2) erratum. Under very rare timing conditions,
+ execution of a DMB ST instruction might fail to properly order
+ stores from GroupA and stores from GroupB.
+
+config ARM_ERRATA_852423
+ bool "ARM errata: A17: some seqs of opposed cond code instrs => deadlock or corruption"
+ depends on CPU_V7
+ help
+ This option enables the workaround for:
+ - Cortex-A17 852423: Execution of a sequence of instructions might
+ lead to either a data corruption or a CPU deadlock. Not fixed in
+ any Cortex-A17 cores yet.
+ This is identical to Cortex-A12 erratum 852422. It is a separate
+ config option from the A12 erratum due to the way errata are checked
+ for and handled.
+
endmenu
source "arch/arm/common/Kconfig"
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 274e8a6582f1..229afaf2058b 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -327,6 +327,7 @@ zImage: Image
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
+ @$(kecho) ' Kernel: $(boot)/$@ is ready'
$(INSTALL_TARGETS):
$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 5be33a2d59a9..bdc1d5af03d2 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -31,7 +31,7 @@ ifeq ($(CONFIG_XIP_KERNEL),y)
$(obj)/xipImage: vmlinux FORCE
$(call if_changed,objcopy)
- @$(kecho) ' Kernel: $@ is ready (physical address: $(CONFIG_XIP_PHYS_ADDR))'
+ @$(kecho) ' Physical Address of xipImage: $(CONFIG_XIP_PHYS_ADDR)'
$(obj)/Image $(obj)/zImage: FORCE
@echo 'Kernel configured for XIP (CONFIG_XIP_KERNEL=y)'
@@ -46,14 +46,12 @@ $(obj)/xipImage: FORCE
$(obj)/Image: vmlinux FORCE
$(call if_changed,objcopy)
- @$(kecho) ' Kernel: $@ is ready'
$(obj)/compressed/vmlinux: $(obj)/Image FORCE
$(Q)$(MAKE) $(build)=$(obj)/compressed $@
$(obj)/zImage: $(obj)/compressed/vmlinux FORCE
$(call if_changed,objcopy)
- @$(kecho) ' Kernel: $@ is ready'
endif
@@ -78,14 +76,12 @@ fi
$(obj)/uImage: $(obj)/zImage FORCE
@$(check_for_multiple_loadaddr)
$(call if_changed,uimage)
- @$(kecho) ' Image $@ is ready'
$(obj)/bootp/bootp: $(obj)/zImage initrd FORCE
$(Q)$(MAKE) $(build)=$(obj)/bootp $@
$(obj)/bootpImage: $(obj)/bootp/bootp FORCE
$(call if_changed,objcopy)
- @$(kecho) ' Kernel: $@ is ready'
PHONY += initrd install zinstall uinstall
initrd:
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 52be48bbd2dd..7fa295155543 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -766,7 +766,6 @@
ale_entries = <1024>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
- rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
active_slave = <0>;
@@ -789,7 +788,7 @@
status = "disabled";
davinci_mdio: mdio@4a101000 {
- compatible = "ti,davinci_mdio";
+ compatible = "ti,cpsw-mdio","ti,davinci_mdio";
#address-cells = <1>;
#size-cells = <0>;
ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 12fcde4d4d2e..cd81ecf12731 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -626,7 +626,6 @@
ale_entries = <1024>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
- rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
active_slave = <0>;
@@ -636,7 +635,7 @@
syscon = <&scm_conf>;
davinci_mdio: mdio@4a101000 {
- compatible = "ti,am4372-mdio","ti,davinci_mdio";
+ compatible = "ti,am4372-mdio","ti,cpsw-mdio","ti,davinci_mdio";
reg = <0x4a101000 0x100>;
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 81d6c3033b51..c4d04c5293b9 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -86,7 +86,7 @@
led@3 {
label = "beagle-x15:usr3";
gpios = <&gpio7 15 GPIO_ACTIVE_HIGH>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
default-state = "off";
};
};
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index d4537dc61497..f23cae0c2179 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -509,7 +509,6 @@
ale_entries = <1024>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
- rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
active_slave = <0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 3a8f3976f6f9..de559f6e4fee 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1628,7 +1628,6 @@
ale_entries = <1024>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
- rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
active_slave = <0>;
@@ -1663,7 +1662,7 @@
status = "disabled";
davinci_mdio: mdio@48485000 {
- compatible = "ti,davinci_mdio";
+ compatible = "ti,cpsw-mdio","ti,davinci_mdio";
#address-cells = <1>;
#size-cells = <0>;
ti,hwmods = "davinci_mdio";
diff --git a/arch/arm/boot/dts/kirkwood-ns2lite.dts b/arch/arm/boot/dts/kirkwood-ns2lite.dts
index 1f2ca60d8b3d..2c661add0cc0 100644
--- a/arch/arm/boot/dts/kirkwood-ns2lite.dts
+++ b/arch/arm/boot/dts/kirkwood-ns2lite.dts
@@ -26,7 +26,7 @@
blue-sata {
label = "ns2:blue:sata";
gpios = <&gpio0 30 GPIO_ACTIVE_LOW>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
};
};
diff --git a/arch/arm/boot/dts/kirkwood-topkick.dts b/arch/arm/boot/dts/kirkwood-topkick.dts
index f5c8c0dd41dc..1e9a72100a45 100644
--- a/arch/arm/boot/dts/kirkwood-topkick.dts
+++ b/arch/arm/boot/dts/kirkwood-topkick.dts
@@ -129,7 +129,7 @@
disk {
label = "topkick:yellow:disk";
gpios = <&gpio0 21 GPIO_ACTIVE_LOW>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
system2 {
label = "topkick:red:system";
diff --git a/arch/arm/boot/dts/meson8-minix-neo-x8.dts b/arch/arm/boot/dts/meson8-minix-neo-x8.dts
index 4f536bb1f002..8bceb8d343f6 100644
--- a/arch/arm/boot/dts/meson8-minix-neo-x8.dts
+++ b/arch/arm/boot/dts/meson8-minix-neo-x8.dts
@@ -80,6 +80,7 @@
pmic@32 {
compatible = "ricoh,rn5t618";
reg = <0x32>;
+ system-power-controller;
regulators {
};
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 3b44ef3cff12..3ebee530f2b0 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -539,8 +539,9 @@
gmac: ethernet@ff290000 {
compatible = "rockchip,rk3288-gmac";
reg = <0xff290000 0x10000>;
- interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "macirq";
+ interrupts = <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
rockchip,grf = <&grf>;
clocks = <&cru SCLK_MAC>,
<&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>,
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 17e81dc9213e..5820b70c95b3 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -621,6 +621,22 @@
compatible = "altr,socfpga-a10-ocram-ecc";
reg = <0xff8c3000 0x400>;
};
+
+ emac0-rx-ecc@ff8c0800 {
+ compatible = "altr,socfpga-eth-mac-ecc";
+ reg = <0xff8c0800 0x400>;
+ altr,ecc-parent = <&gmac0>;
+ interrupts = <4 IRQ_TYPE_LEVEL_HIGH>,
+ <36 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ emac0-tx-ecc@ff8c0c00 {
+ compatible = "altr,socfpga-eth-mac-ecc";
+ reg = <0xff8c0c00 0x400>;
+ altr,ecc-parent = <&gmac0>;
+ interrupts = <5 IRQ_TYPE_LEVEL_HIGH>,
+ <37 IRQ_TYPE_LEVEL_HIGH>;
+ };
};
rst: rstmgr@ffd05000 {
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index 6c60b7f91104..5c1fcab4a6f7 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -85,187 +85,199 @@
reg = <1>;
#address-cells = <1>;
#size-cells = <0>;
+
+ switch0: switch0@0 {
+ compatible = "marvell,mv88e6085";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ dsa,member = <0 0>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan0";
+ };
+
+ port@1 {
+ reg = <1>;
+ label = "lan1";
+ };
+
+ port@2 {
+ reg = <2>;
+ label = "lan2";
+ };
+
+ switch0port5: port@5 {
+ reg = <5>;
+ label = "dsa";
+ phy-mode = "rgmii-txid";
+ link = <&switch1port6
+ &switch2port9>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+
+ port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <&fec1>;
+ fixed-link {
+ speed = <100>;
+ full-duplex;
+ };
+ };
+ };
+ };
};
mdio_mux_2: mdio@2 {
reg = <2>;
#address-cells = <1>;
#size-cells = <0>;
- };
-
- mdio_mux_4: mdio@4 {
- reg = <4>;
- #address-cells = <1>;
- #size-cells = <0>;
- };
-
- mdio_mux_8: mdio@8 {
- reg = <8>;
- #address-cells = <1>;
- #size-cells = <0>;
- };
- };
-
- dsa {
- compatible = "marvell,dsa";
- #address-cells = <2>;
- #size-cells = <0>;
- dsa,ethernet = <&fec1>;
- dsa,mii-bus = <&mdio_mux_1>;
-
- /* 6352 - Primary - 7 ports */
- switch0: switch@0-0 {
- #address-cells = <1>;
- #size-cells = <0>;
- reg = <0x00 0>;
- eeprom-length = <512>;
- port@0 {
+ switch1: switch1@0 {
+ compatible = "marvell,mv88e6085";
+ #address-cells = <1>;
+ #size-cells = <0>;
reg = <0>;
- label = "lan0";
- };
-
- port@1 {
- reg = <1>;
- label = "lan1";
- };
-
- port@2 {
- reg = <2>;
- label = "lan2";
- };
-
- switch0port5: port@5 {
- reg = <5>;
- label = "dsa";
- phy-mode = "rgmii-txid";
- link = <&switch1port6
- &switch2port9>;
-
- fixed-link {
- speed = <1000>;
- full-duplex;
+ dsa,member = <0 1>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan3";
+ phy-handle = <&switch1phy0>;
+ };
+
+ port@1 {
+ reg = <1>;
+ label = "lan4";
+ phy-handle = <&switch1phy1>;
+ };
+
+ port@2 {
+ reg = <2>;
+ label = "lan5";
+ phy-handle = <&switch1phy2>;
+ };
+
+ switch1port5: port@5 {
+ reg = <5>;
+ label = "dsa";
+ link = <&switch2port9>;
+ phy-mode = "rgmii-txid";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+
+ switch1port6: port@6 {
+ reg = <6>;
+ label = "dsa";
+ phy-mode = "rgmii-txid";
+ link = <&switch0port5>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
};
- };
-
- port@6 {
- reg = <6>;
- label = "cpu";
-
- fixed-link {
- speed = <100>;
- full-duplex;
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ switch1phy0: switch1phy0@0 {
+ reg = <0>;
+ };
+ switch1phy1: switch1phy0@1 {
+ reg = <1>;
+ };
+ switch1phy2: switch1phy0@2 {
+ reg = <2>;
+ };
};
};
-
};
- /* 6352 - Secondary - 7 ports */
- switch1: switch@0-1 {
+ mdio_mux_4: mdio@4 {
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x00 1>;
- eeprom-length = <512>;
- mii-bus = <&mdio_mux_2>;
+ reg = <4>;
- port@0 {
+ switch2: switch2@0 {
+ compatible = "marvell,mv88e6085";
+ #address-cells = <1>;
+ #size-cells = <0>;
reg = <0>;
- label = "lan3";
- };
-
- port@1 {
- reg = <1>;
- label = "lan4";
- };
-
- port@2 {
- reg = <2>;
- label = "lan5";
- };
-
- switch1port5: port@5 {
- reg = <5>;
- label = "dsa";
- link = <&switch2port9>;
- phy-mode = "rgmii-txid";
-
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
-
- switch1port6: port@6 {
- reg = <6>;
- label = "dsa";
- phy-mode = "rgmii-txid";
- link = <&switch0port5>;
-
- fixed-link {
- speed = <1000>;
- full-duplex;
+ dsa,member = <0 2>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ port@0 {
+ reg = <0>;
+ label = "lan6";
+ };
+
+ port@1 {
+ reg = <1>;
+ label = "lan7";
+ };
+
+ port@2 {
+ reg = <2>;
+ label = "lan8";
+ };
+
+ port@3 {
+ reg = <3>;
+ label = "optical3";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ link-gpios = <&gpio6 2
+ GPIO_ACTIVE_HIGH>;
+ };
+ };
+
+ port@4 {
+ reg = <4>;
+ label = "optical4";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ link-gpios = <&gpio6 3
+ GPIO_ACTIVE_HIGH>;
+ };
+ };
+
+ switch2port9: port@9 {
+ reg = <9>;
+ label = "dsa";
+ phy-mode = "rgmii-txid";
+ link = <&switch1port5
+ &switch0port5>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
};
};
};
- /* 6185 - 10 ports */
- switch2: switch@0-2 {
+ mdio_mux_8: mdio@8 {
+ reg = <8>;
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x00 2>;
- mii-bus = <&mdio_mux_4>;
-
- port@0 {
- reg = <0>;
- label = "lan6";
- };
-
- port@1 {
- reg = <1>;
- label = "lan7";
- };
-
- port@2 {
- reg = <2>;
- label = "lan8";
- };
-
- port@3 {
- reg = <3>;
- label = "optical3";
-
- fixed-link {
- speed = <1000>;
- full-duplex;
- link-gpios = <&gpio6 2
- GPIO_ACTIVE_HIGH>;
- };
- };
-
- port@4 {
- reg = <4>;
- label = "optical4";
-
- fixed-link {
- speed = <1000>;
- full-duplex;
- link-gpios = <&gpio6 3
- GPIO_ACTIVE_HIGH>;
- };
- };
-
- switch2port9: port@9 {
- reg = <9>;
- label = "dsa";
- phy-mode = "rgmii-txid";
- link = <&switch1port5
- &switch0port5>;
-
- fixed-link {
- speed = <1000>;
- full-duplex;
- };
- };
};
};
diff --git a/arch/arm/configs/collie_defconfig b/arch/arm/configs/collie_defconfig
index 6c56ad086c7c..52dbad5619e2 100644
--- a/arch/arm/configs/collie_defconfig
+++ b/arch/arm/configs/collie_defconfig
@@ -76,7 +76,7 @@ CONFIG_LEDS_CLASS=y
CONFIG_LEDS_LOCOMO=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
# CONFIG_DNOTIFY is not set
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
diff --git a/arch/arm/configs/ixp4xx_defconfig b/arch/arm/configs/ixp4xx_defconfig
index 24636cfdf6df..cf4918a2c51f 100644
--- a/arch/arm/configs/ixp4xx_defconfig
+++ b/arch/arm/configs/ixp4xx_defconfig
@@ -180,7 +180,7 @@ CONFIG_LEDS_FSG=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_ISL1208=y
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index b2bc8e11471d..4eaea2173bf8 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -480,13 +480,13 @@ THUMB( orr \reg , \reg , #PSR_T_BIT )
.macro uaccess_save, tmp
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
mrc p15, 0, \tmp, c3, c0, 0
- str \tmp, [sp, #S_FRAME_SIZE]
+ str \tmp, [sp, #SVC_DACR]
#endif
.endm
.macro uaccess_restore
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
- ldr r0, [sp, #S_FRAME_SIZE]
+ ldr r0, [sp, #SVC_DACR]
mcr p15, 0, r0, c3, c0, 0
#endif
.endm
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 112cc1a5d47f..f5d698182d50 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -44,9 +44,7 @@ extern void arm_heavy_mb(void);
#define __arm_heavy_mb(x...) dsb(x)
#endif
-#ifdef CONFIG_ARCH_HAS_BARRIERS
-#include <mach/barriers.h>
-#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#if defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
#define mb() __arm_heavy_mb()
#define rmb() dsb()
#define wmb() __arm_heavy_mb(st)
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index dff714d886d5..b7a428154355 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -10,8 +10,8 @@
#include <asm/param.h> /* HZ */
#define MAX_UDELAY_MS 2
-#define UDELAY_MULT ((UL(2199023) * HZ) >> 11)
-#define UDELAY_SHIFT 30
+#define UDELAY_MULT UL(2047 * HZ + 483648 * HZ / 1000000)
+#define UDELAY_SHIFT 31
#ifndef __ASSEMBLY__
@@ -34,7 +34,7 @@ extern struct arm_delay_ops {
* it, it means that you're calling udelay() with an out of range value.
*
* With currently imposed limits, this means that we support a max delay
- * of 2000us. Further limits: HZ<=1000 and bogomips<=3355
+ * of 2000us. Further limits: HZ<=1000
*/
extern void __bad_udelay(void);
diff --git a/arch/arm/include/asm/floppy.h b/arch/arm/include/asm/floppy.h
index f4882553fbb0..85a34cc8316a 100644
--- a/arch/arm/include/asm/floppy.h
+++ b/arch/arm/include/asm/floppy.h
@@ -17,7 +17,7 @@
#define fd_outb(val,port) \
do { \
- if ((port) == FD_DOR) \
+ if ((port) == (u32)FD_DOR) \
fd_setdor((val)); \
else \
outb((val),(port)); \
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 781ef5fe235d..021692c64de3 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -282,7 +282,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
* These perform PCI memory accesses via an ioremap region. They don't
* take an address as such, but a cookie.
*
- * Again, this are defined to perform little endian accesses. See the
+ * Again, these are defined to perform little endian accesses. See the
* IO port primitives for more information.
*/
#ifndef readl
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 20febb368844..b2902a5cd780 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -57,7 +57,7 @@ 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_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
static inline void clean_pte_table(pte_t *pte)
{
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 51622ba7c4a6..e9c9a117bd25 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -13,10 +13,20 @@
#include <uapi/asm/ptrace.h>
#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
struct pt_regs {
unsigned long uregs[18];
};
+struct svc_pt_regs {
+ struct pt_regs regs;
+ u32 dacr;
+ u32 addr_limit;
+};
+
+#define to_svc_pt_regs(r) container_of(r, struct svc_pt_regs, regs)
+
#define user_mode(regs) \
(((regs)->ARM_cpsr & 0xf) == 0)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 3cadb726ec88..1e25cd80589e 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -209,17 +209,38 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
tlb_flush(tlb);
}
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
+ if (tlb->nr == tlb->max)
+ return true;
tlb->pages[tlb->nr++] = page;
- VM_BUG_ON(tlb->nr > tlb->max);
- return tlb->max - tlb->nr;
+ return false;
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
- if (!__tlb_remove_page(tlb, page))
+ if (__tlb_remove_page(tlb, page)) {
tlb_flush_mmu(tlb);
+ __tlb_remove_page(tlb, page);
+ }
+}
+
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+ struct page *page)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return tlb_remove_page(tlb, page);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 35c9db857ebe..62a6f65029e6 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -104,14 +104,6 @@ static inline void set_fs(mm_segment_t fs)
#define segment_eq(a, b) ((a) == (b))
-#define __addr_ok(addr) ({ \
- unsigned long flag; \
- __asm__("cmp %2, %0; movlo %0, #0" \
- : "=&r" (flag) \
- : "0" (current_thread_info()->addr_limit), "r" (addr) \
- : "cc"); \
- (flag == 0); })
-
/* We use 33-bit arithmetic here... */
#define __range_ok(addr, size) ({ \
unsigned long flag, roksum; \
@@ -238,49 +230,23 @@ extern int __put_user_2(void *, unsigned int);
extern int __put_user_4(void *, unsigned int);
extern int __put_user_8(void *, unsigned long long);
-#define __put_user_x(__r2, __p, __e, __l, __s) \
- __asm__ __volatile__ ( \
- __asmeq("%0", "r0") __asmeq("%2", "r2") \
- __asmeq("%3", "r1") \
- "bl __put_user_" #__s \
- : "=&r" (__e) \
- : "0" (__p), "r" (__r2), "r" (__l) \
- : "ip", "lr", "cc")
-
-#define __put_user_check(x, p) \
+#define __put_user_check(__pu_val, __ptr, __err, __s) \
({ \
unsigned long __limit = current_thread_info()->addr_limit - 1; \
- const typeof(*(p)) __user *__tmp_p = (p); \
- register const typeof(*(p)) __r2 asm("r2") = (x); \
- register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
+ register typeof(__pu_val) __r2 asm("r2") = __pu_val; \
+ register const void __user *__p asm("r0") = __ptr; \
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
- unsigned int __ua_flags = uaccess_save_and_enable(); \
- switch (sizeof(*(__p))) { \
- case 1: \
- __put_user_x(__r2, __p, __e, __l, 1); \
- break; \
- case 2: \
- __put_user_x(__r2, __p, __e, __l, 2); \
- break; \
- case 4: \
- __put_user_x(__r2, __p, __e, __l, 4); \
- break; \
- case 8: \
- __put_user_x(__r2, __p, __e, __l, 8); \
- break; \
- default: __e = __put_user_bad(); break; \
- } \
- uaccess_restore(__ua_flags); \
- __e; \
+ __asm__ __volatile__ ( \
+ __asmeq("%0", "r0") __asmeq("%2", "r2") \
+ __asmeq("%3", "r1") \
+ "bl __put_user_" #__s \
+ : "=&r" (__e) \
+ : "0" (__p), "r" (__r2), "r" (__l) \
+ : "ip", "lr", "cc"); \
+ __err = __e; \
})
-#define put_user(x, p) \
- ({ \
- might_fault(); \
- __put_user_check(x, p); \
- })
-
#else /* CONFIG_MMU */
/*
@@ -298,7 +264,7 @@ static inline void set_fs(mm_segment_t fs)
}
#define get_user(x, p) __get_user(x, p)
-#define put_user(x, p) __put_user(x, p)
+#define __put_user_check __put_user_nocheck
#endif /* CONFIG_MMU */
@@ -389,36 +355,54 @@ do { \
#define __get_user_asm_word(x, addr, err) \
__get_user_asm(x, addr, err, ldr)
+
+#define __put_user_switch(x, ptr, __err, __fn) \
+ do { \
+ const __typeof__(*(ptr)) __user *__pu_ptr = (ptr); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ unsigned int __ua_flags; \
+ might_fault(); \
+ __ua_flags = uaccess_save_and_enable(); \
+ switch (sizeof(*(ptr))) { \
+ case 1: __fn(__pu_val, __pu_ptr, __err, 1); break; \
+ case 2: __fn(__pu_val, __pu_ptr, __err, 2); break; \
+ case 4: __fn(__pu_val, __pu_ptr, __err, 4); break; \
+ case 8: __fn(__pu_val, __pu_ptr, __err, 8); break; \
+ default: __err = __put_user_bad(); break; \
+ } \
+ uaccess_restore(__ua_flags); \
+ } while (0)
+
+#define put_user(x, ptr) \
+({ \
+ int __pu_err = 0; \
+ __put_user_switch((x), (ptr), __pu_err, __put_user_check); \
+ __pu_err; \
+})
+
#define __put_user(x, ptr) \
({ \
long __pu_err = 0; \
- __put_user_err((x), (ptr), __pu_err); \
+ __put_user_switch((x), (ptr), __pu_err, __put_user_nocheck); \
__pu_err; \
})
#define __put_user_error(x, ptr, err) \
({ \
- __put_user_err((x), (ptr), err); \
+ __put_user_switch((x), (ptr), (err), __put_user_nocheck); \
(void) 0; \
})
-#define __put_user_err(x, ptr, err) \
-do { \
- unsigned long __pu_addr = (unsigned long)(ptr); \
- unsigned int __ua_flags; \
- __typeof__(*(ptr)) __pu_val = (x); \
- __chk_user_ptr(ptr); \
- might_fault(); \
- __ua_flags = uaccess_save_and_enable(); \
- switch (sizeof(*(ptr))) { \
- case 1: __put_user_asm_byte(__pu_val, __pu_addr, err); break; \
- case 2: __put_user_asm_half(__pu_val, __pu_addr, err); break; \
- case 4: __put_user_asm_word(__pu_val, __pu_addr, err); break; \
- case 8: __put_user_asm_dword(__pu_val, __pu_addr, err); break; \
- default: __put_user_bad(); \
- } \
- uaccess_restore(__ua_flags); \
-} while (0)
+#define __put_user_nocheck(x, __pu_ptr, __err, __size) \
+ do { \
+ unsigned long __pu_addr = (unsigned long)__pu_ptr; \
+ __put_user_nocheck_##__size(x, __pu_addr, __err); \
+ } while (0)
+
+#define __put_user_nocheck_1 __put_user_asm_byte
+#define __put_user_nocheck_2 __put_user_asm_half
+#define __put_user_nocheck_4 __put_user_asm_word
+#define __put_user_nocheck_8 __put_user_asm_dword
#define __put_user_asm(x, __pu_addr, err, instr) \
__asm__ __volatile__( \
diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h
index b6b962d70db9..9d874db13c0e 100644
--- a/arch/arm/include/asm/xen/hypercall.h
+++ b/arch/arm/include/asm/xen/hypercall.h
@@ -52,6 +52,7 @@ int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
int HYPERVISOR_physdev_op(int cmd, void *arg);
int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
int HYPERVISOR_platform_op_raw(void *arg);
static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
{
diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h
new file mode 100644
index 000000000000..ec154e719b11
--- /dev/null
+++ b/arch/arm/include/asm/xen/xen-ops.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_XEN_OPS_H
+#define _ASM_XEN_OPS_H
+
+void xen_efi_runtime_setup(void);
+
+#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 27d05813ff09..608008229c7d 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -107,7 +107,10 @@ int main(void)
DEFINE(S_PC, offsetof(struct pt_regs, ARM_pc));
DEFINE(S_PSR, offsetof(struct pt_regs, ARM_cpsr));
DEFINE(S_OLD_R0, offsetof(struct pt_regs, ARM_ORIG_r0));
- DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
+ DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
+ DEFINE(SVC_DACR, offsetof(struct svc_pt_regs, dacr));
+ DEFINE(SVC_ADDR_LIMIT, offsetof(struct svc_pt_regs, addr_limit));
+ DEFINE(SVC_REGS_SIZE, sizeof(struct svc_pt_regs));
BLANK();
#ifdef CONFIG_CACHE_L2X0
DEFINE(L2X0_R_PHY_BASE, offsetof(struct l2x0_regs, phy_base));
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index a44b268e12e1..7dccc964d75f 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -47,18 +47,13 @@ int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
* This function calls the underlying arch specific low level PM code as
* registered at the init time.
*
- * Returns -EOPNOTSUPP if no suspend callback is defined, the result of the
- * callback otherwise.
+ * Returns the result of the suspend callback.
*/
int arm_cpuidle_suspend(int index)
{
- int ret = -EOPNOTSUPP;
int cpu = smp_processor_id();
- if (cpuidle_ops[cpu].suspend)
- ret = cpuidle_ops[cpu].suspend(index);
-
- return ret;
+ return cpuidle_ops[cpu].suspend(index);
}
/**
@@ -92,7 +87,8 @@ static const struct cpuidle_ops *__init arm_cpuidle_get_ops(const char *method)
* process.
*
* Return 0 on sucess, -ENOENT if no 'enable-method' is defined, -EOPNOTSUPP if
- * no cpuidle_ops is registered for the 'enable-method'.
+ * no cpuidle_ops is registered for the 'enable-method', or if either init or
+ * suspend callback isn't defined.
*/
static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
{
@@ -110,6 +106,12 @@ static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
return -EOPNOTSUPP;
}
+ if (!ops->init || !ops->suspend) {
+ pr_warn("cpuidle_ops '%s': no init or suspend callback\n",
+ enable_method);
+ return -EOPNOTSUPP;
+ }
+
cpuidle_ops[cpu] = *ops; /* structure copy */
pr_notice("cpuidle: enable-method property '%s'"
@@ -129,7 +131,8 @@ static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
* Returns:
* 0 on success,
* -ENODEV if it fails to find the cpu node in the device tree,
- * -EOPNOTSUPP if it does not find a registered cpuidle_ops for this cpu,
+ * -EOPNOTSUPP if it does not find a registered and valid cpuidle_ops for
+ * this cpu,
* -ENOENT if it fails to find an 'enable-method' property,
* -ENXIO if the HW reports a failure or a misconfiguration,
* -ENOMEM if the HW report an memory allocation failure
@@ -143,7 +146,7 @@ int __init arm_cpuidle_init(int cpu)
return -ENODEV;
ret = arm_cpuidle_read_ops(cpu_node, cpu);
- if (!ret && cpuidle_ops[cpu].init)
+ if (!ret)
ret = cpuidle_ops[cpu].init(cpu_node, cpu);
of_node_put(cpu_node);
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 2e26016a91a5..40ecd5f514a2 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -23,6 +23,7 @@
#include <asm/cputype.h>
#include <asm/setup.h>
#include <asm/page.h>
+#include <asm/prom.h>
#include <asm/smp_plat.h>
#include <asm/mach/arch.h>
#include <asm/mach-types.h>
@@ -213,6 +214,8 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
#if defined(CONFIG_ARCH_MULTIPLATFORM) || defined(CONFIG_ARM_SINGLE_ARMV7M)
DT_MACHINE_START(GENERIC_DT, "Generic DT based system")
+ .l2c_aux_val = 0x0,
+ .l2c_aux_mask = ~0x0,
MACHINE_END
mdesc_best = &__mach_desc_GENERIC_DT;
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index e2550500486d..bc5f50799d75 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -92,7 +92,7 @@
* Invalid mode handlers
*/
.macro inv_entry, reason
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
ARM( stmib sp, {r1 - lr} )
THUMB( stmia sp, {r0 - r12} )
THUMB( str sp, [sp, #S_SP] )
@@ -152,7 +152,7 @@ ENDPROC(__und_invalid)
.macro svc_entry, stack_hole=0, trace=1, uaccess=1
UNWIND(.fnstart )
UNWIND(.save {r0 - pc} )
- sub sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
+ sub sp, sp, #(SVC_REGS_SIZE + \stack_hole - 4)
#ifdef CONFIG_THUMB2_KERNEL
SPFIX( str r0, [sp] ) @ temporarily saved
SPFIX( mov r0, sp )
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
ldmia r0, {r3 - r5}
add r7, sp, #S_SP - 4 @ here for interlock avoidance
mov r6, #-1 @ "" "" "" ""
- add r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
+ add r2, sp, #(SVC_REGS_SIZE + \stack_hole - 4)
SPFIX( addeq r2, r2, #4 )
str r3, [sp, #-4]! @ save the "real" r0 copied
@ from the exception stack
@@ -185,6 +185,12 @@ ENDPROC(__und_invalid)
@
stmia r7, {r2 - r6}
+ get_thread_info tsk
+ ldr r0, [tsk, #TI_ADDR_LIMIT]
+ mov r1, #TASK_SIZE
+ str r1, [tsk, #TI_ADDR_LIMIT]
+ str r0, [sp, #SVC_ADDR_LIMIT]
+
uaccess_save r0
.if \uaccess
uaccess_disable r0
@@ -213,7 +219,6 @@ __irq_svc:
irq_handler
#ifdef CONFIG_PREEMPT
- get_thread_info tsk
ldr r8, [tsk, #TI_PREEMPT] @ get preempt count
ldr r0, [tsk, #TI_FLAGS] @ get flags
teq r8, #0 @ if preempt count != 0
@@ -366,17 +371,17 @@ ENDPROC(__fiq_abt)
/*
* User mode handlers
*
- * EABI note: sp_svc is always 64-bit aligned here, so should S_FRAME_SIZE
+ * EABI note: sp_svc is always 64-bit aligned here, so should PT_REGS_SIZE
*/
-#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (S_FRAME_SIZE & 7)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (PT_REGS_SIZE & 7)
#error "sizeof(struct pt_regs) must be a multiple of 8"
#endif
.macro usr_entry, trace=1, uaccess=1
UNWIND(.fnstart )
UNWIND(.cantunwind ) @ don't unwind the user space
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
ARM( stmib sp, {r1 - r12} )
THUMB( stmia sp, {r0 - r12} )
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 30a7228eaceb..10c3283d6c19 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -145,7 +145,7 @@ ENTRY(vector_swi)
#ifdef CONFIG_CPU_V7M
v7m_exception_entry
#else
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
stmia sp, {r0 - r12} @ Calling r0 - r12
ARM( add r8, sp, #S_PC )
ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 0d22ad206d52..6391728c8f03 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -90,7 +90,7 @@
@ Linux expects to have irqs off. Do it here before taking stack space
cpsid i
- sub sp, #S_FRAME_SIZE-S_IP
+ sub sp, #PT_REGS_SIZE-S_IP
stmdb sp!, {r0-r11}
@ load saved r12, lr, return address and xPSR.
@@ -160,7 +160,7 @@
ldmia sp!, {r0-r11}
@ restore main sp
- add sp, sp, #S_FRAME_SIZE-S_IP
+ add sp, sp, #PT_REGS_SIZE-S_IP
cpsie i
bx lr
@@ -215,7 +215,9 @@
blne trace_hardirqs_off
#endif
.endif
+ ldr r1, [sp, #SVC_ADDR_LIMIT]
uaccess_restore
+ str r1, [tsk, #TI_ADDR_LIMIT]
#ifndef CONFIG_THUMB2_KERNEL
@ ARM mode SVC restore
@@ -259,7 +261,9 @@
@ on the stack remains correct).
@
.macro svc_exit_via_fiq
+ ldr r1, [sp, #SVC_ADDR_LIMIT]
uaccess_restore
+ str r1, [tsk, #TI_ADDR_LIMIT]
#ifndef CONFIG_THUMB2_KERNEL
@ ARM mode restore
mov r0, sp
@@ -307,7 +311,7 @@
.endif
mov r0, r0 @ ARMv5T and earlier require a nop
@ after ldm {}^
- add sp, sp, #\offset + S_FRAME_SIZE
+ add sp, sp, #\offset + PT_REGS_SIZE
movs pc, lr @ return & move spsr_svc into cpsr
#elif defined(CONFIG_CPU_V7M)
@ V7M restore.
@@ -334,7 +338,7 @@
.else
ldmdb sp, {r0 - r12} @ get calling r0 - r12
.endif
- add sp, sp, #S_FRAME_SIZE - S_SP
+ add sp, sp, #PT_REGS_SIZE - S_SP
movs pc, lr @ return & move spsr_svc into cpsr
#endif /* !CONFIG_THUMB2_KERNEL */
.endm
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 907534f97053..abcf47848525 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -73,7 +73,7 @@ __irq_entry:
@ correctness they don't need to be restored. So only r8-r11 must be
@ restored here. The easiest way to do so is to restore r0-r7, too.
ldmia sp!, {r0-r11}
- add sp, #S_FRAME_SIZE-S_IP
+ add sp, #PT_REGS_SIZE-S_IP
cpsie i
bx lr
ENDPROC(__irq_entry)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 4a803c5a1ff7..612eb530f33f 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -96,19 +96,23 @@ void __show_regs(struct pt_regs *regs)
unsigned long flags;
char buf[64];
#ifndef CONFIG_CPU_V7M
- unsigned int domain;
+ unsigned int domain, fs;
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
/*
* Get the domain register for the parent context. In user
* mode, we don't save the DACR, so lets use what it should
* be. For other modes, we place it after the pt_regs struct.
*/
- if (user_mode(regs))
+ if (user_mode(regs)) {
domain = DACR_UACCESS_ENABLE;
- else
- domain = *(unsigned int *)(regs + 1);
+ fs = get_fs();
+ } else {
+ domain = to_svc_pt_regs(regs)->dacr;
+ fs = to_svc_pt_regs(regs)->addr_limit;
+ }
#else
domain = get_domain();
+ fs = get_fs();
#endif
#endif
@@ -144,7 +148,7 @@ void __show_regs(struct pt_regs *regs)
if ((domain & domain_mask(DOMAIN_USER)) ==
domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
segment = "none";
- else if (get_fs() == get_ds())
+ else if (fs == get_ds())
segment = "kernel";
else
segment = "user";
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7b5350060612..85a0bcb1f7ca 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -844,7 +844,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
struct resource *res;
kernel_code.start = virt_to_phys(_text);
- kernel_code.end = virt_to_phys(_etext - 1);
+ kernel_code.end = virt_to_phys(__init_begin - 1);
kernel_data.start = virt_to_phys(_sdata);
kernel_data.end = virt_to_phys(_end - 1);
@@ -1064,6 +1064,7 @@ void __init setup_arch(char **cmdline_p)
early_paging_init(mdesc);
#endif
setup_dma_zone(mdesc);
+ xen_early_init();
efi_init();
sanity_check_meminfo();
arm_memblock_init(mdesc);
@@ -1080,7 +1081,6 @@ void __init setup_arch(char **cmdline_p)
arm_dt_init_cpu_maps();
psci_dt_init();
- xen_early_init();
#ifdef CONFIG_SMP
if (is_smp()) {
if (!mdesc->smp_init || !mdesc->smp_init()) {
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 2e72be4f623e..22313cb53362 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -93,17 +93,53 @@ void erratum_a15_798181_init(void)
unsigned int revidr = read_cpuid(CPUID_REVIDR);
/* Brahma-B15 r0p0..r0p2 affected
- * Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
- if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2)
+ * Cortex-A15 r0p0..r3p3 w/o ECO fix affected
+ * Fixes applied to A15 with respect to the revision and revidr are:
+ *
+ * r0p0-r2p1: No fixes applied
+ * r2p2,r2p3:
+ * REVIDR[4]: 798181 Moving a virtual page that is being accessed
+ * by an active process can lead to unexpected behavior
+ * REVIDR[9]: Not defined
+ * r2p4,r3p0,r3p1,r3p2:
+ * REVIDR[4]: 798181 Moving a virtual page that is being accessed
+ * by an active process can lead to unexpected behavior
+ * REVIDR[9]: 798181 Moving a virtual page that is being accessed
+ * by an active process can lead to unexpected behavior
+ * - This is an update to a previously released ECO.
+ * r3p3:
+ * REVIDR[4]: Reserved
+ * REVIDR[9]: 798181 Moving a virtual page that is being accessed
+ * by an active process can lead to unexpected behavior
+ * - This is an update to a previously released ECO.
+ *
+ * Handling:
+ * REVIDR[9] set -> No WA
+ * REVIDR[4] set, REVIDR[9] cleared -> Partial WA
+ * Both cleared -> Full WA
+ */
+ if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2) {
erratum_a15_798181_handler = erratum_a15_798181_broadcast;
- else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr <= 0x413fc0f2 &&
- (revidr & 0x210) != 0x210) {
+ } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f2) {
+ erratum_a15_798181_handler = erratum_a15_798181_broadcast;
+ } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f4) {
if (revidr & 0x10)
erratum_a15_798181_handler =
erratum_a15_798181_partial;
else
erratum_a15_798181_handler =
erratum_a15_798181_broadcast;
+ } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x413fc0f3) {
+ if ((revidr & 0x210) == 0)
+ erratum_a15_798181_handler =
+ erratum_a15_798181_broadcast;
+ else if (revidr & 0x10)
+ erratum_a15_798181_handler =
+ erratum_a15_798181_partial;
+ } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x414fc0f0) {
+ if ((revidr & 0x200) == 0)
+ erratum_a15_798181_handler =
+ erratum_a15_798181_partial;
}
}
#endif
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index b6ec65e68009..02d5e5e8d44c 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -310,24 +310,17 @@ static void twd_timer_setup(void)
enable_percpu_irq(clk->irq, 0);
}
-static int twd_timer_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int twd_timer_starting_cpu(unsigned int cpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- twd_timer_setup();
- break;
- case CPU_DYING:
- twd_timer_stop();
- break;
- }
-
- return NOTIFY_OK;
+ twd_timer_setup();
+ return 0;
}
-static struct notifier_block twd_timer_cpu_nb = {
- .notifier_call = twd_timer_cpu_notify,
-};
+static int twd_timer_dying_cpu(unsigned int cpu)
+{
+ twd_timer_stop();
+ return 0;
+}
static int __init twd_local_timer_common_register(struct device_node *np)
{
@@ -345,9 +338,9 @@ static int __init twd_local_timer_common_register(struct device_node *np)
goto out_free;
}
- err = register_cpu_notifier(&twd_timer_cpu_nb);
- if (err)
- goto out_irq;
+ cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
+ "AP_ARM_TWD_STARTING",
+ twd_timer_starting_cpu, twd_timer_dying_cpu);
twd_get_clock(np);
if (!of_property_read_bool(np, "always-on"))
@@ -365,8 +358,6 @@ static int __init twd_local_timer_common_register(struct device_node *np)
return 0;
-out_irq:
- free_percpu_irq(twd_ppi, twd_evt);
out_free:
iounmap(twd_base);
twd_base = NULL;
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index e2c6da096cef..99420fc1f066 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -125,6 +125,8 @@ SECTIONS
#ifdef CONFIG_DEBUG_ALIGN_RODATA
. = ALIGN(1<<SECTION_SHIFT);
#endif
+ _etext = .; /* End of text section */
+
RO_DATA(PAGE_SIZE)
. = ALIGN(4);
@@ -155,8 +157,6 @@ SECTIONS
NOTES
- _etext = .; /* End of text and rodata section */
-
#ifdef CONFIG_DEBUG_RODATA
. = ALIGN(1<<SECTION_SHIFT);
#else
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index d8a780799506..27f4d96258a2 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -29,7 +29,10 @@ else
lib-y += io-readsw-armv4.o io-writesw-armv4.o
endif
-lib-$(CONFIG_ARCH_RPC) += ecard.o io-acorn.o floppydma.o
+ifeq ($(CONFIG_ARCH_RPC),y)
+ lib-y += ecard.o io-acorn.o floppydma.o
+ AFLAGS_delay-loop.o += -march=armv4
+endif
$(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S
$(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S
diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S
index 518bf6e93f78..792c59d885bc 100644
--- a/arch/arm/lib/delay-loop.S
+++ b/arch/arm/lib/delay-loop.S
@@ -10,6 +10,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/delay.h>
+
.text
.LC0: .word loops_per_jiffy
@@ -17,7 +18,6 @@
/*
* r0 <= 2000
- * lpj <= 0x01ffffff (max. 3355 bogomips)
* HZ <= 1000
*/
@@ -25,16 +25,11 @@ ENTRY(__loop_udelay)
ldr r2, .LC1
mul r0, r2, r0
ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0x7fffff06
- mov r1, #-1
ldr r2, .LC0
- ldr r2, [r2] @ max = 0x01ffffff
- add r0, r0, r1, lsr #32-14
- mov r0, r0, lsr #14 @ max = 0x0001ffff
- add r2, r2, r1, lsr #32-10
- mov r2, r2, lsr #10 @ max = 0x00007fff
- mul r0, r2, r0 @ max = 2^32-1
- add r0, r0, r1, lsr #32-6
- movs r0, r0, lsr #6
+ ldr r2, [r2]
+ umull r1, r0, r2, r0
+ adds r1, r1, #0xffffffff
+ adcs r0, r0, r0
reteq lr
/*
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 68cc09907828..ab47b8eb1b15 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -288,7 +288,7 @@ static struct gpio_led evm_leds[] = {
{ .name = "DS2", .active_low = 1,
.default_trigger = "mmc0", },
{ .name = "DS1", .active_low = 1,
- .default_trigger = "ide-disk", },
+ .default_trigger = "disk-activity", },
};
static const struct gpio_led_platform_data evm_led_data = {
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index e80f0dde2189..ae2a018b9305 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -111,20 +111,12 @@ static struct notifier_block mvebu_hwcc_pci_nb __maybe_unused = {
.notifier_call = mvebu_hwcc_notifier,
};
-static int armada_xp_clear_shared_l2_notifier_func(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int armada_xp_clear_l2_starting(unsigned int cpu)
{
- if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
- armada_xp_clear_shared_l2();
-
- return NOTIFY_OK;
+ armada_xp_clear_shared_l2();
+ return 0;
}
-static struct notifier_block armada_xp_clear_shared_l2_notifier = {
- .notifier_call = armada_xp_clear_shared_l2_notifier_func,
- .priority = 100,
-};
-
static void __init armada_370_coherency_init(struct device_node *np)
{
struct resource res;
@@ -155,8 +147,9 @@ static void __init armada_370_coherency_init(struct device_node *np)
of_node_put(cpu_config_np);
- register_cpu_notifier(&armada_xp_clear_shared_l2_notifier);
-
+ cpuhp_setup_state_nocalls(CPUHP_AP_ARM_MVEBU_COHERENCY,
+ "AP_ARM_MVEBU_COHERENCY",
+ armada_xp_clear_l2_starting, NULL);
exit:
set_cpu_coherent();
}
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 209aecb0df68..4dfb99504810 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -172,7 +172,7 @@ static struct gpio_led tps_leds[] = {
* Also, D9 requires non-battery power.
*/
{ .gpio = OSK_TPS_GPIO_LED_D9, .name = "d9",
- .default_trigger = "ide-disk", },
+ .default_trigger = "disk-activity", },
{ .gpio = OSK_TPS_GPIO_LED_D2, .name = "d2", },
{ .gpio = OSK_TPS_GPIO_LED_D3, .name = "d3", .active_low = 1,
.default_trigger = "heartbeat", },
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index bd7cd8b6a286..1080580b1343 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -464,7 +464,7 @@ static struct gpio_led spitz_gpio_leds[] = {
},
{
.name = "spitz:green:hddactivity",
- .default_trigger = "ide-disk",
+ .default_trigger = "disk-activity",
.gpio = SPITZ_GPIO_LED_GREEN,
},
};
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cb569b65a54d..d15a7fe51618 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1025,12 +1025,6 @@ config ARM_DMA_MEM_BUFFERABLE
You are recommended say 'Y' here and debug any affected drivers.
-config ARCH_HAS_BARRIERS
- bool
- help
- This option allows the use of custom mandatory barriers
- included via the mach/barriers.h file.
-
config ARM_HEAVY_MB
bool
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c61996c256cc..cc12905ae6f8 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -597,17 +597,16 @@ static void l2c310_configure(void __iomem *base)
L310_POWER_CTRL);
}
-static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data)
+static int l2c310_starting_cpu(unsigned int cpu)
{
- switch (act & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
- break;
- case CPU_DYING:
- set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
- break;
- }
- return NOTIFY_OK;
+ set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
+ return 0;
+}
+
+static int l2c310_dying_cpu(unsigned int cpu)
+{
+ set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
+ return 0;
}
static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
@@ -678,10 +677,10 @@ static void __init l2c310_enable(void __iomem *base, unsigned num_lock)
power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis");
}
- if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) {
- set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
- cpu_notifier(l2c310_cpu_enable_flz, 0);
- }
+ if (aux & L310_AUX_CTRL_FULL_LINE_ZERO)
+ cpuhp_setup_state(CPUHP_AP_ARM_L2X0_STARTING,
+ "AP_ARM_L2X0_STARTING", l2c310_starting_cpu,
+ l2c310_dying_cpu);
}
static void __init l2c310_fixup(void __iomem *base, u32 cache_id,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ff7ed5697d3e..b7eed75960fe 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -49,6 +49,7 @@ struct arm_dma_alloc_args {
pgprot_t prot;
const void *caller;
bool want_vaddr;
+ int coherent_flag;
};
struct arm_dma_free_args {
@@ -59,6 +60,9 @@ struct arm_dma_free_args {
bool want_vaddr;
};
+#define NORMAL 0
+#define COHERENT 1
+
struct arm_dma_allocator {
void *(*alloc)(struct arm_dma_alloc_args *args,
struct page **ret_page);
@@ -272,7 +276,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
return mask;
}
-static void __dma_clear_buffer(struct page *page, size_t size)
+static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
{
/*
* Ensure that the allocated pages are zeroed, and that any data
@@ -284,17 +288,21 @@ static void __dma_clear_buffer(struct page *page, size_t size)
while (size > 0) {
void *ptr = kmap_atomic(page);
memset(ptr, 0, PAGE_SIZE);
- dmac_flush_range(ptr, ptr + PAGE_SIZE);
+ if (coherent_flag != COHERENT)
+ dmac_flush_range(ptr, ptr + PAGE_SIZE);
kunmap_atomic(ptr);
page++;
size -= PAGE_SIZE;
}
- outer_flush_range(base, end);
+ if (coherent_flag != COHERENT)
+ outer_flush_range(base, end);
} else {
void *ptr = page_address(page);
memset(ptr, 0, size);
- dmac_flush_range(ptr, ptr + size);
- outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ if (coherent_flag != COHERENT) {
+ dmac_flush_range(ptr, ptr + size);
+ outer_flush_range(__pa(ptr), __pa(ptr) + size);
+ }
}
}
@@ -302,7 +310,8 @@ static void __dma_clear_buffer(struct page *page, size_t size)
* Allocate a DMA buffer for 'dev' of size 'size' using the
* specified gfp mask. Note that 'size' must be page aligned.
*/
-static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size,
+ gfp_t gfp, int coherent_flag)
{
unsigned long order = get_order(size);
struct page *page, *p, *e;
@@ -318,7 +327,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
__free_page(p);
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, coherent_flag);
return page;
}
@@ -340,7 +349,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
static void *__alloc_from_contiguous(struct device *dev, size_t size,
pgprot_t prot, struct page **ret_page,
- const void *caller, bool want_vaddr);
+ const void *caller, bool want_vaddr,
+ int coherent_flag);
static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
pgprot_t prot, struct page **ret_page,
@@ -405,10 +415,13 @@ static int __init atomic_pool_init(void)
atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
if (!atomic_pool)
goto out;
-
+ /*
+ * The atomic pool is only used for non-coherent allocations
+ * so we must pass NORMAL for coherent_flag.
+ */
if (dev_get_cma_area(NULL))
ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
- &page, atomic_pool_init, true);
+ &page, atomic_pool_init, true, NORMAL);
else
ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
&page, atomic_pool_init, true);
@@ -522,7 +535,11 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
{
struct page *page;
void *ptr = NULL;
- page = __dma_alloc_buffer(dev, size, gfp);
+ /*
+ * __alloc_remap_buffer is only called when the device is
+ * non-coherent
+ */
+ page = __dma_alloc_buffer(dev, size, gfp, NORMAL);
if (!page)
return NULL;
if (!want_vaddr)
@@ -577,7 +594,8 @@ static int __free_from_pool(void *start, size_t size)
static void *__alloc_from_contiguous(struct device *dev, size_t size,
pgprot_t prot, struct page **ret_page,
- const void *caller, bool want_vaddr)
+ const void *caller, bool want_vaddr,
+ int coherent_flag)
{
unsigned long order = get_order(size);
size_t count = size >> PAGE_SHIFT;
@@ -588,7 +606,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
if (!page)
return NULL;
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, coherent_flag);
if (!want_vaddr)
goto out;
@@ -638,7 +656,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
#define __get_dma_pgprot(attrs, prot) __pgprot(0)
#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv) NULL
#define __alloc_from_pool(size, ret_page) NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv) NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag) NULL
#define __free_from_pool(cpu_addr, size) do { } while (0)
#define __free_from_contiguous(dev, page, cpu_addr, size, wv) do { } while (0)
#define __dma_free_remap(cpu_addr, size) do { } while (0)
@@ -649,7 +667,8 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
struct page **ret_page)
{
struct page *page;
- page = __dma_alloc_buffer(dev, size, gfp);
+ /* __alloc_simple_buffer is only called when the device is coherent */
+ page = __dma_alloc_buffer(dev, size, gfp, COHERENT);
if (!page)
return NULL;
@@ -679,7 +698,7 @@ static void *cma_allocator_alloc(struct arm_dma_alloc_args *args,
{
return __alloc_from_contiguous(args->dev, args->size, args->prot,
ret_page, args->caller,
- args->want_vaddr);
+ args->want_vaddr, args->coherent_flag);
}
static void cma_allocator_free(struct arm_dma_free_args *args)
@@ -746,6 +765,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
.prot = prot,
.caller = caller,
.want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs),
+ .coherent_flag = is_coherent ? COHERENT : NORMAL,
};
#ifdef CONFIG_DMA_API_DEBUG
@@ -1253,7 +1273,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
static const int iommu_order_array[] = { 9, 8, 4, 0 };
static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
- gfp_t gfp, struct dma_attrs *attrs)
+ gfp_t gfp, struct dma_attrs *attrs,
+ int coherent_flag)
{
struct page **pages;
int count = size >> PAGE_SHIFT;
@@ -1277,7 +1298,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
if (!page)
goto error;
- __dma_clear_buffer(page, size);
+ __dma_clear_buffer(page, size, coherent_flag);
for (i = 0; i < count; i++)
pages[i] = page + i;
@@ -1327,7 +1348,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
pages[i + j] = pages[i] + j;
}
- __dma_clear_buffer(pages[i], PAGE_SIZE << order);
+ __dma_clear_buffer(pages[i], PAGE_SIZE << order, coherent_flag);
i += 1 << order;
count -= 1 << order;
}
@@ -1455,13 +1476,16 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
return NULL;
}
-static void *__iommu_alloc_atomic(struct device *dev, size_t size,
- dma_addr_t *handle)
+static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
+ dma_addr_t *handle, int coherent_flag)
{
struct page *page;
void *addr;
- addr = __alloc_from_pool(size, &page);
+ if (coherent_flag == COHERENT)
+ addr = __alloc_simple_buffer(dev, size, gfp, &page);
+ else
+ addr = __alloc_from_pool(size, &page);
if (!addr)
return NULL;
@@ -1477,14 +1501,18 @@ err_mapping:
}
static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
- dma_addr_t handle, size_t size)
+ dma_addr_t handle, size_t size, int coherent_flag)
{
__iommu_remove_mapping(dev, handle, size);
- __free_from_pool(cpu_addr, size);
+ if (coherent_flag == COHERENT)
+ __dma_free_buffer(virt_to_page(cpu_addr), size);
+ else
+ __free_from_pool(cpu_addr, size);
}
-static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs,
+ int coherent_flag)
{
pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
struct page **pages;
@@ -1493,8 +1521,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
*handle = DMA_ERROR_CODE;
size = PAGE_ALIGN(size);
- if (!gfpflags_allow_blocking(gfp))
- return __iommu_alloc_atomic(dev, size, handle);
+ if (coherent_flag == COHERENT || !gfpflags_allow_blocking(gfp))
+ return __iommu_alloc_simple(dev, size, gfp, handle,
+ coherent_flag);
/*
* Following is a work-around (a.k.a. hack) to prevent pages
@@ -1505,7 +1534,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
*/
gfp &= ~(__GFP_COMP);
- pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+ pages = __iommu_alloc_buffer(dev, size, gfp, attrs, coherent_flag);
if (!pages)
return NULL;
@@ -1530,7 +1559,19 @@ err_buffer:
return NULL;
}
-static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
+static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+ return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, NORMAL);
+}
+
+static void *arm_coherent_iommu_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
+{
+ return __arm_iommu_alloc_attrs(dev, size, handle, gfp, attrs, COHERENT);
+}
+
+static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
struct dma_attrs *attrs)
{
@@ -1540,8 +1581,6 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-
if (!pages)
return -ENXIO;
@@ -1562,19 +1601,34 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
return 0;
}
+static int arm_iommu_mmap_attrs(struct device *dev,
+ struct vm_area_struct *vma, void *cpu_addr,
+ dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
+
+ return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
+
+static int arm_coherent_iommu_mmap_attrs(struct device *dev,
+ struct vm_area_struct *vma, void *cpu_addr,
+ dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+ return __arm_iommu_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, attrs);
+}
/*
* free a page as defined by the above mapping.
