Home Home > GIT Browse > vanilla
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorKernel Build Daemon <kbuild@suse.de>2019-07-09 12:01:57 +0200
committerKernel Build Daemon <kbuild@suse.de>2019-07-09 12:01:57 +0200
commit555ebe0647024d1f5ef0e9f792dc9ddf24cc43bf (patch)
treea819a972347bd9c0c693c34c1bb315f5bf94f929
parent6d2616e4a00cfbf3a98c9bd379cd96c44ecaf73e (diff)
Automatically updated to 5.2-915-g5ad18b2e60b7
-rw-r--r--Documentation/ABI/testing/ima_policy6
-rw-r--r--Documentation/ABI/testing/sysfs-bus-css23
-rw-r--r--Documentation/ABI/testing/sysfs-devices-system-cpu23
-rw-r--r--Documentation/RCU/rcuref.txt21
-rw-r--r--Documentation/RCU/stallwarn.txt2
-rw-r--r--Documentation/RCU/whatisRCU.txt8
-rw-r--r--Documentation/admin-guide/cgroup-v2.rst6
-rw-r--r--Documentation/admin-guide/hw-vuln/l1tf.rst2
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt25
-rw-r--r--Documentation/admin-guide/mm/numa_memory_policy.rst2
-rw-r--r--Documentation/arm64/elf_hwcaps.txt8
-rw-r--r--Documentation/atomic_t.txt26
-rw-r--r--Documentation/block/bfq-iosched.txt2
-rw-r--r--Documentation/cgroup-v1/blkio-controller.rst (renamed from Documentation/cgroup-v1/blkio-controller.txt)79
-rw-r--r--Documentation/cgroup-v1/cgroups.rst (renamed from Documentation/cgroup-v1/cgroups.txt)186
-rw-r--r--Documentation/cgroup-v1/cpuacct.rst (renamed from Documentation/cgroup-v1/cpuacct.txt)15
-rw-r--r--Documentation/cgroup-v1/cpusets.rst (renamed from Documentation/cgroup-v1/cpusets.txt)209
-rw-r--r--Documentation/cgroup-v1/devices.rst (renamed from Documentation/cgroup-v1/devices.txt)40
-rw-r--r--Documentation/cgroup-v1/freezer-subsystem.rst (renamed from Documentation/cgroup-v1/freezer-subsystem.txt)14
-rw-r--r--Documentation/cgroup-v1/hugetlb.rst (renamed from Documentation/cgroup-v1/hugetlb.txt)41
-rw-r--r--Documentation/cgroup-v1/index.rst30
-rw-r--r--Documentation/cgroup-v1/memcg_test.rst (renamed from Documentation/cgroup-v1/memcg_test.txt)265
-rw-r--r--Documentation/cgroup-v1/memory.rst (renamed from Documentation/cgroup-v1/memory.txt)463
-rw-r--r--Documentation/cgroup-v1/net_cls.rst (renamed from Documentation/cgroup-v1/net_cls.txt)37
-rw-r--r--Documentation/cgroup-v1/net_prio.rst (renamed from Documentation/cgroup-v1/net_prio.txt)24
-rw-r--r--Documentation/cgroup-v1/pids.rst (renamed from Documentation/cgroup-v1/pids.txt)82
-rw-r--r--Documentation/cgroup-v1/rdma.rst (renamed from Documentation/cgroup-v1/rdma.txt)66
-rw-r--r--Documentation/core-api/circular-buffers.rst2
-rw-r--r--Documentation/core-api/timekeeping.rst12
-rw-r--r--Documentation/cputopology.txt48
-rw-r--r--Documentation/crypto/api-samples.rst176
-rw-r--r--Documentation/crypto/api-skcipher.rst2
-rw-r--r--Documentation/crypto/architecture.rst4
-rw-r--r--Documentation/crypto/crypto_engine.rst111
-rw-r--r--Documentation/devicetree/bindings/crypto/atmel-crypto.txt13
-rw-r--r--Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt29
-rw-r--r--Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt1
-rw-r--r--Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt20
-rw-r--r--Documentation/devicetree/bindings/interrupt-controller/renesas,rza1-irqc.txt43
-rw-r--r--Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt21
-rw-r--r--Documentation/devicetree/bindings/rng/brcm,iproc-rng200.txt1
-rw-r--r--Documentation/devicetree/bindings/timer/nxp,sysctr-timer.txt25
-rw-r--r--Documentation/devicetree/bindings/trivial-devices.yaml4
-rw-r--r--Documentation/driver-api/s390-drivers.rst4
-rw-r--r--Documentation/filesystems/proc.txt40
-rw-r--r--Documentation/filesystems/tmpfs.txt2
-rw-r--r--Documentation/locking/lockdep-design.txt112
-rw-r--r--Documentation/memory-barriers.txt2
-rw-r--r--Documentation/process/changes.rst6
-rw-r--r--Documentation/s390/3270.rst (renamed from Documentation/s390/3270.txt)85
-rw-r--r--Documentation/s390/Debugging390.txt2142
-rw-r--r--Documentation/s390/cds.rst (renamed from Documentation/s390/cds.txt)368
-rw-r--r--Documentation/s390/common_io.rst (renamed from Documentation/s390/CommonIO)49
-rw-r--r--Documentation/s390/dasd.rst (renamed from Documentation/s390/DASD)33
-rw-r--r--Documentation/s390/debugging390.rst2613
-rw-r--r--Documentation/s390/driver-model.rst (renamed from Documentation/s390/driver-model.txt)179
-rw-r--r--Documentation/s390/index.rst30
-rw-r--r--Documentation/s390/monreader.rst (renamed from Documentation/s390/monreader.txt)85
-rw-r--r--Documentation/s390/qeth.rst (renamed from Documentation/s390/qeth.txt)36
-rw-r--r--Documentation/s390/s390dbf.rst487
-rw-r--r--Documentation/s390/s390dbf.txt667
-rw-r--r--Documentation/s390/text_files.rst11
-rw-r--r--Documentation/s390/vfio-ap.rst (renamed from Documentation/s390/vfio-ap.txt)499
-rw-r--r--Documentation/s390/vfio-ccw.rst (renamed from Documentation/s390/vfio-ccw.txt)92
-rw-r--r--Documentation/s390/zfcpdump.rst (renamed from Documentation/s390/zfcpdump.txt)2
-rw-r--r--Documentation/scheduler/sched-deadline.txt2
-rw-r--r--Documentation/scheduler/sched-design-CFS.txt2
-rw-r--r--Documentation/scheduler/sched-pelt.c3
-rw-r--r--Documentation/scheduler/sched-rt-group.txt2
-rw-r--r--Documentation/security/IMA-templates.rst7
-rw-r--r--Documentation/security/keys/core.rst217
-rw-r--r--Documentation/security/keys/request-key.rst57
-rw-r--r--Documentation/sysctl/kernel.txt16
-rw-r--r--Documentation/translations/ko_KR/memory-barriers.txt2
-rw-r--r--Documentation/vm/numa.rst4
-rw-r--r--Documentation/vm/page_migration.rst2
-rw-r--r--Documentation/vm/unevictable-lru.rst2
-rw-r--r--Documentation/x86/exception-tables.rst2
-rw-r--r--Documentation/x86/topology.rst4
-rw-r--r--Documentation/x86/x86_64/fake-numa-for-cpusets.rst4
-rw-r--r--MAINTAINERS40
-rw-r--r--arch/alpha/include/asm/atomic.h20
-rw-r--r--arch/alpha/kernel/signal.c4
-rw-r--r--arch/alpha/kernel/smp.c19
-rw-r--r--arch/alpha/kernel/traps.c2
-rw-r--r--arch/alpha/mm/fault.c4
-rw-r--r--arch/alpha/oprofile/common.c6
-rw-r--r--arch/arc/include/asm/atomic.h41
-rw-r--r--arch/arc/kernel/process.c4
-rw-r--r--arch/arc/kernel/signal.c2
-rw-r--r--arch/arc/kernel/traps.c2
-rw-r--r--arch/arc/mm/fault.c4
-rw-r--r--arch/arm/Kconfig30
-rw-r--r--arch/arm/boot/dts/imx7ulp.dtsi23
-rw-r--r--arch/arm/common/bL_switcher.c6
-rw-r--r--arch/arm/configs/exynos_defconfig1
-rw-r--r--arch/arm/crypto/chacha-neon-glue.c2
-rw-r--r--arch/arm/crypto/sha512-glue.c2
-rw-r--r--arch/arm/include/asm/arch_timer.h10
-rw-r--r--arch/arm/include/asm/atomic.h50
-rw-r--r--arch/arm/include/asm/bug.h2
-rw-r--r--arch/arm/include/asm/cacheflush.h7
-rw-r--r--arch/arm/include/asm/traps.h2
-rw-r--r--arch/arm/kernel/ptrace.c6
-rw-r--r--arch/arm/kernel/signal.c4
-rw-r--r--arch/arm/kernel/smp.c1
-rw-r--r--arch/arm/kernel/topology.c2
-rw-r--r--arch/arm/kernel/traps.c7
-rw-r--r--arch/arm/mach-stm32/Kconfig1
-rw-r--r--arch/arm/mm/Kconfig8
-rw-r--r--arch/arm/mm/alignment.c2
-rw-r--r--arch/arm/mm/cache-v7.S16
-rw-r--r--arch/arm/mm/fault.c33
-rw-r--r--arch/arm/mm/init.c22
-rw-r--r--arch/arm/mm/mm.h2
-rw-r--r--arch/arm/mm/proc-v7.S10
-rw-r--r--arch/arm/vdso/Makefile3
-rw-r--r--arch/arm64/Kconfig38
-rw-r--r--arch/arm64/Makefile23
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/crypto/aes-ce.S60
-rw-r--r--arch/arm64/crypto/aes-modes.S118
-rw-r--r--arch/arm64/crypto/aes-neon.S48
-rw-r--r--arch/arm64/crypto/chacha-neon-glue.c2
-rw-r--r--arch/arm64/crypto/sha1-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sha2-ce-glue.c2
-rw-r--r--arch/arm64/include/asm/acpi.h3
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h4
-rw-r--r--arch/arm64/include/asm/arch_timer.h13
-rw-r--r--arch/arm64/include/asm/atomic_ll_sc.h20
-rw-r--r--arch/arm64/include/asm/atomic_lse.h34
-rw-r--r--arch/arm64/include/asm/cache.h5
-rw-r--r--arch/arm64/include/asm/cacheflush.h3
-rw-r--r--arch/arm64/include/asm/cpufeature.h6
-rw-r--r--arch/arm64/include/asm/daifflags.h75
-rw-r--r--arch/arm64/include/asm/elf.h14
-rw-r--r--arch/arm64/include/asm/fpsimd.h5
-rw-r--r--arch/arm64/include/asm/hwcap.h2
-rw-r--r--arch/arm64/include/asm/irqflags.h79
-rw-r--r--arch/arm64/include/asm/kvm_host.h7
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h3
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h1
-rw-r--r--arch/arm64/include/asm/pgtable.h56
-rw-r--r--arch/arm64/include/asm/ptrace.h10
-rw-r--r--arch/arm64/include/asm/signal32.h46
-rw-r--r--arch/arm64/include/asm/simd.h10
-rw-r--r--arch/arm64/include/asm/sysreg.h1
-rw-r--r--arch/arm64/include/asm/thread_info.h5
-rw-r--r--arch/arm64/include/asm/unistd.h5
-rw-r--r--arch/arm64/include/asm/vdso.h3
-rw-r--r--arch/arm64/include/asm/vdso/compat_barrier.h44
-rw-r--r--arch/arm64/include/asm/vdso/compat_gettimeofday.h126
-rw-r--r--arch/arm64/include/asm/vdso/gettimeofday.h103
-rw-r--r--arch/arm64/include/asm/vdso/vsyscall.h53
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h2
-rw-r--r--arch/arm64/include/uapi/asm/ptrace.h3
-rw-r--r--arch/arm64/kernel/Makefile6
-rw-r--r--arch/arm64/kernel/acpi.c10
-rw-r--r--arch/arm64/kernel/asm-offsets.c34
-rw-r--r--arch/arm64/kernel/cacheinfo.c9
-rw-r--r--arch/arm64/kernel/cpufeature.c8
-rw-r--r--arch/arm64/kernel/cpuinfo.c2
-rw-r--r--arch/arm64/kernel/entry.S84
-rw-r--r--arch/arm64/kernel/fpsimd.c139
-rw-r--r--arch/arm64/kernel/irq.c26
-rw-r--r--arch/arm64/kernel/module.c4
-rw-r--r--arch/arm64/kernel/probes/kprobes.c4
-rw-r--r--arch/arm64/kernel/process.c2
-rw-r--r--arch/arm64/kernel/ptrace.c6
-rw-r--r--arch/arm64/kernel/signal32.c72
-rw-r--r--arch/arm64/kernel/sleep.S2
-rw-r--r--arch/arm64/kernel/smp.c27
-rw-r--r--arch/arm64/kernel/traps.c29
-rw-r--r--arch/arm64/kernel/vdso.c356
-rw-r--r--arch/arm64/kernel/vdso/Makefile41
-rw-r--r--arch/arm64/kernel/vdso/gettimeofday.S323
-rw-r--r--arch/arm64/kernel/vdso/vgettimeofday.c27
-rw-r--r--arch/arm64/kernel/vdso32/.gitignore2
-rw-r--r--arch/arm64/kernel/vdso32/Makefile186
-rw-r--r--arch/arm64/kernel/vdso32/note.c15
-rw-r--r--arch/arm64/kernel/vdso32/sigreturn.S62
-rw-r--r--arch/arm64/kernel/vdso32/vdso.S19
-rw-r--r--arch/arm64/kernel/vdso32/vdso.lds.S82
-rw-r--r--arch/arm64/kernel/vdso32/vgettimeofday.c59
-rw-r--r--arch/arm64/kvm/fpsimd.c4
-rw-r--r--arch/arm64/kvm/hyp/switch.c2
-rw-r--r--arch/arm64/mm/dma-mapping.c12
-rw-r--r--arch/arm64/mm/fault.c61
-rw-r--r--arch/arm64/mm/hugetlbpage.c12
-rw-r--r--arch/arm64/mm/init.c5
-rw-r--r--arch/arm64/mm/mmu.c14
-rw-r--r--arch/arm64/mm/pageattr.c48
-rw-r--r--arch/arm64/net/bpf_jit_comp.c2
-rw-r--r--arch/c6x/kernel/signal.c2
-rw-r--r--arch/c6x/kernel/traps.c2
-rw-r--r--arch/csky/abiv1/alignment.c2
-rw-r--r--arch/csky/abiv2/fpu.c2
-rw-r--r--arch/csky/kernel/signal.c4
-rw-r--r--arch/csky/kernel/traps.c2
-rw-r--r--arch/csky/mm/fault.c4
-rw-r--r--arch/h8300/kernel/ptrace_h.c4
-rw-r--r--arch/h8300/kernel/ptrace_s.c2
-rw-r--r--arch/h8300/kernel/signal.c2
-rw-r--r--arch/hexagon/kernel/signal.c2
-rw-r--r--arch/hexagon/kernel/traps.c12
-rw-r--r--arch/hexagon/mm/vm_fault.c4
-rw-r--r--arch/ia64/include/asm/atomic.h20
-rw-r--r--arch/ia64/kernel/brl_emu.c6
-rw-r--r--arch/ia64/kernel/mca.c2
-rw-r--r--arch/ia64/kernel/perfmon.c12
-rw-r--r--arch/ia64/kernel/signal.c8
-rw-r--r--arch/ia64/kernel/traps.c24
-rw-r--r--arch/ia64/kernel/unaligned.c2
-rw-r--r--arch/ia64/kernel/uncached.c8
-rw-r--r--arch/ia64/mm/fault.c2
-rw-r--r--arch/m68k/Kconfig3
-rw-r--r--arch/m68k/configs/amiga_defconfig17
-rw-r--r--arch/m68k/configs/apollo_defconfig17
-rw-r--r--arch/m68k/configs/atari_defconfig17
-rw-r--r--arch/m68k/configs/bvme6000_defconfig17
-rw-r--r--arch/m68k/configs/hp300_defconfig17
-rw-r--r--arch/m68k/configs/mac_defconfig17
-rw-r--r--arch/m68k/configs/multi_defconfig17
-rw-r--r--arch/m68k/configs/mvme147_defconfig17
-rw-r--r--arch/m68k/configs/mvme16x_defconfig17
-rw-r--r--arch/m68k/configs/q40_defconfig17
-rw-r--r--arch/m68k/configs/sun3_defconfig17
-rw-r--r--arch/m68k/configs/sun3x_defconfig17
-rw-r--r--arch/m68k/kernel/dma.c57
-rw-r--r--arch/m68k/kernel/signal.c4
-rw-r--r--arch/m68k/kernel/traps.c20
-rw-r--r--arch/m68k/mm/fault.c4
-rw-r--r--arch/microblaze/kernel/exceptions.c2
-rw-r--r--arch/microblaze/kernel/signal.c2
-rw-r--r--arch/microblaze/mm/fault.c2
-rw-r--r--arch/mips/include/asm/atomic.h22
-rw-r--r--arch/mips/include/asm/switch_to.h4
-rw-r--r--arch/mips/kernel/branch.c18
-rw-r--r--arch/mips/kernel/kprobes.c2
-rw-r--r--arch/mips/kernel/mips-mt-fpaff.c2
-rw-r--r--arch/mips/kernel/signal.c8
-rw-r--r--arch/mips/kernel/signal_n32.c4
-rw-r--r--arch/mips/kernel/signal_o32.c8
-rw-r--r--arch/mips/kernel/traps.c56
-rw-r--r--arch/mips/kernel/unaligned.c20
-rw-r--r--arch/mips/mm/fault.c4
-rw-r--r--arch/mips/sgi-ip22/ip22-berr.c2
-rw-r--r--arch/mips/sgi-ip22/ip28-berr.c2
-rw-r--r--arch/mips/sgi-ip27/ip27-berr.c2
-rw-r--r--arch/mips/sgi-ip32/ip32-berr.c2
-rw-r--r--arch/nds32/kernel/fpu.c2
-rw-r--r--arch/nds32/kernel/signal.c2
-rw-r--r--arch/nds32/kernel/traps.c17
-rw-r--r--arch/nds32/mm/fault.c4
-rw-r--r--arch/nios2/kernel/signal.c4
-rw-r--r--arch/nios2/kernel/traps.c2
-rw-r--r--arch/openrisc/kernel/signal.c2
-rw-r--r--arch/openrisc/kernel/traps.c12
-rw-r--r--arch/openrisc/mm/fault.c4
-rw-r--r--arch/parisc/kernel/ptrace.c6
-rw-r--r--arch/parisc/kernel/signal.c2
-rw-r--r--arch/parisc/kernel/traps.c14
-rw-r--r--arch/parisc/kernel/unaligned.c4
-rw-r--r--arch/parisc/math-emu/driver.c2
-rw-r--r--arch/parisc/mm/fault.c4
-rw-r--r--arch/powerpc/include/asm/atomic.h44
-rw-r--r--arch/powerpc/include/asm/processor.h2
-rw-r--r--arch/powerpc/kernel/process.c2
-rw-r--r--arch/powerpc/kernel/ptrace.c1
-rw-r--r--arch/powerpc/kernel/rtas.c3
-rw-r--r--arch/powerpc/kernel/signal_32.c6
-rw-r--r--arch/powerpc/kernel/signal_64.c2
-rw-r--r--arch/powerpc/kernel/traps.c4
-rw-r--r--arch/powerpc/mm/fault.c5
-rw-r--r--arch/powerpc/platforms/cell/spufs/fault.c9
-rw-r--r--arch/powerpc/platforms/cell/spufs/run.c2
-rw-r--r--arch/powerpc/platforms/cell/spufs/sched.c2
-rw-r--r--arch/riscv/include/asm/atomic.h44
-rw-r--r--arch/riscv/include/asm/bug.h2
-rw-r--r--arch/riscv/kernel/signal.c2
-rw-r--r--arch/riscv/kernel/traps.c11
-rw-r--r--arch/riscv/mm/fault.c6
-rw-r--r--arch/s390/Kconfig41
-rw-r--r--arch/s390/configs/debug_defconfig2
-rw-r--r--arch/s390/configs/defconfig600
-rw-r--r--arch/s390/configs/performance_defconfig678
-rw-r--r--arch/s390/configs/zfcpdump_defconfig1
-rw-r--r--arch/s390/crypto/ghash_s390.c2
-rw-r--r--arch/s390/crypto/prng.c4
-rw-r--r--arch/s390/crypto/sha1_s390.c2
-rw-r--r--arch/s390/crypto/sha256_s390.c2
-rw-r--r--arch/s390/crypto/sha512_s390.c2
-rw-r--r--arch/s390/include/asm/airq.h2
-rw-r--r--arch/s390/include/asm/atomic.h38
-rw-r--r--arch/s390/include/asm/ccwdev.h4
-rw-r--r--arch/s390/include/asm/cio.h41
-rw-r--r--arch/s390/include/asm/ctl_reg.h9
-rw-r--r--arch/s390/include/asm/debug.h153
-rw-r--r--arch/s390/include/asm/facility.h21
-rw-r--r--arch/s390/include/asm/idals.h3
-rw-r--r--arch/s390/include/asm/kvm_host.h7
-rw-r--r--arch/s390/include/asm/mem_encrypt.h17
-rw-r--r--arch/s390/include/asm/pci.h5
-rw-r--r--arch/s390/include/asm/percpu.h2
-rw-r--r--arch/s390/include/asm/processor.h7
-rw-r--r--arch/s390/include/asm/smp.h35
-rw-r--r--arch/s390/include/asm/spinlock.h4
-rw-r--r--arch/s390/include/asm/tlbflush.h17
-rw-r--r--arch/s390/include/asm/unwind.h19
-rw-r--r--arch/s390/include/uapi/asm/runtime_instr.h2
-rw-r--r--arch/s390/kernel/Makefile2
-rw-r--r--arch/s390/kernel/compat_signal.c4
-rw-r--r--arch/s390/kernel/debug.c105
-rw-r--r--arch/s390/kernel/dis.c5
-rw-r--r--arch/s390/kernel/dumpstack.c2
-rw-r--r--arch/s390/kernel/entry.S4
-rw-r--r--arch/s390/kernel/jump_label.c23
-rw-r--r--arch/s390/kernel/machine_kexec.c3
-rw-r--r--arch/s390/kernel/processor.c19
-rw-r--r--arch/s390/kernel/setup.c2
-rw-r--r--arch/s390/kernel/signal.c4
-rw-r--r--arch/s390/kernel/smp.c21
-rw-r--r--arch/s390/kernel/swsusp.S2
-rw-r--r--arch/s390/kernel/traps.c16
-rw-r--r--arch/s390/kernel/unwind_bc.c16
-rw-r--r--arch/s390/kvm/kvm-s390.c3
-rw-r--r--arch/s390/kvm/priv.c86
-rw-r--r--arch/s390/lib/Makefile3
-rw-r--r--arch/s390/mm/fault.c6
-rw-r--r--arch/s390/mm/init.c47
-rw-r--r--arch/s390/mm/maccess.c9
-rw-r--r--arch/s390/mm/mmap.c2
-rw-r--r--arch/s390/pci/pci.c15
-rw-r--r--arch/s390/pci/pci_clp.c2
-rw-r--r--arch/s390/pci/pci_debug.c2
-rw-r--r--arch/s390/purgatory/.gitignore3
-rw-r--r--arch/s390/tools/Makefile7
-rw-r--r--arch/s390/tools/opcodes.txt51
-rw-r--r--arch/sh/kernel/cpu/sh2a/fpu.c2
-rw-r--r--arch/sh/kernel/cpu/sh4/fpu.c2
-rw-r--r--arch/sh/kernel/cpu/sh5/fpu.c4
-rw-r--r--arch/sh/kernel/hw_breakpoint.c2
-rw-r--r--arch/sh/kernel/ptrace_64.c4
-rw-r--r--arch/sh/kernel/signal_32.c4
-rw-r--r--arch/sh/kernel/signal_64.c4
-rw-r--r--arch/sh/kernel/traps.c4
-rw-r--r--arch/sh/kernel/traps_32.c12
-rw-r--r--arch/sh/kernel/traps_64.c2
-rw-r--r--arch/sh/math-emu/math.c2
-rw-r--r--arch/sh/mm/fault.c11
-rw-r--r--arch/sparc/include/asm/atomic_64.h8
-rw-r--r--arch/sparc/kernel/process_64.c4
-rw-r--r--arch/sparc/kernel/signal32.c8
-rw-r--r--arch/sparc/kernel/signal_32.c4
-rw-r--r--arch/sparc/kernel/signal_64.c8
-rw-r--r--arch/sparc/kernel/sys_sparc_32.c2
-rw-r--r--arch/sparc/kernel/sys_sparc_64.c2
-rw-r--r--arch/sparc/kernel/traps_32.c4
-rw-r--r--arch/sparc/kernel/traps_64.c41
-rw-r--r--arch/sparc/mm/fault_32.c4
-rw-r--r--arch/sparc/mm/fault_64.c2
-rw-r--r--arch/um/kernel/exec.c2
-rw-r--r--arch/um/kernel/ptrace.c7
-rw-r--r--arch/um/kernel/skas/mmu.c2
-rw-r--r--arch/um/kernel/tlb.c4
-rw-r--r--arch/um/kernel/trap.c16
-rw-r--r--arch/unicore32/kernel/signal.c4
-rw-r--r--arch/unicore32/kernel/traps.c2
-rw-r--r--arch/unicore32/mm/fault.c13
-rw-r--r--arch/x86/Kconfig53
-rw-r--r--arch/x86/Kconfig.cpu13
-rw-r--r--arch/x86/Kconfig.debug44
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c45
-rw-r--r--arch/x86/crypto/chacha_glue.c2
-rw-r--r--arch/x86/entry/calling.h15
-rw-r--r--arch/x86/entry/common.c17
-rw-r--r--arch/x86/entry/entry_32.S169
-rw-r--r--arch/x86/entry/entry_64.S41
-rw-r--r--arch/x86/entry/vdso/Makefile9
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c256
-rw-r--r--arch/x86/entry/vdso/vdso.lds.S2
-rw-r--r--arch/x86/entry/vdso/vdso32/vdso32.lds.S2
-rw-r--r--arch/x86/entry/vdso/vdsox32.lds.S1
-rw-r--r--arch/x86/entry/vdso/vma.c2
-rw-r--r--arch/x86/entry/vsyscall/Makefile2
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c41
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_gtod.c83
-rw-r--r--arch/x86/events/core.c2
-rw-r--r--arch/x86/events/intel/cstate.c14
-rw-r--r--arch/x86/events/intel/ds.c8
-rw-r--r--arch/x86/events/intel/rapl.c20
-rw-r--r--arch/x86/events/intel/uncore.c81
-rw-r--r--arch/x86/events/intel/uncore.h4
-rw-r--r--arch/x86/events/intel/uncore_snbep.c4
-rw-r--r--arch/x86/hyperv/hv_init.c91
-rw-r--r--arch/x86/include/asm/acrn.h11
-rw-r--r--arch/x86/include/asm/apic.h5
-rw-r--r--arch/x86/include/asm/atomic.h8
-rw-r--r--arch/x86/include/asm/atomic64_32.h66
-rw-r--r--arch/x86/include/asm/atomic64_64.h46
-rw-r--r--arch/x86/include/asm/barrier.h4
-rw-r--r--arch/x86/include/asm/cpufeature.h4
-rw-r--r--arch/x86/include/asm/cpufeatures.h21
-rw-r--r--arch/x86/include/asm/fpu/xstate.h1
-rw-r--r--arch/x86/include/asm/frame.h49
-rw-r--r--arch/x86/include/asm/hardirq.h2
-rw-r--r--arch/x86/include/asm/hpet.h7
-rw-r--r--arch/x86/include/asm/hw_irq.h5
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h6
-rw-r--r--arch/x86/include/asm/hypervisor.h1
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/irq_regs.h4
-rw-r--r--arch/x86/include/asm/jump_label.h2
-rw-r--r--arch/x86/include/asm/kexec.h17
-rw-r--r--arch/x86/include/asm/mshyperv.h81
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/mwait.h4
-rw-r--r--arch/x86/include/asm/paravirt_types.h21
-rw-r--r--arch/x86/include/asm/percpu.h236
-rw-r--r--arch/x86/include/asm/processor.h7
-rw-r--r--arch/x86/include/asm/ptrace.h20
-rw-r--r--arch/x86/include/asm/pvclock.h2
-rw-r--r--arch/x86/include/asm/smp.h4
-rw-r--r--arch/x86/include/asm/special_insns.h37
-rw-r--r--arch/x86/include/asm/stacktrace.h2
-rw-r--r--arch/x86/include/asm/text-patching.h17
-rw-r--r--arch/x86/include/asm/time.h1
-rw-r--r--arch/x86/include/asm/topology.h17
-rw-r--r--arch/x86/include/asm/vdso/gettimeofday.h261
-rw-r--r--arch/x86/include/asm/vdso/vsyscall.h44
-rw-r--r--arch/x86/include/asm/vgtod.h75
-rw-r--r--arch/x86/include/asm/vsyscall.h6
-rw-r--r--arch/x86/include/asm/vvar.h7
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/acpi/cstate.c15
-rw-r--r--arch/x86/kernel/alternative.c288
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/apic/apic.c87
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c4
-rw-r--r--arch/x86/kernel/apic/io_apic.c50
-rw-r--r--arch/x86/kernel/apic/msi.c4
-rw-r--r--arch/x86/kernel/apic/vector.c4
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c1
-rw-r--r--arch/x86/kernel/cpu/Makefile6
-rw-r--r--arch/x86/kernel/cpu/acrn.c69
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c12
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c3
-rw-r--r--arch/x86/kernel/cpu/common.c79
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c9
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c4
-rw-r--r--arch/x86/kernel/cpu/intel.c27
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c92
-rw-r--r--arch/x86/kernel/cpu/mce/core.c179
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c37
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h12
-rw-r--r--arch/x86/kernel/cpu/mce/severity.c14
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.sh2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c8
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c15
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c12
-rw-r--r--arch/x86/kernel/cpu/scattered.c4
-rw-r--r--arch/x86/kernel/cpu/topology.c88
-rw-r--r--arch/x86/kernel/cpu/umwait.c200
-rw-r--r--arch/x86/kernel/cpu/vmware.c2
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c167
-rw-r--r--arch/x86/kernel/crash.c12
-rw-r--r--arch/x86/kernel/fpu/core.c52
-rw-r--r--arch/x86/kernel/fpu/init.c19
-rw-r--r--arch/x86/kernel/fpu/xstate.c58
-rw-r--r--arch/x86/kernel/ftrace.c7
-rw-r--r--arch/x86/kernel/ftrace_32.S78
-rw-r--r--arch/x86/kernel/ftrace_64.S3
-rw-r--r--arch/x86/kernel/hpet.c935
-rw-r--r--arch/x86/kernel/i8253.c25
-rw-r--r--arch/x86/kernel/idt.c3
-rw-r--r--arch/x86/kernel/ima_arch.c12
-rw-r--r--arch/x86/kernel/io_delay.c38
-rw-r--r--arch/x86/kernel/irq.c4
-rw-r--r--arch/x86/kernel/jailhouse.c4
-rw-r--r--arch/x86/kernel/jump_label.c121
-rw-r--r--arch/x86/kernel/kgdb.c8
-rw-r--r--arch/x86/kernel/kprobes/common.h28
-rw-r--r--arch/x86/kernel/kprobes/core.c29
-rw-r--r--arch/x86/kernel/kprobes/opt.c36
-rw-r--r--arch/x86/kernel/paravirt.c46
-rw-r--r--arch/x86/kernel/paravirt_patch.c126
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c67
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c75
-rw-r--r--arch/x86/kernel/process_32.c16
-rw-r--r--arch/x86/kernel/ptrace.c59
-rw-r--r--arch/x86/kernel/pvclock.c1
-rw-r--r--arch/x86/kernel/signal.c2
-rw-r--r--arch/x86/kernel/smp.c2
-rw-r--r--arch/x86/kernel/smpboot.c77
-rw-r--r--arch/x86/kernel/time.c10
-rw-r--r--arch/x86/kernel/tls.c9
-rw-r--r--arch/x86/kernel/traps.c10
-rw-r--r--arch/x86/kernel/tsc.c61
-rw-r--r--arch/x86/kernel/tsc_msr.c4
-rw-r--r--arch/x86/kernel/umip.c2
-rw-r--r--arch/x86/kernel/unwind_frame.c32
-rw-r--r--arch/x86/kernel/unwind_orc.c2
-rw-r--r--arch/x86/kernel/uprobes.c2
-rw-r--r--arch/x86/kernel/vm86_32.c2
-rw-r--r--arch/x86/kvm/cpuid.h2
-rw-r--r--arch/x86/kvm/pmu.c4
-rw-r--r--arch/x86/kvm/x86.c13
-rw-r--r--arch/x86/lib/cache-smp.c3
-rw-r--r--arch/x86/mm/fault.c30
-rw-r--r--arch/x86/mm/mpx.c2
-rw-r--r--arch/x86/platform/geode/alix.c1
-rw-r--r--arch/x86/platform/geode/geos.c1
-rw-r--r--arch/x86/platform/geode/net5501.c1
-rw-r--r--arch/x86/ras/Kconfig10
-rw-r--r--arch/x86/tools/insn_decoder_test.c8
-rw-r--r--arch/x86/tools/insn_sanity.c28
-rw-r--r--arch/x86/um/signal.c4
-rw-r--r--arch/x86/xen/Kconfig1
-rw-r--r--arch/x86/xen/smp_pv.c1
-rw-r--r--arch/xtensa/kernel/signal.c2
-rw-r--r--arch/xtensa/kernel/traps.c8
-rw-r--r--arch/xtensa/mm/fault.c4
-rw-r--r--block/Kconfig2
-rw-r--r--certs/blacklist.c9
-rw-r--r--certs/system_keyring.c12
-rw-r--r--crypto/Kconfig39
-rw-r--r--crypto/Makefile3
-rw-r--r--crypto/aead.c36
-rw-r--r--crypto/algapi.c35
-rw-r--r--crypto/anubis.c1
-rw-r--r--crypto/arc4.c125
-rw-r--r--crypto/asymmetric_keys/Kconfig3
-rw-r--r--crypto/asymmetric_keys/asymmetric_type.c2
-rw-r--r--crypto/chacha20poly1305.c73
-rw-r--r--crypto/chacha_generic.c4
-rw-r--r--crypto/cryptd.c26
-rw-r--r--crypto/crypto_null.c3
-rw-r--r--crypto/crypto_wq.c35
-rw-r--r--crypto/deflate.c1
-rw-r--r--crypto/drbg.c94
-rw-r--r--crypto/fcrypt.c1
-rw-r--r--crypto/ghash-generic.c8
-rw-r--r--crypto/jitterentropy-kcapi.c5
-rw-r--r--crypto/jitterentropy.c305
-rw-r--r--crypto/khazad.c1
-rw-r--r--crypto/lrw.c2
-rw-r--r--crypto/lz4.c1
-rw-r--r--crypto/lz4hc.c1
-rw-r--r--crypto/lzo-rle.c1
-rw-r--r--crypto/lzo.c1
-rw-r--r--crypto/md4.c7
-rw-r--r--crypto/md5.c7
-rw-r--r--crypto/michael_mic.c1
-rw-r--r--crypto/rmd128.c1
-rw-r--r--crypto/rmd160.c1
-rw-r--r--crypto/rmd256.c1
-rw-r--r--crypto/rmd320.c1
-rw-r--r--crypto/serpent_generic.c9
-rw-r--r--crypto/skcipher.c34
-rw-r--r--crypto/tea.c3
-rw-r--r--crypto/testmgr.c478
-rw-r--r--crypto/testmgr.h116
-rw-r--r--crypto/tgr192.c21
-rw-r--r--crypto/wp512.c21
-rw-r--r--crypto/xxhash_generic.c108
-rw-r--r--crypto/zstd.c1
-rw-r--r--drivers/acpi/acpi_pad.c1
-rw-r--r--drivers/acpi/irq.c26
-rw-r--r--drivers/acpi/pptt.c61
-rw-r--r--drivers/acpi/processor_idle.c1
-rw-r--r--drivers/base/arch_topology.c6
-rw-r--r--drivers/base/cacheinfo.c5
-rw-r--r--drivers/base/topology.c22
-rw-r--r--drivers/block/drbd/drbd_int.h2
-rw-r--r--drivers/block/drbd/drbd_main.c2
-rw-r--r--drivers/block/drbd/drbd_nl.c2
-rw-r--r--drivers/char/agp/generic.c3
-rw-r--r--drivers/char/hw_random/iproc-rng200.c1
-rw-r--r--drivers/char/hw_random/meson-rng.c52
-rw-r--r--drivers/char/tpm/eventlog/efi.c59
-rw-r--r--drivers/char/tpm/eventlog/tpm2.c47
-rw-r--r--drivers/char/tpm/tpm-chip.c6
-rw-r--r--drivers/char/tpm/tpm1-cmd.c7
-rw-r--r--drivers/char/tpm/tpm2-cmd.c7
-rw-r--r--drivers/clocksource/Kconfig14
-rw-r--r--drivers/clocksource/Makefile5
-rw-r--r--drivers/clocksource/arc_timer.c3
-rw-r--r--drivers/clocksource/arm_arch_timer.c15
-rw-r--r--drivers/clocksource/exynos_mct.c4
-rw-r--r--drivers/clocksource/hyperv_timer.c339
-rw-r--r--drivers/clocksource/timer-davinci.c369
-rw-r--r--drivers/clocksource/timer-imx-sysctr.c145
-rw-r--r--drivers/clocksource/timer-ixp4xx.c16
-rw-r--r--drivers/clocksource/timer-meson6.c5
-rw-r--r--drivers/clocksource/timer-tegra.c416
-rw-r--r--drivers/clocksource/timer-tegra20.c379
-rw-r--r--drivers/crypto/Kconfig20
-rw-r--r--drivers/crypto/Makefile2
-rw-r--r--drivers/crypto/amcc/crypto4xx_alg.c36
-rw-r--r--drivers/crypto/amcc/crypto4xx_core.c25
-rw-r--r--drivers/crypto/amcc/crypto4xx_core.h10
-rw-r--r--drivers/crypto/atmel-ecc.c403
-rw-r--r--drivers/crypto/atmel-ecc.h116
-rw-r--r--drivers/crypto/atmel-i2c.c364
-rw-r--r--drivers/crypto/atmel-i2c.h197
-rw-r--r--drivers/crypto/atmel-sha204a.c171
-rw-r--r--drivers/crypto/bcm/cipher.c8
-rw-r--r--drivers/crypto/bcm/spu2.c10
-rw-r--r--drivers/crypto/caam/Kconfig46
-rw-r--r--drivers/crypto/caam/Makefile18
-rw-r--r--drivers/crypto/caam/caamalg.c338
-rw-r--r--drivers/crypto/caam/caamalg_desc.c147
-rw-r--r--drivers/crypto/caam/caamalg_desc.h4
-rw-r--r--drivers/crypto/caam/caamalg_qi.c267
-rw-r--r--drivers/crypto/caam/caamalg_qi2.c202
-rw-r--r--drivers/crypto/caam/caamhash.c329
-rw-r--r--drivers/crypto/caam/caampkc.c177
-rw-r--r--drivers/crypto/caam/caampkc.h9
-rw-r--r--drivers/crypto/caam/caamrng.c76
-rw-r--r--drivers/crypto/caam/ctrl.c56
-rw-r--r--drivers/crypto/caam/desc_constr.h11
-rw-r--r--drivers/crypto/caam/error.c8
-rw-r--r--drivers/crypto/caam/error.h2
-rw-r--r--drivers/crypto/caam/intern.h102
-rw-r--r--drivers/crypto/caam/jr.c43
-rw-r--r--drivers/crypto/caam/key_gen.c28
-rw-r--r--drivers/crypto/caam/qi.c52
-rw-r--r--drivers/crypto/caam/sg_sw_qm.h18
-rw-r--r--drivers/crypto/caam/sg_sw_qm2.h18
-rw-r--r--drivers/crypto/caam/sg_sw_sec4.h26
-rw-r--r--drivers/crypto/cavium/cpt/cptvf_algs.c1
-rw-r--r--drivers/crypto/cavium/nitrox/nitrox_debugfs.h2
-rw-r--r--drivers/crypto/cavium/nitrox/nitrox_mbx.h2
-rw-r--r--drivers/crypto/ccp/ccp-crypto-aes.c7
-rw-r--r--drivers/crypto/ccp/ccp-dev.c96
-rw-r--r--drivers/crypto/ccp/ccp-dev.h2
-rw-r--r--drivers/crypto/ccp/ccp-ops.c20
-rw-r--r--drivers/crypto/ccree/cc_driver.c70
-rw-r--r--drivers/crypto/ccree/cc_driver.h6
-rw-r--r--drivers/crypto/ccree/cc_host_regs.h20
-rw-r--r--drivers/crypto/ccree/cc_pm.c11
-rw-r--r--drivers/crypto/ccree/cc_pm.h7
-rw-r--r--drivers/crypto/hisilicon/sec/sec_drv.h2
-rw-r--r--drivers/crypto/inside-secure/safexcel.c13
-rw-r--r--drivers/crypto/inside-secure/safexcel.h17
-rw-r--r--drivers/crypto/inside-secure/safexcel_cipher.c116
-rw-r--r--drivers/crypto/inside-secure/safexcel_hash.c92
-rw-r--r--drivers/crypto/inside-secure/safexcel_ring.c3
-rw-r--r--drivers/crypto/ixp4xx_crypto.c15
-rw-r--r--drivers/crypto/mxs-dcp.c5
-rw-r--r--drivers/crypto/nx/nx-842-powernv.c8
-rw-r--r--drivers/crypto/nx/nx-842-pseries.c6
-rw-r--r--drivers/crypto/nx/nx.c4
-rw-r--r--drivers/crypto/nx/nx.h12
-rw-r--r--drivers/crypto/nx/nx_debugfs.c71
-rw-r--r--drivers/crypto/qat/qat_common/qat_algs.c294
-rw-r--r--drivers/crypto/qat/qat_common/qat_crypto.h2
-rw-r--r--drivers/crypto/sahara.c4
-rw-r--r--drivers/crypto/stm32/Makefile2
-rw-r--r--drivers/crypto/stm32/stm32-crc32.c (renamed from drivers/crypto/stm32/stm32_crc32.c)0
-rw-r--r--drivers/crypto/stm32/stm32-hash.c6
-rw-r--r--drivers/crypto/sunxi-ss/sun4i-ss-cipher.c47
-rw-r--r--drivers/crypto/talitos.c368
-rw-r--r--drivers/crypto/talitos.h73
-rw-r--r--drivers/crypto/vmx/aes_cbc.c183
-rw-r--r--drivers/crypto/vmx/aes_ctr.c165
-rw-r--r--drivers/crypto/vmx/aes_xts.c175
-rw-r--r--drivers/crypto/vmx/aesp8-ppc.h2
-rw-r--r--drivers/crypto/vmx/aesp8-ppc.pl22
-rw-r--r--drivers/crypto/vmx/vmx.c72
-rw-r--r--drivers/firmware/efi/efi.c2
-rw-r--r--drivers/firmware/efi/libstub/efi-stub-helper.c15