* Must not be called with IRQs disabled.
*/
-void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
- dma_addr_t handle, struct dma_attrs *attrs)
+void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t handle, struct dma_attrs *attrs, int coherent_flag)
{
struct page **pages;
size = PAGE_ALIGN(size);
- if (__in_atomic_pool(cpu_addr, size)) {
- __iommu_free_atomic(dev, cpu_addr, handle, size);
+ if (coherent_flag == COHERENT || __in_atomic_pool(cpu_addr, size)) {
+ __iommu_free_atomic(dev, cpu_addr, handle, size, coherent_flag);
return;
}
@@ -1593,6 +1647,18 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
__iommu_free_buffer(dev, pages, size, attrs);
}
+void arm_iommu_free_attrs(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+ __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, NORMAL);
+}
+
+void arm_coherent_iommu_free_attrs(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
+{
+ __arm_iommu_free_attrs(dev, size, cpu_addr, handle, attrs, COHERENT);
+}
+
static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t dma_addr,
size_t size, struct dma_attrs *attrs)
@@ -1997,9 +2063,9 @@ struct dma_map_ops iommu_ops = {
};
struct dma_map_ops iommu_coherent_ops = {
- .alloc = arm_iommu_alloc_attrs,
- .free = arm_iommu_free_attrs,
- .mmap = arm_iommu_mmap_attrs,
+ .alloc = arm_coherent_iommu_alloc_attrs,
+ .free = arm_coherent_iommu_free_attrs,
+ .mmap = arm_coherent_iommu_mmap_attrs,
.get_sgtable = arm_iommu_get_sgtable,
.map_page = arm_coherent_iommu_map_page,
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index ad5841856007..3a2e678b8d30 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -243,7 +243,7 @@ good_area:
goto out;
}
- return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
+ return handle_mm_fault(vma, addr & PAGE_MASK, flags);
check_stack:
/* Don't allow expansion below FIRST_USER_ADDRESS */
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index b8d477321730..c1c1a5c67da1 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -23,7 +23,7 @@
#define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
#define __pgd_free(pgd) kfree(pgd)
#else
-#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2)
+#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2)
#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2)
#endif
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6fcaac8e200f..a7123b4e129d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -362,6 +362,39 @@ __ca15_errata:
#endif
b __errata_finish
+__ca12_errata:
+#ifdef CONFIG_ARM_ERRATA_818325_852422
+ mrc p15, 0, r10, c15, c0, 1 @ read diagnostic register
+ orr r10, r10, #1 << 12 @ set bit #12
+ mcr p15, 0, r10, c15, c0, 1 @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_821420
+ mrc p15, 0, r10, c15, c0, 2 @ read internal feature reg
+ orr r10, r10, #1 << 1 @ set bit #1
+ mcr p15, 0, r10, c15, c0, 2 @ write internal feature reg
+#endif
+#ifdef CONFIG_ARM_ERRATA_825619
+ mrc p15, 0, r10, c15, c0, 1 @ read diagnostic register
+ orr r10, r10, #1 << 24 @ set bit #24
+ mcr p15, 0, r10, c15, c0, 1 @ write diagnostic register
+#endif
+ b __errata_finish
+
+__ca17_errata:
+#ifdef CONFIG_ARM_ERRATA_852421
+ cmp r6, #0x12 @ only present up to r1p2
+ mrcle p15, 0, r10, c15, c0, 1 @ read diagnostic register
+ orrle r10, r10, #1 << 24 @ set bit #24
+ mcrle p15, 0, r10, c15, c0, 1 @ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_852423
+ cmp r6, #0x12 @ only present up to r1p2
+ mrcle p15, 0, r10, c15, c0, 1 @ read diagnostic register
+ orrle r10, r10, #1 << 12 @ set bit #12
+ mcrle p15, 0, r10, c15, c0, 1 @ write diagnostic register
+#endif
+ b __errata_finish
+
__v7_pj4b_setup:
#ifdef CONFIG_CPU_PJ4B
@@ -443,6 +476,16 @@ __v7_setup_cont:
teq r0, r10
beq __ca9_errata
+ /* Cortex-A12 Errata */
+ ldr r10, =0x00000c0d @ Cortex-A12 primary part number
+ teq r0, r10
+ beq __ca12_errata
+
+ /* Cortex-A17 Errata */
+ ldr r10, =0x00000c0e @ Cortex-A17 primary part number
+ teq r0, r10
+ beq __ca17_errata
+
/* Cortex-A15 Errata */
ldr r10, =0x00000c0f @ Cortex-A15 primary part number
teq r0, r10
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 73085d3482ed..da0b33deba6d 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -643,19 +643,19 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
* hardware state at every thread switch. We clear our held state when
* a CPU has been killed, indicating that the VFP hardware doesn't contain
* a threads VFP state. When a CPU starts up, we re-enable access to the
- * VFP hardware.
- *
- * Both CPU_DYING and CPU_STARTING are called on the CPU which
+ * VFP hardware. The callbacks below are called on the CPU which
* is being offlined/onlined.
*/
-static int vfp_hotplug(struct notifier_block *b, unsigned long action,
- void *hcpu)
+static int vfp_dying_cpu(unsigned int cpu)
{
- if (action == CPU_DYING || action == CPU_DYING_FROZEN)
- vfp_current_hw_state[(long)hcpu] = NULL;
- else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
- vfp_enable(NULL);
- return NOTIFY_OK;
+ vfp_force_reload(cpu, current_thread_info());
+ return 0;
+}
+
+static int vfp_starting_cpu(unsigned int unused)
+{
+ vfp_enable(NULL);
+ return 0;
}
void vfp_kmode_exception(void)
@@ -732,6 +732,10 @@ static int __init vfp_init(void)
unsigned int vfpsid;
unsigned int cpu_arch = cpu_architecture();
+ /*
+ * Enable the access to the VFP on all online CPUs so the
+ * following test on FPSID will succeed.
+ */
if (cpu_arch >= CPU_ARCH_ARMv6)
on_each_cpu(vfp_enable, NULL, 1);
@@ -794,7 +798,9 @@ static int __init vfp_init(void)
VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;
}
- hotcpu_notifier(vfp_hotplug, 0);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ARM_VFP_STARTING,
+ "AP_ARM_VFP_STARTING", vfp_starting_cpu,
+ vfp_dying_cpu);
vfp_vector = vfp_support_entry;
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 12969523414c..227952103b0b 100644
--- a/arch/arm/xen/Makefile
+++ b/arch/arm/xen/Makefile
@@ -1 +1,2 @@
obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o
+obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c
new file mode 100644
index 000000000000..16db419f9e90
--- /dev/null
+++ b/arch/arm/xen/efi.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2015, Linaro Limited, Shannon Zhao
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/efi.h>
+#include <xen/xen-ops.h>
+#include <asm/xen/xen-ops.h>
+
+/* Set XEN EFI runtime services function pointers. Other fields of struct efi,
+ * e.g. efi.systab, will be set like normal EFI.
+ */
+void __init xen_efi_runtime_setup(void)
+{
+ efi.get_time = xen_efi_get_time;
+ efi.set_time = xen_efi_set_time;
+ efi.get_wakeup_time = xen_efi_get_wakeup_time;
+ efi.set_wakeup_time = xen_efi_set_wakeup_time;
+ efi.get_variable = xen_efi_get_variable;
+ efi.get_next_variable = xen_efi_get_next_variable;
+ efi.set_variable = xen_efi_set_variable;
+ efi.query_variable_info = xen_efi_query_variable_info;
+ efi.update_capsule = xen_efi_update_capsule;
+ efi.query_capsule_caps = xen_efi_query_capsule_caps;
+ efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
+ efi.reset_system = NULL; /* Functionality provided by Xen. */
+}
+EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 75cd7345c654..b0b82f5ea338 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -12,14 +12,16 @@
#include <xen/page.h>
#include <xen/interface/sched.h>
#include <xen/xen-ops.h>
-#include <asm/paravirt.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
+#include <asm/xen/xen-ops.h>
#include <asm/system_misc.h>
+#include <asm/efi.h>
#include <linux/interrupt.h>
#include <linux/irqreturn.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_fdt.h>
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/cpuidle.h>
@@ -30,6 +32,7 @@
#include <linux/time64.h>
#include <linux/timekeeping.h>
#include <linux/timekeeper_internal.h>
+#include <linux/acpi.h>
#include <linux/mm.h>
@@ -46,14 +49,16 @@ struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
static struct vcpu_info __percpu *xen_vcpu_info;
+/* Linux <-> Xen vCPU id mapping */
+DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
/* These are unused until we support booting "pre-ballooned" */
unsigned long xen_released_pages;
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
static __read_mostly unsigned int xen_events_irq;
-static __initdata struct device_node *xen_node;
-
int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t *gfn, int nr,
@@ -84,19 +89,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
}
EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
-static unsigned long long xen_stolen_accounting(int cpu)
-{
- struct vcpu_runstate_info state;
-
- BUG_ON(cpu != smp_processor_id());
-
- xen_get_runstate_snapshot(&state);
-
- WARN_ON(state.state != RUNSTATE_running);
-
- return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
-}
-
static void xen_read_wallclock(struct timespec64 *ts)
{
u32 version;
@@ -161,12 +153,11 @@ static struct notifier_block xen_pvclock_gtod_notifier = {
.notifier_call = xen_pvclock_gtod_notify,
};
-static void xen_percpu_init(void)
+static int xen_starting_cpu(unsigned int cpu)
{
struct vcpu_register_vcpu_info info;
struct vcpu_info *vcpup;
int err;
- int cpu = get_cpu();
/*
* VCPUOP_register_vcpu_info cannot be called twice for the same
@@ -179,10 +170,14 @@ static void xen_percpu_init(void)
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
+ /* Direct vCPU id mapping for ARM guests. */
+ per_cpu(xen_vcpu_id, cpu) = cpu;
+
info.mfn = virt_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
- err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
+ err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+ &info);
BUG_ON(err);
per_cpu(xen_vcpu, cpu) = vcpup;
@@ -190,7 +185,13 @@ static void xen_percpu_init(void)
after_register_vcpu_info:
enable_percpu_irq(xen_events_irq, 0);
- put_cpu();
+ return 0;
+}
+
+static int xen_dying_cpu(unsigned int cpu)
+{
+ disable_percpu_irq(xen_events_irq);
+ return 0;
}
static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
@@ -209,32 +210,50 @@ static void xen_power_off(void)
BUG_ON(rc);
}
-static int xen_cpu_notification(struct notifier_block *self,
- unsigned long action,
- void *hcpu)
+static irqreturn_t xen_arm_callback(int irq, void *arg)
{
- switch (action) {
- case CPU_STARTING:
- xen_percpu_init();
- break;
- case CPU_DYING:
- disable_percpu_irq(xen_events_irq);
- break;
- default:
- break;
- }
-
- return NOTIFY_OK;
+ xen_hvm_evtchn_do_upcall();
+ return IRQ_HANDLED;
}
-static struct notifier_block xen_cpu_notifier = {
- .notifier_call = xen_cpu_notification,
-};
+static __initdata struct {
+ const char *compat;
+ const char *prefix;
+ const char *version;
+ bool found;
+} hyper_node = {"xen,xen", "xen,xen-", NULL, false};
-static irqreturn_t xen_arm_callback(int irq, void *arg)
+static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
+ int depth, void *data)
{
- xen_hvm_evtchn_do_upcall();
- return IRQ_HANDLED;
+ const void *s = NULL;
+ int len;
+
+ if (depth != 1 || strcmp(uname, "hypervisor") != 0)
+ return 0;
+
+ if (of_flat_dt_is_compatible(node, hyper_node.compat))
+ hyper_node.found = true;
+
+ s = of_get_flat_dt_prop(node, "compatible", &len);
+ if (strlen(hyper_node.prefix) + 3 < len &&
+ !strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
+ hyper_node.version = s + strlen(hyper_node.prefix);
+
+ /*
+ * Check if Xen supports EFI by checking whether there is the
+ * "/hypervisor/uefi" node in DT. If so, runtime services are available
+ * through proxy functions (e.g. in case of Xen dom0 EFI implementation
+ * they call special hypercall which executes relevant EFI functions)
+ * and that is why they are always enabled.
+ */
+ if (IS_ENABLED(CONFIG_XEN_EFI)) {
+ if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
+ !efi_runtime_disabled())
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ }
+
+ return 0;
}
/*
@@ -244,26 +263,18 @@ static irqreturn_t xen_arm_callback(int irq, void *arg)
#define GRANT_TABLE_PHYSADDR 0
void __init xen_early_init(void)
{
- int len;
- const char *s = NULL;
- const char *version = NULL;
- const char *xen_prefix = "xen,xen-";
-
- xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
- if (!xen_node) {
+ of_scan_flat_dt(fdt_find_hyper_node, NULL);
+ if (!hyper_node.found) {
pr_debug("No Xen support\n");
return;
}
- s = of_get_property(xen_node, "compatible", &len);
- if (strlen(xen_prefix) + 3 < len &&
- !strncmp(xen_prefix, s, strlen(xen_prefix)))
- version = s + strlen(xen_prefix);
- if (version == NULL) {
+
+ if (hyper_node.version == NULL) {
pr_debug("Xen version not found\n");
return;
}
- pr_info("Xen %s support found\n", version);
+ pr_info("Xen %s support found\n", hyper_node.version);
xen_domain_type = XEN_HVM_DOMAIN;
@@ -278,28 +289,68 @@ void __init xen_early_init(void)
add_preferred_console("hvc", 0, NULL);
}
+static void __init xen_acpi_guest_init(void)
+{
+#ifdef CONFIG_ACPI
+ struct xen_hvm_param a;
+ int interrupt, trigger, polarity;
+
+ a.domid = DOMID_SELF;
+ a.index = HVM_PARAM_CALLBACK_IRQ;
+
+ if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
+ || (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
+ xen_events_irq = 0;
+ return;
+ }
+
+ interrupt = a.value & 0xff;
+ trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
+ : ACPI_LEVEL_SENSITIVE;
+ polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
+ : ACPI_ACTIVE_HIGH;
+ xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
+#endif
+}
+
+static void __init xen_dt_guest_init(void)
+{
+ struct device_node *xen_node;
+
+ xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
+ if (!xen_node) {
+ pr_err("Xen support was detected before, but it has disappeared\n");
+ return;
+ }
+
+ xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+}
+
static int __init xen_guest_init(void)
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
- struct resource res;
- phys_addr_t grant_frames;
if (!xen_domain())
return 0;
- if (of_address_to_resource(xen_node, GRANT_TABLE_PHYSADDR, &res)) {
- pr_err("Xen grant table base address not found\n");
- return -ENODEV;
- }
- grant_frames = res.start;
+ if (!acpi_disabled)
+ xen_acpi_guest_init();
+ else
+ xen_dt_guest_init();
- xen_events_irq = irq_of_parse_and_map(xen_node, 0);
if (!xen_events_irq) {
pr_err("Xen event channel interrupt not found\n");
return -ENODEV;
}
+ /*
+ * The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
+ * parameters are found. Force enable runtime services.
+ */
+ if (efi_enabled(EFI_RUNTIME_SERVICES))
+ xen_efi_runtime_setup();
+
shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
if (!shared_info_page) {
@@ -328,7 +379,13 @@ static int __init xen_guest_init(void)
if (xen_vcpu_info == NULL)
return -ENOMEM;
- if (gnttab_setup_auto_xlat_frames(grant_frames)) {
+ /* Direct vCPU id mapping for ARM guests. */
+ per_cpu(xen_vcpu_id, 0) = 0;
+
+ xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
+ if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
+ &xen_auto_xlat_grant_frames.vaddr,
+ xen_auto_xlat_grant_frames.count)) {
free_percpu(xen_vcpu_info);
return -ENOMEM;
}
@@ -351,16 +408,14 @@ static int __init xen_guest_init(void)
return -EINVAL;
}
- xen_percpu_init();
+ xen_time_setup_guest();
- register_cpu_notifier(&xen_cpu_notifier);
-
- pv_time_ops.steal_clock = xen_stolen_accounting;
- static_key_slow_inc(&paravirt_steal_enabled);
if (xen_initial_domain())
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
- return 0;
+ return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
+ "AP_ARM_XEN_STARTING", xen_starting_cpu,
+ xen_dying_cpu);
}
early_initcall(xen_guest_init);
@@ -403,4 +458,5 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
+EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
EXPORT_SYMBOL_GPL(privcmd_call);
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index 9a36f4f49c10..a648dfc3be30 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -91,6 +91,7 @@ HYPERCALL3(vcpu_op);
HYPERCALL1(tmem_op);
HYPERCALL1(platform_op_raw);
HYPERCALL2(multicall);
+HYPERCALL2(vm_assist);
ENTRY(privcmd_call)
stmdb sp!, {r4}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5a0a691d4220..9f8b99e20557 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,9 +4,11 @@ config ARM64
select ACPI_GENERIC_GSI if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_KCOV
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_USE_CMPXCHG_LOCKREF
@@ -85,8 +87,11 @@ config ARM64
select HAVE_PERF_EVENTS
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
select HAVE_SYSCALL_TRACEPOINTS
+ select HAVE_KPROBES
+ select HAVE_KRETPROBES if HAVE_KPROBES
select IOMMU_DMA if IOMMU_SUPPORT
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
@@ -664,6 +669,16 @@ config PARAVIRT_TIME_ACCOUNTING
If in doubt, say N here.
+config KEXEC
+ depends on PM_SLEEP_SMP
+ select KEXEC_CORE
+ bool "kexec system call"
+ ---help---
+ kexec is a system call that implements the ability to shutdown your
+ current kernel, and to start another kernel. It is like a reboot
+ but it is independent of the system firmware. And like a reboot
+ you can start any kernel with it, not just Linux.
+
config XEN_DOM0
def_bool y
depends on XEN
@@ -872,7 +887,7 @@ config RELOCATABLE
config RANDOMIZE_BASE
bool "Randomize the address of the kernel image"
- select ARM64_MODULE_PLTS
+ select ARM64_MODULE_PLTS if MODULES
select RELOCATABLE
help
Randomizes the virtual address at which the kernel image is
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 648a32c89541..d59b6908a21a 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -12,7 +12,6 @@
LDFLAGS_vmlinux :=-p --no-undefined -X
CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
-OBJCOPYFLAGS :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
GZFLAGS :=-9
ifneq ($(CONFIG_RELOCATABLE),)
@@ -121,6 +120,16 @@ archclean:
$(Q)$(MAKE) $(clean)=$(boot)
$(Q)$(MAKE) $(clean)=$(boot)/dts
+# We need to generate vdso-offsets.h before compiling certain files in kernel/.
+# In order to do that, we should use the archprepare target, but we can't since
+# asm-offsets.h is included in some files used to generate vdso-offsets.h, and
+# asm-offsets.h is built in prepare0, for which archprepare is a dependency.
+# Therefore we need to generate the header after prepare0 has been made, hence
+# this hack.
+prepare: vdso_prepare
+vdso_prepare: prepare0
+ $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
+
define archhelp
echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index 305c552b5ec1..1f012c506434 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -14,6 +14,8 @@
# Based on the ia64 boot/Makefile.
#
+OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+
targets := Image Image.gz
$(obj)/Image: vmlinux FORCE
diff --git a/arch/arm64/boot/dts/apm/apm-merlin.dts b/arch/arm64/boot/dts/apm/apm-merlin.dts
index 387c6a8d0da9..b0f64414c1b0 100644
--- a/arch/arm64/boot/dts/apm/apm-merlin.dts
+++ b/arch/arm64/boot/dts/apm/apm-merlin.dts
@@ -83,3 +83,9 @@
status = "ok";
};
};
+
+&mdio {
+ sgenet0phy: phy@0 {
+ reg = <0x0>;
+ };
+};
diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 44db32ec5e9c..b7fb5d9295c2 100644
--- a/arch/arm64/boot/dts/apm/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
@@ -79,3 +79,15 @@
&mmc0 {
status = "ok";
};
+
+&mdio {
+ menet0phy: phy@3 {
+ reg = <0x3>;
+ };
+ sgenet0phy: phy@4 {
+ reg = <0x4>;
+ };
+ sgenet1phy: phy@5 {
+ reg = <0x5>;
+ };
+};
diff --git a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
index c569f761d090..2e1e5daa1dc7 100644
--- a/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi
@@ -625,10 +625,18 @@
apm,irq-start = <8>;
};
+ mdio: mdio@1f610000 {
+ compatible = "apm,xgene-mdio-xfi";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x1f610000 0x0 0xd100>;
+ clocks = <&xge0clk 0>;
+ };
+
sgenet0: ethernet@1f610000 {
compatible = "apm,xgene2-sgenet";
status = "disabled";
- reg = <0x0 0x1f610000 0x0 0x10000>,
+ reg = <0x0 0x1f610000 0x0 0xd100>,
<0x0 0x1f600000 0x0 0Xd100>,
<0x0 0x20000000 0x0 0X20000>;
interrupts = <0 96 4>,
@@ -637,6 +645,7 @@
clocks = <&xge0clk 0>;
local-mac-address = [00 01 73 00 00 01];
phy-connection-type = "sgmii";
+ phy-handle = <&sgenet0phy>;
};
xgenet1: ethernet@1f620000 {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 5147d7698924..6bf7cbe2e72d 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -237,20 +237,11 @@
clocks = <&socplldiv2 0>;
reg = <0x0 0x1f21c000 0x0 0x1000>;
reg-names = "csr-reg";
- csr-mask = <0x3>;
+ csr-mask = <0xa>;
+ enable-mask = <0xf>;
clock-output-names = "sge0clk";
};
- sge1clk: sge1clk@1f21c000 {
- compatible = "apm,xgene-device-clock";
- #clock-cells = <1>;
- clocks = <&socplldiv2 0>;
- reg = <0x0 0x1f21c000 0x0 0x1000>;
- reg-names = "csr-reg";
- csr-mask = <0xc>;
- clock-output-names = "sge1clk";
- };
-
xge0clk: xge0clk@1f61c000 {
compatible = "apm,xgene-device-clock";
#clock-cells = <1>;
@@ -921,6 +912,14 @@
clocks = <&rtcclk 0>;
};
+ mdio: mdio@17020000 {
+ compatible = "apm,xgene-mdio-rgmii";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0x0 0x17020000 0x0 0xd100>;
+ clocks = <&menetclk 0>;
+ };
+
menet: ethernet@17020000 {
compatible = "apm,xgene-enet";
status = "disabled";
@@ -934,7 +933,7 @@
/* mac address will be overwritten by the bootloader */
local-mac-address = [00 00 00 00 00 00];
phy-connection-type = "rgmii";
- phy-handle = <&menetphy>;
+ phy-handle = <&menet0phy>,<&menetphy>;
mdio {
compatible = "apm,xgene-mdio";
#address-cells = <1>;
@@ -960,6 +959,7 @@
clocks = <&sge0clk 0>;
local-mac-address = [00 00 00 00 00 00];
phy-connection-type = "sgmii";
+ phy-handle = <&sgenet0phy>;
};
sgenet1: ethernet@1f210030 {
@@ -973,9 +973,9 @@
<0x0 0xAD 0x4>;
port-id = <1>;
dma-coherent;
- clocks = <&sge1clk 0>;
local-mac-address = [00 00 00 00 00 00];
phy-connection-type = "sgmii";
+ phy-handle = <&sgenet1phy>;
};
xgenet: ethernet@1f610000 {
diff --git a/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
index 54ca40c9f711..ea5603fd106a 100644
--- a/arch/arm64/boot/dts/broadcom/ns2-svk.dts
+++ b/arch/arm64/boot/dts/broadcom/ns2-svk.dts
@@ -52,6 +52,14 @@
};
};
+&pci_phy0 {
+ status = "ok";
+};
+
+&pci_phy1 {
+ status = "ok";
+};
+
&pcie0 {
status = "ok";
};
@@ -132,3 +140,11 @@
#size-cells = <1>;
};
};
+
+&mdio_mux_iproc {
+ mdio@10 {
+ gphy0: eth-phy@10 {
+ reg = <0x10>;
+ };
+ };
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index ec68ec1a80c8..46b78fa89f4c 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -263,6 +263,45 @@
IRQ_TYPE_LEVEL_HIGH)>;
};
+ mdio_mux_iproc: mdio-mux@6602023c {
+ compatible = "brcm,mdio-mux-iproc";
+ reg = <0x6602023c 0x14>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ mdio@0 {
+ reg = <0x0>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ pci_phy0: pci-phy@0 {
+ compatible = "brcm,ns2-pcie-phy";
+ reg = <0x0>;
+ #phy-cells = <0>;
+ status = "disabled";
+ };
+ };
+
+ mdio@7 {
+ reg = <0x7>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ pci_phy1: pci-phy@0 {
+ compatible = "brcm,ns2-pcie-phy";
+ reg = <0x0>;
+ #phy-cells = <0>;
+ status = "disabled";
+ };
+ };
+
+ mdio@10 {
+ reg = <0x10>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ };
+ };
+
timer0: timer@66030000 {
compatible = "arm,sp804", "arm,primecell";
reg = <0x66030000 0x1000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 05f89c4a5413..77b8c4e388ca 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -168,6 +168,18 @@
};
};
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ vpu_dma_reserved: vpu_dma_mem_region {
+ compatible = "shared-dma-pool";
+ reg = <0 0xb7000000 0 0x500000>;
+ alignment = <0x1000>;
+ no-map;
+ };
+ };
+
timer {
compatible = "arm,armv8-timer";
interrupt-parent = <&gic>;
@@ -312,6 +324,17 @@
clock-names = "spi", "wrap";
};
+ vpu: vpu@10020000 {
+ compatible = "mediatek,mt8173-vpu";
+ reg = <0 0x10020000 0 0x30000>,
+ <0 0x10050000 0 0x100>;
+ reg-names = "tcm", "cfg_reg";
+ interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&topckgen CLK_TOP_SCP_SEL>;
+ clock-names = "main";
+ memory-region = <&vpu_dma_reserved>;
+ };
+
sysirq: intpol-controller@10200620 {
compatible = "mediatek,mt8173-sysirq",
"mediatek,mt6577-sysirq";
@@ -754,6 +777,45 @@
clock-names = "apb", "smi";
};
+ vcodec_enc: vcodec@18002000 {
+ compatible = "mediatek,mt8173-vcodec-enc";
+ reg = <0 0x18002000 0 0x1000>, /* VENC_SYS */
+ <0 0x19002000 0 0x1000>; /* VENC_LT_SYS */
+ interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 202 IRQ_TYPE_LEVEL_LOW>;
+ mediatek,larb = <&larb3>,
+ <&larb5>;
+ iommus = <&iommu M4U_PORT_VENC_RCPU>,
+ <&iommu M4U_PORT_VENC_REC>,
+ <&iommu M4U_PORT_VENC_BSDMA>,
+ <&iommu M4U_PORT_VENC_SV_COMV>,
+ <&iommu M4U_PORT_VENC_RD_COMV>,
+ <&iommu M4U_PORT_VENC_CUR_LUMA>,
+ <&iommu M4U_PORT_VENC_CUR_CHROMA>,
+ <&iommu M4U_PORT_VENC_REF_LUMA>,
+ <&iommu M4U_PORT_VENC_REF_CHROMA>,
+ <&iommu M4U_PORT_VENC_NBM_RDMA>,
+ <&iommu M4U_PORT_VENC_NBM_WDMA>,
+ <&iommu M4U_PORT_VENC_RCPU_SET2>,
+ <&iommu M4U_PORT_VENC_REC_FRM_SET2>,
+ <&iommu M4U_PORT_VENC_BSDMA_SET2>,
+ <&iommu M4U_PORT_VENC_SV_COMA_SET2>,
+ <&iommu M4U_PORT_VENC_RD_COMA_SET2>,
+ <&iommu M4U_PORT_VENC_CUR_LUMA_SET2>,
+ <&iommu M4U_PORT_VENC_CUR_CHROMA_SET2>,
+ <&iommu M4U_PORT_VENC_REF_LUMA_SET2>,
+ <&iommu M4U_PORT_VENC_REC_CHROMA_SET2>;
+ mediatek,vpu = <&vpu>;
+ clocks = <&topckgen CLK_TOP_VENCPLL_D2>,
+ <&topckgen CLK_TOP_VENC_SEL>,
+ <&topckgen CLK_TOP_UNIVPLL1_D2>,
+ <&topckgen CLK_TOP_VENC_LT_SEL>;
+ clock-names = "venc_sel_src",
+ "venc_sel",
+ "venc_lt_sel_src",
+ "venc_lt_sel";
+ };
+
vencltsys: clock-controller@19000000 {
compatible = "mediatek,mt8173-vencltsys", "syscon";
reg = <0 0x19000000 0 0x1000>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index fd2d74d0491e..4ed4756dfa97 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -70,6 +70,7 @@ CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CMA=y
CONFIG_XEN=y
+CONFIG_KEXEC=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_COMPAT=y
CONFIG_CPU_IDLE=y
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index cff532a6744e..f43d2c44c765 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,6 +1,5 @@
generic-y += bug.h
generic-y += bugs.h
-generic-y += checksum.h
generic-y += clkdev.h
generic-y += cputime.h
generic-y += current.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index aee323b13802..5420cb0fcb3e 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -113,4 +113,14 @@ static inline const char *acpi_get_enable_method(int cpu)
pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
#endif
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+#endif /* CONFIG_ACPI_NUMA */
+
+#define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
+
#endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index beccbdefa106..8746ff6abd77 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -95,13 +95,11 @@ void apply_alternatives(void *start, size_t length);
* The code that follows this macro will be assembled and linked as
* normal. There are no restrictions on this code.
*/
-.macro alternative_if_not cap, enable = 1
- .if \enable
+.macro alternative_if_not cap
.pushsection .altinstructions, "a"
altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
.popsection
661:
- .endif
.endm
/*
@@ -118,27 +116,27 @@ void apply_alternatives(void *start, size_t length);
* alternative sequence it is defined in (branches into an
* alternative sequence are not fixed up).
*/
-.macro alternative_else, enable = 1
- .if \enable
+.macro alternative_else
662: .pushsection .altinstr_replacement, "ax"
663:
- .endif
.endm
/*
* Complete an alternative code sequence.
*/
-.macro alternative_endif, enable = 1
- .if \enable
+.macro alternative_endif
664: .popsection
.org . - (664b-663b) + (662b-661b)
.org . - (662b-661b) + (664b-663b)
- .endif
.endm
#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \
alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
+.macro user_alt, label, oldinstr, newinstr, cond
+9999: alternative_insn "\oldinstr", "\newinstr", \cond
+ _ASM_EXTABLE 9999b, \label
+.endm
/*
* Generate the assembly for UAO alternatives with exception table entries.
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 10b017c4bdd8..d5025c69ca81 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -24,6 +24,7 @@
#define __ASM_ASSEMBLER_H
#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
#include <asm/page.h>
#include <asm/pgtable-hwdef.h>
#include <asm/ptrace.h>
@@ -261,7 +262,16 @@ lr .req x30 // link register
add \size, \kaddr, \size
sub \tmp2, \tmp1, #1
bic \kaddr, \kaddr, \tmp2
-9998: dc \op, \kaddr
+9998:
+ .if (\op == cvau || \op == cvac)
+alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
+ dc \op, \kaddr
+alternative_else
+ dc civac, \kaddr
+alternative_endif
+ .else
+ dc \op, \kaddr
+ .endif
add \kaddr, \kaddr, \tmp1
cmp \kaddr, \size
b.lo 9998b
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
new file mode 100644
index 000000000000..09f65339d66d
--- /dev/null
+++ b/arch/arm64/include/asm/checksum.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CHECKSUM_H
+#define __ASM_CHECKSUM_H
+
+#include <linux/types.h>
+
+static inline __sum16 csum_fold(__wsum csum)
+{
+ u32 sum = (__force u32)csum;
+ sum += (sum >> 16) | (sum << 16);
+ return ~(__force __sum16)(sum >> 16);
+}
+#define csum_fold csum_fold
+
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+ __uint128_t tmp;
+ u64 sum;
+
+ tmp = *(const __uint128_t *)iph;
+ iph += 16;
+ ihl -= 4;
+ tmp += ((tmp >> 64) | (tmp << 64));
+ sum = tmp >> 64;
+ do {
+ sum += *(const u32 *)iph;
+ iph += 4;
+ } while (--ihl);
+
+ sum += ((sum >> 32) | (sum << 32));
+ return csum_fold(sum >> 32);
+}
+#define ip_fast_csum ip_fast_csum
+
+#include <asm-generic/checksum.h>
+
+#endif /* __ASM_CHECKSUM_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 13a6103130cd..889226b4c6e1 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -25,10 +25,12 @@
*/
struct cpuinfo_arm64 {
struct cpu cpu;
+ struct kobject kobj;
u32 reg_ctr;
u32 reg_cntfrq;
u32 reg_dczid;
u32 reg_midr;
+ u32 reg_revidr;
u64 reg_id_aa64dfr0;
u64 reg_id_aa64dfr1;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 224efe730e46..49dd1bd3ea50 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -191,7 +191,9 @@ void __init setup_cpu_features(void);
void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
const char *info);
+void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
void check_local_cpu_errata(void);
+void __init enable_errata_workarounds(void);
void verify_local_cpu_errata(void);
void verify_local_cpu_capabilities(void);
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 2fcb9b7c876c..4b6b3f72a215 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -66,6 +66,11 @@
#define CACHE_FLUSH_IS_SAFE 1
+/* kprobes BRK opcodes with ESR encoding */
+#define BRK64_ESR_MASK 0xFFFF
+#define BRK64_ESR_KPROBES 0x0004
+#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+
/* AArch32 */
#define DBG_ESR_EVT_BKPT 0x4
#define DBG_ESR_EVT_VECC 0x5
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index bd887663689b..a9e54aad15ef 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -14,8 +14,7 @@ extern void efi_init(void);
#endif
int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
-
-#define efi_set_mapping_permissions efi_create_mapping
+int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
#define arch_efi_call_virt_setup() \
({ \
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 77eeb2cc648f..f772e15c4766 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -74,6 +74,7 @@
#define ESR_ELx_EC_SHIFT (26)
#define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT)
+#define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT)
#define ESR_ELx_IL (UL(1) << 25)
#define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 30e50eb54a67..1dbaa901d7e5 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -120,6 +120,29 @@ enum aarch64_insn_register {
AARCH64_INSN_REG_SP = 31 /* Stack pointer: as load/store base reg */
};
+enum aarch64_insn_special_register {
+ AARCH64_INSN_SPCLREG_SPSR_EL1 = 0xC200,
+ AARCH64_INSN_SPCLREG_ELR_EL1 = 0xC201,
+ AARCH64_INSN_SPCLREG_SP_EL0 = 0xC208,
+ AARCH64_INSN_SPCLREG_SPSEL = 0xC210,
+ AARCH64_INSN_SPCLREG_CURRENTEL = 0xC212,
+ AARCH64_INSN_SPCLREG_DAIF = 0xDA11,
+ AARCH64_INSN_SPCLREG_NZCV = 0xDA10,
+ AARCH64_INSN_SPCLREG_FPCR = 0xDA20,
+ AARCH64_INSN_SPCLREG_DSPSR_EL0 = 0xDA28,
+ AARCH64_INSN_SPCLREG_DLR_EL0 = 0xDA29,
+ AARCH64_INSN_SPCLREG_SPSR_EL2 = 0xE200,
+ AARCH64_INSN_SPCLREG_ELR_EL2 = 0xE201,
+ AARCH64_INSN_SPCLREG_SP_EL1 = 0xE208,
+ AARCH64_INSN_SPCLREG_SPSR_INQ = 0xE218,
+ AARCH64_INSN_SPCLREG_SPSR_ABT = 0xE219,
+ AARCH64_INSN_SPCLREG_SPSR_UND = 0xE21A,
+ AARCH64_INSN_SPCLREG_SPSR_FIQ = 0xE21B,
+ AARCH64_INSN_SPCLREG_SPSR_EL3 = 0xF200,
+ AARCH64_INSN_SPCLREG_ELR_EL3 = 0xF201,
+ AARCH64_INSN_SPCLREG_SP_EL2 = 0xF210
+};
+
enum aarch64_insn_variant {
AARCH64_INSN_VARIANT_32BIT,
AARCH64_INSN_VARIANT_64BIT
@@ -223,8 +246,15 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
{ return (val); }
+__AARCH64_INSN_FUNCS(adr_adrp, 0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000)
__AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800)
__AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800)
+__AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000)
+__AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000)
+__AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000)
+__AARCH64_INSN_FUNCS(load_ex, 0x3F400000, 0x08400000)
+__AARCH64_INSN_FUNCS(store_ex, 0x3F400000, 0x08000000)
__AARCH64_INSN_FUNCS(stp_post, 0x7FC00000, 0x28800000)
__AARCH64_INSN_FUNCS(ldp_post, 0x7FC00000, 0x28C00000)
__AARCH64_INSN_FUNCS(stp_pre, 0x7FC00000, 0x29800000)
@@ -273,10 +303,15 @@ __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001)
__AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002)
__AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003)
__AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000)
+__AARCH64_INSN_FUNCS(exception, 0xFF000000, 0xD4000000)
__AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F)
__AARCH64_INSN_FUNCS(br, 0xFFFFFC1F, 0xD61F0000)
__AARCH64_INSN_FUNCS(blr, 0xFFFFFC1F, 0xD63F0000)
__AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000)
+__AARCH64_INSN_FUNCS(eret, 0xFFFFFFFF, 0xD69F03E0)
+__AARCH64_INSN_FUNCS(mrs, 0xFFF00000, 0xD5300000)
+__AARCH64_INSN_FUNCS(msr_imm, 0xFFF8F01F, 0xD500401F)
+__AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000)
#undef __AARCH64_INSN_FUNCS
@@ -286,6 +321,8 @@ bool aarch64_insn_is_branch_imm(u32 insn);
int aarch64_insn_read(void *addr, u32 *insnp);
int aarch64_insn_write(void *addr, u32 insn);
enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
+bool aarch64_insn_uses_literal(u32 insn);
+bool aarch64_insn_is_branch(u32 insn);
u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
u32 insn, u64 imm);
@@ -367,9 +404,13 @@ bool aarch32_insn_is_wide(u32 insn);
#define A32_RT_OFFSET 12
#define A32_RT2_OFFSET 0
+u32 aarch64_insn_extract_system_reg(u32 insn);
u32 aarch32_insn_extract_reg_num(u32 insn, int offset);
u32 aarch32_insn_mcr_extract_opc2(u32 insn);
u32 aarch32_insn_mcr_extract_crm(u32 insn);
+
+typedef bool (pstate_check_t)(unsigned long);
+extern pstate_check_t * const aarch32_opcode_cond_checks[16];
#endif /* __ASSEMBLY__ */
#endif /* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 11cc941bd107..8c581281fa12 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -110,8 +110,5 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
: : "r" (flags) : "memory"); \
} while (0)
-#define local_dbg_enable() asm("msr daifclr, #8" : : : "memory")
-#define local_dbg_disable() asm("msr daifset, #8" : : : "memory")
-
#endif
#endif
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
new file mode 100644
index 000000000000..04744dc5fb61
--- /dev/null
+++ b/arch/arm64/include/asm/kexec.h
@@ -0,0 +1,48 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ARM64_KEXEC_H
+#define _ARM64_KEXEC_H
+
+/* Maximum physical address we can use pages from */
+
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can reach in physical address mode */
+
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+
+/* Maximum address we can use for the control code buffer */
+
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE 4096
+
+#define KEXEC_ARCH KEXEC_ARCH_AARCH64
+
+#ifndef __ASSEMBLY__
+
+/**
+ * crash_setup_regs() - save registers for the panic kernel
+ *
+ * @newregs: registers are saved here
+ * @oldregs: registers to be saved (may be %NULL)
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+ struct pt_regs *oldregs)
+{
+ /* Empty routine needed to avoid build errors. */
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
new file mode 100644
index 000000000000..61b49150dfa3
--- /dev/null
+++ b/arch/arm64/include/asm/kprobes.h
@@ -0,0 +1,62 @@
+/*
+ * arch/arm64/include/asm/kprobes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KPROBES_H
+#define _ARM_KPROBES_H
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define MAX_INSN_SIZE 1
+#define MAX_STACK_SIZE 128
+
+#define flush_insn_slot(p) do { } while (0)
+#define kretprobe_blacklist_size 0
+
+#include <asm/probes.h>
+
+struct prev_kprobe {
+ struct kprobe *kp;
+ unsigned int status;
+};
+
+/* Single step context for kprobe */
+struct kprobe_step_ctx {
+ unsigned long ss_pending;
+ unsigned long match_addr;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+ unsigned int kprobe_status;
+ unsigned long saved_irqflag;
+ struct prev_kprobe prev_kprobe;
+ struct kprobe_step_ctx ss_ctx;
+ struct pt_regs jprobe_saved_regs;
+ char jprobes_stack[MAX_STACK_SIZE];
+};
+
+void arch_remove_kprobe(struct kprobe *);
+int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data);
+int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
+int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
+void kretprobe_trampoline(void);
+void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
+
+#endif /* _ARM_KPROBES_H */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 40bc1681b6d5..4cdeae3b17c6 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -210,7 +210,7 @@ static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_get_hsr(vcpu) >> ESR_ELx_EC_SHIFT;
+ return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
}
static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 97b1d8f26b9c..8d9fce037b2f 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -34,7 +34,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
extern void init_mem_pgprot(void);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
- pgprot_t prot);
+ pgprot_t prot, bool allow_block_mappings);
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
#endif
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index e9b4f2942335..600887e491fd 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -5,6 +5,8 @@
#ifdef CONFIG_NUMA
+#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2)
+
/* currently, arm64 implements flat NUMA topology */
#define parent_node(node) (node)
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
new file mode 100644
index 000000000000..5af574d632fa
--- /dev/null
+++ b/arch/arm64/include/asm/probes.h
@@ -0,0 +1,35 @@
+/*
+ * arch/arm64/include/asm/probes.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef _ARM_PROBES_H
+#define _ARM_PROBES_H
+
+#include <asm/opcodes.h>
+
+struct kprobe;
+struct arch_specific_insn;
+
+typedef u32 kprobe_opcode_t;
+typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+
+/* architecture specific copy of original instruction */
+struct arch_specific_insn {
+ kprobe_opcode_t *insn;
+ pstate_check_t *pstate_cc;
+ kprobes_handler_t *handler;
+ /* restore address after step xol */
+ unsigned long restore;
+};
+
+#endif
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index cef1cf398356..ace0a96e7d6e 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -192,5 +192,6 @@ static inline void spin_lock_prefetch(const void *ptr)
void cpu_enable_pan(void *__unused);
void cpu_enable_uao(void *__unused);
+void cpu_enable_cache_maint_trap(void *__unused);
#endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
new file mode 100644
index 000000000000..07b8ed037dee
--- /dev/null
+++ b/arch/arm64/include/asm/ptdump.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_PTDUMP_H
+#define __ASM_PTDUMP_H
+
+#ifdef CONFIG_ARM64_PTDUMP
+
+#include <linux/mm_types.h>
+
+struct addr_marker {
+ unsigned long start_address;
+ char *name;
+};
+
+struct ptdump_info {
+ struct mm_struct *mm;
+ const struct addr_marker *markers;
+ unsigned long base_addr;
+ unsigned long max_addr;
+};
+
+int ptdump_register(struct ptdump_info *info, const char *name);
+
+#else
+static inline int ptdump_register(struct ptdump_info *info, const char *name)
+{
+ return 0;
+}
+#endif /* CONFIG_ARM64_PTDUMP */
+
+#endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 7f94755089e2..ada08b5b036d 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -46,7 +46,6 @@
#define COMPAT_PSR_MODE_UND 0x0000001b
#define COMPAT_PSR_MODE_SYS 0x0000001f
#define COMPAT_PSR_T_BIT 0x00000020
-#define COMPAT_PSR_E_BIT 0x00000200
#define COMPAT_PSR_F_BIT 0x00000040
#define COMPAT_PSR_I_BIT 0x00000080
#define COMPAT_PSR_A_BIT 0x00000100
@@ -74,6 +73,7 @@
#define COMPAT_PT_DATA_ADDR 0x10004
#define COMPAT_PT_TEXT_END_ADDR 0x10008
#ifndef __ASSEMBLY__
+#include <linux/bug.h>
/* sizeof(struct user) for AArch32 */
#define COMPAT_USER_SZ 296
@@ -121,6 +121,8 @@ struct pt_regs {
u64 unused; // maintain 16 byte alignment
};
+#define MAX_REG_OFFSET offsetof(struct pt_regs, pstate)
+
#define arch_has_single_step() (1)
#ifdef CONFIG_COMPAT
@@ -146,9 +148,58 @@ struct pt_regs {
#define fast_interrupts_enabled(regs) \
(!((regs)->pstate & PSR_F_BIT))
-#define user_stack_pointer(regs) \
+#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))
+
+extern int regs_query_register_offset(const char *name);
+extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+ unsigned int n);
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs: pt_regs from which register value is gotten
+ * @offset: offset of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset)
+{
+ u64 val = 0;
+
+ WARN_ON(offset & 7);
+
+ offset >>= 3;
+ switch (offset) {
+ case 0 ... 30:
+ val = regs->regs[offset];
+ break;
+ case offsetof(struct pt_regs, sp) >> 3:
+ val = regs->sp;
+ break;
+ case offsetof(struct pt_regs, pc) >> 3:
+ val = regs->pc;
+ break;
+ case offsetof(struct pt_regs, pstate) >> 3:
+ val = regs->pstate;
+ break;
+ default:
+ val = 0;
+ }
+
+ return val;
+}
+
+/* Valid only for Kernel mode traps. */
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+ return regs->sp;
+}
+
static inline unsigned long regs_return_value(struct pt_regs *regs)
{
return regs->regs[0];
@@ -158,8 +209,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
struct task_struct;
int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
-#define instruction_pointer(regs) ((unsigned long)(regs)->pc)
+#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)))
+
+#include <asm-generic/ptrace.h>
+#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 751e901c8d37..cc06794b7346 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -98,11 +98,11 @@
SCTLR_ELx_SA | SCTLR_ELx_I)
/* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_UCI (1 << 26)
#define SCTLR_EL1_SPAN (1 << 23)
#define SCTLR_EL1_SED (1 << 8)
#define SCTLR_EL1_CP15BEN (1 << 5)
-
/* id_aa64isar0 */
#define ID_AA64ISAR0_RDM_SHIFT 28
#define ID_AA64ISAR0_ATOMICS_SHIFT 20
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 0cc2f29bf9da..9cd03f3e812f 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -34,6 +34,8 @@ struct undef_hook {
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
+void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 9e397a542756..5e834d10b291 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -21,6 +21,7 @@
/*
* User space memory access functions
*/
+#include <linux/kasan-checks.h>
#include <linux/string.h>
#include <linux/thread_info.h>
@@ -256,15 +257,29 @@ do { \
-EFAULT; \
})
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ kasan_check_write(to, n);
+ return __arch_copy_from_user(to, from, n);
+}
+
+static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ kasan_check_read(from, n);
+ return __arch_copy_to_user(to, from, n);
+}
+
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ kasan_check_write(to, n);
+
if (access_ok(VERIFY_READ, from, n))
- n = __copy_from_user(to, from, n);
+ n = __arch_copy_from_user(to, from, n);
else /* security hole - plug it */
memset(to, 0, n);
return n;
@@ -272,8 +287,10 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u
static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ kasan_check_read(from, n);
+
if (access_ok(VERIFY_WRITE, to, n))
- n = __copy_to_user(to, from, n);
+ n = __arch_copy_to_user(to, from, n);
return n;
}
diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
index de66199673d7..2b9a63771eda 100644
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ b/arch/arm64/include/asm/vdso_datapage.h
@@ -22,6 +22,8 @@
struct vdso_data {
__u64 cs_cycle_last; /* Timebase at clocksource init */
+ __u64 raw_time_sec; /* Raw time */
+ __u64 raw_time_nsec;
__u64 xtime_clock_sec; /* Kernel time */
__u64 xtime_clock_nsec;
__u64 xtime_coarse_sec; /* Coarse time */
@@ -29,8 +31,10 @@ struct vdso_data {
__u64 wtm_clock_sec; /* Wall to monotonic time */
__u64 wtm_clock_nsec;
__u32 tb_seq_count; /* Timebase sequence counter */
- __u32 cs_mult; /* Clocksource multiplier */
- __u32 cs_shift; /* Clocksource shift */
+ /* cs_* members must be adjacent and in this order (ldp accesses) */
+ __u32 cs_mono_mult; /* NTP-adjusted clocksource multiplier */
+ __u32 cs_shift; /* Clocksource shift (mono = raw) */
+ __u32 cs_raw_mult; /* Raw clocksource multiplier */
__u32 tz_minuteswest; /* Whacky timezone stuff */
__u32 tz_dsttime;
__u32 use_syscall;
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index dcbcf8dcbefb..bbc6a8cf83f1 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -34,6 +34,11 @@
*/
#define HVC_SET_VECTORS 1
+/*
+ * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
+ */
+#define HVC_SOFT_RESTART 2
+
#define BOOT_CPU_MODE_EL1 (0xe11)
#define BOOT_CPU_MODE_EL2 (0xe12)
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
new file mode 100644
index 000000000000..ec154e719b11
--- /dev/null
+++ b/arch/arm64/include/asm/xen/xen-ops.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_XEN_OPS_H
+#define _ASM_XEN_OPS_H
+
+void xen_efi_runtime_setup(void);
+
+#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2173149d8954..14f7b651c787 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -26,8 +26,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
$(call if_changed,objcopy)
arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
- sys_compat.o entry32.o \
- ../../arm/kernel/opcodes.o
+ sys_compat.o entry32.o
arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o
arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o
arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o
@@ -42,16 +41,15 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o
arm64-obj-$(CONFIG_PCI) += pci.o
arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o
arm64-obj-$(CONFIG_ACPI) += acpi.o
+arm64-obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o
arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o
arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o
arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o
+arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \
+ cpu-reset.o
-obj-y += $(arm64-obj-y) vdso/
+obj-y += $(arm64-obj-y) vdso/ probes/
obj-m += $(arm64-obj-m)
head-y := head.o
extra-y += $(head-y) vmlinux.lds
-
-# vDSO - this must be built first to generate the symbol offsets
-$(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h
-$(obj)/vdso/vdso-offsets.h: $(obj)/vdso
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
new file mode 100644
index 000000000000..f85149cc7c71
--- /dev/null
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -0,0 +1,112 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ * Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+ u32 node_id; /* logical node containing this CPU */
+ u64 cpu_hwid; /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+{
+ int i;
+
+ for (i = 0; i < cpus_in_srat; i++) {
+ if (hwid == early_node_cpu_hwid[i].cpu_hwid)
+ return early_node_cpu_hwid[i].node_id;
+ }
+
+ return NUMA_NO_NODE;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+ int pxm, node;
+ phys_cpuid_t mpidr;
+
+ if (srat_disabled())
+ return;
+
+ if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+ pr_err("SRAT: Invalid SRAT header length: %d\n",
+ pa->header.length);
+ bad_srat();
+ return;
+ }
+
+ if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+ return;
+
+ if (cpus_in_srat >= NR_CPUS) {
+ pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+ NR_CPUS);
+ return;
+ }
+
+ pxm = pa->proximity_domain;
+ node = acpi_map_pxm_to_node(pxm);
+
+ if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+ pr_err("SRAT: Too many proximity domains %d\n", pxm);
+ bad_srat();
+ return;
+ }
+
+ mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
+ if (mpidr == PHYS_CPUID_INVALID) {
+ pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+ pxm, pa->acpi_processor_uid);
+ bad_srat();
+ return;
+ }
+
+ early_node_cpu_hwid[cpus_in_srat].node_id = node;
+ early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr;
+ node_set(node, numa_nodes_parsed);
+ cpus_in_srat++;
+ pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
+ pxm, mpidr, node);
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+ int ret;
+
+ ret = acpi_numa_init();
+ if (ret)
+ return ret;
+
+ return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 678f30b05a45..78f368039c79 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -27,6 +27,7 @@
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/arm-smccc.h>
+#include <linux/kprobes.h>
#include <asm/checksum.h>
@@ -34,8 +35,8 @@ EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(clear_page);
/* user mem (segment) */
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(__arch_copy_from_user);
+EXPORT_SYMBOL(__arch_copy_to_user);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(__copy_in_user);
@@ -68,6 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit);
#ifdef CONFIG_FUNCTION_TRACER
EXPORT_SYMBOL(_mcount);
+NOKPROBE_SYMBOL(_mcount);
#endif
/* arm-smccc */
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index c37202c0c838..42ffdb54e162 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -121,7 +121,7 @@ static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
* 0 - If all the hooks ran successfully.
* -EINVAL - At least one hook is not supported by the CPU.
*/
-static int run_all_insn_set_hw_mode(unsigned long cpu)
+static int run_all_insn_set_hw_mode(unsigned int cpu)
{
int rc = 0;
unsigned long flags;
@@ -131,7 +131,7 @@ static int run_all_insn_set_hw_mode(unsigned long cpu)
list_for_each_entry(insn, &insn_emulation, node) {
bool enable = (insn->current_mode == INSN_HW);
if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) {
- pr_warn("CPU[%ld] cannot support the emulation of %s",
+ pr_warn("CPU[%u] cannot support the emulation of %s",
cpu, insn->ops->name);
rc = -EINVAL;
}
@@ -316,28 +316,6 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
*/
#define TYPE_SWPB (1 << 22)
-/*
- * Set up process info to signal segmentation fault - called on access error.