-rw-r--r--drivers/firmware/efi/libstub/efistub.h2
-rw-r--r--drivers/firmware/efi/libstub/fdt.c27
-rw-r--r--drivers/firmware/efi/libstub/tpm.c80
-rw-r--r--drivers/firmware/efi/tpm.c63
-rw-r--r--drivers/gpio/gpio-mb86s7x.c51
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_chardev.c2
-rw-r--r--drivers/hv/Kconfig4
-rw-r--r--drivers/hv/hv.c156
-rw-r--r--drivers/hv/hv_util.c1
-rw-r--r--drivers/hv/hyperv_vmbus.h3
-rw-r--r--drivers/hv/vmbus_drv.c42
-rw-r--r--drivers/hwmon/coretemp.c36
-rw-r--r--drivers/i2c/i2c-core-acpi.c6
-rw-r--r--drivers/iio/humidity/dht11.c8
-rw-r--r--drivers/iio/industrialio-core.c4
-rw-r--r--drivers/infiniband/core/device.c8
-rw-r--r--drivers/infiniband/hw/hfi1/affinity.c6
-rw-r--r--drivers/infiniband/hw/hfi1/sdma.c3
-rw-r--r--drivers/infiniband/hw/mlx4/alias_GUID.c6
-rw-r--r--drivers/infiniband/hw/qib/qib_file_ops.c7
-rw-r--r--drivers/irqchip/Kconfig32
-rw-r--r--drivers/irqchip/Makefile2
-rw-r--r--drivers/irqchip/irq-al-fic.c278
-rw-r--r--drivers/irqchip/irq-csky-mpintc.c86
-rw-r--r--drivers/irqchip/irq-gic-v2m.c85
-rw-r--r--drivers/irqchip/irq-gic-v3.c10
-rw-r--r--drivers/irqchip/irq-mbigen.c3
-rw-r--r--drivers/irqchip/irq-meson-gpio.c1
-rw-r--r--drivers/irqchip/irq-renesas-intc-irqpin.c3
-rw-r--r--drivers/irqchip/irq-renesas-irqc.c91
-rw-r--r--drivers/irqchip/irq-renesas-rza1.c283
-rw-r--r--drivers/irqchip/irq-sni-exiu.c142
-rw-r--r--drivers/irqchip/qcom-irq-combiner.c5
-rw-r--r--drivers/leds/trigger/ledtrig-activity.c2
-rw-r--r--drivers/md/dm-crypt.c2
-rw-r--r--drivers/misc/lkdtm/bugs.c2
-rw-r--r--drivers/net/ppp/Kconfig3
-rw-r--r--drivers/net/ppp/ppp_mppe.c97
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rx.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c2
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/utils.c2
-rw-r--r--drivers/net/wireless/mac80211_hwsim.c2
-rw-r--r--drivers/net/wireless/ti/wlcore/main.c2
-rw-r--r--drivers/net/wireless/ti/wlcore/rx.c2
-rw-r--r--drivers/net/wireless/ti/wlcore/tx.c2
-rw-r--r--drivers/net/wireless/virt_wifi.c2
-rw-r--r--drivers/nvdimm/security.c2
-rw-r--r--drivers/perf/Kconfig8
-rw-r--r--drivers/perf/Makefile1
-rw-r--r--drivers/perf/arm_pmu_acpi.c72
-rw-r--r--drivers/perf/arm_spe_pmu.c12
-rw-r--r--drivers/perf/fsl_imx8_ddr_perf.c554
-rw-r--r--drivers/powercap/intel_rapl.c75
-rw-r--r--drivers/ras/cec.c132
-rw-r--r--drivers/s390/block/Kconfig2
-rw-r--r--drivers/s390/block/dasd_devmap.c2
-rw-r--r--drivers/s390/char/Kconfig22
-rw-r--r--drivers/s390/char/Makefile1
-rw-r--r--drivers/s390/char/sclp_async.c189
-rw-r--r--drivers/s390/char/zcore.c2
-rw-r--r--drivers/s390/cio/airq.c37
-rw-r--r--drivers/s390/cio/ccwreq.c9
-rw-r--r--drivers/s390/cio/chsc.c30
-rw-r--r--drivers/s390/cio/cio.h3
-rw-r--r--drivers/s390/cio/css.c187
-rw-r--r--drivers/s390/cio/device.c68
-rw-r--r--drivers/s390/cio/device_fsm.c49
-rw-r--r--drivers/s390/cio/device_id.c20
-rw-r--r--drivers/s390/cio/device_ops.c21
-rw-r--r--drivers/s390/cio/device_pgid.c22
-rw-r--r--drivers/s390/cio/device_status.c24
-rw-r--r--drivers/s390/cio/io_sch.h20
-rw-r--r--drivers/s390/cio/qdio_main.c1
-rw-r--r--drivers/s390/cio/qdio_setup.c2
-rw-r--r--drivers/s390/cio/qdio_thinint.c6
-rw-r--r--drivers/s390/cio/vfio_ccw_cp.c524
-rw-r--r--drivers/s390/cio/vfio_ccw_cp.h7
-rw-r--r--drivers/s390/cio/vfio_ccw_drv.c13
-rw-r--r--drivers/s390/crypto/pkey_api.c8
-rw-r--r--drivers/s390/crypto/vfio_ap_drv.c34
-rw-r--r--drivers/s390/crypto/vfio_ap_ops.c380
-rw-r--r--drivers/s390/crypto/vfio_ap_private.h15
-rw-r--r--drivers/s390/crypto/zcrypt_msgtype6.c4
-rw-r--r--drivers/s390/net/Kconfig8
-rw-r--r--drivers/s390/virtio/virtio_ccw.c246
-rw-r--r--drivers/thermal/intel/x86_pkg_temp_thermal.c142
-rw-r--r--drivers/tty/tty_ldisc.c8
-rw-r--r--drivers/usb/core/devio.c48
-rw-r--r--fs/afs/addr_list.c4
-rw-r--r--fs/afs/dynroot.c8
-rw-r--r--fs/afs/security.c2
-rw-r--r--fs/cifs/Kconfig2
-rw-r--r--fs/cifs/cifs_spnego.c25
-rw-r--r--fs/cifs/cifsacl.c28
-rw-r--r--fs/cifs/cifsencrypt.c62
-rw-r--r--fs/cifs/cifsfs.c1
-rw-r--r--fs/cifs/connect.c6
-rw-r--r--fs/cifs/dns_resolve.c3
-rw-r--r--fs/crypto/keyinfo.c2
-rw-r--r--fs/dax.c2
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h2
-rw-r--r--fs/ecryptfs/keystore.c2
-rw-r--r--fs/exec.c2
-rw-r--r--fs/fscache/object-list.c2
-rw-r--r--fs/nfs/dns_resolve.c3
-rw-r--r--fs/nfs/nfs4idmap.c30
-rw-r--r--fs/proc/Kconfig4
-rw-r--r--fs/proc/array.c4
-rw-r--r--fs/proc/base.c6
-rw-r--r--fs/ubifs/auth.c2
-rw-r--r--include/asm-generic/atomic64.h20
-rw-r--r--include/asm-generic/vdso/vsyscall.h50
-rw-r--r--include/clocksource/hyperv_timer.h107
-rw-r--r--include/clocksource/timer-davinci.h44
-rw-r--r--include/crypto/aead.h34
-rw-r--r--include/crypto/algapi.h7
-rw-r--r--include/crypto/arc4.h10
-rw-r--r--include/crypto/chacha.h2
-rw-r--r--include/crypto/crypto_wq.h8
-rw-r--r--include/crypto/drbg.h2
-rw-r--r--include/crypto/internal/hash.h6
-rw-r--r--include/crypto/internal/skcipher.h60
-rw-r--r--include/crypto/skcipher.h92
-rw-r--r--include/keys/request_key_auth-type.h1
-rw-r--r--include/linux/acpi.h12
-rw-r--r--include/linux/arch_topology.h2
-rw-r--r--include/linux/audit.h9
-rw-r--r--include/linux/cacheinfo.h2
-rw-r--r--include/linux/cgroup-defs.h2
-rw-r--r--include/linux/cgroup.h2
-rw-r--r--include/linux/cpuhotplug.h2
-rw-r--r--include/linux/crypto.h12
-rw-r--r--include/linux/dns_resolver.h3
-rw-r--r--include/linux/efi.h10
-rw-r--r--include/linux/energy_model.h2
-rw-r--r--include/linux/hrtimer.h16
-rw-r--r--include/linux/hrtimer_defs.h27
-rw-r--r--include/linux/ima.h2
-rw-r--r--include/linux/irqchip/arm-gic-common.h5
-rw-r--r--include/linux/irqchip/arm-gic.h3
-rw-r--r--include/linux/jump_label.h3
-rw-r--r--include/linux/key-type.h3
-rw-r--r--include/linux/key.h213
-rw-r--r--include/linux/lockdep.h43
-rw-r--r--include/linux/log2.h34
-rw-r--r--include/linux/module.h5
-rw-r--r--include/linux/percpu-rwsem.h14
-rw-r--r--include/linux/perf/arm_pmu.h2
-rw-r--r--include/linux/proc_fs.h9
-rw-r--r--include/linux/processor.h9
-rw-r--r--include/linux/ptrace.h2
-rw-r--r--include/linux/rcu_sync.h40
-rw-r--r--include/linux/rcupdate.h21
-rw-r--r--include/linux/rwsem.h16
-rw-r--r--include/linux/sched.h90
-rw-r--r--include/linux/sched/nohz.h8
-rw-r--r--include/linux/sched/signal.h15
-rw-r--r--include/linux/sched/sysctl.h11
-rw-r--r--include/linux/sched/topology.h25
-rw-r--r--include/linux/sched/user.h14
-rw-r--r--include/linux/sched/wake_q.h5
-rw-r--r--include/linux/security.h12
-rw-r--r--include/linux/smp.h52
-rw-r--r--include/linux/srcutree.h14
-rw-r--r--include/linux/stop_machine.h1
-rw-r--r--include/linux/syscalls.h2
-rw-r--r--include/linux/timekeeping.h32
-rw-r--r--include/linux/timer.h27
-rw-r--r--include/linux/topology.h6
-rw-r--r--include/linux/torture.h2
-rw-r--r--include/linux/tpm_eventlog.h152
-rw-r--r--include/linux/tracehook.h7
-rw-r--r--include/linux/types.h2
-rw-r--r--include/linux/user_namespace.h12
-rw-r--r--include/linux/workqueue.h4
-rw-r--r--include/net/cfg80211.h2
-rw-r--r--include/net/net_namespace.h3
-rw-r--r--include/trace/events/sched.h31
-rw-r--r--include/uapi/linux/audit.h1
-rw-r--r--include/uapi/linux/bpf.h2
-rw-r--r--include/uapi/linux/keyctl.h84
-rw-r--r--include/uapi/linux/sched.h14
-rw-r--r--include/uapi/linux/sched/types.h66
-rw-r--r--include/vdso/datapage.h89
-rw-r--r--include/vdso/helpers.h56
-rw-r--r--include/vdso/vsyscall.h11
-rw-r--r--init/Kconfig55
-rw-r--r--init/init_task.c5
-rw-r--r--kernel/audit.c27
-rw-r--r--kernel/audit.h8
-rw-r--r--kernel/auditfilter.c62
-rw-r--r--kernel/auditsc.c42
-rw-r--r--kernel/bpf/syscall.c2
-rw-r--r--kernel/cgroup/cgroup.c46
-rw-r--r--kernel/cgroup/cpuset.c4
-rw-r--r--kernel/cpu.c9
-rw-r--r--kernel/cred.c13
-rw-r--r--kernel/events/core.c4
-rw-r--r--kernel/events/uprobes.c8
-rw-r--r--kernel/fork.c7
-rw-r--r--kernel/futex.c69
-rw-r--r--kernel/irq/Makefile3
-rw-r--r--kernel/irq/affinity.c12
-rw-r--r--kernel/irq/autoprobe.c6
-rw-r--r--kernel/irq/chip.c10
-rw-r--r--kernel/irq/cpuhotplug.c2
-rw-r--r--kernel/irq/internals.h26
-rw-r--r--kernel/irq/irqdesc.c16
-rw-r--r--kernel/irq/irqdomain.c4
-rw-r--r--kernel/irq/manage.c90
-rw-r--r--kernel/irq/timings.c453
-rw-r--r--kernel/jump_label.c64
-rw-r--r--kernel/kexec_file.c9
-rw-r--r--kernel/locking/Makefile2
-rw-r--r--kernel/locking/lock_events.h45
-rw-r--r--kernel/locking/lock_events_list.h12
-rw-r--r--kernel/locking/lockdep.c742
-rw-r--r--kernel/locking/lockdep_internals.h36
-rw-r--r--kernel/locking/locktorture.c2
-rw-r--r--kernel/locking/percpu-rwsem.c2
-rw-r--r--kernel/locking/rwsem-xadd.c745
-rw-r--r--kernel/locking/rwsem.c1453
-rw-r--r--kernel/locking/rwsem.h306
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--kernel/power/energy_model.c2
-rw-r--r--kernel/ptrace.c3
-rw-r--r--kernel/rcu/rcu.h5
-rw-r--r--kernel/rcu/rcutorture.c96
-rw-r--r--kernel/rcu/srcutree.c69
-rw-r--r--kernel/rcu/sync.c214
-rw-r--r--kernel/rcu/tree.c164
-rw-r--r--kernel/rcu/tree.h6
-rw-r--r--kernel/rcu/tree_exp.h53
-rw-r--r--kernel/rcu/tree_plugin.h195
-rw-r--r--kernel/rcu/tree_stall.h4
-rw-r--r--kernel/rcu/update.c13
-rw-r--r--kernel/rseq.c4
-rw-r--r--kernel/sched/autogroup.c2
-rw-r--r--kernel/sched/core.c533
-rw-r--r--kernel/sched/cpudeadline.c4
-rw-r--r--kernel/sched/cpufreq_schedutil.c24
-rw-r--r--kernel/sched/cpupri.c4
-rw-r--r--kernel/sched/deadline.c8
-rw-r--r--kernel/sched/debug.c43
-rw-r--r--kernel/sched/fair.c628
-rw-r--r--kernel/sched/features.h1
-rw-r--r--kernel/sched/pelt.c13
-rw-r--r--kernel/sched/pelt.h2
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/sched/sched-pelt.h2
-rw-r--r--kernel/sched/sched.h134
-rw-r--r--kernel/sched/topology.c18
-rw-r--r--kernel/sched/wait.c8
-rw-r--r--kernel/seccomp.c2
-rw-r--r--kernel/signal.c251
-rw-r--r--kernel/smp.c12
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/stop_machine.c19
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/time/Makefile1
-rw-r--r--kernel/time/alarmtimer.c1
-rw-r--r--kernel/time/clocksource.c4
-rw-r--r--kernel/time/hrtimer.c8
-rw-r--r--kernel/time/ntp.c4
-rw-r--r--kernel/time/posix-timers.c13
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/time/time.c4
-rw-r--r--kernel/time/timekeeping.c2
-rw-r--r--kernel/time/timer_list.c36
-rw-r--r--kernel/time/vsyscall.c133
-rw-r--r--kernel/torture.c23
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--kernel/up.c3
-rw-r--r--kernel/user.c8
-rw-r--r--kernel/user_namespace.c9
-rw-r--r--kernel/workqueue.c28
-rw-r--r--lib/Kconfig5
-rw-r--r--lib/Kconfig.debug28
-rw-r--r--lib/Makefile2
-rw-r--r--lib/atomic64.c32
-rw-r--r--lib/crypto/Makefile4
-rw-r--r--lib/crypto/arc4.c74
-rw-r--r--lib/debugobjects.c321
-rw-r--r--lib/digsig.c4
-rw-r--r--lib/raid6/s390vx.uc2
-rw-r--r--lib/reed_solomon/Makefile2
-rw-r--r--lib/reed_solomon/decode_rs.c115
-rw-r--r--lib/reed_solomon/reed_solomon.c12
-rw-r--r--lib/reed_solomon/test_rslib.c518
-rw-r--r--lib/scatterlist.c9
-rw-r--r--lib/smp_processor_id.c2
-rw-r--r--lib/vdso/Kconfig36
-rw-r--r--lib/vdso/Makefile22
-rw-r--r--lib/vdso/gettimeofday.c239
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/vmalloc.c11
-rw-r--r--net/bpfilter/bpfilter_kern.c2
-rw-r--r--net/ceph/ceph_common.c2
-rw-r--r--net/ceph/messenger.c3
-rw-r--r--net/core/net_namespace.c20
-rw-r--r--net/dns_resolver/dns_key.c13
-rw-r--r--net/dns_resolver/dns_query.c20
-rw-r--r--net/mac80211/Kconfig2
-rw-r--r--net/mac80211/cfg.c4
-rw-r--r--net/mac80211/ieee80211_i.h4
-rw-r--r--net/mac80211/key.h1
-rw-r--r--net/mac80211/main.c6
-rw-r--r--net/mac80211/mlme.c3
-rw-r--r--net/mac80211/tkip.c8
-rw-r--r--net/mac80211/tkip.h4
-rw-r--r--net/mac80211/wep.c49
-rw-r--r--net/mac80211/wep.h5
-rw-r--r--net/mac80211/wpa.c4
-rw-r--r--net/rxrpc/key.c21
-rw-r--r--net/rxrpc/security.c2
-rw-r--r--net/wireless/Kconfig2
-rw-r--r--net/wireless/lib80211_crypt_tkip.c48
-rw-r--r--net/wireless/lib80211_crypt_wep.c51
-rw-r--r--net/wireless/reg.c6
-rw-r--r--samples/trace_events/trace-events-sample.c2
-rwxr-xr-xscripts/atomic/check-atomics.sh2
-rw-r--r--security/apparmor/label.c8
-rw-r--r--security/device_cgroup.c2
-rw-r--r--security/integrity/digsig.c34
-rw-r--r--security/integrity/digsig_asymmetric.c6
-rw-r--r--security/integrity/evm/evm_crypto.c2
-rw-r--r--security/integrity/evm/evm_main.c8
-rw-r--r--security/integrity/ima/Kconfig3
-rw-r--r--security/integrity/ima/ima.h21
-rw-r--r--security/integrity/ima/ima_api.c38
-rw-r--r--security/integrity/ima/ima_appraise.c9
-rw-r--r--security/integrity/ima/ima_init.c6
-rw-r--r--security/integrity/ima/ima_main.c123
-rw-r--r--security/integrity/ima/ima_mok.c13
-rw-r--r--security/integrity/ima/ima_policy.c163
-rw-r--r--security/integrity/ima/ima_template.c23
-rw-r--r--security/integrity/ima/ima_template_lib.c21
-rw-r--r--security/integrity/ima/ima_template_lib.h4
-rw-r--r--security/integrity/integrity.h12
-rw-r--r--security/integrity/platform_certs/platform_keyring.c14
-rw-r--r--security/keys/Kconfig18
-rw-r--r--security/keys/compat.c8
-rw-r--r--security/keys/encrypted-keys/encrypted.c2
-rw-r--r--security/keys/encrypted-keys/masterkey_trusted.c2
-rw-r--r--security/keys/gc.c4
-rw-r--r--security/keys/internal.h37
-rw-r--r--security/keys/key.c65
-rw-r--r--security/keys/keyctl.c198
-rw-r--r--security/keys/keyring.c582
-rw-r--r--security/keys/permission.c361
-rw-r--r--security/keys/persistent.c37
-rw-r--r--security/keys/proc.c25
-rw-r--r--security/keys/process_keys.c399
-rw-r--r--security/keys/request_key.c238
-rw-r--r--security/keys/request_key_auth.c80
-rw-r--r--security/safesetid/lsm.c4
-rw-r--r--security/security.c23
-rw-r--r--security/selinux/hooks.c29
-rw-r--r--security/selinux/selinuxfs.c2
-rw-r--r--security/selinux/ss/ebitmap.c10
-rw-r--r--security/selinux/ss/services.c33
-rw-r--r--security/smack/smack_lsm.c3
-rw-r--r--tools/include/linux/rcu.h4
-rw-r--r--tools/include/uapi/linux/bpf.h2
-rw-r--r--tools/memory-model/linux-kernel.bell6
-rw-r--r--tools/memory-model/linux-kernel.cat102
-rw-r--r--tools/memory-model/linux-kernel.def1
-rw-r--r--tools/memory-model/litmus-tests/MP+poonceonces.litmus2
-rw-r--r--tools/memory-model/litmus-tests/README2
-rw-r--r--tools/memory-model/lock.cat2
-rw-r--r--tools/memory-model/scripts/README4
-rwxr-xr-xtools/memory-model/scripts/checkalllitmus.sh2
-rwxr-xr-xtools/memory-model/scripts/checklitmus.sh2
-rw-r--r--tools/memory-model/scripts/parseargs.sh2
-rw-r--r--tools/memory-model/scripts/runlitmushist.sh2
-rw-r--r--tools/testing/radix-tree/linux/rcupdate.h2
-rw-r--r--tools/testing/selftests/rcutorture/Makefile3
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/configinit.sh39
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/cpus2use.sh5
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh13
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/jitter.sh13
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-build.sh9
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh3
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh13
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh23
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh14
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-build.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/CFcommon3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL14
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRIVIAL.boot3
-rw-r--r--tools/testing/selftests/timers/freq-step.c6
-rw-r--r--tools/testing/selftests/x86/Makefile5
-rw-r--r--tools/testing/selftests/x86/fsgsbase.c223
-rw-r--r--tools/testing/selftests/x86/syscall_arg_fault.c112
-rw-r--r--tools/testing/selftests/x86/test_vsyscall.c120
1075 files changed, 31682 insertions, 18800 deletions
diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index 74c6702de74e..fc376a323908 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -24,11 +24,11 @@ Description:
[euid=] [fowner=] [fsname=]]
lsm: [[subj_user=] [subj_role=] [subj_type=]
[obj_user=] [obj_role=] [obj_type=]]
- option: [[appraise_type=]] [permit_directio]
-
+ option: [[appraise_type=]] [template=] [permit_directio]
base: func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK][MODULE_CHECK]
[FIRMWARE_CHECK]
[KEXEC_KERNEL_CHECK] [KEXEC_INITRAMFS_CHECK]
+ [KEXEC_CMDLINE]
mask:= [[^]MAY_READ] [[^]MAY_WRITE] [[^]MAY_APPEND]
[[^]MAY_EXEC]
fsmagic:= hex value
@@ -38,6 +38,8 @@ Description:
fowner:= decimal value
lsm: are LSM specific
option: appraise_type:= [imasig]
+ template:= name of a defined IMA template type
+ (eg, ima-ng). Only valid when action is "measure".
pcr:= decimal value
default policy:
diff --git a/Documentation/ABI/testing/sysfs-bus-css b/Documentation/ABI/testing/sysfs-bus-css
index 2979c40c10e9..966f8504bd7b 100644
--- a/Documentation/ABI/testing/sysfs-bus-css
+++ b/Documentation/ABI/testing/sysfs-bus-css
@@ -33,3 +33,26 @@ Description: Contains the PIM/PAM/POM values, as reported by the
in sync with the values current in the channel subsystem).
Note: This is an I/O-subchannel specific attribute.
Users: s390-tools, HAL
+
+What: /sys/bus/css/devices/.../driver_override
+Date: June 2019
+Contact: Cornelia Huck <cohuck@redhat.com>
+ linux-s390@vger.kernel.org
+Description: This file allows the driver for a device to be specified. When
+ specified, only a driver with a name matching the value written
+ to driver_override will have an opportunity to bind to the
+ device. The override is specified by writing a string to the
+ driver_override file (echo vfio-ccw > driver_override) and
+ may be cleared with an empty string (echo > driver_override).
+ This returns the device to standard matching rules binding.
+ Writing to driver_override does not automatically unbind the
+ device from its current driver or make any attempt to
+ automatically load the specified driver. If no driver with a
+ matching name is currently loaded in the kernel, the device
+ will not bind to any driver. This also allows devices to
+ opt-out of driver binding using a driver_override name such as
+ "none". Only a single driver may be specified in the override,
+ there is no support for parsing delimiters.
+ Note that unlike the mechanism of the same name for pci, this
+ file does not allow to override basic matching rules. I.e.,
+ the driver must still match the subchannel type of the device.
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 1528239f69b2..923fe2001472 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -538,3 +538,26 @@ Description: Intel Energy and Performance Bias Hint (EPB)
This attribute is present for all online CPUs supporting the
Intel EPB feature.
+
+What: /sys/devices/system/cpu/umwait_control
+ /sys/devices/system/cpu/umwait_control/enable_c02
+ /sys/devices/system/cpu/umwait_control/max_time
+Date: May 2019
+Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description: Umwait control
+
+ enable_c02: Read/write interface to control umwait C0.2 state
+ Read returns C0.2 state status:
+ 0: C0.2 is disabled
+ 1: C0.2 is enabled
+
+ Write 'y' or '1' or 'on' to enable C0.2 state.
+ Write 'n' or '0' or 'off' to disable C0.2 state.
+
+ The interface is case insensitive.
+
+ max_time: Read/write interface to control umwait maximum time
+ in TSC-quanta that the CPU can reside in either C0.1
+ or C0.2 state. The time is an unsigned 32-bit number.
+ Note that a value of zero means there is no limit.
+ Low order two bits must be zero.
diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt
index 613033ff2b9b..5e6429d66c24 100644
--- a/Documentation/RCU/rcuref.txt
+++ b/Documentation/RCU/rcuref.txt
@@ -12,6 +12,7 @@ please read on.
Reference counting on elements of lists which are protected by traditional
reader/writer spinlocks or semaphores are straightforward:
+CODE LISTING A:
1. 2.
add() search_and_reference()
{ {
@@ -28,7 +29,8 @@ add() search_and_reference()
release_referenced() delete()
{ {
... write_lock(&list_lock);
- atomic_dec(&el->rc, relfunc) ...
+ if(atomic_dec_and_test(&el->rc)) ...
+ kfree(el);
... remove_element
} write_unlock(&list_lock);
...
@@ -44,6 +46,7 @@ search_and_reference() could potentially hold reference to an element which
has already been deleted from the list/array. Use atomic_inc_not_zero()
in this scenario as follows:
+CODE LISTING B:
1. 2.
add() search_and_reference()
{ {
@@ -79,6 +82,7 @@ search_and_reference() code path. In such cases, the
atomic_dec_and_test() may be moved from delete() to el_free()
as follows:
+CODE LISTING C:
1. 2.
add() search_and_reference()
{ {
@@ -114,6 +118,17 @@ element can therefore safely be freed. This in turn guarantees that if
any reader finds the element, that reader may safely acquire a reference
without checking the value of the reference counter.
+A clear advantage of the RCU-based pattern in listing C over the one
+in listing B is that any call to search_and_reference() that locates
+a given object will succeed in obtaining a reference to that object,
+even given a concurrent invocation of delete() for that same object.
+Similarly, a clear advantage of both listings B and C over listing A is
+that a call to delete() is not delayed even if there are an arbitrarily
+large number of calls to search_and_reference() searching for the same
+object that delete() was invoked on. Instead, all that is delayed is
+the eventual invocation of kfree(), which is usually not a problem on
+modern computer systems, even the small ones.
+
In cases where delete() can sleep, synchronize_rcu() can be called from
delete(), so that el_free() can be subsumed into delete as follows:
@@ -130,3 +145,7 @@ delete()
kfree(el);
...
}
+
+As additional examples in the kernel, the pattern in listing C is used by
+reference counting of struct pid, while the pattern in listing B is used by
+struct posix_acl.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 1ab70c37921f..13e88fc00f01 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -153,7 +153,7 @@ rcupdate.rcu_task_stall_timeout
This boot/sysfs parameter controls the RCU-tasks stall warning
interval. A value of zero or less suppresses RCU-tasks stall
warnings. A positive value sets the stall-warning interval
- in jiffies. An RCU-tasks stall warning starts with the line:
+ in seconds. An RCU-tasks stall warning starts with the line:
INFO: rcu_tasks detected stalls on tasks:
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 981651a8b65d..7e1a8721637a 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -212,7 +212,7 @@ synchronize_rcu()
rcu_assign_pointer()
- typeof(p) rcu_assign_pointer(p, typeof(p) v);
+ void rcu_assign_pointer(p, typeof(p) v);
Yes, rcu_assign_pointer() -is- implemented as a macro, though it
would be cool to be able to declare a function in this manner.
@@ -220,9 +220,9 @@ rcu_assign_pointer()
The updater uses this function to assign a new value to an
RCU-protected pointer, in order to safely communicate the change
- in value from the updater to the reader. This function returns
- the new value, and also executes any memory-barrier instructions
- required for a given CPU architecture.
+ in value from the updater to the reader. This macro does not
+ evaluate to an rvalue, but it does execute any memory-barrier
+ instructions required for a given CPU architecture.
Perhaps just as important, it serves to document (1) which
pointers are protected by RCU and (2) the point at which a
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index cf88c1f98270..a5c845338d6d 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -705,6 +705,12 @@ Conventions
informational files on the root cgroup which end up showing global
information available elsewhere shouldn't exist.
+- The default time unit is microseconds. If a different unit is ever
+ used, an explicit unit suffix must be present.
+
+- A parts-per quantity should use a percentage decimal with at least
+ two digit fractional part - e.g. 13.40.
+
- If a controller implements weight based resource distribution, its
interface file should be named "weight" and have the range [1,
10000] with 100 as the default. The values are chosen to allow
diff --git a/Documentation/admin-guide/hw-vuln/l1tf.rst b/Documentation/admin-guide/hw-vuln/l1tf.rst
index 31653a9f0e1b..656aee262e23 100644
--- a/Documentation/admin-guide/hw-vuln/l1tf.rst
+++ b/Documentation/admin-guide/hw-vuln/l1tf.rst
@@ -241,7 +241,7 @@ Guest mitigation mechanisms
For further information about confining guests to a single or to a group
of cores consult the cpusets documentation:
- https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt
+ https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.rst
.. _interrupt_isolation:
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 138f6664b2e2..74d28efa1c40 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -478,7 +478,7 @@
others).
ccw_timeout_log [S390]
- See Documentation/s390/CommonIO for details.
+ See Documentation/s390/common_io.rst for details.
cgroup_disable= [KNL] Disable a particular controller
Format: {name of the controller(s) to disable}
@@ -516,7 +516,7 @@
/selinux/checkreqprot.
cio_ignore= [S390]
- See Documentation/s390/CommonIO for details.
+ See Documentation/s390/common_io.rst for details.
clk_ignore_unused
[CLK]
Prevents the clock framework from automatically gating
@@ -3752,6 +3752,12 @@
the propagation of recent CPU-hotplug changes up
the rcu_node combining tree.
+ rcutree.use_softirq= [KNL]
+ If set to zero, move all RCU_SOFTIRQ processing to
+ per-CPU rcuc kthreads. Defaults to a non-zero
+ value, meaning that RCU_SOFTIRQ is used by default.
+ Specify rcutree.use_softirq=0 to use rcuc kthreads.
+
rcutree.rcu_fanout_exact= [KNL]
Disable autobalancing of the rcu_node combining
tree. This is used by rcutorture, and might
@@ -4078,7 +4084,7 @@
relax_domain_level=
[KNL, SMP] Set scheduler's default relax_domain_level.
- See Documentation/cgroup-v1/cpusets.txt.
+ See Documentation/cgroup-v1/cpusets.rst.
reserve= [KNL,BUGS] Force kernel to ignore I/O ports or memory
Format: <base1>,<size1>[,<base2>,<size2>,...]
@@ -4588,7 +4594,7 @@
swapaccount=[0|1]
[KNL] Enable accounting of swap in memory resource
controller if no parameter or 1 is given or disable
- it if 0 is given (See Documentation/cgroup-v1/memory.txt)
+ it if 0 is given (See Documentation/cgroup-v1/memory.rst)
swiotlb= [ARM,IA-64,PPC,MIPS,X86]
Format: { <int> | force | noforce }
@@ -5100,13 +5106,12 @@
targets for exploits that can control RIP.
emulate [default] Vsyscalls turn into traps and are
- emulated reasonably safely.
+ emulated reasonably safely. The vsyscall
+ page is readable.
- native Vsyscalls are native syscall instructions.
- This is a little bit faster than trapping
- and makes a few dynamic recompilers work
- better than they would in emulation mode.
- It also makes exploits much easier to write.
+ xonly Vsyscalls turn into traps and are
+ emulated reasonably safely. The vsyscall
+ page is not readable.
none Vsyscalls don't work at all. This makes
them quite hard to use for exploits but
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index d78c5b315f72..546f174e5d6a 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -15,7 +15,7 @@ document attempts to describe the concepts and APIs of the 2.6 memory policy
support.
Memory policies should not be confused with cpusets
-(``Documentation/cgroup-v1/cpusets.txt``)
+(``Documentation/cgroup-v1/cpusets.rst``)
which is an administrative mechanism for restricting the nodes from which
memory may be allocated by a set of processes. Memory policies are a
programming interface that a NUMA-aware application can take advantage of. When
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index b73a2519ecf2..5ae2ef2c12f3 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -207,6 +207,10 @@ HWCAP_FLAGM
Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0001.
+HWCAP2_FLAGM2
+
+ Functionality implied by ID_AA64ISAR0_EL1.TS == 0b0010.
+
HWCAP_SSBS
Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010.
@@ -223,6 +227,10 @@ HWCAP_PACG
ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
Documentation/arm64/pointer-authentication.txt.
+HWCAP2_FRINT
+
+ Functionality implied by ID_AA64ISAR1_EL1.FRINTTS == 0b0001.
+
4. Unused AT_HWCAP bits
-----------------------
diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index dca3fb0554db..0ab747e0d5ac 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -81,9 +81,11 @@ Non-RMW ops:
The non-RMW ops are (typically) regular LOADs and STOREs and are canonically
implemented using READ_ONCE(), WRITE_ONCE(), smp_load_acquire() and
-smp_store_release() respectively.
+smp_store_release() respectively. Therefore, if you find yourself only using
+the Non-RMW operations of atomic_t, you do not in fact need atomic_t at all
+and are doing it wrong.
-The one detail to this is that atomic_set{}() should be observable to the RMW
+A subtle detail of atomic_set{}() is that it should be observable to the RMW
ops. That is:
C atomic-set
@@ -187,13 +189,22 @@ The barriers:
smp_mb__{before,after}_atomic()
-only apply to the RMW ops and can be used to augment/upgrade the ordering
-inherent to the used atomic op. These barriers provide a full smp_mb().
+only apply to the RMW atomic ops and can be used to augment/upgrade the
+ordering inherent to the op. These barriers act almost like a full smp_mb():
+smp_mb__before_atomic() orders all earlier accesses against the RMW op
+itself and all accesses following it, and smp_mb__after_atomic() orders all
+later accesses against the RMW op and all accesses preceding it. However,
+accesses between the smp_mb__{before,after}_atomic() and the RMW op are not
+ordered, so it is advisable to place the barrier right next to the RMW atomic
+op whenever possible.
These helper barriers exist because architectures have varying implicit
ordering on their SMP atomic primitives. For example our TSO architectures
provide full ordered atomics and these barriers are no-ops.
+NOTE: when the atomic RmW ops are fully ordered, they should also imply a
+compiler barrier.