- */
-static void set_segfault(struct pt_regs *regs, unsigned long addr)
-{
- siginfo_t info;
-
- down_read(&current->mm->mmap_sem);
- if (find_vma(current->mm, addr) == NULL)
- info.si_code = SEGV_MAPERR;
- else
- info.si_code = SEGV_ACCERR;
- up_read(&current->mm->mmap_sem);
-
- info.si_signo = SIGSEGV;
- info.si_errno = 0;
- info.si_addr = (void *) instruction_pointer(regs);
-
- pr_debug("SWP{B} emulation: access caused memory abort!\n");
- arm64_notify_die("Illegal memory access", regs, &info, 0);
-}
-
static int emulate_swpX(unsigned int address, unsigned int *data,
unsigned int type)
{
@@ -366,6 +344,21 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
return res;
}
+#define ARM_OPCODE_CONDITION_UNCOND 0xf
+
+static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)
+{
+ u32 cc_bits = opcode >> 28;
+
+ if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
+ if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
+ return ARM_OPCODE_CONDTEST_PASS;
+ else
+ return ARM_OPCODE_CONDTEST_FAIL;
+ }
+ return ARM_OPCODE_CONDTEST_UNCOND;
+}
+
/*
* swp_handler logs the id of calling process, dissects the instruction, sanity
* checks the memory location, calls emulate_swpX for the actual operation and
@@ -380,7 +373,7 @@ static int swp_handler(struct pt_regs *regs, u32 instr)
type = instr & TYPE_SWPB;
- switch (arm_check_condition(instr, regs->pstate)) {
+ switch (aarch32_check_condition(instr, regs->pstate)) {
case ARM_OPCODE_CONDTEST_PASS:
break;
case ARM_OPCODE_CONDTEST_FAIL:
@@ -430,7 +423,8 @@ ret:
return 0;
fault:
- set_segfault(regs, address);
+ pr_debug("SWP{B} emulation: access caused memory abort!\n");
+ arm64_notify_segfault(regs, address);
return 0;
}
@@ -461,7 +455,7 @@ static int cp15barrier_handler(struct pt_regs *regs, u32 instr)
{
perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
- switch (arm_check_condition(instr, regs->pstate)) {
+ switch (aarch32_check_condition(instr, regs->pstate)) {
case ARM_OPCODE_CONDTEST_PASS:
break;
case ARM_OPCODE_CONDTEST_FAIL:
@@ -617,20 +611,6 @@ static struct insn_emulation_ops setend_ops = {
.set_hw_mode = setend_set_hw_mode,
};
-static int insn_cpu_hotplug_notify(struct notifier_block *b,
- unsigned long action, void *hcpu)
-{
- int rc = 0;
- if ((action & ~CPU_TASKS_FROZEN) == CPU_STARTING)
- rc = run_all_insn_set_hw_mode((unsigned long)hcpu);
-
- return notifier_from_errno(rc);
-}
-
-static struct notifier_block insn_cpu_hotplug_notifier = {
- .notifier_call = insn_cpu_hotplug_notify,
-};
-
/*
* Invoked as late_initcall, since not needed before init spawned.
*/
@@ -649,7 +629,9 @@ static int __init armv8_deprecated_init(void)
pr_info("setend instruction emulation is not supported on the system");
}
- register_cpu_notifier(&insn_cpu_hotplug_notifier);
+ cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
+ "AP_ARM64_ISNDEP_STARTING",
+ run_all_insn_set_hw_mode, NULL);
register_insn_emulation_sysctl(ctl_abi);
return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 2f4ba774488a..05070b72fc28 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -51,6 +51,17 @@ int main(void)
DEFINE(S_X5, offsetof(struct pt_regs, regs[5]));
DEFINE(S_X6, offsetof(struct pt_regs, regs[6]));
DEFINE(S_X7, offsetof(struct pt_regs, regs[7]));
+ DEFINE(S_X8, offsetof(struct pt_regs, regs[8]));
+ DEFINE(S_X10, offsetof(struct pt_regs, regs[10]));
+ DEFINE(S_X12, offsetof(struct pt_regs, regs[12]));
+ DEFINE(S_X14, offsetof(struct pt_regs, regs[14]));
+ DEFINE(S_X16, offsetof(struct pt_regs, regs[16]));
+ DEFINE(S_X18, offsetof(struct pt_regs, regs[18]));
+ DEFINE(S_X20, offsetof(struct pt_regs, regs[20]));
+ DEFINE(S_X22, offsetof(struct pt_regs, regs[22]));
+ DEFINE(S_X24, offsetof(struct pt_regs, regs[24]));
+ DEFINE(S_X26, offsetof(struct pt_regs, regs[26]));
+ DEFINE(S_X28, offsetof(struct pt_regs, regs[28]));
DEFINE(S_LR, offsetof(struct pt_regs, regs[30]));
DEFINE(S_SP, offsetof(struct pt_regs, sp));
#ifdef CONFIG_COMPAT
@@ -78,6 +89,7 @@ int main(void)
BLANK();
DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+ DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW);
DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
@@ -85,6 +97,8 @@ int main(void)
DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
BLANK();
DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last));
+ DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec));
+ DEFINE(VDSO_RAW_TIME_NSEC, offsetof(struct vdso_data, raw_time_nsec));
DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec));
DEFINE(VDSO_XTIME_CLK_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
@@ -92,7 +106,8 @@ int main(void)
DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec));
DEFINE(VDSO_WTM_CLK_NSEC, offsetof(struct vdso_data, wtm_clock_nsec));
DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count));
- DEFINE(VDSO_CS_MULT, offsetof(struct vdso_data, cs_mult));
+ DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult));
+ DEFINE(VDSO_CS_RAW_MULT, offsetof(struct vdso_data, cs_raw_mult));
DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift));
DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest));
DEFINE(VDSO_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime));
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
new file mode 100644
index 000000000000..65f42d257414
--- /dev/null
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -0,0 +1,54 @@
+/*
+ * CPU reset routines
+ *
+ * Copyright (C) 2001 Deep Blue Solutions Ltd.
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Huawei Futurewei Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/sysreg.h>
+#include <asm/virt.h>
+
+.text
+.pushsection .idmap.text, "ax"
+
+/*
+ * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
+ * cpu_soft_restart.
+ *
+ * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @entry: Location to jump to for soft reset.
+ * arg0: First argument passed to @entry.
+ * arg1: Second argument passed to @entry.
+ * arg2: Third argument passed to @entry.
+ *
+ * Put the CPU into the same state as it would be if it had been reset, and
+ * branch to what would be the reset vector. It must be executed with the
+ * flat identity mapping.
+ */
+ENTRY(__cpu_soft_restart)
+ /* Clear sctlr_el1 flags. */
+ mrs x12, sctlr_el1
+ ldr x13, =SCTLR_ELx_FLAGS
+ bic x12, x12, x13
+ msr sctlr_el1, x12
+ isb
+
+ cbz x0, 1f // el2_switch?
+ mov x0, #HVC_SOFT_RESTART
+ hvc #0 // no return
+
+1: mov x18, x1 // entry
+ mov x0, x2 // arg0
+ mov x1, x3 // arg1
+ mov x2, x4 // arg2
+ br x18
+ENDPROC(__cpu_soft_restart)
+
+.popsection
diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
new file mode 100644
index 000000000000..d4e9ecb264f0
--- /dev/null
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -0,0 +1,34 @@
+/*
+ * CPU reset routines
+ *
+ * Copyright (C) 2015 Huawei Futurewei Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ARM64_CPU_RESET_H
+#define _ARM64_CPU_RESET_H
+
+#include <asm/virt.h>
+
+void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
+ unsigned long arg0, unsigned long arg1, unsigned long arg2);
+
+static inline void __noreturn cpu_soft_restart(unsigned long el2_switch,
+ unsigned long entry, unsigned long arg0, unsigned long arg1,
+ unsigned long arg2)
+{
+ typeof(__cpu_soft_restart) *restart;
+
+ el2_switch = el2_switch && !is_kernel_in_hyp_mode() &&
+ is_hyp_mode_available();
+ restart = (void *)virt_to_phys(__cpu_soft_restart);
+
+ cpu_install_idmap();
+ restart(el2_switch, entry, arg0, arg1, arg2);
+ unreachable();
+}
+
+#endif
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index af716b65110d..82b0fc2e637b 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -46,6 +46,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
.desc = "ARM errata 826319, 827319, 824069",
.capability = ARM64_WORKAROUND_CLEAN_CACHE,
MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02),
+ .enable = cpu_enable_cache_maint_trap,
},
#endif
#ifdef CONFIG_ARM64_ERRATUM_819472
@@ -54,6 +55,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
.desc = "ARM errata 819472",
.capability = ARM64_WORKAROUND_CLEAN_CACHE,
MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01),
+ .enable = cpu_enable_cache_maint_trap,
},
#endif
#ifdef CONFIG_ARM64_ERRATUM_832075
@@ -133,3 +135,8 @@ void check_local_cpu_errata(void)
{
update_cpu_capabilities(arm64_errata, "enabling workaround for");
}
+
+void __init enable_errata_workarounds(void)
+{
+ enable_cpu_capabilities(arm64_errata);
+}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 811773d1c1d0..916d27ad79c1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -913,8 +913,7 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
* Run through the enabled capabilities and enable() it on all active
* CPUs
*/
-static void __init
-enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
+void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
{
for (; caps->matches; caps++)
if (caps->enable && cpus_have_cap(caps->capability))
@@ -1036,6 +1035,7 @@ void __init setup_cpu_features(void)
/* Set the CPU feature capabilies */
setup_feature_capabilities();
+ enable_errata_workarounds();
setup_elf_hwcaps(arm64_elf_hwcaps);
if (system_supports_32bit_el0())
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index e11857fce05f..75a0f8acef66 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -9,13 +9,16 @@
* published by the Free Software Foundation.
*/
+#include <linux/acpi.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <asm/cpuidle.h>
#include <asm/cpu_ops.h>
-int __init arm_cpuidle_init(unsigned int cpu)
+int arm_cpuidle_init(unsigned int cpu)
{
int ret = -EOPNOTSUPP;
@@ -39,3 +42,18 @@ int arm_cpuidle_suspend(int index)
return cpu_ops[cpu]->cpu_suspend(index);
}
+
+#ifdef CONFIG_ACPI
+
+#include <acpi/processor.h>
+
+int acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+ return arm_cpuidle_init(cpu);
+}
+
+int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+ return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+}
+#endif
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index c173d329397f..ed1b84fe6925 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -183,6 +183,123 @@ const struct seq_operations cpuinfo_op = {
.show = c_show
};
+
+static struct kobj_type cpuregs_kobj_type = {
+ .sysfs_ops = &kobj_sysfs_ops,
+};
+
+/*
+ * The ARM ARM uses the phrase "32-bit register" to describe a register
+ * whose upper 32 bits are RES0 (per C5.1.1, ARM DDI 0487A.i), however
+ * no statement is made as to whether the upper 32 bits will or will not
+ * be made use of in future, and between ARM DDI 0487A.c and ARM DDI
+ * 0487A.d CLIDR_EL1 was expanded from 32-bit to 64-bit.
+ *
+ * Thus, while both MIDR_EL1 and REVIDR_EL1 are described as 32-bit
+ * registers, we expose them both as 64 bit values to cater for possible
+ * future expansion without an ABI break.
+ */
+#define kobj_to_cpuinfo(kobj) container_of(kobj, struct cpuinfo_arm64, kobj)
+#define CPUREGS_ATTR_RO(_name, _field) \
+ static ssize_t _name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+ { \
+ struct cpuinfo_arm64 *info = kobj_to_cpuinfo(kobj); \
+ \
+ if (info->reg_midr) \
+ return sprintf(buf, "0x%016x\n", info->reg_##_field); \
+ else \
+ return 0; \
+ } \
+ static struct kobj_attribute cpuregs_attr_##_name = __ATTR_RO(_name)
+
+CPUREGS_ATTR_RO(midr_el1, midr);
+CPUREGS_ATTR_RO(revidr_el1, revidr);
+
+static struct attribute *cpuregs_id_attrs[] = {
+ &cpuregs_attr_midr_el1.attr,
+ &cpuregs_attr_revidr_el1.attr,
+ NULL
+};
+
+static struct attribute_group cpuregs_attr_group = {
+ .attrs = cpuregs_id_attrs,
+ .name = "identification"
+};
+
+static int cpuid_add_regs(int cpu)
+{
+ int rc;
+ struct device *dev;
+ struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
+
+ dev = get_cpu_device(cpu);
+ if (!dev) {
+ rc = -ENODEV;
+ goto out;
+ }
+ rc = kobject_add(&info->kobj, &dev->kobj, "regs");
+ if (rc)
+ goto out;
+ rc = sysfs_create_group(&info->kobj, &cpuregs_attr_group);
+ if (rc)
+ kobject_del(&info->kobj);
+out:
+ return rc;
+}
+
+static int cpuid_remove_regs(int cpu)
+{
+ struct device *dev;
+ struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
+
+ dev = get_cpu_device(cpu);
+ if (!dev)
+ return -ENODEV;
+ if (info->kobj.parent) {
+ sysfs_remove_group(&info->kobj, &cpuregs_attr_group);
+ kobject_del(&info->kobj);
+ }
+
+ return 0;
+}
+
+static int cpuid_callback(struct notifier_block *nb,
+ unsigned long action, void *hcpu)
+{
+ int rc = 0;
+ unsigned long cpu = (unsigned long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_ONLINE:
+ rc = cpuid_add_regs(cpu);
+ break;
+ case CPU_DEAD:
+ rc = cpuid_remove_regs(cpu);
+ break;
+ }
+
+ return notifier_from_errno(rc);
+}
+
+static int __init cpuinfo_regs_init(void)
+{
+ int cpu;
+
+ cpu_notifier_register_begin();
+
+ for_each_possible_cpu(cpu) {
+ struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
+
+ kobject_init(&info->kobj, &cpuregs_kobj_type);
+ if (cpu_online(cpu))
+ cpuid_add_regs(cpu);
+ }
+ __hotcpu_notifier(cpuid_callback, 0);
+
+ cpu_notifier_register_done();
+ return 0;
+}
static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
{
unsigned int cpu = smp_processor_id();
@@ -212,6 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
info->reg_ctr = read_cpuid_cachetype();
info->reg_dczid = read_cpuid(DCZID_EL0);
info->reg_midr = read_cpuid_id();
+ info->reg_revidr = read_cpuid(REVIDR_EL1);
info->reg_id_aa64dfr0 = read_cpuid(ID_AA64DFR0_EL1);
info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1);
@@ -264,3 +382,5 @@ void __init cpuinfo_store_boot_cpu(void)
boot_cpu_data = *info;
init_cpu_features(&boot_cpu_data);
}
+
+device_initcall(cpuinfo_regs_init);
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 4fbf3c54275c..91fff48d0f57 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -23,6 +23,7 @@
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/ptrace.h>
+#include <linux/kprobes.h>
#include <linux/stat.h>
#include <linux/uaccess.h>
@@ -48,6 +49,7 @@ static void mdscr_write(u32 mdscr)
asm volatile("msr mdscr_el1, %0" :: "r" (mdscr));
local_dbg_restore(flags);
}
+NOKPROBE_SYMBOL(mdscr_write);
static u32 mdscr_read(void)
{
@@ -55,6 +57,7 @@ static u32 mdscr_read(void)
asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr));
return mdscr;
}
+NOKPROBE_SYMBOL(mdscr_read);
/*
* Allow root to disable self-hosted debug from userspace.
@@ -103,6 +106,7 @@ void enable_debug_monitors(enum dbg_active_el el)
mdscr_write(mdscr);
}
}
+NOKPROBE_SYMBOL(enable_debug_monitors);
void disable_debug_monitors(enum dbg_active_el el)
{
@@ -123,6 +127,7 @@ void disable_debug_monitors(enum dbg_active_el el)
mdscr_write(mdscr);
}
}
+NOKPROBE_SYMBOL(disable_debug_monitors);
/*
* OS lock clearing.
@@ -151,7 +156,6 @@ static int debug_monitors_init(void)
/* Clear the OS lock. */
on_each_cpu(clear_os_lock, NULL, 1);
isb();
- local_dbg_enable();
/* Register hotplug handler. */
__register_cpu_notifier(&os_lock_nb);
@@ -166,22 +170,15 @@ postcore_initcall(debug_monitors_init);
*/
static void set_regs_spsr_ss(struct pt_regs *regs)
{
- unsigned long spsr;
-
- spsr = regs->pstate;
- spsr &= ~DBG_SPSR_SS;
- spsr |= DBG_SPSR_SS;
- regs->pstate = spsr;
+ regs->pstate |= DBG_SPSR_SS;
}
+NOKPROBE_SYMBOL(set_regs_spsr_ss);
static void clear_regs_spsr_ss(struct pt_regs *regs)
{
- unsigned long spsr;
-
- spsr = regs->pstate;
- spsr &= ~DBG_SPSR_SS;
- regs->pstate = spsr;
+ regs->pstate &= ~DBG_SPSR_SS;
}
+NOKPROBE_SYMBOL(clear_regs_spsr_ss);
/* EL1 Single Step Handler hooks */
static LIST_HEAD(step_hook);
@@ -225,6 +222,7 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
return retval;
}
+NOKPROBE_SYMBOL(call_step_hook);
static void send_user_sigtrap(int si_code)
{
@@ -266,6 +264,10 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
*/
user_rewind_single_step(current);
} else {
+#ifdef CONFIG_KPROBES
+ if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
+ return 0;
+#endif
if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
return 0;
@@ -279,6 +281,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
return 0;
}
+NOKPROBE_SYMBOL(single_step_handler);
/*
* Breakpoint handler is re-entrant as another breakpoint can
@@ -316,19 +319,28 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
}
+NOKPROBE_SYMBOL(call_break_hook);
static int brk_handler(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
if (user_mode(regs)) {
send_user_sigtrap(TRAP_BRKPT);
- } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
- pr_warning("Unexpected kernel BRK exception at EL1\n");
+ }
+#ifdef CONFIG_KPROBES
+ else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
+ if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED)
+ return -EFAULT;
+ }
+#endif
+ else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+ pr_warn("Unexpected kernel BRK exception at EL1\n");
return -EFAULT;
}
return 0;
}
+NOKPROBE_SYMBOL(brk_handler);
int aarch32_break_handler(struct pt_regs *regs)
{
@@ -365,6 +377,7 @@ int aarch32_break_handler(struct pt_regs *regs)
send_user_sigtrap(TRAP_BRKPT);
return 0;
}
+NOKPROBE_SYMBOL(aarch32_break_handler);
static int __init debug_traps_init(void)
{
@@ -386,6 +399,7 @@ void user_rewind_single_step(struct task_struct *task)
if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
set_regs_spsr_ss(task_pt_regs(task));
}
+NOKPROBE_SYMBOL(user_rewind_single_step);
void user_fastforward_single_step(struct task_struct *task)
{
@@ -401,6 +415,7 @@ void kernel_enable_single_step(struct pt_regs *regs)
mdscr_write(mdscr_read() | DBG_MDSCR_SS);
enable_debug_monitors(DBG_ACTIVE_EL1);
}
+NOKPROBE_SYMBOL(kernel_enable_single_step);
void kernel_disable_single_step(void)
{
@@ -408,12 +423,14 @@ void kernel_disable_single_step(void)
mdscr_write(mdscr_read() & ~DBG_MDSCR_SS);
disable_debug_monitors(DBG_ACTIVE_EL1);
}
+NOKPROBE_SYMBOL(kernel_disable_single_step);
int kernel_active_single_step(void)
{
WARN_ON(!irqs_disabled());
return mdscr_read() & DBG_MDSCR_SS;
}
+NOKPROBE_SYMBOL(kernel_active_single_step);
/* ptrace API */
void user_enable_single_step(struct task_struct *task)
@@ -421,8 +438,10 @@ void user_enable_single_step(struct task_struct *task)
set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
set_regs_spsr_ss(task_pt_regs(task));
}
+NOKPROBE_SYMBOL(user_enable_single_step);
void user_disable_single_step(struct task_struct *task)
{
clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
}
+NOKPROBE_SYMBOL(user_disable_single_step);
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 78f52488f9ff..ba9bee389fd5 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -62,13 +62,61 @@ struct screen_info screen_info __section(.data);
int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
{
pteval_t prot_val = create_mapping_protection(md);
+ bool allow_block_mappings = (md->type != EFI_RUNTIME_SERVICES_CODE &&
+ md->type != EFI_RUNTIME_SERVICES_DATA);
+
+ if (!PAGE_ALIGNED(md->phys_addr) ||
+ !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) {
+ /*
+ * If the end address of this region is not aligned to page
+ * size, the mapping is rounded up, and may end up sharing a
+ * page frame with the next UEFI memory region. If we create
+ * a block entry now, we may need to split it again when mapping
+ * the next region, and support for that is going to be removed
+ * from the MMU routines. So avoid block mappings altogether in
+ * that case.
+ */
+ allow_block_mappings = false;
+ }
create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
md->num_pages << EFI_PAGE_SHIFT,
- __pgprot(prot_val | PTE_NG));
+ __pgprot(prot_val | PTE_NG), allow_block_mappings);
+ return 0;
+}
+
+static int __init set_permissions(pte_t *ptep, pgtable_t token,
+ unsigned long addr, void *data)
+{
+ efi_memory_desc_t *md = data;
+ pte_t pte = *ptep;
+
+ if (md->attribute & EFI_MEMORY_RO)
+ pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+ if (md->attribute & EFI_MEMORY_XP)
+ pte = set_pte_bit(pte, __pgprot(PTE_PXN));
+ set_pte(ptep, pte);
return 0;
}
+int __init efi_set_mapping_permissions(struct mm_struct *mm,
+ efi_memory_desc_t *md)
+{
+ BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE &&
+ md->type != EFI_RUNTIME_SERVICES_DATA);
+
+ /*
+ * Calling apply_to_page_range() is only safe on regions that are
+ * guaranteed to be mapped down to pages. Since we are only called
+ * for regions that have been mapped using efi_create_mapping() above
+ * (and this is checked by the generic Memory Attributes table parsing
+ * routines), there is no need to check that again here.
+ */
+ return apply_to_page_range(mm, md->virt_addr,
+ md->num_pages << EFI_PAGE_SHIFT,
+ set_permissions, md);
+}
+
static int __init arm64_dmi_init(void)
{
/*
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6c3b7345a6c4..96e4a2b64cc1 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -258,6 +258,7 @@ tsk .req x28 // current thread_info
/*
* Exception vectors.
*/
+ .pushsection ".entry.text", "ax"
.align 11
ENTRY(vectors)
@@ -466,7 +467,7 @@ el0_sync:
cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception
b.eq el0_fpsimd_exc
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
- b.eq el0_undef
+ b.eq el0_sys
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
b.eq el0_sp_pc
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
@@ -547,7 +548,7 @@ el0_ia:
enable_dbg_and_irq
ct_user_exit
mov x0, x26
- orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts
+ mov x1, x25
mov x2, sp
bl do_mem_abort
b ret_to_user
@@ -594,6 +595,16 @@ el0_undef:
mov x0, sp
bl do_undefinstr
b ret_to_user
+el0_sys:
+ /*
+ * System instructions, for trapped cache maintenance instructions
+ */
+ enable_dbg_and_irq
+ ct_user_exit
+ mov x0, x25
+ mov x1, sp
+ bl do_sysinstr
+ b ret_to_user
el0_dbg:
/*
* Debug exception handling
@@ -789,6 +800,8 @@ __ni_sys_trace:
bl do_ni_syscall
b __sys_trace_return
+ .popsection // .entry.text
+
/*
* Special system call wrappers.
*/
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index ce21aa88263f..26a6bf77d272 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -24,6 +24,7 @@
#include <linux/cpu_pm.h>
#include <linux/errno.h>
#include <linux/hw_breakpoint.h>
+#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/smp.h>
@@ -127,6 +128,7 @@ static u64 read_wb_reg(int reg, int n)
return val;
}
+NOKPROBE_SYMBOL(read_wb_reg);
static void write_wb_reg(int reg, int n, u64 val)
{
@@ -140,6 +142,7 @@ static void write_wb_reg(int reg, int n, u64 val)
}
isb();
}
+NOKPROBE_SYMBOL(write_wb_reg);
/*
* Convert a breakpoint privilege level to the corresponding exception
@@ -157,6 +160,7 @@ static enum dbg_active_el debug_exception_level(int privilege)
return -EINVAL;
}
}
+NOKPROBE_SYMBOL(debug_exception_level);
enum hw_breakpoint_ops {
HW_BREAKPOINT_INSTALL,
@@ -575,6 +579,7 @@ static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable)
write_wb_reg(reg, i, ctrl);
}
}
+NOKPROBE_SYMBOL(toggle_bp_registers);
/*
* Debug exception handlers.
@@ -654,6 +659,7 @@ unlock:
return 0;
}
+NOKPROBE_SYMBOL(breakpoint_handler);
static int watchpoint_handler(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
@@ -756,6 +762,7 @@ unlock:
return 0;
}
+NOKPROBE_SYMBOL(watchpoint_handler);
/*
* Handle single-step exception.
@@ -813,6 +820,7 @@ int reinstall_suspended_bps(struct pt_regs *regs)
return !handled_exception;
}
+NOKPROBE_SYMBOL(reinstall_suspended_bps);
/*
* Context-switcher for restoring suspended breakpoints.
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 8727f4490772..d3b5f75e652e 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -71,8 +71,16 @@ el1_sync:
msr vbar_el2, x1
b 9f
+2: cmp x0, #HVC_SOFT_RESTART
+ b.ne 3f
+ mov x0, x2
+ mov x2, x4
+ mov x4, x1
+ mov x1, x3
+ br x4 // no return
+
/* Someone called kvm_call_hyp() against the hyp-stub... */
-2: mov x0, #ARM_EXCEPTION_HYP_GONE
+3: mov x0, #ARM_EXCEPTION_HYP_GONE
9: eret
ENDPROC(el1_sync)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 368c08290dd8..63f9432d05e8 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -30,6 +30,7 @@
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
#include <asm/fixmap.h>
+#include <asm/opcodes.h>
#include <asm/insn.h>
#define AARCH64_INSN_SF_BIT BIT(31)
@@ -162,6 +163,32 @@ static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
aarch64_insn_is_nop(insn);
}
+bool __kprobes aarch64_insn_uses_literal(u32 insn)
+{
+ /* ldr/ldrsw (literal), prfm */
+
+ return aarch64_insn_is_ldr_lit(insn) ||
+ aarch64_insn_is_ldrsw_lit(insn) ||
+ aarch64_insn_is_adr_adrp(insn) ||
+ aarch64_insn_is_prfm_lit(insn);
+}
+
+bool __kprobes aarch64_insn_is_branch(u32 insn)
+{
+ /* b, bl, cb*, tb*, b.cond, br, blr */
+
+ return aarch64_insn_is_b(insn) ||
+ aarch64_insn_is_bl(insn) ||
+ aarch64_insn_is_cbz(insn) ||
+ aarch64_insn_is_cbnz(insn) ||
+ aarch64_insn_is_tbz(insn) ||
+ aarch64_insn_is_tbnz(insn) ||
+ aarch64_insn_is_ret(insn) ||
+ aarch64_insn_is_br(insn) ||
+ aarch64_insn_is_blr(insn) ||
+ aarch64_insn_is_bcond(insn);
+}
+
/*
* ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
* Section B2.6.5 "Concurrent modification and execution of instructions":
@@ -1175,6 +1202,14 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset)
BUG();
}
+/*
+ * Extract the Op/CR data from a msr/mrs instruction.
+ */
+u32 aarch64_insn_extract_system_reg(u32 insn)
+{
+ return (insn & 0x1FFFE0) >> 5;
+}
+
bool aarch32_insn_is_wide(u32 insn)
{
return insn >= 0xe800;
@@ -1200,3 +1235,101 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn)
{
return insn & CRM_MASK;
}
+
+static bool __kprobes __check_eq(unsigned long pstate)
+{
+ return (pstate & PSR_Z_BIT) != 0;
+}
+
+static bool __kprobes __check_ne(unsigned long pstate)
+{
+ return (pstate & PSR_Z_BIT) == 0;
+}
+
+static bool __kprobes __check_cs(unsigned long pstate)
+{
+ return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_cc(unsigned long pstate)
+{
+ return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_mi(unsigned long pstate)
+{
+ return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_pl(unsigned long pstate)
+{
+ return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_vs(unsigned long pstate)
+{
+ return (pstate & PSR_V_BIT) != 0;
+}
+
+static bool __kprobes __check_vc(unsigned long pstate)
+{
+ return (pstate & PSR_V_BIT) == 0;
+}
+
+static bool __kprobes __check_hi(unsigned long pstate)
+{
+ pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+ return (pstate & PSR_C_BIT) != 0;
+}
+
+static bool __kprobes __check_ls(unsigned long pstate)
+{
+ pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+ return (pstate & PSR_C_BIT) == 0;
+}
+
+static bool __kprobes __check_ge(unsigned long pstate)
+{
+ pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+ return (pstate & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_lt(unsigned long pstate)
+{
+ pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+ return (pstate & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_gt(unsigned long pstate)
+{
+ /*PSR_N_BIT ^= PSR_V_BIT */
+ unsigned long temp = pstate ^ (pstate << 3);
+
+ temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */
+ return (temp & PSR_N_BIT) == 0;
+}
+
+static bool __kprobes __check_le(unsigned long pstate)
+{
+ /*PSR_N_BIT ^= PSR_V_BIT */
+ unsigned long temp = pstate ^ (pstate << 3);
+
+ temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */
+ return (temp & PSR_N_BIT) != 0;
+}
+
+static bool __kprobes __check_al(unsigned long pstate)
+{
+ return true;
+}
+
+/*
+ * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that
+ * it behaves identically to 0b1110 ("al").
+ */
+pstate_check_t * const aarch32_opcode_cond_checks[16] = {
+ __check_eq, __check_ne, __check_cs, __check_cc,
+ __check_mi, __check_pl, __check_vs, __check_vc,
+ __check_hi, __check_ls, __check_ge, __check_lt,
+ __check_gt, __check_le, __check_al, __check_al
+};
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b5f063e5eff7..8c57f6496e56 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -22,6 +22,7 @@
#include <linux/irq.h>
#include <linux/kdebug.h>
#include <linux/kgdb.h>
+#include <linux/kprobes.h>
#include <asm/traps.h>
struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
@@ -230,6 +231,7 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return 0;
}
+NOKPROBE_SYMBOL(kgdb_brk_fn)
static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
{
@@ -238,12 +240,14 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
return 0;
}
+NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
{
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return 0;
}
+NOKPROBE_SYMBOL(kgdb_step_brk_fn);
static struct break_hook kgdb_brkpt_hook = {
.esr_mask = 0xffffffff,
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
new file mode 100644
index 000000000000..bc96c8a7fc79
--- /dev/null
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -0,0 +1,212 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kexec.h>
+#include <linux/smp.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/mmu_context.h>
+
+#include "cpu-reset.h"
+
+/* Global variables for the arm64_relocate_new_kernel routine. */
+extern const unsigned char arm64_relocate_new_kernel[];
+extern const unsigned long arm64_relocate_new_kernel_size;
+
+static unsigned long kimage_start;
+
+/**
+ * kexec_image_info - For debugging output.
+ */
+#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i)
+static void _kexec_image_info(const char *func, int line,
+ const struct kimage *kimage)
+{
+ unsigned long i;
+
+ pr_debug("%s:%d:\n", func, line);
+ pr_debug(" kexec kimage info:\n");
+ pr_debug(" type: %d\n", kimage->type);
+ pr_debug(" start: %lx\n", kimage->start);
+ pr_debug(" head: %lx\n", kimage->head);
+ pr_debug(" nr_segments: %lu\n", kimage->nr_segments);
+
+ for (i = 0; i < kimage->nr_segments; i++) {
+ pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
+ i,
+ kimage->segment[i].mem,
+ kimage->segment[i].mem + kimage->segment[i].memsz,
+ kimage->segment[i].memsz,
+ kimage->segment[i].memsz / PAGE_SIZE);
+ }
+}
+
+void machine_kexec_cleanup(struct kimage *kimage)
+{
+ /* Empty routine needed to avoid build errors. */
+}
+
+/**
+ * machine_kexec_prepare - Prepare for a kexec reboot.
+ *
+ * Called from the core kexec code when a kernel image is loaded.
+ * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus
+ * are stuck in the kernel. This avoids a panic once we hit machine_kexec().
+ */
+int machine_kexec_prepare(struct kimage *kimage)
+{
+ kimage_start = kimage->start;
+
+ kexec_image_info(kimage);
+
+ if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
+ pr_err("Can't kexec: CPUs are stuck in the kernel.\n");
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
+/**
+ * kexec_list_flush - Helper to flush the kimage list and source pages to PoC.
+ */
+static void kexec_list_flush(struct kimage *kimage)
+{
+ kimage_entry_t *entry;
+
+ for (entry = &kimage->head; ; entry++) {
+ unsigned int flag;
+ void *addr;
+
+ /* flush the list entries. */
+ __flush_dcache_area(entry, sizeof(kimage_entry_t));
+
+ flag = *entry & IND_FLAGS;
+ if (flag == IND_DONE)
+ break;
+
+ addr = phys_to_virt(*entry & PAGE_MASK);
+
+ switch (flag) {
+ case IND_INDIRECTION:
+ /* Set entry point just before the new list page. */
+ entry = (kimage_entry_t *)addr - 1;
+ break;
+ case IND_SOURCE:
+ /* flush the source pages. */
+ __flush_dcache_area(addr, PAGE_SIZE);
+ break;
+ case IND_DESTINATION:
+ break;
+ default:
+ BUG();
+ }
+ }
+}
+
+/**
+ * kexec_segment_flush - Helper to flush the kimage segments to PoC.
+ */
+static void kexec_segment_flush(const struct kimage *kimage)
+{
+ unsigned long i;
+
+ pr_debug("%s:\n", __func__);
+
+ for (i = 0; i < kimage->nr_segments; i++) {
+ pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n",
+ i,
+ kimage->segment[i].mem,
+ kimage->segment[i].mem + kimage->segment[i].memsz,
+ kimage->segment[i].memsz,
+ kimage->segment[i].memsz / PAGE_SIZE);
+
+ __flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
+ kimage->segment[i].memsz);
+ }
+}
+
+/**
+ * machine_kexec - Do the kexec reboot.
+ *
+ * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC.
+ */
+void machine_kexec(struct kimage *kimage)
+{
+ phys_addr_t reboot_code_buffer_phys;
+ void *reboot_code_buffer;
+
+ /*
+ * New cpus may have become stuck_in_kernel after we loaded the image.
+ */
+ BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1));
+
+ reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
+ reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
+
+ kexec_image_info(kimage);
+
+ pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__,
+ kimage->control_code_page);
+ pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__,
+ &reboot_code_buffer_phys);
+ pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__,
+ reboot_code_buffer);
+ pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__,
+ arm64_relocate_new_kernel);
+ pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n",
+ __func__, __LINE__, arm64_relocate_new_kernel_size,
+ arm64_relocate_new_kernel_size);
+
+ /*
+ * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use
+ * after the kernel is shut down.
+ */
+ memcpy(reboot_code_buffer, arm64_relocate_new_kernel,
+ arm64_relocate_new_kernel_size);
+
+ /* Flush the reboot_code_buffer in preparation for its execution. */
+ __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
+ flush_icache_range((uintptr_t)reboot_code_buffer,
+ arm64_relocate_new_kernel_size);
+
+ /* Flush the kimage list and its buffers. */
+ kexec_list_flush(kimage);
+
+ /* Flush the new image if already in place. */
+ if (kimage->head & IND_DONE)
+ kexec_segment_flush(kimage);
+
+ pr_info("Bye!\n");
+
+ /* Disable all DAIF exceptions. */
+ asm volatile ("msr daifset, #0xf" : : : "memory");
+
+ /*
+ * cpu_soft_restart will shutdown the MMU, disable data caches, then
+ * transfer control to the reboot_code_buffer which contains a copy of
+ * the arm64_relocate_new_kernel routine. arm64_relocate_new_kernel
+ * uses physical addressing to relocate the new image to its final
+ * position and transfers control to the image entry point when the
+ * relocation is complete.
+ */
+
+ cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head,
+ kimage_start, 0);
+
+ BUG(); /* Should never get here. */
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+ /* Empty routine needed to avoid build errors. */
+}
diff --git a/arch/arm64/kernel/probes/Makefile b/arch/arm64/kernel/probes/Makefile
new file mode 100644
index 000000000000..ce06312e3d34
--- /dev/null
+++ b/arch/arm64/kernel/probes/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o \
+ kprobes_trampoline.o \
+ simulate-insn.o
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
new file mode 100644
index 000000000000..37e47a9d617e
--- /dev/null
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -0,0 +1,174 @@
+/*
+ * arch/arm64/kernel/probes/decode-insn.c
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <asm/kprobes.h>
+#include <asm/insn.h>
+#include <asm/sections.h>
+
+#include "decode-insn.h"
+#include "simulate-insn.h"
+
+static bool __kprobes aarch64_insn_is_steppable(u32 insn)
+{
+ /*
+ * Branch instructions will write a new value into the PC which is
+ * likely to be relative to the XOL address and therefore invalid.
+ * Deliberate generation of an exception during stepping is also not
+ * currently safe. Lastly, MSR instructions can do any number of nasty
+ * things we can't handle during single-stepping.
+ */
+ if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) {
+ if (aarch64_insn_is_branch(insn) ||
+ aarch64_insn_is_msr_imm(insn) ||
+ aarch64_insn_is_msr_reg(insn) ||
+ aarch64_insn_is_exception(insn) ||
+ aarch64_insn_is_eret(insn))
+ return false;
+
+ /*
+ * The MRS instruction may not return a correct value when
+ * executing in the single-stepping environment. We do make one
+ * exception, for reading the DAIF bits.
+ */
+ if (aarch64_insn_is_mrs(insn))
+ return aarch64_insn_extract_system_reg(insn)
+ != AARCH64_INSN_SPCLREG_DAIF;
+
+ /*
+ * The HINT instruction is is problematic when single-stepping,
+ * except for the NOP case.
+ */
+ if (aarch64_insn_is_hint(insn))
+ return aarch64_insn_is_nop(insn);
+
+ return true;
+ }
+
+ /*
+ * Instructions which load PC relative literals are not going to work
+ * when executed from an XOL slot. Instructions doing an exclusive
+ * load/store are not going to complete successfully when single-step
+ * exception handling happens in the middle of the sequence.
+ */
+ if (aarch64_insn_uses_literal(insn) ||
+ aarch64_insn_is_exclusive(insn))
+ return false;
+
+ return true;
+}
+
+/* Return:
+ * INSN_REJECTED If instruction is one not allowed to kprobe,
+ * INSN_GOOD If instruction is supported and uses instruction slot,
+ * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ */
+static enum kprobe_insn __kprobes
+arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+{
+ /*
+ * Instructions reading or modifying the PC won't work from the XOL
+ * slot.
+ */
+ if (aarch64_insn_is_steppable(insn))
+ return INSN_GOOD;
+
+ if (aarch64_insn_is_bcond(insn)) {
+ asi->handler = simulate_b_cond;
+ } else if (aarch64_insn_is_cbz(insn) ||
+ aarch64_insn_is_cbnz(insn)) {
+ asi->handler = simulate_cbz_cbnz;
+ } else if (aarch64_insn_is_tbz(insn) ||
+ aarch64_insn_is_tbnz(insn)) {
+ asi->handler = simulate_tbz_tbnz;
+ } else if (aarch64_insn_is_adr_adrp(insn)) {
+ asi->handler = simulate_adr_adrp;
+ } else if (aarch64_insn_is_b(insn) ||
+ aarch64_insn_is_bl(insn)) {
+ asi->handler = simulate_b_bl;
+ } else if (aarch64_insn_is_br(insn) ||
+ aarch64_insn_is_blr(insn) ||
+ aarch64_insn_is_ret(insn)) {
+ asi->handler = simulate_br_blr_ret;
+ } else if (aarch64_insn_is_ldr_lit(insn)) {
+ asi->handler = simulate_ldr_literal;
+ } else if (aarch64_insn_is_ldrsw_lit(insn)) {
+ asi->handler = simulate_ldrsw_literal;
+ } else {
+ /*
+ * Instruction cannot be stepped out-of-line and we don't
+ * (yet) simulate it.
+ */
+ return INSN_REJECTED;
+ }
+
+ return INSN_GOOD_NO_SLOT;
+}
+
+static bool __kprobes
+is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
+{
+ while (scan_start > scan_end) {
+ /*
+ * atomic region starts from exclusive load and ends with
+ * exclusive store.
+ */
+ if (aarch64_insn_is_store_ex(le32_to_cpu(*scan_start)))
+ return false;
+ else if (aarch64_insn_is_load_ex(le32_to_cpu(*scan_start)))
+ return true;
+ scan_start--;
+ }
+
+ return false;
+}
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
+{
+ enum kprobe_insn decoded;
+ kprobe_opcode_t insn = le32_to_cpu(*addr);
+ kprobe_opcode_t *scan_start = addr - 1;
+ kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+ struct module *mod;
+#endif
+
+ if (addr >= (kprobe_opcode_t *)_text &&
+ scan_end < (kprobe_opcode_t *)_text)
+ scan_end = (kprobe_opcode_t *)_text;
+#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
+ else {
+ preempt_disable();
+ mod = __module_address((unsigned long)addr);
+ if (mod && within_module_init((unsigned long)addr, mod) &&
+ !within_module_init((unsigned long)scan_end, mod))
+ scan_end = (kprobe_opcode_t *)mod->init_layout.base;
+ else if (mod && within_module_core((unsigned long)addr, mod) &&
+ !within_module_core((unsigned long)scan_end, mod))
+ scan_end = (kprobe_opcode_t *)mod->core_layout.base;
+ preempt_enable();
+ }
+#endif
+ decoded = arm_probe_decode_insn(insn, asi);
+
+ if (decoded == INSN_REJECTED ||
+ is_probed_address_atomic(scan_start, scan_end))
+ return INSN_REJECTED;
+
+ return decoded;
+}
diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h
new file mode 100644
index 000000000000..d438289646a6
--- /dev/null
+++ b/arch/arm64/kernel/probes/decode-insn.h
@@ -0,0 +1,35 @@
+/*
+ * arch/arm64/kernel/probes/decode-insn.h
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_ARM64_H
+#define _ARM_KERNEL_KPROBES_ARM64_H
+
+/*
+ * ARM strongly recommends a limit of 128 bytes between LoadExcl and
+ * StoreExcl instructions in a single thread of execution. So keep the
+ * max atomic context size as 32.
+ */
+#define MAX_ATOMIC_CONTEXT_SIZE (128 / sizeof(kprobe_opcode_t))
+
+enum kprobe_insn {
+ INSN_REJECTED,
+ INSN_GOOD_NO_SLOT,
+ INSN_GOOD,
+};
+
+enum kprobe_insn __kprobes
+arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi);
+
+#endif /* _ARM_KERNEL_KPROBES_ARM64_H */
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
new file mode 100644
index 000000000000..bf9768588288
--- /dev/null
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -0,0 +1,686 @@
+/*
+ * arch/arm64/kernel/probes/kprobes.c
+ *
+ * Kprobes support for ARM64
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ */
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/stringify.h>
+#include <asm/traps.h>
+#include <asm/ptrace.h>
+#include <asm/cacheflush.h>
+#include <asm/debug-monitors.h>
+#include <asm/system_misc.h>
+#include <asm/insn.h>
+#include <asm/uaccess.h>
+#include <asm/irq.h>
+#include <asm-generic/sections.h>
+
+#include "decode-insn.h"
+
+DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
+DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
+
+static inline unsigned long min_stack_size(unsigned long addr)
+{
+ unsigned long size;
+
+ if (on_irq_stack(addr, raw_smp_processor_id()))
+ size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
+ else
+ size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
+
+ return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
+}
+
+static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+{
+ /* prepare insn slot */
+ p->ainsn.insn[0] = cpu_to_le32(p->opcode);
+
+ flush_icache_range((uintptr_t) (p->ainsn.insn),
+ (uintptr_t) (p->ainsn.insn) +
+ MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+
+ /*
+ * Needs restoring of return address after stepping xol.
+ */
+ p->ainsn.restore = (unsigned long) p->addr +
+ sizeof(kprobe_opcode_t);
+}
+
+static void __kprobes arch_prepare_simulate(struct kprobe *p)
+{
+ /* This instructions is not executed xol. No need to adjust the PC */
+ p->ainsn.restore = 0;
+}
+
+static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ if (p->ainsn.handler)
+ p->ainsn.handler((u32)p->opcode, (long)p->addr, regs);
+
+ /* single step simulated, now go for post processing */
+ post_kprobe_handler(kcb, regs);
+}
+
+int __kprobes arch_prepare_kprobe(struct kprobe *p)
+{
+ unsigned long probe_addr = (unsigned long)p->addr;
+ extern char __start_rodata[];
+ extern char __end_rodata[];
+
+ if (probe_addr & 0x3)
+ return -EINVAL;
+
+ /* copy instruction */
+ p->opcode = le32_to_cpu(*p->addr);
+
+ if (in_exception_text(probe_addr))
+ return -EINVAL;
+ if (probe_addr >= (unsigned long) __start_rodata &&
+ probe_addr <= (unsigned long) __end_rodata)
+ return -EINVAL;
+
+ /* decode instruction */
+ switch (arm_kprobe_decode_insn(p->addr, &p->ainsn)) {
+ case INSN_REJECTED: /* insn not supported */
+ return -EINVAL;
+
+ case INSN_GOOD_NO_SLOT: /* insn need simulation */
+ p->ainsn.insn = NULL;
+ break;
+
+ case INSN_GOOD: /* instruction uses slot */
+ p->ainsn.insn = get_insn_slot();
+ if (!p->ainsn.insn)
+ return -ENOMEM;
+ break;
+ };
+
+ /* prepare the instruction */
+ if (p->ainsn.insn)
+ arch_prepare_ss_slot(p);
+ else
+ arch_prepare_simulate(p);
+
+ return 0;
+}
+
+static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
+{
+ void *addrs[1];
+ u32 insns[1];
+
+ addrs[0] = (void *)addr;
+ insns[0] = (u32)opcode;
+
+ return aarch64_insn_patch_text(addrs, insns, 1);
+}
+
+/* arm kprobe: install breakpoint in text */
+void __kprobes arch_arm_kprobe(struct kprobe *p)
+{
+ patch_text(p->addr, BRK64_OPCODE_KPROBES);
+}
+
+/* disarm kprobe: remove breakpoint from text */
+void __kprobes arch_disarm_kprobe(struct kprobe *p)
+{
+ patch_text(p->addr, p->opcode);
+}
+
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+ if (p->ainsn.insn) {
+ free_insn_slot(p->ainsn.insn, 0);
+ p->ainsn.insn = NULL;
+ }
+}
+
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+ kcb->prev_kprobe.kp = kprobe_running();
+ kcb->prev_kprobe.status = kcb->kprobe_status;
+}
+
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+{
+ __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
+ kcb->kprobe_status = kcb->prev_kprobe.status;
+}
+
+static void __kprobes set_current_kprobe(struct kprobe *p)
+{
+ __this_cpu_write(current_kprobe, p);
+}
+
+/*
+ * The D-flag (Debug mask) is set (masked) upon debug exception entry.
+ * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
+ * probe i.e. when probe hit from kprobe handler context upon
+ * executing the pre/post handlers. In this case we return with
+ * D-flag clear so that single-stepping can be carried-out.
+ *
+ * Leave D-flag set in all other cases.
+ */
+static void __kprobes
+spsr_set_debug_flag(struct pt_regs *regs, int mask)
+{
+ unsigned long spsr = regs->pstate;
+
+ if (mask)
+ spsr |= PSR_D_BIT;
+ else
+ spsr &= ~PSR_D_BIT;
+
+ regs->pstate = spsr;
+}
+
+/*
+ * Interrupts need to be disabled before single-step mode is set, and not
+ * reenabled until after single-step mode ends.
+ * Without disabling interrupt on local CPU, there is a chance of
+ * interrupt occurrence in the period of exception return and start of
+ * out-of-line single-step, that result in wrongly single stepping
+ * into the interrupt handler.
+ */
+static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
+ struct pt_regs *regs)
+{
+ kcb->saved_irqflag = regs->pstate;
+ regs->pstate |= PSR_I_BIT;
+}
+
+static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
+ struct pt_regs *regs)
+{
+ if (kcb->saved_irqflag & PSR_I_BIT)
+ regs->pstate |= PSR_I_BIT;
+ else
+ regs->pstate &= ~PSR_I_BIT;
+}
+
+static void __kprobes
+set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+ kcb->ss_ctx.ss_pending = true;
+ kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t);
+}
+
+static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb)
+{
+ kcb->ss_ctx.ss_pending = false;
+ kcb->ss_ctx.match_addr = 0;
+}
+
+static void __kprobes setup_singlestep(struct kprobe *p,
+ struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb, int reenter)
+{
+ unsigned long slot;
+
+ if (reenter) {
+ save_previous_kprobe(kcb);
+ set_current_kprobe(p);
+ kcb->kprobe_status = KPROBE_REENTER;
+ } else {
+ kcb->kprobe_status = KPROBE_HIT_SS;
+ }
+
+
+ if (p->ainsn.insn) {
+ /* prepare for single stepping */
+ slot = (unsigned long)p->ainsn.insn;
+
+ set_ss_context(kcb, slot); /* mark pending ss */
+
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ spsr_set_debug_flag(regs, 0);
+ else
+ WARN_ON(regs->pstate & PSR_D_BIT);
+
+ /* IRQs and single stepping do not mix well. */
+ kprobes_save_local_irqflag(kcb, regs);
+ kernel_enable_single_step(regs);
+ instruction_pointer_set(regs, slot);
+ } else {
+ /* insn simulation */
+ arch_simulate_insn(p, regs);
+ }
+}
+
+static int __kprobes reenter_kprobe(struct kprobe *p,
+ struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ switch (kcb->kprobe_status) {
+ case KPROBE_HIT_SSDONE:
+ case KPROBE_HIT_ACTIVE:
+ kprobes_inc_nmissed_count(p);
+ setup_singlestep(p, regs, kcb, 1);
+ break;
+ case KPROBE_HIT_SS:
+ case KPROBE_REENTER:
+ pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+ dump_kprobe(p);
+ BUG();
+ break;
+ default:
+ WARN_ON(1);
+ return 0;
+ }
+
+ return 1;
+}
+
+static void __kprobes
+post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
+{
+ struct kprobe *cur = kprobe_running();
+
+ if (!cur)
+ return;
+
+ /* return addr restore if non-branching insn */
+ if (cur->ainsn.restore != 0)
+ instruction_pointer_set(regs, cur->ainsn.restore);
+
+ /* restore back original saved kprobe variables and continue */
+ if (kcb->kprobe_status == KPROBE_REENTER) {
+ restore_previous_kprobe(kcb);
+ return;
+ }
+ /* call post handler */
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ if (cur->post_handler) {
+ /* post_handler can hit breakpoint and single step
+ * again, so we enable D-flag for recursive exception.
+ */
+ cur->post_handler(cur, regs, 0);
+ }
+
+ reset_current_kprobe();
+}
+
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
+{
+ struct kprobe *cur = kprobe_running();
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ switch (kcb->kprobe_status) {
+ case KPROBE_HIT_SS:
+ case KPROBE_REENTER:
+ /*
+ * We are here because the instruction being single
+ * stepped caused a page fault. We reset the current
+ * kprobe and the ip points back to the probe address
+ * and allow the page fault handler to continue as a
+ * normal page fault.
+ */
+ instruction_pointer_set(regs, (unsigned long) cur->addr);
+ if (!instruction_pointer(regs))
+ BUG();
+
+ kernel_disable_single_step();
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ spsr_set_debug_flag(regs, 1);
+
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ restore_previous_kprobe(kcb);
+ else
+ reset_current_kprobe();
+
+ break;
+ case KPROBE_HIT_ACTIVE:
+ case KPROBE_HIT_SSDONE:
+ /*
+ * We increment the nmissed count for accounting,
+ * we can also use npre/npostfault count for accounting
+ * these specific fault cases.
+ */
+ kprobes_inc_nmissed_count(cur);
+
+ /*
+ * We come here because instructions in the pre/post
+ * handler caused the page_fault, this could happen
+ * if handler tries to access user space by
+ * copy_from_user(), get_user() etc. Let the
+ * user-specified handler try to fix it first.
+ */
+ if (cur->fault_handler && cur->fault_handler(cur, regs, fsr))
+ return 1;
+
+ /*
+ * In case the user-specified fault handler returned
+ * zero, try to fix up.
+ */
+ if (fixup_exception(regs))
+ return 1;
+ }
+ return 0;
+}
+
+int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ return NOTIFY_DONE;
+}
+
+static void __kprobes kprobe_handler(struct pt_regs *regs)
+{
+ struct kprobe *p, *cur_kprobe;
+ struct kprobe_ctlblk *kcb;
+ unsigned long addr = instruction_pointer(regs);
+
+ kcb = get_kprobe_ctlblk();
+ cur_kprobe = kprobe_running();
+
+ p = get_kprobe((kprobe_opcode_t *) addr);
+
+ if (p) {
+ if (cur_kprobe) {
+ if (reenter_kprobe(p, regs, kcb))
+ return;
+ } else {
+ /* Probe hit */
+ set_current_kprobe(p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+ /*
+ * If we have no pre-handler or it returned 0, we
+ * continue with normal processing. If we have a
+ * pre-handler and it returned non-zero, it prepped
+ * for calling the break_handler below on re-entry,
+ * so get out doing nothing more here.
+ *
+ * pre_handler can hit a breakpoint and can step thru
+ * before return, keep PSTATE D-flag enabled until
+ * pre_handler return back.
+ */
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
+ setup_singlestep(p, regs, kcb, 0);
+ return;
+ }
+ }
+ } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
+ BRK64_OPCODE_KPROBES) && cur_kprobe) {
+ /* We probably hit a jprobe. Call its break handler. */
+ if (cur_kprobe->break_handler &&
+ cur_kprobe->break_handler(cur_kprobe, regs)) {
+ setup_singlestep(cur_kprobe, regs, kcb, 0);
+ return;
+ }
+ }
+ /*
+ * The breakpoint instruction was removed right
+ * after we hit it. Another cpu has removed
+ * either a probepoint or a debugger breakpoint
+ * at this address. In either case, no further
+ * handling of this interrupt is appropriate.
+ * Return back to original instruction, and continue.
+ */
+}
+
+static int __kprobes
+kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
+{
+ if ((kcb->ss_ctx.ss_pending)
+ && (kcb->ss_ctx.match_addr == addr)) {
+ clear_ss_context(kcb); /* clear pending ss */
+ return DBG_HOOK_HANDLED;
+ }
+ /* not ours, kprobes should ignore it */
+ return DBG_HOOK_ERROR;
+}
+
+int __kprobes
+kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ int retval;
+
+ /* return error if this is not our step */
+ retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
+
+ if (retval == DBG_HOOK_HANDLED) {
+ kprobes_restore_local_irqflag(kcb, regs);
+ kernel_disable_single_step();
+
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ spsr_set_debug_flag(regs, 1);
+
+ post_kprobe_handler(kcb, regs);
+ }
+
+ return retval;
+}
+
+int __kprobes
+kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
+{
+ kprobe_handler(regs);
+ return DBG_HOOK_HANDLED;
+}
+
+int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct jprobe *jp = container_of(p, struct jprobe, kp);
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ long stack_ptr = kernel_stack_pointer(regs);
+
+ kcb->jprobe_saved_regs = *regs;
+ /*
+ * As Linus pointed out, gcc assumes that the callee
+ * owns the argument space and could overwrite it, e.g.
+ * tailcall optimization. So, to be absolutely safe
+ * we also save and restore enough stack bytes to cover
+ * the argument area.
+ */
+ kasan_disable_current();
+ memcpy(kcb->jprobes_stack, (void *)stack_ptr,
+ min_stack_size(stack_ptr));
+ kasan_enable_current();
+
+ instruction_pointer_set(regs, (unsigned long) jp->entry);
+ preempt_disable();
+ pause_graph_tracing();
+ return 1;
+}
+
+void __kprobes jprobe_return(void)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+
+ /*
+ * Jprobe handler return by entering break exception,
+ * encoded same as kprobe, but with following conditions
+ * -a special PC to identify it from the other kprobes.
+ * -restore stack addr to original saved pt_regs
+ */
+ asm volatile(" mov sp, %0 \n"
+ "jprobe_return_break: brk %1 \n"
+ :
+ : "r" (kcb->jprobe_saved_regs.sp),
+ "I" (BRK64_ESR_KPROBES)
+ : "memory");
+
+ unreachable();
+}
+
+int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+ long stack_addr = kcb->jprobe_saved_regs.sp;
+ long orig_sp = kernel_stack_pointer(regs);
+ struct jprobe *jp = container_of(p, struct jprobe, kp);
+ extern const char jprobe_return_break[];
+
+ if (instruction_pointer(regs) != (u64) jprobe_return_break)
+ return 0;
+
+ if (orig_sp != stack_addr) {
+ struct pt_regs *saved_regs =
+ (struct pt_regs *)kcb->jprobe_saved_regs.sp;
+ pr_err("current sp %lx does not match saved sp %lx\n",
+ orig_sp, stack_addr);
+ pr_err("Saved registers for jprobe %p\n", jp);
+ show_regs(saved_regs);
+ pr_err("Current registers\n");
+ show_regs(regs);
+ BUG();
+ }
+ unpause_graph_tracing();
+ *regs = kcb->jprobe_saved_regs;
+ kasan_disable_current();
+ memcpy((void *)stack_addr, kcb->jprobes_stack,
+ min_stack_size(stack_addr));
+ kasan_enable_current();
+ preempt_enable_no_resched();
+ return 1;
+}
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+ extern char __idmap_text_start[], __idmap_text_end[];
+ extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+
+ if ((addr >= (unsigned long)__kprobes_text_start &&
+ addr < (unsigned long)__kprobes_text_end) ||
+ (addr >= (unsigned long)__entry_text_start &&
+ addr < (unsigned long)__entry_text_end) ||
+ (addr >= (unsigned long)__idmap_text_start &&
+ addr < (unsigned long)__idmap_text_end) ||
+ !!search_exception_tables(addr))
+ return true;
+
+ if (!is_kernel_in_hyp_mode()) {
+ if ((addr >= (unsigned long)__hyp_text_start &&
+ addr < (unsigned long)__hyp_text_end) ||
+ (addr >= (unsigned long)__hyp_idmap_text_start &&
+ addr < (unsigned long)__hyp_idmap_text_end))
+ return true;
+ }
+
+ return false;
+}
+
+void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
+{
+ struct kretprobe_instance *ri = NULL;
+ struct hlist_head *head, empty_rp;
+ struct hlist_node *tmp;
+ unsigned long flags, orig_ret_address = 0;
+ unsigned long trampoline_address =
+ (unsigned long)&kretprobe_trampoline;
+ kprobe_opcode_t *correct_ret_addr = NULL;
+
+ INIT_HLIST_HEAD(&empty_rp);
+ kretprobe_hash_lock(current, &head, &flags);
+
+ /*
+ * It is possible to have multiple instances associated with a given
+ * task either because multiple functions in the call path have
+ * return probes installed on them, and/or more than one
+ * return probe was registered for a target function.
+ *
+ * We can handle this because:
+ * - instances are always pushed into the head of the list
+ * - when multiple return probes are registered for the same
+ * function, the (chronologically) first instance's ret_addr
+ * will be the real return address, and all the rest will
+ * point to kretprobe_trampoline.
+ */
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ if (ri->task != current)
+ /* another task is sharing our hash bucket */
+ continue;
+
+ orig_ret_address = (unsigned long)ri->ret_addr;
+
+ if (orig_ret_address != trampoline_address)
+ /*
+ * This is the real return address. Any other
+ * instances associated with this task are for
+ * other calls deeper on the call stack
+ */
+ break;
+ }
+
+ kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+ correct_ret_addr = ri->ret_addr;
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ if (ri->task != current)
+ /* another task is sharing our hash bucket */
+ continue;
+
+ orig_ret_address = (unsigned long)ri->ret_addr;
+ if (ri->rp && ri->rp->handler) {
+ __this_cpu_write(current_kprobe, &ri->rp->kp);
+ get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+ ri->ret_addr = correct_ret_addr;
+ ri->rp->handler(ri, regs);
+ __this_cpu_write(current_kprobe, NULL);
+ }
+
+ recycle_rp_inst(ri, &empty_rp);
+
+ if (orig_ret_address != trampoline_address)
+ /*
+ * This is the real return address. Any other
+ * instances associated with this task are for
+ * other calls deeper on the call stack
+ */
+ break;
+ }
+
+ kretprobe_hash_unlock(current, &flags);
+
+ hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+ hlist_del(&ri->hlist);
+ kfree(ri);
+ }
+ return (void *)orig_ret_address;
+}
+
+void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
+ struct pt_regs *regs)
+{
+ ri->ret_addr = (kprobe_opcode_t *)regs->regs[30];
+
+ /* replace return addr (x30) with trampoline */
+ regs->regs[30] = (long)&kretprobe_trampoline;
+}
+
+int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+{
+ return 0;
+}
+
+int __init arch_init_kprobes(void)
+{
+ return 0;
+}
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
new file mode 100644
index 000000000000..5d6e7f14638c
--- /dev/null
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -0,0 +1,81 @@
+/*
+ * trampoline entry and return code for kretprobes.
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+ .text
+
+ .macro save_all_base_regs
+ stp x0, x1, [sp, #S_X0]
+ stp x2, x3, [sp, #S_X2]
+ stp x4, x5, [sp, #S_X4]
+ stp x6, x7, [sp, #S_X6]
+ stp x8, x9, [sp, #S_X8]
+ stp x10, x11, [sp, #S_X10]
+ stp x12, x13, [sp, #S_X12]
+ stp x14, x15, [sp, #S_X14]
+ stp x16, x17, [sp, #S_X16]
+ stp x18, x19, [sp, #S_X18]
+ stp x20, x21, [sp, #S_X20]
+ stp x22, x23, [sp, #S_X22]
+ stp x24, x25, [sp, #S_X24]
+ stp x26, x27, [sp, #S_X26]
+ stp x28, x29, [sp, #S_X28]
+ add x0, sp, #S_FRAME_SIZE
+ stp lr, x0, [sp, #S_LR]
+ /*
+ * Construct a useful saved PSTATE
+ */
+ mrs x0, nzcv
+ mrs x1, daif
+ orr x0, x0, x1
+ mrs x1, CurrentEL
+ orr x0, x0, x1
+ mrs x1, SPSel
+ orr x0, x0, x1
+ stp xzr, x0, [sp, #S_PC]
+ .endm
+
+ .macro restore_all_base_regs
+ ldr x0, [sp, #S_PSTATE]
+ and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT)
+ msr nzcv, x0
+ ldp x0, x1, [sp, #S_X0]
+ ldp x2, x3, [sp, #S_X2]
+ ldp x4, x5, [sp, #S_X4]
+ ldp x6, x7, [sp, #S_X6]
+ ldp x8, x9, [sp, #S_X8]
+ ldp x10, x11, [sp, #S_X10]
+ ldp x12, x13, [sp, #S_X12]
+ ldp x14, x15, [sp, #S_X14]
+ ldp x16, x17, [sp, #S_X16]
+ ldp x18, x19, [sp, #S_X18]
+ ldp x20, x21, [sp, #S_X20]
+ ldp x22, x23, [sp, #S_X22]
+ ldp x24, x25, [sp, #S_X24]
+ ldp x26, x27, [sp, #S_X26]
+ ldp x28, x29, [sp, #S_X28]
+ .endm
+
+ENTRY(kretprobe_trampoline)
+ sub sp, sp, #S_FRAME_SIZE
+
+ save_all_base_regs
+
+ mov x0, sp
+ bl trampoline_probe_handler
+ /*
+ * Replace trampoline address in lr with actual orig_ret_addr return
+ * address.
+ */
+ mov lr, x0
+
+ restore_all_base_regs
+
+ add sp, sp, #S_FRAME_SIZE
+ ret
+
+ENDPROC(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
new file mode 100644
index 000000000000..8977ce9d009d
--- /dev/null
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -0,0 +1,217 @@
+/*
+ * arch/arm64/kernel/probes/simulate-insn.c
+ *
+ * Copyright (C) 2013 Linaro Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+
+#include "simulate-insn.h"
+
+#define sign_extend(x, signbit) \
+ ((x) | (0 - ((x) & (1 << (signbit)))))
+
+#define bbl_displacement(insn) \
+ sign_extend(((insn) & 0x3ffffff) << 2, 27)
+
+#define bcond_displacement(insn) \
+ sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+#define cbz_displacement(insn) \
+ sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+#define tbz_displacement(insn) \
+ sign_extend(((insn >> 5) & 0x3fff) << 2, 15)
+
+#define ldr_displacement(insn) \
+ sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+
+static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val)
+{
+ if (reg < 31)
+ regs->regs[reg] = val;
+}
+
+static inline void set_w_reg(struct pt_regs *regs, int reg, u64 val)
+{
+ if (reg < 31)
+ regs->regs[reg] = lower_32_bits(val);
+}
+
+static inline u64 get_x_reg(struct pt_regs *regs, int reg)
+{
+ if (reg < 31)
+ return regs->regs[reg];
+ else
+ return 0;
+}
+
+static inline u32 get_w_reg(struct pt_regs *regs, int reg)
+{
+ if (reg < 31)
+ return lower_32_bits(regs->regs[reg]);
+ else
+ return 0;
+}
+
+static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs)
+{
+ int xn = opcode & 0x1f;
+
+ return (opcode & (1 << 31)) ?
+ (get_x_reg(regs, xn) == 0) : (get_w_reg(regs, xn) == 0);
+}
+
+static bool __kprobes check_cbnz(u32 opcode, struct pt_regs *regs)
+{
+ int xn = opcode & 0x1f;
+
+ return (opcode & (1 << 31)) ?
+ (get_x_reg(regs, xn) != 0) : (get_w_reg(regs, xn) != 0);
+}
+
+static bool __kprobes check_tbz(u32 opcode, struct pt_regs *regs)
+{
+ int xn = opcode & 0x1f;
+ int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f);
+
+ return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) == 0;
+}
+
+static bool __kprobes check_tbnz(u32 opcode, struct pt_regs *regs)
+{
+ int xn = opcode & 0x1f;
+ int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f);
+
+ return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) != 0;
+}
+
+/*
+ * instruction simulation functions
+ */
+void __kprobes
+simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs)
+{
+ long imm, xn, val;
+
+ xn = opcode & 0x1f;
+ imm = ((opcode >> 3) & 0x1ffffc) | ((opcode >> 29) & 0x3);
+ imm = sign_extend(imm, 20);
+ if (opcode & 0x80000000)
+ val = (imm<<12) + (addr & 0xfffffffffffff000);
+ else
+ val = imm + addr;
+
+ set_x_reg(regs, xn, val);
+
+ instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
+
+void __kprobes
+simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs)
+{
+ int disp = bbl_displacement(opcode);
+
+ /* Link register is x30 */
+ if (opcode & (1 << 31))
+ set_x_reg(regs, 30, addr + 4);
+
+ instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs)
+{
+ int disp = 4;
+
+ if (aarch32_opcode_cond_checks[opcode & 0xf](regs->pstate & 0xffffffff))
+ disp = bcond_displacement(opcode);
+
+ instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs)
+{
+ int xn = (opcode >> 5) & 0x1f;
+
+ /* update pc first in case we're doing a "blr lr" */
+ instruction_pointer_set(regs, get_x_reg(regs, xn));
+
+ /* Link register is x30 */
+ if (((opcode >> 21) & 0x3) == 1)
+ set_x_reg(regs, 30, addr + 4);
+}
+
+void __kprobes
+simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs)
+{
+ int disp = 4;
+
+ if (opcode & (1 << 24)) {
+ if (check_cbnz(opcode, regs))
+ disp = cbz_displacement(opcode);
+ } else {
+ if (check_cbz(opcode, regs))
+ disp = cbz_displacement(opcode);
+ }
+ instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs)
+{
+ int disp = 4;
+
+ if (opcode & (1 << 24)) {
+ if (check_tbnz(opcode, regs))
+ disp = tbz_displacement(opcode);
+ } else {
+ if (check_tbz(opcode, regs))
+ disp = tbz_displacement(opcode);
+ }
+ instruction_pointer_set(regs, addr + disp);
+}
+
+void __kprobes
+simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
+{
+ u64 *load_addr;
+ int xn = opcode & 0x1f;
+ int disp;
+
+ disp = ldr_displacement(opcode);
+ load_addr = (u64 *) (addr + disp);
+
+ if (opcode & (1 << 30)) /* x0-x30 */
+ set_x_reg(regs, xn, *load_addr);
+ else /* w0-w30 */
+ set_w_reg(regs, xn, *load_addr);
+
+ instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
+
+void __kprobes
+simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs)
+{
+ s32 *load_addr;
+ int xn = opcode & 0x1f;
+ int disp;
+
+ disp = ldr_displacement(opcode);
+ load_addr = (s32 *) (addr + disp);
+
+ set_x_reg(regs, xn, *load_addr);
+
+ instruction_pointer_set(regs, instruction_pointer(regs) + 4);
+}
diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h
new file mode 100644
index 000000000000..050bde683c2d
--- /dev/null
+++ b/arch/arm64/kernel/probes/simulate-insn.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm64/kernel/probes/simulate-insn.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ARM_KERNEL_KPROBES_SIMULATE_INSN_H
+#define _ARM_KERNEL_KPROBES_SIMULATE_INSN_H
+
+void simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs);
+
+#endif /* _ARM_KERNEL_KPROBES_SIMULATE_INSN_H */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 3f6cd5c5234f..030c1d5aa46d 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -48,6 +48,107 @@
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
+struct pt_regs_offset {
+ const char *name;
+ int offset;
+};
+
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+#define GPR_OFFSET_NAME(r) \
+ {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])}
+
+static const struct pt_regs_offset regoffset_table[] = {
+ GPR_OFFSET_NAME(0),
+ GPR_OFFSET_NAME(1),
+ GPR_OFFSET_NAME(2),
+ GPR_OFFSET_NAME(3),
+ GPR_OFFSET_NAME(4),
+ GPR_OFFSET_NAME(5),
+ GPR_OFFSET_NAME(6),
+ GPR_OFFSET_NAME(7),
+ GPR_OFFSET_NAME(8),
+ GPR_OFFSET_NAME(9),
+ GPR_OFFSET_NAME(10),
+ GPR_OFFSET_NAME(11),
+ GPR_OFFSET_NAME(12),
+ GPR_OFFSET_NAME(13),
+ GPR_OFFSET_NAME(14),
+ GPR_OFFSET_NAME(15),
+ GPR_OFFSET_NAME(16),
+ GPR_OFFSET_NAME(17),
+ GPR_OFFSET_NAME(18),
+ GPR_OFFSET_NAME(19),
+ GPR_OFFSET_NAME(20),
+ GPR_OFFSET_NAME(21),
+ GPR_OFFSET_NAME(22),
+ GPR_OFFSET_NAME(23),
+ GPR_OFFSET_NAME(24),
+ GPR_OFFSET_NAME(25),
+ GPR_OFFSET_NAME(26),
+ GPR_OFFSET_NAME(27),
+ GPR_OFFSET_NAME(28),
+ GPR_OFFSET_NAME(29),
+ GPR_OFFSET_NAME(30),
+ {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])},
+ REG_OFFSET_NAME(sp),
+ REG_OFFSET_NAME(pc),
+ REG_OFFSET_NAME(pstate),
+ REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name: the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_offset *roff;
+
+ for (roff = regoffset_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->offset;
+ return -EINVAL;
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @addr: address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
+{
+ return ((addr & ~(THREAD_SIZE - 1)) ==
+ (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
+ on_irq_stack(addr, raw_smp_processor_id());
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @n: stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+ addr += n;
+ if (regs_within_kernel_stack(regs, (unsigned long)addr))
+ return *addr;
+ else
+ return 0;
+}
+
/*
* TODO: does not yet catch signals sent when the child dies.
* in exit.c or in signal.c.
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
new file mode 100644
index 000000000000..51b73cdde287
--- /dev/null
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -0,0 +1,130 @@
+/*
+ * kexec for arm64
+ *
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kexec.h>
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/kexec.h>
+#include <asm/page.h>
+#include <asm/sysreg.h>
+
+/*
+ * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it.
+ *
+ * The memory that the old kernel occupies may be overwritten when coping the
+ * new image to its final location. To assure that the
+ * arm64_relocate_new_kernel routine which does that copy is not overwritten,
+ * all code and data needed by arm64_relocate_new_kernel must be between the
+ * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end. The
+ * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec
+ * control_code_page, a special page which has been set up to be preserved
+ * during the copy operation.
+ */
+ENTRY(arm64_relocate_new_kernel)
+
+ /* Setup the list loop variables. */
+ mov x17, x1 /* x17 = kimage_start */
+ mov x16, x0 /* x16 = kimage_head */
+ dcache_line_size x15, x0 /* x15 = dcache line size */
+ mov x14, xzr /* x14 = entry ptr */
+ mov x13, xzr /* x13 = copy dest */
+
+ /* Clear the sctlr_el2 flags. */
+ mrs x0, CurrentEL
+ cmp x0, #CurrentEL_EL2
+ b.ne 1f
+ mrs x0, sctlr_el2
+ ldr x1, =SCTLR_ELx_FLAGS
+ bic x0, x0, x1
+ msr sctlr_el2, x0
+ isb
+1:
+
+ /* Check if the new image needs relocation. */
+ tbnz x16, IND_DONE_BIT, .Ldone
+
+.Lloop:
+ and x12, x16, PAGE_MASK /* x12 = addr */
+
+ /* Test the entry flags. */
+.Ltest_source:
+ tbz x16, IND_SOURCE_BIT, .Ltest_indirection
+
+ /* Invalidate dest page to PoC. */
+ mov x0, x13
+ add x20, x0, #PAGE_SIZE
+ sub x1, x15, #1
+ bic x0, x0, x1
+2: dc ivac, x0
+ add x0, x0, x15
+ cmp x0, x20
+ b.lo 2b
+ dsb sy
+
+ mov x20, x13
+ mov x21, x12
+ copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7
+
+ /* dest += PAGE_SIZE */
+ add x13, x13, PAGE_SIZE
+ b .Lnext
+
+.Ltest_indirection:
+ tbz x16, IND_INDIRECTION_BIT, .Ltest_destination
+
+ /* ptr = addr */
+ mov x14, x12
+ b .Lnext
+
+.Ltest_destination:
+ tbz x16, IND_DESTINATION_BIT, .Lnext
+
+ /* dest = addr */
+ mov x13, x12
+
+.Lnext:
+ /* entry = *ptr++ */
+ ldr x16, [x14], #8
+
+ /* while (!(entry & DONE)) */
+ tbz x16, IND_DONE_BIT, .Lloop
+
+.Ldone:
+ /* wait for writes from copy_page to finish */
+ dsb nsh
+ ic iallu
+ dsb nsh
+ isb
+
+ /* Start new image. */
+ mov x0, xzr
+ mov x1, xzr
+ mov x2, xzr
+ mov x3, xzr
+ br x17
+
+ENDPROC(arm64_relocate_new_kernel)
+
+.ltorg
+
+.align 3 /* To keep the 64-bit values below naturally aligned. */
+
+.Lcopy_end:
+.org KEXEC_CONTROL_PAGE_SIZE
+
+/*
+ * arm64_relocate_new_kernel_size - Number of bytes to copy to the
+ * control_code_page.
+ */
+.globl arm64_relocate_new_kernel_size
+arm64_relocate_new_kernel_size:
+ .quad .Lcopy_end - arm64_relocate_new_kernel
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 3279defabaa2..2981f1bdd073 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -202,7 +202,7 @@ static void __init request_standard_resources(void)
struct resource *res;
kernel_code.start = virt_to_phys(_text);
- kernel_code.end = virt_to_phys(_etext - 1);
+ kernel_code.end = virt_to_phys(__init_begin - 1);
kernel_data.start = virt_to_phys(_sdata);
kernel_data.end = virt_to_phys(_end - 1);
@@ -257,14 +257,17 @@ void __init setup_arch(char **cmdline_p)
*/
cpu_uninstall_idmap();
+ xen_early_init();
efi_init();
arm64_memblock_init();
+ paging_init();
+
+ acpi_table_upgrade();
+
/* Parse the ACPI tables for possible boot-time configuration */
acpi_boot_table_init();
- paging_init();
-
if (acpi_disabled)
unflatten_device_tree();
@@ -281,8 +284,6 @@ void __init setup_arch(char **cmdline_p)
else
psci_acpi_init();
- xen_early_init();
-
cpu_read_bootcpu_ops();
smp_init_cpus();
smp_build_mpidr_hash();
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 62ff3c0622e2..76a6d9263908 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -267,7 +267,6 @@ asmlinkage void secondary_start_kernel(void)
set_cpu_online(cpu, true);
complete(&cpu_running);
- local_dbg_enable();
local_irq_enable();
local_async_enable();
@@ -437,9 +436,9 @@ 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()));
cpuinfo_store_boot_cpu();
save_boot_cpu_run_el();
- set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -560,6 +559,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
*/
acpi_set_mailbox_entry(cpu_count, processor);
+ early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
+
cpu_count++;
}
@@ -694,6 +695,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
smp_store_cpu_info(smp_processor_id());
/*
+ * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
+ * secondary CPUs present.
+ */
+ if (max_cpus == 0)
+ return;
+
+ /*
* Initialise the present map (which describes the set of CPUs
* actually populated at the present time) and release the
* secondaries from the bootloader.
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 2a43012616b7..e04f83873af7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -41,6 +41,7 @@
#include <asm/stacktrace.h>
#include <asm/exception.h>
#include <asm/system_misc.h>
+#include <asm/sysreg.h>
static const char *handler[]= {
"Synchronous Abort",
@@ -52,15 +53,14 @@ static const char *handler[]= {
int show_unhandled_signals = 1;
/*
- * Dump out the contents of some memory nicely...
+ * Dump out the contents of some kernel memory nicely...
*/
static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
- unsigned long top, bool compat)
+ unsigned long top)
{
unsigned long first;
mm_segment_t fs;
int i;
- unsigned int width = compat ? 4 : 8;
/*
* We need to switch to kernel mode so that we can use __get_user
@@ -78,22 +78,15 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
memset(str, ' ', sizeof(str));
str[sizeof(str) - 1] = '\0';
- for (p = first, i = 0; i < (32 / width)
- && p < top; i++, p += width) {
+ for (p = first, i = 0; i < (32 / 8)
+ && p < top; i++, p += 8) {
if (p >= bottom && p < top) {
unsigned long val;
- if (width == 8) {
- if (__get_user(val, (unsigned long *)p) == 0)
- sprintf(str + i * 17, " %016lx", val);
- else
- sprintf(str + i * 17, " ????????????????");
- } else {
- if (__get_user(val, (unsigned int *)p) == 0)
- sprintf(str + i * 9, " %08lx", val);
- else
- sprintf(str + i * 9, " ????????");
- }
+ if (__get_user(val, (unsigned long *)p) == 0)
+ sprintf(str + i * 17, " %016lx", val);
+ else
+ sprintf(str + i * 17, " ????????????????");
}
}
printk("%s%04lx:%s\n", lvl, first & 0xffff, str);
@@ -216,7 +209,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
dump_mem("", "Exception stack", stack,
- stack + sizeof(struct pt_regs), false);
+ stack + sizeof(struct pt_regs));
}
}
}
@@ -254,10 +247,9 @@ static int __die(const char *str, int err, struct thread_info *thread,
pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
- if (!user_mode(regs) || in_interrupt()) {
+ if (!user_mode(regs)) {
dump_mem(KERN_EMERG, "Stack: ", regs->sp,
- THREAD_SIZE + (unsigned long)task_stack_page(tsk),
- compat_user_mode(regs));
+ THREAD_SIZE + (unsigned long)task_stack_page(tsk));
dump_backtrace(regs, tsk);
dump_instr(KERN_EMERG, regs);
}
@@ -373,11 +365,59 @@ exit:
return fn ? fn(regs, instr) : 1;
}
-asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+static void force_signal_inject(int signal, int code, struct pt_regs *regs,
+ unsigned long address)
{
siginfo_t info;
void __user *pc = (void __user *)instruction_pointer(regs);
+ const char *desc;
+ switch (signal) {
+ case SIGILL:
+ desc = "undefined instruction";
+ break;
+ case SIGSEGV:
+ desc = "illegal memory access";
+ break;
+ default:
+ desc = "bad mode";
+ break;
+ }
+
+ if (unhandled_signal(current, signal) &&
+ show_unhandled_signals_ratelimited()) {
+ pr_info("%s[%d]: %s: pc=%p\n",
+ current->comm, task_pid_nr(current), desc, pc);
+ dump_instr(KERN_INFO, regs);
+ }
+
+ info.si_signo = signal;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = pc;
+
+ arm64_notify_die(desc, regs, &info, 0);
+}
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr)
+{
+ int code;
+
+ down_read(&current->mm->mmap_sem);
+ if (find_vma(current->mm, addr) == NULL)
+ code = SEGV_MAPERR;
+ else
+ code = SEGV_ACCERR;
+ up_read(&current->mm->mmap_sem);
+
+ force_signal_inject(SIGSEGV, code, regs, addr);
+}
+
+asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
+{
/* check for AArch32 breakpoint instructions */
if (!aarch32_break_handler(regs))
return;
@@ -385,18 +425,66 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
if (call_undef_hook(regs) == 0)
return;
- if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) {
- pr_info("%s[%d]: undefined instruction: pc=%p\n",
- current->comm, task_pid_nr(current), pc);
- dump_instr(KERN_INFO, regs);
- }
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+}
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = pc;
+void cpu_enable_cache_maint_trap(void *__unused)
+{
+ config_sctlr_el1(SCTLR_EL1_UCI, 0);
+}
+
+#define __user_cache_maint(insn, address, res) \
+ asm volatile ( \
+ "1: " insn ", %1\n" \
+ " mov %w0, #0\n" \
+ "2:\n" \
+ " .pushsection .fixup,\"ax\"\n" \
+ " .align 2\n" \
+ "3: mov %w0, %w2\n" \
+ " b 2b\n" \
+ " .popsection\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : "=r" (res) \
+ : "r" (address), "i" (-EFAULT) )
+
+asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+{
+ unsigned long address;
+ int ret;
- arm64_notify_die("Oops - undefined instruction", regs, &info, 0);
+ /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */
+ if ((esr & 0x01fffc01) == 0x0012dc00) {
+ int rt = (esr >> 5) & 0x1f;
+ int crm = (esr >> 1) & 0x0f;
+
+ address = (rt == 31) ? 0 : regs->regs[rt];
+
+ switch (crm) {
+ case 11: /* DC CVAU, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case 10: /* DC CVAC, gets promoted */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case 14: /* DC CIVAC */
+ __user_cache_maint("dc civac", address, ret);
+ break;
+ case 5: /* IC IVAU */
+ __user_cache_maint("ic ivau", address, ret);
+ break;
+ default:
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+ return;
+ }
+ } else {
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+ return;
+ }
+
+ if (ret)
+ arm64_notify_segfault(regs, address);
+ else
+ regs->pc += 4;
}
long compat_arm_syscall(struct pt_regs *regs);
@@ -465,7 +553,7 @@ static const char *esr_class_str[] = {
const char *esr_get_class_string(u32 esr)
{
- return esr_class_str[esr >> ESR_ELx_EC_SHIFT];
+ return esr_class_str[ESR_ELx_EC(esr)];
}
/*
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 9fefb005812a..076312b17d4f 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -214,10 +214,16 @@ void update_vsyscall(struct timekeeper *tk)
vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec;
if (!use_syscall) {
+ /* tkr_mono.cycle_last == tkr_raw.cycle_last */
vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last;
+ vdso_data->raw_time_sec = tk->raw_time.tv_sec;
+ vdso_data->raw_time_nsec = tk->raw_time.tv_nsec;
vdso_data->xtime_clock_sec = tk->xtime_sec;
vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec;
- vdso_data->cs_mult = tk->tkr_mono.mult;
+ /* tkr_raw.xtime_nsec == 0 */
+ vdso_data->cs_mono_mult = tk->tkr_mono.mult;
+ vdso_data->cs_raw_mult = tk->tkr_raw.mult;
+ /* tkr_mono.shift == tkr_raw.shift */
vdso_data->cs_shift = tk->tkr_mono.shift;
}
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index b467fd0a384b..62c84f7cb01b 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -23,7 +23,7 @@ GCOV_PROFILE := n
ccflags-y += -Wl,-shared
obj-y += vdso.o
-extra-y += vdso.lds vdso-offsets.h
+extra-y += vdso.lds
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
# Force dependency (incbin is bad)
@@ -42,11 +42,10 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
quiet_cmd_vdsosym = VDSOSYM $@
define cmd_vdsosym
- $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ && \
- cp $@ include/generated/
+ $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
endef
-$(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
+include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
$(call if_changed,vdsosym)
# Assembly rules for the .S files
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index efa79e8d4196..e00b4671bd7c 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -26,24 +26,109 @@
#define NSEC_PER_SEC_HI16 0x3b9a
vdso_data .req x6
-use_syscall .req w7
-seqcnt .req w8
+seqcnt .req w7
+w_tmp .req w8
+x_tmp .req x8
+
+/*
+ * Conventions for macro arguments:
+ * - An argument is write-only if its name starts with "res".
+ * - All other arguments are read-only, unless otherwise specified.
+ */
.macro seqcnt_acquire
9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT]
tbnz seqcnt, #0, 9999b
dmb ishld
- ldr use_syscall, [vdso_data, #VDSO_USE_SYSCALL]
.endm
- .macro seqcnt_read, cnt
+ .macro seqcnt_check fail
dmb ishld
- ldr \cnt, [vdso_data, #VDSO_TB_SEQ_COUNT]
+ ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT]
+ cmp w_tmp, seqcnt
+ b.ne \fail
.endm
- .macro seqcnt_check, cnt, fail
- cmp \cnt, seqcnt
- b.ne \fail
+ .macro syscall_check fail
+ ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL]
+ cbnz w_tmp, \fail
+ .endm
+
+ .macro get_nsec_per_sec res
+ mov \res, #NSEC_PER_SEC_LO16
+ movk \res, #NSEC_PER_SEC_HI16, lsl #16
+ .endm
+
+ /*
+ * Returns the clock delta, in nanoseconds left-shifted by the clock
+ * shift.
+ */
+ .macro get_clock_shifted_nsec res, cycle_last, mult
+ /* Read the virtual counter. */
+ isb
+ mrs x_tmp, cntvct_el0
+ /* Calculate cycle delta and convert to ns. */
+ sub \res, x_tmp, \cycle_last
+ /* We can only guarantee 56 bits of precision. */
+ movn x_tmp, #0xff00, lsl #48
+ and \res, x_tmp, \res
+ mul \res, \res, \mult
+ .endm
+
+ /*
+ * Returns in res_{sec,nsec} the REALTIME timespec, based on the
+ * "wall time" (xtime) and the clock_mono delta.
+ */
+ .macro get_ts_realtime res_sec, res_nsec, \
+ clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec
+ add \res_nsec, \clock_nsec, \xtime_nsec
+ udiv x_tmp, \res_nsec, \nsec_to_sec
+ add \res_sec, \xtime_sec, x_tmp
+ msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec
+ .endm
+
+ /*
+ * Returns in res_{sec,nsec} the timespec based on the clock_raw delta,
+ * used for CLOCK_MONOTONIC_RAW.
+ */
+ .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec
+ udiv \res_sec, \clock_nsec, \nsec_to_sec
+ msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec
+ .endm
+
+ /* sec and nsec are modified in place. */
+ .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec
+ /* Add timespec. */
+ add \sec, \sec, \ts_sec
+ add \nsec, \nsec, \ts_nsec
+
+ /* Normalise the new timespec. */
+ cmp \nsec, \nsec_to_sec
+ b.lt 9999f
+ sub \nsec, \nsec, \nsec_to_sec
+ add \sec, \sec, #1
+9999:
+ cmp \nsec, #0
+ b.ge 9998f
+ add \nsec, \nsec, \nsec_to_sec
+ sub \sec, \sec, #1
+9998:
+ .endm
+
+ .macro clock_gettime_return, shift=0
+ .if \shift == 1
+ lsr x11, x11, x12
+ .endif
+ stp x10, x11, [x1, #TSPEC_TV_SEC]
+ mov x0, xzr
+ ret
+ .endm
+
+ .macro jump_slot jumptable, index, label
+ .if (. - \jumptable) != 4 * (\index)
+ .error "Jump slot index mismatch"
+ .endif
+ b \label
.endm
.text
@@ -51,18 +136,25 @@ seqcnt .req w8
/* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */
ENTRY(__kernel_gettimeofday)
.cfi_startproc
- mov x2, x30
- .cfi_register x30, x2
-
- /* Acquire the sequence counter and get the timespec. */
adr vdso_data, _vdso_data
-1: seqcnt_acquire
- cbnz use_syscall, 4f
-
/* If tv is NULL, skip to the timezone code. */
cbz x0, 2f
- bl __do_get_tspec
- seqcnt_check w9, 1b
+
+ /* Compute the time of day. */
+1: seqcnt_acquire
+ syscall_check fail=4f
+ ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
+ /* w11 = cs_mono_mult, w12 = cs_shift */
+ ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
+ ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
+ seqcnt_check fail=1b
+
+ get_nsec_per_sec res=x9
+ lsl x9, x9, x12
+
+ get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ get_ts_realtime res_sec=x10, res_nsec=x11, \
+ clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
/* Convert ns to us. */
mov x13, #1000
@@ -76,95 +168,126 @@ ENTRY(__kernel_gettimeofday)
stp w4, w5, [x1, #TZ_MINWEST]
3:
mov x0, xzr
- ret x2
+ ret
4:
/* Syscall fallback. */
mov x8, #__NR_gettimeofday
svc #0
- ret x2
+ ret
.cfi_endproc
ENDPROC(__kernel_gettimeofday)
+#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE
+
/* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */
ENTRY(__kernel_clock_gettime)
.cfi_startproc
- cmp w0, #CLOCK_REALTIME
- ccmp w0, #CLOCK_MONOTONIC, #0x4, ne
- b.ne 2f
+ cmp w0, #JUMPSLOT_MAX
+ b.hi syscall
+ adr vdso_data, _vdso_data
+ adr x_tmp, jumptable
+ add x_tmp, x_tmp, w0, uxtw #2
+ br x_tmp
+
+ ALIGN
+jumptable:
+ jump_slot jumptable, CLOCK_REALTIME, realtime
+ jump_slot jumptable, CLOCK_MONOTONIC, monotonic
+ b syscall
+ b syscall
+ jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw
+ jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse
+ jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse
+
+ .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1)
+ .error "Wrong jumptable size"
+ .endif
+
+ ALIGN
+realtime:
+ seqcnt_acquire
+ syscall_check fail=syscall
+ ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
+ /* w11 = cs_mono_mult, w12 = cs_shift */
+ ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
+ ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
+ seqcnt_check fail=realtime
- mov x2, x30
- .cfi_register x30, x2
+ /* All computations are done with left-shifted nsecs. */
+ get_nsec_per_sec res=x9
+ lsl x9, x9, x12
- /* Get kernel timespec. */
- adr vdso_data, _vdso_data
-1: seqcnt_acquire
- cbnz use_syscall, 7f
+ get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ get_ts_realtime res_sec=x10, res_nsec=x11, \
+ clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
+ clock_gettime_return, shift=1
- bl __do_get_tspec
- seqcnt_check w9, 1b
+ ALIGN
+monotonic:
+ seqcnt_acquire
+ syscall_check fail=syscall
+ ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
+ /* w11 = cs_mono_mult, w12 = cs_shift */
+ ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
+ ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
+ ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
+ seqcnt_check fail=monotonic
- mov x30, x2
+ /* All computations are done with left-shifted nsecs. */
+ lsl x4, x4, x12
+ get_nsec_per_sec res=x9
+ lsl x9, x9, x12
- cmp w0, #CLOCK_MONOTONIC
- b.ne 6f
+ get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ get_ts_realtime res_sec=x10, res_nsec=x11, \
+ clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
- /* Get wtm timespec. */
- ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC]
+ add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9
+ clock_gettime_return, shift=1
- /* Check the sequence counter. */
- seqcnt_read w9
- seqcnt_check w9, 1b
- b 4f
-2:
- cmp w0, #CLOCK_REALTIME_COARSE
- ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
- b.ne 8f
+ ALIGN
+monotonic_raw:
+ seqcnt_acquire
+ syscall_check fail=syscall
+ ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
+ /* w11 = cs_raw_mult, w12 = cs_shift */
+ ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT]
+ ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
+ seqcnt_check fail=monotonic_raw
- /* xtime_coarse_nsec is already right-shifted */
- mov x12, #0
+ /* All computations are done with left-shifted nsecs. */
+ lsl x14, x14, x12
+ get_nsec_per_sec res=x9
+ lsl x9, x9, x12
- /* Get coarse timespec. */
- adr vdso_data, _vdso_data
-3: seqcnt_acquire
+ get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ get_ts_clock_raw res_sec=x10, res_nsec=x11, \
+ clock_nsec=x15, nsec_to_sec=x9
+
+ add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
+ clock_gettime_return, shift=1
+
+ ALIGN
+realtime_coarse:
+ seqcnt_acquire
ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
+ seqcnt_check fail=realtime_coarse
+ clock_gettime_return
- /* Get wtm timespec. */
+ ALIGN
+monotonic_coarse:
+ seqcnt_acquire
+ ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC]
+ seqcnt_check fail=monotonic_coarse
- /* Check the sequence counter. */
- seqcnt_read w9
- seqcnt_check w9, 3b
+ /* Computations are done in (non-shifted) nsecs. */
+ get_nsec_per_sec res=x9
+ add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
+ clock_gettime_return
- cmp w0, #CLOCK_MONOTONIC_COARSE
- b.ne 6f
-4:
- /* Add on wtm timespec. */
- add x10, x10, x13
- lsl x14, x14, x12
- add x11, x11, x14
-
- /* Normalise the new timespec. */
- mov x15, #NSEC_PER_SEC_LO16
- movk x15, #NSEC_PER_SEC_HI16, lsl #16
- lsl x15, x15, x12
- cmp x11, x15
- b.lt 5f
- sub x11, x11, x15
- add x10, x10, #1
-5:
- cmp x11, #0
- b.ge 6f
- add x11, x11, x15
- sub x10, x10, #1
-
-6: /* Store to the user timespec. */
- lsr x11, x11, x12
- stp x10, x11, [x1, #TSPEC_TV_SEC]
- mov x0, xzr
- ret
-7:
- mov x30, x2
-8: /* Syscall fallback. */
+ ALIGN
+syscall: /* Syscall fallback. */
mov x8, #__NR_clock_gettime
svc #0
ret
@@ -176,6 +299,7 @@ ENTRY(__kernel_clock_getres)
.cfi_startproc
cmp w0, #CLOCK_REALTIME
ccmp w0, #CLOCK_MONOTONIC, #0x4, ne
+ ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
b.ne 1f
ldr x2, 5f
@@ -203,46 +327,3 @@ ENTRY(__kernel_clock_getres)
.quad CLOCK_COARSE_RES
.cfi_endproc
ENDPROC(__kernel_clock_getres)
-
-/*
- * Read the current time from the architected counter.
- * Expects vdso_data to be initialised.
- * Clobbers the temporary registers (x9 - x15).
- * Returns:
- * - w9 = vDSO sequence counter
- * - (x10, x11) = (ts->tv_sec, shifted ts->tv_nsec)
- * - w12 = cs_shift
- */
-ENTRY(__do_get_tspec)
- .cfi_startproc
-
- /* Read from the vDSO data page. */
- ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
- ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
- ldp w11, w12, [vdso_data, #VDSO_CS_MULT]
- seqcnt_read w9
-
- /* Read the virtual counter. */
- isb
- mrs x15, cntvct_el0
-
- /* Calculate cycle delta and convert to ns. */
- sub x10, x15, x10
- /* We can only guarantee 56 bits of precision. */
- movn x15, #0xff00, lsl #48
- and x10, x15, x10
- mul x10, x10, x11
-
- /* Use the kernel time to calculate the new timespec. */
- mov x11, #NSEC_PER_SEC_LO16
- movk x11, #NSEC_PER_SEC_HI16, lsl #16
- lsl x11, x11, x12
- add x15, x10, x14
- udiv x14, x15, x11
- add x10, x13, x14
- mul x13, x14, x11
- sub x11, x15, x13
-
- ret
- .cfi_endproc
-ENDPROC(__do_get_tspec)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 435e820e898d..89d6e177ecbd 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
__exception_text_end = .;
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
+ ENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
+ KPROBES_TEXT
HYPERVISOR_TEXT
IDMAP_TEXT
HIBERNATE_TEXT
@@ -131,12 +133,13 @@ SECTIONS
}
. = ALIGN(SEGMENT_ALIGN);
- RO_DATA(PAGE_SIZE) /* everything from this point to */
- EXCEPTION_TABLE(8) /* _etext will be marked RO NX */
+ _etext = .; /* End of text section */
+
+ RO_DATA(PAGE_SIZE) /* everything from this point to */
+ EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */
NOTES
. = ALIGN(SEGMENT_ALIGN);
- _etext = .; /* End of text and rodata section */
__init_begin = .;
INIT_TEXT_SECTION(8)
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 3246c4aba5b1..fa96fe2bd469 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -106,7 +106,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
run->exit_reason = KVM_EXIT_DEBUG;
run->debug.arch.hsr = hsr;
- switch (hsr >> ESR_ELx_EC_SHIFT) {
+ switch (ESR_ELx_EC(hsr)) {
case ESR_ELx_EC_WATCHPT_LOW:
run->debug.arch.far = vcpu->arch.fault.far_el2;
/* fall through */
@@ -149,7 +149,7 @@ static exit_handle_fn arm_exit_handlers[] = {
static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
{
u32 hsr = kvm_vcpu_get_hsr(vcpu);
- u8 hsr_ec = hsr >> ESR_ELx_EC_SHIFT;
+ u8 hsr_ec = ESR_ELx_EC(hsr);
if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
!arm_exit_handlers[hsr_ec]) {
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 778d0effa2af..0c85febcc1eb 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -17,6 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
+# KVM code is run at a different exception code with a different map, so
+# compiler instrumentation that inserts callbacks or checks into the code may
+# cause crashes. Just disable it.
GCOV_PROFILE := n
KASAN_SANITIZE := n
UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 437cfad5e3d8..4373997d1a70 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -198,7 +198,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
{
u64 esr = read_sysreg_el2(esr);
- u8 ec = esr >> ESR_ELx_EC_SHIFT;
+ u8 ec = ESR_ELx_EC(esr);
u64 hpfar, far;
vcpu->arch.fault.esr_el2 = esr;
diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S
index 17e8306dca29..0b90497d4424 100644
--- a/arch/arm64/lib/copy_from_user.S
+++ b/arch/arm64/lib/copy_from_user.S
@@ -66,7 +66,7 @@
.endm
end .req x5
-ENTRY(__copy_from_user)
+ENTRY(__arch_copy_from_user)
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
CONFIG_ARM64_PAN)
add end, x0, x2
@@ -75,7 +75,7 @@ ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
CONFIG_ARM64_PAN)
mov x0, #0 // Nothing to copy
ret
-ENDPROC(__copy_from_user)
+ENDPROC(__arch_copy_from_user)
.section .fixup,"ax"
.align 2
diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S
index 21faae60f988..7a7efe255034 100644
--- a/arch/arm64/lib/copy_to_user.S
+++ b/arch/arm64/lib/copy_to_user.S
@@ -65,7 +65,7 @@
.endm
end .req x5
-ENTRY(__copy_to_user)
+ENTRY(__arch_copy_to_user)
ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
CONFIG_ARM64_PAN)
add end, x0, x2
@@ -74,7 +74,7 @@ ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
CONFIG_ARM64_PAN)
mov x0, #0
ret
-ENDPROC(__copy_to_user)
+ENDPROC(__arch_copy_to_user)
.section .fixup,"ax"
.align 2
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 50ff9ba3a236..07d7352d7c38 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -52,7 +52,7 @@ ENTRY(__flush_cache_user_range)
sub x3, x2, #1
bic x4, x0, x3
1:
-USER(9f, dc cvau, x4 ) // clean D line to PoU
+user_alt 9f, "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE
add x4, x4, x2
cmp x4, x1
b.lo 1b
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index c566ec83719f..f6c55afab3e2 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -19,6 +19,7 @@
#include <linux/gfp.h>
#include <linux/acpi.h>
+#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/genalloc.h>
@@ -29,6 +30,8 @@
#include <asm/cacheflush.h>
+static int swiotlb __read_mostly;
+
static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
bool coherent)
{
@@ -341,6 +344,13 @@ static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
return ret;
}
+static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+ if (swiotlb)
+ return swiotlb_dma_supported(hwdev, mask);
+ return 1;
+}
+
static struct dma_map_ops swiotlb_dma_ops = {
.alloc = __dma_alloc,
.free = __dma_free,
@@ -354,7 +364,7 @@ static struct dma_map_ops swiotlb_dma_ops = {
.sync_single_for_device = __swiotlb_sync_single_for_device,
.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
.sync_sg_for_device = __swiotlb_sync_sg_for_device,
- .dma_supported = swiotlb_dma_supported,
+ .dma_supported = __swiotlb_dma_supported,
.mapping_error = swiotlb_dma_mapping_error,
};
@@ -513,6 +523,9 @@ EXPORT_SYMBOL(dummy_dma_ops);
static int __init arm64_dma_init(void)
{
+ if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+ swiotlb = 1;
+
return atomic_pool_init();
}
arch_initcall(arm64_dma_init);
@@ -848,15 +861,16 @@ static int __iommu_attach_notifier(struct notifier_block *nb,
{
struct iommu_dma_notifier_data *master, *tmp;
- if (action != BUS_NOTIFY_ADD_DEVICE)
+ if (action != BUS_NOTIFY_BIND_DRIVER)
return 0;
mutex_lock(&iommu_dma_notifier_lock);
list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
- if (do_iommu_attach(master->dev, master->ops,
- master->dma_base, master->size)) {
+ if (data == master->dev && do_iommu_attach(master->dev,
+ master->ops, master->dma_base, master->size)) {
list_del(&master->list);
kfree(master);
+ break;
}
}
mutex_unlock(&iommu_dma_notifier_lock);
@@ -870,17 +884,8 @@ static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
if (!nb)
return -ENOMEM;
- /*
- * The device must be attached to a domain before the driver probe
- * routine gets a chance to start allocating DMA buffers. However,
- * the IOMMU driver also needs a chance to configure the iommu_group
- * via its add_device callback first, so we need to make the attach
- * happen between those two points. Since the IOMMU core uses a bus
- * notifier with default priority for add_device, do the same but
- * with a lower priority to ensure the appropriate ordering.
- */
+
nb->notifier_call = __iommu_attach_notifier;
- nb->priority = -100;
ret = bus_register_notifier(bus, nb);
if (ret) {
@@ -904,10 +909,6 @@ static int __init __iommu_dma_init(void)
if (!ret)
ret = register_iommu_dma_ops_notifier(&pci_bus_type);
#endif
-
- /* handle devices queued before this arch_initcall */
- if (!ret)
- __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
return ret;
}
arch_initcall(__iommu_dma_init);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index ccfde237d6e6..f94b80eb295d 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -27,11 +27,7 @@
#include <asm/memory.h>
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
-
-struct addr_marker {
- unsigned long start_address;
- const char *name;
-};
+#include <asm/ptdump.h>
static const struct addr_marker address_markers[] = {
#ifdef CONFIG_KASAN
@@ -290,7 +286,8 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
}
}
-static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start)
+static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
+ unsigned long start)
{
pgd_t *pgd = pgd_offset(mm, 0UL);
unsigned i;
@@ -309,12 +306,13 @@ static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long st
static int ptdump_show(struct seq_file *m, void *v)
{
+ struct ptdump_info *info = m->private;
struct pg_state st = {
.seq = m,
- .marker = address_markers,
+ .marker = info->markers,
};
- walk_pgd(&st, &init_mm, VA_START);
+ walk_pgd(&st, info->mm, info->base_addr);
note_page(&st, 0, 0, 0);
return 0;
@@ -322,7 +320,7 @@ static int ptdump_show(struct seq_file *m, void *v)
static int ptdump_open(struct inode *inode, struct file *file)
{
- return single_open(file, ptdump_show, NULL);
+ return single_open(file, ptdump_show, inode->i_private);
}
static const struct file_operations ptdump_fops = {
@@ -332,7 +330,7 @@ static const struct file_operations ptdump_fops = {
.release = single_release,
};
-static int ptdump_init(void)
+int ptdump_register(struct ptdump_info *info, const char *name)
{
struct dentry *pe;
unsigned i, j;
@@ -342,8 +340,18 @@ static int ptdump_init(void)
for (j = 0; j < pg_level[i].num; j++)
pg_level[i].mask |= pg_level[i].bits[j].mask;
- pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
- &ptdump_fops);
+ pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
return pe ? 0 : -ENOMEM;
}
+
+static struct ptdump_info kernel_ptdump_info = {
+ .mm = &init_mm,
+ .markers = address_markers,
+ .base_addr = VA_START,
+};
+
+static int ptdump_init(void)
+{
+ return ptdump_register(&kernel_ptdump_info, "kernel_page_tables");
+}
device_initcall(ptdump_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index b1166d1e5955..c8beaa0da7df 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -41,6 +41,28 @@
static const char *fault_name(unsigned int esr);
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ int ret = 0;
+
+ /* kprobe_running() needs smp_processor_id() */
+ if (!user_mode(regs)) {
+ preempt_disable();
+ if (kprobe_running() && kprobe_fault_handler(regs, esr))
+ ret = 1;
+ preempt_enable();
+ }
+
+ return ret;
+}
+#else
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+ return 0;
+}
+#endif
+
/*
* Dump out the page tables associated with 'addr' in mm 'mm'.
*/
@@ -202,8 +224,6 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
#define VM_FAULT_BADMAP 0x010000
#define VM_FAULT_BADACCESS 0x020000
-#define ESR_LNX_EXEC (1 << 24)
-
static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
unsigned int mm_flags, unsigned long vm_flags,
struct task_struct *tsk)
@@ -233,7 +253,7 @@ good_area:
goto out;
}
- return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
+ return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
check_stack:
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
@@ -242,14 +262,19 @@ out:
return fault;
}
-static inline int permission_fault(unsigned int esr)
+static inline bool is_permission_fault(unsigned int esr)
{
- unsigned int ec = (esr & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT;
+ unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
}
+static bool is_el0_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
+}
+
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
@@ -259,6 +284,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ if (notify_page_fault(regs, esr))
+ return 0;
+
tsk = current;
mm = tsk->mm;
@@ -272,14 +300,14 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
if (user_mode(regs))
mm_flags |= FAULT_FLAG_USER;
- if (esr & ESR_LNX_EXEC) {
+ if (is_el0_instruction_abort(esr)) {
vm_flags = VM_EXEC;
} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
vm_flags = VM_WRITE;
mm_flags |= FAULT_FLAG_WRITE;
}
- if (permission_fault(esr) && (addr < USER_DS)) {
+ if (is_permission_fault(esr) && (addr < USER_DS)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
@@ -630,6 +658,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
return rv;
}
+NOKPROBE_SYMBOL(do_debug_exception);
#ifdef CONFIG_ARM64_PAN
void cpu_enable_pan(void *__unused)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d45f8627012c..bbb7ee76e319 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -160,12 +160,10 @@ static void __init arm64_memory_present(void)
static void __init arm64_memory_present(void)
{
struct memblock_region *reg;
- int nid = 0;
for_each_memblock(memory, reg) {
-#ifdef CONFIG_NUMA
- nid = reg->nid;
-#endif
+ int nid = memblock_get_region_node(reg);
+
memory_present(nid, memblock_region_memory_base_pfn(reg),
memblock_region_memory_end_pfn(reg));
}
@@ -226,7 +224,7 @@ void __init arm64_memblock_init(void)
* via the linear mapping.
*/
if (memory_limit != (phys_addr_t)ULLONG_MAX) {
- memblock_enforce_memory_limit(memory_limit);
+ memblock_mem_limit_remove_map(memory_limit);
memblock_add(__pa(_text), (u64)(_end - _text));
}
@@ -403,7 +401,8 @@ static void __init free_unused_memmap(void)
*/
void __init mem_init(void)
{
- swiotlb_init(1);
+ if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+ swiotlb_init(1);
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
@@ -430,9 +429,9 @@ void __init mem_init(void)
pr_cont(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n",
MLG(VMALLOC_START, VMALLOC_END));
pr_cont(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(_text, __start_rodata));
+ MLK_ROUNDUP(_text, _etext));
pr_cont(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n",
- MLK_ROUNDUP(__start_rodata, _etext));
+ MLK_ROUNDUP(__start_rodata, __init_begin));
pr_cont(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n",
MLK_ROUNDUP(__init_begin, __init_end));
pr_cont(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n",
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0f85a46c3e18..51a558195bb9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -77,7 +77,6 @@ static phys_addr_t __init early_pgtable_alloc(void)
void *ptr;
phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- BUG_ON(!phys);
/*
* The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
@@ -97,24 +96,6 @@ static phys_addr_t __init early_pgtable_alloc(void)
return phys;
}
-/*
- * remap a PMD into pages
- */
-static void split_pmd(pmd_t *pmd, pte_t *pte)
-{
- unsigned long pfn = pmd_pfn(*pmd);
- int i = 0;
-
- do {
- /*
- * Need to have the least restrictive permissions available
- * permissions will be fixed up later
- */
- set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
- pfn++;
- } while (pte++, i++, i < PTRS_PER_PTE);
-}
-
static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
unsigned long end, unsigned long pfn,
pgprot_t prot,
@@ -122,15 +103,13 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
{
pte_t *pte;
- if (pmd_none(*pmd) || pmd_sect(*pmd)) {
+ BUG_ON(pmd_sect(*pmd));
+ if (pmd_none(*pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
pte_phys = pgtable_alloc();
pte = pte_set_fixmap(pte_phys);
- if (pmd_sect(*pmd))
- split_pmd(pmd, pte);
__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
- flush_tlb_all();
pte_clear_fixmap();
}
BUG_ON(pmd_bad(*pmd));
@@ -144,41 +123,10 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
pte_clear_fixmap();
}
-static void split_pud(pud_t *old_pud, pmd_t *pmd)
-{
- unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT;
- pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr);
- int i = 0;
-
- do {
- set_pmd(pmd, __pmd(addr | pgprot_val(prot)));
- addr += PMD_SIZE;
- } while (pmd++, i++, i < PTRS_PER_PMD);
-}
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-
- /*
- * If debug_page_alloc is enabled we must map the linear map
- * using pages. However, other mappings created by
- * create_mapping_noalloc must use sections in some cases. Allow
- * sections to be used in those cases, where no pgtable_alloc
- * function is provided.