+
Thus:
atomic_fetch_add();
@@ -212,7 +223,9 @@ Further, while something like:
atomic_dec(&X);
is a 'typical' RELEASE pattern, the barrier is strictly stronger than
-a RELEASE. Similarly for something like:
+a RELEASE because it orders preceding instructions against both the read
+and write parts of the atomic_dec(), and against all following instructions
+as well. Similarly, something like:
atomic_inc(&X);
smp_mb__after_atomic();
@@ -244,7 +257,8 @@ strictly stronger than ACQUIRE. As illustrated:
This should not happen; but a hypothetical atomic_inc_acquire() --
(void)atomic_fetch_inc_acquire() for instance -- would allow the outcome,
-since then:
+because it would not order the W part of the RMW against the following
+WRITE_ONCE. Thus:
P1 P2
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
index 1a0f2ac02eb6..b2265cf6c9c3 100644
--- a/Documentation/block/bfq-iosched.txt
+++ b/Documentation/block/bfq-iosched.txt
@@ -539,7 +539,7 @@ As for cgroups-v1 (blkio controller), the exact set of stat files
created, and kept up-to-date by bfq, depends on whether
CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq creates all
the stat files documented in
-Documentation/cgroup-v1/blkio-controller.txt. If, instead,
+Documentation/cgroup-v1/blkio-controller.rst. If, instead,
CONFIG_DEBUG_BLK_CGROUP is not set, then bfq creates only the files
blkio.bfq.io_service_bytes
blkio.bfq.io_service_bytes_recursive
diff --git a/Documentation/cgroup-v1/blkio-controller.txt b/Documentation/cgroup-v1/blkio-controller.rst
index d1a1b7bdd03a..fd3184537d23 100644
--- a/Documentation/cgroup-v1/blkio-controller.txt
+++ b/Documentation/cgroup-v1/blkio-controller.rst
@@ -1,5 +1,7 @@
- Block IO Controller
- ===================
+===================
+Block IO Controller
+===================
+
Overview
========
cgroup subsys "blkio" implements the block io controller. There seems to be
@@ -17,24 +19,27 @@ HOWTO
=====
Throttling/Upper Limit policy
-----------------------------
-- Enable Block IO controller
+- Enable Block IO controller::
+
CONFIG_BLK_CGROUP=y
-- Enable throttling in block layer
+- Enable throttling in block layer::
+
CONFIG_BLK_DEV_THROTTLING=y
-- Mount blkio controller (see cgroups.txt, Why are cgroups needed?)
+- Mount blkio controller (see cgroups.txt, Why are cgroups needed?)::
+
mount -t cgroup -o blkio none /sys/fs/cgroup/blkio
- Specify a bandwidth rate on particular device for root group. The format
- for policy is "<major>:<minor> <bytes_per_second>".
+ for policy is "<major>:<minor> <bytes_per_second>"::
echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device
Above will put a limit of 1MB/second on reads happening for root group
on device having major/minor number 8:16.
-- Run dd to read a file and see if rate is throttled to 1MB/s or not.
+- Run dd to read a file and see if rate is throttled to 1MB/s or not::
# dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
1024+0 records in
@@ -51,7 +56,7 @@ throttling's hierarchy support is enabled iff "sane_behavior" is
enabled from cgroup side, which currently is a development option and
not publicly available.
-If somebody created a hierarchy like as follows.
+If somebody created a hierarchy like as follows::
root
/ \
@@ -66,7 +71,7 @@ directly generated by tasks in that cgroup.
Throttling without "sane_behavior" enabled from cgroup side will
practically treat all groups at same level as if it looks like the
-following.
+following::
pivot
/ / \ \
@@ -99,27 +104,31 @@ Proportional weight policy files
These rules override the default value of group weight as specified
by blkio.weight.
- Following is the format.
+ Following is the format::
+
+ # echo dev_maj:dev_minor weight > blkio.weight_device
+
+ Configure weight=300 on /dev/sdb (8:16) in this cgroup::
+
+ # echo 8:16 300 > blkio.weight_device
+ # cat blkio.weight_device
+ dev weight
+ 8:16 300
+
+ Configure weight=500 on /dev/sda (8:0) in this cgroup::
- # echo dev_maj:dev_minor weight > blkio.weight_device
- Configure weight=300 on /dev/sdb (8:16) in this cgroup
- # echo 8:16 300 > blkio.weight_device
- # cat blkio.weight_device
- dev weight
- 8:16 300
+ # echo 8:0 500 > blkio.weight_device
+ # cat blkio.weight_device
+ dev weight
+ 8:0 500
+ 8:16 300
- Configure weight=500 on /dev/sda (8:0) in this cgroup
- # echo 8:0 500 > blkio.weight_device
- # cat blkio.weight_device
- dev weight
- 8:0 500
- 8:16 300
+ Remove specific weight for /dev/sda in this cgroup::
- Remove specific weight for /dev/sda in this cgroup
- # echo 8:0 0 > blkio.weight_device
- # cat blkio.weight_device
- dev weight
- 8:16 300
+ # echo 8:0 0 > blkio.weight_device
+ # cat blkio.weight_device
+ dev weight
+ 8:16 300
- blkio.leaf_weight[_device]
- Equivalents of blkio.weight[_device] for the purpose of
@@ -244,30 +253,30 @@ Throttling/Upper limit policy files
- blkio.throttle.read_bps_device
- Specifies upper limit on READ rate from the device. IO rate is
specified in bytes per second. Rules are per device. Following is
- the format.
+ the format::
- echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device
+ echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device
- blkio.throttle.write_bps_device
- Specifies upper limit on WRITE rate to the device. IO rate is
specified in bytes per second. Rules are per device. Following is
- the format.
+ the format::
- echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device
+ echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device
- blkio.throttle.read_iops_device
- Specifies upper limit on READ rate from the device. IO rate is
specified in IO per second. Rules are per device. Following is
- the format.
+ the format::
- echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device
+ echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device
- blkio.throttle.write_iops_device
- Specifies upper limit on WRITE rate to the device. IO rate is
specified in io per second. Rules are per device. Following is
- the format.
+ the format::
- echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device
+ echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device
Note: If both BW and IOPS rules are specified for a device, then IO is
subjected to both the constraints.
diff --git a/Documentation/cgroup-v1/cgroups.txt b/Documentation/cgroup-v1/cgroups.rst
index 059f7063eea6..46bbe7e022d4 100644
--- a/Documentation/cgroup-v1/cgroups.txt
+++ b/Documentation/cgroup-v1/cgroups.rst
@@ -1,35 +1,39 @@
- CGROUPS
- -------
+==============
+Control Groups
+==============
Written by Paul Menage <menage@google.com> based on
-Documentation/cgroup-v1/cpusets.txt
+Documentation/cgroup-v1/cpusets.rst
Original copyright statements from cpusets.txt:
+
Portions Copyright (C) 2004 BULL SA.
+
Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
+
Modified by Paul Jackson <pj@sgi.com>
+
Modified by Christoph Lameter <cl@linux.com>
-CONTENTS:
-=========
-
-1. Control Groups
- 1.1 What are cgroups ?
- 1.2 Why are cgroups needed ?
- 1.3 How are cgroups implemented ?
- 1.4 What does notify_on_release do ?
- 1.5 What does clone_children do ?
- 1.6 How do I use cgroups ?
-2. Usage Examples and Syntax
- 2.1 Basic Usage
- 2.2 Attaching processes
- 2.3 Mounting hierarchies by name
-3. Kernel API
- 3.1 Overview
- 3.2 Synchronization
- 3.3 Subsystem API
-4. Extended attributes usage
-5. Questions
+.. CONTENTS:
+
+ 1. Control Groups
+ 1.1 What are cgroups ?
+ 1.2 Why are cgroups needed ?
+ 1.3 How are cgroups implemented ?
+ 1.4 What does notify_on_release do ?
+ 1.5 What does clone_children do ?
+ 1.6 How do I use cgroups ?
+ 2. Usage Examples and Syntax
+ 2.1 Basic Usage
+ 2.2 Attaching processes
+ 2.3 Mounting hierarchies by name
+ 3. Kernel API
+ 3.1 Overview
+ 3.2 Synchronization
+ 3.3 Subsystem API
+ 4. Extended attributes usage
+ 5. Questions
1. Control Groups
=================
@@ -72,7 +76,7 @@ On their own, the only use for cgroups is for simple job
tracking. The intention is that other subsystems hook into the generic
cgroup support to provide new attributes for cgroups, such as
accounting/limiting the resources which processes in a cgroup can
-access. For example, cpusets (see Documentation/cgroup-v1/cpusets.txt) allow
+access. For example, cpusets (see Documentation/cgroup-v1/cpusets.rst) allow
you to associate a set of CPUs and a set of memory nodes with the
tasks in each cgroup.
@@ -108,7 +112,7 @@ As an example of a scenario (originally proposed by vatsa@in.ibm.com)
that can benefit from multiple hierarchies, consider a large
university server with various users - students, professors, system
tasks etc. The resource planning for this server could be along the
-following lines:
+following lines::
CPU : "Top cpuset"
/ \
@@ -136,7 +140,7 @@ depending on who launched it (prof/student).
With the ability to classify tasks differently for different resources
(by putting those resource subsystems in different hierarchies),
the admin can easily set up a script which receives exec notifications
-and depending on who is launching the browser he can
+and depending on who is launching the browser he can::
# echo browser_pid > /sys/fs/cgroup/<restype>/<userclass>/tasks
@@ -151,7 +155,7 @@ wants to do online gaming :)) OR give one of the student's simulation
apps enhanced CPU power.
With ability to write PIDs directly to resource classes, it's just a
-matter of:
+matter of::
# echo pid > /sys/fs/cgroup/network/<new_class>/tasks
(after some time)
@@ -306,7 +310,7 @@ configuration from the parent during initialization.
--------------------------
To start a new job that is to be contained within a cgroup, using
-the "cpuset" cgroup subsystem, the steps are something like:
+the "cpuset" cgroup subsystem, the steps are something like::
1) mount -t tmpfs cgroup_root /sys/fs/cgroup
2) mkdir /sys/fs/cgroup/cpuset
@@ -320,7 +324,7 @@ the "cpuset" cgroup subsystem, the steps are something like:
For example, the following sequence of commands will setup a cgroup
named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
-and then start a subshell 'sh' in that cgroup:
+and then start a subshell 'sh' in that cgroup::
mount -t tmpfs cgroup_root /sys/fs/cgroup
mkdir /sys/fs/cgroup/cpuset
@@ -345,8 +349,9 @@ and then start a subshell 'sh' in that cgroup:
Creating, modifying, using cgroups can be done through the cgroup
virtual filesystem.
-To mount a cgroup hierarchy with all available subsystems, type:
-# mount -t cgroup xxx /sys/fs/cgroup
+To mount a cgroup hierarchy with all available subsystems, type::
+
+ # mount -t cgroup xxx /sys/fs/cgroup
The "xxx" is not interpreted by the cgroup code, but will appear in
/proc/mounts so may be any useful identifying string that you like.
@@ -355,18 +360,19 @@ Note: Some subsystems do not work without some user input first. For instance,
if cpusets are enabled the user will have to populate the cpus and mems files
for each new cgroup created before that group can be used.
-As explained in section `1.2 Why are cgroups needed?' you should create
+As explained in section `1.2 Why are cgroups needed?` you should create
different hierarchies of cgroups for each single resource or group of
resources you want to control. Therefore, you should mount a tmpfs on
/sys/fs/cgroup and create directories for each cgroup resource or resource
-group.
+group::
-# mount -t tmpfs cgroup_root /sys/fs/cgroup
-# mkdir /sys/fs/cgroup/rg1
+ # mount -t tmpfs cgroup_root /sys/fs/cgroup
+ # mkdir /sys/fs/cgroup/rg1
To mount a cgroup hierarchy with just the cpuset and memory
-subsystems, type:
-# mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1
+subsystems, type::
+
+ # mount -t cgroup -o cpuset,memory hier1 /sys/fs/cgroup/rg1
While remounting cgroups is currently supported, it is not recommend
to use it. Remounting allows changing bound subsystems and
@@ -375,9 +381,10 @@ hierarchy is empty and release_agent itself should be replaced with
conventional fsnotify. The support for remounting will be removed in
the future.
-To Specify a hierarchy's release_agent:
-# mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \
- xxx /sys/fs/cgroup/rg1
+To Specify a hierarchy's release_agent::
+
+ # mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \
+ xxx /sys/fs/cgroup/rg1
Note that specifying 'release_agent' more than once will return failure.
@@ -390,32 +397,39 @@ Then under /sys/fs/cgroup/rg1 you can find a tree that corresponds to the
tree of the cgroups in the system. For instance, /sys/fs/cgroup/rg1
is the cgroup that holds the whole system.
-If you want to change the value of release_agent:
-# echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent
+If you want to change the value of release_agent::
+
+ # echo "/sbin/new_release_agent" > /sys/fs/cgroup/rg1/release_agent
It can also be changed via remount.
-If you want to create a new cgroup under /sys/fs/cgroup/rg1:
-# cd /sys/fs/cgroup/rg1
-# mkdir my_cgroup
+If you want to create a new cgroup under /sys/fs/cgroup/rg1::
+
+ # cd /sys/fs/cgroup/rg1
+ # mkdir my_cgroup
+
+Now you want to do something with this cgroup:
+
+ # cd my_cgroup
-Now you want to do something with this cgroup.
-# cd my_cgroup
+In this directory you can find several files::
-In this directory you can find several files:
-# ls
-cgroup.procs notify_on_release tasks
-(plus whatever files added by the attached subsystems)
+ # ls
+ cgroup.procs notify_on_release tasks
+ (plus whatever files added by the attached subsystems)
-Now attach your shell to this cgroup:
-# /bin/echo $$ > tasks
+Now attach your shell to this cgroup::
+
+ # /bin/echo $$ > tasks
You can also create cgroups inside your cgroup by using mkdir in this
-directory.
-# mkdir my_sub_cs
+directory::
+
+ # mkdir my_sub_cs
+
+To remove a cgroup, just use rmdir::
-To remove a cgroup, just use rmdir:
-# rmdir my_sub_cs
+ # rmdir my_sub_cs
This will fail if the cgroup is in use (has cgroups inside, or
has processes attached, or is held alive by other subsystem-specific
@@ -424,19 +438,21 @@ reference).
2.2 Attaching processes
-----------------------
-# /bin/echo PID > tasks
+::
+
+ # /bin/echo PID > tasks
Note that it is PID, not PIDs. You can only attach ONE task at a time.
-If you have several tasks to attach, you have to do it one after another:
+If you have several tasks to attach, you have to do it one after another::
-# /bin/echo PID1 > tasks
-# /bin/echo PID2 > tasks
- ...
-# /bin/echo PIDn > tasks
+ # /bin/echo PID1 > tasks
+ # /bin/echo PID2 > tasks
+ ...
+ # /bin/echo PIDn > tasks
-You can attach the current shell task by echoing 0:
+You can attach the current shell task by echoing 0::
-# echo 0 > tasks
+ # echo 0 > tasks
You can use the cgroup.procs file instead of the tasks file to move all
threads in a threadgroup at once. Echoing the PID of any task in a
@@ -529,7 +545,7 @@ Each subsystem may export the following methods. The only mandatory
methods are css_alloc/free. Any others that are null are presumed to
be successful no-ops.
-struct cgroup_subsys_state *css_alloc(struct cgroup *cgrp)
+``struct cgroup_subsys_state *css_alloc(struct cgroup *cgrp)``
(cgroup_mutex held by caller)
Called to allocate a subsystem state object for a cgroup. The
@@ -544,7 +560,7 @@ identified by the passed cgroup object having a NULL parent (since
it's the root of the hierarchy) and may be an appropriate place for
initialization code.
-int css_online(struct cgroup *cgrp)
+``int css_online(struct cgroup *cgrp)``
(cgroup_mutex held by caller)
Called after @cgrp successfully completed all allocations and made
@@ -554,7 +570,7 @@ callback can be used to implement reliable state sharing and
propagation along the hierarchy. See the comment on
cgroup_for_each_descendant_pre() for details.
-void css_offline(struct cgroup *cgrp);
+``void css_offline(struct cgroup *cgrp);``
(cgroup_mutex held by caller)
This is the counterpart of css_online() and called iff css_online()
@@ -564,7 +580,7 @@ all references it's holding on @cgrp. When all references are dropped,
cgroup removal will proceed to the next step - css_free(). After this
callback, @cgrp should be considered dead to the subsystem.
-void css_free(struct cgroup *cgrp)
+``void css_free(struct cgroup *cgrp)``
(cgroup_mutex held by caller)
The cgroup system is about to free @cgrp; the subsystem should free
@@ -573,7 +589,7 @@ is completely unused; @cgrp->parent is still valid. (Note - can also
be called for a newly-created cgroup if an error occurs after this
subsystem's create() method has been called for the new cgroup).
-int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+``int can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)``
(cgroup_mutex held by caller)
Called prior to moving one or more tasks into a cgroup; if the
@@ -594,7 +610,7 @@ fork. If this method returns 0 (success) then this should remain valid
while the caller holds cgroup_mutex and it is ensured that either
attach() or cancel_attach() will be called in future.
-void css_reset(struct cgroup_subsys_state *css)
+``void css_reset(struct cgroup_subsys_state *css)``
(cgroup_mutex held by caller)
An optional operation which should restore @css's configuration to the
@@ -608,7 +624,7 @@ This prevents unexpected resource control from a hidden css and
ensures that the configuration is in the initial state when it is made
visible again later.
-void cancel_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+``void cancel_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)``
(cgroup_mutex held by caller)
Called when a task attach operation has failed after can_attach() has succeeded.
@@ -617,26 +633,26 @@ function, so that the subsystem can implement a rollback. If not, not necessary.
This will be called only about subsystems whose can_attach() operation have
succeeded. The parameters are identical to can_attach().
-void attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+``void attach(struct cgroup *cgrp, struct cgroup_taskset *tset)``
(cgroup_mutex held by caller)
Called after the task has been attached to the cgroup, to allow any
post-attachment activity that requires memory allocations or blocking.
The parameters are identical to can_attach().
-void fork(struct task_struct *task)
+``void fork(struct task_struct *task)``
Called when a task is forked into a cgroup.
-void exit(struct task_struct *task)
+``void exit(struct task_struct *task)``
Called during task exit.
-void free(struct task_struct *task)
+``void free(struct task_struct *task)``
Called when the task_struct is freed.
-void bind(struct cgroup *root)
+``void bind(struct cgroup *root)``
(cgroup_mutex held by caller)
Called when a cgroup subsystem is rebound to a different hierarchy
@@ -649,6 +665,7 @@ that is being created/destroyed (and hence has no sub-cgroups).
cgroup filesystem supports certain types of extended attributes in its
directories and files. The current supported types are:
+
- Trusted (XATTR_TRUSTED)
- Security (XATTR_SECURITY)
@@ -666,12 +683,13 @@ in containers and systemd for assorted meta data like main PID in a cgroup
5. Questions
============
-Q: what's up with this '/bin/echo' ?
-A: bash's builtin 'echo' command does not check calls to write() against
- errors. If you use it in the cgroup file system, you won't be
- able to tell whether a command succeeded or failed.
+::
-Q: When I attach processes, only the first of the line gets really attached !
-A: We can only return one error code per call to write(). So you should also
- put only ONE PID.
+ Q: what's up with this '/bin/echo' ?
+ A: bash's builtin 'echo' command does not check calls to write() against
+ errors. If you use it in the cgroup file system, you won't be
+ able to tell whether a command succeeded or failed.
+ Q: When I attach processes, only the first of the line gets really attached !
+ A: We can only return one error code per call to write(). So you should also
+ put only ONE PID.
diff --git a/Documentation/cgroup-v1/cpuacct.txt b/Documentation/cgroup-v1/cpuacct.rst
index 9d73cc0cadb9..d30ed81d2ad7 100644
--- a/Documentation/cgroup-v1/cpuacct.txt
+++ b/Documentation/cgroup-v1/cpuacct.rst
@@ -1,5 +1,6 @@
+=========================
CPU Accounting Controller
--------------------------
+=========================
The CPU accounting controller is used to group tasks using cgroups and
account the CPU usage of these groups of tasks.
@@ -8,9 +9,9 @@ The CPU accounting controller supports multi-hierarchy groups. An accounting
group accumulates the CPU usage of all of its child groups and the tasks
directly present in its group.
-Accounting groups can be created by first mounting the cgroup filesystem.
+Accounting groups can be created by first mounting the cgroup filesystem::
-# mount -t cgroup -ocpuacct none /sys/fs/cgroup
+ # mount -t cgroup -ocpuacct none /sys/fs/cgroup
With the above step, the initial or the parent accounting group becomes
visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
@@ -19,11 +20,11 @@ the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
by this group which is essentially the CPU time obtained by all the tasks
in the system.
-New accounting groups can be created under the parent group /sys/fs/cgroup.
+New accounting groups can be created under the parent group /sys/fs/cgroup::
-# cd /sys/fs/cgroup
-# mkdir g1
-# echo $$ > g1/tasks
+ # cd /sys/fs/cgroup
+ # mkdir g1
+ # echo $$ > g1/tasks
The above steps create a new group g1 and move the current shell
process (bash) into it. CPU time consumed by this bash and its children
diff --git a/Documentation/cgroup-v1/cpusets.txt b/Documentation/cgroup-v1/cpusets.rst
index 8402dd6de8df..b6a42cdea72b 100644
--- a/Documentation/cgroup-v1/cpusets.txt
+++ b/Documentation/cgroup-v1/cpusets.rst
@@ -1,35 +1,36 @@
- CPUSETS
- -------
+=======
+CPUSETS
+=======
Copyright (C) 2004 BULL SA.
-Written by Simon.Derr@bull.net
-
-Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
-Modified by Paul Jackson <pj@sgi.com>
-Modified by Christoph Lameter <cl@linux.com>
-Modified by Paul Menage <menage@google.com>
-Modified by Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
-CONTENTS:
-=========
+Written by Simon.Derr@bull.net
-1. Cpusets
- 1.1 What are cpusets ?
- 1.2 Why are cpusets needed ?
- 1.3 How are cpusets implemented ?
- 1.4 What are exclusive cpusets ?
- 1.5 What is memory_pressure ?
- 1.6 What is memory spread ?
- 1.7 What is sched_load_balance ?
- 1.8 What is sched_relax_domain_level ?
- 1.9 How do I use cpusets ?
-2. Usage Examples and Syntax
- 2.1 Basic Usage
- 2.2 Adding/removing cpus
- 2.3 Setting flags
- 2.4 Attaching processes
-3. Questions
-4. Contact
+- Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
+- Modified by Paul Jackson <pj@sgi.com>
+- Modified by Christoph Lameter <cl@linux.com>
+- Modified by Paul Menage <menage@google.com>
+- Modified by Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
+
+.. CONTENTS:
+
+ 1. Cpusets
+ 1.1 What are cpusets ?
+ 1.2 Why are cpusets needed ?
+ 1.3 How are cpusets implemented ?
+ 1.4 What are exclusive cpusets ?
+ 1.5 What is memory_pressure ?
+ 1.6 What is memory spread ?
+ 1.7 What is sched_load_balance ?
+ 1.8 What is sched_relax_domain_level ?
+ 1.9 How do I use cpusets ?
+ 2. Usage Examples and Syntax
+ 2.1 Basic Usage
+ 2.2 Adding/removing cpus
+ 2.3 Setting flags
+ 2.4 Attaching processes
+ 3. Questions
+ 4. Contact
1. Cpusets
==========
@@ -48,7 +49,7 @@ hooks, beyond what is already present, required to manage dynamic
job placement on large systems.
Cpusets use the generic cgroup subsystem described in
-Documentation/cgroup-v1/cgroups.txt.
+Documentation/cgroup-v1/cgroups.rst.
Requests by a task, using the sched_setaffinity(2) system call to
include CPUs in its CPU affinity mask, and using the mbind(2) and
@@ -157,7 +158,7 @@ modifying cpusets is via this cpuset file system.
The /proc/<pid>/status file for each task has four added lines,
displaying the task's cpus_allowed (on which CPUs it may be scheduled)
and mems_allowed (on which Memory Nodes it may obtain memory),
-in the two formats seen in the following example:
+in the two formats seen in the following example::
Cpus_allowed: ffffffff,ffffffff,ffffffff,ffffffff
Cpus_allowed_list: 0-127
@@ -181,6 +182,7 @@ files describing that cpuset:
- cpuset.sched_relax_domain_level: the searching range when migrating tasks
In addition, only the root cpuset has the following file:
+
- cpuset.memory_pressure_enabled flag: compute memory_pressure?
New cpusets are created using the mkdir system call or shell
@@ -266,7 +268,8 @@ to monitor a cpuset for signs of memory pressure. It's up to the
batch manager or other user code to decide what to do about it and
take action.
-==> Unless this feature is enabled by writing "1" to the special file
+==>
+ Unless this feature is enabled by writing "1" to the special file
/dev/cpuset/memory_pressure_enabled, the hook in the rebalance
code of __alloc_pages() for this metric reduces to simply noticing
that the cpuset_memory_pressure_enabled flag is zero. So only
@@ -399,6 +402,7 @@ have tasks running on them unless explicitly assigned.
This default load balancing across all CPUs is not well suited for
the following two situations:
+
1) On large systems, load balancing across many CPUs is expensive.
If the system is managed using cpusets to place independent jobs
on separate sets of CPUs, full load balancing is unnecessary.
@@ -501,6 +505,7 @@ all the CPUs that must be load balanced.
The cpuset code builds a new such partition and passes it to the
scheduler sched domain setup code, to have the sched domains rebuilt
as necessary, whenever:
+
- the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes,
- or CPUs come or go from a cpuset with this flag enabled,
- or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs
@@ -553,13 +558,15 @@ this searching range as you like. This file takes int value which
indicates size of searching range in levels ideally as follows,
otherwise initial value -1 that indicates the cpuset has no request.
- -1 : no request. use system default or follow request of others.
- 0 : no search.
- 1 : search siblings (hyperthreads in a core).
- 2 : search cores in a package.
- 3 : search cpus in a node [= system wide on non-NUMA system]
- 4 : search nodes in a chunk of node [on NUMA system]
- 5 : search system wide [on NUMA system]
+====== ===========================================================
+ -1 no request. use system default or follow request of others.
+ 0 no search.
+ 1 search siblings (hyperthreads in a core).
+ 2 search cores in a package.
+ 3 search cpus in a node [= system wide on non-NUMA system]
+ 4 search nodes in a chunk of node [on NUMA system]
+ 5 search system wide [on NUMA system]
+====== ===========================================================
The system default is architecture dependent. The system default
can be changed using the relax_domain_level= boot parameter.
@@ -578,13 +585,14 @@ and whether it is acceptable or not depends on your situation.
Don't modify this file if you are not sure.
If your situation is:
+
- The migration costs between each cpu can be assumed considerably
small(for you) due to your special application's behavior or
special hardware support for CPU cache etc.
- The searching cost doesn't have impact(for you) or you can make
the searching cost enough small by managing cpuset to compact etc.
- The latency is required even it sacrifices cache hit rate etc.
-then increasing 'sched_relax_domain_level' would benefit you.
+ then increasing 'sched_relax_domain_level' would benefit you.
1.9 How do I use cpusets ?
@@ -678,7 +686,7 @@ To start a new job that is to be contained within a cpuset, the steps are:
For example, the following sequence of commands will setup a cpuset
named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
-and then start a subshell 'sh' in that cpuset:
+and then start a subshell 'sh' in that cpuset::
mount -t cgroup -ocpuset cpuset /sys/fs/cgroup/cpuset
cd /sys/fs/cgroup/cpuset
@@ -693,6 +701,7 @@ and then start a subshell 'sh' in that cpuset:
cat /proc/self/cpuset
There are ways to query or modify cpusets:
+
- via the cpuset file system directly, using the various cd, mkdir, echo,
cat, rmdir commands from the shell, or their equivalent from C.
- via the C library libcpuset.
@@ -722,115 +731,133 @@ Then under /sys/fs/cgroup/cpuset you can find a tree that corresponds to the
tree of the cpusets in the system. For instance, /sys/fs/cgroup/cpuset
is the cpuset that holds the whole system.
-If you want to create a new cpuset under /sys/fs/cgroup/cpuset:
-# cd /sys/fs/cgroup/cpuset
-# mkdir my_cpuset
+If you want to create a new cpuset under /sys/fs/cgroup/cpuset::
+
+ # cd /sys/fs/cgroup/cpuset
+ # mkdir my_cpuset
-Now you want to do something with this cpuset.
-# cd my_cpuset
+Now you want to do something with this cpuset::
-In this directory you can find several files:
-# ls
-cgroup.clone_children cpuset.memory_pressure
-cgroup.event_control cpuset.memory_spread_page
-cgroup.procs cpuset.memory_spread_slab
-cpuset.cpu_exclusive cpuset.mems
-cpuset.cpus cpuset.sched_load_balance
-cpuset.mem_exclusive cpuset.sched_relax_domain_level
-cpuset.mem_hardwall notify_on_release
-cpuset.memory_migrate tasks
+ # cd my_cpuset
+
+In this directory you can find several files::
+
+ # ls
+ cgroup.clone_children cpuset.memory_pressure
+ cgroup.event_control cpuset.memory_spread_page
+ cgroup.procs cpuset.memory_spread_slab
+ cpuset.cpu_exclusive cpuset.mems
+ cpuset.cpus cpuset.sched_load_balance
+ cpuset.mem_exclusive cpuset.sched_relax_domain_level
+ cpuset.mem_hardwall notify_on_release
+ cpuset.memory_migrate tasks
Reading them will give you information about the state of this cpuset:
the CPUs and Memory Nodes it can use, the processes that are using
it, its properties. By writing to these files you can manipulate
the cpuset.
-Set some flags:
-# /bin/echo 1 > cpuset.cpu_exclusive
+Set some flags::
+
+ # /bin/echo 1 > cpuset.cpu_exclusive
+
+Add some cpus::
+
+ # /bin/echo 0-7 > cpuset.cpus
+
+Add some mems::
-Add some cpus:
-# /bin/echo 0-7 > cpuset.cpus
+ # /bin/echo 0-7 > cpuset.mems
-Add some mems:
-# /bin/echo 0-7 > cpuset.mems
+Now attach your shell to this cpuset::
-Now attach your shell to this cpuset:
-# /bin/echo $$ > tasks
+ # /bin/echo $$ > tasks
You can also create cpusets inside your cpuset by using mkdir in this
-directory.
-# mkdir my_sub_cs
+directory::
+
+ # mkdir my_sub_cs
+
+To remove a cpuset, just use rmdir::
+
+ # rmdir my_sub_cs
-To remove a cpuset, just use rmdir:
-# rmdir my_sub_cs
This will fail if the cpuset is in use (has cpusets inside, or has
processes attached).
Note that for legacy reasons, the "cpuset" filesystem exists as a
wrapper around the cgroup filesystem.
-The command
+The command::
-mount -t cpuset X /sys/fs/cgroup/cpuset
+ mount -t cpuset X /sys/fs/cgroup/cpuset
-is equivalent to
+is equivalent to::
-mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset
-echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent
+ mount -t cgroup -ocpuset,noprefix X /sys/fs/cgroup/cpuset
+ echo "/sbin/cpuset_release_agent" > /sys/fs/cgroup/cpuset/release_agent
2.2 Adding/removing cpus
------------------------
This is the syntax to use when writing in the cpus or mems files
-in cpuset directories:
+in cpuset directories::
-# /bin/echo 1-4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4
+ # /bin/echo 1-4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4
+ # /bin/echo 1,2,3,4 > cpuset.cpus -> set cpus list to cpus 1,2,3,4
To add a CPU to a cpuset, write the new list of CPUs including the
-CPU to be added. To add 6 to the above cpuset:
+CPU to be added. To add 6 to the above cpuset::
-# /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6
+ # /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6
Similarly to remove a CPU from a cpuset, write the new list of CPUs
without the CPU to be removed.
-To remove all the CPUs:
+To remove all the CPUs::
-# /bin/echo "" > cpuset.cpus -> clear cpus list
+ # /bin/echo "" > cpuset.cpus -> clear cpus list
2.3 Setting flags
-----------------
-The syntax is very simple:
+The syntax is very simple::
-# /bin/echo 1 > cpuset.cpu_exclusive -> set flag 'cpuset.cpu_exclusive'
-# /bin/echo 0 > cpuset.cpu_exclusive -> unset flag 'cpuset.cpu_exclusive'
+ # /bin/echo 1 > cpuset.cpu_exclusive -> set flag 'cpuset.cpu_exclusive'
+ # /bin/echo 0 > cpuset.cpu_exclusive -> unset flag 'cpuset.cpu_exclusive'
2.4 Attaching processes
-----------------------
-# /bin/echo PID > tasks
+::
+
+ # /bin/echo PID > tasks
Note that it is PID, not PIDs. You can only attach ONE task at a time.
-If you have several tasks to attach, you have to do it one after another:
+If you have several tasks to attach, you have to do it one after another::
-# /bin/echo PID1 > tasks
-# /bin/echo PID2 > tasks
+ # /bin/echo PID1 > tasks
+ # /bin/echo PID2 > tasks
...
-# /bin/echo PIDn > tasks
+ # /bin/echo PIDn > tasks
3. Questions
============
-Q: what's up with this '/bin/echo' ?
-A: bash's builtin 'echo' command does not check calls to write() against
+Q:
+ what's up with this '/bin/echo' ?
+
+A:
+ bash's builtin 'echo' command does not check calls to write() against
errors. If you use it in the cpuset file system, you won't be
able to tell whether a command succeeded or failed.
-Q: When I attach processes, only the first of the line gets really attached !
-A: We can only return one error code per call to write(). So you should also
+Q:
+ When I attach processes, only the first of the line gets really attached !
+
+A:
+ We can only return one error code per call to write(). So you should also
put only ONE pid.
4. Contact
diff --git a/Documentation/cgroup-v1/devices.txt b/Documentation/cgroup-v1/devices.rst
index 3c1095ca02ea..e1886783961e 100644
--- a/Documentation/cgroup-v1/devices.txt
+++ b/Documentation/cgroup-v1/devices.rst
@@ -1,6 +1,9 @@
+===========================
Device Whitelist Controller
+===========================
-1. Description:
+1. Description
+==============
Implement a cgroup to track and enforce open and mknod restrictions
on device files. A device cgroup associates a device access
@@ -16,24 +19,26 @@ devices from the whitelist or add new entries. A child cgroup can
never receive a device access which is denied by its parent.
2. User Interface
+=================
An entry is added using devices.allow, and removed using
-devices.deny. For instance
+devices.deny. For instance::
echo 'c 1:3 mr' > /sys/fs/cgroup/1/devices.allow
allows cgroup 1 to read and mknod the device usually known as
-/dev/null. Doing
+/dev/null. Doing::
echo a > /sys/fs/cgroup/1/devices.deny
-will remove the default 'a *:* rwm' entry. Doing
+will remove the default 'a *:* rwm' entry. Doing::
echo a > /sys/fs/cgroup/1/devices.allow
will add the 'a *:* rwm' entry to the whitelist.
3. Security
+===========
Any task can move itself between cgroups. This clearly won't
suffice, but we can decide the best way to adequately restrict
@@ -50,6 +55,7 @@ A cgroup may not be granted more permissions than the cgroup's
parent has.
4. Hierarchy
+============
device cgroups maintain hierarchy by making sure a cgroup never has more
access permissions than its parent. Every time an entry is written to
@@ -58,7 +64,8 @@ from their whitelist and all the locally set whitelist entries will be
re-evaluated. In case one of the locally set whitelist entries would provide
more access than the cgroup's parent, it'll be removed from the whitelist.
-Example:
+Example::
+
A
/ \
B
@@ -67,10 +74,12 @@ Example:
A allow "b 8:* rwm", "c 116:1 rw"
B deny "c 1:3 rwm", "c 116:2 rwm", "b 3:* rwm"
-If a device is denied in group A:
+If a device is denied in group A::
+
# echo "c 116:* r" > A/devices.deny
+
it'll propagate down and after revalidating B's entries, the whitelist entry
-"c 116:2 rwm" will be removed:
+"c 116:2 rwm" will be removed::
group whitelist entries denied devices
A all "b 8:* rwm", "c 116:* rw"
@@ -79,7 +88,8 @@ it'll propagate down and after revalidating B's entries, the whitelist entry
In case parent's exceptions change and local exceptions are not allowed
anymore, they'll be deleted.
-Notice that new whitelist entries will not be propagated:
+Notice that new whitelist entries will not be propagated::
+
A
/ \
B
@@ -88,24 +98,30 @@ Notice that new whitelist entries will not be propagated:
A "c 1:3 rwm", "c 1:5 r" all the rest
B "c 1:3 rwm", "c 1:5 r" all the rest
-when adding "c *:3 rwm":
+when adding ``c *:3 rwm``::
+
# echo "c *:3 rwm" >A/devices.allow
-the result:
+the result::
+
group whitelist entries denied devices
A "c *:3 rwm", "c 1:5 r" all the rest
B "c 1:3 rwm", "c 1:5 r" all the rest
-but now it'll be possible to add new entries to B:
+but now it'll be possible to add new entries to B::
+
# echo "c 2:3 rwm" >B/devices.allow
# echo "c 50:3 r" >B/devices.allow
-or even
+
+or even::
+
# echo "c *:3 rwm" >B/devices.allow
Allowing or denying all by writing 'a' to devices.allow or devices.deny will
not be possible once the device cgroups has children.
4.1 Hierarchy (internal implementation)
+---------------------------------------
device cgroups is implemented internally using a behavior (ALLOW, DENY) and a
list of exceptions. The internal state is controlled using the same user
diff --git a/Documentation/cgroup-v1/freezer-subsystem.txt b/Documentation/cgroup-v1/freezer-subsystem.rst
index e831cb2b8394..582d3427de3f 100644
--- a/Documentation/cgroup-v1/freezer-subsystem.txt
+++ b/Documentation/cgroup-v1/freezer-subsystem.rst
@@ -1,3 +1,7 @@
+==============
+Cgroup Freezer
+==============
+
The cgroup freezer is useful to batch job management system which start
and stop sets of tasks in order to schedule the resources of a machine
according to the desires of a system administrator. This sort of program
@@ -23,7 +27,7 @@ blocked, or ignored it can be seen by waiting or ptracing parent tasks.
SIGCONT is especially unsuitable since it can be caught by the task. Any
programs designed to watch for SIGSTOP and SIGCONT could be broken by
attempting to use SIGSTOP and SIGCONT to stop and resume tasks. We can
-demonstrate this problem using nested bash shells:
+demonstrate this problem using nested bash shells::
$ echo $$
16644
@@ -93,19 +97,19 @@ The following cgroupfs files are created by cgroup freezer.
The root cgroup is non-freezable and the above interface files don't
exist.
-* Examples of usage :
+* Examples of usage::
# mkdir /sys/fs/cgroup/freezer
# mount -t cgroup -ofreezer freezer /sys/fs/cgroup/freezer
# mkdir /sys/fs/cgroup/freezer/0
# echo $some_pid > /sys/fs/cgroup/freezer/0/tasks
-to get status of the freezer subsystem :
+to get status of the freezer subsystem::
# cat /sys/fs/cgroup/freezer/0/freezer.state
THAWED
-to freeze all tasks in the container :
+to freeze all tasks in the container::
# echo FROZEN > /sys/fs/cgroup/freezer/0/freezer.state
# cat /sys/fs/cgroup/freezer/0/freezer.state
@@ -113,7 +117,7 @@ to freeze all tasks in the container :
# cat /sys/fs/cgroup/freezer/0/freezer.state
FROZEN
-to unfreeze all tasks in the container :
+to unfreeze all tasks in the container::
# echo THAWED > /sys/fs/cgroup/freezer/0/freezer.state
# cat /sys/fs/cgroup/freezer/0/freezer.state
diff --git a/Documentation/cgroup-v1/hugetlb.txt b/Documentation/cgroup-v1/hugetlb.rst
index 1260e5369b9b..a3902aa253a9 100644
--- a/Documentation/cgroup-v1/hugetlb.txt
+++ b/Documentation/cgroup-v1/hugetlb.rst
@@ -1,5 +1,6 @@
+==================
HugeTLB Controller
--------------------
+==================
The HugeTLB controller allows to limit the HugeTLB usage per control group and
enforces the controller limit during page fault. Since HugeTLB doesn't
@@ -16,16 +17,16 @@ With the above step, the initial or the parent HugeTLB group becomes
visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
-New groups can be created under the parent group /sys/fs/cgroup.
+New groups can be created under the parent group /sys/fs/cgroup::
-# cd /sys/fs/cgroup
-# mkdir g1
-# echo $$ > g1/tasks
+ # cd /sys/fs/cgroup
+ # mkdir g1
+ # echo $$ > g1/tasks
The above steps create a new group g1 and move the current shell
process (bash) into it.
-Brief summary of control files
+Brief summary of control files::
hugetlb.<hugepagesize>.limit_in_bytes # set/show limit of "hugepagesize" hugetlb usage
hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded
@@ -33,17 +34,17 @@ Brief summary of control files
hugetlb.<hugepagesize>.failcnt # show the number of allocation failure due to HugeTLB limit
For a system supporting three hugepage sizes (64k, 32M and 1G), the control
-files include:
-
-hugetlb.1GB.limit_in_bytes
-hugetlb.1GB.max_usage_in_bytes
-hugetlb.1GB.usage_in_bytes
-hugetlb.1GB.failcnt
-hugetlb.64KB.limit_in_bytes
-hugetlb.64KB.max_usage_in_bytes
-hugetlb.64KB.usage_in_bytes
-hugetlb.64KB.failcnt
-hugetlb.32MB.limit_in_bytes
-hugetlb.32MB.max_usage_in_bytes
-hugetlb.32MB.usage_in_bytes
-hugetlb.32MB.failcnt
+files include::
+
+ hugetlb.1GB.limit_in_bytes
+ hugetlb.1GB.max_usage_in_bytes
+ hugetlb.1GB.usage_in_bytes
+ hugetlb.1GB.failcnt
+ hugetlb.64KB.limit_in_bytes
+ hugetlb.64KB.max_usage_in_bytes
+ hugetlb.64KB.usage_in_bytes
+ hugetlb.64KB.failcnt
+ hugetlb.32MB.limit_in_bytes
+ hugetlb.32MB.max_usage_in_bytes
+ hugetlb.32MB.usage_in_bytes
+ hugetlb.32MB.failcnt
diff --git a/Documentation/cgroup-v1/index.rst b/Documentation/cgroup-v1/index.rst
new file mode 100644
index 000000000000..fe76d42edc11
--- /dev/null
+++ b/Documentation/cgroup-v1/index.rst
@@ -0,0 +1,30 @@
+:orphan:
+
+========================
+Control Groups version 1
+========================
+
+.. toctree::
+ :maxdepth: 1
+
+ cgroups
+
+ blkio-controller
+ cpuacct
+ cpusets
+ devices
+ freezer-subsystem
+ hugetlb
+ memcg_test
+ memory
+ net_cls
+ net_prio
+ pids
+ rdma
+
+.. only:: subproject and html
+
+ Indices
+ =======
+
+ * :ref:`genindex`
diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.rst
index 621e29ffb358..91bd18c6a514 100644
--- a/Documentation/cgroup-v1/memcg_test.txt
+++ b/Documentation/cgroup-v1/memcg_test.rst
@@ -1,32 +1,43 @@
-Memory Resource Controller(Memcg) Implementation Memo.
+=====================================================
+Memory Resource Controller(Memcg) Implementation Memo
+=====================================================
+
Last Updated: 2010/2
+
Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
Because VM is getting complex (one of reasons is memcg...), memcg's behavior
is complex. This is a document for memcg's internal behavior.
Please note that implementation details can be changed.
-(*) Topics on API should be in Documentation/cgroup-v1/memory.txt)
+(*) Topics on API should be in Documentation/cgroup-v1/memory.rst)
0. How to record usage ?
+========================
+
2 objects are used.
page_cgroup ....an object per page.
+
Allocated at boot or memory hotplug. Freed at memory hot removal.
swap_cgroup ... an entry per swp_entry.
+
Allocated at swapon(). Freed at swapoff().
The page_cgroup has USED bit and double count against a page_cgroup never
occurs. swap_cgroup is used only when a charged page is swapped-out.
1. Charge
+=========
a page/swp_entry may be charged (usage += PAGE_SIZE) at
mem_cgroup_try_charge()
2. Uncharge
+===========
+
a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
mem_cgroup_uncharge()
@@ -37,9 +48,12 @@ Please note that implementation details can be changed.
disappears.
3. charge-commit-cancel
+=======================
+
Memcg pages are charged in two steps:
- mem_cgroup_try_charge()
- mem_cgroup_commit_charge() or mem_cgroup_cancel_charge()
+
+ - mem_cgroup_try_charge()
+ - mem_cgroup_commit_charge() or mem_cgroup_cancel_charge()
At try_charge(), there are no flags to say "this page is charged".
at this point, usage += PAGE_SIZE.
@@ -51,6 +65,8 @@ Please note that implementation details can be changed.
Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
4. Anonymous
+============
+
Anonymous page is newly allocated at
- page fault into MAP_ANONYMOUS mapping.
- Copy-On-Write.
@@ -78,34 +94,45 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
5. Page Cache
- Page Cache is charged at
+=============
+
+ Page Cache is charged at
- add_to_page_cache_locked().
The logic is very clear. (About migration, see below)
- Note: __remove_from_page_cache() is called by remove_from_page_cache()
- and __remove_mapping().
+
+ Note:
+ __remove_from_page_cache() is called by remove_from_page_cache()
+ and __remove_mapping().
6. Shmem(tmpfs) Page Cache
+===========================
+
The best way to understand shmem's page state transition is to read
mm/shmem.c.
+
But brief explanation of the behavior of memcg around shmem will be
helpful to understand the logic.
Shmem's page (just leaf page, not direct/indirect block) can be on
+
- radix-tree of shmem's inode.
- SwapCache.
- Both on radix-tree and SwapCache. This happens at swap-in
and swap-out,
It's charged when...
+
- A new page is added to shmem's radix-tree.
- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
7. Page Migration
+=================
mem_cgroup_migrate()
8. LRU
+======
Each memcg has its own private LRU. Now, its handling is under global
VM's control (means that it's handled under global pgdat->lru_lock).
Almost all routines around memcg's LRU is called by global LRU's
@@ -114,163 +141,211 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
A special function is mem_cgroup_isolate_pages(). This scans
memcg's private LRU and call __isolate_lru_page() to extract a page
from LRU.
+
(By __isolate_lru_page(), the page is removed from both of global and
- private LRU.)
+ private LRU.)
9. Typical Tests.
+=================
Tests for racy cases.
- 9.1 Small limit to memcg.
+9.1 Small limit to memcg.
+-------------------------
+
When you do test to do racy case, it's good test to set memcg's limit
to be very small rather than GB. Many races found in the test under
xKB or xxMB limits.
+
(Memory behavior under GB and Memory behavior under MB shows very
- different situation.)
+ different situation.)
+
+9.2 Shmem
+---------
- 9.2 Shmem
Historically, memcg's shmem handling was poor and we saw some amount
of troubles here. This is because shmem is page-cache but can be
SwapCache. Test with shmem/tmpfs is always good test.
- 9.3 Migration
+9.3 Migration
+-------------
+
For NUMA, migration is an another special case. To do easy test, cpuset
- is useful. Following is a sample script to do migration.
+ is useful. Following is a sample script to do migration::
- mount -t cgroup -o cpuset none /opt/cpuset
+ mount -t cgroup -o cpuset none /opt/cpuset
- mkdir /opt/cpuset/01
- echo 1 > /opt/cpuset/01/cpuset.cpus
- echo 0 > /opt/cpuset/01/cpuset.mems
- echo 1 > /opt/cpuset/01/cpuset.memory_migrate
- mkdir /opt/cpuset/02
- echo 1 > /opt/cpuset/02/cpuset.cpus
- echo 1 > /opt/cpuset/02/cpuset.mems
- echo 1 > /opt/cpuset/02/cpuset.memory_migrate
+ mkdir /opt/cpuset/01
+ echo 1 > /opt/cpuset/01/cpuset.cpus
+ echo 0 > /opt/cpuset/01/cpuset.mems
+ echo 1 > /opt/cpuset/01/cpuset.memory_migrate
+ mkdir /opt/cpuset/02
+ echo 1 > /opt/cpuset/02/cpuset.cpus
+ echo 1 > /opt/cpuset/02/cpuset.mems
+ echo 1 > /opt/cpuset/02/cpuset.memory_migrate
In above set, when you moves a task from 01 to 02, page migration to
node 0 to node 1 will occur. Following is a script to migrate all
- under cpuset.
- --
- move_task()
- {
- for pid in $1
- do
- /bin/echo $pid >$2/tasks 2>/dev/null
- echo -n $pid
- echo -n " "
- done
- echo END
- }
-
- G1_TASK=`cat ${G1}/tasks`
- G2_TASK=`cat ${G2}/tasks`
- move_task "${G1_TASK}" ${G2} &
- --
- 9.4 Memory hotplug.
+ under cpuset.::
+
+ --
+ move_task()
+ {
+ for pid in $1
+ do
+ /bin/echo $pid >$2/tasks 2>/dev/null
+ echo -n $pid
+ echo -n " "
+ done
+ echo END
+ }
+
+ G1_TASK=`cat ${G1}/tasks`
+ G2_TASK=`cat ${G2}/tasks`
+ move_task "${G1_TASK}" ${G2} &
+ --
+
+9.4 Memory hotplug
+------------------
+
memory hotplug test is one of good test.
- to offline memory, do following.
- # echo offline > /sys/devices/system/memory/memoryXXX/state
+
+ to offline memory, do following::
+
+ # echo offline > /sys/devices/system/memory/memoryXXX/state
+
(XXX is the place of memory)
+
This is an easy way to test page migration, too.
- 9.5 mkdir/rmdir
+9.5 mkdir/rmdir
+---------------
+
When using hierarchy, mkdir/rmdir test should be done.
- Use tests like the following.
+ Use tests like the following::
+
+ echo 1 >/opt/cgroup/01/memory/use_hierarchy
+ mkdir /opt/cgroup/01/child_a
+ mkdir /opt/cgroup/01/child_b
- echo 1 >/opt/cgroup/01/memory/use_hierarchy
- mkdir /opt/cgroup/01/child_a
- mkdir /opt/cgroup/01/child_b
+ set limit to 01.
+ add limit to 01/child_b
+ run jobs under child_a and child_b
- set limit to 01.
- add limit to 01/child_b
- run jobs under child_a and child_b
+ create/delete following groups at random while jobs are running::
- create/delete following groups at random while jobs are running.
- /opt/cgroup/01/child_a/child_aa
- /opt/cgroup/01/child_b/child_bb
- /opt/cgroup/01/child_c
+ /opt/cgroup/01/child_a/child_aa
+ /opt/cgroup/01/child_b/child_bb
+ /opt/cgroup/01/child_c
running new jobs in new group is also good.
- 9.6 Mount with other subsystems.
+9.6 Mount with other subsystems
+-------------------------------
+
Mounting with other subsystems is a good test because there is a
race and lock dependency with other cgroup subsystems.
- example)
- # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
+ example::
+
+ # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
and do task move, mkdir, rmdir etc...under this.
- 9.7 swapoff.
+9.7 swapoff
+-----------
+
Besides management of swap is one of complicated parts of memcg,
call path of swap-in at swapoff is not same as usual swap-in path..
It's worth to be tested explicitly.
- For example, test like following is good.
- (Shell-A)
- # mount -t cgroup none /cgroup -o memory
- # mkdir /cgroup/test
- # echo 40M > /cgroup/test/memory.limit_in_bytes
- # echo 0 > /cgroup/test/tasks
+ For example, test like following is good:
+
+ (Shell-A)::
+
+ # mount -t cgroup none /cgroup -o memory
+ # mkdir /cgroup/test
+ # echo 40M > /cgroup/test/memory.limit_in_bytes
+ # echo 0 > /cgroup/test/tasks
+
Run malloc(100M) program under this. You'll see 60M of swaps.
- (Shell-B)
- # move all tasks in /cgroup/test to /cgroup
- # /sbin/swapoff -a
- # rmdir /cgroup/test
- # kill malloc task.
+
+ (Shell-B)::
+
+ # move all tasks in /cgroup/test to /cgroup
+ # /sbin/swapoff -a
+ # rmdir /cgroup/test
+ # kill malloc task.
Of course, tmpfs v.s. swapoff test should be tested, too.
- 9.8 OOM-Killer
+9.8 OOM-Killer
+--------------
+
Out-of-memory caused by memcg's limit will kill tasks under
the memcg. When hierarchy is used, a task under hierarchy
will be killed by the kernel.
+
In this case, panic_on_oom shouldn't be invoked and tasks
in other groups shouldn't be killed.
It's not difficult to cause OOM under memcg as following.
- Case A) when you can swapoff
- #swapoff -a
- #echo 50M > /memory.limit_in_bytes
+
+ Case A) when you can swapoff::
+
+ #swapoff -a
+ #echo 50M > /memory.limit_in_bytes
+
run 51M of malloc
- Case B) when you use mem+swap limitation.
- #echo 50M > memory.limit_in_bytes
- #echo 50M > memory.memsw.limit_in_bytes
+ Case B) when you use mem+swap limitation::
+
+ #echo 50M > memory.limit_in_bytes
+ #echo 50M > memory.memsw.limit_in_bytes
+
run 51M of malloc
- 9.9 Move charges at task migration
+9.9 Move charges at task migration
+----------------------------------
+
Charges associated with a task can be moved along with task migration.
- (Shell-A)
- #mkdir /cgroup/A
- #echo $$ >/cgroup/A/tasks
+ (Shell-A)::
+
+ #mkdir /cgroup/A
+ #echo $$ >/cgroup/A/tasks
+
run some programs which uses some amount of memory in /cgroup/A.
- (Shell-B)
- #mkdir /cgroup/B
- #echo 1 >/cgroup/B/memory.move_charge_at_immigrate
- #echo "pid of the program running in group A" >/cgroup/B/tasks
+ (Shell-B)::
+
+ #mkdir /cgroup/B
+ #echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+ #echo "pid of the program running in group A" >/cgroup/B/tasks
- You can see charges have been moved by reading *.usage_in_bytes or
+ You can see charges have been moved by reading ``*.usage_in_bytes`` or
memory.stat of both A and B.
- See 8.2 of Documentation/cgroup-v1/memory.txt to see what value should be
- written to move_charge_at_immigrate.
- 9.10 Memory thresholds
+ See 8.2 of Documentation/cgroup-v1/memory.rst to see what value should
+ be written to move_charge_at_immigrate.
+
+9.10 Memory thresholds
+----------------------
+
Memory controller implements memory thresholds using cgroups notification
API. You can use tools/cgroup/cgroup_event_listener.c to test it.
- (Shell-A) Create cgroup and run event listener
- # mkdir /cgroup/A
- # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+ (Shell-A) Create cgroup and run event listener::
+
+ # mkdir /cgroup/A
+ # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+
+ (Shell-B) Add task to cgroup and try to allocate and free memory::
- (Shell-B) Add task to cgroup and try to allocate and free memory
- # echo $$ >/cgroup/A/tasks
- # a="$(dd if=/dev/zero bs=1M count=10)"
- # a=
+ # echo $$ >/cgroup/A/tasks
+ # a="$(dd if=/dev/zero bs=1M count=10)"
+ # a=
You will see message from cgroup_event_listener every time you cross
the thresholds.
diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.rst
index a33cedf85427..41bdc038dad9 100644
--- a/Documentation/cgroup-v1/memory.txt
+++ b/Documentation/cgroup-v1/memory.rst
@@ -1,22 +1,26 @@
+==========================
Memory Resource Controller
+==========================
-NOTE: This document is hopelessly outdated and it asks for a complete
+NOTE:
+ This document is hopelessly outdated and it asks for a complete
rewrite. It still contains a useful information so we are keeping it
here but make sure to check the current code if you need a deeper
understanding.
-NOTE: The Memory Resource Controller has generically been referred to as the
+NOTE:
+ The Memory Resource Controller has generically been referred to as the
memory controller in this document. Do not confuse memory controller
used here with the memory controller that is used in hardware.
-(For editors)
-In this document:
+(For editors) In this document:
When we mention a cgroup (cgroupfs's directory) with memory controller,
we call it "memory cgroup". When you see git-log and source code, you'll
see patch's title and function names tend to use "memcg".
In this document, we avoid using it.
Benefits and Purpose of the memory controller
+=============================================
The memory controller isolates the memory behaviour of a group of tasks
from the rest of the system. The article on LWN [12] mentions some probable
@@ -38,6 +42,7 @@ e. There are several other use cases; find one or use the controller just
Current Status: linux-2.6.34-mmotm(development version of 2010/April)
Features:
+
- accounting anonymous pages, file caches, swap caches usage and limiting them.
- pages are linked to per-memcg LRU exclusively, and there is no global LRU.
- optionally, memory+swap usage can be accounted and limited.
@@ -54,41 +59,48 @@ Features:
Brief summary of control files.
- tasks # attach a task(thread) and show list of threads
- cgroup.procs # show list of processes
- cgroup.event_control # an interface for event_fd()
- memory.usage_in_bytes # show current usage for memory
- (See 5.5 for details)
- memory.memsw.usage_in_bytes # show current usage for memory+Swap
- (See 5.5 for details)
- memory.limit_in_bytes # set/show limit of memory usage
- memory.memsw.limit_in_bytes # set/show limit of memory+Swap usage
- memory.failcnt # show the number of memory usage hits limits
- memory.memsw.failcnt # show the number of memory+Swap hits limits
- memory.max_usage_in_bytes # show max memory usage recorded
- memory.memsw.max_usage_in_bytes # show max memory+Swap usage recorded
- memory.soft_limit_in_bytes # set/show soft limit of memory usage
- memory.stat # show various statistics
- memory.use_hierarchy # set/show hierarchical account enabled
- memory.force_empty # trigger forced page reclaim
- memory.pressure_level # set memory pressure notifications
- memory.swappiness # set/show swappiness parameter of vmscan
- (See sysctl's vm.swappiness)
- memory.move_charge_at_immigrate # set/show controls of moving charges
- memory.oom_control # set/show oom controls.
- memory.numa_stat # show the number of memory usage per numa node
-
- memory.kmem.limit_in_bytes # set/show hard limit for kernel memory
- memory.kmem.usage_in_bytes # show current kernel memory allocation
- memory.kmem.failcnt # show the number of kernel memory usage hits limits
- memory.kmem.max_usage_in_bytes # show max kernel memory usage recorded
-
- memory.kmem.tcp.limit_in_bytes # set/show hard limit for tcp buf memory
- memory.kmem.tcp.usage_in_bytes # show current tcp buf memory allocation
- memory.kmem.tcp.failcnt # show the number of tcp buf memory usage hits limits
- memory.kmem.tcp.max_usage_in_bytes # show max tcp buf memory usage recorded
+==================================== ==========================================
+ tasks attach a task(thread) and show list of
+ threads
+ cgroup.procs show list of processes
+ cgroup.event_control an interface for event_fd()
+ memory.usage_in_bytes show current usage for memory
+ (See 5.5 for details)
+ memory.memsw.usage_in_bytes show current usage for memory+Swap
+ (See 5.5 for details)
+ memory.limit_in_bytes set/show limit of memory usage
+ memory.memsw.limit_in_bytes set/show limit of memory+Swap usage
+ memory.failcnt show the number of memory usage hits limits
+ memory.memsw.failcnt show the number of memory+Swap hits limits
+ memory.max_usage_in_bytes show max memory usage recorded
+ memory.memsw.max_usage_in_bytes show max memory+Swap usage recorded
+ memory.soft_limit_in_bytes set/show soft limit of memory usage
+ memory.stat show various statistics
+ memory.use_hierarchy set/show hierarchical account enabled
+ memory.force_empty trigger forced page reclaim
+ memory.pressure_level set memory pressure notifications
+ memory.swappiness set/show swappiness parameter of vmscan
+ (See sysctl's vm.swappiness)
+ memory.move_charge_at_immigrate set/show controls of moving charges
+ memory.oom_control set/show oom controls.
+ memory.numa_stat show the number of memory usage per numa
+ node
+
+ memory.kmem.limit_in_bytes set/show hard limit for kernel memory
+ memory.kmem.usage_in_bytes show current kernel memory allocation
+ memory.kmem.failcnt show the number of kernel memory usage
+ hits limits
+ memory.kmem.max_usage_in_bytes show max kernel memory usage recorded
+
+ memory.kmem.tcp.limit_in_bytes set/show hard limit for tcp buf memory
+ memory.kmem.tcp.usage_in_bytes show current tcp buf memory allocation
+ memory.kmem.tcp.failcnt show the number of tcp buf memory usage
+ hits limits
+ memory.kmem.tcp.max_usage_in_bytes show max tcp buf memory usage recorded
+==================================== ==========================================
1. History
+==========
The memory controller has a long history. A request for comments for the memory
controller was posted by Balbir Singh [1]. At the time the RFC was posted
@@ -103,6 +115,7 @@ at version 6; it combines both mapped (RSS) and unmapped Page
Cache Control [11].
2. Memory Control
+=================
Memory is a unique resource in the sense that it is present in a limited
amount. If a task requires a lot of CPU processing, the task can spread
@@ -120,6 +133,7 @@ are:
The memory controller is the first controller developed.
2.1. Design
+-----------
The core of the design is a counter called the page_counter. The
page_counter tracks the current memory usage and limit of the group of
@@ -127,6 +141,9 @@ processes associated with the controller. Each cgroup has a memory controller
specific data structure (mem_cgroup) associated with it.
2.2. Accounting
+---------------
+
+::
+--------------------+
| mem_cgroup |
@@ -165,6 +182,7 @@ updated. page_cgroup has its own LRU on cgroup.
(*) page_cgroup structure is allocated at boot/memory-hotplug time.
2.2.1 Accounting details
+------------------------
All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
Some pages which are never reclaimable and will not be on the LRU
@@ -191,6 +209,7 @@ Note: we just account pages-on-LRU because our purpose is to control amount
of used pages; not-on-LRU pages tend to be out-of-control from VM view.
2.3 Shared Page Accounting
+--------------------------
Shared pages are accounted on the basis of the first touch approach. The
cgroup that first touches a page is accounted for the page. The principle
@@ -207,11 +226,13 @@ be backed into memory in force, charges for pages are accounted against the
caller of swapoff rather than the users of shmem.
2.4 Swap Extension (CONFIG_MEMCG_SWAP)
+--------------------------------------
Swap Extension allows you to record charge for swap. A swapped-in page is
charged back to original page allocator if possible.
When swap is accounted, following files are added.
+
- memory.memsw.usage_in_bytes.
- memory.memsw.limit_in_bytes.
@@ -224,14 +245,16 @@ In this case, setting memsw.limit_in_bytes=3G will prevent bad use of swap.
By using the memsw limit, you can avoid system OOM which can be caused by swap
shortage.
-* why 'memory+swap' rather than swap.
+**why 'memory+swap' rather than swap**
+
The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
to move account from memory to swap...there is no change in usage of
memory+swap. In other words, when we want to limit the usage of swap without
affecting global LRU, memory+swap limit is better than just limiting swap from
an OS point of view.
-* What happens when a cgroup hits memory.memsw.limit_in_bytes
+**What happens when a cgroup hits memory.memsw.limit_in_bytes**
+
When a cgroup hits memory.memsw.limit_in_bytes, it's useless to do swap-out
in this cgroup. Then, swap-out will not be done by cgroup routine and file
caches are dropped. But as mentioned above, global LRU can do swapout memory
@@ -239,6 +262,7 @@ from it for sanity of the system's memory management state. You can't forbid
it by cgroup.
2.5 Reclaim
+-----------
Each cgroup maintains a per cgroup LRU which has the same structure as
global VM. When a cgroup goes over its limit, we first try
@@ -251,29 +275,36 @@ The reclaim algorithm has not been modified for cgroups, except that
pages that are selected for reclaiming come from the per-cgroup LRU
list.
-NOTE: Reclaim does not work for the root cgroup, since we cannot set any
-limits on the root cgroup.
+NOTE:
+ Reclaim does not work for the root cgroup, since we cannot set any
+ limits on the root cgroup.
-Note2: When panic_on_oom is set to "2", the whole system will panic.
+Note2:
+ When panic_on_oom is set to "2", the whole system will panic.
When oom event notifier is registered, event will be delivered.
(See oom_control section)
2.6 Locking
+-----------
lock_page_cgroup()/unlock_page_cgroup() should not be called under
the i_pages lock.
Other lock order is following:
+
PG_locked.
- mm->page_table_lock
- pgdat->lru_lock
- lock_page_cgroup.
+ mm->page_table_lock
+ pgdat->lru_lock
+ lock_page_cgroup.
+
In many cases, just lock_page_cgroup() is called.
+
per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
pgdat->lru_lock, it has no lock of its own.
2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
+-----------------------------------------------
With the Kernel memory extension, the Memory Controller is able to limit
the amount of kernel memory used by the system. Kernel memory is fundamentally
@@ -288,6 +319,7 @@ Kernel memory limits are not imposed for the root cgroup. Usage for the root
cgroup may or may not be accounted. The memory used is accumulated into
memory.kmem.usage_in_bytes, or in a separate counter when it makes sense.
(currently only for tcp).
+
The main "kmem" counter is fed into the main counter, so kmem charges will
also be visible from the user counter.
@@ -295,36 +327,42 @@ Currently no soft limit is implemented for kernel memory. It is future work
to trigger slab reclaim when those limits are reached.
2.7.1 Current Kernel Memory resources accounted
+-----------------------------------------------
-* stack pages: every process consumes some stack pages. By accounting into
-kernel memory, we prevent new processes from being created when the kernel
-memory usage is too high.
+stack pages:
+ every process consumes some stack pages. By accounting into
+ kernel memory, we prevent new processes from being created when the kernel
+ memory usage is too high.
-* slab pages: pages allocated by the SLAB or SLUB allocator are tracked. A copy
-of each kmem_cache is created every time the cache is touched by the first time
-from inside the memcg. The creation is done lazily, so some objects can still be
-skipped while the cache is being created. All objects in a slab page should
-belong to the same memcg. This only fails to hold when a task is migrated to a
-different memcg during the page allocation by the cache.
+slab pages:
+ pages allocated by the SLAB or SLUB allocator are tracked. A copy
+ of each kmem_cache is created every time the cache is touched by the first time
+ from inside the memcg. The creation is done lazily, so some objects can still be
+ skipped while the cache is being created. All objects in a slab page should
+ belong to the same memcg. This only fails to hold when a task is migrated to a
+ different memcg during the page allocation by the cache.
-* sockets memory pressure: some sockets protocols have memory pressure
-thresholds. The Memory Controller allows them to be controlled individually
-per cgroup, instead of globally.
+sockets memory pressure:
+ some sockets protocols have memory pressure
+ thresholds. The Memory Controller allows them to be controlled individually
+ per cgroup, instead of globally.
-* tcp memory pressure: sockets memory pressure for the tcp protocol.
+tcp memory pressure:
+ sockets memory pressure for the tcp protocol.
2.7.2 Common use cases
+----------------------
Because the "kmem" counter is fed to the main user counter, kernel memory can
never be limited completely independently of user memory. Say "U" is the user
limit, and "K" the kernel limit. There are three possible ways limits can be
set:
- U != 0, K = unlimited:
+U != 0, K = unlimited:
This is the standard memcg limitation mechanism already present before kmem
accounting. Kernel memory is completely ignored.
- U != 0, K < U:
+U != 0, K < U:
Kernel memory is a subset of the user memory. This setup is useful in
deployments where the total amount of memory per-cgroup is overcommited.
Overcommiting kernel memory limits is definitely not recommended, since the
@@ -332,19 +370,23 @@ set:
In this case, the admin could set up K so that the sum of all groups is
never greater than the total memory, and freely set U at the cost of his
QoS.
- WARNING: In the current implementation, memory reclaim will NOT be
+
+WARNING:
+ In the current implementation, memory reclaim will NOT be
triggered for a cgroup when it hits K while staying below U, which makes
this setup impractical.
- U != 0, K >= U:
+U != 0, K >= U:
Since kmem charges will also be fed to the user counter and reclaim will be
triggered for the cgroup for both kinds of memory. This setup gives the
admin a unified view of memory, and it is also useful for people who just
want to track kernel memory usage.
3. User Interface
+=================
3.0. Configuration
+------------------
a. Enable CONFIG_CGROUPS
b. Enable CONFIG_MEMCG
@@ -352,39 +394,53 @@ c. Enable CONFIG_MEMCG_SWAP (to use swap extension)
d. Enable CONFIG_MEMCG_KMEM (to use kmem extension)
3.1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
-# mount -t tmpfs none /sys/fs/cgroup
-# mkdir /sys/fs/cgroup/memory
-# mount -t cgroup none /sys/fs/cgroup/memory -o memory
+-------------------------------------------------------------------
+
+::
+
+ # mount -t tmpfs none /sys/fs/cgroup
+ # mkdir /sys/fs/cgroup/memory
+ # mount -t cgroup none /sys/fs/cgroup/memory -o memory
+
+3.2. Make the new group and move bash into it::
+
+ # mkdir /sys/fs/cgroup/memory/0
+ # echo $$ > /sys/fs/cgroup/memory/0/tasks
-3.2. Make the new group and move bash into it
-# mkdir /sys/fs/cgroup/memory/0
-# echo $$ > /sys/fs/cgroup/memory/0/tasks
+Since now we're in the 0 cgroup, we can alter the memory limit::
-Since now we're in the 0 cgroup, we can alter the memory limit:
-# echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
+ # echo 4M > /sys/fs/cgroup/memory/0/memory.limit_in_bytes
-NOTE: We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
-mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes, Gibibytes.)
+NOTE:
+ We can use a suffix (k, K, m, M, g or G) to indicate values in kilo,
+ mega or gigabytes. (Here, Kilo, Mega, Giga are Kibibytes, Mebibytes,
+ Gibibytes.)
-NOTE: We can write "-1" to reset the *.limit_in_bytes(unlimited).
-NOTE: We cannot set limits on the root cgroup any more.
+NOTE:
+ We can write "-1" to reset the ``*.limit_in_bytes(unlimited)``.
-# cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
-4194304
+NOTE:
+ We cannot set limits on the root cgroup any more.
-We can check the usage:
-# cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
-1216512
+::
+
+ # cat /sys/fs/cgroup/memory/0/memory.limit_in_bytes
+ 4194304
+
+We can check the usage::
+
+ # cat /sys/fs/cgroup/memory/0/memory.usage_in_bytes
+ 1216512
A successful write to this file does not guarantee a successful setting of
this limit to the value written into the file. This can be due to a
number of factors, such as rounding up to page boundaries or the total
availability of memory on the system. The user is required to re-read
-this file after a write to guarantee the value committed by the kernel.
+this file after a write to guarantee the value committed by the kernel::
-# echo 1 > memory.limit_in_bytes
-# cat memory.limit_in_bytes
-4096
+ # echo 1 > memory.limit_in_bytes
+ # cat memory.limit_in_bytes
+ 4096
The memory.failcnt field gives the number of times that the cgroup limit was
exceeded.
@@ -393,6 +449,7 @@ The memory.stat file gives accounting information. Now, the number of
caches, RSS and Active pages/Inactive pages are shown.
4. Testing
+==========
For testing features and implementation, see memcg_test.txt.
@@ -408,6 +465,7 @@ But the above two are testing extreme situations.
Trying usual test under memory controller is always helpful.
4.1 Troubleshooting
+-------------------
Sometimes a user might find that the application under a cgroup is
terminated by the OOM killer. There are several causes for this:
@@ -422,6 +480,7 @@ To know what happens, disabling OOM_Kill as per "10. OOM Control" (below) and
seeing what happens will be helpful.
4.2 Task migration
+------------------
When a task migrates from one cgroup to another, its charge is not
carried forward by default. The pages allocated from the original cgroup still
@@ -432,6 +491,7 @@ You can move charges of a task along with task migration.
See 8. "Move charges at task migration"
4.3 Removing a cgroup
+---------------------
A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
cgroup might have some charge associated with it, even though all
@@ -448,13 +508,15 @@ will be charged as a new owner of it.
About use_hierarchy, see Section 6.
-5. Misc. interfaces.
+5. Misc. interfaces
+===================
5.1 force_empty
+---------------
memory.force_empty interface is provided to make cgroup's memory usage empty.
- When writing anything to this
+ When writing anything to this::
- # echo 0 > memory.force_empty
+ # echo 0 > memory.force_empty
the cgroup will be reclaimed and as many pages reclaimed as possible.
@@ -471,50 +533,61 @@ About use_hierarchy, see Section 6.
About use_hierarchy, see Section 6.
5.2 stat file
+-------------
memory.stat file includes following statistics
-# per-memory cgroup local status
-cache - # of bytes of page cache memory.
-rss - # of bytes of anonymous and swap cache memory (includes
+per-memory cgroup local status
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+=============== ===============================================================
+cache # of bytes of page cache memory.
+rss # of bytes of anonymous and swap cache memory (includes
transparent hugepages).
-rss_huge - # of bytes of anonymous transparent hugepages.
-mapped_file - # of bytes of mapped file (includes tmpfs/shmem)
-pgpgin - # of charging events to the memory cgroup. The charging
+rss_huge # of bytes of anonymous transparent hugepages.
+mapped_file # of bytes of mapped file (includes tmpfs/shmem)
+pgpgin # of charging events to the memory cgroup. The charging
event happens each time a page is accounted as either mapped
anon page(RSS) or cache page(Page Cache) to the cgroup.
-pgpgout - # of uncharging events to the memory cgroup. The uncharging
+pgpgout # of uncharging events to the memory cgroup. The uncharging
event happens each time a page is unaccounted from the cgroup.
-swap - # of bytes of swap usage
-dirty - # of bytes that are waiting to get written back to the disk.
-writeback - # of bytes of file/anon cache that are queued for syncing to
+swap # of bytes of swap usage
+dirty # of bytes that are waiting to get written back to the disk.
+writeback # of bytes of file/anon cache that are queued for syncing to
disk.
-inactive_anon - # of bytes of anonymous and swap cache memory on inactive
+inactive_anon # of bytes of anonymous and swap cache memory on inactive
LRU list.
-active_anon - # of bytes of anonymous and swap cache memory on active
+active_anon # of bytes of anonymous and swap cache memory on active
LRU list.
-inactive_file - # of bytes of file-backed memory on inactive LRU list.
-active_file - # of bytes of file-backed memory on active LRU list.
-unevictable - # of bytes of memory that cannot be reclaimed (mlocked etc).
-
-# status considering hierarchy (see memory.use_hierarchy settings)
-
-hierarchical_memory_limit - # of bytes of memory limit with regard to hierarchy
- under which the memory cgroup is
-hierarchical_memsw_limit - # of bytes of memory+swap limit with regard to
- hierarchy under which memory cgroup is.
-
-total_<counter> - # hierarchical version of <counter>, which in
- addition to the cgroup's own value includes the
- sum of all hierarchical children's values of
- <counter>, i.e. total_cache
-
-# The following additional stats are dependent on CONFIG_DEBUG_VM.
-
-recent_rotated_anon - VM internal parameter. (see mm/vmscan.c)
-recent_rotated_file - VM internal parameter. (see mm/vmscan.c)
-recent_scanned_anon - VM internal parameter. (see mm/vmscan.c)
-recent_scanned_file - VM internal parameter. (see mm/vmscan.c)
+inactive_file # of bytes of file-backed memory on inactive LRU list.
+active_file # of bytes of file-backed memory on active LRU list.
+unevictable # of bytes of memory that cannot be reclaimed (mlocked etc).
+=============== ===============================================================
+
+status considering hierarchy (see memory.use_hierarchy settings)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+========================= ===================================================
+hierarchical_memory_limit # of bytes of memory limit with regard to hierarchy
+ under which the memory cgroup is
+hierarchical_memsw_limit # of bytes of memory+swap limit with regard to
+ hierarchy under which memory cgroup is.
+
+total_<counter> # hierarchical version of <counter>, which in
+ addition to the cgroup's own value includes the
+ sum of all hierarchical children's values of
+ <counter>, i.e. total_cache
+========================= ===================================================
+
+The following additional stats are dependent on CONFIG_DEBUG_VM
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+========================= ========================================
+recent_rotated_anon VM internal parameter. (see mm/vmscan.c)
+recent_rotated_file VM internal parameter. (see mm/vmscan.c)
+recent_scanned_anon VM internal parameter. (see mm/vmscan.c)
+recent_scanned_file VM internal parameter. (see mm/vmscan.c)
+========================= ========================================
Memo:
recent_rotated means recent frequency of LRU rotation.
@@ -525,12 +598,15 @@ Note:
Only anonymous and swap cache memory is listed as part of 'rss' stat.
This should not be confused with the true 'resident set size' or the
amount of physical memory used by the cgroup.
+
'rss + mapped_file" will give you resident set size of cgroup.
+
(Note: file and shmem may be shared among other cgroups. In that case,
- mapped_file is accounted only when the memory cgroup is owner of page
- cache.)
+ mapped_file is accounted only when the memory cgroup is owner of page
+ cache.)
5.3 swappiness
+--------------
Overrides /proc/sys/vm/swappiness for the particular group. The tunable
in the root cgroup corresponds to the global swappiness setting.
@@ -541,16 +617,19 @@ there is a swap storage available. This might lead to memcg OOM killer
if there are no file pages to reclaim.
5.4 failcnt
+-----------
A memory cgroup provides memory.failcnt and memory.memsw.failcnt files.
This failcnt(== failure count) shows the number of times that a usage counter
hit its limit. When a memory cgroup hits a limit, failcnt increases and
memory under it will be reclaimed.
-You can reset failcnt by writing 0 to failcnt file.
-# echo 0 > .../memory.failcnt
+You can reset failcnt by writing 0 to failcnt file::
+
+ # echo 0 > .../memory.failcnt
5.5 usage_in_bytes
+------------------
For efficiency, as other kernel components, memory cgroup uses some optimization
to avoid unnecessary cacheline false sharing. usage_in_bytes is affected by the
@@ -560,6 +639,7 @@ If you want to know more exact memory usage, you should use RSS+CACHE(+SWAP)
value in memory.stat(see 5.2).
5.6 numa_stat
+-------------
This is similar to numa_maps but operates on a per-memcg basis. This is
useful for providing visibility into the numa locality information within
@@ -571,22 +651,23 @@ Each memcg's numa_stat file includes "total", "file", "anon" and "unevictable"
per-node page counts including "hierarchical_<counter>" which sums up all
hierarchical children's values in addition to the memcg's own value.