- */
- return !pgtable_alloc || !debug_pagealloc_enabled();
-}
-#else
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
- return true;
-}
-#endif
-
static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void))
+ phys_addr_t (*pgtable_alloc)(void),
+ bool allow_block_mappings)
{
pmd_t *pmd;
unsigned long next;
@@ -186,20 +134,13 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
/*
* Check for initial section mappings in the pgd/pud and remove them.
*/
- if (pud_none(*pud) || pud_sect(*pud)) {
+ BUG_ON(pud_sect(*pud));
+ if (pud_none(*pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
pmd_phys = pgtable_alloc();
pmd = pmd_set_fixmap(pmd_phys);
- if (pud_sect(*pud)) {
- /*
- * need to have the 1G of mappings continue to be
- * present
- */
- split_pud(pud, pmd);
- }
__pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
- flush_tlb_all();
pmd_clear_fixmap();
}
BUG_ON(pud_bad(*pud));
@@ -209,7 +150,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
next = pmd_addr_end(addr, end);
/* try section mapping first */
if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
- block_mappings_allowed(pgtable_alloc)) {
+ allow_block_mappings) {
pmd_t old_pmd =*pmd;
pmd_set_huge(pmd, phys, prot);
/*
@@ -248,7 +189,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void))
+ phys_addr_t (*pgtable_alloc)(void),
+ bool allow_block_mappings)
{
pud_t *pud;
unsigned long next;
@@ -268,8 +210,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
/*
* For 4K granule only, attempt to put down a 1GB block
*/
- if (use_1G_block(addr, next, phys) &&
- block_mappings_allowed(pgtable_alloc)) {
+ if (use_1G_block(addr, next, phys) && allow_block_mappings) {
pud_t old_pud = *pud;
pud_set_huge(pud, phys, prot);
@@ -290,7 +231,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
}
} else {
alloc_init_pmd(pud, addr, next, phys, prot,
- pgtable_alloc);
+ pgtable_alloc, allow_block_mappings);
}
phys += next - addr;
} while (pud++, addr = next, addr != end);
@@ -298,15 +239,14 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
pud_clear_fixmap();
}
-/*
- * Create the page directory entries and any necessary page tables for the
- * mapping specified by 'md'.
- */
-static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
- phys_addr_t size, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void))
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void),
+ bool allow_block_mappings)
{
unsigned long addr, length, end, next;
+ pgd_t *pgd = pgd_offset_raw(pgdir, virt);
/*
* If the virtual and physical address don't have the same offset
@@ -322,29 +262,23 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
end = addr + length;
do {
next = pgd_addr_end(addr, end);
- alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc);
+ alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+ allow_block_mappings);
phys += next - addr;
} while (pgd++, addr = next, addr != end);
}
-static phys_addr_t late_pgtable_alloc(void)
+static phys_addr_t pgd_pgtable_alloc(void)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
- BUG_ON(!ptr);
+ if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+ BUG();
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
return __pa(ptr);
}
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
- unsigned long virt, phys_addr_t size,
- pgprot_t prot,
- phys_addr_t (*alloc)(void))
-{
- init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc);
-}
-
/*
* This function can only be used to modify existing table entries,
* without allocating new levels of table. Note that this permits the
@@ -358,16 +292,17 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
&phys, virt);
return;
}
- __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
- NULL);
+ __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true);
}
void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
- pgprot_t prot)
+ pgprot_t prot, bool allow_block_mappings)
{
+ BUG_ON(mm == &init_mm);
+
__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
- late_pgtable_alloc);
+ pgd_pgtable_alloc, allow_block_mappings);
}
static void create_mapping_late(phys_addr_t phys, unsigned long virt,
@@ -380,51 +315,54 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
}
__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
- late_pgtable_alloc);
+ NULL, !debug_pagealloc_enabled());
}
static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
{
unsigned long kernel_start = __pa(_text);
- unsigned long kernel_end = __pa(_etext);
+ unsigned long kernel_end = __pa(__init_begin);
/*
* Take care not to create a writable alias for the
* read-only text and rodata sections of the kernel image.
*/
- /* No overlap with the kernel text */
+ /* No overlap with the kernel text/rodata */
if (end < kernel_start || start >= kernel_end) {
__create_pgd_mapping(pgd, start, __phys_to_virt(start),
end - start, PAGE_KERNEL,
- early_pgtable_alloc);
+ early_pgtable_alloc,
+ !debug_pagealloc_enabled());
return;
}
/*
- * This block overlaps the kernel text mapping.
+ * This block overlaps the kernel text/rodata mappings.
* Map the portion(s) which don't overlap.
*/
if (start < kernel_start)
__create_pgd_mapping(pgd, start,
__phys_to_virt(start),
kernel_start - start, PAGE_KERNEL,
- early_pgtable_alloc);
+ early_pgtable_alloc,
+ !debug_pagealloc_enabled());
if (kernel_end < end)
__create_pgd_mapping(pgd, kernel_end,
__phys_to_virt(kernel_end),
end - kernel_end, PAGE_KERNEL,
- early_pgtable_alloc);
+ early_pgtable_alloc,
+ !debug_pagealloc_enabled());
/*
- * Map the linear alias of the [_text, _etext) interval as
+ * Map the linear alias of the [_text, __init_begin) interval as
* read-only/non-executable. This makes the contents of the
* region accessible to subsystems such as hibernate, but
* protects it from inadvertent modification or execution.
*/
__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
kernel_end - kernel_start, PAGE_KERNEL_RO,
- early_pgtable_alloc);
+ early_pgtable_alloc, !debug_pagealloc_enabled());
}
static void __init map_mem(pgd_t *pgd)
@@ -449,14 +387,14 @@ void mark_rodata_ro(void)
{
unsigned long section_size;
- section_size = (unsigned long)__start_rodata - (unsigned long)_text;
+ section_size = (unsigned long)_etext - (unsigned long)_text;
create_mapping_late(__pa(_text), (unsigned long)_text,
section_size, PAGE_KERNEL_ROX);
/*
- * mark .rodata as read only. Use _etext rather than __end_rodata to
- * cover NOTES and EXCEPTION_TABLE.
+ * mark .rodata as read only. Use __init_begin rather than __end_rodata
+ * to cover NOTES and EXCEPTION_TABLE.
*/
- section_size = (unsigned long)_etext - (unsigned long)__start_rodata;
+ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata,
section_size, PAGE_KERNEL_RO);
}
@@ -481,7 +419,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
BUG_ON(!PAGE_ALIGNED(size));
__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
- early_pgtable_alloc);
+ early_pgtable_alloc, !debug_pagealloc_enabled());
vma->addr = va_start;
vma->phys_addr = pa_start;
@@ -499,8 +437,8 @@ static void __init map_kernel(pgd_t *pgd)
{
static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data;
- map_kernel_segment(pgd, _text, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text);
- map_kernel_segment(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata);
+ map_kernel_segment(pgd, _text, _etext, PAGE_KERNEL_EXEC, &vmlinux_text);
+ map_kernel_segment(pgd, __start_rodata, __init_begin, PAGE_KERNEL, &vmlinux_rodata);
map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC,
&vmlinux_init);
map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 98dc1047f2a2..c7fe3ec70774 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/module.h>
@@ -29,7 +30,7 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
static int numa_distance_cnt;
static u8 *numa_distance;
-static int numa_off;
+static bool numa_off;
static __init int numa_parse_early_param(char *opt)
{
@@ -37,7 +38,7 @@ static __init int numa_parse_early_param(char *opt)
return -EINVAL;
if (!strncmp(opt, "off", 3)) {
pr_info("%s\n", "NUMA turned off");
- numa_off = 1;
+ numa_off = true;
}
return 0;
}
@@ -131,25 +132,25 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
* numa_add_memblk - Set node id to memblk
* @nid: NUMA node ID of the new memblk
* @start: Start address of the new memblk
- * @size: Size of the new memblk
+ * @end: End address of the new memblk
*
* RETURNS:
* 0 on success, -errno on failure.
*/
-int __init numa_add_memblk(int nid, u64 start, u64 size)
+int __init numa_add_memblk(int nid, u64 start, u64 end)
{
int ret;
- ret = memblock_set_node(start, size, &memblock.memory, nid);
+ ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
if (ret < 0) {
pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
- start, (start + size - 1), nid);
+ start, (end - 1), nid);
return ret;
}
node_set(nid, numa_nodes_parsed);
pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
- start, (start + size - 1), nid);
+ start, (end - 1), nid);
return ret;
}
@@ -362,12 +363,15 @@ static int __init dummy_numa_init(void)
int ret;
struct memblock_region *mblk;
- pr_info("%s\n", "No NUMA configuration found");
+ if (numa_off)
+ pr_info("NUMA disabled\n"); /* Forced off on command line. */
+ else
+ pr_info("No NUMA configuration found\n");
pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
0LLU, PFN_PHYS(max_pfn) - 1);
for_each_memblock(memory, mblk) {
- ret = numa_add_memblk(0, mblk->base, mblk->size);
+ ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
if (!ret)
continue;
@@ -375,7 +379,7 @@ static int __init dummy_numa_init(void)
return ret;
}
- numa_off = 1;
+ numa_off = true;
return 0;
}
@@ -388,7 +392,9 @@ static int __init dummy_numa_init(void)
void __init arm64_numa_init(void)
{
if (!numa_off) {
- if (!numa_init(of_numa_init))
+ if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+ return;
+ if (acpi_disabled && !numa_init(of_numa_init))
return;
}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c4317879b938..5bb61de23201 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -180,6 +180,8 @@ ENTRY(__cpu_setup)
msr cpacr_el1, x0 // Enable FP/ASIMD
mov x0, #1 << 12 // Reset mdscr_el1 and disable
msr mdscr_el1, x0 // access to the DCC from EL0
+ isb // Unmask debug exceptions now,
+ enable_dbg // since this is per-cpu
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
/*
* Memory region attributes for LPAE:
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index aee5637ea436..7c16e547ccb2 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -1,7 +1,7 @@
/*
* BPF JIT compiler for ARM64
*
- * Copyright (C) 2014-2015 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -55,6 +55,7 @@
#define A64_BL(imm26) A64_BRANCH((imm26) << 2, LINK)
/* Unconditional branch (register) */
+#define A64_BR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_NOLINK)
#define A64_BLR(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_LINK)
#define A64_RET(Rn) aarch64_insn_gen_branch_reg(Rn, AARCH64_INSN_BRANCH_RETURN)
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 49ba37e4bfc0..b2fc97a2c56c 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -18,6 +18,7 @@
#define pr_fmt(fmt) "bpf_jit: " fmt
+#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/printk.h>
#include <linux/skbuff.h>
@@ -33,6 +34,7 @@ int bpf_jit_enable __read_mostly;
#define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
#define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
+#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
/* Map BPF registers to A64 registers */
static const int bpf2a64[] = {
@@ -54,6 +56,8 @@ static const int bpf2a64[] = {
/* temporary registers for internal BPF JIT */
[TMP_REG_1] = A64_R(10),
[TMP_REG_2] = A64_R(11),
+ /* tail_call_cnt */
+ [TCALL_CNT] = A64_R(26),
/* temporary register for blinding constants */
[BPF_REG_AX] = A64_R(9),
};
@@ -146,13 +150,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
-static void build_prologue(struct jit_ctx *ctx)
+#define PROLOGUE_OFFSET 8
+
+static int build_prologue(struct jit_ctx *ctx)
{
const u8 r6 = bpf2a64[BPF_REG_6];
const u8 r7 = bpf2a64[BPF_REG_7];
const u8 r8 = bpf2a64[BPF_REG_8];
const u8 r9 = bpf2a64[BPF_REG_9];
const u8 fp = bpf2a64[BPF_REG_FP];
+ const u8 tcc = bpf2a64[TCALL_CNT];
+ const int idx0 = ctx->idx;
+ int cur_offset;
/*
* BPF prog stack layout
@@ -162,8 +171,6 @@ static void build_prologue(struct jit_ctx *ctx)
* |FP/LR|
* current A64_FP => -16:+-----+
* | ... | callee saved registers
- * +-----+
- * | | x25/x26
* BPF fp register => -64:+-----+ <= (BPF_FP)
* | |
* | ... | BPF prog stack
@@ -183,18 +190,90 @@ static void build_prologue(struct jit_ctx *ctx)
emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
emit(A64_MOV(1, A64_FP, A64_SP), ctx);
- /* Save callee-saved register */
+ /* Save callee-saved registers */
emit(A64_PUSH(r6, r7, A64_SP), ctx);
emit(A64_PUSH(r8, r9, A64_SP), ctx);
+ emit(A64_PUSH(fp, tcc, A64_SP), ctx);
- /* Save fp (x25) and x26. SP requires 16 bytes alignment */
- emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx);
-
- /* Set up BPF prog stack base register (x25) */
+ /* Set up BPF prog stack base register */
emit(A64_MOV(1, fp, A64_SP), ctx);
+ /* Initialize tail_call_cnt */
+ emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+
/* Set up function call stack */
emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
+
+ cur_offset = ctx->idx - idx0;
+ if (cur_offset != PROLOGUE_OFFSET) {
+ pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+ cur_offset, PROLOGUE_OFFSET);
+ return -1;
+ }
+ return 0;
+}
+
+static int out_offset = -1; /* initialized on the first pass of build_body() */
+static int emit_bpf_tail_call(struct jit_ctx *ctx)
+{
+ /* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
+ const u8 r2 = bpf2a64[BPF_REG_2];
+ const u8 r3 = bpf2a64[BPF_REG_3];
+
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ const u8 prg = bpf2a64[TMP_REG_2];
+ const u8 tcc = bpf2a64[TCALL_CNT];
+ const int idx0 = ctx->idx;
+#define cur_offset (ctx->idx - idx0)
+#define jmp_offset (out_offset - (cur_offset))
+ size_t off;
+
+ /* if (index >= array->map.max_entries)
+ * goto out;
+ */
+ off = offsetof(struct bpf_array, map.max_entries);
+ emit_a64_mov_i64(tmp, off, ctx);
+ emit(A64_LDR32(tmp, r2, tmp), ctx);
+ emit(A64_CMP(0, r3, tmp), ctx);
+ emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+
+ /* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+ * goto out;
+ * tail_call_cnt++;
+ */
+ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
+ emit(A64_CMP(1, tcc, tmp), ctx);
+ emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+ emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
+
+ /* prog = array->ptrs[index];
+ * if (prog == NULL)
+ * goto out;
+ */
+ off = offsetof(struct bpf_array, ptrs);
+ emit_a64_mov_i64(tmp, off, ctx);
+ emit(A64_LDR64(tmp, r2, tmp), ctx);
+ emit(A64_LDR64(prg, tmp, r3), ctx);
+ emit(A64_CBZ(1, prg, jmp_offset), ctx);
+
+ /* goto *(prog->bpf_func + prologue_size); */
+ off = offsetof(struct bpf_prog, bpf_func);
+ emit_a64_mov_i64(tmp, off, ctx);
+ emit(A64_LDR64(tmp, prg, tmp), ctx);
+ emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+ emit(A64_BR(tmp), ctx);
+
+ /* out: */
+ if (out_offset == -1)
+ out_offset = cur_offset;
+ if (cur_offset != out_offset) {
+ pr_err_once("tail_call out_offset = %d, expected %d!\n",
+ cur_offset, out_offset);
+ return -1;
+ }
+ return 0;
+#undef cur_offset
+#undef jmp_offset
}
static void build_epilogue(struct jit_ctx *ctx)
@@ -499,13 +578,15 @@ emit_cond_jmp:
const u64 func = (u64)__bpf_call_base + imm;
emit_a64_mov_i64(tmp, func, ctx);
- emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
- emit(A64_MOV(1, A64_FP, A64_SP), ctx);
emit(A64_BLR(tmp), ctx);
emit(A64_MOV(1, r0, A64_R(0)), ctx);
- emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
break;
}
+ /* tail call */
+ case BPF_JMP | BPF_CALL | BPF_X:
+ if (emit_bpf_tail_call(ctx))
+ return -EFAULT;
+ break;
/* function return */
case BPF_JMP | BPF_EXIT:
/* Optimization: when last instruction is EXIT,
@@ -650,11 +731,8 @@ emit_cond_jmp:
emit_a64_mov_i64(r3, size, ctx);
emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
- emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
- emit(A64_MOV(1, A64_FP, A64_SP), ctx);
emit(A64_BLR(r5), ctx);
emit(A64_MOV(1, r0, A64_R(0)), ctx);
- emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx);
jmp_offset = epilogue_offset(ctx);
check_imm19(jmp_offset);
@@ -780,7 +858,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
goto out_off;
}
- build_prologue(&ctx);
+ if (build_prologue(&ctx)) {
+ prog = orig_prog;
+ goto out_off;
+ }
ctx.epilogue_offset = ctx.idx;
build_epilogue(&ctx);
diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile
index 74a8d87e542b..8ff8aa9c6228 100644
--- a/arch/arm64/xen/Makefile
+++ b/arch/arm64/xen/Makefile
@@ -1,2 +1,3 @@
xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o)
obj-y := xen-arm.o hypercall.o
+obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o)
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 70df80e8da2c..329c8027b0a9 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -82,6 +82,7 @@ HYPERCALL3(vcpu_op);
HYPERCALL1(tmem_op);
HYPERCALL1(platform_op_raw);
HYPERCALL2(multicall);
+HYPERCALL2(vm_assist);
ENTRY(privcmd_call)
mov x16, x0
diff --git a/arch/avr32/include/uapi/asm/unistd.h b/arch/avr32/include/uapi/asm/unistd.h
index 60c0f3afc1f9..2c8a0d2b6c30 100644
--- a/arch/avr32/include/uapi/asm/unistd.h
+++ b/arch/avr32/include/uapi/asm/unistd.h
@@ -12,331 +12,333 @@
* This file contains the system call numbers.
*/
-#define __NR_restart_syscall 0
-#define __NR_exit 1
-#define __NR_fork 2
-#define __NR_read 3
-#define __NR_write 4
-#define __NR_open 5
-#define __NR_close 6
-#define __NR_umask 7
-#define __NR_creat 8
-#define __NR_link 9
-#define __NR_unlink 10
-#define __NR_execve 11
-#define __NR_chdir 12
-#define __NR_time 13
-#define __NR_mknod 14
-#define __NR_chmod 15
-#define __NR_chown 16
-#define __NR_lchown 17
-#define __NR_lseek 18
-#define __NR__llseek 19
-#define __NR_getpid 20
-#define __NR_mount 21
-#define __NR_umount2 22
-#define __NR_setuid 23
-#define __NR_getuid 24
-#define __NR_stime 25
-#define __NR_ptrace 26
-#define __NR_alarm 27
-#define __NR_pause 28
-#define __NR_utime 29
-#define __NR_stat 30
-#define __NR_fstat 31
-#define __NR_lstat 32
-#define __NR_access 33
-#define __NR_chroot 34
-#define __NR_sync 35
-#define __NR_fsync 36
-#define __NR_kill 37
-#define __NR_rename 38
-#define __NR_mkdir 39
-#define __NR_rmdir 40
-#define __NR_dup 41
-#define __NR_pipe 42
-#define __NR_times 43
-#define __NR_clone 44
-#define __NR_brk 45
-#define __NR_setgid 46
-#define __NR_getgid 47
-#define __NR_getcwd 48
-#define __NR_geteuid 49
-#define __NR_getegid 50
-#define __NR_acct 51
-#define __NR_setfsuid 52
-#define __NR_setfsgid 53
-#define __NR_ioctl 54
-#define __NR_fcntl 55
-#define __NR_setpgid 56
-#define __NR_mremap 57
-#define __NR_setresuid 58
-#define __NR_getresuid 59
-#define __NR_setreuid 60
-#define __NR_setregid 61
-#define __NR_ustat 62
-#define __NR_dup2 63
-#define __NR_getppid 64
-#define __NR_getpgrp 65
-#define __NR_setsid 66
-#define __NR_rt_sigaction 67
-#define __NR_rt_sigreturn 68
-#define __NR_rt_sigprocmask 69
-#define __NR_rt_sigpending 70
-#define __NR_rt_sigtimedwait 71
-#define __NR_rt_sigqueueinfo 72
-#define __NR_rt_sigsuspend 73
-#define __NR_sethostname 74
-#define __NR_setrlimit 75
-#define __NR_getrlimit 76 /* SuS compliant getrlimit */
-#define __NR_getrusage 77
-#define __NR_gettimeofday 78
-#define __NR_settimeofday 79
-#define __NR_getgroups 80
-#define __NR_setgroups 81
-#define __NR_select 82
-#define __NR_symlink 83
-#define __NR_fchdir 84
-#define __NR_readlink 85
-#define __NR_pread 86
-#define __NR_pwrite 87
-#define __NR_swapon 88
-#define __NR_reboot 89
-#define __NR_mmap2 90
-#define __NR_munmap 91
-#define __NR_truncate 92
-#define __NR_ftruncate 93
-#define __NR_fchmod 94
-#define __NR_fchown 95
-#define __NR_getpriority 96
-#define __NR_setpriority 97
-#define __NR_wait4 98
-#define __NR_statfs 99
-#define __NR_fstatfs 100
-#define __NR_vhangup 101
-#define __NR_sigaltstack 102
-#define __NR_syslog 103
-#define __NR_setitimer 104
-#define __NR_getitimer 105
-#define __NR_swapoff 106
-#define __NR_sysinfo 107
+#define __NR_restart_syscall 0
+#define __NR_exit 1
+#define __NR_fork 2
+#define __NR_read 3
+#define __NR_write 4
+#define __NR_open 5
+#define __NR_close 6
+#define __NR_umask 7
+#define __NR_creat 8
+#define __NR_link 9
+#define __NR_unlink 10
+#define __NR_execve 11
+#define __NR_chdir 12
+#define __NR_time 13
+#define __NR_mknod 14
+#define __NR_chmod 15
+#define __NR_chown 16
+#define __NR_lchown 17
+#define __NR_lseek 18
+#define __NR__llseek 19
+#define __NR_getpid 20
+#define __NR_mount 21
+#define __NR_umount2 22
+#define __NR_setuid 23
+#define __NR_getuid 24
+#define __NR_stime 25
+#define __NR_ptrace 26
+#define __NR_alarm 27
+#define __NR_pause 28
+#define __NR_utime 29
+#define __NR_stat 30
+#define __NR_fstat 31
+#define __NR_lstat 32
+#define __NR_access 33
+#define __NR_chroot 34
+#define __NR_sync 35
+#define __NR_fsync 36
+#define __NR_kill 37
+#define __NR_rename 38
+#define __NR_mkdir 39
+#define __NR_rmdir 40
+#define __NR_dup 41
+#define __NR_pipe 42
+#define __NR_times 43
+#define __NR_clone 44
+#define __NR_brk 45
+#define __NR_setgid 46
+#define __NR_getgid 47
+#define __NR_getcwd 48
+#define __NR_geteuid 49
+#define __NR_getegid 50
+#define __NR_acct 51
+#define __NR_setfsuid 52
+#define __NR_setfsgid 53
+#define __NR_ioctl 54
+#define __NR_fcntl 55
+#define __NR_setpgid 56
+#define __NR_mremap 57
+#define __NR_setresuid 58
+#define __NR_getresuid 59
+#define __NR_setreuid 60
+#define __NR_setregid 61
+#define __NR_ustat 62
+#define __NR_dup2 63
+#define __NR_getppid 64
+#define __NR_getpgrp 65
+#define __NR_setsid 66
+#define __NR_rt_sigaction 67
+#define __NR_rt_sigreturn 68
+#define __NR_rt_sigprocmask 69
+#define __NR_rt_sigpending 70
+#define __NR_rt_sigtimedwait 71
+#define __NR_rt_sigqueueinfo 72
+#define __NR_rt_sigsuspend 73
+#define __NR_sethostname 74
+#define __NR_setrlimit 75
+#define __NR_getrlimit 76 /* SuS compliant getrlimit */
+#define __NR_getrusage 77
+#define __NR_gettimeofday 78
+#define __NR_settimeofday 79
+#define __NR_getgroups 80
+#define __NR_setgroups 81
+#define __NR_select 82
+#define __NR_symlink 83
+#define __NR_fchdir 84
+#define __NR_readlink 85
+#define __NR_pread 86
+#define __NR_pwrite 87
+#define __NR_swapon 88
+#define __NR_reboot 89
+#define __NR_mmap2 90
+#define __NR_munmap 91
+#define __NR_truncate 92
+#define __NR_ftruncate 93
+#define __NR_fchmod 94
+#define __NR_fchown 95
+#define __NR_getpriority 96
+#define __NR_setpriority 97
+#define __NR_wait4 98
+#define __NR_statfs 99
+#define __NR_fstatfs 100
+#define __NR_vhangup 101
+#define __NR_sigaltstack 102
+#define __NR_syslog 103
+#define __NR_setitimer 104
+#define __NR_getitimer 105
+#define __NR_swapoff 106
+#define __NR_sysinfo 107
/* 108 was __NR_ipc for a little while */
-#define __NR_sendfile 109
-#define __NR_setdomainname 110
-#define __NR_uname 111
-#define __NR_adjtimex 112
-#define __NR_mprotect 113
-#define __NR_vfork 114
-#define __NR_init_module 115
-#define __NR_delete_module 116
-#define __NR_quotactl 117
-#define __NR_getpgid 118
-#define __NR_bdflush 119
-#define __NR_sysfs 120
-#define __NR_personality 121
-#define __NR_afs_syscall 122 /* Syscall for Andrew File System */
-#define __NR_getdents 123
-#define __NR_flock 124
-#define __NR_msync 125
-#define __NR_readv 126
-#define __NR_writev 127
-#define __NR_getsid 128
-#define __NR_fdatasync 129
-#define __NR__sysctl 130
-#define __NR_mlock 131
-#define __NR_munlock 132
-#define __NR_mlockall 133
-#define __NR_munlockall 134
-#define __NR_sched_setparam 135
-#define __NR_sched_getparam 136
-#define __NR_sched_setscheduler 137
-#define __NR_sched_getscheduler 138
-#define __NR_sched_yield 139
-#define __NR_sched_get_priority_max 140
-#define __NR_sched_get_priority_min 141
-#define __NR_sched_rr_get_interval 142
-#define __NR_nanosleep 143
-#define __NR_poll 144
-#define __NR_nfsservctl 145
-#define __NR_setresgid 146
-#define __NR_getresgid 147
+#define __NR_sendfile 109
+#define __NR_setdomainname 110
+#define __NR_uname 111
+#define __NR_adjtimex 112
+#define __NR_mprotect 113
+#define __NR_vfork 114
+#define __NR_init_module 115
+#define __NR_delete_module 116
+#define __NR_quotactl 117
+#define __NR_getpgid 118
+#define __NR_bdflush 119
+#define __NR_sysfs 120
+#define __NR_personality 121
+#define __NR_afs_syscall 122 /* Syscall for Andrew File System */
+#define __NR_getdents 123
+#define __NR_flock 124
+#define __NR_msync 125
+#define __NR_readv 126
+#define __NR_writev 127
+#define __NR_getsid 128
+#define __NR_fdatasync 129
+#define __NR__sysctl 130
+#define __NR_mlock 131
+#define __NR_munlock 132
+#define __NR_mlockall 133
+#define __NR_munlockall 134
+#define __NR_sched_setparam 135
+#define __NR_sched_getparam 136
+#define __NR_sched_setscheduler 137
+#define __NR_sched_getscheduler 138
+#define __NR_sched_yield 139
+#define __NR_sched_get_priority_max 140
+#define __NR_sched_get_priority_min 141
+#define __NR_sched_rr_get_interval 142
+#define __NR_nanosleep 143
+#define __NR_poll 144
+#define __NR_nfsservctl 145
+#define __NR_setresgid 146
+#define __NR_getresgid 147
#define __NR_prctl 148
-#define __NR_socket 149
-#define __NR_bind 150
-#define __NR_connect 151
-#define __NR_listen 152
-#define __NR_accept 153
-#define __NR_getsockname 154
-#define __NR_getpeername 155
-#define __NR_socketpair 156
-#define __NR_send 157
-#define __NR_recv 158
-#define __NR_sendto 159
-#define __NR_recvfrom 160
-#define __NR_shutdown 161
-#define __NR_setsockopt 162
-#define __NR_getsockopt 163
-#define __NR_sendmsg 164
-#define __NR_recvmsg 165
-#define __NR_truncate64 166
-#define __NR_ftruncate64 167
-#define __NR_stat64 168
-#define __NR_lstat64 169
-#define __NR_fstat64 170
-#define __NR_pivot_root 171
-#define __NR_mincore 172
-#define __NR_madvise 173
-#define __NR_getdents64 174
-#define __NR_fcntl64 175
-#define __NR_gettid 176
-#define __NR_readahead 177
-#define __NR_setxattr 178
-#define __NR_lsetxattr 179
-#define __NR_fsetxattr 180
-#define __NR_getxattr 181
-#define __NR_lgetxattr 182
-#define __NR_fgetxattr 183
-#define __NR_listxattr 184
-#define __NR_llistxattr 185
-#define __NR_flistxattr 186
-#define __NR_removexattr 187
-#define __NR_lremovexattr 188
-#define __NR_fremovexattr 189
-#define __NR_tkill 190
-#define __NR_sendfile64 191
-#define __NR_futex 192
-#define __NR_sched_setaffinity 193
-#define __NR_sched_getaffinity 194
-#define __NR_capget 195
-#define __NR_capset 196
-#define __NR_io_setup 197
-#define __NR_io_destroy 198
-#define __NR_io_getevents 199
-#define __NR_io_submit 200
-#define __NR_io_cancel 201
-#define __NR_fadvise64 202
-#define __NR_exit_group 203
-#define __NR_lookup_dcookie 204
-#define __NR_epoll_create 205
-#define __NR_epoll_ctl 206
-#define __NR_epoll_wait 207
-#define __NR_remap_file_pages 208
-#define __NR_set_tid_address 209
-#define __NR_timer_create 210
-#define __NR_timer_settime 211
-#define __NR_timer_gettime 212
-#define __NR_timer_getoverrun 213
-#define __NR_timer_delete 214
-#define __NR_clock_settime 215
-#define __NR_clock_gettime 216
-#define __NR_clock_getres 217
-#define __NR_clock_nanosleep 218
-#define __NR_statfs64 219
-#define __NR_fstatfs64 220
-#define __NR_tgkill 221
- /* 222 reserved for tux */
-#define __NR_utimes 223
-#define __NR_fadvise64_64 224
-#define __NR_cacheflush 225
-
-#define __NR_vserver 226
-#define __NR_mq_open 227
-#define __NR_mq_unlink 228
-#define __NR_mq_timedsend 229
-#define __NR_mq_timedreceive 230
-#define __NR_mq_notify 231
-#define __NR_mq_getsetattr 232
-#define __NR_kexec_load 233
-#define __NR_waitid 234
-#define __NR_add_key 235
-#define __NR_request_key 236
-#define __NR_keyctl 237
-#define __NR_ioprio_set 238
-#define __NR_ioprio_get 239
-#define __NR_inotify_init 240
-#define __NR_inotify_add_watch 241
-#define __NR_inotify_rm_watch 242
-#define __NR_openat 243
-#define __NR_mkdirat 244
-#define __NR_mknodat 245
-#define __NR_fchownat 246
-#define __NR_futimesat 247
-#define __NR_fstatat64 248
-#define __NR_unlinkat 249
-#define __NR_renameat 250
-#define __NR_linkat 251
-#define __NR_symlinkat 252
-#define __NR_readlinkat 253
-#define __NR_fchmodat 254
-#define __NR_faccessat 255
-#define __NR_pselect6 256
-#define __NR_ppoll 257
-#define __NR_unshare 258
-#define __NR_set_robust_list 259
-#define __NR_get_robust_list 260
-#define __NR_splice 261
-#define __NR_sync_file_range 262
-#define __NR_tee 263
-#define __NR_vmsplice 264
-#define __NR_epoll_pwait 265
-#define __NR_msgget 266
-#define __NR_msgsnd 267
-#define __NR_msgrcv 268
-#define __NR_msgctl 269
-#define __NR_semget 270
-#define __NR_semop 271
-#define __NR_semctl 272
-#define __NR_semtimedop 273
-#define __NR_shmat 274
-#define __NR_shmget 275
-#define __NR_shmdt 276
-#define __NR_shmctl 277
-#define __NR_utimensat 278
-#define __NR_signalfd 279
+#define __NR_socket 149
+#define __NR_bind 150
+#define __NR_connect 151
+#define __NR_listen 152
+#define __NR_accept 153
+#define __NR_getsockname 154
+#define __NR_getpeername 155
+#define __NR_socketpair 156
+#define __NR_send 157
+#define __NR_recv 158
+#define __NR_sendto 159
+#define __NR_recvfrom 160
+#define __NR_shutdown 161
+#define __NR_setsockopt 162
+#define __NR_getsockopt 163
+#define __NR_sendmsg 164
+#define __NR_recvmsg 165
+#define __NR_truncate64 166
+#define __NR_ftruncate64 167
+#define __NR_stat64 168
+#define __NR_lstat64 169
+#define __NR_fstat64 170
+#define __NR_pivot_root 171
+#define __NR_mincore 172
+#define __NR_madvise 173
+#define __NR_getdents64 174
+#define __NR_fcntl64 175
+#define __NR_gettid 176
+#define __NR_readahead 177
+#define __NR_setxattr 178
+#define __NR_lsetxattr 179
+#define __NR_fsetxattr 180
+#define __NR_getxattr 181
+#define __NR_lgetxattr 182
+#define __NR_fgetxattr 183
+#define __NR_listxattr 184
+#define __NR_llistxattr 185
+#define __NR_flistxattr 186
+#define __NR_removexattr 187
+#define __NR_lremovexattr 188
+#define __NR_fremovexattr 189
+#define __NR_tkill 190
+#define __NR_sendfile64 191
+#define __NR_futex 192
+#define __NR_sched_setaffinity 193
+#define __NR_sched_getaffinity 194
+#define __NR_capget 195
+#define __NR_capset 196
+#define __NR_io_setup 197
+#define __NR_io_destroy 198
+#define __NR_io_getevents 199
+#define __NR_io_submit 200
+#define __NR_io_cancel 201
+#define __NR_fadvise64 202
+#define __NR_exit_group 203
+#define __NR_lookup_dcookie 204
+#define __NR_epoll_create 205
+#define __NR_epoll_ctl 206
+#define __NR_epoll_wait 207
+#define __NR_remap_file_pages 208
+#define __NR_set_tid_address 209
+#define __NR_timer_create 210
+#define __NR_timer_settime 211
+#define __NR_timer_gettime 212
+#define __NR_timer_getoverrun 213
+#define __NR_timer_delete 214
+#define __NR_clock_settime 215
+#define __NR_clock_gettime 216
+#define __NR_clock_getres 217
+#define __NR_clock_nanosleep 218
+#define __NR_statfs64 219
+#define __NR_fstatfs64 220
+#define __NR_tgkill 221
+/* 222 reserved for tux */
+#define __NR_utimes 223
+#define __NR_fadvise64_64 224
+#define __NR_cacheflush 225
+#define __NR_vserver 226
+#define __NR_mq_open 227
+#define __NR_mq_unlink 228
+#define __NR_mq_timedsend 229
+#define __NR_mq_timedreceive 230
+#define __NR_mq_notify 231
+#define __NR_mq_getsetattr 232
+#define __NR_kexec_load 233
+#define __NR_waitid 234
+#define __NR_add_key 235
+#define __NR_request_key 236
+#define __NR_keyctl 237
+#define __NR_ioprio_set 238
+#define __NR_ioprio_get 239
+#define __NR_inotify_init 240
+#define __NR_inotify_add_watch 241
+#define __NR_inotify_rm_watch 242
+#define __NR_openat 243
+#define __NR_mkdirat 244
+#define __NR_mknodat 245
+#define __NR_fchownat 246
+#define __NR_futimesat 247
+#define __NR_fstatat64 248
+#define __NR_unlinkat 249
+#define __NR_renameat 250
+#define __NR_linkat 251
+#define __NR_symlinkat 252
+#define __NR_readlinkat 253
+#define __NR_fchmodat 254
+#define __NR_faccessat 255
+#define __NR_pselect6 256
+#define __NR_ppoll 257
+#define __NR_unshare 258
+#define __NR_set_robust_list 259
+#define __NR_get_robust_list 260
+#define __NR_splice 261
+#define __NR_sync_file_range 262
+#define __NR_tee 263
+#define __NR_vmsplice 264
+#define __NR_epoll_pwait 265
+#define __NR_msgget 266
+#define __NR_msgsnd 267
+#define __NR_msgrcv 268
+#define __NR_msgctl 269
+#define __NR_semget 270
+#define __NR_semop 271
+#define __NR_semctl 272
+#define __NR_semtimedop 273
+#define __NR_shmat 274
+#define __NR_shmget 275
+#define __NR_shmdt 276
+#define __NR_shmctl 277
+#define __NR_utimensat 278
+#define __NR_signalfd 279
/* 280 was __NR_timerfd */
-#define __NR_eventfd 281
-#define __NR_setns 283
-#define __NR_pread64 284
-#define __NR_pwrite64 285
-#define __NR_timerfd_create 286
-#define __NR_fallocate 287
-#define __NR_timerfd_settime 288
-#define __NR_timerfd_gettime 289
-#define __NR_signalfd4 290
-#define __NR_eventfd2 291
-#define __NR_epoll_create1 292
-#define __NR_dup3 293
-#define __NR_pipe2 294
-#define __NR_inotify_init1 295
-#define __NR_preadv 296
-#define __NR_pwritev 297
-#define __NR_rt_tgsigqueueinfo 298
-#define __NR_perf_event_open 299
-#define __NR_recvmmsg 300
-#define __NR_fanotify_init 301
-#define __NR_fanotify_mark 302
-#define __NR_prlimit64 303
-#define __NR_name_to_handle_at 304
-#define __NR_open_by_handle_at 305
-#define __NR_clock_adjtime 306
-#define __NR_syncfs 307
-#define __NR_sendmmsg 308
-#define __NR_process_vm_readv 309
-#define __NR_process_vm_writev 310
-#define __NR_kcmp 311
-#define __NR_finit_module 312
-#define __NR_sched_setattr 313
-#define __NR_sched_getattr 314
-#define __NR_renameat2 315
-#define __NR_seccomp 316
-#define __NR_getrandom 317
-#define __NR_memfd_create 318
-#define __NR_bpf 319
-#define __NR_execveat 320
-#define __NR_accept4 321
-#define __NR_userfaultfd 322
-#define __NR_membarrier 323
-#define __NR_mlock2 324
+#define __NR_eventfd 281
+/* 282 was half-implemented __NR_recvmmsg */
+#define __NR_setns 283
+#define __NR_pread64 284
+#define __NR_pwrite64 285
+#define __NR_timerfd_create 286
+#define __NR_fallocate 287
+#define __NR_timerfd_settime 288
+#define __NR_timerfd_gettime 289
+#define __NR_signalfd4 290
+#define __NR_eventfd2 291
+#define __NR_epoll_create1 292
+#define __NR_dup3 293
+#define __NR_pipe2 294
+#define __NR_inotify_init1 295
+#define __NR_preadv 296
+#define __NR_pwritev 297
+#define __NR_rt_tgsigqueueinfo 298
+#define __NR_perf_event_open 299
+#define __NR_recvmmsg 300
+#define __NR_fanotify_init 301
+#define __NR_fanotify_mark 302
+#define __NR_prlimit64 303
+#define __NR_name_to_handle_at 304
+#define __NR_open_by_handle_at 305
+#define __NR_clock_adjtime 306
+#define __NR_syncfs 307
+#define __NR_sendmmsg 308
+#define __NR_process_vm_readv 309
+#define __NR_process_vm_writev 310
+#define __NR_kcmp 311
+#define __NR_finit_module 312
+#define __NR_sched_setattr 313
+#define __NR_sched_getattr 314
+#define __NR_renameat2 315
+#define __NR_seccomp 316
+#define __NR_getrandom 317
+#define __NR_memfd_create 318
+#define __NR_bpf 319
+#define __NR_execveat 320
+#define __NR_accept4 321
+#define __NR_userfaultfd 322
+#define __NR_membarrier 323
+#define __NR_mlock2 324
#define __NR_copy_file_range 325
+#define __NR_preadv2 326
+#define __NR_pwritev2 327
#endif /* _UAPI__ASM_AVR32_UNISTD_H */
diff --git a/arch/avr32/kernel/syscall-stubs.S b/arch/avr32/kernel/syscall-stubs.S
index cb3991552f14..cb256534ed92 100644
--- a/arch/avr32/kernel/syscall-stubs.S
+++ b/arch/avr32/kernel/syscall-stubs.S
@@ -133,3 +133,21 @@ __sys_copy_file_range:
call sys_copy_file_range
sub sp, -4
popm pc
+
+ .global __sys_preadv2
+ .type __sys_preadv2,@function
+__sys_preadv2:
+ pushm lr
+ st.w --sp, ARG6
+ call sys_preadv2
+ sub sp, -4
+ popm pc
+
+ .global __sys_pwritev2
+ .type __sys_pwritev2,@function
+__sys_pwritev2:
+ pushm lr
+ st.w --sp, ARG6
+ call sys_pwritev2
+ sub sp, -4
+ popm pc
diff --git a/arch/avr32/kernel/syscall_table.S b/arch/avr32/kernel/syscall_table.S
index 64d71a781fa8..7b348ba70e41 100644
--- a/arch/avr32/kernel/syscall_table.S
+++ b/arch/avr32/kernel/syscall_table.S
@@ -9,334 +9,336 @@
*/
.section .rodata,"a",@progbits
- .type sys_call_table,@object
- .global sys_call_table
- .align 2
+ .type sys_call_table,@object
+ .global sys_call_table
+ .align 2
sys_call_table:
- .long sys_restart_syscall
- .long sys_exit
- .long sys_fork
- .long sys_read
- .long sys_write
- .long sys_open /* 5 */
- .long sys_close
- .long sys_umask
- .long sys_creat
- .long sys_link
- .long sys_unlink /* 10 */
- .long sys_execve
- .long sys_chdir
- .long sys_time
- .long sys_mknod
- .long sys_chmod /* 15 */
- .long sys_chown
- .long sys_lchown
- .long sys_lseek
- .long sys_llseek
- .long sys_getpid /* 20 */
- .long sys_mount
- .long sys_umount
- .long sys_setuid
- .long sys_getuid
- .long sys_stime /* 25 */
- .long sys_ptrace
- .long sys_alarm
- .long sys_pause
- .long sys_utime
- .long sys_newstat /* 30 */
- .long sys_newfstat
- .long sys_newlstat
- .long sys_access
- .long sys_chroot
- .long sys_sync /* 35 */
- .long sys_fsync
- .long sys_kill
- .long sys_rename
- .long sys_mkdir
- .long sys_rmdir /* 40 */
- .long sys_dup
- .long sys_pipe
- .long sys_times
- .long sys_clone
- .long sys_brk /* 45 */
- .long sys_setgid
- .long sys_getgid
- .long sys_getcwd
- .long sys_geteuid
- .long sys_getegid /* 50 */
- .long sys_acct
- .long sys_setfsuid
- .long sys_setfsgid
- .long sys_ioctl
- .long sys_fcntl /* 55 */
- .long sys_setpgid
- .long sys_mremap
- .long sys_setresuid
- .long sys_getresuid
- .long sys_setreuid /* 60 */
- .long sys_setregid
- .long sys_ustat
- .long sys_dup2
- .long sys_getppid
- .long sys_getpgrp /* 65 */
- .long sys_setsid
- .long sys_rt_sigaction
- .long __sys_rt_sigreturn
- .long sys_rt_sigprocmask
- .long sys_rt_sigpending /* 70 */
- .long sys_rt_sigtimedwait
- .long sys_rt_sigqueueinfo
- .long __sys_rt_sigsuspend
- .long sys_sethostname
- .long sys_setrlimit /* 75 */
- .long sys_getrlimit
- .long sys_getrusage
- .long sys_gettimeofday
- .long sys_settimeofday
- .long sys_getgroups /* 80 */
- .long sys_setgroups
- .long sys_select
- .long sys_symlink
- .long sys_fchdir
- .long sys_readlink /* 85 */
- .long sys_pread64
- .long sys_pwrite64
- .long sys_swapon
- .long sys_reboot
- .long __sys_mmap2 /* 90 */
- .long sys_munmap
- .long sys_truncate
- .long sys_ftruncate
- .long sys_fchmod
- .long sys_fchown /* 95 */
- .long sys_getpriority
- .long sys_setpriority
- .long sys_wait4
- .long sys_statfs
- .long sys_fstatfs /* 100 */
- .long sys_vhangup
- .long sys_sigaltstack
- .long sys_syslog
- .long sys_setitimer
- .long sys_getitimer /* 105 */
- .long sys_swapoff
- .long sys_sysinfo
- .long sys_ni_syscall /* was sys_ipc briefly */
- .long sys_sendfile
- .long sys_setdomainname /* 110 */
- .long sys_newuname
- .long sys_adjtimex
- .long sys_mprotect
- .long sys_vfork
- .long sys_init_module /* 115 */
- .long sys_delete_module
- .long sys_quotactl
- .long sys_getpgid
- .long sys_bdflush
- .long sys_sysfs /* 120 */
- .long sys_personality
- .long sys_ni_syscall /* reserved for afs_syscall */
- .long sys_getdents
- .long sys_flock
- .long sys_msync /* 125 */
- .long sys_readv
- .long sys_writev
- .long sys_getsid
- .long sys_fdatasync
- .long sys_sysctl /* 130 */
- .long sys_mlock
- .long sys_munlock
- .long sys_mlockall
- .long sys_munlockall
- .long sys_sched_setparam /* 135 */
- .long sys_sched_getparam
- .long sys_sched_setscheduler
- .long sys_sched_getscheduler
- .long sys_sched_yield
- .long sys_sched_get_priority_max /* 140 */
- .long sys_sched_get_priority_min
- .long sys_sched_rr_get_interval
- .long sys_nanosleep
- .long sys_poll
- .long sys_ni_syscall /* 145 was nfsservctl */
- .long sys_setresgid
- .long sys_getresgid
- .long sys_prctl
- .long sys_socket
- .long sys_bind /* 150 */
- .long sys_connect
- .long sys_listen
- .long sys_accept
- .long sys_getsockname
- .long sys_getpeername /* 155 */
- .long sys_socketpair
- .long sys_send
- .long sys_recv
- .long __sys_sendto
- .long __sys_recvfrom /* 160 */
- .long sys_shutdown
- .long sys_setsockopt
- .long sys_getsockopt
- .long sys_sendmsg
- .long sys_recvmsg /* 165 */
- .long sys_truncate64
- .long sys_ftruncate64
- .long sys_stat64
- .long sys_lstat64
- .long sys_fstat64 /* 170 */
- .long sys_pivot_root
- .long sys_mincore
- .long sys_madvise
- .long sys_getdents64
- .long sys_fcntl64 /* 175 */
- .long sys_gettid
- .long sys_readahead
- .long sys_setxattr
- .long sys_lsetxattr
- .long sys_fsetxattr /* 180 */
- .long sys_getxattr
- .long sys_lgetxattr
- .long sys_fgetxattr
- .long sys_listxattr
- .long sys_llistxattr /* 185 */
- .long sys_flistxattr
- .long sys_removexattr
- .long sys_lremovexattr
- .long sys_fremovexattr
- .long sys_tkill /* 190 */
- .long sys_sendfile64
- .long sys_futex
- .long sys_sched_setaffinity
- .long sys_sched_getaffinity
- .long sys_capget /* 195 */
- .long sys_capset
- .long sys_io_setup
- .long sys_io_destroy
- .long sys_io_getevents
- .long sys_io_submit /* 200 */
- .long sys_io_cancel
- .long sys_fadvise64
- .long sys_exit_group
- .long sys_lookup_dcookie
- .long sys_epoll_create /* 205 */
- .long sys_epoll_ctl
- .long sys_epoll_wait
- .long sys_remap_file_pages
- .long sys_set_tid_address
- .long sys_timer_create /* 210 */
- .long sys_timer_settime
- .long sys_timer_gettime
- .long sys_timer_getoverrun
- .long sys_timer_delete
- .long sys_clock_settime /* 215 */
- .long sys_clock_gettime
- .long sys_clock_getres
- .long sys_clock_nanosleep
- .long sys_statfs64
- .long sys_fstatfs64 /* 220 */
- .long sys_tgkill
- .long sys_ni_syscall /* reserved for TUX */
- .long sys_utimes
- .long sys_fadvise64_64
- .long sys_cacheflush /* 225 */
- .long sys_ni_syscall /* sys_vserver */
- .long sys_mq_open
- .long sys_mq_unlink
- .long sys_mq_timedsend
- .long sys_mq_timedreceive /* 230 */
- .long sys_mq_notify
- .long sys_mq_getsetattr
- .long sys_kexec_load
- .long sys_waitid
- .long sys_add_key /* 235 */
- .long sys_request_key
- .long sys_keyctl
- .long sys_ioprio_set
- .long sys_ioprio_get
- .long sys_inotify_init /* 240 */
- .long sys_inotify_add_watch
- .long sys_inotify_rm_watch
- .long sys_openat
- .long sys_mkdirat
- .long sys_mknodat /* 245 */
- .long sys_fchownat
- .long sys_futimesat
- .long sys_fstatat64
- .long sys_unlinkat
- .long sys_renameat /* 250 */
- .long sys_linkat
- .long sys_symlinkat
- .long sys_readlinkat
- .long sys_fchmodat
- .long sys_faccessat /* 255 */
- .long __sys_pselect6
- .long sys_ppoll
- .long sys_unshare
- .long sys_set_robust_list
- .long sys_get_robust_list /* 260 */
- .long __sys_splice
- .long __sys_sync_file_range
- .long sys_tee
- .long sys_vmsplice
- .long __sys_epoll_pwait /* 265 */
- .long sys_msgget
- .long sys_msgsnd
- .long sys_msgrcv
- .long sys_msgctl
- .long sys_semget /* 270 */
- .long sys_semop
- .long sys_semctl
- .long sys_semtimedop
- .long sys_shmat
- .long sys_shmget /* 275 */
- .long sys_shmdt
- .long sys_shmctl
- .long sys_utimensat
- .long sys_signalfd
- .long sys_ni_syscall /* 280, was sys_timerfd */
- .long sys_eventfd
- .long sys_recvmmsg
- .long sys_setns
- .long sys_pread64
- .long sys_pwrite64 /* 285 */
- .long sys_timerfd_create
- .long __sys_fallocate
- .long sys_timerfd_settime
- .long sys_timerfd_gettime
- .long sys_signalfd4 /* 290 */
- .long sys_eventfd2
- .long sys_epoll_create1
- .long sys_dup3
- .long sys_pipe2
- .long sys_inotify_init1 /* 295 */
- .long sys_preadv
- .long sys_pwritev
- .long sys_rt_tgsigqueueinfo
- .long sys_perf_event_open
- .long sys_recvmmsg /* 300 */
- .long sys_fanotify_init
- .long __sys_fanotify_mark
- .long sys_prlimit64
- .long sys_name_to_handle_at
- .long sys_open_by_handle_at /* 305 */
- .long sys_clock_adjtime
- .long sys_syncfs
- .long sys_sendmmsg
- .long __sys_process_vm_readv
- .long __sys_process_vm_writev /* 310 */
- .long sys_kcmp
- .long sys_finit_module
- .long sys_sched_setattr
- .long sys_sched_getattr
- .long sys_renameat2 /* 315 */
- .long sys_seccomp
- .long sys_getrandom
- .long sys_memfd_create
- .long sys_bpf
- .long sys_execveat /* 320 */
- .long sys_accept4
- .long sys_userfaultfd
- .long sys_membarrier
- .long sys_mlock2
- .long __sys_copy_file_range /* 325 */
- .long sys_ni_syscall /* r8 is saturated at nr_syscalls */
+ .long sys_restart_syscall
+ .long sys_exit
+ .long sys_fork
+ .long sys_read
+ .long sys_write
+ .long sys_open
+ .long sys_close
+ .long sys_umask
+ .long sys_creat
+ .long sys_link
+ .long sys_unlink /* 10 */
+ .long sys_execve
+ .long sys_chdir
+ .long sys_time
+ .long sys_mknod
+ .long sys_chmod
+ .long sys_chown
+ .long sys_lchown
+ .long sys_lseek
+ .long sys_llseek
+ .long sys_getpid /* 20 */
+ .long sys_mount
+ .long sys_umount
+ .long sys_setuid
+ .long sys_getuid
+ .long sys_stime
+ .long sys_ptrace
+ .long sys_alarm
+ .long sys_pause
+ .long sys_utime
+ .long sys_newstat /* 30 */
+ .long sys_newfstat
+ .long sys_newlstat
+ .long sys_access
+ .long sys_chroot
+ .long sys_sync
+ .long sys_fsync
+ .long sys_kill
+ .long sys_rename
+ .long sys_mkdir
+ .long sys_rmdir /* 40 */
+ .long sys_dup
+ .long sys_pipe
+ .long sys_times
+ .long sys_clone
+ .long sys_brk
+ .long sys_setgid
+ .long sys_getgid
+ .long sys_getcwd
+ .long sys_geteuid
+ .long sys_getegid /* 50 */
+ .long sys_acct
+ .long sys_setfsuid
+ .long sys_setfsgid
+ .long sys_ioctl
+ .long sys_fcntl
+ .long sys_setpgid
+ .long sys_mremap
+ .long sys_setresuid
+ .long sys_getresuid
+ .long sys_setreuid /* 60 */
+ .long sys_setregid
+ .long sys_ustat
+ .long sys_dup2
+ .long sys_getppid
+ .long sys_getpgrp
+ .long sys_setsid
+ .long sys_rt_sigaction
+ .long __sys_rt_sigreturn
+ .long sys_rt_sigprocmask
+ .long sys_rt_sigpending /* 70 */
+ .long sys_rt_sigtimedwait
+ .long sys_rt_sigqueueinfo
+ .long __sys_rt_sigsuspend
+ .long sys_sethostname
+ .long sys_setrlimit
+ .long sys_getrlimit
+ .long sys_getrusage
+ .long sys_gettimeofday
+ .long sys_settimeofday
+ .long sys_getgroups /* 80 */
+ .long sys_setgroups
+ .long sys_select
+ .long sys_symlink
+ .long sys_fchdir
+ .long sys_readlink
+ .long sys_pread64
+ .long sys_pwrite64
+ .long sys_swapon
+ .long sys_reboot
+ .long __sys_mmap2 /* 90 */
+ .long sys_munmap
+ .long sys_truncate
+ .long sys_ftruncate
+ .long sys_fchmod
+ .long sys_fchown
+ .long sys_getpriority
+ .long sys_setpriority
+ .long sys_wait4
+ .long sys_statfs
+ .long sys_fstatfs /* 100 */
+ .long sys_vhangup
+ .long sys_sigaltstack
+ .long sys_syslog
+ .long sys_setitimer
+ .long sys_getitimer
+ .long sys_swapoff
+ .long sys_sysinfo
+ .long sys_ni_syscall /* was sys_ipc briefly */
+ .long sys_sendfile
+ .long sys_setdomainname /* 110 */
+ .long sys_newuname
+ .long sys_adjtimex
+ .long sys_mprotect
+ .long sys_vfork
+ .long sys_init_module
+ .long sys_delete_module
+ .long sys_quotactl
+ .long sys_getpgid
+ .long sys_bdflush
+ .long sys_sysfs /* 120 */
+ .long sys_personality
+ .long sys_ni_syscall /* reserved for afs_syscall */
+ .long sys_getdents
+ .long sys_flock
+ .long sys_msync
+ .long sys_readv
+ .long sys_writev
+ .long sys_getsid
+ .long sys_fdatasync
+ .long sys_sysctl /* 130 */
+ .long sys_mlock
+ .long sys_munlock
+ .long sys_mlockall
+ .long sys_munlockall
+ .long sys_sched_setparam
+ .long sys_sched_getparam
+ .long sys_sched_setscheduler
+ .long sys_sched_getscheduler
+ .long sys_sched_yield
+ .long sys_sched_get_priority_max /* 140 */
+ .long sys_sched_get_priority_min
+ .long sys_sched_rr_get_interval
+ .long sys_nanosleep
+ .long sys_poll
+ .long sys_ni_syscall /* 145 was nfsservctl */
+ .long sys_setresgid
+ .long sys_getresgid
+ .long sys_prctl
+ .long sys_socket
+ .long sys_bind /* 150 */
+ .long sys_connect
+ .long sys_listen
+ .long sys_accept
+ .long sys_getsockname
+ .long sys_getpeername
+ .long sys_socketpair
+ .long sys_send
+ .long sys_recv
+ .long __sys_sendto
+ .long __sys_recvfrom /* 160 */
+ .long sys_shutdown
+ .long sys_setsockopt
+ .long sys_getsockopt
+ .long sys_sendmsg
+ .long sys_recvmsg
+ .long sys_truncate64
+ .long sys_ftruncate64
+ .long sys_stat64
+ .long sys_lstat64
+ .long sys_fstat64 /* 170 */
+ .long sys_pivot_root
+ .long sys_mincore
+ .long sys_madvise
+ .long sys_getdents64
+ .long sys_fcntl64
+ .long sys_gettid
+ .long sys_readahead
+ .long sys_setxattr
+ .long sys_lsetxattr
+ .long sys_fsetxattr /* 180 */
+ .long sys_getxattr
+ .long sys_lgetxattr
+ .long sys_fgetxattr
+ .long sys_listxattr
+ .long sys_llistxattr
+ .long sys_flistxattr
+ .long sys_removexattr
+ .long sys_lremovexattr
+ .long sys_fremovexattr
+ .long sys_tkill /* 190 */
+ .long sys_sendfile64
+ .long sys_futex
+ .long sys_sched_setaffinity
+ .long sys_sched_getaffinity
+ .long sys_capget
+ .long sys_capset
+ .long sys_io_setup
+ .long sys_io_destroy
+ .long sys_io_getevents
+ .long sys_io_submit /* 200 */
+ .long sys_io_cancel
+ .long sys_fadvise64
+ .long sys_exit_group
+ .long sys_lookup_dcookie
+ .long sys_epoll_create
+ .long sys_epoll_ctl
+ .long sys_epoll_wait
+ .long sys_remap_file_pages
+ .long sys_set_tid_address
+ .long sys_timer_create /* 210 */
+ .long sys_timer_settime
+ .long sys_timer_gettime
+ .long sys_timer_getoverrun
+ .long sys_timer_delete
+ .long sys_clock_settime
+ .long sys_clock_gettime
+ .long sys_clock_getres
+ .long sys_clock_nanosleep
+ .long sys_statfs64
+ .long sys_fstatfs64 /* 220 */
+ .long sys_tgkill
+ .long sys_ni_syscall /* reserved for TUX */
+ .long sys_utimes
+ .long sys_fadvise64_64
+ .long sys_cacheflush
+ .long sys_ni_syscall /* sys_vserver */
+ .long sys_mq_open
+ .long sys_mq_unlink
+ .long sys_mq_timedsend
+ .long sys_mq_timedreceive /* 230 */
+ .long sys_mq_notify
+ .long sys_mq_getsetattr
+ .long sys_kexec_load
+ .long sys_waitid
+ .long sys_add_key
+ .long sys_request_key
+ .long sys_keyctl
+ .long sys_ioprio_set
+ .long sys_ioprio_get
+ .long sys_inotify_init /* 240 */
+ .long sys_inotify_add_watch
+ .long sys_inotify_rm_watch
+ .long sys_openat
+ .long sys_mkdirat
+ .long sys_mknodat
+ .long sys_fchownat
+ .long sys_futimesat
+ .long sys_fstatat64
+ .long sys_unlinkat
+ .long sys_renameat /* 250 */
+ .long sys_linkat
+ .long sys_symlinkat
+ .long sys_readlinkat
+ .long sys_fchmodat
+ .long sys_faccessat
+ .long __sys_pselect6
+ .long sys_ppoll
+ .long sys_unshare
+ .long sys_set_robust_list
+ .long sys_get_robust_list /* 260 */
+ .long __sys_splice
+ .long __sys_sync_file_range
+ .long sys_tee
+ .long sys_vmsplice
+ .long __sys_epoll_pwait
+ .long sys_msgget
+ .long sys_msgsnd
+ .long sys_msgrcv
+ .long sys_msgctl
+ .long sys_semget /* 270 */
+ .long sys_semop
+ .long sys_semctl
+ .long sys_semtimedop
+ .long sys_shmat
+ .long sys_shmget
+ .long sys_shmdt
+ .long sys_shmctl
+ .long sys_utimensat
+ .long sys_signalfd
+ .long sys_ni_syscall /* 280, was sys_timerfd */
+ .long sys_eventfd
+ .long sys_ni_syscall /* 282, was half-implemented recvmmsg */
+ .long sys_setns
+ .long sys_pread64
+ .long sys_pwrite64
+ .long sys_timerfd_create
+ .long __sys_fallocate
+ .long sys_timerfd_settime
+ .long sys_timerfd_gettime
+ .long sys_signalfd4 /* 290 */
+ .long sys_eventfd2
+ .long sys_epoll_create1
+ .long sys_dup3
+ .long sys_pipe2
+ .long sys_inotify_init1
+ .long sys_preadv
+ .long sys_pwritev
+ .long sys_rt_tgsigqueueinfo
+ .long sys_perf_event_open
+ .long sys_recvmmsg /* 300 */
+ .long sys_fanotify_init
+ .long __sys_fanotify_mark
+ .long sys_prlimit64
+ .long sys_name_to_handle_at
+ .long sys_open_by_handle_at
+ .long sys_clock_adjtime
+ .long sys_syncfs
+ .long sys_sendmmsg
+ .long __sys_process_vm_readv
+ .long __sys_process_vm_writev /* 310 */
+ .long sys_kcmp
+ .long sys_finit_module
+ .long sys_sched_setattr
+ .long sys_sched_getattr
+ .long sys_renameat2
+ .long sys_seccomp
+ .long sys_getrandom
+ .long sys_memfd_create
+ .long sys_bpf
+ .long sys_execveat /* 320 */
+ .long sys_accept4
+ .long sys_userfaultfd
+ .long sys_membarrier
+ .long sys_mlock2
+ .long __sys_copy_file_range
+ .long __sys_preadv2
+ .long __sys_pwritev2
+ .long sys_ni_syscall /* r8 is saturated at nr_syscalls */
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
index 83c2a0021b56..13d3fc4270b7 100644
--- a/arch/avr32/mach-at32ap/pio.c
+++ b/arch/avr32/mach-at32ap/pio.c
@@ -435,7 +435,7 @@ void __init at32_init_pio(struct platform_device *pdev)
struct resource *regs;
struct pio_device *pio;
- if (pdev->id > MAX_NR_PIO_DEVICES) {
+ if (pdev->id >= MAX_NR_PIO_DEVICES) {
dev_err(&pdev->dev, "only %d PIO devices supported\n",
MAX_NR_PIO_DEVICES);
return;
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index c03533937a9f..a4b7edac8f10 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -134,7 +134,7 @@ good_area:
* sure we exit gracefully rather than endlessly redo the
* fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 170d786807c4..6355e97d22b9 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -453,29 +453,13 @@ static struct pmu pmu = {
.read = bfin_pmu_read,
};
-static void bfin_pmu_setup(int cpu)
+static int bfin_pmu_prepare_cpu(unsigned int cpu)
{
struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
+ bfin_write_PFCTL(0);
memset(cpuhw, 0, sizeof(struct cpu_hw_events));
-}
-
-static int
-bfin_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- bfin_write_PFCTL(0);
- bfin_pmu_setup(cpu);
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
+ return 0;
}
static int __init bfin_pmu_init(void)
@@ -491,8 +475,8 @@ static int __init bfin_pmu_init(void)
ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
if (!ret)
- perf_cpu_notifier(bfin_pmu_notifier);
-
+ cpuhp_setup_state(CPUHP_PERF_BFIN, "PERF_BFIN",
+ bfin_pmu_prepare_cpu, NULL);
return ret;
}
early_initcall(bfin_pmu_init);
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index aad5d7416886..9231e5a72b93 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -1002,14 +1002,12 @@ static struct adv7842_output_format adv7842_opf[] = {
{
.op_ch_sel = ADV7842_OP_CH_SEL_BRG,
.op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_8,
- .op_656_range = 1,
.blank_data = 1,
.insert_av_codes = 1,
},
{
.op_ch_sel = ADV7842_OP_CH_SEL_RGB,
.op_format_sel = ADV7842_OP_FORMAT_SEL_SDR_ITU656_16,
- .op_656_range = 1,
.blank_data = 1,
},
};
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 3066d40a6db1..112ef26c7f2e 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -168,7 +168,7 @@ retry:
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 61d99767fe16..614a46c413d2 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -164,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, ear0, flags);
+ fault = handle_mm_fault(vma, ear0, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 57298e7b4867..1941e4baaee6 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -8,8 +8,7 @@ config HEXAGON
# select HAVE_REGS_AND_STACK_ACCESS_API
# select HAVE_HW_BREAKPOINT if PERF_EVENTS
# select ARCH_HAS_CPU_IDLE_WAIT
- # select ARCH_WANT_OPTIONAL_GPIOLIB
- # select ARCH_REQUIRE_GPIOLIB
+ # select GPIOLIB
# select HAVE_CLK
# select GENERIC_PENDING_IRQ if SMP
select GENERIC_ATOMIC64
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 8704c9320032..bd7c251e2bce 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -101,7 +101,7 @@ good_area:
break;
}
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index e109ee95e919..6a15083cc366 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -39,7 +39,6 @@ config IA64
select GENERIC_PENDING_IRQ if SMP
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_LEGACY
- select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select GENERIC_IOMAP
select GENERIC_SMP_IDLE_THREAD
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index aa0fdf125aba..a3d0211970e9 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -140,6 +140,9 @@ static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus)
}
}
}
+
+extern void acpi_numa_fixup(void);
+
#endif /* CONFIG_ACPI_NUMA */
#endif /*__KERNEL__*/
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 39d64e0df1de..77e541cf0e5d 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -205,17 +205,18 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
* must be delayed until after the TLB has been flushed (see comments at the beginning of
* this file).