-The output format of memory.numa_stat is:
+The output format of memory.numa_stat is::
-total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
-file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
-anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
-unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
-hierarchical_<counter>=<counter pages> N0=<node 0 pages> N1=<node 1 pages> ...
+ total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
+ file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
+ anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+ unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
+ hierarchical_<counter>=<counter pages> N0=<node 0 pages> N1=<node 1 pages> ...
The "total" count is sum of file + anon + unevictable.
6. Hierarchy support
+====================
The memory controller supports a deep hierarchy and hierarchical accounting.
The hierarchy is created by creating the appropriate cgroups in the
cgroup filesystem. Consider for example, the following cgroup filesystem
-hierarchy
+hierarchy::
root
/ | \
@@ -603,24 +684,28 @@ limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
children of the ancestor.
6.1 Enabling hierarchical accounting and reclaim
+------------------------------------------------
A memory cgroup by default disables the hierarchy feature. Support
-can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
+can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup::
-# echo 1 > memory.use_hierarchy
+ # echo 1 > memory.use_hierarchy
-The feature can be disabled by
+The feature can be disabled by::
-# echo 0 > memory.use_hierarchy
+ # echo 0 > memory.use_hierarchy
-NOTE1: Enabling/disabling will fail if either the cgroup already has other
+NOTE1:
+ Enabling/disabling will fail if either the cgroup already has other
cgroups created below it, or if the parent cgroup has use_hierarchy
enabled.
-NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+NOTE2:
+ When panic_on_oom is set to "2", the whole system will panic in
case of an OOM event in any cgroup.
7. Soft limits
+==============
Soft limits allow for greater sharing of memory. The idea behind soft limits
is to allow control groups to use as much of the memory as needed, provided
@@ -640,22 +725,26 @@ hints/setup. Currently soft limit based reclaim is set up such that
it gets invoked from balance_pgdat (kswapd).
7.1 Interface
+-------------
Soft limits can be setup by using the following commands (in this example we
-assume a soft limit of 256 MiB)
+assume a soft limit of 256 MiB)::
-# echo 256M > memory.soft_limit_in_bytes
+ # echo 256M > memory.soft_limit_in_bytes
-If we want to change this to 1G, we can at any time use
+If we want to change this to 1G, we can at any time use::
-# echo 1G > memory.soft_limit_in_bytes
+ # echo 1G > memory.soft_limit_in_bytes
-NOTE1: Soft limits take effect over a long period of time, since they involve
+NOTE1:
+ Soft limits take effect over a long period of time, since they involve
reclaiming memory for balancing between memory cgroups
-NOTE2: It is recommended to set the soft limit always below the hard limit,
+NOTE2:
+ It is recommended to set the soft limit always below the hard limit,
otherwise the hard limit will take precedence.
8. Move charges at task migration
+=================================
Users can move charges associated with a task along with task migration, that
is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
@@ -663,60 +752,71 @@ This feature is not supported in !CONFIG_MMU environments because of lack of
page tables.
8.1 Interface
+-------------
This feature is disabled by default. It can be enabled (and disabled again) by
writing to memory.move_charge_at_immigrate of the destination cgroup.
-If you want to enable it:
+If you want to enable it::
-# echo (some positive value) > memory.move_charge_at_immigrate
+ # echo (some positive value) > memory.move_charge_at_immigrate
-Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+Note:
+ Each bits of move_charge_at_immigrate has its own meaning about what type
of charges should be moved. See 8.2 for details.
-Note: Charges are moved only when you move mm->owner, in other words,
+Note:
+ Charges are moved only when you move mm->owner, in other words,
a leader of a thread group.
-Note: If we cannot find enough space for the task in the destination cgroup, we
+Note:
+ If we cannot find enough space for the task in the destination cgroup, we
try to make space by reclaiming memory. Task migration may fail if we
cannot make enough space.
-Note: It can take several seconds if you move charges much.
+Note:
+ It can take several seconds if you move charges much.
-And if you want disable it again:
+And if you want disable it again::
-# echo 0 > memory.move_charge_at_immigrate
+ # echo 0 > memory.move_charge_at_immigrate
8.2 Type of charges which can be moved
+--------------------------------------
Each bit in move_charge_at_immigrate has its own meaning about what type of
charges should be moved. But in any case, it must be noted that an account of
a page or a swap can be moved only when it is charged to the task's current
(old) memory cgroup.
- bit | what type of charges would be moved ?
- -----+------------------------------------------------------------------------
- 0 | A charge of an anonymous page (or swap of it) used by the target task.
- | You must enable Swap Extension (see 2.4) to enable move of swap charges.
- -----+------------------------------------------------------------------------
- 1 | A charge of file pages (normal file, tmpfs file (e.g. ipc shared memory)
- | and swaps of tmpfs file) mmapped by the target task. Unlike the case of
- | anonymous pages, file pages (and swaps) in the range mmapped by the task
- | will be moved even if the task hasn't done page fault, i.e. they might
- | not be the task's "RSS", but other task's "RSS" that maps the same file.
- | And mapcount of the page is ignored (the page can be moved even if
- | page_mapcount(page) > 1). You must enable Swap Extension (see 2.4) to
- | enable move of swap charges.
++---+--------------------------------------------------------------------------+
+|bit| what type of charges would be moved ? |
++===+==========================================================================+
+| 0 | A charge of an anonymous page (or swap of it) used by the target task. |
+| | You must enable Swap Extension (see 2.4) to enable move of swap charges. |
++---+--------------------------------------------------------------------------+
+| 1 | A charge of file pages (normal file, tmpfs file (e.g. ipc shared memory) |
+| | and swaps of tmpfs file) mmapped by the target task. Unlike the case of |
+| | anonymous pages, file pages (and swaps) in the range mmapped by the task |
+| | will be moved even if the task hasn't done page fault, i.e. they might |
+| | not be the task's "RSS", but other task's "RSS" that maps the same file. |
+| | And mapcount of the page is ignored (the page can be moved even if |
+| | page_mapcount(page) > 1). You must enable Swap Extension (see 2.4) to |
+| | enable move of swap charges. |
++---+--------------------------------------------------------------------------+
8.3 TODO
+--------
- All of moving charge operations are done under cgroup_mutex. It's not good
behavior to hold the mutex too long, so we may need some trick.
9. Memory thresholds
+====================
Memory cgroup implements memory thresholds using the cgroups notification
API (see cgroups.txt). It allows to register multiple memory and memsw
thresholds and gets notifications when it crosses.
To register a threshold, an application must:
+
- create an eventfd using eventfd(2);
- open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
- write string like "<event_fd> <fd of memory.usage_in_bytes> <threshold>" to
@@ -728,6 +828,7 @@ threshold in any direction.
It's applicable for root and non-root cgroup.
10. OOM Control
+===============
memory.oom_control file is for OOM notification and other controls.
@@ -736,6 +837,7 @@ API (See cgroups.txt). It allows to register multiple OOM notification
delivery and gets notification when OOM happens.
To register a notifier, an application must:
+
- create an eventfd using eventfd(2)
- open memory.oom_control file
- write string like "<event_fd> <fd of memory.oom_control>" to
@@ -752,8 +854,11 @@ If OOM-killer is disabled, tasks under cgroup will hang/sleep
in memory cgroup's OOM-waitqueue when they request accountable memory.
For running them, you have to relax the memory cgroup's OOM status by
+
* enlarge limit or reduce usage.
+
To reduce usage,
+
* kill some tasks.
* move some tasks to other group with account migration.
* remove some files (on tmpfs?)
@@ -761,11 +866,14 @@ To reduce usage,
Then, stopped tasks will work again.
At reading, current status of OOM is shown.
- oom_kill_disable 0 or 1 (if 1, oom-killer is disabled)
- under_oom 0 or 1 (if 1, the memory cgroup is under OOM, tasks may
- be stopped.)
+
+ - oom_kill_disable 0 or 1
+ (if 1, oom-killer is disabled)
+ - under_oom 0 or 1
+ (if 1, the memory cgroup is under OOM, tasks may be stopped.)
11. Memory Pressure
+===================
The pressure level notifications can be used to monitor the memory
allocation cost; based on the pressure, applications can implement
@@ -840,21 +948,22 @@ Test:
Here is a small script example that makes a new cgroup, sets up a
memory limit, sets up a notification in the cgroup and then makes child
- cgroup experience a critical pressure:
+ cgroup experience a critical pressure::
- # cd /sys/fs/cgroup/memory/
- # mkdir foo
- # cd foo
- # cgroup_event_listener memory.pressure_level low,hierarchy &
- # echo 8000000 > memory.limit_in_bytes
- # echo 8000000 > memory.memsw.limit_in_bytes
- # echo $$ > tasks
- # dd if=/dev/zero | read x
+ # cd /sys/fs/cgroup/memory/
+ # mkdir foo
+ # cd foo
+ # cgroup_event_listener memory.pressure_level low,hierarchy &
+ # echo 8000000 > memory.limit_in_bytes
+ # echo 8000000 > memory.memsw.limit_in_bytes
+ # echo $$ > tasks
+ # dd if=/dev/zero | read x
(Expect a bunch of notifications, and eventually, the oom-killer will
trigger.)
12. TODO
+========
1. Make per-cgroup scanner reclaim not-shared pages first
2. Teach controller to account for shared-pages
@@ -862,11 +971,13 @@ Test:
not yet hit but the usage is getting closer
Summary
+=======
Overall, the memory controller has been a stable controller and has been
commented and discussed quite extensively in the community.
References
+==========
1. Singh, Balbir. RFC: Memory Controller, http://lwn.net/Articles/206697/
2. Singh, Balbir. Memory Controller (RSS Control),
diff --git a/Documentation/cgroup-v1/net_cls.txt b/Documentation/cgroup-v1/net_cls.rst
index ec182346dea2..a2cf272af7a0 100644
--- a/Documentation/cgroup-v1/net_cls.txt
+++ b/Documentation/cgroup-v1/net_cls.rst
@@ -1,5 +1,6 @@
+=========================
Network classifier cgroup
--------------------------
+=========================
The Network classifier cgroup provides an interface to
tag network packets with a class identifier (classid).
@@ -17,23 +18,27 @@ values is 0xAAAABBBB; AAAA is the major handle number and BBBB
is the minor handle number.
Reading net_cls.classid yields a decimal result.
-Example:
-mkdir /sys/fs/cgroup/net_cls
-mount -t cgroup -onet_cls net_cls /sys/fs/cgroup/net_cls
-mkdir /sys/fs/cgroup/net_cls/0
-echo 0x100001 > /sys/fs/cgroup/net_cls/0/net_cls.classid
- - setting a 10:1 handle.
+Example::
-cat /sys/fs/cgroup/net_cls/0/net_cls.classid
-1048577
+ mkdir /sys/fs/cgroup/net_cls
+ mount -t cgroup -onet_cls net_cls /sys/fs/cgroup/net_cls
+ mkdir /sys/fs/cgroup/net_cls/0
+ echo 0x100001 > /sys/fs/cgroup/net_cls/0/net_cls.classid
-configuring tc:
-tc qdisc add dev eth0 root handle 10: htb
+- setting a 10:1 handle::
-tc class add dev eth0 parent 10: classid 10:1 htb rate 40mbit
- - creating traffic class 10:1
+ cat /sys/fs/cgroup/net_cls/0/net_cls.classid
+ 1048577
-tc filter add dev eth0 parent 10: protocol ip prio 10 handle 1: cgroup
+- configuring tc::
-configuring iptables, basic example:
-iptables -A OUTPUT -m cgroup ! --cgroup 0x100001 -j DROP
+ tc qdisc add dev eth0 root handle 10: htb
+ tc class add dev eth0 parent 10: classid 10:1 htb rate 40mbit
+
+- creating traffic class 10:1::
+
+ tc filter add dev eth0 parent 10: protocol ip prio 10 handle 1: cgroup
+
+configuring iptables, basic example::
+
+ iptables -A OUTPUT -m cgroup ! --cgroup 0x100001 -j DROP
diff --git a/Documentation/cgroup-v1/net_prio.txt b/Documentation/cgroup-v1/net_prio.rst
index a82cbd28ea8a..b40905871c64 100644
--- a/Documentation/cgroup-v1/net_prio.txt
+++ b/Documentation/cgroup-v1/net_prio.rst
@@ -1,5 +1,6 @@
+=======================
Network priority cgroup
--------------------------
+=======================
The Network priority cgroup provides an interface to allow an administrator to
dynamically set the priority of network traffic generated by various
@@ -14,9 +15,9 @@ SO_PRIORITY socket option. This however, is not always possible because:
This cgroup allows an administrator to assign a process to a group which defines
the priority of egress traffic on a given interface. Network priority groups can
-be created by first mounting the cgroup filesystem.
+be created by first mounting the cgroup filesystem::
-# mount -t cgroup -onet_prio none /sys/fs/cgroup/net_prio
+ # mount -t cgroup -onet_prio none /sys/fs/cgroup/net_prio
With the above step, the initial group acting as the parent accounting group
becomes visible at '/sys/fs/cgroup/net_prio'. This group includes all tasks in
@@ -25,17 +26,18 @@ the system. '/sys/fs/cgroup/net_prio/tasks' lists the tasks in this cgroup.
Each net_prio cgroup contains two files that are subsystem specific
net_prio.prioidx
-This file is read-only, and is simply informative. It contains a unique integer
-value that the kernel uses as an internal representation of this cgroup.
+ This file is read-only, and is simply informative. It contains a unique
+ integer value that the kernel uses as an internal representation of this
+ cgroup.
net_prio.ifpriomap
-This file contains a map of the priorities assigned to traffic originating from
-processes in this group and egressing the system on various interfaces. It
-contains a list of tuples in the form <ifname priority>. Contents of this file
-can be modified by echoing a string into the file using the same tuple format.
-for example:
+ This file contains a map of the priorities assigned to traffic originating
+ from processes in this group and egressing the system on various interfaces.
+ It contains a list of tuples in the form <ifname priority>. Contents of this
+ file can be modified by echoing a string into the file using the same tuple
+ format. For example::
-echo "eth0 5" > /sys/fs/cgroups/net_prio/iscsi/net_prio.ifpriomap
+ echo "eth0 5" > /sys/fs/cgroups/net_prio/iscsi/net_prio.ifpriomap
This command would force any traffic originating from processes belonging to the
iscsi net_prio cgroup and egressing on interface eth0 to have the priority of
diff --git a/Documentation/cgroup-v1/pids.txt b/Documentation/cgroup-v1/pids.rst
index e105d708ccde..6acebd9e72c8 100644
--- a/Documentation/cgroup-v1/pids.txt
+++ b/Documentation/cgroup-v1/pids.rst
@@ -1,5 +1,6 @@
- Process Number Controller
- =========================
+=========================
+Process Number Controller
+=========================
Abstract
--------
@@ -34,55 +35,58 @@ pids.current tracks all child cgroup hierarchies, so parent/pids.current is a
superset of parent/child/pids.current.
The pids.events file contains event counters:
+
- max: Number of times fork failed because limit was hit.
Example
-------
-First, we mount the pids controller:
-# mkdir -p /sys/fs/cgroup/pids
-# mount -t cgroup -o pids none /sys/fs/cgroup/pids
+First, we mount the pids controller::
+
+ # mkdir -p /sys/fs/cgroup/pids
+ # mount -t cgroup -o pids none /sys/fs/cgroup/pids
+
+Then we create a hierarchy, set limits and attach processes to it::
-Then we create a hierarchy, set limits and attach processes to it:
-# mkdir -p /sys/fs/cgroup/pids/parent/child
-# echo 2 > /sys/fs/cgroup/pids/parent/pids.max
-# echo $$ > /sys/fs/cgroup/pids/parent/cgroup.procs
-# cat /sys/fs/cgroup/pids/parent/pids.current
-2
-#
+ # mkdir -p /sys/fs/cgroup/pids/parent/child
+ # echo 2 > /sys/fs/cgroup/pids/parent/pids.max
+ # echo $$ > /sys/fs/cgroup/pids/parent/cgroup.procs
+ # cat /sys/fs/cgroup/pids/parent/pids.current
+ 2
+ #
It should be noted that attempts to overcome the set limit (2 in this case) will
-fail:
+fail::
-# cat /sys/fs/cgroup/pids/parent/pids.current
-2
-# ( /bin/echo "Here's some processes for you." | cat )
-sh: fork: Resource temporary unavailable
-#
+ # cat /sys/fs/cgroup/pids/parent/pids.current
+ 2
+ # ( /bin/echo "Here's some processes for you." | cat )
+ sh: fork: Resource temporary unavailable
+ #
Even if we migrate to a child cgroup (which doesn't have a set limit), we will
not be able to overcome the most stringent limit in the hierarchy (in this case,
-parent's):
-
-# echo $$ > /sys/fs/cgroup/pids/parent/child/cgroup.procs
-# cat /sys/fs/cgroup/pids/parent/pids.current
-2
-# cat /sys/fs/cgroup/pids/parent/child/pids.current
-2
-# cat /sys/fs/cgroup/pids/parent/child/pids.max
-max
-# ( /bin/echo "Here's some processes for you." | cat )
-sh: fork: Resource temporary unavailable
-#
+parent's)::
+
+ # echo $$ > /sys/fs/cgroup/pids/parent/child/cgroup.procs
+ # cat /sys/fs/cgroup/pids/parent/pids.current
+ 2
+ # cat /sys/fs/cgroup/pids/parent/child/pids.current
+ 2
+ # cat /sys/fs/cgroup/pids/parent/child/pids.max
+ max
+ # ( /bin/echo "Here's some processes for you." | cat )
+ sh: fork: Resource temporary unavailable
+ #
We can set a limit that is smaller than pids.current, which will stop any new
processes from being forked at all (note that the shell itself counts towards
-pids.current):
-
-# echo 1 > /sys/fs/cgroup/pids/parent/pids.max
-# /bin/echo "We can't even spawn a single process now."
-sh: fork: Resource temporary unavailable
-# echo 0 > /sys/fs/cgroup/pids/parent/pids.max
-# /bin/echo "We can't even spawn a single process now."
-sh: fork: Resource temporary unavailable
-#
+pids.current)::
+
+ # echo 1 > /sys/fs/cgroup/pids/parent/pids.max
+ # /bin/echo "We can't even spawn a single process now."
+ sh: fork: Resource temporary unavailable
+ # echo 0 > /sys/fs/cgroup/pids/parent/pids.max
+ # /bin/echo "We can't even spawn a single process now."
+ sh: fork: Resource temporary unavailable
+ #
diff --git a/Documentation/cgroup-v1/rdma.txt b/Documentation/cgroup-v1/rdma.rst
index 9bdb7fd03f83..2fcb0a9bf790 100644
--- a/Documentation/cgroup-v1/rdma.txt
+++ b/Documentation/cgroup-v1/rdma.rst
@@ -1,16 +1,17 @@
- RDMA Controller
- ----------------
+===============
+RDMA Controller
+===============
-Contents
---------
+.. Contents
-1. Overview
- 1-1. What is RDMA controller?
- 1-2. Why RDMA controller needed?
- 1-3. How is RDMA controller implemented?
-2. Usage Examples
+ 1. Overview
+ 1-1. What is RDMA controller?
+ 1-2. Why RDMA controller needed?
+ 1-3. How is RDMA controller implemented?
+ 2. Usage Examples
1. Overview
+===========
1-1. What is RDMA controller?
-----------------------------
@@ -83,27 +84,34 @@ what is configured by user for a given cgroup and what is supported by
IB device.
Following resources can be accounted by rdma controller.
+
+ ========== =============================
hca_handle Maximum number of HCA Handles
hca_object Maximum number of HCA Objects
+ ========== =============================
2. Usage Examples
------------------
-
-(a) Configure resource limit:
-echo mlx4_0 hca_handle=2 hca_object=2000 > /sys/fs/cgroup/rdma/1/rdma.max
-echo ocrdma1 hca_handle=3 > /sys/fs/cgroup/rdma/2/rdma.max
-
-(b) Query resource limit:
-cat /sys/fs/cgroup/rdma/2/rdma.max
-#Output:
-mlx4_0 hca_handle=2 hca_object=2000
-ocrdma1 hca_handle=3 hca_object=max
-
-(c) Query current usage:
-cat /sys/fs/cgroup/rdma/2/rdma.current
-#Output:
-mlx4_0 hca_handle=1 hca_object=20
-ocrdma1 hca_handle=1 hca_object=23
-
-(d) Delete resource limit:
-echo echo mlx4_0 hca_handle=max hca_object=max > /sys/fs/cgroup/rdma/1/rdma.max
+=================
+
+(a) Configure resource limit::
+
+ echo mlx4_0 hca_handle=2 hca_object=2000 > /sys/fs/cgroup/rdma/1/rdma.max
+ echo ocrdma1 hca_handle=3 > /sys/fs/cgroup/rdma/2/rdma.max
+
+(b) Query resource limit::
+
+ cat /sys/fs/cgroup/rdma/2/rdma.max
+ #Output:
+ mlx4_0 hca_handle=2 hca_object=2000
+ ocrdma1 hca_handle=3 hca_object=max
+
+(c) Query current usage::
+
+ cat /sys/fs/cgroup/rdma/2/rdma.current
+ #Output:
+ mlx4_0 hca_handle=1 hca_object=20
+ ocrdma1 hca_handle=1 hca_object=23
+
+(d) Delete resource limit::
+
+ echo echo mlx4_0 hca_handle=max hca_object=max > /sys/fs/cgroup/rdma/1/rdma.max
diff --git a/Documentation/core-api/circular-buffers.rst b/Documentation/core-api/circular-buffers.rst
index 53e51caa3347..50966f66e398 100644
--- a/Documentation/core-api/circular-buffers.rst
+++ b/Documentation/core-api/circular-buffers.rst
@@ -3,7 +3,7 @@ Circular Buffers
================
:Author: David Howells <dhowells@redhat.com>
-:Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+:Author: Paul E. McKenney <paulmck@linux.ibm.com>
Linux provides a number of features that can be used to implement circular
diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst
index 93cbeb9daec0..20ee447a50f3 100644
--- a/Documentation/core-api/timekeeping.rst
+++ b/Documentation/core-api/timekeeping.rst
@@ -65,7 +65,7 @@ different format depending on what is required by the user:
.. c:function:: u64 ktime_get_ns( void )
u64 ktime_get_boottime_ns( void )
u64 ktime_get_real_ns( void )
- u64 ktime_get_tai_ns( void )
+ u64 ktime_get_clocktai_ns( void )
u64 ktime_get_raw_ns( void )
Same as the plain ktime_get functions, but returning a u64 number
@@ -99,16 +99,20 @@ Coarse and fast_ns access
Some additional variants exist for more specialized cases:
-.. c:function:: ktime_t ktime_get_coarse_boottime( void )
+.. c:function:: ktime_t ktime_get_coarse( void )
+ ktime_t ktime_get_coarse_boottime( void )
ktime_t ktime_get_coarse_real( void )
ktime_t ktime_get_coarse_clocktai( void )
- ktime_t ktime_get_coarse_raw( void )
+
+.. c:function:: u64 ktime_get_coarse_ns( void )
+ u64 ktime_get_coarse_boottime_ns( void )
+ u64 ktime_get_coarse_real_ns( void )
+ u64 ktime_get_coarse_clocktai_ns( void )
.. c:function:: void ktime_get_coarse_ts64( struct timespec64 * )
void ktime_get_coarse_boottime_ts64( struct timespec64 * )
void ktime_get_coarse_real_ts64( struct timespec64 * )
void ktime_get_coarse_clocktai_ts64( struct timespec64 * )
- void ktime_get_coarse_raw_ts64( struct timespec64 * )
These are quicker than the non-coarse versions, but less accurate,
corresponding to CLOCK_MONONOTNIC_COARSE and CLOCK_REALTIME_COARSE
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index cb61277e2308..b90dafcc8237 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -12,6 +12,12 @@ physical_package_id:
socket number, but the actual value is architecture and platform
dependent.
+die_id:
+
+ the CPU die ID of cpuX. Typically it is the hardware platform's
+ identifier (rather than the kernel's). The actual value is
+ architecture and platform dependent.
+
core_id:
the CPU core ID of cpuX. Typically it is the hardware platform's
@@ -30,25 +36,33 @@ drawer_id:
identifier (rather than the kernel's). The actual value is
architecture and platform dependent.
-thread_siblings:
+core_cpus:
- internal kernel map of cpuX's hardware threads within the same
- core as cpuX.
+ internal kernel map of CPUs within the same core.
+ (deprecated name: "thread_siblings")
-thread_siblings_list:
+core_cpus_list:
- human-readable list of cpuX's hardware threads within the same
- core as cpuX.
+ human-readable list of CPUs within the same core.
+ (deprecated name: "thread_siblings_list");
-core_siblings:
+package_cpus:
- internal kernel map of cpuX's hardware threads within the same
- physical_package_id.
+ internal kernel map of the CPUs sharing the same physical_package_id.
+ (deprecated name: "core_siblings")
-core_siblings_list:
+package_cpus_list:
- human-readable list of cpuX's hardware threads within the same
- physical_package_id.
+ human-readable list of CPUs sharing the same physical_package_id.
+ (deprecated name: "core_siblings_list")
+
+die_cpus:
+
+ internal kernel map of CPUs within the same die.
+
+die_cpus_list:
+
+ human-readable list of CPUs within the same die.
book_siblings:
@@ -81,11 +95,13 @@ For an architecture to support this feature, it must define some of
these macros in include/asm-XXX/topology.h::
#define topology_physical_package_id(cpu)
+ #define topology_die_id(cpu)
#define topology_core_id(cpu)
#define topology_book_id(cpu)
#define topology_drawer_id(cpu)
#define topology_sibling_cpumask(cpu)
#define topology_core_cpumask(cpu)
+ #define topology_die_cpumask(cpu)
#define topology_book_cpumask(cpu)
#define topology_drawer_cpumask(cpu)
@@ -99,9 +115,11 @@ provides default definitions for any of the above macros that are
not defined by include/asm-XXX/topology.h:
1) topology_physical_package_id: -1
-2) topology_core_id: 0
-3) topology_sibling_cpumask: just the given CPU
-4) topology_core_cpumask: just the given CPU
+2) topology_die_id: -1
+3) topology_core_id: 0
+4) topology_sibling_cpumask: just the given CPU
+5) topology_core_cpumask: just the given CPU
+6) topology_die_cpumask: just the given CPU
For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
default definitions for topology_book_id() and topology_book_cpumask().
diff --git a/Documentation/crypto/api-samples.rst b/Documentation/crypto/api-samples.rst
index f14afaaf2f32..e923f17bc2bd 100644
--- a/Documentation/crypto/api-samples.rst
+++ b/Documentation/crypto/api-samples.rst
@@ -4,111 +4,89 @@ Code Examples
Code Example For Symmetric Key Cipher Operation
-----------------------------------------------
-::
-
-
- /* tie all data structures together */
- struct skcipher_def {
- struct scatterlist sg;
- struct crypto_skcipher *tfm;
- struct skcipher_request *req;
- struct crypto_wait wait;
- };
-
- /* Perform cipher operation */
- static unsigned int test_skcipher_encdec(struct skcipher_def *sk,
- int enc)
- {
- int rc;
-
- if (enc)
- rc = crypto_wait_req(crypto_skcipher_encrypt(sk->req), &sk->wait);
- else
- rc = crypto_wait_req(crypto_skcipher_decrypt(sk->req), &sk->wait);
-
- if (rc)
- pr_info("skcipher encrypt returned with result %d\n", rc);
+This code encrypts some data with AES-256-XTS. For sake of example,
+all inputs are random bytes, the encryption is done in-place, and it's
+assumed the code is running in a context where it can sleep.
- return rc;
- }
+::
- /* Initialize and trigger cipher operation */
static int test_skcipher(void)
{
- struct skcipher_def sk;
- struct crypto_skcipher *skcipher = NULL;
- struct skcipher_request *req = NULL;
- char *scratchpad = NULL;
- char *ivdata = NULL;
- unsigned char key[32];
- int ret = -EFAULT;
-
- skcipher = crypto_alloc_skcipher("cbc-aes-aesni", 0, 0);
- if (IS_ERR(skcipher)) {
- pr_info("could not allocate skcipher handle\n");
- return PTR_ERR(skcipher);
- }
-
- req = skcipher_request_alloc(skcipher, GFP_KERNEL);
- if (!req) {
- pr_info("could not allocate skcipher request\n");
- ret = -ENOMEM;
- goto out;
- }
-
- skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
- crypto_req_done,
- &sk.wait);
-
- /* AES 256 with random key */
- get_random_bytes(&key, 32);
- if (crypto_skcipher_setkey(skcipher, key, 32)) {
- pr_info("key could not be set\n");
- ret = -EAGAIN;
- goto out;
- }
-
- /* IV will be random */
- ivdata = kmalloc(16, GFP_KERNEL);
- if (!ivdata) {
- pr_info("could not allocate ivdata\n");
- goto out;
- }
- get_random_bytes(ivdata, 16);
-
- /* Input data will be random */
- scratchpad = kmalloc(16, GFP_KERNEL);
- if (!scratchpad) {
- pr_info("could not allocate scratchpad\n");
- goto out;
- }
- get_random_bytes(scratchpad, 16);
-
- sk.tfm = skcipher;
- sk.req = req;
-
- /* We encrypt one block */
- sg_init_one(&sk.sg, scratchpad, 16);
- skcipher_request_set_crypt(req, &sk.sg, &sk.sg, 16, ivdata);
- crypto_init_wait(&sk.wait);
-
- /* encrypt data */
- ret = test_skcipher_encdec(&sk, 1);
- if (ret)
- goto out;
-
- pr_info("Encryption triggered successfully\n");
-
+ struct crypto_skcipher *tfm = NULL;
+ struct skcipher_request *req = NULL;
+ u8 *data = NULL;
+ const size_t datasize = 512; /* data size in bytes */
+ struct scatterlist sg;
+ DECLARE_CRYPTO_WAIT(wait);
+ u8 iv[16]; /* AES-256-XTS takes a 16-byte IV */
+ u8 key[64]; /* AES-256-XTS takes a 64-byte key */
+ int err;
+
+ /*
+ * Allocate a tfm (a transformation object) and set the key.
+ *
+ * In real-world use, a tfm and key are typically used for many
+ * encryption/decryption operations. But in this example, we'll just do a
+ * single encryption operation with it (which is not very efficient).
+ */
+
+ tfm = crypto_alloc_skcipher("xts(aes)", 0, 0);
+ if (IS_ERR(tfm)) {
+ pr_err("Error allocating xts(aes) handle: %ld\n", PTR_ERR(tfm));
+ return PTR_ERR(tfm);
+ }
+
+ get_random_bytes(key, sizeof(key));
+ err = crypto_skcipher_setkey(tfm, key, sizeof(key));
+ if (err) {
+ pr_err("Error setting key: %d\n", err);
+ goto out;
+ }
+
+ /* Allocate a request object */
+ req = skcipher_request_alloc(tfm, GFP_KERNEL);
+ if (!req) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* Prepare the input data */
+ data = kmalloc(datasize, GFP_KERNEL);
+ if (!data) {
+ err = -ENOMEM;
+ goto out;
+ }
+ get_random_bytes(data, datasize);
+
+ /* Initialize the IV */
+ get_random_bytes(iv, sizeof(iv));
+
+ /*
+ * Encrypt the data in-place.
+ *
+ * For simplicity, in this example we wait for the request to complete
+ * before proceeding, even if the underlying implementation is asynchronous.
+ *
+ * To decrypt instead of encrypt, just change crypto_skcipher_encrypt() to
+ * crypto_skcipher_decrypt().
+ */
+ sg_init_one(&sg, data, datasize);
+ skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+ CRYPTO_TFM_REQ_MAY_SLEEP,
+ crypto_req_done, &wait);
+ skcipher_request_set_crypt(req, &sg, &sg, datasize, iv);
+ err = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+ if (err) {
+ pr_err("Error encrypting data: %d\n", err);
+ goto out;
+ }
+
+ pr_debug("Encryption was successful\n");
out:
- if (skcipher)
- crypto_free_skcipher(skcipher);
- if (req)
+ crypto_free_skcipher(tfm);
skcipher_request_free(req);
- if (ivdata)
- kfree(ivdata);
- if (scratchpad)
- kfree(scratchpad);
- return ret;
+ kfree(data);
+ return err;
}
diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst
index 4eec4a93f7e3..20ba08dddf2e 100644
--- a/Documentation/crypto/api-skcipher.rst
+++ b/Documentation/crypto/api-skcipher.rst
@@ -5,7 +5,7 @@ Block Cipher Algorithm Definitions
:doc: Block Cipher Algorithm Definitions
.. kernel-doc:: include/linux/crypto.h
- :functions: crypto_alg ablkcipher_alg blkcipher_alg cipher_alg
+ :functions: crypto_alg ablkcipher_alg blkcipher_alg cipher_alg compress_alg
Symmetric Key Cipher API
------------------------
diff --git a/Documentation/crypto/architecture.rst b/Documentation/crypto/architecture.rst
index ee8ff0762d7f..3eae1ae7f798 100644
--- a/Documentation/crypto/architecture.rst
+++ b/Documentation/crypto/architecture.rst
@@ -208,9 +208,7 @@ the aforementioned cipher types:
- CRYPTO_ALG_TYPE_KPP Key-agreement Protocol Primitive (KPP) such as
an ECDH or DH implementation
-- CRYPTO_ALG_TYPE_DIGEST Raw message digest
-
-- CRYPTO_ALG_TYPE_HASH Alias for CRYPTO_ALG_TYPE_DIGEST
+- CRYPTO_ALG_TYPE_HASH Raw message digest
- CRYPTO_ALG_TYPE_SHASH Synchronous multi-block hash
diff --git a/Documentation/crypto/crypto_engine.rst b/Documentation/crypto/crypto_engine.rst
index 1d56221dfe35..236c674d6897 100644
--- a/Documentation/crypto/crypto_engine.rst
+++ b/Documentation/crypto/crypto_engine.rst
@@ -1,50 +1,85 @@
-=============
-CRYPTO ENGINE
+.. SPDX-License-Identifier: GPL-2.0
+Crypto Engine
=============
Overview
--------
-The crypto engine API (CE), is a crypto queue manager.
+The crypto engine (CE) API is a crypto queue manager.
Requirement
-----------
-You have to put at start of your tfm_ctx the struct crypto_engine_ctx::
+You must put, at the start of your transform context your_tfm_ctx, the structure
+crypto_engine:
+
+::
- struct your_tfm_ctx {
- struct crypto_engine_ctx enginectx;
- ...
- };
+ struct your_tfm_ctx {
+ struct crypto_engine engine;
+ ...
+ };
-Why: Since CE manage only crypto_async_request, it cannot know the underlying
-request_type and so have access only on the TFM.
-So using container_of for accessing __ctx is impossible.
-Furthermore, the crypto engine cannot know the "struct your_tfm_ctx",
-so it must assume that crypto_engine_ctx is at start of it.
+The crypto engine only manages asynchronous requests in the form of
+crypto_async_request. It cannot know the underlying request type and thus only
+has access to the transform structure. It is not possible to access the context
+using container_of. In addition, the engine knows nothing about your
+structure "``struct your_tfm_ctx``". The engine assumes (requires) the placement
+of the known member ``struct crypto_engine`` at the beginning.
Order of operations
-------------------
-You have to obtain a struct crypto_engine via crypto_engine_alloc_init().
-And start it via crypto_engine_start().
-
-Before transferring any request, you have to fill the enginectx.
-- prepare_request: (taking a function pointer) If you need to do some processing before doing the request
-- unprepare_request: (taking a function pointer) Undoing what's done in prepare_request
-- do_one_request: (taking a function pointer) Do encryption for current request
-
-Note: that those three functions get the crypto_async_request associated with the received request.
-So your need to get the original request via container_of(areq, struct yourrequesttype_request, base);
-
-When your driver receive a crypto_request, you have to transfer it to
-the cryptoengine via one of:
-- crypto_transfer_ablkcipher_request_to_engine()
-- crypto_transfer_aead_request_to_engine()
-- crypto_transfer_akcipher_request_to_engine()
-- crypto_transfer_hash_request_to_engine()
-- crypto_transfer_skcipher_request_to_engine()
-
-At the end of the request process, a call to one of the following function is needed:
-- crypto_finalize_ablkcipher_request
-- crypto_finalize_aead_request
-- crypto_finalize_akcipher_request
-- crypto_finalize_hash_request
-- crypto_finalize_skcipher_request
+You are required to obtain a struct crypto_engine via ``crypto_engine_alloc_init()``.
+Start it via ``crypto_engine_start()``. When finished with your work, shut down the
+engine using ``crypto_engine_stop()`` and destroy the engine with
+``crypto_engine_exit()``.
+
+Before transferring any request, you have to fill the context enginectx by
+providing functions for the following:
+
+* ``prepare_crypt_hardware``: Called once before any prepare functions are
+ called.
+
+* ``unprepare_crypt_hardware``: Called once after all unprepare functions have
+ been called.
+
+* ``prepare_cipher_request``/``prepare_hash_request``: Called before each
+ corresponding request is performed. If some processing or other preparatory
+ work is required, do it here.
+
+* ``unprepare_cipher_request``/``unprepare_hash_request``: Called after each
+ request is handled. Clean up / undo what was done in the prepare function.
+
+* ``cipher_one_request``/``hash_one_request``: Handle the current request by
+ performing the operation.
+
+Note that these functions access the crypto_async_request structure
+associated with the received request. You are able to retrieve the original
+request by using:
+
+::
+
+ container_of(areq, struct yourrequesttype_request, base);
+
+When your driver receives a crypto_request, you must to transfer it to
+the crypto engine via one of:
+
+* crypto_transfer_ablkcipher_request_to_engine()
+
+* crypto_transfer_aead_request_to_engine()
+
+* crypto_transfer_akcipher_request_to_engine()
+
+* crypto_transfer_hash_request_to_engine()
+
+* crypto_transfer_skcipher_request_to_engine()
+
+At the end of the request process, a call to one of the following functions is needed:
+
+* crypto_finalize_ablkcipher_request()
+
+* crypto_finalize_aead_request()
+
+* crypto_finalize_akcipher_request()
+
+* crypto_finalize_hash_request()
+
+* crypto_finalize_skcipher_request()
diff --git a/Documentation/devicetree/bindings/crypto/atmel-crypto.txt b/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
index 6b458bb2440d..f2aab3dc2b52 100644
--- a/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
+++ b/Documentation/devicetree/bindings/crypto/atmel-crypto.txt
@@ -66,16 +66,3 @@ sha@f8034000 {
dmas = <&dma1 2 17>;
dma-names = "tx";
};
-
-* Eliptic Curve Cryptography (I2C)
-
-Required properties:
-- compatible : must be "atmel,atecc508a".
-- reg: I2C bus address of the device.
-- clock-frequency: must be present in the i2c controller node.
-
-Example:
-atecc508a@c0 {
- compatible = "atmel,atecc508a";
- reg = <0xC0>;
-};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt
new file mode 100644
index 000000000000..4e82fd575cec
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/amazon,al-fic.txt
@@ -0,0 +1,29 @@
+Amazon's Annapurna Labs Fabric Interrupt Controller
+
+Required properties:
+
+- compatible: should be "amazon,al-fic"
+- reg: physical base address and size of the registers
+- interrupt-controller: identifies the node as an interrupt controller
+- #interrupt-cells: must be 2.
+ First cell defines the index of the interrupt within the controller.
+ Second cell is used to specify the trigger type and must be one of the
+ following:
+ - bits[3:0] trigger type and level flags
+ 1 = low-to-high edge triggered
+ 4 = active high level-sensitive
+- interrupt-parent: specifies the parent interrupt controller.
+- interrupts: describes which input line in the interrupt parent, this
+ fic's output is connected to. This field property depends on the parent's
+ binding
+
+Example:
+
+amazon_fic: interrupt-controller@0xfd8a8500 {
+ compatible = "amazon,al-fic";
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ reg = <0x0 0xfd8a8500 0x0 0x1000>;
+ interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 0x0 IRQ_TYPE_LEVEL_HIGH>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index 1502a51548bb..7d531d5fff29 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -15,6 +15,7 @@ Required properties:
"amlogic,meson-gxbb-gpio-intc" for GXBB SoCs (S905) or
"amlogic,meson-gxl-gpio-intc" for GXL SoCs (S905X, S912)
"amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
+ "amlogic,meson-g12a-gpio-intc" for G12A SoCs (S905D2, S905X2, S905Y2)
- reg : Specifies base physical address and size of the registers.
- interrupt-controller : Identifies the node as an interrupt controller.
- #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
index ab921f1698fb..e13405355166 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
@@ -6,11 +6,16 @@ C-SKY Multi-processors Interrupt Controller is designed for ck807/ck810/ck860
SMP soc, and it also could be used in non-SMP system.
Interrupt number definition:
-
0-15 : software irq, and we use 15 as our IPI_IRQ.
16-31 : private irq, and we use 16 as the co-processor timer.
31-1024: common irq for soc ip.
+Interrupt triger mode: (Defined in dt-bindings/interrupt-controller/irq.h)
+ IRQ_TYPE_LEVEL_HIGH (default)
+ IRQ_TYPE_LEVEL_LOW
+ IRQ_TYPE_EDGE_RISING
+ IRQ_TYPE_EDGE_FALLING
+
=============================
intc node bindings definition
=============================
@@ -26,15 +31,22 @@ intc node bindings definition
- #interrupt-cells
Usage: required
Value type: <u32>
- Definition: must be <1>
+ Definition: <2>
- interrupt-controller:
Usage: required
-Examples:
+Examples: ("interrupts = <irq_num IRQ_TYPE_XXX>")
---------
+#include <dt-bindings/interrupt-controller/irq.h>
intc: interrupt-controller {
compatible = "csky,mpintc";
- #interrupt-cells = <1>;
+ #interrupt-cells = <2>;
interrupt-controller;
};
+
+ device: device-example {
+ ...
+ interrupts = <34 IRQ_TYPE_EDGE_RISING>;
+ interrupt-parent = <&intc>;
+ };
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,rza1-irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,rza1-irqc.txt
new file mode 100644
index 000000000000..727b7e4cd6e0
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,rza1-irqc.txt
@@ -0,0 +1,43 @@
+DT bindings for the Renesas RZ/A1 Interrupt Controller
+
+The RZ/A1 Interrupt Controller is a front-end for the GIC found on Renesas
+RZ/A1 and RZ/A2 SoCs:
+ - IRQ sense select for 8 external interrupts, 1:1-mapped to 8 GIC SPI
+ interrupts,
+ - NMI edge select.
+
+Required properties:
+ - compatible: Must be "renesas,<soctype>-irqc", and "renesas,rza1-irqc" as
+ fallback.
+ Examples with soctypes are:
+ - "renesas,r7s72100-irqc" (RZ/A1H)
+ - "renesas,r7s9210-irqc" (RZ/A2M)
+ - #interrupt-cells: Must be 2 (an interrupt index and flags, as defined
+ in interrupts.txt in this directory)
+ - #address-cells: Must be zero
+ - interrupt-controller: Marks the device as an interrupt controller
+ - reg: Base address and length of the memory resource used by the interrupt
+ controller
+ - interrupt-map: Specifies the mapping from external interrupts to GIC
+ interrupts
+ - interrupt-map-mask: Must be <7 0>
+
+Example:
+
+ irqc: interrupt-controller@fcfef800 {
+ compatible = "renesas,r7s72100-irqc", "renesas,rza1-irqc";
+ #interrupt-cells = <2>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0xfcfef800 0x6>;
+ interrupt-map =
+ <0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
+ <1 0 &gic GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>,
+ <2 0 &gic GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
+ <3 0 &gic GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+ <4 0 &gic GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+ <5 0 &gic GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+ <6 0 &gic GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
+ <7 0 &gic GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-map-mask = <7 0>;
+ };
diff --git a/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
new file mode 100644
index 000000000000..d77e3f26f9e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
@@ -0,0 +1,21 @@
+* Freescale(NXP) IMX8 DDR performance monitor
+
+Required properties:
+
+- compatible: should be one of:
+ "fsl,imx8-ddr-pmu"
+ "fsl,imx8m-ddr-pmu"
+
+- reg: physical address and size
+
+- interrupts: single interrupt
+ generated by the control block
+
+Example:
+
+ ddr-pmu@5c020000 {
+ compatible = "fsl,imx8-ddr-pmu";
+ reg = <0x5c020000 0x10000>;
+ interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+ };
diff --git a/Documentation/devicetree/bindings/rng/brcm,iproc-rng200.txt b/Documentation/devicetree/bindings/rng/brcm,iproc-rng200.txt
index 0014da9145af..c223e54452da 100644
--- a/Documentation/devicetree/bindings/rng/brcm,iproc-rng200.txt
+++ b/Documentation/devicetree/bindings/rng/brcm,iproc-rng200.txt
@@ -2,6 +2,7 @@ HWRNG support for the iproc-rng200 driver
Required properties:
- compatible : Must be one of:
+ "brcm,bcm7211-rng200"
"brcm,bcm7278-rng200"
"brcm,iproc-rng200"
- reg : base address and size of control register block
diff --git a/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.txt b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.txt
new file mode 100644
index 000000000000..d57659996d62
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nxp,sysctr-timer.txt
@@ -0,0 +1,25 @@
+NXP System Counter Module(sys_ctr)
+
+The system counter(sys_ctr) is a programmable system counter which provides
+a shared time base to Cortex A15, A7, A53, A73, etc. it is intended for use in
+applications where the counter is always powered and support multiple,
+unrelated clocks. The compare frame inside can be used for timer purpose.
+
+Required properties:
+
+- compatible : should be "nxp,sysctr-timer"
+- reg : Specifies the base physical address and size of the comapre
+ frame and the counter control, read & compare.
+- interrupts : should be the first compare frames' interrupt
+- clocks : Specifies the counter clock.
+- clock-names: Specifies the clock's name of this module
+
+Example:
+
+ system_counter: timer@306a0000 {
+ compatible = "nxp,sysctr-timer";
+ reg = <0x306a0000 0x20000>;/* system-counter-rd & compare */
+ clocks = <&clk_8m>;
+ clock-names = "per";
+ interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>;
+ };
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 747fd3f689dc..2e742d399e87 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -52,6 +52,10 @@ properties:
- at,24c08
# i2c trusted platform module (TPM)
- atmel,at97sc3204t
+ # i2c h/w symmetric crypto module
+ - atmel,atsha204a
+ # i2c h/w elliptic curve crypto module
+ - atmel,atecc508a
# CM32181: Ambient Light Sensor
- capella,cm32181
# CM3232: Ambient Light Sensor
diff --git a/Documentation/driver-api/s390-drivers.rst b/Documentation/driver-api/s390-drivers.rst
index 30e6aa7e160b..5158577bc29b 100644
--- a/Documentation/driver-api/s390-drivers.rst
+++ b/Documentation/driver-api/s390-drivers.rst
@@ -27,7 +27,7 @@ not strictly considered I/O devices. They are considered here as well,
although they are not the focus of this document.
Some additional information can also be found in the kernel source under
-Documentation/s390/driver-model.txt.
+Documentation/s390/driver-model.rst.
The css bus
===========
@@ -38,7 +38,7 @@ into several categories:
* Standard I/O subchannels, for use by the system. They have a child
device on the ccw bus and are described below.
* I/O subchannels bound to the vfio-ccw driver. See
- Documentation/s390/vfio-ccw.txt.
+ Documentation/s390/vfio-ccw.rst.
* Message subchannels. No Linux driver currently exists.
* CHSC subchannels (at most one). The chsc subchannel driver can be used
to send asynchronous chsc commands.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 66cad5c86171..a226061fa109 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -45,6 +45,7 @@ Table of Contents
3.9 /proc/<pid>/map_files - Information about memory mapped files
3.10 /proc/<pid>/timerslack_ns - Task timerslack value
3.11 /proc/<pid>/patch_state - Livepatch patch operation state
+ 3.12 /proc/<pid>/arch_status - Task architecture specific information
4 Configuring procfs
4.1 Mount options
@@ -1948,6 +1949,45 @@ patched. If the patch is being enabled, then the task has already been
patched. If the patch is being disabled, then the task hasn't been
unpatched yet.
+3.12 /proc/<pid>/arch_status - task architecture specific status
+-------------------------------------------------------------------
+When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the
+architecture specific status of the task.
+
+Example
+-------
+ $ cat /proc/6753/arch_status
+ AVX512_elapsed_ms: 8
+
+Description
+-----------
+
+x86 specific entries:
+---------------------
+ AVX512_elapsed_ms:
+ ------------------
+ If AVX512 is supported on the machine, this entry shows the milliseconds
+ elapsed since the last time AVX512 usage was recorded. The recording
+ happens on a best effort basis when a task is scheduled out. This means
+ that the value depends on two factors:
+
+ 1) The time which the task spent on the CPU without being scheduled
+ out. With CPU isolation and a single runnable task this can take
+ several seconds.
+
+ 2) The time since the task was scheduled out last. Depending on the
+ reason for being scheduled out (time slice exhausted, syscall ...)
+ this can be arbitrary long time.
+
+ As a consequence the value cannot be considered precise and authoritative
+ information. The application which uses this information has to be aware
+ of the overall scenario on the system in order to determine whether a
+ task is a real AVX512 user or not. Precise information can be obtained
+ with performance counters.
+
+ A special value of '-1' indicates that no AVX512 usage was recorded, thus
+ the task is unlikely an AVX512 user, but depends on the workload and the
+ scheduling scenario, it also could be a false negative mentioned above.
------------------------------------------------------------------------------
Configuring procfs
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index d06e9a59a9f4..cad797a8a39e 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -98,7 +98,7 @@ A memory policy with a valid NodeList will be saved, as specified, for
use at file creation time. When a task allocates a file in the file
system, the mount option memory policy will be applied with a NodeList,
if any, modified by the calling task's cpuset constraints
-[See Documentation/cgroup-v1/cpusets.txt] and any optional flags, listed
+[See Documentation/cgroup-v1/cpusets.rst] and any optional flags, listed
below. If the resulting NodeLists is the empty set, the effective memory
policy for the file will revert to "default" policy.
diff --git a/Documentation/locking/lockdep-design.txt b/Documentation/locking/lockdep-design.txt
index 39fae143c9cb..f189d130e543 100644
--- a/Documentation/locking/lockdep-design.txt
+++ b/Documentation/locking/lockdep-design.txt
@@ -15,34 +15,48 @@ tens of thousands of) instantiations. For example a lock in the inode
struct is one class, while each inode has its own instantiation of that
lock class.
-The validator tracks the 'state' of lock-classes, and it tracks
-dependencies between different lock-classes. The validator maintains a
-rolling proof that the state and the dependencies are correct.
-
-Unlike an lock instantiation, the lock-class itself never goes away: when
-a lock-class is used for the first time after bootup it gets registered,
-and all subsequent uses of that lock-class will be attached to this
-lock-class.
+The validator tracks the 'usage state' of lock-classes, and it tracks
+the dependencies between different lock-classes. Lock usage indicates
+how a lock is used with regard to its IRQ contexts, while lock
+dependency can be understood as lock order, where L1 -> L2 suggests that
+a task is attempting to acquire L2 while holding L1. From lockdep's
+perspective, the two locks (L1 and L2) are not necessarily related; that
+dependency just means the order ever happened. The validator maintains a
+continuing effort to prove lock usages and dependencies are correct or
+the validator will shoot a splat if incorrect.
+
+A lock-class's behavior is constructed by its instances collectively:
+when the first instance of a lock-class is used after bootup the class
+gets registered, then all (subsequent) instances will be mapped to the
+class and hence their usages and dependecies will contribute to those of
+the class. A lock-class does not go away when a lock instance does, but
+it can be removed if the memory space of the lock class (static or
+dynamic) is reclaimed, this happens for example when a module is
+unloaded or a workqueue is destroyed.
State
-----
-The validator tracks lock-class usage history into 4 * nSTATEs + 1 separate
-state bits:
+The validator tracks lock-class usage history and divides the usage into
+(4 usages * n STATEs + 1) categories:
+where the 4 usages can be:
- 'ever held in STATE context'
- 'ever held as readlock in STATE context'
- 'ever held with STATE enabled'
- 'ever held as readlock with STATE enabled'
-Where STATE can be either one of (kernel/locking/lockdep_states.h)
- - hardirq
- - softirq
+where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
+now they include:
+- hardirq
+- softirq
+where the last 1 category is:
- 'ever used' [ == !unused ]
-When locking rules are violated, these state bits are presented in the
-locking error messages, inside curlies. A contrived example:
+When locking rules are violated, these usage bits are presented in the
+locking error messages, inside curlies, with a total of 2 * n STATEs bits.
+A contrived example:
modprobe/2287 is trying to acquire lock:
(&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
@@ -51,28 +65,67 @@ locking error messages, inside curlies. A contrived example:
(&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
-The bit position indicates STATE, STATE-read, for each of the states listed
-above, and the character displayed in each indicates:
+For a given lock, the bit positions from left to right indicate the usage
+of the lock and readlock (if exists), for each of the n STATEs listed
+above respectively, and the character displayed at each bit position
+indicates:
'.' acquired while irqs disabled and not in irq context
'-' acquired in irq context
'+' acquired with irqs enabled
'?' acquired in irq context with irqs enabled.
-Unused mutexes cannot be part of the cause of an error.
+The bits are illustrated with an example:
+
+ (&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
+ ||||
+ ||| \-> softirq disabled and not in softirq context
+ || \--> acquired in softirq context
+ | \---> hardirq disabled and not in hardirq context
+ \----> acquired in hardirq context
+
+
+For a given STATE, whether the lock is ever acquired in that STATE
+context and whether that STATE is enabled yields four possible cases as
+shown in the table below. The bit character is able to indicate which
+exact case is for the lock as of the reporting time.
+
+ -------------------------------------------
+ | | irq enabled | irq disabled |
+ |-------------------------------------------|
+ | ever in irq | ? | - |
+ |-------------------------------------------|
+ | never in irq | + | . |
+ -------------------------------------------
+
+The character '-' suggests irq is disabled because if otherwise the
+charactor '?' would have been shown instead. Similar deduction can be
+applied for '+' too.
+
+Unused locks (e.g., mutexes) cannot be part of the cause of an error.
Single-lock state rules:
------------------------
+A lock is irq-safe means it was ever used in an irq context, while a lock
+is irq-unsafe means it was ever acquired with irq enabled.
+
A softirq-unsafe lock-class is automatically hardirq-unsafe as well. The
-following states are exclusive, and only one of them is allowed to be
-set for any lock-class:
+following states must be exclusive: only one of them is allowed to be set
+for any lock-class based on its usage:
+
+ <hardirq-safe> or <hardirq-unsafe>
+ <softirq-safe> or <softirq-unsafe>
- <hardirq-safe> and <hardirq-unsafe>
- <softirq-safe> and <softirq-unsafe>
+This is because if a lock can be used in irq context (irq-safe) then it
+cannot be ever acquired with irq enabled (irq-unsafe). Otherwise, a
+deadlock may happen. For example, in the scenario that after this lock
+was acquired but before released, if the context is interrupted this
+lock will be attempted to acquire twice, which creates a deadlock,
+referred to as lock recursion deadlock.
-The validator detects and reports lock usage that violate these
+The validator detects and reports lock usage that violates these
single-lock state rules.
Multi-lock dependency rules:
@@ -81,15 +134,18 @@ Multi-lock dependency rules:
The same lock-class must not be acquired twice, because this could lead
to lock recursion deadlocks.
-Furthermore, two locks may not be taken in different order:
+Furthermore, two locks can not be taken in inverse order:
<L1> -> <L2>
<L2> -> <L1>
-because this could lead to lock inversion deadlocks. (The validator
-finds such dependencies in arbitrary complexity, i.e. there can be any
-other locking sequence between the acquire-lock operations, the
-validator will still track all dependencies between locks.)
+because this could lead to a deadlock - referred to as lock inversion
+deadlock - as attempts to acquire the two locks form a circle which
+could lead to the two contexts waiting for each other permanently. The
+validator will find such dependency circle in arbitrary complexity,
+i.e., there can be any other locking sequence between the acquire-lock
+operations; the validator will still find whether these locks can be
+acquired in a circular fashion.
Furthermore, the following usage based lock dependencies are not allowed
between any two lock-classes:
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f70ebcdfe592..e4e07c8ab89e 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -3,7 +3,7 @@
============================
By: David Howells <dhowells@redhat.com>
- Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ Paul E. McKenney <paulmck@linux.ibm.com>
Will Deacon <will.deacon@arm.com>
Peter Zijlstra <peterz@infradead.org>
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 18735dc460a0..0a18075c485e 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,7 +31,7 @@ you probably needn't concern yourself with isdn4k-utils.
====================== =============== ========================================
GNU C 4.6 gcc --version
GNU make 3.81 make --version
-binutils 2.20 ld -v
+binutils 2.21 ld -v
flex 2.5.35 flex --version
bison 2.0 bison --version
util-linux 2.10o fdformat --version
@@ -77,9 +77,7 @@ You will need GNU make 3.81 or later to build the kernel.
Binutils
--------
-The build system has, as of 4.13, switched to using thin archives (`ar T`)
-rather than incremental linking (`ld -r`) for built-in.a intermediate steps.
-This requires binutils 2.20 or newer.
+Binutils 2.21 or newer is needed to build the kernel.
pkg-config
----------
diff --git a/Documentation/s390/3270.txt b/Documentation/s390/3270.rst
index 7c715de99774..e09e77954238 100644
--- a/Documentation/s390/3270.txt
+++ b/Documentation/s390/3270.rst
@@ -1,13 +1,17 @@
+===============================
IBM 3270 Display System support
+===============================
This file describes the driver that supports local channel attachment
of IBM 3270 devices. It consists of three sections:
+
* Introduction
* Installation
* Operation
-INTRODUCTION.
+Introduction
+============
This paper describes installing and operating 3270 devices under
Linux/390. A 3270 device is a block-mode rows-and-columns terminal of
@@ -17,12 +21,12 @@ twenty and thirty years ago.
You may have 3270s in-house and not know it. If you're using the
VM-ESA operating system, define a 3270 to your virtual machine by using
the command "DEF GRAF <hex-address>" This paper presumes you will be
-defining four 3270s with the CP/CMS commands
+defining four 3270s with the CP/CMS commands:
- DEF GRAF 620
- DEF GRAF 621
- DEF GRAF 622
- DEF GRAF 623
+ - DEF GRAF 620
+ - DEF GRAF 621
+ - DEF GRAF 622
+ - DEF GRAF 623
Your network connection from VM-ESA allows you to use x3270, tn3270, or
another 3270 emulator, started from an xterm window on your PC or
@@ -34,7 +38,8 @@ This paper covers installation of the driver and operation of a
dialed-in x3270.
-INSTALLATION.
+Installation
+============
You install the driver by installing a patch, doing a kernel build, and
running the configuration script (config3270.sh, in this directory).
@@ -59,13 +64,15 @@ Use #CP TERM CONMODE 3270 to change it to 3270. If you generate only
at boot time to a 3270 if it is a 3215.
In brief, these are the steps:
+
1. Install the tub3270 patch
- 2. (If a module) add a line to a file in /etc/modprobe.d/*.conf
+ 2. (If a module) add a line to a file in `/etc/modprobe.d/*.conf`
3. (If VM) define devices with DEF GRAF
4. Reboot
5. Configure
To test that everything works, assuming VM and x3270,
+
1. Bring up an x3270 window.
2. Use the DIAL command in that window.
3. You should immediately see a Linux login screen.
@@ -74,7 +81,8 @@ Here are the installation steps in detail:
1. The 3270 driver is a part of the official Linux kernel
source. Build a tree with the kernel source and any necessary
- patches. Then do
+ patches. Then do::
+
make oldconfig
(If you wish to disable 3215 console support, edit
.config; change CONFIG_TN3215's value to "n";
@@ -84,20 +92,22 @@ Here are the installation steps in detail:
make modules_install
2. (Perform this step only if you have configured tub3270 as a
- module.) Add a line to a file /etc/modprobe.d/*.conf to automatically
+ module.) Add a line to a file `/etc/modprobe.d/*.conf` to automatically
load the driver when it's needed. With this line added, you will see
login prompts appear on your 3270s as soon as boot is complete (or
with emulated 3270s, as soon as you dial into your vm guest using the
command "DIAL <vmguestname>"). Since the line-mode major number is
- 227, the line to add should be:
+ 227, the line to add should be::
+
alias char-major-227 tub3270
3. Define graphic devices to your vm guest machine, if you
haven't already. Define them before you reboot (reipl):
- DEFINE GRAF 620
- DEFINE GRAF 621
- DEFINE GRAF 622
- DEFINE GRAF 623
+
+ - DEFINE GRAF 620
+ - DEFINE GRAF 621
+ - DEFINE GRAF 622
+ - DEFINE GRAF 623
4. Reboot. The reboot process scans hardware devices, including
3270s, and this enables the tub3270 driver once loaded to respond
@@ -107,21 +117,23 @@ Here are the installation steps in detail:
5. Run the 3270 configuration script config3270. It is
distributed in this same directory, Documentation/s390, as
- config3270.sh. Inspect the output script it produces,
+ config3270.sh. Inspect the output script it produces,
/tmp/mkdev3270, and then run that script. This will create the
necessary character special device files and make the necessary
changes to /etc/inittab.
Then notify /sbin/init that /etc/inittab has changed, by issuing
- the telinit command with the q operand:
+ the telinit command with the q operand::
+
cd Documentation/s390
sh config3270.sh
sh /tmp/mkdev3270
telinit q
- This should be sufficient for your first time. If your 3270
+ This should be sufficient for your first time. If your 3270
configuration has changed and you're reusing config3270, you
- should follow these steps:
+ should follow these steps::
+
Change 3270 configuration
Reboot
Run config3270 and /tmp/mkdev3270
@@ -132,8 +144,10 @@ Here are the testing steps in detail:
1. Bring up an x3270 window, or use an actual hardware 3278 or
3279, or use the 3270 emulator of your choice. You would be
running the emulator on your PC or workstation. You would use
- the command, for example,
+ the command, for example::
+
x3270 vm-esa-domain-name &
+
if you wanted a 3278 Model 4 with 43 rows of 80 columns, the
default model number. The driver does not take advantage of
extended attributes.
@@ -144,7 +158,8 @@ Here are the testing steps in detail:
2. Use the DIAL command instead of the LOGIN command to connect
to one of the virtual 3270s you defined with the DEF GRAF
- commands:
+ commands::
+
dial my-vm-guest-name
3. You should immediately see a login prompt from your
@@ -171,14 +186,17 @@ Here are the testing steps in detail:
Wrong major number? Wrong minor number? There's your
problem!
- D. Do you get the message
+ D. Do you get the message::
+
"HCPDIA047E my-vm-guest-name 0620 does not exist"?
+
If so, you must issue the command "DEF GRAF 620" from your VM
3215 console and then reboot the system.
OPERATION.
+==========
The driver defines three areas on the 3270 screen: the log area, the
input area, and the status area.
@@ -203,8 +221,10 @@ which indicates no scrolling will occur. (If you hit ENTER with "Linux
Running" and nothing typed, the application receives a newline.)
You may change the scrolling timeout value. For example, the following
-command line:
+command line::
+
echo scrolltime=60 > /proc/tty/driver/tty3270
+
changes the scrolling timeout value to 60 sec. Set scrolltime to 0 if
you wish to prevent scrolling entirely.
@@ -228,7 +248,8 @@ cause an EOF also by typing "^D" and hitting ENTER.
No PF key is preassigned to cause a job suspension, but you may cause a
job suspension by typing "^Z" and hitting ENTER. You may wish to
assign this function to a PF key. To make PF7 cause job suspension,
-execute the command:
+execute the command::
+
echo pf7=^z > /proc/tty/driver/tty3270
If the input you type does not end with the two characters "^n", the
@@ -243,8 +264,10 @@ command is entered into the stack only when the input area is not made
invisible (such as for password entry) and it is not identical to the
current top entry. PF10 rotates backward through the command stack;
PF11 rotates forward. You may assign the backward function to any PF
-key (or PA key, for that matter), say, PA3, with the command:
+key (or PA key, for that matter), say, PA3, with the command::
+
echo -e pa3=\\033k > /proc/tty/driver/tty3270
+
This assigns the string ESC-k to PA3. Similarly, the string ESC-j
performs the forward function. (Rationale: In bash with vi-mode line
editing, ESC-k and ESC-j retrieve backward and forward history.
@@ -252,15 +275,19 @@ Suggestions welcome.)
Is a stack size of twenty commands not to your liking? Change it on
the fly. To change to saving the last 100 commands, execute the
-command:
+command::
+
echo recallsize=100 > /proc/tty/driver/tty3270
Have a command you issue frequently? Assign it to a PF or PA key! Use
-the command
- echo pf24="mkdir foobar; cd foobar" > /proc/tty/driver/tty3270
+the command::
+
+ echo pf24="mkdir foobar; cd foobar" > /proc/tty/driver/tty3270
+
to execute the commands mkdir foobar and cd foobar immediately when you
hit PF24. Want to see the command line first, before you execute it?
-Use the -n option of the echo command:
+Use the -n option of the echo command::
+
echo -n pf24="mkdir foo; cd foo" > /proc/tty/driver/tty3270
diff --git a/Documentation/s390/Debugging390.txt b/Documentation/s390/Debugging390.txt
deleted file mode 100644
index 5ae7f868a007..000000000000
--- a/Documentation/s390/Debugging390.txt
+++ /dev/null
@@ -1,2142 +0,0 @@
-
- Debugging on Linux for s/390 & z/Architecture
- by
- Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
- Copyright (C) 2000-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation
- Best viewed with fixed width fonts
-
-Overview of Document:
-=====================
-This document is intended to give a good overview of how to debug Linux for
-s/390 and z/Architecture. It is not intended as a complete reference and not a
-tutorial on the fundamentals of C & assembly. It doesn't go into
-390 IO in any detail. It is intended to complement the documents in the
-reference section below & any other worthwhile references you get.
-
-It is intended like the Enterprise Systems Architecture/390 Reference Summary
-to be printed out & used as a quick cheat sheet self help style reference when
-problems occur.
-
-Contents
-========
-Register Set
-Address Spaces on Intel Linux
-Address Spaces on Linux for s/390 & z/Architecture
-The Linux for s/390 & z/Architecture Kernel Task Structure
-Register Usage & Stackframes on Linux for s/390 & z/Architecture
-A sample program with comments
-Compiling programs for debugging on Linux for s/390 & z/Architecture
-Debugging under VM
-s/390 & z/Architecture IO Overview
-Debugging IO on s/390 & z/Architecture under VM
-GDB on s/390 & z/Architecture
-Stack chaining in gdb by hand
-Examining core dumps
-ldd
-Debugging modules
-The proc file system
-SysRq
-References
-Special Thanks
-
-Register Set
-============
-The current architectures have the following registers.
-
-16 General propose registers, 32 bit on s/390 and 64 bit on z/Architecture,
-r0-r15 (or gpr0-gpr15), used for arithmetic and addressing.
-
-16 Control registers, 32 bit on s/390 and 64 bit on z/Architecture, cr0-cr15,
-kernel usage only, used for memory management, interrupt control, debugging
-control etc.
-
-16 Access registers (ar0-ar15), 32 bit on both s/390 and z/Architecture,
-normally not used by normal programs but potentially could be used as
-temporary storage. These registers have a 1:1 association with general
-purpose registers and are designed to be used in the so-called access
-register mode to select different address spaces.
-Access register 0 (and access register 1 on z/Architecture, which needs a
-64 bit pointer) is currently used by the pthread library as a pointer to
-the current running threads private area.
-
-16 64 bit floating point registers (fp0-fp15 ) IEEE & HFP floating
-point format compliant on G5 upwards & a Floating point control reg (FPC)
-4 64 bit registers (fp0,fp2,fp4 & fp6) HFP only on older machines.
-Note:
-Linux (currently) always uses IEEE & emulates G5 IEEE format on older machines,
-( provided the kernel is configured for this ).
-
-
-The PSW is the most important register on the machine it
-is 64 bit on s/390 & 128 bit on z/Architecture & serves the roles of
-a program counter (pc), condition code register,memory space designator.
-In IBM standard notation I am counting bit 0 as the MSB.
-It has several advantages over a normal program counter
-in that you can change address translation & program counter
-in a single instruction. To change address translation,
-e.g. switching address translation off requires that you
-have a logical=physical mapping for the address you are
-currently running at.
-
- Bit Value
-s/390 z/Architecture
-0 0 Reserved ( must be 0 ) otherwise specification exception occurs.
-
-1 1 Program Event Recording 1 PER enabled,
- PER is used to facilitate debugging e.g. single stepping.
-
-2-4 2-4 Reserved ( must be 0 ).
-
-5 5 Dynamic address translation 1=DAT on.
-
-6 6 Input/Output interrupt Mask
-
-7 7 External interrupt Mask used primarily for interprocessor
- signalling and clock interrupts.
-
-8-11 8-11 PSW Key used for complex memory protection mechanism
- (not used under linux)
-
-12 12 1 on s/390 0 on z/Architecture
-
-13 13 Machine Check Mask 1=enable machine check interrupts
-
-14 14 Wait State. Set this to 1 to stop the processor except for
- interrupts and give time to other LPARS. Used in CPU idle in
- the kernel to increase overall usage of processor resources.
-
-15 15 Problem state ( if set to 1 certain instructions are disabled )
- all linux user programs run with this bit 1
- ( useful info for debugging under VM ).
-
-16-17 16-17 Address Space Control
-
- 00 Primary Space Mode:
- The register CR1 contains the primary address-space control ele-
- ment (PASCE), which points to the primary space region/segment
- table origin.
-
- 01 Access register mode
-
- 10 Secondary Space Mode:
- The register CR7 contains the secondary address-space control
- element (SASCE), which points to the secondary space region or
- segment table origin.
-
- 11 Home Space Mode:
- The register CR13 contains the home space address-space control
- element (HASCE), which points to the home space region/segment
- table origin.
-
- See "Address Spaces on Linux for s/390 & z/Architecture" below
- for more information about address space usage in Linux.
-
-18-19 18-19 Condition codes (CC)
-
-20 20 Fixed point overflow mask if 1=FPU exceptions for this event
- occur ( normally 0 )
-
-21 21 Decimal overflow mask if 1=FPU exceptions for this event occur
- ( normally 0 )
-
-22 22 Exponent underflow mask if 1=FPU exceptions for this event occur
- ( normally 0 )
-
-23 23 Significance Mask if 1=FPU exceptions for this event occur
- ( normally 0 )
-
-24-31 24-30 Reserved Must be 0.
-
- 31 Extended Addressing Mode
- 32 Basic Addressing Mode
- Used to set addressing mode
- PSW 31 PSW 32
- 0 0 24 bit
- 0 1 31 bit
- 1 1 64 bit
-
-32 1=31 bit addressing mode 0=24 bit addressing mode (for backward
- compatibility), linux always runs with this bit set to 1
-
-33-64 Instruction address.
- 33-63 Reserved must be 0
- 64-127 Address
- In 24 bits mode bits 64-103=0 bits 104-127 Address
- In 31 bits mode bits 64-96=0 bits 97-127 Address
- Note: unlike 31 bit mode on s/390 bit 96 must be zero
- when loading the address with LPSWE otherwise a
- specification exception occurs, LPSW is fully backward
- compatible.
-
-
-Prefix Page(s)
---------------
-This per cpu memory area is too intimately tied to the processor not to mention.
-It exists between the real addresses 0-4096 on s/390 and between 0-8192 on
-z/Architecture and is exchanged with one page on s/390 or two pages on
-z/Architecture in absolute storage by the set prefix instruction during Linux
-startup.
-This page is mapped to a different prefix for each processor in an SMP
-configuration (assuming the OS designer is sane of course).
-Bytes 0-512 (200 hex) on s/390 and 0-512, 4096-4544, 4604-5119 currently on
-z/Architecture are used by the processor itself for holding such information
-as exception indications and entry points for exceptions.
-Bytes after 0xc00 hex are used by linux for per processor globals on s/390 and
-z/Architecture (there is a gap on z/Architecture currently between 0xc00 and
-0x1000, too, which is used by Linux).
-The closest thing to this on traditional architectures is the interrupt
-vector table. This is a good thing & does simplify some of the kernel coding
-however it means that we now cannot catch stray NULL pointers in the
-kernel without hard coded checks.
-
-
-
-Address Spaces on Intel Linux
-=============================
-
-The traditional Intel Linux is approximately mapped as follows forgive
-the ascii art.
-0xFFFFFFFF 4GB Himem *****************
- * *
- * Kernel Space *
- * *
- ***************** ****************
-User Space Himem * User Stack * * *
-(typically 0xC0000000 3GB ) ***************** * *
- * Shared Libs * * Next Process *
- ***************** * to *
- * * <== * Run * <==
- * User Program * * *
- * Data BSS * * *
- * Text * * *
- * Sections * * *
-0x00000000 ***************** ****************
-
-Now it is easy to see that on Intel it is quite easy to recognise a kernel
-address as being one greater than user space himem (in this case 0xC0000000),
-and addresses of less than this are the ones in the current running program on
-this processor (if an smp box).
-If using the virtual machine ( VM ) as a debugger it is quite difficult to
-know which user process is running as the address space you are looking at
-could be from any process in the run queue.
-
-The limitation of Intels addressing technique is that the linux
-kernel uses a very simple real address to virtual addressing technique
-of Real Address=Virtual Address-User Space Himem.
-This means that on Intel the kernel linux can typically only address
-Himem=0xFFFFFFFF-0xC0000000=1GB & this is all the RAM these machines
-can typically use.
-They can lower User Himem to 2GB or lower & thus be
-able to use 2GB of RAM however this shrinks the maximum size
-of User Space from 3GB to 2GB they have a no win limit of 4GB unless
-they go to 64 Bit.
-
-
-On 390 our limitations & strengths make us slightly different.
-For backward compatibility we are only allowed use 31 bits (2GB)
-of our 32 bit addresses, however, we use entirely separate address
-spaces for the user & kernel.
-
-This means we can support 2GB of non Extended RAM on s/390, & more
-with the Extended memory management swap device &
-currently 4TB of physical memory currently on z/Architecture.
-
-
-Address Spaces on Linux for s/390 & z/Architecture
-==================================================
-
-Our addressing scheme is basically as follows:
-
- Primary Space Home Space
-Himem 0x7fffffff 2GB on s/390 ***************** ****************
-currently 0x3ffffffffff (2^42)-1 * User Stack * * *
-on z/Architecture. ***************** * *
- * Shared Libs * * *
- ***************** * *
- * * * Kernel *
- * User Program * * *
- * Data BSS * * *
- * Text * * *
- * Sections * * *
-0x00000000 ***************** ****************
-
-This also means that we need to look at the PSW problem state bit and the
-addressing mode to decide whether we are looking at user or kernel space.
-
-User space runs in primary address mode (or access register mode within
-the vdso code).
-
-The kernel usually also runs in home space mode, however when accessing
-user space the kernel switches to primary or secondary address mode if
-the mvcos instruction is not available or if a compare-and-swap (futex)
-instruction on a user space address is performed.
-
-When also looking at the ASCE control registers, this means:
-
-User space:
-- runs in primary or access register mode
-- cr1 contains the user asce
-- cr7 contains the user asce
-- cr13 contains the kernel asce
-
-Kernel space:
-- runs in home space mode
-- cr1 contains the user or kernel asce
- -> the kernel asce is loaded when a uaccess requires primary or
- secondary address mode
-- cr7 contains the user or kernel asce, (changed with set_fs())
-- cr13 contains the kernel asce
-
-In case of uaccess the kernel changes to:
-- primary space mode in case of a uaccess (copy_to_user) and uses
- e.g. the mvcp instruction to access user space. However the kernel
- will stay in home space mode if the mvcos instruction is available
-- secondary space mode in case of futex atomic operations, so that the
- instructions come from primary address space and data from secondary
- space
-
-In case of KVM, the kernel runs in home space mode, but cr1 gets switched
-to contain the gmap asce before the SIE instruction gets executed. When
-the SIE instruction is finished, cr1 will be switched back to contain the
-user asce.
-
-
-Virtual Addresses on s/390 & z/Architecture
-===========================================
-
-A virtual address on s/390 is made up of 3 parts
-The SX (segment index, roughly corresponding to the PGD & PMD in Linux
-terminology) being bits 1-11.
-The PX (page index, corresponding to the page table entry (pte) in Linux
-terminology) being bits 12-19.
-The remaining bits BX (the byte index are the offset in the page )
-i.e. bits 20 to 31.
-
-On z/Architecture in linux we currently make up an address from 4 parts.
-The region index bits (RX) 0-32 we currently use bits 22-32
-The segment index (SX) being bits 33-43
-The page index (PX) being bits 44-51
-The byte index (BX) being bits 52-63
-
-Notes:
-1) s/390 has no PMD so the PMD is really the PGD also.
-A lot of this stuff is defined in pgtable.h.
-
-2) Also seeing as s/390's page indexes are only 1k in size
-(bits 12-19 x 4 bytes per pte ) we use 1 ( page 4k )
-to make the best use of memory by updating 4 segment indices
-entries each time we mess with a PMD & use offsets
-0,1024,2048 & 3072 in this page as for our segment indexes.
-On z/Architecture our page indexes are now 2k in size
-( bits 12-19 x 8 bytes per pte ) we do a similar trick
-but only mess with 2 segment indices each time we mess with
-a PMD.
-
-3) As z/Architecture supports up to a massive 5-level page table lookup we
-can only use 3 currently on Linux ( as this is all the generic kernel
-currently supports ) however this may change in future
-this allows us to access ( according to my sums )
-4TB of virtual storage per process i.e.
-4096*512(PTES)*1024(PMDS)*2048(PGD) = 4398046511104 bytes,
-enough for another 2 or 3 of years I think :-).
-to do this we use a region-third-table designation type in
-our address space control registers.
-
-
-The Linux for s/390 & z/Architecture Kernel Task Structure
-==========================================================
-Each process/thread under Linux for S390 has its own kernel task_struct
-defined in linux/include/linux/sched.h
-The S390 on initialisation & resuming of a process on a cpu sets
-the __LC_KERNEL_STACK variable in the spare prefix area for this cpu
-(which we use for per-processor globals).
-
-The kernel stack pointer is intimately tied with the task structure for
-each processor as follows.