*/
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
+ if (tlb->nr == tlb->max)
+ return true;
+
tlb->need_flush = 1;
if (!tlb->nr && tlb->pages == tlb->local)
__tlb_alloc_page(tlb);
tlb->pages[tlb->nr++] = page;
- VM_BUG_ON(tlb->nr > tlb->max);
-
- return tlb->max - tlb->nr;
+ return false;
}
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -235,8 +236,28 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
- if (!__tlb_remove_page(tlb, page))
+ if (__tlb_remove_page(tlb, page)) {
tlb_flush_mmu(tlb);
+ __tlb_remove_page(tlb, page);
+ }
+}
+
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+ struct page *page)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return tlb_remove_page(tlb, page);
}
/*
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index b1698bc042c8..92b7bc956795 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -524,7 +524,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return 0;
}
-void __init acpi_numa_arch_fixup(void)
+void __init acpi_numa_fixup(void)
{
int i, j, node_from, node_to;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 2029a38a72ae..afddb3e80a29 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -552,6 +552,7 @@ setup_arch (char **cmdline_p)
early_acpi_boot_init();
# ifdef CONFIG_ACPI_NUMA
acpi_numa_init();
+ acpi_numa_fixup();
# ifdef CONFIG_ACPI_HOTPLUG_CPU
prefill_possible_map();
# endif
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 70b40d1205a6..fa6ad95e992e 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -159,7 +159,7 @@ retry:
* sure we exit gracefully rather than endlessly redo the
* fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c
index b727e693c805..23f26f4adfff 100644
--- a/arch/m32r/kernel/m32r_ksyms.c
+++ b/arch/m32r/kernel/m32r_ksyms.c
@@ -41,6 +41,9 @@ EXPORT_SYMBOL(cpu_data);
EXPORT_SYMBOL(smp_flush_tlb_page);
#endif
+extern int __ucmpdi2(unsigned long long a, unsigned long long b);
+EXPORT_SYMBOL(__ucmpdi2);
+
/* compiler generated symbol */
extern void __ashldi3(void);
extern void __ashrdi3(void);
diff --git a/arch/m32r/lib/Makefile b/arch/m32r/lib/Makefile
index d16b4e40d1ae..5889eb9610b5 100644
--- a/arch/m32r/lib/Makefile
+++ b/arch/m32r/lib/Makefile
@@ -3,5 +3,5 @@
#
lib-y := checksum.o ashxdi3.o memset.o memcpy.o \
- delay.o strlen.o usercopy.o csum_partial_copy.o
-
+ delay.o strlen.o usercopy.o csum_partial_copy.o \
+ ucmpdi2.o
diff --git a/arch/m32r/lib/libgcc.h b/arch/m32r/lib/libgcc.h
new file mode 100644
index 000000000000..267aa435bc35
--- /dev/null
+++ b/arch/m32r/lib/libgcc.h
@@ -0,0 +1,23 @@
+#ifndef __ASM_LIBGCC_H
+#define __ASM_LIBGCC_H
+
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
+struct DWstruct {
+ int high, low;
+};
+#elif defined(__LITTLE_ENDIAN)
+struct DWstruct {
+ int low, high;
+};
+#else
+#error I feel sick.
+#endif
+
+typedef union {
+ struct DWstruct s;
+ long long ll;
+} DWunion;
+
+#endif /* __ASM_LIBGCC_H */
diff --git a/arch/m32r/lib/ucmpdi2.c b/arch/m32r/lib/ucmpdi2.c
new file mode 100644
index 000000000000..9d3c682c89b5
--- /dev/null
+++ b/arch/m32r/lib/ucmpdi2.c
@@ -0,0 +1,17 @@
+#include "libgcc.h"
+
+int __ucmpdi2(unsigned long long a, unsigned long long b)
+{
+ const DWunion au = {.ll = a};
+ const DWunion bu = {.ll = b};
+
+ if ((unsigned int)au.s.high < (unsigned int)bu.s.high)
+ return 0;
+ else if ((unsigned int)au.s.high > (unsigned int)bu.s.high)
+ return 2;
+ if ((unsigned int)au.s.low < (unsigned int)bu.s.low)
+ return 0;
+ else if ((unsigned int)au.s.low > (unsigned int)bu.s.low)
+ return 2;
+ return 1;
+}
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 8f9875b7933d..a3785d3644c2 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -196,7 +196,7 @@ good_area:
*/
addr = (address & PAGE_MASK);
set_thread_fault_code(error_code);
- fault = handle_mm_fault(mm, vma, addr, flags);
+ fault = handle_mm_fault(vma, addr, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 6a94cdd0c830..bd66a0b20c6b 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -136,7 +136,7 @@ good_area:
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
pr_debug("handle_mm_fault returns %d\n", fault);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 33a365f924be..052cba23708c 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -806,25 +806,16 @@ static struct metag_pmu _metag_pmu = {
};
/* PMU CPU hotplug notifier */
-static int metag_pmu_cpu_notify(struct notifier_block *b, unsigned long action,
- void *hcpu)
+static int metag_pmu_starting_cpu(unsigned int cpu)
{
- unsigned int cpu = (unsigned int)hcpu;
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
- if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
- return NOTIFY_DONE;
-
memset(cpuc, 0, sizeof(struct cpu_hw_events));
raw_spin_lock_init(&cpuc->pmu_lock);
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block metag_pmu_notifier = {
- .notifier_call = metag_pmu_cpu_notify,
-};
-
/* PMU Initialisation */
static int __init init_hw_perf_events(void)
{
@@ -876,16 +867,13 @@ static int __init init_hw_perf_events(void)
metag_out32(0, PERF_COUNT(0));
metag_out32(0, PERF_COUNT(1));
- for_each_possible_cpu(cpu) {
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ cpuhp_setup_state(CPUHP_AP_PERF_METAG_STARTING,
+ "AP_PERF_METAG_STARTING", metag_pmu_starting_cpu,
+ NULL);
- memset(cpuc, 0, sizeof(struct cpu_hw_events));
- raw_spin_lock_init(&cpuc->pmu_lock);
- }
-
- register_cpu_notifier(&metag_pmu_notifier);
ret = perf_pmu_register(&pmu, metag_pmu->name, PERF_TYPE_RAW);
-out:
+ if (ret)
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_METAG_STARTING);
return ret;
}
early_initcall(init_hw_perf_events);
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index f57edca63609..372783a67dda 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -133,7 +133,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return 0;
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 636e0720fb20..86f65721e629 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -3,7 +3,6 @@ config MICROBLAZE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_WANT_IPC_PARSE_VERSION
- select ARCH_WANT_OPTIONAL_GPIOLIB
select BUILDTIME_EXTABLE_SORT
select CLKSRC_OF
select CLONE_BACKWARDS3
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 177dfc003643..abb678ccde6f 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -216,7 +216,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 7f50dd67aa8d..65f140e1e872 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -146,7 +146,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_BACKLIGHT=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index a9d433a17fcf..799c4338fd5e 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -147,7 +147,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_BACKLIGHT=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 2774ef064505..31846000530f 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -152,7 +152,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_BACKLIGHT=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 9bbd2218f0bf..a79107da0675 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -146,7 +146,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_BACKLIGHT=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
diff --git a/arch/mips/configs/rbtx49xx_defconfig b/arch/mips/configs/rbtx49xx_defconfig
index f8bf9b4c1343..43d55e5abacb 100644
--- a/arch/mips/configs/rbtx49xx_defconfig
+++ b/arch/mips/configs/rbtx49xx_defconfig
@@ -90,7 +90,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_GPIO=y
CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_INTF_DEV_UIE_EMUL=y
diff --git a/arch/mips/include/asm/octeon/cvmx-mpi-defs.h b/arch/mips/include/asm/octeon/cvmx-mpi-defs.h
deleted file mode 100644
index 4615b102625b..000000000000
--- a/arch/mips/include/asm/octeon/cvmx-mpi-defs.h
+++ /dev/null
@@ -1,328 +0,0 @@
-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
-
-#ifndef __CVMX_MPI_DEFS_H__
-#define __CVMX_MPI_DEFS_H__
-
-#define CVMX_MPI_CFG (CVMX_ADD_IO_SEG(0x0001070000001000ull))
-#define CVMX_MPI_DATX(offset) (CVMX_ADD_IO_SEG(0x0001070000001080ull) + ((offset) & 15) * 8)
-#define CVMX_MPI_STS (CVMX_ADD_IO_SEG(0x0001070000001008ull))
-#define CVMX_MPI_TX (CVMX_ADD_IO_SEG(0x0001070000001010ull))
-
-union cvmx_mpi_cfg {
- uint64_t u64;
- struct cvmx_mpi_cfg_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_29_63:35;
- uint64_t clkdiv:13;
- uint64_t csena3:1;
- uint64_t csena2:1;
- uint64_t csena1:1;
- uint64_t csena0:1;
- uint64_t cslate:1;
- uint64_t tritx:1;
- uint64_t idleclks:2;
- uint64_t cshi:1;
- uint64_t csena:1;
- uint64_t int_ena:1;
- uint64_t lsbfirst:1;
- uint64_t wireor:1;
- uint64_t clk_cont:1;
- uint64_t idlelo:1;
- uint64_t enable:1;
-#else
- uint64_t enable:1;
- uint64_t idlelo:1;
- uint64_t clk_cont:1;
- uint64_t wireor:1;
- uint64_t lsbfirst:1;
- uint64_t int_ena:1;
- uint64_t csena:1;
- uint64_t cshi:1;
- uint64_t idleclks:2;
- uint64_t tritx:1;
- uint64_t cslate:1;
- uint64_t csena0:1;
- uint64_t csena1:1;
- uint64_t csena2:1;
- uint64_t csena3:1;
- uint64_t clkdiv:13;
- uint64_t reserved_29_63:35;
-#endif
- } s;
- struct cvmx_mpi_cfg_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_29_63:35;
- uint64_t clkdiv:13;
- uint64_t reserved_12_15:4;
- uint64_t cslate:1;
- uint64_t tritx:1;
- uint64_t idleclks:2;
- uint64_t cshi:1;
- uint64_t csena:1;
- uint64_t int_ena:1;
- uint64_t lsbfirst:1;
- uint64_t wireor:1;
- uint64_t clk_cont:1;
- uint64_t idlelo:1;
- uint64_t enable:1;
-#else
- uint64_t enable:1;
- uint64_t idlelo:1;
- uint64_t clk_cont:1;
- uint64_t wireor:1;
- uint64_t lsbfirst:1;
- uint64_t int_ena:1;
- uint64_t csena:1;
- uint64_t cshi:1;
- uint64_t idleclks:2;
- uint64_t tritx:1;
- uint64_t cslate:1;
- uint64_t reserved_12_15:4;
- uint64_t clkdiv:13;
- uint64_t reserved_29_63:35;
-#endif
- } cn30xx;
- struct cvmx_mpi_cfg_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_29_63:35;
- uint64_t clkdiv:13;
- uint64_t reserved_11_15:5;
- uint64_t tritx:1;
- uint64_t idleclks:2;
- uint64_t cshi:1;
- uint64_t csena:1;
- uint64_t int_ena:1;
- uint64_t lsbfirst:1;
- uint64_t wireor:1;
- uint64_t clk_cont:1;
- uint64_t idlelo:1;
- uint64_t enable:1;
-#else
- uint64_t enable:1;
- uint64_t idlelo:1;
- uint64_t clk_cont:1;
- uint64_t wireor:1;
- uint64_t lsbfirst:1;
- uint64_t int_ena:1;
- uint64_t csena:1;
- uint64_t cshi:1;
- uint64_t idleclks:2;
- uint64_t tritx:1;
- uint64_t reserved_11_15:5;
- uint64_t clkdiv:13;
- uint64_t reserved_29_63:35;
-#endif
- } cn31xx;
- struct cvmx_mpi_cfg_cn30xx cn50xx;
- struct cvmx_mpi_cfg_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_29_63:35;
- uint64_t clkdiv:13;
- uint64_t reserved_14_15:2;
- uint64_t csena1:1;
- uint64_t csena0:1;
- uint64_t cslate:1;
- uint64_t tritx:1;
- uint64_t idleclks:2;
- uint64_t cshi:1;
- uint64_t reserved_6_6:1;
- uint64_t int_ena:1;
- uint64_t lsbfirst:1;
- uint64_t wireor:1;
- uint64_t clk_cont:1;
- uint64_t idlelo:1;
- uint64_t enable:1;
-#else
- uint64_t enable:1;
- uint64_t idlelo:1;
- uint64_t clk_cont:1;
- uint64_t wireor:1;
- uint64_t lsbfirst:1;
- uint64_t int_ena:1;
- uint64_t reserved_6_6:1;
- uint64_t cshi:1;
- uint64_t idleclks:2;
- uint64_t tritx:1;
- uint64_t cslate:1;
- uint64_t csena0:1;
- uint64_t csena1:1;
- uint64_t reserved_14_15:2;
- uint64_t clkdiv:13;
- uint64_t reserved_29_63:35;
-#endif
- } cn61xx;
- struct cvmx_mpi_cfg_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_29_63:35;
- uint64_t clkdiv:13;
- uint64_t csena3:1;
- uint64_t csena2:1;
- uint64_t reserved_12_13:2;
- uint64_t cslate:1;
- uint64_t tritx:1;
- uint64_t idleclks:2;
- uint64_t cshi:1;
- uint64_t reserved_6_6:1;
- uint64_t int_ena:1;
- uint64_t lsbfirst:1;
- uint64_t wireor:1;
- uint64_t clk_cont:1;
- uint64_t idlelo:1;
- uint64_t enable:1;
-#else
- uint64_t enable:1;
- uint64_t idlelo:1;
- uint64_t clk_cont:1;
- uint64_t wireor:1;
- uint64_t lsbfirst:1;
- uint64_t int_ena:1;
- uint64_t reserved_6_6:1;
- uint64_t cshi:1;
- uint64_t idleclks:2;
- uint64_t tritx:1;
- uint64_t cslate:1;
- uint64_t reserved_12_13:2;
- uint64_t csena2:1;
- uint64_t csena3:1;
- uint64_t clkdiv:13;
- uint64_t reserved_29_63:35;
-#endif
- } cn66xx;
- struct cvmx_mpi_cfg_cn61xx cnf71xx;
-};
-
-union cvmx_mpi_datx {
- uint64_t u64;
- struct cvmx_mpi_datx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_8_63:56;
- uint64_t data:8;
-#else
- uint64_t data:8;
- uint64_t reserved_8_63:56;
-#endif
- } s;
- struct cvmx_mpi_datx_s cn30xx;
- struct cvmx_mpi_datx_s cn31xx;
- struct cvmx_mpi_datx_s cn50xx;
- struct cvmx_mpi_datx_s cn61xx;
- struct cvmx_mpi_datx_s cn66xx;
- struct cvmx_mpi_datx_s cnf71xx;
-};
-
-union cvmx_mpi_sts {
- uint64_t u64;
- struct cvmx_mpi_sts_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_13_63:51;
- uint64_t rxnum:5;
- uint64_t reserved_1_7:7;
- uint64_t busy:1;
-#else
- uint64_t busy:1;
- uint64_t reserved_1_7:7;
- uint64_t rxnum:5;
- uint64_t reserved_13_63:51;
-#endif
- } s;
- struct cvmx_mpi_sts_s cn30xx;
- struct cvmx_mpi_sts_s cn31xx;
- struct cvmx_mpi_sts_s cn50xx;
- struct cvmx_mpi_sts_s cn61xx;
- struct cvmx_mpi_sts_s cn66xx;
- struct cvmx_mpi_sts_s cnf71xx;
-};
-
-union cvmx_mpi_tx {
- uint64_t u64;
- struct cvmx_mpi_tx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_22_63:42;
- uint64_t csid:2;
- uint64_t reserved_17_19:3;
- uint64_t leavecs:1;
- uint64_t reserved_13_15:3;
- uint64_t txnum:5;
- uint64_t reserved_5_7:3;
- uint64_t totnum:5;
-#else
- uint64_t totnum:5;
- uint64_t reserved_5_7:3;
- uint64_t txnum:5;
- uint64_t reserved_13_15:3;
- uint64_t leavecs:1;
- uint64_t reserved_17_19:3;
- uint64_t csid:2;
- uint64_t reserved_22_63:42;
-#endif
- } s;
- struct cvmx_mpi_tx_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_17_63:47;
- uint64_t leavecs:1;
- uint64_t reserved_13_15:3;
- uint64_t txnum:5;
- uint64_t reserved_5_7:3;
- uint64_t totnum:5;
-#else
- uint64_t totnum:5;
- uint64_t reserved_5_7:3;
- uint64_t txnum:5;
- uint64_t reserved_13_15:3;
- uint64_t leavecs:1;
- uint64_t reserved_17_63:47;
-#endif
- } cn30xx;
- struct cvmx_mpi_tx_cn30xx cn31xx;
- struct cvmx_mpi_tx_cn30xx cn50xx;
- struct cvmx_mpi_tx_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
- uint64_t reserved_21_63:43;
- uint64_t csid:1;
- uint64_t reserved_17_19:3;
- uint64_t leavecs:1;
- uint64_t reserved_13_15:3;
- uint64_t txnum:5;
- uint64_t reserved_5_7:3;
- uint64_t totnum:5;
-#else
- uint64_t totnum:5;
- uint64_t reserved_5_7:3;
- uint64_t txnum:5;
- uint64_t reserved_13_15:3;
- uint64_t leavecs:1;
- uint64_t reserved_17_19:3;
- uint64_t csid:1;
- uint64_t reserved_21_63:43;
-#endif
- } cn61xx;
- struct cvmx_mpi_tx_s cn66xx;
- struct cvmx_mpi_tx_cn61xx cnf71xx;
-};
-
-#endif
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 4b88fa031891..9560ad731120 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -153,7 +153,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/mips/oprofile/op_model_loongson3.c b/arch/mips/oprofile/op_model_loongson3.c
index 8bcf7fc40f0d..85f3ee4ab456 100644
--- a/arch/mips/oprofile/op_model_loongson3.c
+++ b/arch/mips/oprofile/op_model_loongson3.c
@@ -168,33 +168,26 @@ static int loongson3_perfcount_handler(void)
return handled;
}
-static int loongson3_cpu_callback(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int loongson3_starting_cpu(unsigned int cpu)
{
- switch (action) {
- case CPU_STARTING:
- case CPU_STARTING_FROZEN:
- write_c0_perflo1(reg.control1);
- write_c0_perflo2(reg.control2);
- break;
- case CPU_DYING:
- case CPU_DYING_FROZEN:
- write_c0_perflo1(0xc0000000);
- write_c0_perflo2(0x40000000);
- break;
- }
-
- return NOTIFY_OK;
+ write_c0_perflo1(reg.control1);
+ write_c0_perflo2(reg.control2);
+ return 0;
}
-static struct notifier_block loongson3_notifier_block = {
- .notifier_call = loongson3_cpu_callback
-};
+static int loongson3_dying_cpu(unsigned int cpu)
+{
+ write_c0_perflo1(0xc0000000);
+ write_c0_perflo2(0x40000000);
+ return 0;
+}
static int __init loongson3_init(void)
{
on_each_cpu(reset_counters, NULL, 1);
- register_hotcpu_notifier(&loongson3_notifier_block);
+ cpuhp_setup_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
+ "AP_MIPS_OP_LOONGSON3_STARTING",
+ loongson3_starting_cpu, loongson3_dying_cpu);
save_perf_irq = perf_irq;
perf_irq = loongson3_perfcount_handler;
@@ -204,7 +197,7 @@ static int __init loongson3_init(void)
static void loongson3_exit(void)
{
on_each_cpu(reset_counters, NULL, 1);
- unregister_hotcpu_notifier(&loongson3_notifier_block);
+ cpuhp_remove_state_nocalls(CPUHP_AP_MIPS_OP_LOONGSON3_STARTING);
perf_irq = save_perf_irq;
}
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 108f8a8d1640..ada92db92f87 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -727,7 +727,7 @@ void __init txx9_iocled_init(unsigned long baseaddr,
int i;
static char *default_triggers[] __initdata = {
"heartbeat",
- "ide-disk",
+ "disk-activity",
"nand-disk",
NULL,
};
diff --git a/arch/mips/txx9/rbtx4939/setup.c b/arch/mips/txx9/rbtx4939/setup.c
index 37030409745c..8b937300fb7f 100644
--- a/arch/mips/txx9/rbtx4939/setup.c
+++ b/arch/mips/txx9/rbtx4939/setup.c
@@ -215,7 +215,7 @@ static int __init rbtx4939_led_probe(struct platform_device *pdev)
int i;
static char *default_triggers[] __initdata = {
"heartbeat",
- "ide-disk",
+ "disk-activity",
"nand-disk",
};
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 4a1d181ed32f..f23781d6bbb3 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -254,7 +254,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index b51878b0c6b8..affc4eb3f89e 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -131,7 +131,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 142cb057c41b..489e7f909286 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -10,7 +10,7 @@ config OPENRISC
select IRQ_DOMAIN
select HANDLE_DOMAIN_IRQ
select HAVE_MEMBLOCK
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select HAVE_ARCH_TRACEHOOK
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_PROBE
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 230ac20ae794..e94cd225e816 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -163,7 +163,7 @@ good_area:
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index 5b04d703a924..8688ba7f5966 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -214,7 +214,7 @@ CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
CONFIG_DMADEVICES=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index e945c08892fa..7e0792658952 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -231,7 +231,7 @@ CONFIG_LEDS_CLASS=y
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_LEDS_TRIGGER_ONESHOT=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=m
CONFIG_LEDS_TRIGGER_BACKLIGHT=m
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 16dbe81c97c9..163af2c31d76 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -239,7 +239,7 @@ good_area:
* fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 0a9d439bcda6..d111044f41a2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -98,7 +98,6 @@ config PPC
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select SYSCTL_EXCEPTION_TRACE
- select ARCH_WANT_OPTIONAL_GPIOLIB
select VIRT_TO_BUS if !PPC64
select HAVE_IDE
select HAVE_IOREMAP_PROT
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 43546844ea5a..ca5139ee5074 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -472,7 +472,7 @@
hdd {
gpios = <&mcu_pio 1 0>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
};
};
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 2b4b6532d69c..e32613963ab0 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -496,7 +496,7 @@
hdd {
gpios = <&mcu_pio 1 0>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
};
};
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index 74b6a535a413..71842fcd621f 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -480,7 +480,7 @@
hdd {
gpios = <&mcu_pio 1 0>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
};
};
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index 3b5cbac85368..e442a29b2fe0 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -446,7 +446,7 @@
hdd {
gpios = <&mcu_pio 1 0>;
- linux,default-trigger = "ide-disk";
+ linux,default-trigger = "disk-activity";
};
};
};
diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig
index ea8705ffcd76..3f6c9a6c815c 100644
--- a/arch/powerpc/configs/pmac32_defconfig
+++ b/arch/powerpc/configs/pmac32_defconfig
@@ -158,7 +158,7 @@ CONFIG_ADB=y
CONFIG_ADB_CUDA=y
CONFIG_ADB_PMU=y
CONFIG_ADB_PMU_LED=y
-CONFIG_ADB_PMU_LED_IDE=y
+CONFIG_ADB_PMU_LED_DISK=y
CONFIG_PMAC_APM_EMU=m
CONFIG_PMAC_MEDIABAY=y
CONFIG_PMAC_BACKLIGHT=y
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 99ccbebabfd3..1dde0be2be30 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -442,7 +442,7 @@ CONFIG_ADB=y
CONFIG_ADB_CUDA=y
CONFIG_ADB_PMU=y
CONFIG_ADB_PMU_LED=y
-CONFIG_ADB_PMU_LED_IDE=y
+CONFIG_ADB_PMU_LED_DISK=y
CONFIG_PMAC_APM_EMU=y
CONFIG_PMAC_MEDIABAY=y
CONFIG_PMAC_BACKLIGHT=y
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index ee09e99097f0..9bd87f269d6d 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -71,10 +71,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
bool *is_thp, unsigned *shift)
{
- if (!arch_irqs_disabled()) {
- pr_info("%s called with irq enabled\n", __func__);
- dump_stack();
- }
+ VM_WARN(!arch_irqs_disabled(),
+ "%s called with irq enabled\n", __func__);
return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
}
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 856f9a7944cd..64174bf95611 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -444,7 +444,8 @@ static int nvram_pstore_write(enum pstore_type_id type,
*/
static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
int *count, struct timespec *time, char **buf,
- bool *compressed, struct pstore_info *psi)
+ bool *compressed, ssize_t *ecc_notice_size,
+ struct pstore_info *psi)
{
struct oops_log_info *oops_hdr;
unsigned int err_type, id_no, size = 0;
@@ -545,6 +546,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
return -ENOMEM;
kfree(buff);
+ *ecc_notice_size = 0;
if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
*compressed = true;
else
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 6527882ce05e..bb0354222b11 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -75,7 +75,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
}
ret = 0;
- *flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+ *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
if (unlikely(*flt & VM_FAULT_ERROR)) {
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a67c6d781c52..a4db22f65021 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -429,7 +429,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 669a15e7fa76..6dc07ddbfd04 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -581,30 +581,22 @@ static void verify_cpu_node_mapping(int cpu, int node)
}
}
-static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
- void *hcpu)
+/* Must run before sched domains notifier. */
+static int ppc_numa_cpu_prepare(unsigned int cpu)
{
- unsigned long lcpu = (unsigned long)hcpu;
- int ret = NOTIFY_DONE, nid;
+ int nid;
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- nid = numa_setup_cpu(lcpu);
- verify_cpu_node_mapping((int)lcpu, nid);
- ret = NOTIFY_OK;
- break;
+ nid = numa_setup_cpu(cpu);
+ verify_cpu_node_mapping(cpu, nid);
+ return 0;
+}
+
+static int ppc_numa_cpu_dead(unsigned int cpu)
+{
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- unmap_cpu_from_node(lcpu);
- ret = NOTIFY_OK;
- break;
+ unmap_cpu_from_node(cpu);
#endif
- }
- return ret;
+ return 0;
}
/*
@@ -913,11 +905,6 @@ static void __init dump_numa_memory_topology(void)
}
}
-static struct notifier_block ppc64_numa_nb = {
- .notifier_call = cpu_numa_callback,
- .priority = 1 /* Must run before sched domains notifier. */
-};
-
/* Initialize NODE_DATA for a node on the local memory */
static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
{
@@ -985,15 +972,18 @@ void __init initmem_init(void)
setup_node_to_cpumask_map();
reset_numa_cpu_lookup_table();
- register_cpu_notifier(&ppc64_numa_nb);
+
/*
* We need the numa_cpu_lookup_table to be accurate for all CPUs,
* even before we online them, so that we can use cpu_to_{node,mem}
* early in boot, cf. smp_prepare_cpus().
+ * _nocalls() + manual invocation is used because cpuhp is not yet
+ * initialized for the boot CPU.
*/
- for_each_present_cpu(cpu) {
- numa_setup_cpu((unsigned long)cpu);
- }
+ cpuhp_setup_state_nocalls(CPUHP_POWER_NUMA_PREPARE, "POWER_NUMA_PREPARE",
+ ppc_numa_cpu_prepare, ppc_numa_cpu_dead);
+ for_each_present_cpu(cpu)
+ numa_setup_cpu(cpu);
}
static int __init early_numa(char *p)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 97a1d40d8696..ffd61d55fb25 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2158,31 +2158,15 @@ static void perf_event_interrupt(struct pt_regs *regs)
irq_exit();
}
-static void power_pmu_setup(int cpu)
+int power_pmu_prepare_cpu(unsigned int cpu)
{
struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
- if (!ppmu)
- return;
- memset(cpuhw, 0, sizeof(*cpuhw));
- cpuhw->mmcr[0] = MMCR0_FC;
-}
-
-static int
-power_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- power_pmu_setup(cpu);
- break;
-
- default:
- break;
+ if (ppmu) {
+ memset(cpuhw, 0, sizeof(*cpuhw));
+ cpuhw->mmcr[0] = MMCR0_FC;
}
-
- return NOTIFY_OK;
+ return 0;
}
int register_power_pmu(struct power_pmu *pmu)
@@ -2205,7 +2189,7 @@ int register_power_pmu(struct power_pmu *pmu)
#endif /* CONFIG_PPC64 */
perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
- perf_cpu_notifier(power_pmu_notifier);
-
+ cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+ power_pmu_prepare_cpu, NULL);
return 0;
}
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index 6e287f1294fa..e3257f24a8a1 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -137,7 +137,7 @@ config STB03xxx
config PPC4xx_GPIO
bool "PPC4xx GPIO support"
depends on 40x
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Enable gpiolib support for ppc40x based boards
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 5538e57c36c1..48fc18041ff6 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -273,7 +273,7 @@ config PPC44x_SIMPLE
config PPC4xx_GPIO
bool "PPC4xx GPIO support"
depends on 44x
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Enable gpiolib support for ppc440 based boards
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index f09016f6b3a6..bf7ae5cbd07a 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -6,7 +6,6 @@ config PPC_MPC512x
select IPIC
select PPC_PCI_CHOICE
select FSL_PCI if PCI
- select ARCH_WANT_OPTIONAL_GPIOLIB
select USB_EHCI_BIG_ENDIAN_MMIO if USB_EHCI_HCD
select USB_EHCI_BIG_ENDIAN_DESC if USB_EHCI_HCD
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 2bdc8c862c46..4ef7f1cd05b7 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -116,7 +116,6 @@ endif
# used for usb & gpio
config PPC_MPC831x
bool
- select ARCH_WANT_OPTIONAL_GPIOLIB
# used for math-emu
config PPC_MPC832x
@@ -125,9 +124,7 @@ config PPC_MPC832x
# used for usb & gpio
config PPC_MPC834x
bool
- select ARCH_WANT_OPTIONAL_GPIOLIB
# used for usb & gpio
config PPC_MPC837x
bool
- select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index e626461a63bd..df25a3ed489d 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -225,7 +225,7 @@ config GE_IMP3A
select DEFAULT_UIMAGE
select SWIOTLB
select MMIO_NVRAM
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select GE_FPGA
help
This option enables support for the GE Intelligent Platforms IMP3A
@@ -272,7 +272,7 @@ config CORENET_GENERIC
select PPC_E500MC
select PHYS_64BIT
select SWIOTLB
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select GPIO_MPC8XXX
select HAS_RAPIDIO
select PPC_EPAPR_HV_PIC
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 1afd1e4a2dd2..3988f16e46c1 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -4,7 +4,6 @@ menuconfig PPC_86xx
depends on 6xx
select FSL_SOC
select ALTIVEC
- select ARCH_WANT_OPTIONAL_GPIOLIB
help
The Freescale E600 SoCs have 74xx cores.
@@ -37,7 +36,7 @@ config GEF_PPC9A
bool "GE PPC9A"
select DEFAULT_UIMAGE
select MMIO_NVRAM
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select GE_FPGA
help
This option enables support for the GE PPC9A.
@@ -46,7 +45,7 @@ config GEF_SBC310
bool "GE SBC310"
select DEFAULT_UIMAGE
select MMIO_NVRAM
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select GE_FPGA
help
This option enables support for the GE SBC310.
@@ -55,7 +54,7 @@ config GEF_SBC610
bool "GE SBC610"
select DEFAULT_UIMAGE
select MMIO_NVRAM
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select GE_FPGA
select HAS_RAPIDIO
help
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index 157250426b56..564d99bb2a26 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -109,7 +109,7 @@ config 8xx_COPYBACK
config 8xx_GPIO
bool "GPIO API Support"
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Saying Y here will cause the ports on an MPC8xx processor to be used
with the GPIO API. If you say N here, the kernel needs less memory.
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 46a3533d3acb..3663f71fd913 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -275,7 +275,7 @@ config TAU_AVERAGE
config QE_GPIO
bool "QE GPIO support"
depends on QUICC_ENGINE
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Say Y here if you're going to use hardware that connects to the
QE GPIOs.
@@ -285,7 +285,7 @@ config CPM2
depends on (FSL_SOC_BOOKE && PPC32) || 8260
select CPM
select PPC_PCI_CHOICE
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
The CPM2 (Communications Processor Module) is a coprocessor on
embedded CPUs made by Freescale. Selecting this option means that
@@ -324,7 +324,7 @@ config OF_RTC
config SIMPLE_GPIO
bool "Support for simple, memory-mapped GPIO controllers"
depends on PPC
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Say Y here to support simple, memory-mapped GPIO controllers.
These are usually BCSRs used to control board's switches, LEDs,
@@ -334,7 +334,7 @@ config SIMPLE_GPIO
config MCU_MPC8349EMITX
bool "MPC8349E-mITX MCU driver"
depends on I2C=y && PPC_83xx
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
help
Say Y here to enable soft power-off functionality on the Freescale
boards with the MPC8349E-mITX-compatible MCU chips. This driver will
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index f9af6461521a..9144204442eb 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -143,12 +143,12 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
*/
static long
axon_ram_direct_access(struct block_device *device, sector_t sector,
- void __pmem **kaddr, pfn_t *pfn, long size)
+ void **kaddr, pfn_t *pfn, long size)
{
struct axon_ram_bank *bank = device->bd_disk->private_data;
loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
- *kaddr = (void __pmem __force *) bank->io_addr + offset;
+ *kaddr = (void *) bank->io_addr + offset;
*pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV);
return bank->size - offset;
}
diff --git a/arch/s390/appldata/appldata_mem.c b/arch/s390/appldata/appldata_mem.c
index edcf2a706942..598df5708501 100644
--- a/arch/s390/appldata/appldata_mem.c
+++ b/arch/s390/appldata/appldata_mem.c
@@ -102,7 +102,7 @@ static void appldata_get_mem_data(void *data)
mem_data->totalhigh = P2K(val.totalhigh);
mem_data->freehigh = P2K(val.freehigh);
mem_data->bufferram = P2K(val.bufferram);
- mem_data->cached = P2K(global_page_state(NR_FILE_PAGES)
+ mem_data->cached = P2K(global_node_page_state(NR_FILE_PAGES)
- val.bufferram);
si_swapinfo(&val);
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 7a92e69c50bc..15711de10403 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -87,10 +87,10 @@ static inline void tlb_finish_mmu(struct mmu_gather *tlb,
* tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
* has already been freed, so just do free_page_and_swap_cache.
*/
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
free_page_and_swap_cache(page);
- return 1; /* avoid calling tlb_flush_mmu */
+ return false; /* avoid calling tlb_flush_mmu */
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -98,6 +98,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
free_page_and_swap_cache(page);
}
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+ struct page *page)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return tlb_remove_page(tlb, page);
+}
+
/*
* pte_free_tlb frees a pte table and clears the CRSTE for the
* page table from the tlb.
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 7ec63b1d920d..037c2a253ae4 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -664,30 +664,22 @@ static struct pmu cpumf_pmu = {
.cancel_txn = cpumf_pmu_cancel_txn,
};
-static int cpumf_pmu_notifier(struct notifier_block *self, unsigned long action,
- void *hcpu)
+static int cpumf_pmf_setup(unsigned int cpu, int flags)
{
- int flags;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- flags = PMC_INIT;
- local_irq_disable();
- setup_pmc_cpu(&flags);
- local_irq_enable();
- break;
- case CPU_DOWN_PREPARE:
- flags = PMC_RELEASE;
- local_irq_disable();
- setup_pmc_cpu(&flags);
- local_irq_enable();
- break;
- default:
- break;
- }
+ local_irq_disable();
+ setup_pmc_cpu(&flags);
+ local_irq_enable();
+ return 0;
+}
+
+static int s390_pmu_online_cpu(unsigned int cpu)
+{
+ return cpumf_pmf_setup(cpu, PMC_INIT);
+}
- return NOTIFY_OK;
+static int s390_pmu_offline_cpu(unsigned int cpu)
+{
+ return cpumf_pmf_setup(cpu, PMC_RELEASE);
}
static int __init cpumf_pmu_init(void)
@@ -707,7 +699,7 @@ static int __init cpumf_pmu_init(void)
if (rc) {
pr_err("Registering for CPU-measurement alerts "
"failed with rc=%i\n", rc);
- goto out;
+ return rc;
}
cpumf_pmu.attr_groups = cpumf_cf_event_group();
@@ -716,10 +708,10 @@ static int __init cpumf_pmu_init(void)
pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
unregister_external_irq(EXT_IRQ_MEASURE_ALERT,
cpumf_measurement_alert);
- goto out;
+ return rc;
}
- perf_cpu_notifier(cpumf_pmu_notifier);
-out:
- return rc;
+ return cpuhp_setup_state(CPUHP_AP_PERF_S390_CF_ONLINE,
+ "AP_PERF_S390_CF_ONLINE",
+ s390_pmu_online_cpu, s390_pmu_offline_cpu);
}
early_initcall(cpumf_pmu_init);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 9ea26dface38..fcc634c1479a 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -974,12 +974,15 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
struct pt_regs regs;
struct perf_sf_sde_regs *sde_regs;
struct perf_sample_data data;
- struct perf_raw_record raw;
+ struct perf_raw_record raw = {
+ .frag = {
+ .size = sfr->size,
+ .data = sfr,
+ },
+ };
/* Setup perf sample */
perf_sample_data_init(&data, 0, event->hw.last_period);
- raw.size = sfr->size;
- raw.data = sfr;
data.raw = &raw;
/* Setup pt_regs to look like an CPU-measurement external interrupt
@@ -1501,37 +1504,28 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
sf_disable();
}
}
-
-static int cpumf_pmu_notifier(struct notifier_block *self,
- unsigned long action, void *hcpu)
+static int cpusf_pmu_setup(unsigned int cpu, int flags)
{
- int flags;
-
/* Ignore the notification if no events are scheduled on the PMU.
* This might be racy...
*/
if (!atomic_read(&num_events))
- return NOTIFY_OK;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- flags = PMC_INIT;
- local_irq_disable();
- setup_pmc_cpu(&flags);
- local_irq_enable();
- break;
- case CPU_DOWN_PREPARE:
- flags = PMC_RELEASE;
- local_irq_disable();
- setup_pmc_cpu(&flags);
- local_irq_enable();
- break;
- default:
- break;
- }
+ return 0;
- return NOTIFY_OK;
+ local_irq_disable();
+ setup_pmc_cpu(&flags);
+ local_irq_enable();
+ return 0;
+}
+
+static int s390_pmu_sf_online_cpu(unsigned int cpu)
+{
+ return cpusf_pmu_setup(cpu, PMC_INIT);
+}
+
+static int s390_pmu_sf_offline_cpu(unsigned int cpu)
+{
+ return cpusf_pmu_setup(cpu, PMC_RELEASE);
}
static int param_get_sfb_size(char *buffer, const struct kernel_param *kp)
@@ -1631,7 +1625,9 @@ static int __init init_cpum_sampling_pmu(void)
cpumf_measurement_alert);
goto out;
}
- perf_cpu_notifier(cpumf_pmu_notifier);
+
+ cpuhp_setup_state(CPUHP_AP_PERF_S390_SF_ONLINE, "AP_PERF_S390_SF_ONLINE",
+ s390_pmu_sf_online_cpu, s390_pmu_sf_offline_cpu);
out:
return err;
}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 6ad7eff84c82..25783dc3c813 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -456,7 +456,7 @@ retry:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
/* No reason to continue if interrupted by SIGKILL. */
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
fault = VM_FAULT_SIGNAL;
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 37a6c2e0e969..995b71e4db4b 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -111,7 +111,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index e803a836cb7c..0d5f3a9bb315 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -264,7 +264,6 @@ config CPU_SUBTYPE_SH7203
select CPU_HAS_FPU
select SYS_SUPPORTS_SH_CMT
select SYS_SUPPORTS_SH_MTU2
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
config CPU_SUBTYPE_SH7206
@@ -353,7 +352,6 @@ config CPU_SUBTYPE_SH7720
select CPU_SH3
select CPU_HAS_DSP
select SYS_SUPPORTS_SH_CMT
- select ARCH_WANT_OPTIONAL_GPIOLIB
select USB_OHCI_SH if USB_OHCI_HCD
select PINCTRL
help
@@ -419,7 +417,6 @@ config CPU_SUBTYPE_SH7723
select ARCH_SHMOBILE
select ARCH_SPARSEMEM_ENABLE
select SYS_SUPPORTS_SH_CMT
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
help
Select SH7723 if you have an SH-MobileR2 CPU.
@@ -431,7 +428,6 @@ config CPU_SUBTYPE_SH7724
select ARCH_SHMOBILE
select ARCH_SPARSEMEM_ENABLE
select SYS_SUPPORTS_SH_CMT
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
help
Select SH7724 if you have an SH-MobileR2R CPU.
@@ -440,7 +436,6 @@ config CPU_SUBTYPE_SH7734
bool "Support SH7734 processor"
select CPU_SH4A
select CPU_SHX2
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
help
Select SH7734 if you have a SH4A SH7734 CPU.
@@ -449,7 +444,6 @@ config CPU_SUBTYPE_SH7757
bool "Support SH7757 processor"
select CPU_SH4A
select CPU_SHX2
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
help
Select SH7757 if you have a SH4A SH7757 CPU.
@@ -475,7 +469,6 @@ config CPU_SUBTYPE_SH7785
select CPU_SHX2
select ARCH_SPARSEMEM_ENABLE
select SYS_SUPPORTS_NUMA
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
config CPU_SUBTYPE_SH7786
@@ -484,7 +477,6 @@ config CPU_SUBTYPE_SH7786
select CPU_SHX3
select CPU_HAS_PTEAEX
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
- select ARCH_WANT_OPTIONAL_GPIOLIB
select USB_OHCI_SH if USB_OHCI_HCD
select USB_EHCI_SH if USB_EHCI_HCD
select PINCTRL
@@ -494,7 +486,7 @@ config CPU_SUBTYPE_SHX3
select CPU_SH4A
select CPU_SHX3
select GENERIC_CLOCKEVENTS_BROADCAST if SMP
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select PINCTRL
# SH4AL-DSP Processor Support
@@ -513,7 +505,6 @@ config CPU_SUBTYPE_SH7722
select ARCH_SPARSEMEM_ENABLE
select SYS_SUPPORTS_NUMA
select SYS_SUPPORTS_SH_CMT
- select ARCH_WANT_OPTIONAL_GPIOLIB
select PINCTRL
config CPU_SUBTYPE_SH7366
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index 5e52d5362292..e0db04664e2e 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -70,7 +70,7 @@ config SH_7724_SOLUTION_ENGINE
bool "SolutionEngine7724"
select SOLUTION_ENGINE
depends on CPU_SUBTYPE_SH7724
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select SND_SOC_AK4642 if SND_SIMPLE_CARD
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
@@ -174,7 +174,6 @@ config SH_SDK7786
depends on CPU_SUBTYPE_SH7786
select SYS_SUPPORTS_PCI
select NO_IOPORT_MAP if !PCI
- select ARCH_WANT_OPTIONAL_GPIOLIB
select HAVE_SRAM_POOL
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
@@ -190,7 +189,7 @@ config SH_HIGHLANDER
config SH_SH7757LCR
bool "SH7757LCR"
depends on CPU_SUBTYPE_SH7757
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select REGULATOR_FIXED_VOLTAGE if REGULATOR
config SH_SH7785LCR
@@ -217,14 +216,14 @@ config SH_SH7785LCR_PT
config SH_URQUELL
bool "Urquell"
depends on CPU_SUBTYPE_SH7786
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select SYS_SUPPORTS_PCI
select NO_IOPORT_MAP if !PCI
config SH_MIGOR
bool "Migo-R"
depends on CPU_SUBTYPE_SH7722
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
Select Migo-R if configuring for the SH7722 Migo-R platform
@@ -233,7 +232,7 @@ config SH_MIGOR
config SH_AP325RXA
bool "AP-325RXA"
depends on CPU_SUBTYPE_SH7723
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
Renesas "AP-325RXA" support.