-
- s/390
- ************************
- * 1 page kernel stack *
- * ( 4K ) *
- ************************
- * 1 page task_struct *
- * ( 4K ) *
-8K aligned ************************
-
- z/Architecture
- ************************
- * 2 page kernel stack *
- * ( 8K ) *
- ************************
- * 2 page task_struct *
- * ( 8K ) *
-16K aligned ************************
-
-What this means is that we don't need to dedicate any register or global
-variable to point to the current running process & can retrieve it with the
-following very simple construct for s/390 & one very similar for z/Architecture.
-
-static inline struct task_struct * get_current(void)
-{
- struct task_struct *current;
- __asm__("lhi %0,-8192\n\t"
- "nr %0,15"
- : "=r" (current) );
- return current;
-}
-
-i.e. just anding the current kernel stack pointer with the mask -8192.
-Thankfully because Linux doesn't have support for nested IO interrupts
-& our devices have large buffers can survive interrupts being shut for
-short amounts of time we don't need a separate stack for interrupts.
-
-
-
-
-Register Usage & Stackframes on Linux for s/390 & z/Architecture
-=================================================================
-Overview:
----------
-This is the code that gcc produces at the top & the bottom of
-each function. It usually is fairly consistent & similar from
-function to function & if you know its layout you can probably
-make some headway in finding the ultimate cause of a problem
-after a crash without a source level debugger.
-
-Note: To follow stackframes requires a knowledge of C or Pascal &
-limited knowledge of one assembly language.
-
-It should be noted that there are some differences between the
-s/390 and z/Architecture stack layouts as the z/Architecture stack layout
-didn't have to maintain compatibility with older linkage formats.
-
-Glossary:
----------
-alloca:
-This is a built in compiler function for runtime allocation
-of extra space on the callers stack which is obviously freed
-up on function exit ( e.g. the caller may choose to allocate nothing
-of a buffer of 4k if required for temporary purposes ), it generates
-very efficient code ( a few cycles ) when compared to alternatives
-like malloc.
-
-automatics: These are local variables on the stack,
-i.e they aren't in registers & they aren't static.
-
-back-chain:
-This is a pointer to the stack pointer before entering a
-framed functions ( see frameless function ) prologue got by
-dereferencing the address of the current stack pointer,
- i.e. got by accessing the 32 bit value at the stack pointers
-current location.
-
-base-pointer:
-This is a pointer to the back of the literal pool which
-is an area just behind each procedure used to store constants
-in each function.
-
-call-clobbered: The caller probably needs to save these registers if there
-is something of value in them, on the stack or elsewhere before making a
-call to another procedure so that it can restore it later.
-
-epilogue:
-The code generated by the compiler to return to the caller.
-
-frameless-function
-A frameless function in Linux for s390 & z/Architecture is one which doesn't
-need more than the register save area (96 bytes on s/390, 160 on z/Architecture)
-given to it by the caller.
-A frameless function never:
-1) Sets up a back chain.
-2) Calls alloca.
-3) Calls other normal functions
-4) Has automatics.
-
-GOT-pointer:
-This is a pointer to the global-offset-table in ELF
-( Executable Linkable Format, Linux'es most common executable format ),
-all globals & shared library objects are found using this pointer.
-
-lazy-binding
-ELF shared libraries are typically only loaded when routines in the shared
-library are actually first called at runtime. This is lazy binding.
-
-procedure-linkage-table
-This is a table found from the GOT which contains pointers to routines
-in other shared libraries which can't be called to by easier means.
-
-prologue:
-The code generated by the compiler to set up the stack frame.
-
-outgoing-args:
-This is extra area allocated on the stack of the calling function if the
-parameters for the callee's cannot all be put in registers, the same
-area can be reused by each function the caller calls.
-
-routine-descriptor:
-A COFF executable format based concept of a procedure reference
-actually being 8 bytes or more as opposed to a simple pointer to the routine.
-This is typically defined as follows
-Routine Descriptor offset 0=Pointer to Function
-Routine Descriptor offset 4=Pointer to Table of Contents
-The table of contents/TOC is roughly equivalent to a GOT pointer.
-& it means that shared libraries etc. can be shared between several
-environments each with their own TOC.
-
-
-static-chain: This is used in nested functions a concept adopted from pascal
-by gcc not used in ansi C or C++ ( although quite useful ), basically it
-is a pointer used to reference local variables of enclosing functions.
-You might come across this stuff once or twice in your lifetime.
-
-e.g.
-The function below should return 11 though gcc may get upset & toss warnings
-about unused variables.
-int FunctionA(int a)
-{
- int b;
- FunctionC(int c)
- {
- b=c+1;
- }
- FunctionC(10);
- return(b);
-}
-
-
-s/390 & z/Architecture Register usage
-=====================================
-r0 used by syscalls/assembly call-clobbered
-r1 used by syscalls/assembly call-clobbered
-r2 argument 0 / return value 0 call-clobbered
-r3 argument 1 / return value 1 (if long long) call-clobbered
-r4 argument 2 call-clobbered
-r5 argument 3 call-clobbered
-r6 argument 4 saved
-r7 pointer-to arguments 5 to ... saved
-r8 this & that saved
-r9 this & that saved
-r10 static-chain ( if nested function ) saved
-r11 frame-pointer ( if function used alloca ) saved
-r12 got-pointer saved
-r13 base-pointer saved
-r14 return-address saved
-r15 stack-pointer saved
-
-f0 argument 0 / return value ( float/double ) call-clobbered
-f2 argument 1 call-clobbered
-f4 z/Architecture argument 2 saved
-f6 z/Architecture argument 3 saved
-The remaining floating points
-f1,f3,f5 f7-f15 are call-clobbered.
-
-Notes:
-------
-1) The only requirement is that registers which are used
-by the callee are saved, e.g. the compiler is perfectly
-capable of using r11 for purposes other than a frame a
-frame pointer if a frame pointer is not needed.
-2) In functions with variable arguments e.g. printf the calling procedure
-is identical to one without variable arguments & the same number of
-parameters. However, the prologue of this function is somewhat more
-hairy owing to it having to move these parameters to the stack to
-get va_start, va_arg & va_end to work.
-3) Access registers are currently unused by gcc but are used in
-the kernel. Possibilities exist to use them at the moment for
-temporary storage but it isn't recommended.
-4) Only 4 of the floating point registers are used for
-parameter passing as older machines such as G3 only have only 4
-& it keeps the stack frame compatible with other compilers.
-However with IEEE floating point emulation under linux on the
-older machines you are free to use the other 12.
-5) A long long or double parameter cannot be have the
-first 4 bytes in a register & the second four bytes in the
-outgoing args area. It must be purely in the outgoing args
-area if crossing this boundary.
-6) Floating point parameters are mixed with outgoing args
-on the outgoing args area in the order the are passed in as parameters.
-7) Floating point arguments 2 & 3 are saved in the outgoing args area for
-z/Architecture
-
-
-Stack Frame Layout
-------------------
-s/390 z/Architecture
-0 0 back chain ( a 0 here signifies end of back chain )
-4 8 eos ( end of stack, not used on Linux for S390 used in other linkage formats )
-8 16 glue used in other s/390 linkage formats for saved routine descriptors etc.
-12 24 glue used in other s/390 linkage formats for saved routine descriptors etc.
-16 32 scratch area
-20 40 scratch area
-24 48 saved r6 of caller function
-28 56 saved r7 of caller function
-32 64 saved r8 of caller function
-36 72 saved r9 of caller function
-40 80 saved r10 of caller function
-44 88 saved r11 of caller function
-48 96 saved r12 of caller function
-52 104 saved r13 of caller function
-56 112 saved r14 of caller function
-60 120 saved r15 of caller function
-64 128 saved f4 of caller function
-72 132 saved f6 of caller function
-80 undefined
-96 160 outgoing args passed from caller to callee
-96+x 160+x possible stack alignment ( 8 bytes desirable )
-96+x+y 160+x+y alloca space of caller ( if used )
-96+x+y+z 160+x+y+z automatics of caller ( if used )
-0 back-chain
-
-A sample program with comments.
-===============================
-
-Comments on the function test
------------------------------
-1) It didn't need to set up a pointer to the constant pool gpr13 as it is not
-used ( :-( ).
-2) This is a frameless function & no stack is bought.
-3) The compiler was clever enough to recognise that it could return the
-value in r2 as well as use it for the passed in parameter ( :-) ).
-4) The basr ( branch relative & save ) trick works as follows the instruction
-has a special case with r0,r0 with some instruction operands is understood as
-the literal value 0, some risc architectures also do this ). So now
-we are branching to the next address & the address new program counter is
-in r13,so now we subtract the size of the function prologue we have executed
-+ the size of the literal pool to get to the top of the literal pool
-0040037c int test(int b)
-{ # Function prologue below
- 40037c: 90 de f0 34 stm %r13,%r14,52(%r15) # Save registers r13 & r14
- 400380: 0d d0 basr %r13,%r0 # Set up pointer to constant pool using
- 400382: a7 da ff fa ahi %r13,-6 # basr trick
- return(5+b);
- # Huge main program
- 400386: a7 2a 00 05 ahi %r2,5 # add 5 to r2
-
- # Function epilogue below
- 40038a: 98 de f0 34 lm %r13,%r14,52(%r15) # restore registers r13 & 14
- 40038e: 07 fe br %r14 # return
-}
-
-Comments on the function main
------------------------------
-1) The compiler did this function optimally ( 8-) )
-
-Literal pool for main.
-400390: ff ff ff ec .long 0xffffffec
-main(int argc,char *argv[])
-{ # Function prologue below
- 400394: 90 bf f0 2c stm %r11,%r15,44(%r15) # Save necessary registers
- 400398: 18 0f lr %r0,%r15 # copy stack pointer to r0
- 40039a: a7 fa ff a0 ahi %r15,-96 # Make area for callee saving
- 40039e: 0d d0 basr %r13,%r0 # Set up r13 to point to
- 4003a0: a7 da ff f0 ahi %r13,-16 # literal pool
- 4003a4: 50 00 f0 00 st %r0,0(%r15) # Save backchain
-
- return(test(5)); # Main Program Below
- 4003a8: 58 e0 d0 00 l %r14,0(%r13) # load relative address of test from
- # literal pool
- 4003ac: a7 28 00 05 lhi %r2,5 # Set first parameter to 5
- 4003b0: 4d ee d0 00 bas %r14,0(%r14,%r13) # jump to test setting r14 as return
- # address using branch & save instruction.
-
- # Function Epilogue below
- 4003b4: 98 bf f0 8c lm %r11,%r15,140(%r15)# Restore necessary registers.
- 4003b8: 07 fe br %r14 # return to do program exit
-}
-
-
-Compiler updates
-----------------
-
-main(int argc,char *argv[])
-{
- 4004fc: 90 7f f0 1c stm %r7,%r15,28(%r15)
- 400500: a7 d5 00 04 bras %r13,400508 <main+0xc>
- 400504: 00 40 04 f4 .long 0x004004f4
- # compiler now puts constant pool in code to so it saves an instruction
- 400508: 18 0f lr %r0,%r15
- 40050a: a7 fa ff a0 ahi %r15,-96
- 40050e: 50 00 f0 00 st %r0,0(%r15)
- return(test(5));
- 400512: 58 10 d0 00 l %r1,0(%r13)
- 400516: a7 28 00 05 lhi %r2,5
- 40051a: 0d e1 basr %r14,%r1
- # compiler adds 1 extra instruction to epilogue this is done to
- # avoid processor pipeline stalls owing to data dependencies on g5 &
- # above as register 14 in the old code was needed directly after being loaded
- # by the lm %r11,%r15,140(%r15) for the br %14.
- 40051c: 58 40 f0 98 l %r4,152(%r15)
- 400520: 98 7f f0 7c lm %r7,%r15,124(%r15)
- 400524: 07 f4 br %r4
-}
-
-
-Hartmut ( our compiler developer ) also has been threatening to take out the
-stack backchain in optimised code as this also causes pipeline stalls, you
-have been warned.
-
-64 bit z/Architecture code disassembly
---------------------------------------
-
-If you understand the stuff above you'll understand the stuff
-below too so I'll avoid repeating myself & just say that
-some of the instructions have g's on the end of them to indicate
-they are 64 bit & the stack offsets are a bigger,
-the only other difference you'll find between 32 & 64 bit is that
-we now use f4 & f6 for floating point arguments on 64 bit.
-00000000800005b0 <test>:
-int test(int b)
-{
- return(5+b);
- 800005b0: a7 2a 00 05 ahi %r2,5
- 800005b4: b9 14 00 22 lgfr %r2,%r2 # downcast to integer
- 800005b8: 07 fe br %r14
- 800005ba: 07 07 bcr 0,%r7
-
-
-}
-
-00000000800005bc <main>:
-main(int argc,char *argv[])
-{
- 800005bc: eb bf f0 58 00 24 stmg %r11,%r15,88(%r15)
- 800005c2: b9 04 00 1f lgr %r1,%r15
- 800005c6: a7 fb ff 60 aghi %r15,-160
- 800005ca: e3 10 f0 00 00 24 stg %r1,0(%r15)
- return(test(5));
- 800005d0: a7 29 00 05 lghi %r2,5
- # brasl allows jumps > 64k & is overkill here bras would do fune
- 800005d4: c0 e5 ff ff ff ee brasl %r14,800005b0 <test>
- 800005da: e3 40 f1 10 00 04 lg %r4,272(%r15)
- 800005e0: eb bf f0 f8 00 04 lmg %r11,%r15,248(%r15)
- 800005e6: 07 f4 br %r4
-}
-
-
-
-Compiling programs for debugging on Linux for s/390 & z/Architecture
-====================================================================
--gdwarf-2 now works it should be considered the default debugging
-format for s/390 & z/Architecture as it is more reliable for debugging
-shared libraries, normal -g debugging works much better now
-Thanks to the IBM java compiler developers bug reports.
-
-This is typically done adding/appending the flags -g or -gdwarf-2 to the
-CFLAGS & LDFLAGS variables Makefile of the program concerned.
-
-If using gdb & you would like accurate displays of registers &
- stack traces compile without optimisation i.e make sure
-that there is no -O2 or similar on the CFLAGS line of the Makefile &
-the emitted gcc commands, obviously this will produce worse code
-( not advisable for shipment ) but it is an aid to the debugging process.
-
-This aids debugging because the compiler will copy parameters passed in
-in registers onto the stack so backtracing & looking at passed in
-parameters will work, however some larger programs which use inline functions
-will not compile without optimisation.
-
-Debugging with optimisation has since much improved after fixing
-some bugs, please make sure you are using gdb-5.0 or later developed
-after Nov'2000.
-
-
-
-Debugging under VM
-==================
-
-Notes
------
-Addresses & values in the VM debugger are always hex never decimal
-Address ranges are of the format <HexValue1>-<HexValue2> or
-<HexValue1>.<HexValue2>
-For example, the address range 0x2000 to 0x3000 can be described as 2000-3000
-or 2000.1000
-
-The VM Debugger is case insensitive.
-
-VM's strengths are usually other debuggers weaknesses you can get at any
-resource no matter how sensitive e.g. memory management resources, change
-address translation in the PSW. For kernel hacking you will reap dividends if
-you get good at it.
-
-The VM Debugger displays operators but not operands, and also the debugger
-displays useful information on the same line as the author of the code probably
-felt that it was a good idea not to go over the 80 columns on the screen.
-This isn't as unintuitive as it may seem as the s/390 instructions are easy to
-decode mentally and you can make a good guess at a lot of them as all the
-operands are nibble (half byte aligned).
-So if you have an objdump listing by hand, it is quite easy to follow, and if
-you don't have an objdump listing keep a copy of the s/390 Reference Summary
-or alternatively the s/390 principles of operation next to you.
-e.g. even I can guess that
-0001AFF8' LR 180F CC 0
-is a ( load register ) lr r0,r15
-
-Also it is very easy to tell the length of a 390 instruction from the 2 most
-significant bits in the instruction (not that this info is really useful except
-if you are trying to make sense of a hexdump of code).
-Here is a table
-Bits Instruction Length
-------------------------------------------
-00 2 Bytes
-01 4 Bytes
-10 4 Bytes
-11 6 Bytes
-
-The debugger also displays other useful info on the same line such as the
-addresses being operated on destination addresses of branches & condition codes.
-e.g.
-00019736' AHI A7DAFF0E CC 1
-000198BA' BRC A7840004 -> 000198C2' CC 0
-000198CE' STM 900EF068 >> 0FA95E78 CC 2
-
-
-
-Useful VM debugger commands
----------------------------
-
-I suppose I'd better mention this before I start
-to list the current active traces do
-Q TR
-there can be a maximum of 255 of these per set
-( more about trace sets later ).
-To stop traces issue a
-TR END.
-To delete a particular breakpoint issue
-TR DEL <breakpoint number>
-
-The PA1 key drops to CP mode so you can issue debugger commands,
-Doing alt c (on my 3270 console at least ) clears the screen.
-hitting b <enter> comes back to the running operating system
-from cp mode ( in our case linux ).
-It is typically useful to add shortcuts to your profile.exec file
-if you have one ( this is roughly equivalent to autoexec.bat in DOS ).
-file here are a few from mine.
-/* this gives me command history on issuing f12 */
-set pf12 retrieve
-/* this continues */
-set pf8 imm b
-/* goes to trace set a */
-set pf1 imm tr goto a
-/* goes to trace set b */
-set pf2 imm tr goto b
-/* goes to trace set c */
-set pf3 imm tr goto c
-
-
-
-Instruction Tracing
--------------------
-Setting a simple breakpoint
-TR I PSWA <address>
-To debug a particular function try
-TR I R <function address range>
-TR I on its own will single step.
-TR I DATA <MNEMONIC> <OPTIONAL RANGE> will trace for particular mnemonics
-e.g.
-TR I DATA 4D R 0197BC.4000
-will trace for BAS'es ( opcode 4D ) in the range 0197BC.4000
-if you were inclined you could add traces for all branch instructions &
-suffix them with the run prefix so you would have a backtrace on screen
-when a program crashes.
-TR BR <INTO OR FROM> will trace branches into or out of an address.
-e.g.
-TR BR INTO 0 is often quite useful if a program is getting awkward & deciding
-to branch to 0 & crashing as this will stop at the address before in jumps to 0.
-TR I R <address range> RUN cmd d g
-single steps a range of addresses but stays running &
-displays the gprs on each step.
-
-
-
-Displaying & modifying Registers
---------------------------------
-D G will display all the gprs
-Adding a extra G to all the commands is necessary to access the full 64 bit
-content in VM on z/Architecture. Obviously this isn't required for access
-registers as these are still 32 bit.
-e.g. DGG instead of DG
-D X will display all the control registers
-D AR will display all the access registers
-D AR4-7 will display access registers 4 to 7
-CPU ALL D G will display the GRPS of all CPUS in the configuration
-D PSW will display the current PSW
-st PSW 2000 will put the value 2000 into the PSW &
-cause crash your machine.
-D PREFIX displays the prefix offset
-
-
-Displaying Memory
------------------
-To display memory mapped using the current PSW's mapping try
-D <range>
-To make VM display a message each time it hits a particular address and
-continue try
-D I<range> will disassemble/display a range of instructions.
-ST addr 32 bit word will store a 32 bit aligned address
-D T<range> will display the EBCDIC in an address (if you are that way inclined)
-D R<range> will display real addresses ( without DAT ) but with prefixing.
-There are other complex options to display if you need to get at say home space
-but are in primary space the easiest thing to do is to temporarily
-modify the PSW to the other addressing mode, display the stuff & then
-restore it.
-
-
-
-Hints
------
-If you want to issue a debugger command without halting your virtual machine
-with the PA1 key try prefixing the command with #CP e.g.
-#cp tr i pswa 2000
-also suffixing most debugger commands with RUN will cause them not
-to stop just display the mnemonic at the current instruction on the console.
-If you have several breakpoints you want to put into your program &
-you get fed up of cross referencing with System.map
-you can do the following trick for several symbols.
-grep do_signal System.map
-which emits the following among other things
-0001f4e0 T do_signal
-now you can do
-
-TR I PSWA 0001f4e0 cmd msg * do_signal
-This sends a message to your own console each time do_signal is entered.
-( As an aside I wrote a perl script once which automatically generated a REXX
-script with breakpoints on every kernel procedure, this isn't a good idea
-because there are thousands of these routines & VM can only set 255 breakpoints
-at a time so you nearly had to spend as long pruning the file down as you would
-entering the msgs by hand), however, the trick might be useful for a single
-object file. In the 3270 terminal emulator x3270 there is a very useful option
-in the file menu called "Save Screen In File" - this is very good for keeping a
-copy of traces.
-
-From CMS help <command name> will give you online help on a particular command.
-e.g.
-HELP DISPLAY
-
-Also CP has a file called profile.exec which automatically gets called
-on startup of CMS ( like autoexec.bat ), keeping on a DOS analogy session
-CP has a feature similar to doskey, it may be useful for you to
-use profile.exec to define some keystrokes.
-e.g.
-SET PF9 IMM B
-This does a single step in VM on pressing F8.
-SET PF10 ^
-This sets up the ^ key.
-which can be used for ^c (ctrl-c),^z (ctrl-z) which can't be typed directly
-into some 3270 consoles.
-SET PF11 ^-
-This types the starting keystrokes for a sysrq see SysRq below.
-SET PF12 RETRIEVE
-This retrieves command history on pressing F12.
-
-
-Sometimes in VM the display is set up to scroll automatically this
-can be very annoying if there are messages you wish to look at
-to stop this do
-TERM MORE 255 255
-This will nearly stop automatic screen updates, however it will
-cause a denial of service if lots of messages go to the 3270 console,
-so it would be foolish to use this as the default on a production machine.
-
-
-Tracing particular processes
-----------------------------
-The kernel's text segment is intentionally at an address in memory that it will
-very seldom collide with text segments of user programs ( thanks Martin ),
-this simplifies debugging the kernel.
-However it is quite common for user processes to have addresses which collide
-this can make debugging a particular process under VM painful under normal
-circumstances as the process may change when doing a
-TR I R <address range>.
-Thankfully after reading VM's online help I figured out how to debug
-I particular process.
-
-Your first problem is to find the STD ( segment table designation )
-of the program you wish to debug.
-There are several ways you can do this here are a few
-1) objdump --syms <program to be debugged> | grep main
-To get the address of main in the program.
-tr i pswa <address of main>
-Start the program, if VM drops to CP on what looks like the entry
-point of the main function this is most likely the process you wish to debug.
-Now do a D X13 or D XG13 on z/Architecture.
-On 31 bit the STD is bits 1-19 ( the STO segment table origin )
-& 25-31 ( the STL segment table length ) of CR13.
-now type
-TR I R STD <CR13's value> 0.7fffffff
-e.g.
-TR I R STD 8F32E1FF 0.7fffffff
-Another very useful variation is
-TR STORE INTO STD <CR13's value> <address range>
-for finding out when a particular variable changes.
-
-An alternative way of finding the STD of a currently running process
-is to do the following, ( this method is more complex but
-could be quite convenient if you aren't updating the kernel much &
-so your kernel structures will stay constant for a reasonable period of
-time ).
-
-grep task /proc/<pid>/status
-from this you should see something like
-task: 0f160000 ksp: 0f161de8 pt_regs: 0f161f68
-This now gives you a pointer to the task structure.
-Now make CC:="s390-gcc -g" kernel/sched.s
-To get the task_struct stabinfo.
-( task_struct is defined in include/linux/sched.h ).
-Now we want to look at
-task->active_mm->pgd
-on my machine the active_mm in the task structure stab is
-active_mm:(4,12),672,32
-its offset is 672/8=84=0x54
-the pgd member in the mm_struct stab is
-pgd:(4,6)=*(29,5),96,32
-so its offset is 96/8=12=0xc
-
-so we'll
-hexdump -s 0xf160054 /dev/mem | more
-i.e. task_struct+active_mm offset
-to look at the active_mm member
-f160054 0fee cc60 0019 e334 0000 0000 0000 0011
-hexdump -s 0x0feecc6c /dev/mem | more
-i.e. active_mm+pgd offset
-feecc6c 0f2c 0000 0000 0001 0000 0001 0000 0010
-we get something like
-now do
-TR I R STD <pgd|0x7f> 0.7fffffff
-i.e. the 0x7f is added because the pgd only
-gives the page table origin & we need to set the low bits
-to the maximum possible segment table length.
-TR I R STD 0f2c007f 0.7fffffff
-on z/Architecture you'll probably need to do
-TR I R STD <pgd|0x7> 0.ffffffffffffffff
-to set the TableType to 0x1 & the Table length to 3.
-
-
-
-Tracing Program Exceptions
---------------------------
-If you get a crash which says something like
-illegal operation or specification exception followed by a register dump
-You can restart linux & trace these using the tr prog <range or value> trace
-option.
-
-
-The most common ones you will normally be tracing for is
-1=operation exception
-2=privileged operation exception
-4=protection exception
-5=addressing exception
-6=specification exception
-10=segment translation exception
-11=page translation exception
-
-The full list of these is on page 22 of the current s/390 Reference Summary.
-e.g.
-tr prog 10 will trace segment translation exceptions.
-tr prog on its own will trace all program interruption codes.
-
-Trace Sets
-----------
-On starting VM you are initially in the INITIAL trace set.
-You can do a Q TR to verify this.
-If you have a complex tracing situation where you wish to wait for instance
-till a driver is open before you start tracing IO, but know in your
-heart that you are going to have to make several runs through the code till you
-have a clue whats going on.
-
-What you can do is
-TR I PSWA <Driver open address>
-hit b to continue till breakpoint
-reach the breakpoint
-now do your
-TR GOTO B
-TR IO 7c08-7c09 inst int run
-or whatever the IO channels you wish to trace are & hit b
-
-To got back to the initial trace set do
-TR GOTO INITIAL
-& the TR I PSWA <Driver open address> will be the only active breakpoint again.
-
-
-Tracing linux syscalls under VM
--------------------------------
-Syscalls are implemented on Linux for S390 by the Supervisor call instruction
-(SVC). There 256 possibilities of these as the instruction is made up of a 0xA
-opcode and the second byte being the syscall number. They are traced using the
-simple command:
-TR SVC <Optional value or range>
-the syscalls are defined in linux/arch/s390/include/asm/unistd.h
-e.g. to trace all file opens just do
-TR SVC 5 ( as this is the syscall number of open )
-
-
-SMP Specific commands
----------------------
-To find out how many cpus you have
-Q CPUS displays all the CPU's available to your virtual machine
-To find the cpu that the current cpu VM debugger commands are being directed at
-do Q CPU to change the current cpu VM debugger commands are being directed at do
-CPU <desired cpu no>
-
-On a SMP guest issue a command to all CPUs try prefixing the command with cpu
-all. To issue a command to a particular cpu try cpu <cpu number> e.g.
-CPU 01 TR I R 2000.3000
-If you are running on a guest with several cpus & you have a IO related problem
-& cannot follow the flow of code but you know it isn't smp related.
-from the bash prompt issue
-shutdown -h now or halt.
-do a Q CPUS to find out how many cpus you have
-detach each one of them from cp except cpu 0
-by issuing a
-DETACH CPU 01-(number of cpus in configuration)
-& boot linux again.
-TR SIGP will trace inter processor signal processor instructions.
-DEFINE CPU 01-(number in configuration)
-will get your guests cpus back.
-
-
-Help for displaying ascii textstrings
--------------------------------------
-On the very latest VM Nucleus'es VM can now display ascii
-( thanks Neale for the hint ) by doing
-D TX<lowaddr>.<len>
-e.g.
-D TX0.100
-
-Alternatively
-=============
-Under older VM debuggers (I love EBDIC too) you can use following little
-program which converts a command line of hex digits to ascii text. It can be
-compiled under linux and you can copy the hex digits from your x3270 terminal
-to your xterm if you are debugging from a linuxbox.
-
-This is quite useful when looking at a parameter passed in as a text string
-under VM ( unless you are good at decoding ASCII in your head ).
-
-e.g. consider tracing an open syscall
-TR SVC 5
-We have stopped at a breakpoint
-000151B0' SVC 0A05 -> 0001909A' CC 0
-
-D 20.8 to check the SVC old psw in the prefix area and see was it from userspace
-(for the layout of the prefix area consult the "Fixed Storage Locations"
-chapter of the s/390 Reference Summary if you have it available).
-V00000020 070C2000 800151B2
-The problem state bit wasn't set & it's also too early in the boot sequence
-for it to be a userspace SVC if it was we would have to temporarily switch the
-psw to user space addressing so we could get at the first parameter of the open
-in gpr2.
-Next do a
-D G2
-GPR 2 = 00014CB4
-Now display what gpr2 is pointing to
-D 00014CB4.20
-V00014CB4 2F646576 2F636F6E 736F6C65 00001BF5
-V00014CC4 FC00014C B4001001 E0001000 B8070707
-Now copy the text till the first 00 hex ( which is the end of the string
-to an xterm & do hex2ascii on it.
-hex2ascii 2F646576 2F636F6E 736F6C65 00
-outputs
-Decoded Hex:=/ d e v / c o n s o l e 0x00
-We were opening the console device,
-
-You can compile the code below yourself for practice :-),
-/*
- * hex2ascii.c
- * a useful little tool for converting a hexadecimal command line to ascii
- *
- * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
- * (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation.
- */
-#include <stdio.h>
-
-int main(int argc,char *argv[])
-{
- int cnt1,cnt2,len,toggle=0;
- int startcnt=1;
- unsigned char c,hex;
-
- if(argc>1&&(strcmp(argv[1],"-a")==0))
- startcnt=2;
- printf("Decoded Hex:=");
- for(cnt1=startcnt;cnt1<argc;cnt1++)
- {
- len=strlen(argv[cnt1]);
- for(cnt2=0;cnt2<len;cnt2++)
- {
- c=argv[cnt1][cnt2];
- if(c>='0'&&c<='9')
- c=c-'0';
- if(c>='A'&&c<='F')
- c=c-'A'+10;
- if(c>='a'&&c<='f')
- c=c-'a'+10;
- switch(toggle)
- {
- case 0:
- hex=c<<4;
- toggle=1;
- break;
- case 1:
- hex+=c;
- if(hex<32||hex>127)
- {
- if(startcnt==1)
- printf("0x%02X ",(int)hex);
- else
- printf(".");
- }
- else
- {
- printf("%c",hex);
- if(startcnt==1)
- printf(" ");
- }
- toggle=0;
- break;
- }
- }
- }
- printf("\n");
-}
-
-
-
-
-Stack tracing under VM
-----------------------
-A basic backtrace
------------------
-
-Here are the tricks I use 9 out of 10 times it works pretty well,
-
-When your backchain reaches a dead end
---------------------------------------
-This can happen when an exception happens in the kernel and the kernel is
-entered twice. If you reach the NULL pointer at the end of the back chain you
-should be able to sniff further back if you follow the following tricks.
-1) A kernel address should be easy to recognise since it is in
-primary space & the problem state bit isn't set & also
-The Hi bit of the address is set.
-2) Another backchain should also be easy to recognise since it is an
-address pointing to another address approximately 100 bytes or 0x70 hex
-behind the current stackpointer.
-
-
-Here is some practice.
-boot the kernel & hit PA1 at some random time
-d g to display the gprs, this should display something like
-GPR 0 = 00000001 00156018 0014359C 00000000
-GPR 4 = 00000001 001B8888 000003E0 00000000
-GPR 8 = 00100080 00100084 00000000 000FE000
-GPR 12 = 00010400 8001B2DC 8001B36A 000FFED8
-Note that GPR14 is a return address but as we are real men we are going to
-trace the stack.
-display 0x40 bytes after the stack pointer.
-
-V000FFED8 000FFF38 8001B838 80014C8E 000FFF38
-V000FFEE8 00000000 00000000 000003E0 00000000
-V000FFEF8 00100080 00100084 00000000 000FE000
-V000FFF08 00010400 8001B2DC 8001B36A 000FFED8
-
-
-Ah now look at whats in sp+56 (sp+0x38) this is 8001B36A our saved r14 if
-you look above at our stackframe & also agrees with GPR14.
-
-now backchain
-d 000FFF38.40
-we now are taking the contents of SP to get our first backchain.
-
-V000FFF38 000FFFA0 00000000 00014995 00147094
-V000FFF48 00147090 001470A0 000003E0 00000000
-V000FFF58 00100080 00100084 00000000 001BF1D0
-V000FFF68 00010400 800149BA 80014CA6 000FFF38
-
-This displays a 2nd return address of 80014CA6
-
-now do d 000FFFA0.40 for our 3rd backchain
-
-V000FFFA0 04B52002 0001107F 00000000 00000000
-V000FFFB0 00000000 00000000 FF000000 0001107F
-V000FFFC0 00000000 00000000 00000000 00000000
-V000FFFD0 00010400 80010802 8001085A 000FFFA0
-
-
-our 3rd return address is 8001085A
-
-as the 04B52002 looks suspiciously like rubbish it is fair to assume that the
-kernel entry routines for the sake of optimisation don't set up a backchain.
-
-now look at System.map to see if the addresses make any sense.
-
-grep -i 0001b3 System.map
-outputs among other things
-0001b304 T cpu_idle
-so 8001B36A
-is cpu_idle+0x66 ( quiet the cpu is asleep, don't wake it )
-
-
-grep -i 00014 System.map
-produces among other things
-00014a78 T start_kernel
-so 0014CA6 is start_kernel+some hex number I can't add in my head.
-
-grep -i 00108 System.map
-this produces
-00010800 T _stext
-so 8001085A is _stext+0x5a
-
-Congrats you've done your first backchain.
-
-
-
-s/390 & z/Architecture IO Overview
-==================================
-
-I am not going to give a course in 390 IO architecture as this would take me
-quite a while and I'm no expert. Instead I'll give a 390 IO architecture
-summary for Dummies. If you have the s/390 principles of operation available
-read this instead. If nothing else you may find a few useful keywords in here
-and be able to use them on a web search engine to find more useful information.
-
-Unlike other bus architectures modern 390 systems do their IO using mostly
-fibre optics and devices such as tapes and disks can be shared between several
-mainframes. Also S390 can support up to 65536 devices while a high end PC based
-system might be choking with around 64.
-
-Here is some of the common IO terminology:
-
-Subchannel:
-This is the logical number most IO commands use to talk to an IO device. There
-can be up to 0x10000 (65536) of these in a configuration, typically there are a
-few hundred. Under VM for simplicity they are allocated contiguously, however
-on the native hardware they are not. They typically stay consistent between
-boots provided no new hardware is inserted or removed.
-Under Linux for s390 we use these as IRQ's and also when issuing an IO command
-(CLEAR SUBCHANNEL, HALT SUBCHANNEL, MODIFY SUBCHANNEL, RESUME SUBCHANNEL,
-START SUBCHANNEL, STORE SUBCHANNEL and TEST SUBCHANNEL). We use this as the ID
-of the device we wish to talk to. The most important of these instructions are
-START SUBCHANNEL (to start IO), TEST SUBCHANNEL (to check whether the IO
-completed successfully) and HALT SUBCHANNEL (to kill IO). A subchannel can have
-up to 8 channel paths to a device, this offers redundancy if one is not
-available.
-
-Device Number:
-This number remains static and is closely tied to the hardware. There are 65536
-of these, made up of a CHPID (Channel Path ID, the most significant 8 bits) and
-another lsb 8 bits. These remain static even if more devices are inserted or
-removed from the hardware. There is a 1 to 1 mapping between subchannels and
-device numbers, provided devices aren't inserted or removed.
-
-Channel Control Words:
-CCWs are linked lists of instructions initially pointed to by an operation
-request block (ORB), which is initially given to Start Subchannel (SSCH)
-command along with the subchannel number for the IO subsystem to process
-while the CPU continues executing normal code.
-CCWs come in two flavours, Format 0 (24 bit for backward compatibility) and
-Format 1 (31 bit). These are typically used to issue read and write (and many
-other) instructions. They consist of a length field and an absolute address
-field.
-Each IO typically gets 1 or 2 interrupts, one for channel end (primary status)
-when the channel is idle, and the second for device end (secondary status).
-Sometimes you get both concurrently. You check how the IO went on by issuing a
-TEST SUBCHANNEL at each interrupt, from which you receive an Interruption
-response block (IRB). If you get channel and device end status in the IRB
-without channel checks etc. your IO probably went okay. If you didn't you
-probably need to examine the IRB, extended status word etc.
-If an error occurs, more sophisticated control units have a facility known as
-concurrent sense. This means that if an error occurs Extended sense information
-will be presented in the Extended status word in the IRB. If not you have to
-issue a subsequent SENSE CCW command after the test subchannel.
-
-
-TPI (Test pending interrupt) can also be used for polled IO, but in
-multitasking multiprocessor systems it isn't recommended except for
-checking special cases (i.e. non looping checks for pending IO etc.).
-
-Store Subchannel and Modify Subchannel can be used to examine and modify
-operating characteristics of a subchannel (e.g. channel paths).
-
-Other IO related Terms:
-Sysplex: S390's Clustering Technology
-QDIO: S390's new high speed IO architecture to support devices such as gigabit
-ethernet, this architecture is also designed to be forward compatible with
-upcoming 64 bit machines.
-
-
-General Concepts
-
-Input Output Processors (IOP's) are responsible for communicating between
-the mainframe CPU's & the channel & relieve the mainframe CPU's from the
-burden of communicating with IO devices directly, this allows the CPU's to
-concentrate on data processing.
-
-IOP's can use one or more links ( known as channel paths ) to talk to each
-IO device. It first checks for path availability & chooses an available one,
-then starts ( & sometimes terminates IO ).
-There are two types of channel path: ESCON & the Parallel IO interface.
-
-IO devices are attached to control units, control units provide the
-logic to interface the channel paths & channel path IO protocols to
-the IO devices, they can be integrated with the devices or housed separately
-& often talk to several similar devices ( typical examples would be raid
-controllers or a control unit which connects to 1000 3270 terminals ).
-
-
- +---------------------------------------------------------------+
- | +-----+ +-----+ +-----+ +-----+ +----------+ +----------+ |
- | | CPU | | CPU | | CPU | | CPU | | Main | | Expanded | |
- | | | | | | | | | | Memory | | Storage | |
- | +-----+ +-----+ +-----+ +-----+ +----------+ +----------+ |
- |---------------------------------------------------------------+
- | IOP | IOP | IOP |
- |---------------------------------------------------------------
- | C | C | C | C | C | C | C | C | C | C | C | C | C | C | C | C |
- ----------------------------------------------------------------
- || ||
- || Bus & Tag Channel Path || ESCON
- || ====================== || Channel
- || || || || Path
- +----------+ +----------+ +----------+
- | | | | | |
- | CU | | CU | | CU |
- | | | | | |
- +----------+ +----------+ +----------+
- | | | | |
-+----------+ +----------+ +----------+ +----------+ +----------+
-|I/O Device| |I/O Device| |I/O Device| |I/O Device| |I/O Device|
-+----------+ +----------+ +----------+ +----------+ +----------+
- CPU = Central Processing Unit
- C = Channel
- IOP = IP Processor
- CU = Control Unit
-
-The 390 IO systems come in 2 flavours the current 390 machines support both
-
-The Older 360 & 370 Interface,sometimes called the Parallel I/O interface,
-sometimes called Bus-and Tag & sometimes Original Equipment Manufacturers
-Interface (OEMI).