@@ -242,7 +241,7 @@ config SH_AP325RXA
config SH_KFR2R09
bool "KFR2R09"
depends on CPU_SUBTYPE_SH7724
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
"Kit For R2R for 2009" support.
@@ -250,7 +249,7 @@ config SH_KFR2R09
config SH_ECOVEC
bool "EcoVec"
depends on CPU_SUBTYPE_SH7724
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select SND_SOC_DA7210 if SND_SIMPLE_CARD
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
@@ -327,7 +326,7 @@ config SH_X3PROTO
config SH_MAGIC_PANEL_R2
bool "Magic Panel R2"
depends on CPU_SUBTYPE_SH7720
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
select REGULATOR_FIXED_VOLTAGE if REGULATOR
help
Select Magic Panel R2 if configuring for Magic Panel R2.
diff --git a/arch/sh/boards/mach-highlander/Kconfig b/arch/sh/boards/mach-highlander/Kconfig
index def49cc0a7b9..42f5589b4bf3 100644
--- a/arch/sh/boards/mach-highlander/Kconfig
+++ b/arch/sh/boards/mach-highlander/Kconfig
@@ -18,7 +18,7 @@ config SH_R7780MP
config SH_R7785RP
bool "R7785RP board support"
depends on CPU_SUBTYPE_SH7785
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
endchoice
diff --git a/arch/sh/boards/mach-rsk/Kconfig b/arch/sh/boards/mach-rsk/Kconfig
index 458a11ffd022..0b9b2c4952c1 100644
--- a/arch/sh/boards/mach-rsk/Kconfig
+++ b/arch/sh/boards/mach-rsk/Kconfig
@@ -10,17 +10,17 @@ config SH_RSK7201
config SH_RSK7203
bool "RSK7203"
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
depends on CPU_SUBTYPE_SH7203
config SH_RSK7264
bool "RSK2+SH7264"
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
depends on CPU_SUBTYPE_SH7264
config SH_RSK7269
bool "RSK2+SH7269"
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
depends on CPU_SUBTYPE_SH7269
endchoice
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 62f80d2a9df9..025cdb1032f6 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -101,7 +101,7 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
free_page_and_swap_cache(page);
- return 1; /* avoid calling tlb_flush_mmu */
+ return false; /* avoid calling tlb_flush_mmu */
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -109,6 +109,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
__tlb_remove_page(tlb, page);
}
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+ struct page *page)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return tlb_remove_page(tlb, page);
+}
+
#define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep)
#define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp)
#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 4dca18347ee9..ba3269a8304b 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -352,28 +352,12 @@ static struct pmu pmu = {
.read = sh_pmu_read,
};
-static void sh_pmu_setup(int cpu)
+static int sh_pmu_prepare_cpu(unsigned int cpu)
{
struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
memset(cpuhw, 0, sizeof(struct cpu_hw_events));
-}
-
-static int
-sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- sh_pmu_setup(cpu);
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
+ return 0;
}
int register_sh_pmu(struct sh_pmu *_pmu)
@@ -394,6 +378,7 @@ int register_sh_pmu(struct sh_pmu *_pmu)
WARN_ON(_pmu->num_events > MAX_HWEVENTS);
perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
- perf_cpu_notifier(sh_pmu_notifier);
+ cpuhp_setup_state(CPUHP_PERF_SUPERH, "PERF_SUPERH", sh_pmu_prepare_cpu,
+ NULL);
return 0;
}
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 79d8276377d1..9bf876780cef 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -487,7 +487,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
if (mm_fault_error(regs, error_code, address, fault))
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 139e711ff80c..dcbf985ab243 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -31,14 +31,6 @@ static inline int prepare_hugepage_range(struct file *file,
return 0;
}
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end,
- unsigned long floor,
- unsigned long ceiling)
-{
- free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
@@ -82,4 +74,8 @@ static inline void arch_clear_hugepage_flags(struct page *page)
{
}
+void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling);
+
#endif /* _ASM_SPARC64_HUGETLB_H */
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index 70067ce184b1..f7de0dbc38af 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -92,7 +92,8 @@ struct tsb_config {
typedef struct {
spinlock_t lock;
unsigned long sparc64_ctx_val;
- unsigned long huge_pte_count;
+ unsigned long hugetlb_pte_count;
+ unsigned long thp_pte_count;
struct tsb_config tsb_block[MM_NUM_TSBS];
struct hv_tsb_descr tsb_descr[MM_NUM_TSBS];
} mm_context_t;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index e7d82803a48f..1fb317fbc0b3 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -395,7 +395,7 @@ static inline unsigned long __pte_huge_mask(void)
static inline pte_t pte_mkhuge(pte_t pte)
{
- return __pte(pte_val(pte) | __pte_huge_mask());
+ return __pte(pte_val(pte) | _PAGE_PMD_HUGE | __pte_huge_mask());
}
static inline bool is_hugetlb_pte(pte_t pte)
@@ -403,6 +403,11 @@ static inline bool is_hugetlb_pte(pte_t pte)
return !!(pte_val(pte) & __pte_huge_mask());
}
+static inline bool is_hugetlb_pmd(pmd_t pmd)
+{
+ return !!(pmd_val(pmd) & _PAGE_PMD_HUGE);
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index c6a155c3904e..32258e08da03 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -203,7 +203,7 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
* We have to propagate the 4MB bit of the virtual address
* because we are fabricating 8MB pages using 4MB hw pages.
*/
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
#define USER_PGTABLE_CHECK_PMD_HUGE(VADDR, REG1, REG2, FAIL_LABEL, PTE_LABEL) \
brz,pn REG1, FAIL_LABEL; \
sethi %uhi(_PAGE_PMD_HUGE), REG2; \
diff --git a/arch/sparc/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index d668ca149e64..4087a62f96b0 100644
--- a/arch/sparc/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
@@ -25,13 +25,13 @@
/* PROT ** ICACHE line 2: More real fault processing */
ldxa [%g4] ASI_DMMU, %g5 ! Put tagaccess in %g5
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5 ! Clear context ID bits
bgu,pn %xcc, winfix_trampoline ! Yes, perform winfixup
mov FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
ba,pt %xcc, sparc64_realfault_common ! Nope, normal fault
nop
nop
- nop
- nop
/* PROT ** ICACHE line 3: Unused... */
nop
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index a979e99f8751..cac4a5554c0e 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -165,7 +165,7 @@ void irq_link(unsigned int irq)
p = &irq_table[irq];
pil = p->pil;
- BUG_ON(pil > SUN4D_MAX_IRQ);
+ BUG_ON(pil >= SUN4D_MAX_IRQ);
p->next = irq_map[pil];
irq_map[pil] = p;
@@ -182,7 +182,7 @@ void irq_unlink(unsigned int irq)
spin_lock_irqsave(&irq_map_lock, flags);
p = &irq_table[irq];
- BUG_ON(p->pil > SUN4D_MAX_IRQ);
+ BUG_ON(p->pil >= SUN4D_MAX_IRQ);
pnext = &irq_map[p->pil];
while (*pnext != p)
pnext = &(*pnext)->next;
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index ef0d8e9e1210..f22bec0db645 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -20,6 +20,10 @@ kvmap_itlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_IMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_itlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -128,6 +132,10 @@ kvmap_dtlb:
mov TLB_TAG_ACCESS, %g4
ldxa [%g4] ASI_DMMU, %g4
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g4 here.
+ */
+
/* sun4v_dtlb_miss branches here with the missing virtual
* address already loaded into %g4
*/
@@ -251,6 +259,10 @@ kvmap_dtlb_longpath:
nop
.previous
+ /* The kernel executes in context zero, therefore we do not
+ * need to clear the context ID bits out of %g5 here.
+ */
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index be98685c14c6..d568c8207af7 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -29,13 +29,17 @@
*/
tsb_miss_dtlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_DMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_DMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
tsb_miss_itlb:
mov TLB_TAG_ACCESS, %g4
+ ldxa [%g4] ASI_IMMU, %g4
+ srlx %g4, PAGE_SHIFT, %g4
ba,pt %xcc, tsb_miss_page_table_walk
- ldxa [%g4] ASI_IMMU, %g4
+ sllx %g4, PAGE_SHIFT, %g4
/* At this point we have:
* %g1 -- PAGE_SIZE TSB entry address
@@ -284,6 +288,10 @@ tsb_do_dtlb_fault:
nop
.previous
+ /* Clear context ID bits. */
+ srlx %g5, PAGE_SHIFT, %g5
+ sllx %g5, PAGE_SHIFT, %g5
+
be,pt %xcc, sparc64_realfault_common
mov FAULT_CODE_DTLB, %g4
ba,pt %xcc, winfix_trampoline
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index b6c559cbd64d..4714061d6cd3 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -241,7 +241,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
@@ -411,7 +411,7 @@ good_area:
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- switch (handle_mm_fault(mm, vma, address, flags)) {
+ switch (handle_mm_fault(vma, address, flags)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index cb841a33da59..e16fdd28a931 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -111,8 +111,8 @@ static unsigned int get_user_insn(unsigned long tpc)
if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
goto out_irq_enable;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (pmd_trans_huge(*pmdp)) {
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ if (is_hugetlb_pmd(*pmdp)) {
pa = pmd_pfn(*pmdp) << PAGE_SHIFT;
pa += tpc & ~HPAGE_MASK;
@@ -436,7 +436,7 @@ good_area:
goto bad_area;
}
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
goto exit_exception;
@@ -476,14 +476,14 @@ good_area:
up_read(&mm->mmap_sem);
mm_rss = get_mm_rss(mm);
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
#endif
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss = mm->context.huge_pte_count;
+ mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ba52e6466a82..988acc8b1b80 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -12,6 +12,7 @@
#include <asm/mman.h>
#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
@@ -131,23 +132,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
{
pgd_t *pgd;
pud_t *pud;
- pmd_t *pmd;
pte_t *pte = NULL;
- /* We must align the address, because our caller will run
- * set_huge_pte_at() on whatever we return, which writes out
- * all of the sub-ptes for the hugepage range. So we have
- * to give it the first such sub-pte.
- */
- addr &= HPAGE_MASK;
-
pgd = pgd_offset(mm, addr);
pud = pud_alloc(mm, pgd, addr);
- if (pud) {
- pmd = pmd_alloc(mm, pud, addr);
- if (pmd)
- pte = pte_alloc_map(mm, pmd, addr);
- }
+ if (pud)
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
return pte;
}
@@ -155,19 +146,13 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
- pmd_t *pmd;
pte_t *pte = NULL;
- addr &= HPAGE_MASK;
-
pgd = pgd_offset(mm, addr);
if (!pgd_none(*pgd)) {
pud = pud_offset(pgd, addr);
- if (!pud_none(*pud)) {
- pmd = pmd_offset(pud, addr);
- if (!pmd_none(*pmd))
- pte = pte_offset_map(pmd, addr);
- }
+ if (!pud_none(*pud))
+ pte = (pte_t *)pmd_offset(pud, addr);
}
return pte;
}
@@ -175,70 +160,143 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
- int i;
- pte_t orig[2];
- unsigned long nptes;
+ pte_t orig;
if (!pte_present(*ptep) && pte_present(entry))
- mm->context.huge_pte_count++;
+ mm->context.hugetlb_pte_count++;
addr &= HPAGE_MASK;
-
- nptes = 1 << HUGETLB_PAGE_ORDER;
- orig[0] = *ptep;
- orig[1] = *(ptep + nptes / 2);
- for (i = 0; i < nptes; i++) {
- *ptep = entry;
- ptep++;
- addr += PAGE_SIZE;
- pte_val(entry) += PAGE_SIZE;
- }
+ orig = *ptep;
+ *ptep = entry;
/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
- addr -= REAL_HPAGE_SIZE;
- ptep -= nptes / 2;
- maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
- addr -= REAL_HPAGE_SIZE;
- ptep -= nptes / 2;
- maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
+ maybe_tlb_batch_add(mm, addr, ptep, orig, 0);
+ maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0);
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
pte_t entry;
- int i;
- unsigned long nptes;
entry = *ptep;
if (pte_present(entry))
- mm->context.huge_pte_count--;
+ mm->context.hugetlb_pte_count--;
addr &= HPAGE_MASK;
- nptes = 1 << HUGETLB_PAGE_ORDER;
- for (i = 0; i < nptes; i++) {
- *ptep = __pte(0UL);
- addr += PAGE_SIZE;
- ptep++;
- }
+ *ptep = __pte(0UL);
/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
- addr -= REAL_HPAGE_SIZE;
- ptep -= nptes / 2;
- maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
- addr -= REAL_HPAGE_SIZE;
- ptep -= nptes / 2;
maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+ maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0);
return entry;
}
int pmd_huge(pmd_t pmd)
{
- return 0;
+ return !pmd_none(pmd) &&
+ (pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID;
}
int pud_huge(pud_t pud)
{
return 0;
}
+
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr)
+{
+ pgtable_t token = pmd_pgtable(*pmd);
+
+ pmd_clear(pmd);
+ pte_free_tlb(tlb, token, addr);
+ atomic_long_dec(&tlb->mm->nr_ptes);
+}
+
+static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ pmd_t *pmd;
+ unsigned long next;
+ unsigned long start;
+
+ start = addr;
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (pmd_none(*pmd))
+ continue;
+ if (is_hugetlb_pmd(*pmd))
+ pmd_clear(pmd);
+ else
+ hugetlb_free_pte_range(tlb, pmd, addr);
+ } while (pmd++, addr = next, addr != end);
+
+ start &= PUD_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PUD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pmd = pmd_offset(pud, start);
+ pud_clear(pud);
+ pmd_free_tlb(tlb, pmd, start);
+ mm_dec_nr_pmds(tlb->mm);
+}
+
+static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ pud_t *pud;
+ unsigned long next;
+ unsigned long start;
+
+ start = addr;
+ pud = pud_offset(pgd, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
+ ceiling);
+ } while (pud++, addr = next, addr != end);
+
+ start &= PGDIR_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PGDIR_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pud = pud_offset(pgd, start);
+ pgd_clear(pgd);
+ pud_free_tlb(tlb, pud, start);
+}
+
+void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ pgd_t *pgd;
+ unsigned long next;
+
+ pgd = pgd_offset(tlb->mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ } while (pgd++, addr = next, addr != end);
+}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index aec508e37490..65457c9f1365 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -346,10 +346,13 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
spin_lock_irqsave(&mm->context.lock, flags);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+ if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
+ is_hugetlb_pte(pte)) {
+ /* We are fabricating 8MB pages using 4MB real hw pages. */
+ pte_val(pte) |= (address & (1UL << REAL_HPAGE_SHIFT));
__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
address, pte_val(pte));
- else
+ } else
#endif
__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
address, pte_val(pte));
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index f81cd9736700..3659d37b4d81 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -175,9 +175,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.huge_pte_count++;
+ mm->context.thp_pte_count++;
else
- mm->context.huge_pte_count--;
+ mm->context.thp_pte_count--;
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a0604a493a36..6725ed45580e 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -470,7 +470,7 @@ retry_tsb_alloc:
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long huge_pte_count;
+ unsigned long total_huge_pte_count;
#endif
unsigned int i;
@@ -479,12 +479,14 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
mm->context.sparc64_ctx_val = 0UL;
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- /* We reset it to zero because the fork() page copying
+ /* We reset them to zero because the fork() page copying
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
*/
- huge_pte_count = mm->context.huge_pte_count;
- mm->context.huge_pte_count = 0;
+ total_huge_pte_count = mm->context.hugetlb_pte_count +
+ mm->context.thp_pte_count;
+ mm->context.hugetlb_pte_count = 0;
+ mm->context.thp_pte_count = 0;
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -500,8 +502,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (unlikely(huge_pte_count))
- tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
+ if (unlikely(total_huge_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/tile/include/asm/elf.h b/arch/tile/include/asm/elf.h
index c505d77e4d06..e9d54a06736f 100644
--- a/arch/tile/include/asm/elf.h
+++ b/arch/tile/include/asm/elf.h
@@ -129,6 +129,7 @@ extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int executable_stack);
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
#define ARCH_DLINFO \
do { \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_BASE); \
diff --git a/arch/tile/include/asm/setup.h b/arch/tile/include/asm/setup.h
index e98909033e5b..2a0347af0702 100644
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -25,7 +25,12 @@
#define MAXMEM_PFN PFN_DOWN(MAXMEM)
int tile_console_write(const char *buf, int count);
+
+#ifdef CONFIG_EARLY_PRINTK
void early_panic(const char *fmt, ...);
+#else
+#define early_panic panic
+#endif
/* Init-time routine to do tile-specific per-cpu setup. */
void setup_cpu(int boot);
diff --git a/arch/tile/include/uapi/asm/auxvec.h b/arch/tile/include/uapi/asm/auxvec.h
index c93e92709f14..f497123ed980 100644
--- a/arch/tile/include/uapi/asm/auxvec.h
+++ b/arch/tile/include/uapi/asm/auxvec.h
@@ -18,4 +18,6 @@
/* The vDSO location. */
#define AT_SYSINFO_EHDR 33
+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
#endif /* _ASM_TILE_AUXVEC_H */
diff --git a/arch/tile/kernel/compat.c b/arch/tile/kernel/compat.c
index 49120843ff96..bdaf71d31a4a 100644
--- a/arch/tile/kernel/compat.c
+++ b/arch/tile/kernel/compat.c
@@ -23,42 +23,50 @@
#include <linux/uaccess.h>
#include <linux/signal.h>
#include <asm/syscalls.h>
+#include <asm/byteorder.h>
/*
* Syscalls that take 64-bit numbers traditionally take them in 32-bit
* "high" and "low" value parts on 32-bit architectures.
* In principle, one could imagine passing some register arguments as
* fully 64-bit on TILE-Gx in 32-bit mode, but it seems easier to
- * adapt the usual convention.
+ * adopt the usual convention.
*/
+#ifdef __BIG_ENDIAN
+#define SYSCALL_PAIR(name) u32, name ## _hi, u32, name ## _lo
+#else
+#define SYSCALL_PAIR(name) u32, name ## _lo, u32, name ## _hi
+#endif
+
COMPAT_SYSCALL_DEFINE4(truncate64, char __user *, filename, u32, dummy,
- u32, low, u32, high)
+ SYSCALL_PAIR(length))
{
- return sys_truncate(filename, ((loff_t)high << 32) | low);
+ return sys_truncate(filename, ((loff_t)length_hi << 32) | length_lo);
}
COMPAT_SYSCALL_DEFINE4(ftruncate64, unsigned int, fd, u32, dummy,
- u32, low, u32, high)
+ SYSCALL_PAIR(length))
{
- return sys_ftruncate(fd, ((loff_t)high << 32) | low);
+ return sys_ftruncate(fd, ((loff_t)length_hi << 32) | length_lo);
}
COMPAT_SYSCALL_DEFINE6(pread64, unsigned int, fd, char __user *, ubuf,
- size_t, count, u32, dummy, u32, low, u32, high)
+ size_t, count, u32, dummy, SYSCALL_PAIR(offset))
{
- return sys_pread64(fd, ubuf, count, ((loff_t)high << 32) | low);
+ return sys_pread64(fd, ubuf, count,
+ ((loff_t)offset_hi << 32) | offset_lo);
}
COMPAT_SYSCALL_DEFINE6(pwrite64, unsigned int, fd, char __user *, ubuf,
- size_t, count, u32, dummy, u32, low, u32, high)
+ size_t, count, u32, dummy, SYSCALL_PAIR(offset))
{
- return sys_pwrite64(fd, ubuf, count, ((loff_t)high << 32) | low);
+ return sys_pwrite64(fd, ubuf, count,
+ ((loff_t)offset_hi << 32) | offset_lo);
}
COMPAT_SYSCALL_DEFINE6(sync_file_range2, int, fd, unsigned int, flags,
- u32, offset_lo, u32, offset_hi,
- u32, nbytes_lo, u32, nbytes_hi)
+ SYSCALL_PAIR(offset), SYSCALL_PAIR(nbytes))
{
return sys_sync_file_range(fd, ((loff_t)offset_hi << 32) | offset_lo,
((loff_t)nbytes_hi << 32) | nbytes_lo,
@@ -66,8 +74,7 @@ COMPAT_SYSCALL_DEFINE6(sync_file_range2, int, fd, unsigned int, flags,
}
COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode,
- u32, offset_lo, u32, offset_hi,
- u32, len_lo, u32, len_hi)
+ SYSCALL_PAIR(offset), SYSCALL_PAIR(len))
{
return sys_fallocate(fd, mode, ((loff_t)offset_hi << 32) | offset_lo,
((loff_t)len_hi << 32) | len_lo);
@@ -77,6 +84,8 @@ COMPAT_SYSCALL_DEFINE6(fallocate, int, fd, int, mode,
* Avoid bug in generic sys_llseek() that specifies offset_high and
* offset_low as "unsigned long", thus making it possible to pass
* a sign-extended high 32 bits in offset_low.
+ * Note that we do not use SYSCALL_PAIR here since glibc passes the
+ * high and low parts explicitly in that order.
*/
COMPAT_SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned int, offset_high,
unsigned int, offset_low, loff_t __user *, result,
diff --git a/arch/tile/kernel/sys.c b/arch/tile/kernel/sys.c
index 38debe706061..c7418dcbbb08 100644
--- a/arch/tile/kernel/sys.c
+++ b/arch/tile/kernel/sys.c
@@ -33,6 +33,7 @@
#include <asm/pgtable.h>
#include <asm/homecache.h>
#include <asm/cachectl.h>
+#include <asm/byteorder.h>
#include <arch/chip.h>
SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, len,
@@ -59,13 +60,19 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, len,
#if !defined(__tilegx__) || defined(CONFIG_COMPAT)
-ssize_t sys32_readahead(int fd, u32 offset_lo, u32 offset_hi, u32 count)
+#ifdef __BIG_ENDIAN
+#define SYSCALL_PAIR(name) u32 name ## _hi, u32 name ## _lo
+#else
+#define SYSCALL_PAIR(name) u32 name ## _lo, u32 name ## _hi
+#endif
+
+ssize_t sys32_readahead(int fd, SYSCALL_PAIR(offset), u32 count)
{
return sys_readahead(fd, ((loff_t)offset_hi << 32) | offset_lo, count);
}
-int sys32_fadvise64_64(int fd, u32 offset_lo, u32 offset_hi,
- u32 len_lo, u32 len_hi, int advice)
+int sys32_fadvise64_64(int fd, SYSCALL_PAIR(offset),
+ SYSCALL_PAIR(len), int advice)
{
return sys_fadvise64_64(fd, ((loff_t)offset_hi << 32) | offset_lo,
((loff_t)len_hi << 32) | len_lo, advice);
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index 9d171ca4302c..c5369fe643c7 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -77,7 +77,11 @@ uint64_t __umoddi3(uint64_t dividend, uint64_t divisor);
EXPORT_SYMBOL(__umoddi3);
int64_t __moddi3(int64_t dividend, int64_t divisor);
EXPORT_SYMBOL(__moddi3);
-#ifndef __tilegx__
+#ifdef __tilegx__
+typedef int TItype __attribute__((mode(TI)));
+TItype __multi3(TItype a, TItype b);
+EXPORT_SYMBOL(__multi3); /* required for gcc 7 and later */
+#else
int64_t __muldi3(int64_t, int64_t);
EXPORT_SYMBOL(__muldi3);
uint64_t __lshrdi3(uint64_t, unsigned int);
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 26734214818c..beba986589e5 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -434,7 +434,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return 0;
diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index c4d5bf841a7f..7cc6ee7f1a58 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -45,20 +45,20 @@ void show_mem(unsigned int filter)
struct zone *zone;
pr_err("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu free:%lu\n slab:%lu mapped:%lu pagetables:%lu bounce:%lu pagecache:%lu swap:%lu\n",
- (global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_ACTIVE_FILE)),
- (global_page_state(NR_INACTIVE_ANON) +
- global_page_state(NR_INACTIVE_FILE)),
- global_page_state(NR_FILE_DIRTY),
- global_page_state(NR_WRITEBACK),
- global_page_state(NR_UNSTABLE_NFS),
+ (global_node_page_state(NR_ACTIVE_ANON) +
+ global_node_page_state(NR_ACTIVE_FILE)),
+ (global_node_page_state(NR_INACTIVE_ANON) +
+ global_node_page_state(NR_INACTIVE_FILE)),
+ global_node_page_state(NR_FILE_DIRTY),
+ global_node_page_state(NR_WRITEBACK),
+ global_node_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_FREE_PAGES),
(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
- global_page_state(NR_FILE_MAPPED),
+ global_node_page_state(NR_FILE_MAPPED),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE),
- global_page_state(NR_FILE_PAGES),
+ global_node_page_state(NR_FILE_PAGES),
get_nr_swap_pages());
for_each_zone(zone) {
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 16eb63fac57d..821ff0acfe17 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -102,7 +102,7 @@ static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
tlb->need_flush = 1;
free_page_and_swap_cache(page);
- return 1; /* avoid calling tlb_flush_mmu */
+ return false; /* avoid calling tlb_flush_mmu */
}
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -110,6 +110,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
__tlb_remove_page(tlb, page);
}
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+ struct page *page)
+{
+ return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+ struct page *page, int page_size)
+{
+ return tlb_remove_page(tlb, page);
+}
+
/**
* tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
*
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 98783dd0fa2e..ad8f206ab5e8 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -73,7 +73,7 @@ good_area:
do {
int fault;
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
goto out_nosemaphore;
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index e5602ee9c610..0769066929c6 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -80,7 +80,7 @@ config ARCH_PUV3
select CPU_UCV2
select GENERIC_CLOCKEVENTS
select HAVE_CLK
- select ARCH_REQUIRE_GPIOLIB
+ select GPIOLIB
# CONFIGs for ARCH_PUV3
diff --git a/arch/unicore32/configs/unicore32_defconfig b/arch/unicore32/configs/unicore32_defconfig
index 45f47f88d86a..aebd01fc28e5 100644
--- a/arch/unicore32/configs/unicore32_defconfig
+++ b/arch/unicore32/configs/unicore32_defconfig
@@ -161,7 +161,7 @@ CONFIG_LEDS_GPIO=y
# LED Triggers
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_DISK=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
# Real Time Clock
diff --git a/arch/unicore32/kernel/gpio.c b/arch/unicore32/kernel/gpio.c
index 49347a0e9288..bf164bb4dba2 100644
--- a/arch/unicore32/kernel/gpio.c
+++ b/arch/unicore32/kernel/gpio.c
@@ -27,7 +27,7 @@ static const struct gpio_led puv3_gpio_leds[] = {
{ .name = "cpuhealth", .gpio = GPO_CPU_HEALTH, .active_low = 0,
.default_trigger = "heartbeat", },
{ .name = "hdd_led", .gpio = GPO_HDD_LED, .active_low = 1,
- .default_trigger = "ide-disk", },
+ .default_trigger = "disk-activity", },
};
static const struct gpio_led_platform_data puv3_gpio_led_data = {
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 2ec3d3adcefc..6c7f70bcaae3 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -194,7 +194,7 @@ good_area:
* If for any reason at all we couldn't handle the fault, make
* sure we exit gracefully rather than endlessly redo the fault.
*/
- fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
+ fault = handle_mm_fault(vma, addr & PAGE_MASK, flags);
return fault;
check_stack:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5977fea2c8b1..2fa55851d2a9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,6 +22,7 @@ config X86
select ANON_INODES
select ARCH_CLOCKSOURCE_DATA
select ARCH_DISCARD_MEMBLOCK
+ select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 6fce7f096b88..830ed391e7ef 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -126,14 +126,6 @@ else
KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
endif
-# Make sure compiler does not have buggy stack-protector support.
-ifdef CONFIG_CC_STACKPROTECTOR
- cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
- ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
- $(warning stack-protector enabled but compiler support broken)
- endif
-endif
-
ifdef CONFIG_X86_X32
x32_ld_ok := $(call try-run,\
/bin/echo -e '1: .quad 1b' | \
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 3329844e3c43..f840766659a8 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -331,15 +331,9 @@ static void vgetcpu_cpu_init(void *arg)
write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}
-static int
-vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg)
+static int vgetcpu_online(unsigned int cpu)
{
- long cpu = (long)arg;
-
- if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
-
- return NOTIFY_DONE;
+ return smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
}
static int __init init_vdso(void)
@@ -350,15 +344,9 @@ static int __init init_vdso(void)
init_vdso_image(&vdso_image_x32);
#endif
- cpu_notifier_register_begin();
-
- on_each_cpu(vgetcpu_cpu_init, NULL, 1);
/* notifier priority > KVM */
- __hotcpu_notifier(vgetcpu_cpu_notifier, 30);
-
- cpu_notifier_register_done();
-
- return 0;
+ return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
+ "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
}
subsys_initcall(init_vdso);
#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index bd3e8421b57c..e07a22bb9308 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -370,13 +370,13 @@ static int amd_pmu_cpu_prepare(int cpu)
WARN_ON_ONCE(cpuc->amd_nb);
if (!x86_pmu.amd_nb_constraints)
- return NOTIFY_OK;
+ return 0;
cpuc->amd_nb = amd_alloc_nb(cpu);
if (!cpuc->amd_nb)
- return NOTIFY_BAD;
+ return -ENOMEM;
- return NOTIFY_OK;
+ return 0;
}
static void amd_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index feb90f6730e8..155ea5324ae0 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -655,8 +655,12 @@ fail:
}
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
- raw.size = sizeof(u32) + ibs_data.size;
- raw.data = ibs_data.data;
+ raw = (struct perf_raw_record){
+ .frag = {
+ .size = sizeof(u32) + ibs_data.size,
+ .data = ibs_data.data,
+ },
+ };
data.raw = &raw;
}
@@ -721,13 +725,10 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
return ret;
}
-static __init int perf_event_ibs_init(void)
+static __init void perf_event_ibs_init(void)
{
struct attribute **attr = ibs_op_format_attrs;
- if (!ibs_caps)
- return -ENODEV; /* ibs not supported by the cpu */
-
perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
if (ibs_caps & IBS_CAPS_OPCNT) {
@@ -738,13 +739,11 @@ static __init int perf_event_ibs_init(void)
register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps);
-
- return 0;
}
#else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */
-static __init int perf_event_ibs_init(void) { return 0; }
+static __init void perf_event_ibs_init(void) { }
#endif
@@ -921,7 +920,7 @@ static inline int get_ibs_lvt_offset(void)
return val & IBSCTL_LVT_OFFSET_MASK;
}
-static void setup_APIC_ibs(void *dummy)
+static void setup_APIC_ibs(void)
{
int offset;
@@ -936,7 +935,7 @@ failed:
smp_processor_id());
}
-static void clear_APIC_ibs(void *dummy)
+static void clear_APIC_ibs(void)
{
int offset;
@@ -945,18 +944,24 @@ static void clear_APIC_ibs(void *dummy)
setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
}
+static int x86_pmu_amd_ibs_starting_cpu(unsigned int cpu)
+{
+ setup_APIC_ibs();
+ return 0;
+}
+
#ifdef CONFIG_PM
static int perf_ibs_suspend(void)
{
- clear_APIC_ibs(NULL);
+ clear_APIC_ibs();
return 0;
}
static void perf_ibs_resume(void)
{
ibs_eilvt_setup();
- setup_APIC_ibs(NULL);
+ setup_APIC_ibs();
}
static struct syscore_ops perf_ibs_syscore_ops = {
@@ -975,27 +980,15 @@ static inline void perf_ibs_pm_init(void) { }
#endif
-static int
-perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+static int x86_pmu_amd_ibs_dying_cpu(unsigned int cpu)
{
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- setup_APIC_ibs(NULL);
- break;
- case CPU_DYING:
- clear_APIC_ibs(NULL);
- break;
- default:
- break;
- }
-
- return NOTIFY_OK;
+ clear_APIC_ibs();
+ return 0;
}
static __init int amd_ibs_init(void)
{
u32 caps;
- int ret = -EINVAL;
caps = __get_ibs_caps();
if (!caps)
@@ -1004,22 +997,25 @@ static __init int amd_ibs_init(void)
ibs_eilvt_setup();
if (!ibs_eilvt_valid())
- goto out;
+ return -EINVAL;
perf_ibs_pm_init();
- cpu_notifier_register_begin();
+
ibs_caps = caps;
/* make ibs_caps visible to other cpus: */
smp_mb();
- smp_call_function(setup_APIC_ibs, NULL, 1);
- __perf_cpu_notifier(perf_ibs_cpu_notifier);
- cpu_notifier_register_done();
+ /*
+ * x86_pmu_amd_ibs_starting_cpu will be called from core on
+ * all online cpus.
+ */
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
+ "AP_PERF_X86_AMD_IBS_STARTING",
+ x86_pmu_amd_ibs_starting_cpu,
+ x86_pmu_amd_ibs_dying_cpu);
- ret = perf_event_ibs_init();
-out:
- if (ret)
- pr_err("Failed to setup IBS, %d\n", ret);
- return ret;
+ perf_event_ibs_init();
+
+ return 0;
}
/* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 55a3529dbf12..9842270ed2f2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -228,12 +228,12 @@ static struct pmu pmu_class = {
.read = pmu_event_read,
};
-static void power_cpu_exit(int cpu)
+static int power_cpu_exit(unsigned int cpu)
{
int target;
if (!cpumask_test_and_clear_cpu(cpu, &cpu_mask))
- return;
+ return 0;
/*
* Find a new CPU on the same compute unit, if was set in cpumask
@@ -245,9 +245,10 @@ static void power_cpu_exit(int cpu)
cpumask_set_cpu(target, &cpu_mask);
perf_pmu_migrate_context(&pmu_class, cpu, target);
}
+ return 0;
}
-static void power_cpu_init(int cpu)
+static int power_cpu_init(unsigned int cpu)
{
int target;
@@ -255,7 +256,7 @@ static void power_cpu_init(int cpu)
* 1) If any CPU is set at cpu_mask in the same compute unit, do
* nothing.
* 2) If no CPU is set at cpu_mask in the same compute unit,
- * set current STARTING CPU.
+ * set current ONLINE CPU.
*
* Note: if there is a CPU aside of the new one already in the
* sibling mask, then it is also in cpu_mask.
@@ -263,33 +264,9 @@ static void power_cpu_init(int cpu)
target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
if (target >= nr_cpumask_bits)
cpumask_set_cpu(cpu, &cpu_mask);
+ return 0;
}
-static int
-power_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DOWN_FAILED:
- case CPU_STARTING:
- power_cpu_init(cpu);
- break;
- case CPU_DOWN_PREPARE:
- power_cpu_exit(cpu);
- break;
- default:
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block power_cpu_notifier_nb = {
- .notifier_call = power_cpu_notifier,
- .priority = CPU_PRI_PERF,
-};
-
static const struct x86_cpu_id cpu_match[] = {
{ .vendor = X86_VENDOR_AMD, .family = 0x15 },
{},
@@ -297,7 +274,7 @@ static const struct x86_cpu_id cpu_match[] = {
static int __init amd_power_pmu_init(void)
{
- int cpu, target, ret;
+ int ret;
if (!x86_match_cpu(cpu_match))
return 0;
@@ -312,38 +289,25 @@ static int __init amd_power_pmu_init(void)
return -ENODEV;
}
- cpu_notifier_register_begin();
- /* Choose one online core of each compute unit. */
- for_each_online_cpu(cpu) {
- target = cpumask_first(topology_sibling_cpumask(cpu));
- if (!cpumask_test_cpu(target, &cpu_mask))
- cpumask_set_cpu(target, &cpu_mask);
- }
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
+ "AP_PERF_X86_AMD_POWER_ONLINE",
+ power_cpu_init, power_cpu_exit);
ret = perf_pmu_register(&pmu_class, "power", -1);
if (WARN_ON(ret)) {
pr_warn("AMD Power PMU registration failed\n");
- goto out;
+ return ret;
}
- __register_cpu_notifier(&power_cpu_notifier_nb);
-
pr_info("AMD Power PMU detected\n");
-
-out:
- cpu_notifier_register_done();
-
return ret;
}
module_init(amd_power_pmu_init);
static void __exit amd_power_pmu_exit(void)
{
- cpu_notifier_register_begin();
- __unregister_cpu_notifier(&power_cpu_notifier_nb);
- cpu_notifier_register_done();
-
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE);
perf_pmu_unregister(&pmu_class);
}
module_exit(amd_power_pmu_exit);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 98ac57381bf9..e6131d4454e6 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -358,7 +358,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
return this;
}
-static void amd_uncore_cpu_starting(unsigned int cpu)
+static int amd_uncore_cpu_starting(unsigned int cpu)
{
unsigned int eax, ebx, ecx, edx;
struct amd_uncore *uncore;
@@ -384,6 +384,8 @@ static void amd_uncore_cpu_starting(unsigned int cpu)
uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
}
+
+ return 0;
}
static void uncore_online(unsigned int cpu,
@@ -398,13 +400,15 @@ static void uncore_online(unsigned int cpu,
cpumask_set_cpu(cpu, uncore->active_mask);
}
-static void amd_uncore_cpu_online(unsigned int cpu)
+static int amd_uncore_cpu_online(unsigned int cpu)
{
if (amd_uncore_nb)
uncore_online(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_online(cpu, amd_uncore_l2);
+
+ return 0;
}
static void uncore_down_prepare(unsigned int cpu,
@@ -433,13 +437,15 @@ static void uncore_down_prepare(unsigned int cpu,
}
}
-static void amd_uncore_cpu_down_prepare(unsigned int cpu)
+static int amd_uncore_cpu_down_prepare(unsigned int cpu)
{
if (amd_uncore_nb)
uncore_down_prepare(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_down_prepare(cpu, amd_uncore_l2);
+
+ return 0;
}
static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
@@ -454,74 +460,19 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
*per_cpu_ptr(uncores, cpu) = NULL;
}
-static void amd_uncore_cpu_dead(unsigned int cpu)
+static int amd_uncore_cpu_dead(unsigned int cpu)
{
if (amd_uncore_nb)
uncore_dead(cpu, amd_uncore_nb);
if (amd_uncore_l2)
uncore_dead(cpu, amd_uncore_l2);
-}
-
-static int
-amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
- void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- if (amd_uncore_cpu_up_prepare(cpu))
- return notifier_from_errno(-ENOMEM);
- break;
-
- case CPU_STARTING:
- amd_uncore_cpu_starting(cpu);
- break;
-
- case CPU_ONLINE:
- amd_uncore_cpu_online(cpu);
- break;
-
- case CPU_DOWN_PREPARE:
- amd_uncore_cpu_down_prepare(cpu);
- break;
-
- case CPU_UP_CANCELED:
- case CPU_DEAD:
- amd_uncore_cpu_dead(cpu);
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block amd_uncore_cpu_notifier_block = {
- .notifier_call = amd_uncore_cpu_notifier,
- .priority = CPU_PRI_PERF + 1,
-};
-
-static void __init init_cpu_already_online(void *dummy)
-{
- unsigned int cpu = smp_processor_id();
-
- amd_uncore_cpu_starting(cpu);
- amd_uncore_cpu_online(cpu);
-}
-static void cleanup_cpu_online(void *dummy)
-{
- unsigned int cpu = smp_processor_id();
-
- amd_uncore_cpu_dead(cpu);
+ return 0;
}
static int __init amd_uncore_init(void)
{
- unsigned int cpu, cpu2;
int ret = -ENODEV;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
@@ -558,38 +509,29 @@ static int __init amd_uncore_init(void)
ret = 0;
}
- if (ret)
- goto fail_nodev;
-
- cpu_notifier_register_begin();
-
- /* init cpus already online before registering for hotplug notifier */
- for_each_online_cpu(cpu) {
- ret = amd_uncore_cpu_up_prepare(cpu);
- if (ret)
- goto fail_online;
- smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
- }
-
- __register_cpu_notifier(&amd_uncore_cpu_notifier_block);
- cpu_notifier_register_done();
-
+ /*
+ * Install callbacks. Core will call them for each online cpu.
+ */
+ if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
+ "PERF_X86_AMD_UNCORE_PREP",
+ amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
+ goto fail_l2;
+
+ if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
+ "AP_PERF_X86_AMD_UNCORE_STARTING",
+ amd_uncore_cpu_starting, NULL))
+ goto fail_prep;
+ if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
+ "AP_PERF_X86_AMD_UNCORE_ONLINE",
+ amd_uncore_cpu_online,
+ amd_uncore_cpu_down_prepare))
+ goto fail_start;
return 0;
-
-fail_online:
- for_each_online_cpu(cpu2) {
- if (cpu2 == cpu)
- break;
- smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1);
- }
- cpu_notifier_register_done();
-
- /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
- amd_uncore_nb = amd_uncore_l2 = NULL;
-
- if (boot_cpu_has(X86_FEATURE_PERFCTR_L2))
- perf_pmu_unregister(&amd_l2_pmu);
+fail_start:
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
+fail_prep:
+ cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
fail_l2:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index dfebbde2a4cc..c17f0de5fd39 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1477,49 +1477,49 @@ NOKPROBE_SYMBOL(perf_event_nmi_handler);
struct event_constraint emptyconstraint;
struct event_constraint unconstrained;
-static int
-x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+static int x86_pmu_prepare_cpu(unsigned int cpu)
{
- unsigned int cpu = (long)hcpu;
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
- int i, ret = NOTIFY_OK;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
- cpuc->kfree_on_online[i] = NULL;
- if (x86_pmu.cpu_prepare)
- ret = x86_pmu.cpu_prepare(cpu);
- break;
-
- case CPU_STARTING:
- if (x86_pmu.cpu_starting)
- x86_pmu.cpu_starting(cpu);
- break;
+ int i;
- case CPU_ONLINE:
- for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
- kfree(cpuc->kfree_on_online[i]);
- cpuc->kfree_on_online[i] = NULL;
- }
- break;
+ for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
+ cpuc->kfree_on_online[i] = NULL;
+ if (x86_pmu.cpu_prepare)
+ return x86_pmu.cpu_prepare(cpu);
+ return 0;
+}
- case CPU_DYING:
- if (x86_pmu.cpu_dying)
- x86_pmu.cpu_dying(cpu);
- break;
+static int x86_pmu_dead_cpu(unsigned int cpu)
+{
+ if (x86_pmu.cpu_dead)
+ x86_pmu.cpu_dead(cpu);
+ return 0;
+}
- case CPU_UP_CANCELED:
- case CPU_DEAD:
- if (x86_pmu.cpu_dead)
- x86_pmu.cpu_dead(cpu);
- break;
+static int x86_pmu_online_cpu(unsigned int cpu)
+{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ int i;
- default:
- break;
+ for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
+ kfree(cpuc->kfree_on_online[i]);
+ cpuc->kfree_on_online[i] = NULL;
}
+ return 0;
+}
- return ret;
+static int x86_pmu_starting_cpu(unsigned int cpu)
+{
+ if (x86_pmu.cpu_starting)
+ x86_pmu.cpu_starting(cpu);
+ return 0;
+}
+
+static int x86_pmu_dying_cpu(unsigned int cpu)
+{
+ if (x86_pmu.cpu_dying)
+ x86_pmu.cpu_dying(cpu);
+ return 0;
}
static void __init pmu_check_apic(void)
@@ -1787,10 +1787,39 @@ static int __init init_hw_perf_events(void)
pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed);
pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl);
- perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
- perf_cpu_notifier(x86_pmu_notifier);
+ /*
+ * Install callbacks. Core will call them for each online
+ * cpu.
+ */
+ err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+ x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
+ if (err)
+ return err;
+
+ err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
+ "AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+ x86_pmu_dying_cpu);
+ if (err)
+ goto out;
+
+ err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+ x86_pmu_online_cpu, NULL);
+ if (err)
+ goto out1;
+
+ err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+ if (err)
+ goto out2;
return 0;
+
+out2:
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE);
+out1:
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING);
+out:
+ cpuhp_remove_state(CPUHP_PERF_X86_PREPARE);
+ return err;
}
early_initcall(init_hw_perf_events);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 0974ba11e954..2cbde2f449aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3109,7 +3109,7 @@ static int intel_pmu_cpu_prepare(int cpu)
cpuc->excl_thread_id = 0;
}
- return NOTIFY_OK;
+ return 0;
err_constraint_list:
kfree(cpuc->constraint_list);
@@ -3120,7 +3120,7 @@ err_shared_regs:
cpuc->shared_regs = NULL;
err:
- return NOTIFY_BAD;
+ return -ENOMEM;
}
static void intel_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 7b5fd811ef45..783c49ddef29 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1577,7 +1577,7 @@ static inline void cqm_pick_event_reader(int cpu)
cpumask_set_cpu(cpu, &cqm_cpumask);
}
-static void intel_cqm_cpu_starting(unsigned int cpu)
+static int intel_cqm_cpu_starting(unsigned int cpu)
{
struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1588,39 +1588,26 @@ static void intel_cqm_cpu_starting(unsigned int cpu)
WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
+
+ cqm_pick_event_reader(cpu);
+ return 0;
}
-static void intel_cqm_cpu_exit(unsigned int cpu)
+static int intel_cqm_cpu_exit(unsigned int cpu)
{
int target;
/* Is @cpu the current cqm reader for this package ? */
if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
- return;
+ return 0;
/* Find another online reader in this package */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
if (target < nr_cpu_ids)
cpumask_set_cpu(target, &cqm_cpumask);
-}
-
-static int intel_cqm_cpu_notifier(struct notifier_block *nb,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DOWN_PREPARE:
- intel_cqm_cpu_exit(cpu);
- break;
- case CPU_STARTING:
- intel_cqm_cpu_starting(cpu);
- cqm_pick_event_reader(cpu);
- break;
- }
- return NOTIFY_OK;
+ return 0;
}
static const struct x86_cpu_id intel_cqm_match[] = {
@@ -1682,7 +1669,7 @@ out:
static int __init intel_cqm_init(void)
{
char *str = NULL, scale[20];
- int i, cpu, ret;
+ int cpu, ret;
if (x86_match_cpu(intel_cqm_match))
cqm_enabled = true;
@@ -1705,8 +1692,7 @@ static int __init intel_cqm_init(void)
*
* Also, check that the scales match on all cpus.
*/
- cpu_notifier_register_begin();
-
+ get_online_cpus();
for_each_online_cpu(cpu) {
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1743,11 +1729,6 @@ static int __init intel_cqm_init(void)
if (ret)
goto out;
- for_each_online_cpu(i) {
- intel_cqm_cpu_starting(i);
- cqm_pick_event_reader(i);
- }
-
if (mbm_enabled)
ret = intel_mbm_init();
if (ret && !cqm_enabled)
@@ -1772,12 +1753,18 @@ static int __init intel_cqm_init(void)
pr_info("Intel MBM enabled\n");
/*
- * Register the hot cpu notifier once we are sure cqm
+ * Setup the hot cpu notifier once we are sure cqm
* is enabled to avoid notifier leak.
*/
- __perf_cpu_notifier(intel_cqm_cpu_notifier);
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
+ "AP_PERF_X86_CQM_STARTING",
+ intel_cqm_cpu_starting, NULL);
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+ NULL, intel_cqm_cpu_exit);
+
out:
- cpu_notifier_register_done();
+ put_online_cpus();
+
if (ret) {
kfree(str);
cqm_cleanup();
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4c7638b91fa5..3ca87b5a8677 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -366,7 +366,7 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode)
* Check if exiting cpu is the designated reader. If so migrate the
* events when there is a valid target available
*/
-static void cstate_cpu_exit(int cpu)
+static int cstate_cpu_exit(unsigned int cpu)
{
unsigned int target;
@@ -391,9 +391,10 @@ static void cstate_cpu_exit(int cpu)
perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
}
}
+ return 0;
}
-static void cstate_cpu_init(int cpu)
+static int cstate_cpu_init(unsigned int cpu)
{
unsigned int target;
@@ -415,31 +416,10 @@ static void cstate_cpu_init(int cpu)
topology_core_cpumask(cpu));
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
-}
-static int cstate_cpu_notifier(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- cstate_cpu_init(cpu);
- break;
- case CPU_DOWN_PREPARE:
- cstate_cpu_exit(cpu);
- break;
- default:
- break;
- }
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block cstate_cpu_nb = {
- .notifier_call = cstate_cpu_notifier,
- .priority = CPU_PRI_PERF + 1,
-};
-
static struct pmu cstate_core_pmu = {
.attr_groups = core_attr_groups,
.name = "cstate_core",
@@ -600,18 +580,20 @@ static inline void cstate_cleanup(void)
static int __init cstate_init(void)
{
- int cpu, err;
+ int err;
- cpu_notifier_register_begin();
- for_each_online_cpu(cpu)
- cstate_cpu_init(cpu);
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
+ "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init,
+ NULL);
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
+ "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit);
if (has_cstate_core) {
err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
if (err) {
has_cstate_core = false;
pr_info("Failed to register cstate core pmu\n");
- goto out;
+ return err;
}
}
@@ -621,12 +603,10 @@ static int __init cstate_init(void)
has_cstate_pkg = false;
pr_info("Failed to register cstate pkg pmu\n");
cstate_cleanup();
- goto out;
+ return err;
}
}
- __register_cpu_notifier(&cstate_cpu_nb);
-out:
- cpu_notifier_register_done();
+
return err;
}
@@ -652,9 +632,8 @@ module_init(cstate_pmu_init);
static void __exit cstate_pmu_exit(void)
{
- cpu_notifier_register_begin();
- __unregister_cpu_notifier(&cstate_cpu_nb);
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
cstate_cleanup();
- cpu_notifier_register_done();
}
module_exit(cstate_pmu_exit);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index d0c58b35155f..28865938aadf 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -556,14 +556,14 @@ const struct attribute_group *rapl_attr_groups[] = {
NULL,
};
-static void rapl_cpu_exit(int cpu)
+static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
int target;
/* Check if exiting cpu is used for collecting rapl events */
if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
- return;
+ return 0;
pmu->cpu = -1;
/* Find a new cpu to collect rapl events */
@@ -575,9 +575,10 @@ static void rapl_cpu_exit(int cpu)
pmu->cpu = target;
perf_pmu_migrate_context(pmu->pmu, cpu, target);
}
+ return 0;
}
-static void rapl_cpu_init(int cpu)
+static int rapl_cpu_online(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
int target;
@@ -588,13 +589,14 @@ static void rapl_cpu_init(int cpu)
*/
target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
if (target < nr_cpu_ids)
- return;
+ return 0;
cpumask_set_cpu(cpu, &rapl_cpu_mask);
pmu->cpu = cpu;
+ return 0;
}
-static int rapl_cpu_prepare(int cpu)
+static int rapl_cpu_prepare(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -615,33 +617,6 @@ static int rapl_cpu_prepare(int cpu)
return 0;
}
-static int rapl_cpu_notifier(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- rapl_cpu_prepare(cpu);
- break;
-
- case CPU_DOWN_FAILED:
- case CPU_ONLINE:
- rapl_cpu_init(cpu);
- break;
-
- case CPU_DOWN_PREPARE:
- rapl_cpu_exit(cpu);
- break;
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block rapl_cpu_nb = {
- .notifier_call = rapl_cpu_notifier,
- .priority = CPU_PRI_PERF + 1,
-};
-
static int rapl_check_hw_unit(bool apply_quirk)
{
u64 msr_rapl_power_unit_bits;
@@ -692,24 +667,6 @@ static void __init rapl_advertise(void)
}
}
-static int __init rapl_prepare_cpus(void)
-{
- unsigned int cpu, pkg;
- int ret;
-
- for_each_online_cpu(cpu) {
- pkg = topology_logical_package_id(cpu);
- if (rapl_pmus->pmus[pkg])
- continue;
-
- ret = rapl_cpu_prepare(cpu);
- if (ret)
- return ret;
- rapl_cpu_init(cpu);
- }
- return 0;
-}
-
static void cleanup_rapl_pmus(void)
{
int i;
@@ -837,35 +794,44 @@ static int __init rapl_pmu_init(void)
if (ret)
return ret;
- cpu_notifier_register_begin();
+ /*
+ * Install callbacks. Core will call them for each online cpu.
+ */
- ret = rapl_prepare_cpus();
+ ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+ rapl_cpu_prepare, NULL);
if (ret)
goto out;
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
+ "AP_PERF_X86_RAPL_ONLINE",
+ rapl_cpu_online, rapl_cpu_offline);
+ if (ret)
+ goto out1;
+
ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
if (ret)
- goto out;
+ goto out2;
- __register_cpu_notifier(&rapl_cpu_nb);
- cpu_notifier_register_done();
rapl_advertise();
return 0;
+out2:
+ cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+out1:
+ cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
out:
pr_warn("Initialization failed (%d), disabled\n", ret);
cleanup_rapl_pmus();
- cpu_notifier_register_done();
return ret;
}
module_init(rapl_pmu_init);
static void __exit intel_rapl_exit(void)
{
- cpu_notifier_register_begin();
- __unregister_cpu_notifier(&rapl_cpu_nb);
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+ cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
perf_pmu_unregister(&rapl_pmus->pmu);
cleanup_rapl_pmus();
- cpu_notifier_register_done();
}
module_exit(intel_rapl_exit);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 59b4974c697f..3f3d0d67749b 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1052,7 +1052,7 @@ static void uncore_pci_exit(void)
}
}
-static void uncore_cpu_dying(int cpu)
+static int uncore_cpu_dying(unsigned int cpu)
{
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_pmu *pmu;
@@ -1069,16 +1069,19 @@ static void uncore_cpu_dying(int cpu)
uncore_box_exit(box);
}
}
+ return 0;
}
-static void uncore_cpu_starting(int cpu, bool init)
+static int first_init;
+
+static int uncore_cpu_starting(unsigned int cpu)
{
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
int i, pkg, ncpus = 1;
- if (init) {
+ if (first_init) {
/*
* On init we get the number of online cpus in the package
* and set refcount for all of them.
@@ -1099,9 +1102,11 @@ static void uncore_cpu_starting(int cpu, bool init)
uncore_box_init(box);
}
}
+
+ return 0;
}
-static int uncore_cpu_prepare(int cpu)
+static int uncore_cpu_prepare(unsigned int cpu)
{
struct intel_uncore_type *type, **types = uncore_msr_uncores;
struct intel_uncore_pmu *pmu;
@@ -1164,13 +1169,13 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}
-static void uncore_event_exit_cpu(int cpu)
+static int uncore_event_cpu_offline(unsigned int cpu)
{
int target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
- return;
+ return 0;
/* Find a new cpu to collect uncore events */
target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
@@ -1183,9 +1188,10 @@ static void uncore_event_exit_cpu(int cpu)
uncore_change_context(uncore_msr_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
+ return 0;
}
-static void uncore_event_init_cpu(int cpu)
+static int uncore_event_cpu_online(unsigned int cpu)
{
int target;
@@ -1195,50 +1201,15 @@ static void uncore_event_init_cpu(int cpu)
*/
target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
if (target < nr_cpu_ids)
- return;
+ return 0;
cpumask_set_cpu(cpu, &uncore_cpu_mask);
uncore_change_context(uncore_msr_uncores, -1, cpu);
uncore_change_context(uncore_pci_uncores, -1, cpu);
+ return 0;
}
-static int uncore_cpu_notifier(struct notifier_block *self,
- unsigned long action, void *hcpu)
-{
- unsigned int cpu = (long)hcpu;
-
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_UP_PREPARE:
- return notifier_from_errno(uncore_cpu_prepare(cpu));
-
- case CPU_STARTING:
- uncore_cpu_starting(cpu, false);
- case CPU_DOWN_FAILED:
- uncore_event_init_cpu(cpu);
- break;
-
- case CPU_UP_CANCELED:
- case CPU_DYING:
- uncore_cpu_dying(cpu);
- break;
-
- case CPU_DOWN_PREPARE:
- uncore_event_exit_cpu(cpu);
- break;
- }
- return NOTIFY_OK;
-}
-
-static struct notifier_block uncore_cpu_nb = {
- .notifier_call = uncore_cpu_notifier,
- /*
- * to migrate uncore events, our notifier should be executed
- * before perf core's notifier.
- */
- .priority = CPU_PRI_PERF + 1,
-};
-
static int __init type_pmu_register(struct intel_uncore_type *type)
{
int i, ret;
@@ -1282,41 +1253,6 @@ err:
return ret;
}
-static void __init uncore_cpu_setup(void *dummy)
-{
- uncore_cpu_starting(smp_processor_id(), true);
-}
-
-/* Lazy to avoid allocation of a few bytes for the normal case */
-static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC);
-
-static int __init uncore_cpumask_init(bool msr)
-{
- unsigned int cpu;
-
- for_each_online_cpu(cpu) {
- unsigned int pkg = topology_logical_package_id(cpu);
- int ret;
-
- if (test_and_set_bit(pkg, packages))
- continue;
- /*
- * The first online cpu of each package allocates and takes
- * the refcounts for all other online cpus in that package.
- * If msrs are not enabled no allocation is required.
- */
- if (msr) {
- ret = uncore_cpu_prepare(cpu);
- if (ret)
- return ret;
- }
- uncore_event_init_cpu(cpu);
- smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1);
- }
- __register_cpu_notifier(&uncore_cpu_nb);
- return 0;
-}
-
#define X86_UNCORE_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
@@ -1440,11 +1376,33 @@ static int __init intel_uncore_init(void)
if (cret && pret)
return -ENODEV;
- cpu_notifier_register_begin();
- ret = uncore_cpumask_init(!cret);
- if (ret)
- goto err;
- cpu_notifier_register_done();
+ /*
+ * Install callbacks. Core will call them for each online cpu.
+ *
+ * The first online cpu of each package allocates and takes
+ * the refcounts for all other online cpus in that package.
+ * If msrs are not enabled no allocation is required and
+ * uncore_cpu_prepare() is not called for each online cpu.
+ */
+ if (!cret) {
+ ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
+ "PERF_X86_UNCORE_PREP",
+ uncore_cpu_prepare, NULL);
+ if (ret)
+ goto err;
+ } else {
+ cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
+ "PERF_X86_UNCORE_PREP",
+ uncore_cpu_prepare, NULL);
+ }
+ first_init = 1;
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
+ "AP_PERF_X86_UNCORE_STARTING",
+ uncore_cpu_starting, uncore_cpu_dying);
+ first_init = 0;
+ cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+ "AP_PERF_X86_UNCORE_ONLINE",
+ uncore_event_cpu_online, uncore_event_cpu_offline);
return 0;
err:
@@ -1452,17 +1410,16 @@ err:
on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
- cpu_notifier_register_done();
return ret;
}
module_init(intel_uncore_init);
static void __exit intel_uncore_exit(void)
{
- cpu_notifier_register_begin();
- __unregister_cpu_notifier(&uncore_cpu_nb);
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
+ cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
+ cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
uncore_types_exit(uncore_msr_uncores);
uncore_pci_exit();
- cpu_notifier_register_done();
}
module_exit(intel_uncore_exit);
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 94c18ebfd68c..5391b0ae7cc3 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -145,7 +145,6 @@ static inline void disable_acpi(void) { }
#define ARCH_HAS_POWER_INIT 1
#ifdef CONFIG_ACPI_NUMA
-extern int acpi_numa;
extern int x86_acpi_numa_init(void);
#endif /* CONFIG_ACPI_NUMA */
@@ -170,4 +169,6 @@ static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
}
#endif
+#define ACPI_TABLE_UPGRADE_MAX_PHYS (max_low_pfn_mapped << PAGE_SHIFT)
+
#endif /* _ASM_X86_ACPI_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 59d34c521d96..9b7fa6313f1a 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -16,6 +16,7 @@ extern void prefill_possible_map(void);
static inline void prefill_possible_map(void) {}
#define cpu_physical_id(cpu) boot_cpu_physical_apicid
+#define cpu_acpi_id(cpu) 0
#define safe_smp_processor_id() 0
#endif /* CONFIG_SMP */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c64b1e9c5d1a..d683993248c8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -225,7 +225,6 @@
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 574c23cf761a..b6d425999f99 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -81,7 +81,11 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
struct page *page;
- page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
+ gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;
+
+ if (mm == &init_mm)
+ gfp &= ~__GFP_ACCOUNT;
+ page = alloc_pages(gfp, 0);
if (!page)
return NULL;
if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +129,11 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pud_t *)get_zeroed_page(GFP_KERNEL);
+ gfp_t gfp = GFP_KERNEL_ACCOUNT;
+
+ if (mm == &init_mm)
+ gfp &= ~__GFP_ACCOUNT;
+ return (pud_t *)get_zeroed_page(gfp);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index fbc5e92e1ecc..643eba42d620 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -26,13 +26,11 @@
* @n: length of the copy in bytes
*
* Copy data to persistent memory media via non-temporal stores so that
- * a subsequent arch_wmb_pmem() can flush cpu and memory controller
- * write buffers to guarantee durability.
+ * a subsequent pmem driver flush operation will drain posted write queues.
*/
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
- size_t n)
+static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
{
- int unwritten;
+ int rem;
/*
* We are copying between two kernel buffers, if
@@ -40,59 +38,36 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
* fault) we would have already reported a general protection fault
* before the WARN+BUG.
*/
- unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
- (void __user *) src, n);
- if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
- __func__, dst, src, unwritten))
+ rem = __copy_from_user_inatomic_nocache(dst, (void __user *) src, n);
+ if (WARN(rem, "%s: fault copying %p <- %p unwritten: %d\n",
+ __func__, dst, src, rem))
BUG();
}
-static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
- size_t n)
+static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
{
if (static_cpu_has(X86_FEATURE_MCE_RECOVERY))
- return memcpy_mcsafe(dst, (void __force *) src, n);
- memcpy(dst, (void __force *) src, n);
+ return memcpy_mcsafe(dst, src, n);
+ memcpy(dst, src, n);
return 0;
}
/**
- * arch_wmb_pmem - synchronize writes to persistent memory
- *
- * After a series of arch_memcpy_to_pmem() operations this drains data
- * from cpu write buffers and any platform (memory controller) buffers
- * to ensure that written data is durable on persistent memory media.
- */
-static inline void arch_wmb_pmem(void)
-{
- /*
- * wmb() to 'sfence' all previous writes such that they are
- * architecturally visible to 'pcommit'. Note, that we've
- * already arranged for pmem writes to avoid the cache via
- * arch_memcpy_to_pmem().
- */
- wmb();
- pcommit_sfence();
-}
-
-/**
* arch_wb_cache_pmem - write back a cache range with CLWB
* @vaddr: virtual start address
* @size: number of bytes to write back
*
* Write back a cache range using the CLWB (cache line write back)
- * instruction. This function requires explicit ordering with an
- * arch_wmb_pmem() call.
+ * instruction.
*/
-static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
{
u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
unsigned long clflush_mask = x86_clflush_size - 1;
- void *vaddr = (void __force *)addr;
- void *vend = vaddr + size;
+ void *vend = addr + size;
void *p;
- for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ for (p = (void *)((unsigned long)addr & ~clflush_mask);
p < vend; p += x86_clflush_size)
clwb(p);
}
@@ -113,16 +88,14 @@ static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
* @i: iterator with source data
*
* Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
- * This function requires explicit ordering with an arch_wmb_pmem() call.
*/
-static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
struct iov_iter *i)
{
- void *vaddr = (void __force *)addr;
size_t len;
/* TODO: skip the write-back by always using non-temporal stores */
- len = copy_from_iter_nocache(vaddr, bytes, i);
+ len = copy_from_iter_nocache(addr, bytes, i);
if (__iter_needs_pmem_wb(i))
arch_wb_cache_pmem(addr, bytes);
@@ -136,28 +109,16 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
* @size: number of bytes to zero
*
* Write zeros into the memory range starting at 'addr' for 'size' bytes.
- * This function requires explicit ordering with an arch_wmb_pmem() call.
*/
-static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+static inline void arch_clear_pmem(void *addr, size_t size)
{
- void *vaddr = (void __force *)addr;
-
- memset(vaddr, 0, size);
+ memset(addr, 0, size);
arch_wb_cache_pmem(addr, size);
}
-static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+static inline void arch_invalidate_pmem(void *addr, size_t size)
{
- clflush_cache_range((void __force *) addr, size);
-}
-
-static inline bool __arch_has_wmb_pmem(void)
-{
- /*
- * We require that wmb() be an 'sfence', that is only guaranteed on
- * 64-bit builds
- */
- return static_cpu_has(X86_FEATURE_PCOMMIT);
+ clflush_cache_range(addr, size);
}
#endif /* CONFIG_ARCH_HAS_PMEM_API */
#endif /* __ASM_X86_PMEM_H__ */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index c9734dc76257..ebd0c164cd4e 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -33,6 +33,7 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
}
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
@@ -148,6 +149,7 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle);
void smp_store_boot_cpu_info(void);
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
+#define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu)
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d96d04377765..587d7914ea4b 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -253,52 +253,6 @@ static inline void clwb(volatile void *__p)
: [pax] "a" (p));
}
-/**
- * pcommit_sfence() - persistent commit and fence
- *
- * The PCOMMIT instruction ensures that data that has been flushed from the
- * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
- * memory and is durable on the DIMM. The primary use case for this is
- * persistent memory.
- *
- * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
- * with appropriate fencing.
- *
- * Example:
- * void flush_and_commit_buffer(void *vaddr, unsigned int size)
- * {
- * unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
- * void *vend = vaddr + size;
- * void *p;
- *
- * for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
- * p < vend; p += boot_cpu_data.x86_clflush_size)
- * clwb(p);
- *
- * // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
- * // MFENCE via mb() also works
- * wmb();
- *
- * // PCOMMIT and the required SFENCE for ordering
- * pcommit_sfence();
- * }
- *
- * After this function completes the data pointed to by 'vaddr' has been
- * accepted to memory and will be durable if the 'vaddr' points to persistent
- * memory.
- *
- * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
- * things we include both the PCOMMIT and the required SFENCE in the
- * alternatives generated by pcommit_sfence().
- */
-static inline void pcommit_sfence(void)
-{
- alternative(ASM_NOP7,
- ".byte 0x66, 0x0f, 0xae, 0xf8\n\t" /* pcommit */
- "sfence",
- X86_FEATURE_PCOMMIT);
-}
-
#define nop() asm volatile ("nop")
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 14c63c7e8337..a002b07a7099 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,6 @@
#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
#define SECONDARY_EXEC_ENABLE_PML 0x00020000
#define SECONDARY_EXEC_XSAVES 0x00100000
-#define SECONDARY_EXEC_PCOMMIT 0x00200000
#define SECONDARY_EXEC_TSC_SCALING 0x02000000
#define PIN_BASED_EXT_INTR_MASK 0x00000001
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 0d809e9fc975..3bdd10d71223 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -76,15 +76,18 @@
/*
* Leaf 5 (0x40000x04)
* HVM-specific features
+ * EAX: Features
+ * EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
*/
-/* EAX Features */
/* Virtualized APIC registers */
#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
/* Virtualized x2APIC accesses */
#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1)
/* Memory mapped from other domains has valid IOMMU entries */
#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2)
+/* vcpu id is present in EBX */
+#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3)
#define XEN_CPUID_MAX_NUM_LEAVES 4
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 5b15d94a33f8..37fee272618f 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -78,7 +78,6 @@
#define EXIT_REASON_PML_FULL 62
#define EXIT_REASON_XSAVES 63
#define EXIT_REASON_XRSTORS 64
-#define EXIT_REASON_PCOMMIT 65
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -127,8 +126,7 @@
{ EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }, \
{ EXIT_REASON_XSAVES, "XSAVES" }, \
- { EXIT_REASON_XRSTORS, "XRSTORS" }, \
- { EXIT_REASON_PCOMMIT, "PCOMMIT" }
+ { EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 9414f84584e4..6738e5c82cca 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -161,13 +161,15 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
/**
* acpi_register_lapic - register a local apic and generates a logic cpu number
* @id: local apic id to register
+ * @acpiid: ACPI id to register
* @enabled: this cpu is enabled or not
*
* Returns the logic cpu number which maps to the local apic
*/
-static int acpi_register_lapic(int id, u8 enabled)
+static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
{
unsigned int ver = 0;
+ int cpu;
if (id >= MAX_LOCAL_APIC) {
printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
@@ -182,7 +184,11 @@ static int acpi_register_lapic(int id, u8 enabled)
if (boot_cpu_physical_apicid != -1U)
ver = apic_version[boot_cpu_physical_apicid];
- return generic_processor_info(id, ver);
+ cpu = generic_processor_info(id, ver);
+ if (cpu >= 0)
+ early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
+
+ return cpu;
}
static int __init
@@ -212,7 +218,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
if (!apic->apic_id_valid(apic_id) && enabled)
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
else
- acpi_register_lapic(apic_id, enabled);
+ acpi_register_lapic(apic_id, processor->uid, enabled);
#else
printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
#endif
@@ -240,6 +246,7 @@ acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end)
* when we use CPU hotplug.
*/
acpi_register_lapic(processor->id, /* APIC ID */
+ processor->processor_id, /* ACPI ID */
processor->lapic_flags & ACPI_MADT_ENABLED);
return 0;
@@ -258,6 +265,7 @@ acpi_parse_sapic(struct acpi_subtable_header *header, const unsigned long end)
acpi_table_print_madt_entry(header);
acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */
+ processor->processor_id, /* ACPI ID */
processor->lapic_flags & ACPI_MADT_ENABLED);
return 0;
@@ -714,7 +722,7 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
{
int cpu;
- cpu = acpi_register_lapic(physid, ACPI_MADT_ENABLED);
+ cpu = acpi_register_lapic(physid, U32_MAX, ACPI_MADT_ENABLED);
if (cpu < 0) {
pr_info(PREFIX "Unable to map lapic to logical cpu number\n");
return cpu;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index cefacbad1531..456316f6c868 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -215,26 +215,18 @@ void apbt_setup_secondary_clock(void)
* cpu timers during the offline process due to the ordering of notification.
* the extra interrupt is harmless.
*/
-static int apbt_cpuhp_notify(struct notifier_block *n,
- unsigned long action, void *hcpu)
+static int apbt_cpu_dead(unsigned int cpu)
{
- unsigned long cpu = (unsigned long)hcpu;
struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu);
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_DEAD:
- dw_apb_clockevent_pause(adev->timer);
- if (system_state == SYSTEM_RUNNING) {
- pr_debug("skipping APBT CPU %lu offline\n", cpu);
- } else {
- pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
- dw_apb_clockevent_stop(adev->timer);
- }
- break;
- default:
- pr_debug("APBT notified %lu, no action\n", action);
+ dw_apb_clockevent_pause(adev->timer);
+ if (system_state == SYSTEM_RUNNING) {
+ pr_debug("skipping APBT CPU %u offline\n", cpu);
+ } else {
+ pr_debug("APBT clockevent for cpu %u offline\n", cpu);
+ dw_apb_clockevent_stop(adev->timer);
}
- return NOTIFY_OK;
+ return 0;
}
static __init int apbt_late_init(void)
@@ -242,9 +234,8 @@ static __init int apbt_late_init(void)
if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
!apb_timer_block_enabled)
return 0;
- /* This notifier should be called after workqueue is ready */
- hotcpu_notifier(apbt_cpuhp_notify, -20);
- return 0;
+ return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+ apbt_cpu_dead);
}
fs_initcall(apbt_late_init);
#else
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f943d2f453a4..ac8d8ad8b009 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -92,8 +92,10 @@ static int apic_extnmi = APIC_EXTNMI_BSP;
*/
DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 24170d0809ba..6368fa69d2af 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -152,68 +152,48 @@ static void init_x2apic_ldr(void)
}
}
- /*
- * At CPU state changes, update the x2apic cluster sibling info.
- */
-static int
-update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
+/*
+ * At CPU state changes, update the x2apic cluster sibling info.
+ */
+int x2apic_prepare_cpu(unsigned int cpu)
{
- unsigned int this_cpu = (unsigned long)hcpu;
- unsigned int cpu;
- int err = 0;
-
- switch (action) {
- case CPU_UP_PREPARE:
- if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, this_cpu),
- GFP_KERNEL)) {
- err = -ENOMEM;
- } else if (!zalloc_cpumask_var(&per_cpu(ipi_mask, this_cpu),
- GFP_KERNEL)) {
- free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
- err = -ENOMEM;
- }
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- for_each_online_cpu(cpu) {
- if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
- continue;
- cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
- cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
- }
- free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
- free_cpumask_var(per_cpu(ipi_mask, this_cpu));
- break;
+ if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
+ return -ENOMEM;
+
+ if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) {
+ free_cpumask_var(per_cpu(cpus_in_cluster, cpu));
+ return -ENOMEM;
}
- return notifier_from_errno(err);
+ return 0;
}
-static struct notifier_block x2apic_cpu_notifier = {
- .notifier_call = update_clusterinfo,
-};
-
-static int x2apic_init_cpu_notifier(void)
+int x2apic_dead_cpu(unsigned int this_cpu)
{
- int cpu = smp_processor_id();
-
- zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL);
- zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL);
+ int cpu;
- BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu));
-
- cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
- register_hotcpu_notifier(&x2apic_cpu_notifier);
- return 1;
+ for_each_online_cpu(cpu) {
+ if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
+ continue;
+ cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
+ cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
+ }
+ free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
+ free_cpumask_var(per_cpu(ipi_mask, this_cpu));
+ return 0;
}
static int x2apic_cluster_probe(void)
{
- if (x2apic_mode)
- return x2apic_init_cpu_notifier();
- else
+ int cpu = smp_processor_id();
+
+ if (!x2apic_mode)
return 0;
+
+ cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
+ cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+ x2apic_prepare_cpu, x2apic_dead_cpu);
+ return 1;
}
static const struct cpumask *x2apic_cluster_target_cpus(void)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f112af7aa62e..3d747070fe67 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -710,31 +710,29 @@ static void hpet_work(struct work_struct *w)
complete(&hpet_work->complete);
}
-static int hpet_cpuhp_notify(struct notifier_block *n,
- unsigned long action, void *hcpu)
+static int hpet_cpuhp_online(unsigned int cpu)
{
- unsigned long cpu = (unsigned long)hcpu;
struct hpet_work_struct work;
+
+ INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
+ init_completion(&work.complete);
+ /* FIXME: add schedule_work_on() */
+ schedule_delayed_work_on(cpu, &work.work, 0);
+ wait_for_completion(&work.complete);
+ destroy_delayed_work_on_stack(&work.work);
+ return 0;
+}
+
+static int hpet_cpuhp_dead(unsigned int cpu)
+{
struct hpet_dev *hdev = per_cpu(cpu_hpet_dev, cpu);
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_ONLINE:
- INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
- init_completion(&work.complete);
- /* FIXME: add schedule_work_on() */
- schedule_delayed_work_on(cpu, &work.work, 0);
- wait_for_completion(&work.complete);
- destroy_delayed_work_on_stack(&work.work);
- break;
- case CPU_DEAD:
- if (hdev) {
- free_irq(hdev->irq, hdev);
- hdev->flags &= ~HPET_DEV_USED;
- per_cpu(cpu_hpet_dev, cpu) = NULL;
- }
- break;
- }
- return NOTIFY_OK;
+ if (!hdev)
+ return 0;
+ free_irq(hdev->irq, hdev);
+ hdev->flags &= ~HPET_DEV_USED;
+ per_cpu(cpu_hpet_dev, cpu) = NULL;
+ return 0;
}
#else
@@ -750,11 +748,8 @@ static void hpet_reserve_msi_timers(struct hpet_data *hd)
}
#endif
-static int hpet_cpuhp_notify(struct notifier_block *n,
- unsigned long action, void *hcpu)
-{
- return NOTIFY_OK;
-}
+#define hpet_cpuhp_online NULL
+#define hpet_cpuhp_dead NULL
#endif
@@ -931,7 +926,7 @@ out_nohpet:
*/
static __init int hpet_late_init(void)
{
- int cpu;
+ int ret;
if (boot_hpet_disable)
return -ENODEV;
@@ -961,16 +956,20 @@ static __init int hpet_late_init(void)
if (boot_cpu_has(X86_FEATURE_ARAT))
return 0;
- cpu_notifier_register_begin();
- for_each_online_cpu(cpu) {
- hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
- }
-
/* This notifier should be called after workqueue is ready */
- __hotcpu_notifier(hpet_cpuhp_notify, -20);
- cpu_notifier_register_done();
-
+ ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+ hpet_cpuhp_online, NULL);
+ if (ret)
+ return ret;
+ ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+ hpet_cpuhp_dead);
+ if (ret)
+ goto err_cpuhp;
return 0;
+
+err_cpuhp:
+ cpuhp_remove_state(CPUHP_AP_X86_HPET_ONLINE);
+ return ret;
}
fs_initcall(hpet_late_init);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a2616584b6e9..6cb2b02fcc87 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -400,10 +400,6 @@ static void __init reserve_initrd(void)
memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
}
-static void __init early_initrd_acpi_init(void)
-{
- early_acpi_table_init((void *)initrd_start, initrd_end - initrd_start);
-}
#else
static void __init early_reserve_initrd(void)
{
@@ -411,9 +407,6 @@ static void __init early_reserve_initrd(void)
static void __init reserve_initrd(void)
{
}
-static void __init early_initrd_acpi_init(void)
-{
-}
#endif /* CONFIG_BLK_DEV_INITRD */
static void __init parse_setup_data(void)
@@ -1149,7 +1142,7 @@ void __init setup_arch(char **cmdline_p)
reserve_initrd();
- early_initrd_acpi_init();
+ acpi_table_upgrade();
vsmp_init();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index e4fcb87ba7a6..7a40e068302d 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -236,6 +236,8 @@ void __init setup_per_cpu_areas(void)
early_per_cpu_map(x86_cpu_to_apicid, cpu);
per_cpu(x86_bios_cpu_apicid, cpu) =
early_per_cpu_map(x86_bios_cpu_apicid, cpu);
+ per_cpu(x86_cpu_to_acpiid, cpu) =
+ early_per_cpu_map(x86_cpu_to_acpiid, cpu);
#endif
#ifdef CONFIG_X86_32
per_cpu(x86_cpu_to_logical_apicid, cpu) =
@@ -271,6 +273,7 @@ void __init setup_per_cpu_areas(void)
#ifdef CONFIG_X86_LOCAL_APIC
early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
+ early_per_cpu_ptr(x86_cpu_to_acpiid) = NULL;
#endif
#ifdef CONFIG_X86_32
early_per_cpu_ptr(x86_cpu_to_logical_apicid) = NULL;
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 9b0185fbe3eb..654f6c66fe45 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -323,25 +323,16 @@ static int tboot_wait_for_aps(int num_aps)
return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps);
}
-static int tboot_cpu_callback(struct notifier_block *nfb, unsigned long action,
- void *hcpu)
+static int tboot_dying_cpu(unsigned int cpu)
{
- switch (action) {
- case CPU_DYING:
- atomic_inc(&ap_wfs_count);
- if (num_online_cpus() == 1)
- if (tboot_wait_for_aps(atomic_read(&ap_wfs_count)))
- return NOTIFY_BAD;
- break;
+ atomic_inc(&ap_wfs_count);
+ if (num_online_cpus() == 1) {
+ if (tboot_wait_for_aps(atomic_read(&ap_wfs_count)))
+ return -EBUSY;
}
- return NOTIFY_OK;
+ return 0;
}
-static struct notifier_block tboot_cpu_notifier =
-{
- .notifier_call = tboot_cpu_callback,
-};
-
#ifdef CONFIG_DEBUG_FS
#define TBOOT_LOG_UUID { 0x26, 0x25, 0x19, 0xc0, 0x30, 0x6b, 0xb4, 0x4d, \
@@ -417,8 +408,8 @@ static __init int tboot_late_init(void)
tboot_create_trampoline();
atomic_set(&ap_wfs_count, 0);
- register_hotcpu_notifier(&tboot_cpu_notifier);
-
+ cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+ tboot_dying_cpu);
#ifdef CONFIG_DEBUG_FS
debugfs_create_file("tboot_log", S_IRUSR,
arch_debugfs_dir, NULL, &tboot_log_fops);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7597b42a8a88..643565364497 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -366,7 +366,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
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(AVX512F) | F(AVX512PF) | F(AVX512ER) |
- F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(PCOMMIT);
+ F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB);
/* cpuid 0xD.1.eax */
const u32 kvm_cpuid_D_1_eax_x86_features =
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index e17a74b1d852..35058c2c0eea 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -144,14 +144,6 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
return best && (best->ebx & bit(X86_FEATURE_RTM));
}
-static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_PCOMMIT));
-}
-
static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7758680db20b..df07a0a4611f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2707,8 +2707,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING |
- SECONDARY_EXEC_XSAVES |
- SECONDARY_EXEC_PCOMMIT;
+ SECONDARY_EXEC_XSAVES;
if (enable_ept) {
/* nested EPT: emulate EPT also to L1 */
@@ -3270,7 +3269,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
SECONDARY_EXEC_SHADOW_VMCS |
SECONDARY_EXEC_XSAVES |
SECONDARY_EXEC_ENABLE_PML |
- SECONDARY_EXEC_PCOMMIT |
SECONDARY_EXEC_TSC_SCALING;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
@@ -4858,9 +4856,6 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
if (!enable_pml)
exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
- /* Currently, we allow L1 guest to directly run pcommit instruction. */
- exec_control &= ~SECONDARY_EXEC_PCOMMIT;
-
return exec_control;
}
@@ -4904,9 +4899,10 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
- if (cpu_has_secondary_exec_ctrls())
+ if (cpu_has_secondary_exec_ctrls()) {
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
vmx_secondary_exec_control(vmx));
+ }
if (kvm_vcpu_apicv_active(&vmx->vcpu)) {
vmcs_write64(EOI_EXIT_BITMAP0, 0);
@@ -7564,13 +7560,6 @@ static int handle_pml_full(struct kvm_vcpu *vcpu)
return 1;
}
-static int handle_pcommit(struct kvm_vcpu *vcpu)
-{
- /* we never catch pcommit instruct for L1 guest. */
- WARN_ON(1);
- return 1;
-}
-
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -7621,7 +7610,6 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_XSAVES] = handle_xsaves,
[EXIT_REASON_XRSTORS] = handle_xrstors,
[EXIT_REASON_PML_FULL] = handle_pml_full,
- [EXIT_REASON_PCOMMIT] = handle_pcommit,
};
static const int kvm_vmx_max_exit_handlers =
@@ -7930,8 +7918,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
* the XSS exit bitmap in vmcs12.
*/
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
- case EXIT_REASON_PCOMMIT:
- return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT);
default:
return true;
}
@@ -9094,15 +9080,6 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (cpu_has_secondary_exec_ctrls())
vmcs_set_secondary_exec_control(secondary_exec_ctl);
-
- if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) {
- if (guest_cpuid_has_pcommit(vcpu))
- vmx->nested.nested_vmx_secondary_ctls_high |=
- SECONDARY_EXEC_PCOMMIT;
- else
- vmx->nested.nested_vmx_secondary_ctls_high &=
- ~SECONDARY_EXEC_PCOMMIT;
- }
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -9715,8 +9692,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_APIC_REGISTER_VIRT |
- SECONDARY_EXEC_PCOMMIT);
+ SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
exec_control |= vmcs12->secondary_vm_exec_control;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2766723c951..45608a7da9b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5552,9 +5552,10 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
}
EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
-static void tsc_bad(void *info)
+static int kvmclock_cpu_down_prep(unsigned int cpu)
{
__this_cpu_write(cpu_tsc_khz, 0);
+ return 0;
}
static void tsc_khz_changed(void *data)
@@ -5659,35 +5660,18 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = {
.notifier_call = kvmclock_cpufreq_notifier
};
-static int kvmclock_cpu_notifier(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int kvmclock_cpu_online(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
-
- switch (action) {
- case CPU_ONLINE:
- case CPU_DOWN_FAILED:
- smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
- break;
- case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, tsc_bad, NULL, 1);
- break;
- }
- return NOTIFY_OK;
+ tsc_khz_changed(NULL);
+ return 0;
}
-static struct notifier_block kvmclock_cpu_notifier_block = {
- .notifier_call = kvmclock_cpu_notifier,
- .priority = -INT_MAX
-};
-
static void kvm_timer_init(void)
{
int cpu;
max_tsc_khz = tsc_khz;
- cpu_notifier_register_begin();
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
#ifdef CONFIG_CPU_FREQ
struct cpufreq_policy policy;
@@ -5702,12 +5686,9 @@ static void kvm_timer_init(void)
CPUFREQ_TRANSITION_NOTIFIER);
}
pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
- for_each_online_cpu(cpu)
- smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
-
- __register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
- cpu_notifier_register_done();
+ cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+ kvmclock_cpu_online, kvmclock_cpu_down_prep);
}
static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
@@ -5896,7 +5877,7 @@ void kvm_arch_exit(void)
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
- unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block);
+ cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
#ifdef CONFIG_X86_64
pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
#endif
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index ec378cd7b71e..767be7c76034 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1012,7 +1012,7 @@ GrpTable: Grp15
4: XSAVE
5: XRSTOR | lfence (11B)
6: XSAVEOPT | clwb (66) | mfence (11B)
-7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
+7: clflush | clflushopt (66) | sfence (11B)
EndTable
GrpTable: Grp16
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index d22161ab941d..dc8023060456 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1353,7 +1353,7 @@ good_area:
* the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if
* we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
major |= fault & VM_FAULT_MAJOR;
/*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9c086c57105c..968ac028c34e 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -1,4 +1,5 @@
/* Common code for 32 and 64-bit NUMA */
+#include <linux/acpi.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
@@ -15,7 +16,6 @@
#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
-#include <asm/acpi.h>
#include <asm/amd_nb.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index aa0ff4b02a96..3feec5af4e67 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,7 +6,7 @@
#include <asm/fixmap.h>
#include <asm/mtrr.h>
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
+#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO)
#ifdef CONFIG_HIGHPTE
#define PGALLOC_USER_GFP __GFP_HIGHMEM
@@ -18,7 +18,7 @@ gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
- return (pte_t *)__get_free_page(PGALLOC_GFP);
+ return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT);
}
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
@@ -207,9 +207,13 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
{
int i;
bool failed = false;
+ gfp_t gfp = PGALLOC_GFP;
+
+ if (mm == &init_mm)
+ gfp &= ~__GFP_ACCOUNT;
for(i = 0; i < PREALLOCATED_PMDS; i++) {
- pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
if (!pmd)
failed = true;
if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) {
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index b5f821881465..b1ecff460a46 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -15,8 +15,6 @@
#include <linux/bitmap.h>
#include <linux/module.h>
#include <linux/topology.h>
-#include <linux/bootmem.h>
-#include <linux/memblock.h>
#include <linux/mm.h>
#include <asm/proto.h>
#include <asm/numa.h>
@@ -24,51 +22,6 @@
#include <asm/apic.h>
#include <asm/uv/uv.h>
-int acpi_numa __initdata;
-
-static __init int setup_node(int pxm)
-{
- return acpi_map_pxm_to_node(pxm);
-}
-
-static __init void bad_srat(void)
-{
- printk(KERN_ERR "SRAT: SRAT not used.\n");
- acpi_numa = -1;
-}
-
-static __init inline int srat_disabled(void)
-{
- return acpi_numa < 0;
-}
-
-/*
- * Callback for SLIT parsing. pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them. I/O localities are
- * not supported at this point.
- */
-void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
-{
- int i, j;
-
- for (i = 0; i < slit->locality_count; i++) {
- const int from_node = pxm_to_node(i);
-
- if (from_node == NUMA_NO_NODE)
- continue;
-
- for (j = 0; j < slit->locality_count; j++) {
- const int to_node = pxm_to_node(j);
-
- if (to_node == NUMA_NO_NODE)
- continue;
-
- numa_set_distance(from_node, to_node,
- slit->entry[slit->locality_count * i + j]);
- }
- }
-}
-
/* Callback for Proximity Domain -> x2APIC mapping */
void __init
acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
@@ -91,7 +44,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
pxm, apic_id);
return;
}
- node = setup_node(pxm);
+ node = acpi_map_pxm_to_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
@@ -104,7 +57,6 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
}
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
- acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
pxm, apic_id, node);
}
@@ -127,7 +79,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
pxm = pa->proximity_domain_lo;
if (acpi_srat_revision >= 2)
pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
- node = setup_node(pxm);
+ node = acpi_map_pxm_to_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
bad_srat();
@@ -146,74 +98,10 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
- acpi_numa = 1;
printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
pxm, apic_id, node);
}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static inline int save_add_info(void) {return 1;}
-#else
-static inline int save_add_info(void) {return 0;}
-#endif
-
-/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
-int __init
-acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
-{
- u64 start, end;
- u32 hotpluggable;
- int node, pxm;
-
- if (srat_disabled())
- goto out_err;
- if (ma->header.length != sizeof(struct acpi_srat_mem_affinity))
- goto out_err_bad_srat;
- if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
- goto out_err;
- hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
- if (hotpluggable && !save_add_info())
- goto out_err;
-
- start = ma->base_address;
- end = start + ma->length;
- pxm = ma->proximity_domain;
- if (acpi_srat_revision <= 1)
- pxm &= 0xff;
-
- node = setup_node(pxm);
- if (node < 0) {
- printk(KERN_ERR "SRAT: Too many proximity domains.\n");
- goto out_err_bad_srat;
- }
-
- if (numa_add_memblk(node, start, end) < 0)
- goto out_err_bad_srat;
-
- node_set(node, numa_nodes_parsed);
-
- pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
- node, pxm,
- (unsigned long long) start, (unsigned long long) end - 1,
- hotpluggable ? " hotplug" : "",
- ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
-
- /* Mark hotplug range in memblock. */
- if (hotpluggable && memblock_mark_hotplug(start, ma->length))
- pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
- (unsigned long long)start, (unsigned long long)end - 1);
-
- max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
-
- return 0;
-out_err_bad_srat:
- bad_srat();
-out_err:
- return -1;
-}
-
-void __init acpi_numa_arch_fixup(void) {}
-
int __init x86_acpi_numa_init(void)
{
int ret;
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index be14cc3e48d5..3be012115853 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -20,10 +20,121 @@
#include <linux/init.h>
#include <linux/string.h>
+#include <xen/xen.h>
#include <xen/xen-ops.h>
+#include <xen/interface/platform.h>
#include <asm/page.h>
#include <asm/setup.h>
+#include <asm/xen/hypercall.h>
+
+static efi_char16_t vendor[100] __initdata;
+
+static efi_system_table_t efi_systab_xen __initdata = {
+ .hdr = {
+ .signature = EFI_SYSTEM_TABLE_SIGNATURE,
+ .revision = 0, /* Initialized later. */
+ .headersize = 0, /* Ignored by Linux Kernel. */
+ .crc32 = 0, /* Ignored by Linux Kernel. */
+ .reserved = 0
+ },
+ .fw_vendor = EFI_INVALID_TABLE_ADDR, /* Initialized later. */
+ .fw_revision = 0, /* Initialized later. */
+ .con_in_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .con_in = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .con_out_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .con_out = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .stderr_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .stderr = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+ .runtime = (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR,
+ /* Not used under Xen. */
+ .boottime = (efi_boot_services_t *)EFI_INVALID_TABLE_ADDR,
+ /* Not used under Xen. */
+ .nr_tables = 0, /* Initialized later. */
+ .tables = EFI_INVALID_TABLE_ADDR /* Initialized later. */
+};
+
+static const struct efi efi_xen __initconst = {
+ .systab = NULL, /* Initialized later. */
+ .runtime_version = 0, /* Initialized later. */
+ .mps = EFI_INVALID_TABLE_ADDR,
+ .acpi = EFI_INVALID_TABLE_ADDR,
+ .acpi20 = EFI_INVALID_TABLE_ADDR,
+ .smbios = EFI_INVALID_TABLE_ADDR,
+ .smbios3 = EFI_INVALID_TABLE_ADDR,
+ .sal_systab = EFI_INVALID_TABLE_ADDR,
+ .boot_info = EFI_INVALID_TABLE_ADDR,
+ .hcdp = EFI_INVALID_TABLE_ADDR,
+ .uga = EFI_INVALID_TABLE_ADDR,
+ .uv_systab = EFI_INVALID_TABLE_ADDR,
+ .fw_vendor = EFI_INVALID_TABLE_ADDR,
+ .runtime = EFI_INVALID_TABLE_ADDR,
+ .config_table = EFI_INVALID_TABLE_ADDR,
+ .get_time = xen_efi_get_time,
+ .set_time = xen_efi_set_time,
+ .get_wakeup_time = xen_efi_get_wakeup_time,
+ .set_wakeup_time = xen_efi_set_wakeup_time,
+ .get_variable = xen_efi_get_variable,
+ .get_next_variable = xen_efi_get_next_variable,
+ .set_variable = xen_efi_set_variable,
+ .query_variable_info = xen_efi_query_variable_info,
+ .update_capsule = xen_efi_update_capsule,
+ .query_capsule_caps = xen_efi_query_capsule_caps,
+ .get_next_high_mono_count = xen_efi_get_next_high_mono_count,
+ .reset_system = NULL, /* Functionality provided by Xen. */
+ .set_virtual_address_map = NULL, /* Not used under Xen. */
+ .flags = 0 /* Initialized later. */
+};
+
+static efi_system_table_t __init *xen_efi_probe(void)
+{
+ struct xen_platform_op op = {
+ .cmd = XENPF_firmware_info,
+ .u.firmware_info = {
+ .type = XEN_FW_EFI_INFO,
+ .index = XEN_FW_EFI_CONFIG_TABLE
+ }
+ };
+ union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
+
+ if (!xen_initial_domain() || HYPERVISOR_platform_op(&op) < 0)
+ return NULL;
+
+ /* Here we know that Xen runs on EFI platform. */
+
+ efi = efi_xen;
+
+ efi_systab_xen.tables = info->cfg.addr;
+ efi_systab_xen.nr_tables = info->cfg.nent;
+
+ op.cmd = XENPF_firmware_info;
+ op.u.firmware_info.type = XEN_FW_EFI_INFO;
+ op.u.firmware_info.index = XEN_FW_EFI_VENDOR;
+ info->vendor.bufsz = sizeof(vendor);
+ set_xen_guest_handle(info->vendor.name, vendor);
+
+ if (HYPERVISOR_platform_op(&op) == 0) {
+ efi_systab_xen.fw_vendor = __pa_symbol(vendor);
+ efi_systab_xen.fw_revision = info->vendor.revision;
+ } else
+ efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN");
+
+ op.cmd = XENPF_firmware_info;
+ op.u.firmware_info.type = XEN_FW_EFI_INFO;
+ op.u.firmware_info.index = XEN_FW_EFI_VERSION;
+
+ if (HYPERVISOR_platform_op(&op) == 0)
+ efi_systab_xen.hdr.revision = info->version;
+
+ op.cmd = XENPF_firmware_info;
+ op.u.firmware_info.type = XEN_FW_EFI_INFO;
+ op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
+
+ if (HYPERVISOR_platform_op(&op) == 0)
+ efi.runtime_version = info->version;
+
+ return &efi_systab_xen;
+}
void __init xen_efi_init(void)
{
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0f87db2cc6a8..69b4b6d29738 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -59,6 +59,7 @@
#include <asm/xen/pci.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
+#include <asm/xen/cpuid.h>
#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/proto.h>
@@ -118,6 +119,10 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
*/
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
+/* Linux <-> Xen vCPU id mapping */
+DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
+
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);
@@ -179,7 +184,7 @@ static void clamp_max_cpus(void)
#endif
}
-static void xen_vcpu_setup(int cpu)
+void xen_vcpu_setup(int cpu)
{
struct vcpu_register_vcpu_info info;
int err;
@@ -202,8 +207,9 @@ static void xen_vcpu_setup(int cpu)
if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
return;
}
- if (cpu < MAX_VIRT_CPUS)
- per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS)
+ per_cpu(xen_vcpu, cpu) =
+ &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
if (!have_vcpu_info_placement) {
if (cpu >= MAX_VIRT_CPUS)
@@ -223,7 +229,8 @@ static void xen_vcpu_setup(int cpu)
hypervisor has no unregister variant and this hypercall does not
allow to over-write info.mfn and info.offset.
*/
- err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
+ err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
+ &info);
if (err) {
printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err);
@@ -247,10 +254,11 @@ void xen_vcpu_restore(void)
for_each_possible_cpu(cpu) {
bool other_cpu = (cpu != smp_processor_id());
- bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL);
+ bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu),
+ NULL);
if (other_cpu && is_up &&
- HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+ HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL))
BUG();
xen_setup_runstate_info(cpu);
@@ -259,7 +267,7 @@ void xen_vcpu_restore(void)
xen_vcpu_setup(cpu);
if (other_cpu && is_up &&
- HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+ HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL))
BUG();
}
}
@@ -588,7 +596,7 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
unsigned long frames[pages];
int f;
@@ -637,7 +645,7 @@ static void __init xen_load_gdt_boot(const struct desc_ptr *dtr)
{
unsigned long va = dtr->address;
unsigned int size = dtr->size + 1;
- unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+ unsigned pages = DIV_ROUND_UP(size, PAGE_SIZE);
unsigned long frames[pages];
int f;
@@ -1135,8 +1143,11 @@ void xen_setup_vcpu_info_placement(void)
{
int cpu;
- for_each_possible_cpu(cpu)
+ for_each_possible_cpu(cpu) {
+ /* Set up direct vCPU id mapping for PV guests. */
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_vcpu_setup(cpu);
+ }
/* xen_vcpu_setup managed to place the vcpu_info within the
* percpu area for all cpus, so make use of it. Note that for
@@ -1727,6 +1738,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
#endif
xen_raw_console_write("about to get started...\n");
+ /* Let's presume PV guests always boot on vCPU with id 0. */
+ per_cpu(xen_vcpu_id, 0) = 0;
+
xen_setup_runstate_info(0);
xen_efi_init();
@@ -1768,9 +1782,10 @@ void __ref xen_hvm_init_shared_info(void)
* in that case multiple vcpus might be online. */
for_each_online_cpu(cpu) {
/* Leave it to be NULL. */
- if (cpu >= MAX_VIRT_CPUS)
+ if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS)
continue;
- per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+ per_cpu(xen_vcpu, cpu) =
+ &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)];
}
}
@@ -1795,6 +1810,12 @@ static void __init init_hvm_pv_info(void)
xen_setup_features();
+ cpuid(base + 4, &eax, &ebx, &ecx, &edx);
+ if (eax & XEN_HVM_CPUID_VCPU_ID_PRESENT)
+ this_cpu_write(xen_vcpu_id, ebx);
+ else
+ this_cpu_write(xen_vcpu_id, smp_processor_id());
+
pv_info.name = "Xen HVM";
xen_domain_type = XEN_HVM_DOMAIN;
@@ -1806,6 +1827,10 @@ static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
int cpu = (long)hcpu;
switch (action) {
case CPU_UP_PREPARE:
+ if (cpu_acpi_id(cpu) != U32_MAX)
+ per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu);
+ else
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_vcpu_setup(cpu);
if (xen_have_vector_callback) {
if (xen_feature(XENFEAT_hvm_safe_pvclock))
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index e079500b17f3..de4144c24f1c 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -111,63 +111,18 @@ int arch_gnttab_init(unsigned long nr_shared)
}
#ifdef CONFIG_XEN_PVH
-#include <xen/balloon.h>
#include <xen/events.h>
-#include <linux/slab.h>
-static int __init xlated_setup_gnttab_pages(void)
-{
- struct page **pages;
- xen_pfn_t *pfns;
- void *vaddr;
- int rc;
- unsigned int i;
- unsigned long nr_grant_frames = gnttab_max_grant_frames();
-
- BUG_ON(nr_grant_frames == 0);
- pages = kcalloc(nr_grant_frames, sizeof(pages[0]), GFP_KERNEL);
- if (!pages)
- return -ENOMEM;
-
- pfns = kcalloc(nr_grant_frames, sizeof(pfns[0]), GFP_KERNEL);
- if (!pfns) {
- kfree(pages);
- return -ENOMEM;
- }
- rc = alloc_xenballooned_pages(nr_grant_frames, pages);
- if (rc) {
- pr_warn("%s Couldn't balloon alloc %ld pfns rc:%d\n", __func__,
- nr_grant_frames, rc);
- kfree(pages);
- kfree(pfns);
- return rc;
- }
- for (i = 0; i < nr_grant_frames; i++)
- pfns[i] = page_to_pfn(pages[i]);
-
- vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL);
- if (!vaddr) {
- pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__,
- nr_grant_frames, rc);
- free_xenballooned_pages(nr_grant_frames, pages);
- kfree(pages);
- kfree(pfns);
- return -ENOMEM;
- }
- kfree(pages);
-
- xen_auto_xlat_grant_frames.pfn = pfns;
- xen_auto_xlat_grant_frames.count = nr_grant_frames;
- xen_auto_xlat_grant_frames.vaddr = vaddr;
-
- return 0;
-}
-
+#include <xen/xen-ops.h>
static int __init xen_pvh_gnttab_setup(void)
{
if (!xen_pvh_domain())
return -ENODEV;
- return xlated_setup_gnttab_pages();
+ xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
+
+ return xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
+ &xen_auto_xlat_grant_frames.vaddr,
+ xen_auto_xlat_grant_frames.count);
}
/* Call it _before_ __gnttab_init as we need to initialize the
* xen_auto_xlat_grant_frames first. */
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index a1207cb6472a..33e92955e09d 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -109,7 +109,8 @@ static void xen_safe_halt(void)
static void xen_halt(void)
{
if (irqs_disabled())
- HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
+ HYPERVISOR_vcpu_op(VCPUOP_down,
+ xen_vcpu_nr(smp_processor_id()), NULL);
else
xen_safe_halt();
}
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 9466354d3e49..32bdc2c90297 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -547,7 +547,7 @@ void xen_pmu_init(int cpu)
return;
fail:
- pr_warn_once("Could not initialize VPMU for cpu %d, error %d\n",
+ pr_info_once("Could not initialize VPMU for cpu %d, error %d\n",
cpu, err);
free_pages((unsigned long)xenpmu_data, 0);
}
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 719cf291dcdf..0b4d04c8ab4d 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -322,6 +322,13 @@ static void __init xen_smp_prepare_boot_cpu(void)
xen_filter_cpu_maps();
xen_setup_vcpu_info_placement();
}
+
+ /*
+ * Setup vcpu_info for boot CPU.
+ */
+ if (xen_hvm_domain())
+ xen_vcpu_setup(0);
+
/*
* The alternative logic (which patches the unlock/lock) runs before
* the smp bootup up code is activated. Hence we need to set this up
@@ -454,7 +461,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
#endif
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
- if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt))
+ if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
BUG();
kfree(ctxt);
@@ -492,7 +499,7 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
if (rc)
return rc;
- rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL);
+ rc = HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL);
BUG_ON(rc);
while (cpu_report_state(cpu) != CPU_ONLINE)
@@ -520,7 +527,8 @@ static int xen_cpu_disable(void)
static void xen_cpu_die(unsigned int cpu)
{
- while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) {
+ while (xen_pv_domain() && HYPERVISOR_vcpu_op(VCPUOP_is_up,
+ xen_vcpu_nr(cpu), NULL)) {
__set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(HZ/10);
}
@@ -536,7 +544,7 @@ static void xen_cpu_die(unsigned int cpu)
static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
{
play_dead_common();
- HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
+ HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
cpu_bringup();
/*
* commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down)
@@ -576,7 +584,7 @@ static void stop_self(void *v)
set_cpu_online(cpu, false);
- HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL);
+ HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL);
BUG();
}
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 6deba5bc7e34..67356d29d74d 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -11,8 +11,6 @@
#include <linux/interrupt.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
-#include <linux/kernel_stat.h>
-#include <linux/math64.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/pvclock_gtod.h>
@@ -31,44 +29,6 @@
/* Xen may fire a timer up to this many ns early */
#define TIMER_SLOP 100000
-#define NS_PER_TICK (1000000000LL / HZ)
-
-/* snapshots of runstate info */
-static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
-
-/* unused ns of stolen time */
-static DEFINE_PER_CPU(u64, xen_residual_stolen);
-
-static void do_stolen_accounting(void)
-{
- struct vcpu_runstate_info state;
- struct vcpu_runstate_info *snap;
- s64 runnable, offline, stolen;
- cputime_t ticks;
-
- xen_get_runstate_snapshot(&state);
-
- WARN_ON(state.state != RUNSTATE_running);
-
- snap = this_cpu_ptr(&xen_runstate_snapshot);
-
- /* work out how much time the VCPU has not been runn*ing* */
- runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
- offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline];
-
- *snap = state;
-
- /* Add the appropriate number of ticks of stolen time,
- including any left-overs from last time. */
- stolen = runnable + offline + __this_cpu_read(xen_residual_stolen);
-
- if (stolen < 0)
- stolen = 0;
-
- ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
- __this_cpu_write(xen_residual_stolen, stolen);
- account_steal_ticks(ticks);
-}
/* Get the TSC speed from Xen */
static unsigned long xen_tsc_khz(void)
@@ -263,8 +223,10 @@ static int xen_vcpuop_shutdown(struct clock_event_device *evt)
{
int cpu = smp_processor_id();
- if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) ||
- HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+ if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, xen_vcpu_nr(cpu),
+ NULL) ||
+ HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, xen_vcpu_nr(cpu),
+ NULL))
BUG();
return 0;
@@ -274,7 +236,8 @@ static int xen_vcpuop_set_oneshot(struct clock_event_device *evt)
{
int cpu = smp_processor_id();
- if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+ if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, xen_vcpu_nr(cpu),
+ NULL))
BUG();
return 0;
@@ -293,7 +256,8 @@ static int xen_vcpuop_set_next_event(unsigned long delta,
/* Get an event anyway, even if the timeout is already expired */
single.flags = 0;
- ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single);
+ ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, xen_vcpu_nr(cpu),
+ &single);
BUG_ON(ret != 0);
return ret;
@@ -335,8 +299,6 @@ static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
ret = IRQ_HANDLED;
}
- do_stolen_accounting();
-
return ret;
}
@@ -394,13 +356,15 @@ void xen_timer_resume(void)
return;
for_each_online_cpu(cpu) {
- if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL))
+ if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer,
+ xen_vcpu_nr(cpu), NULL))
BUG();
}
}
static const struct pv_time_ops xen_time_ops __initconst = {
.sched_clock = xen_clocksource_read,
+ .steal_clock = xen_steal_clock,
};
static void __init xen_time_init(void)
@@ -414,7 +378,8 @@ static void __init xen_time_init(void)
clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC);
- if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {
+ if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, xen_vcpu_nr(cpu),
+ NULL) == 0) {
/* Successfully turned off 100Hz tick, so we have the
vcpuop-based timer interface */
printk(KERN_DEBUG "Xen: using vcpuop timer interface\n");
@@ -431,6 +396,8 @@ static void __init xen_time_init(void)
xen_setup_timer(cpu);
xen_setup_cpu_clockevents();
+ xen_time_setup_guest();
+
if (xen_initial_domain())
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
}
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 4140b070f2e9..3cbce3b085e7 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -76,6 +76,7 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
bool xen_vcpu_stolen(int vcpu);
+void xen_vcpu_setup(int cpu);
void xen_setup_vcpu_info_placement(void);
#ifdef CONFIG_SMP
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index ef90479e0397..0fecc8a2c0b5 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -404,7 +404,7 @@ static struct pmu xtensa_pmu = {
.read = xtensa_pmu_read,
};
-static void xtensa_pmu_setup(void)
+static int xtensa_pmu_setup(int cpu)
{
unsigned i;
@@ -413,21 +413,7 @@ static void xtensa_pmu_setup(void)
set_er(0, XTENSA_PMU_PMCTRL(i));
set_er(get_er(XTENSA_PMU_PMSTAT(i)), XTENSA_PMU_PMSTAT(i));
}
-}
-
-static int xtensa_pmu_notifier(struct notifier_block *self,
- unsigned long action, void *data)
-{
- switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
- xtensa_pmu_setup();
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
+ return 0;
}
static int __init xtensa_pmu_init(void)
@@ -435,7 +421,13 @@ static int __init xtensa_pmu_init(void)
int ret;
int irq = irq_create_mapping(NULL, XCHAL_PROFILING_INTERRUPT);
- perf_cpu_notifier(xtensa_pmu_notifier);
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_XTENSA_STARTING,
+ "AP_PERF_XTENSA_STARTING", xtensa_pmu_setup,
+ NULL);
+ if (ret) {
+ pr_err("xtensa_pmu: failed to register CPU-hotplug.\n");
+ return ret;
+ }
#if XTENSA_FAKE_NMI
enable_irq(irq);
#else
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 7f4a1fdb1502..2725e08ef353 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -110,7 +110,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, flags);
+ fault = handle_mm_fault(vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;