-
-This byte wide Parallel channel path/bus has parity & data on the "Bus" cable
-and control lines on the "Tag" cable. These can operate in byte multiplex mode
-for sharing between several slow devices or burst mode and monopolize the
-channel for the whole burst. Up to 256 devices can be addressed on one of these
-cables. These cables are about one inch in diameter. The maximum unextended
-length supported by these cables is 125 Meters but this can be extended up to
-2km with a fibre optic channel extended such as a 3044. The maximum burst speed
-supported is 4.5 megabytes per second. However, some really old processors
-support only transfer rates of 3.0, 2.0 & 1.0 MB/sec.
-One of these paths can be daisy chained to up to 8 control units.
-
-
-ESCON if fibre optic it is also called FICON
-Was introduced by IBM in 1990. Has 2 fibre optic cables and uses either leds or
-lasers for communication at a signaling rate of up to 200 megabits/sec. As
-10bits are transferred for every 8 bits info this drops to 160 megabits/sec
-and to 18.6 Megabytes/sec once control info and CRC are added. ESCON only
-operates in burst mode.
-
-ESCONs typical max cable length is 3km for the led version and 20km for the
-laser version known as XDF (extended distance facility). This can be further
-extended by using an ESCON director which triples the above mentioned ranges.
-Unlike Bus & Tag as ESCON is serial it uses a packet switching architecture,
-the standard Bus & Tag control protocol is however present within the packets.
-Up to 256 devices can be attached to each control unit that uses one of these
-interfaces.
-
-Common 390 Devices include:
-Network adapters typically OSA2,3172's,2116's & OSA-E gigabit ethernet adapters,
-Consoles 3270 & 3215 (a teletype emulated under linux for a line mode console).
-DASD's direct access storage devices ( otherwise known as hard disks ).
-Tape Drives.
-CTC ( Channel to Channel Adapters ),
-ESCON or Parallel Cables used as a very high speed serial link
-between 2 machines.
-
-
-Debugging IO on s/390 & z/Architecture under VM
-===============================================
-
-Now we are ready to go on with IO tracing commands under VM
-
-A few self explanatory queries:
-Q OSA
-Q CTC
-Q DISK ( This command is CMS specific )
-Q DASD
-
-
-
-
-
-
-Q OSA on my machine returns
-OSA 7C08 ON OSA 7C08 SUBCHANNEL = 0000
-OSA 7C09 ON OSA 7C09 SUBCHANNEL = 0001
-OSA 7C14 ON OSA 7C14 SUBCHANNEL = 0002
-OSA 7C15 ON OSA 7C15 SUBCHANNEL = 0003
-
-If you have a guest with certain privileges you may be able to see devices
-which don't belong to you. To avoid this, add the option V.
-e.g.
-Q V OSA
-
-Now using the device numbers returned by this command we will
-Trace the io starting up on the first device 7c08 & 7c09
-In our simplest case we can trace the
-start subchannels
-like TR SSCH 7C08-7C09
-or the halt subchannels
-or TR HSCH 7C08-7C09
-MSCH's ,STSCH's I think you can guess the rest
-
-A good trick is tracing all the IO's and CCWS and spooling them into the reader
-of another VM guest so he can ftp the logfile back to his own machine. I'll do
-a small bit of this and give you a look at the output.
-
-1) Spool stdout to VM reader
-SP PRT TO (another vm guest ) or * for the local vm guest
-2) Fill the reader with the trace
-TR IO 7c08-7c09 INST INT CCW PRT RUN
-3) Start up linux
-i 00c
-4) Finish the trace
-TR END
-5) close the reader
-C PRT
-6) list reader contents
-RDRLIST
-7) copy it to linux4's minidisk
-RECEIVE / LOG TXT A1 ( replace
-8)
-filel & press F11 to look at it
-You should see something like:
-
-00020942' SSCH B2334000 0048813C CC 0 SCH 0000 DEV 7C08
- CPA 000FFDF0 PARM 00E2C9C4 KEY 0 FPI C0 LPM 80
- CCW 000FFDF0 E4200100 00487FE8 0000 E4240100 ........
- IDAL 43D8AFE8
- IDAL 0FB76000
-00020B0A' I/O DEV 7C08 -> 000197BC' SCH 0000 PARM 00E2C9C4
-00021628' TSCH B2354000 >> 00488164 CC 0 SCH 0000 DEV 7C08
- CCWA 000FFDF8 DEV STS 0C SCH STS 00 CNT 00EC
- KEY 0 FPI C0 CC 0 CTLS 4007
-00022238' STSCH B2344000 >> 00488108 CC 0 SCH 0000 DEV 7C08
-
-If you don't like messing up your readed ( because you possibly booted from it )
-you can alternatively spool it to another readers guest.
-
-
-Other common VM device related commands
----------------------------------------------
-These commands are listed only because they have
-been of use to me in the past & may be of use to
-you too. For more complete info on each of the commands
-use type HELP <command> from CMS.
-detaching devices
-DET <devno range>
-ATT <devno range> <guest>
-attach a device to guest * for your own guest
-READY <devno> cause VM to issue a fake interrupt.
-
-The VARY command is normally only available to VM administrators.
-VARY ON PATH <path> TO <devno range>
-VARY OFF PATH <PATH> FROM <devno range>
-This is used to switch on or off channel paths to devices.
-
-Q CHPID <channel path ID>
-This displays state of devices using this channel path
-D SCHIB <subchannel>
-This displays the subchannel information SCHIB block for the device.
-this I believe is also only available to administrators.
-DEFINE CTC <devno>
-defines a virtual CTC channel to channel connection
-2 need to be defined on each guest for the CTC driver to use.
-COUPLE devno userid remote devno
-Joins a local virtual device to a remote virtual device
-( commonly used for the CTC driver ).
-
-Building a VM ramdisk under CMS which linux can use
-def vfb-<blocksize> <subchannel> <number blocks>
-blocksize is commonly 4096 for linux.
-Formatting it
-format <subchannel> <driver letter e.g. x> (blksize <blocksize>
-
-Sharing a disk between multiple guests
-LINK userid devno1 devno2 mode password
-
-
-
-GDB on S390
-===========
-N.B. if compiling for debugging gdb works better without optimisation
-( see Compiling programs for debugging )
-
-invocation
-----------
-gdb <victim program> <optional corefile>
-
-Online help
------------
-help: gives help on commands
-e.g.
-help
-help display
-Note gdb's online help is very good use it.
-
-
-Assembly
---------
-info registers: displays registers other than floating point.
-info all-registers: displays floating points as well.
-disassemble: disassembles
-e.g.
-disassemble without parameters will disassemble the current function
-disassemble $pc $pc+10
-
-Viewing & modifying variables
------------------------------
-print or p: displays variable or register
-e.g. p/x $sp will display the stack pointer
-
-display: prints variable or register each time program stops
-e.g.
-display/x $pc will display the program counter
-display argc
-
-undisplay : undo's display's
-
-info breakpoints: shows all current breakpoints
-
-info stack: shows stack back trace (if this doesn't work too well, I'll show
-you the stacktrace by hand below).
-
-info locals: displays local variables.
-
-info args: display current procedure arguments.
-
-set args: will set argc & argv each time the victim program is invoked.
-
-set <variable>=value
-set argc=100
-set $pc=0
-
-
-
-Modifying execution
--------------------
-step: steps n lines of sourcecode
-step steps 1 line.
-step 100 steps 100 lines of code.
-
-next: like step except this will not step into subroutines
-
-stepi: steps a single machine code instruction.
-e.g. stepi 100
-
-nexti: steps a single machine code instruction but will not step into
-subroutines.
-
-finish: will run until exit of the current routine
-
-run: (re)starts a program
-
-cont: continues a program
-
-quit: exits gdb.
-
-
-breakpoints
-------------
-
-break
-sets a breakpoint
-e.g.
-
-break main
-
-break *$pc
-
-break *0x400618
-
-Here's a really useful one for large programs
-rbr
-Set a breakpoint for all functions matching REGEXP
-e.g.
-rbr 390
-will set a breakpoint with all functions with 390 in their name.
-
-info breakpoints
-lists all breakpoints
-
-delete: delete breakpoint by number or delete them all
-e.g.
-delete 1 will delete the first breakpoint
-delete will delete them all
-
-watch: This will set a watchpoint ( usually hardware assisted ),
-This will watch a variable till it changes
-e.g.
-watch cnt, will watch the variable cnt till it changes.
-As an aside unfortunately gdb's, architecture independent watchpoint code
-is inconsistent & not very good, watchpoints usually work but not always.
-
-info watchpoints: Display currently active watchpoints
-
-condition: ( another useful one )
-Specify breakpoint number N to break only if COND is true.
-Usage is `condition N COND', where N is an integer and COND is an
-expression to be evaluated whenever breakpoint N is reached.
-
-
-
-User defined functions/macros
------------------------------
-define: ( Note this is very very useful,simple & powerful )
-usage define <name> <list of commands> end
-
-examples which you should consider putting into .gdbinit in your home directory
-define d
-stepi
-disassemble $pc $pc+10
-end
-
-define e
-nexti
-disassemble $pc $pc+10
-end
-
-
-Other hard to classify stuff
-----------------------------
-signal n:
-sends the victim program a signal.
-e.g. signal 3 will send a SIGQUIT.
-
-info signals:
-what gdb does when the victim receives certain signals.
-
-list:
-e.g.
-list lists current function source
-list 1,10 list first 10 lines of current file.
-list test.c:1,10
-
-
-directory:
-Adds directories to be searched for source if gdb cannot find the source.
-(note it is a bit sensitive about slashes)
-e.g. To add the root of the filesystem to the searchpath do
-directory //
-
-
-call <function>
-This calls a function in the victim program, this is pretty powerful
-e.g.
-(gdb) call printf("hello world")
-outputs:
-$1 = 11
-
-You might now be thinking that the line above didn't work, something extra had
-to be done.
-(gdb) call fflush(stdout)
-hello world$2 = 0
-As an aside the debugger also calls malloc & free under the hood
-to make space for the "hello world" string.
-
-
-
-hints
------
-1) command completion works just like bash
-( if you are a bad typist like me this really helps )
-e.g. hit br <TAB> & cursor up & down :-).
-
-2) if you have a debugging problem that takes a few steps to recreate
-put the steps into a file called .gdbinit in your current working directory
-if you have defined a few extra useful user defined commands put these in
-your home directory & they will be read each time gdb is launched.
-
-A typical .gdbinit file might be.
-break main
-run
-break runtime_exception
-cont
-
-
-stack chaining in gdb by hand
------------------------------
-This is done using a the same trick described for VM
-p/x (*($sp+56))&0x7fffffff get the first backchain.
-
-For z/Architecture
-Replace 56 with 112 & ignore the &0x7fffffff
-in the macros below & do nasty casts to longs like the following
-as gdb unfortunately deals with printed arguments as ints which
-messes up everything.
-i.e. here is a 3rd backchain dereference
-p/x *(long *)(***(long ***)$sp+112)
-
-
-this outputs
-$5 = 0x528f18
-on my machine.
-Now you can use
-info symbol (*($sp+56))&0x7fffffff
-you might see something like.
-rl_getc + 36 in section .text telling you what is located at address 0x528f18
-Now do.
-p/x (*(*$sp+56))&0x7fffffff
-This outputs
-$6 = 0x528ed0
-Now do.
-info symbol (*(*$sp+56))&0x7fffffff
-rl_read_key + 180 in section .text
-now do
-p/x (*(**$sp+56))&0x7fffffff
-& so on.
-
-Disassembling instructions without debug info
----------------------------------------------
-gdb typically complains if there is a lack of debugging
-symbols in the disassemble command with
-"No function contains specified address." To get around
-this do
-x/<number lines to disassemble>xi <address>
-e.g.
-x/20xi 0x400730
-
-
-
-Note: Remember gdb has history just like bash you don't need to retype the
-whole line just use the up & down arrows.
-
-
-
-For more info
--------------
-From your linuxbox do
-man gdb or info gdb.
-
-core dumps
-----------
-What a core dump ?,
-A core dump is a file generated by the kernel (if allowed) which contains the
-registers and all active pages of the program which has crashed.
-From this file gdb will allow you to look at the registers, stack trace and
-memory of the program as if it just crashed on your system. It is usually
-called core and created in the current working directory.
-This is very useful in that a customer can mail a core dump to a technical
-support department and the technical support department can reconstruct what
-happened. Provided they have an identical copy of this program with debugging
-symbols compiled in and the source base of this build is available.
-In short it is far more useful than something like a crash log could ever hope
-to be.
-
-Why have I never seen one ?.
-Probably because you haven't used the command
-ulimit -c unlimited in bash
-to allow core dumps, now do
-ulimit -a
-to verify that the limit was accepted.
-
-A sample core dump
-To create this I'm going to do
-ulimit -c unlimited
-gdb
-to launch gdb (my victim app. ) now be bad & do the following from another
-telnet/xterm session to the same machine
-ps -aux | grep gdb
-kill -SIGSEGV <gdb's pid>
-or alternatively use killall -SIGSEGV gdb if you have the killall command.
-Now look at the core dump.
-./gdb core
-Displays the following
-GNU gdb 4.18
-Copyright 1998 Free Software Foundation, Inc.
-GDB is free software, covered by the GNU General Public License, and you are
-welcome to change it and/or distribute copies of it under certain conditions.
-Type "show copying" to see the conditions.
-There is absolutely no warranty for GDB. Type "show warranty" for details.
-This GDB was configured as "s390-ibm-linux"...
-Core was generated by `./gdb'.
-Program terminated with signal 11, Segmentation fault.
-Reading symbols from /usr/lib/libncurses.so.4...done.
-Reading symbols from /lib/libm.so.6...done.
-Reading symbols from /lib/libc.so.6...done.
-Reading symbols from /lib/ld-linux.so.2...done.
-#0 0x40126d1a in read () from /lib/libc.so.6
-Setting up the environment for debugging gdb.
-Breakpoint 1 at 0x4dc6f8: file utils.c, line 471.
-Breakpoint 2 at 0x4d87a4: file top.c, line 2609.
-(top-gdb) info stack
-#0 0x40126d1a in read () from /lib/libc.so.6
-#1 0x528f26 in rl_getc (stream=0x7ffffde8) at input.c:402
-#2 0x528ed0 in rl_read_key () at input.c:381
-#3 0x5167e6 in readline_internal_char () at readline.c:454
-#4 0x5168ee in readline_internal_charloop () at readline.c:507
-#5 0x51692c in readline_internal () at readline.c:521
-#6 0x5164fe in readline (prompt=0x7ffff810)
- at readline.c:349
-#7 0x4d7a8a in command_line_input (prompt=0x564420 "(gdb) ", repeat=1,
- annotation_suffix=0x4d6b44 "prompt") at top.c:2091
-#8 0x4d6cf0 in command_loop () at top.c:1345
-#9 0x4e25bc in main (argc=1, argv=0x7ffffdf4) at main.c:635
-
-
-LDD
-===
-This is a program which lists the shared libraries which a library needs,
-Note you also get the relocations of the shared library text segments which
-help when using objdump --source.
-e.g.
- ldd ./gdb
-outputs
-libncurses.so.4 => /usr/lib/libncurses.so.4 (0x40018000)
-libm.so.6 => /lib/libm.so.6 (0x4005e000)
-libc.so.6 => /lib/libc.so.6 (0x40084000)
-/lib/ld-linux.so.2 => /lib/ld-linux.so.2 (0x40000000)
-
-
-Debugging shared libraries
-==========================
-Most programs use shared libraries, however it can be very painful
-when you single step instruction into a function like printf for the
-first time & you end up in functions like _dl_runtime_resolve this is
-the ld.so doing lazy binding, lazy binding is a concept in ELF where
-shared library functions are not loaded into memory unless they are
-actually used, great for saving memory but a pain to debug.
-To get around this either relink the program -static or exit gdb type
-export LD_BIND_NOW=true this will stop lazy binding & restart the gdb'ing
-the program in question.
-
-
-
-Debugging modules
-=================
-As modules are dynamically loaded into the kernel their address can be
-anywhere to get around this use the -m option with insmod to emit a load
-map which can be piped into a file if required.
-
-The proc file system
-====================
-What is it ?.
-It is a filesystem created by the kernel with files which are created on demand
-by the kernel if read, or can be used to modify kernel parameters,
-it is a powerful concept.
-
-e.g.
-
-cat /proc/sys/net/ipv4/ip_forward
-On my machine outputs
-0
-telling me ip_forwarding is not on to switch it on I can do
-echo 1 > /proc/sys/net/ipv4/ip_forward
-cat it again
-cat /proc/sys/net/ipv4/ip_forward
-On my machine now outputs
-1
-IP forwarding is on.
-There is a lot of useful info in here best found by going in and having a look
-around, so I'll take you through some entries I consider important.
-
-All the processes running on the machine have their own entry defined by
-/proc/<pid>
-So lets have a look at the init process
-cd /proc/1
-
-cat cmdline
-emits
-init [2]
-
-cd /proc/1/fd
-This contains numerical entries of all the open files,
-some of these you can cat e.g. stdout (2)
-
-cat /proc/29/maps
-on my machine emits
-
-00400000-00478000 r-xp 00000000 5f:00 4103 /bin/bash
-00478000-0047e000 rw-p 00077000 5f:00 4103 /bin/bash
-0047e000-00492000 rwxp 00000000 00:00 0
-40000000-40015000 r-xp 00000000 5f:00 14382 /lib/ld-2.1.2.so
-40015000-40016000 rw-p 00014000 5f:00 14382 /lib/ld-2.1.2.so
-40016000-40017000 rwxp 00000000 00:00 0
-40017000-40018000 rw-p 00000000 00:00 0
-40018000-4001b000 r-xp 00000000 5f:00 14435 /lib/libtermcap.so.2.0.8
-4001b000-4001c000 rw-p 00002000 5f:00 14435 /lib/libtermcap.so.2.0.8
-4001c000-4010d000 r-xp 00000000 5f:00 14387 /lib/libc-2.1.2.so
-4010d000-40111000 rw-p 000f0000 5f:00 14387 /lib/libc-2.1.2.so
-40111000-40114000 rw-p 00000000 00:00 0
-40114000-4011e000 r-xp 00000000 5f:00 14408 /lib/libnss_files-2.1.2.so
-4011e000-4011f000 rw-p 00009000 5f:00 14408 /lib/libnss_files-2.1.2.so
-7fffd000-80000000 rwxp ffffe000 00:00 0
-
-
-Showing us the shared libraries init uses where they are in memory
-& memory access permissions for each virtual memory area.
-
-/proc/1/cwd is a softlink to the current working directory.
-/proc/1/root is the root of the filesystem for this process.
-
-/proc/1/mem is the current running processes memory which you
-can read & write to like a file.
-strace uses this sometimes as it is a bit faster than the
-rather inefficient ptrace interface for peeking at DATA.
-
-
-cat status
-
-Name: init
-State: S (sleeping)
-Pid: 1
-PPid: 0
-Uid: 0 0 0 0
-Gid: 0 0 0 0
-Groups:
-VmSize: 408 kB
-VmLck: 0 kB
-VmRSS: 208 kB
-VmData: 24 kB
-VmStk: 8 kB
-VmExe: 368 kB
-VmLib: 0 kB
-SigPnd: 0000000000000000
-SigBlk: 0000000000000000
-SigIgn: 7fffffffd7f0d8fc
-SigCgt: 00000000280b2603
-CapInh: 00000000fffffeff
-CapPrm: 00000000ffffffff
-CapEff: 00000000fffffeff
-
-User PSW: 070de000 80414146
-task: 004b6000 tss: 004b62d8 ksp: 004b7ca8 pt_regs: 004b7f68
-User GPRS:
-00000400 00000000 0000000b 7ffffa90
-00000000 00000000 00000000 0045d9f4
-0045cafc 7ffffa90 7fffff18 0045cb08
-00010400 804039e8 80403af8 7ffff8b0
-User ACRS:
-00000000 00000000 00000000 00000000
-00000001 00000000 00000000 00000000
-00000000 00000000 00000000 00000000
-00000000 00000000 00000000 00000000
-Kernel BackChain CallChain BackChain CallChain
- 004b7ca8 8002bd0c 004b7d18 8002b92c
- 004b7db8 8005cd50 004b7e38 8005d12a
- 004b7f08 80019114
-Showing among other things memory usage & status of some signals &
-the processes'es registers from the kernel task_structure
-as well as a backchain which may be useful if a process crashes
-in the kernel for some unknown reason.
-
-Some driver debugging techniques
-================================
-debug feature
--------------
-Some of our drivers now support a "debug feature" in
-/proc/s390dbf see s390dbf.txt in the linux/Documentation directory
-for more info.
-e.g.
-to switch on the lcs "debug feature"
-echo 5 > /proc/s390dbf/lcs/level
-& then after the error occurred.
-cat /proc/s390dbf/lcs/sprintf >/logfile
-the logfile now contains some information which may help
-tech support resolve a problem in the field.
-
-
-
-high level debugging network drivers
-------------------------------------
-ifconfig is a quite useful command
-it gives the current state of network drivers.
-
-If you suspect your network device driver is dead
-one way to check is type
-ifconfig <network device>
-e.g. tr0
-You should see something like
-tr0 Link encap:16/4 Mbps Token Ring (New) HWaddr 00:04:AC:20:8E:48
- inet addr:9.164.185.132 Bcast:9.164.191.255 Mask:255.255.224.0
- UP BROADCAST RUNNING MULTICAST MTU:2000 Metric:1
- RX packets:246134 errors:0 dropped:0 overruns:0 frame:0
- TX packets:5 errors:0 dropped:0 overruns:0 carrier:0
- collisions:0 txqueuelen:100
-
-if the device doesn't say up
-try
-/etc/rc.d/init.d/network start
-( this starts the network stack & hopefully calls ifconfig tr0 up ).
-ifconfig looks at the output of /proc/net/dev and presents it in a more
-presentable form.
-Now ping the device from a machine in the same subnet.
-if the RX packets count & TX packets counts don't increment you probably
-have problems.
-next
-cat /proc/net/arp
-Do you see any hardware addresses in the cache if not you may have problems.
-Next try
-ping -c 5 <broadcast_addr> i.e. the Bcast field above in the output of
-ifconfig. Do you see any replies from machines other than the local machine
-if not you may have problems. also if the TX packets count in ifconfig
-hasn't incremented either you have serious problems in your driver
-(e.g. the txbusy field of the network device being stuck on )
-or you may have multiple network devices connected.
-
-
-chandev
--------
-There is a new device layer for channel devices, some
-drivers e.g. lcs are registered with this layer.
-If the device uses the channel device layer you'll be
-able to find what interrupts it uses & the current state
-of the device.
-See the manpage chandev.8 &type cat /proc/chandev for more info.
-
-
-SysRq
-=====
-This is now supported by linux for s/390 & z/Architecture.
-To enable it do compile the kernel with
-Kernel Hacking -> Magic SysRq Key Enabled
-echo "1" > /proc/sys/kernel/sysrq
-also type
-echo "8" >/proc/sys/kernel/printk
-To make printk output go to console.
-On 390 all commands are prefixed with
-^-
-e.g.
-^-t will show tasks.
-^-? or some unknown command will display help.
-The sysrq key reading is very picky ( I have to type the keys in an
- xterm session & paste them into the x3270 console )
-& it may be wise to predefine the keys as described in the VM hints above
-
-This is particularly useful for syncing disks unmounting & rebooting
-if the machine gets partially hung.
-
-Read Documentation/admin-guide/sysrq.rst for more info
-
-References:
-===========
-Enterprise Systems Architecture Reference Summary
-Enterprise Systems Architecture Principles of Operation
-Hartmut Penners s390 stack frame sheet.
-IBM Mainframe Channel Attachment a technology brief from a CISCO webpage
-Various bits of man & info pages of Linux.
-Linux & GDB source.
-Various info & man pages.
-CMS Help on tracing commands.
-Linux for s/390 Elf Application Binary Interface
-Linux for z/Series Elf Application Binary Interface ( Both Highly Recommended )
-z/Architecture Principles of Operation SA22-7832-00
-Enterprise Systems Architecture/390 Reference Summary SA22-7209-01 & the
-Enterprise Systems Architecture/390 Principles of Operation SA22-7201-05
-
-Special Thanks
-==============
-Special thanks to Neale Ferguson who maintains a much
-prettier HTML version of this page at
-http://linuxvm.org/penguinvm/
-Bob Grainger Stefan Bader & others for reporting bugs
diff --git a/Documentation/s390/cds.txt b/Documentation/s390/cds.rst
index 480a78ef5a1e..7006d8209d2e 100644
--- a/Documentation/s390/cds.txt
+++ b/Documentation/s390/cds.rst
@@ -1,14 +1,18 @@
+===========================
Linux for S/390 and zSeries
+===========================
Common Device Support (CDS)
Device Driver I/O Support Routines
-Authors : Ingo Adlung
- Cornelia Huck
+Authors:
+ - Ingo Adlung
+ - Cornelia Huck
Copyright, IBM Corp. 1999-2002
Introduction
+============
This document describes the common device support routines for Linux/390.
Different than other hardware architectures, ESA/390 has defined a unified
@@ -27,18 +31,20 @@ Operation manual (IBM Form. No. SA22-7201).
In order to build common device support for ESA/390 I/O interfaces, a
functional layer was introduced that provides generic I/O access methods to
-the hardware.
+the hardware.
-The common device support layer comprises the I/O support routines defined
-below. Some of them implement common Linux device driver interfaces, while
+The common device support layer comprises the I/O support routines defined
+below. Some of them implement common Linux device driver interfaces, while
some of them are ESA/390 platform specific.
Note:
-In order to write a driver for S/390, you also need to look into the interface
-described in Documentation/s390/driver-model.txt.
+ In order to write a driver for S/390, you also need to look into the interface
+ described in Documentation/s390/driver-model.rst.
Note for porting drivers from 2.4:
+
The major changes are:
+
* The functions use a ccw_device instead of an irq (subchannel).
* All drivers must define a ccw_driver (see driver-model.txt) and the associated
functions.
@@ -57,19 +63,16 @@ The major changes are:
ccw_device_get_ciw()
get commands from extended sense data.
-ccw_device_start()
-ccw_device_start_timeout()
-ccw_device_start_key()
-ccw_device_start_key_timeout()
+ccw_device_start(), ccw_device_start_timeout(), ccw_device_start_key(), ccw_device_start_key_timeout()
initiate an I/O request.
ccw_device_resume()
resume channel program execution.
-ccw_device_halt()
+ccw_device_halt()
terminate the current I/O request processed on the device.
-do_IRQ()
+do_IRQ()
generic interrupt routine. This function is called by the interrupt entry
routine whenever an I/O interrupt is presented to the system. The do_IRQ()
routine determines the interrupt status and calls the device specific
@@ -82,12 +85,15 @@ first level interrupt handler only and does not comprise a device driver
callable interface. Instead, the functional description of do_IO() also
describes the input to the device specific interrupt handler.
-Note: All explanations apply also to the 64 bit architecture s390x.
+Note:
+ All explanations apply also to the 64 bit architecture s390x.
Common Device Support (CDS) for Linux/390 Device Drivers
+========================================================
General Information
+-------------------
The following chapters describe the I/O related interface routines the
Linux/390 common device support (CDS) provides to allow for device specific
@@ -101,6 +107,7 @@ can be found in the architecture specific C header file
linux/arch/s390/include/asm/irq.h.
Overview of CDS interface concepts
+----------------------------------
Different to other hardware platforms, the ESA/390 architecture doesn't define
interrupt lines managed by a specific interrupt controller and bus systems
@@ -126,7 +133,7 @@ has to call every single device driver registered on this IRQ in order to
determine the device driver owning the device that raised the interrupt.
Up to kernel 2.4, Linux/390 used to provide interfaces via the IRQ (subchannel).
-For internal use of the common I/O layer, these are still there. However,
+For internal use of the common I/O layer, these are still there. However,
device drivers should use the new calling interface via the ccw_device only.
During its startup the Linux/390 system checks for peripheral devices. Each
@@ -134,7 +141,7 @@ of those devices is uniquely defined by a so called subchannel by the ESA/390
channel subsystem. While the subchannel numbers are system generated, each
subchannel also takes a user defined attribute, the so called device number.
Both subchannel number and device number cannot exceed 65535. During sysfs
-initialisation, the information about control unit type and device types that
+initialisation, the information about control unit type and device types that
imply specific I/O commands (channel command words - CCWs) in order to operate
the device are gathered. Device drivers can retrieve this set of hardware
information during their initialization step to recognize the devices they
@@ -164,18 +171,26 @@ get_ciw() - get command information word
This call enables a device driver to get information about supported commands
from the extended SenseID data.
-struct ciw *
-ccw_device_get_ciw(struct ccw_device *cdev, __u32 cmd);
+::
-cdev - The ccw_device for which the command is to be retrieved.
-cmd - The command type to be retrieved.
+ struct ciw *
+ ccw_device_get_ciw(struct ccw_device *cdev, __u32 cmd);
+
+==== ========================================================
+cdev The ccw_device for which the command is to be retrieved.
+cmd The command type to be retrieved.
+==== ========================================================
ccw_device_get_ciw() returns:
-NULL - No extended data available, invalid device or command not found.
-!NULL - The command requested.
+===== ================================================================
+ NULL No extended data available, invalid device or command not found.
+!NULL The command requested.
+===== ================================================================
+
+::
-ccw_device_start() - Initiate I/O Request
+ ccw_device_start() - Initiate I/O Request
The ccw_device_start() routines is the I/O request front-end processor. All
device driver I/O requests must be issued using this routine. A device driver
@@ -186,93 +201,105 @@ This description also covers the status information passed to the device
driver's interrupt handler as this is related to the rules (flags) defined
with the associated I/O request when calling ccw_device_start().
-int ccw_device_start(struct ccw_device *cdev,
- struct ccw1 *cpa,
- unsigned long intparm,
- __u8 lpm,
- unsigned long flags);
-int ccw_device_start_timeout(struct ccw_device *cdev,
- struct ccw1 *cpa,
- unsigned long intparm,
- __u8 lpm,
- unsigned long flags,
- int expires);
-int ccw_device_start_key(struct ccw_device *cdev,
- struct ccw1 *cpa,
- unsigned long intparm,
- __u8 lpm,
- __u8 key,
- unsigned long flags);
-int ccw_device_start_key_timeout(struct ccw_device *cdev,
- struct ccw1 *cpa,
- unsigned long intparm,
- __u8 lpm,
- __u8 key,
- unsigned long flags,
- int expires);
-
-cdev : ccw_device the I/O is destined for
-cpa : logical start address of channel program
-user_intparm : user specific interrupt information; will be presented
- back to the device driver's interrupt handler. Allows a
- device driver to associate the interrupt with a
- particular I/O request.
-lpm : defines the channel path to be used for a specific I/O
- request. A value of 0 will make cio use the opm.
-key : the storage key to use for the I/O (useful for operating on a
- storage with a storage key != default key)
-flag : defines the action to be performed for I/O processing
-expires : timeout value in jiffies. The common I/O layer will terminate
- the running program after this and call the interrupt handler
- with ERR_PTR(-ETIMEDOUT) as irb.
-
-Possible flag values are :
-
-DOIO_ALLOW_SUSPEND - channel program may become suspended
-DOIO_DENY_PREFETCH - don't allow for CCW prefetch; usually
- this implies the channel program might
- become modified
-DOIO_SUPPRESS_INTER - don't call the handler on intermediate status
-
-The cpa parameter points to the first format 1 CCW of a channel program :
-
-struct ccw1 {
- __u8 cmd_code;/* command code */
- __u8 flags; /* flags, like IDA addressing, etc. */
- __u16 count; /* byte count */
- __u32 cda; /* data address */
-} __attribute__ ((packed,aligned(8)));
-
-with the following CCW flags values defined :
-
-CCW_FLAG_DC - data chaining
-CCW_FLAG_CC - command chaining
-CCW_FLAG_SLI - suppress incorrect length
-CCW_FLAG_SKIP - skip
-CCW_FLAG_PCI - PCI
-CCW_FLAG_IDA - indirect addressing
-CCW_FLAG_SUSPEND - suspend
+::
+
+ int ccw_device_start(struct ccw_device *cdev,
+ struct ccw1 *cpa,
+ unsigned long intparm,
+ __u8 lpm,
+ unsigned long flags);
+ int ccw_device_start_timeout(struct ccw_device *cdev,
+ struct ccw1 *cpa,
+ unsigned long intparm,
+ __u8 lpm,
+ unsigned long flags,
+ int expires);
+ int ccw_device_start_key(struct ccw_device *cdev,
+ struct ccw1 *cpa,
+ unsigned long intparm,
+ __u8 lpm,
+ __u8 key,
+ unsigned long flags);
+ int ccw_device_start_key_timeout(struct ccw_device *cdev,
+ struct ccw1 *cpa,
+ unsigned long intparm,
+ __u8 lpm,
+ __u8 key,
+ unsigned long flags,
+ int expires);
+
+============= =============================================================
+cdev ccw_device the I/O is destined for
+cpa logical start address of channel program
+user_intparm user specific interrupt information; will be presented
+ back to the device driver's interrupt handler. Allows a
+ device driver to associate the interrupt with a
+ particular I/O request.
+lpm defines the channel path to be used for a specific I/O
+ request. A value of 0 will make cio use the opm.
+key the storage key to use for the I/O (useful for operating on a
+ storage with a storage key != default key)
+flag defines the action to be performed for I/O processing
+expires timeout value in jiffies. The common I/O layer will terminate
+ the running program after this and call the interrupt handler
+ with ERR_PTR(-ETIMEDOUT) as irb.
+============= =============================================================
+
+Possible flag values are:
+
+========================= =============================================
+DOIO_ALLOW_SUSPEND channel program may become suspended
+DOIO_DENY_PREFETCH don't allow for CCW prefetch; usually
+ this implies the channel program might
+ become modified
+DOIO_SUPPRESS_INTER don't call the handler on intermediate status
+========================= =============================================
+
+The cpa parameter points to the first format 1 CCW of a channel program::
+
+ struct ccw1 {
+ __u8 cmd_code;/* command code */
+ __u8 flags; /* flags, like IDA addressing, etc. */
+ __u16 count; /* byte count */
+ __u32 cda; /* data address */
+ } __attribute__ ((packed,aligned(8)));
+
+with the following CCW flags values defined:
+
+=================== =========================
+CCW_FLAG_DC data chaining
+CCW_FLAG_CC command chaining
+CCW_FLAG_SLI suppress incorrect length
+CCW_FLAG_SKIP skip
+CCW_FLAG_PCI PCI
+CCW_FLAG_IDA indirect addressing
+CCW_FLAG_SUSPEND suspend
+=================== =========================
Via ccw_device_set_options(), the device driver may specify the following
options for the device:
-DOIO_EARLY_NOTIFICATION - allow for early interrupt notification
-DOIO_REPORT_ALL - report all interrupt conditions
+========================= ======================================
+DOIO_EARLY_NOTIFICATION allow for early interrupt notification
+DOIO_REPORT_ALL report all interrupt conditions
+========================= ======================================
-The ccw_device_start() function returns :
+The ccw_device_start() function returns:
- 0 - successful completion or request successfully initiated
--EBUSY - The device is currently processing a previous I/O request, or there is
- a status pending at the device.
--ENODEV - cdev is invalid, the device is not operational or the ccw_device is
- not online.
+======== ======================================================================
+ 0 successful completion or request successfully initiated
+ -EBUSY The device is currently processing a previous I/O request, or there is
+ a status pending at the device.
+-ENODEV cdev is invalid, the device is not operational or the ccw_device is
+ not online.
+======== ======================================================================
When the I/O request completes, the CDS first level interrupt handler will
accumulate the status in a struct irb and then call the device interrupt handler.
-The intparm field will contain the value the device driver has associated with a
-particular I/O request. If a pending device status was recognized,
+The intparm field will contain the value the device driver has associated with a
+particular I/O request. If a pending device status was recognized,
intparm will be set to 0 (zero). This may happen during I/O initiation or delayed
by an alert status notification. In any case this status is not related to the
current (last) I/O request. In case of a delayed status notification no special
@@ -282,9 +309,11 @@ never started, even though ccw_device_start() returned with successful completio
The irb may contain an error value, and the device driver should check for this
first:
--ETIMEDOUT: the common I/O layer terminated the request after the specified
- timeout value
--EIO: the common I/O layer terminated the request due to an error state
+========== =================================================================
+-ETIMEDOUT the common I/O layer terminated the request after the specified
+ timeout value
+-EIO the common I/O layer terminated the request due to an error state
+========== =================================================================
If the concurrent sense flag in the extended status word (esw) in the irb is
set, the field erw.scnt in the esw describes the number of device specific
@@ -294,6 +323,7 @@ sensing by the device driver itself is required.
The device interrupt handler can use the following definitions to investigate
the primary unit check source coded in sense byte 0 :
+======================= ====
SNS0_CMD_REJECT 0x80
SNS0_INTERVENTION_REQ 0x40
SNS0_BUS_OUT_CHECK 0x20
@@ -301,36 +331,41 @@ SNS0_EQUIPMENT_CHECK 0x10
SNS0_DATA_CHECK 0x08
SNS0_OVERRUN 0x04
SNS0_INCOMPL_DOMAIN 0x01
+======================= ====
Depending on the device status, multiple of those values may be set together.
Please refer to the device specific documentation for details.
The irb->scsw.cstat field provides the (accumulated) subchannel status :
-SCHN_STAT_PCI - program controlled interrupt
-SCHN_STAT_INCORR_LEN - incorrect length
-SCHN_STAT_PROG_CHECK - program check
-SCHN_STAT_PROT_CHECK - protection check
-SCHN_STAT_CHN_DATA_CHK - channel data check
-SCHN_STAT_CHN_CTRL_CHK - channel control check
-SCHN_STAT_INTF_CTRL_CHK - interface control check
-SCHN_STAT_CHAIN_CHECK - chaining check
+========================= ============================
+SCHN_STAT_PCI program controlled interrupt
+SCHN_STAT_INCORR_LEN incorrect length
+SCHN_STAT_PROG_CHECK program check
+SCHN_STAT_PROT_CHECK protection check
+SCHN_STAT_CHN_DATA_CHK channel data check
+SCHN_STAT_CHN_CTRL_CHK channel control check
+SCHN_STAT_INTF_CTRL_CHK interface control check
+SCHN_STAT_CHAIN_CHECK chaining check
+========================= ============================
The irb->scsw.dstat field provides the (accumulated) device status :
-DEV_STAT_ATTENTION - attention
-DEV_STAT_STAT_MOD - status modifier
-DEV_STAT_CU_END - control unit end
-DEV_STAT_BUSY - busy
-DEV_STAT_CHN_END - channel end
-DEV_STAT_DEV_END - device end
-DEV_STAT_UNIT_CHECK - unit check
-DEV_STAT_UNIT_EXCEP - unit exception
+===================== =================
+DEV_STAT_ATTENTION attention
+DEV_STAT_STAT_MOD status modifier
+DEV_STAT_CU_END control unit end
+DEV_STAT_BUSY busy
+DEV_STAT_CHN_END channel end
+DEV_STAT_DEV_END device end
+DEV_STAT_UNIT_CHECK unit check
+DEV_STAT_UNIT_EXCEP unit exception
+===================== =================
Please see the ESA/390 Principles of Operation manual for details on the
individual flag meanings.
-Usage Notes :
+Usage Notes:
ccw_device_start() must be called disabled and with the ccw device lock held.
@@ -374,32 +409,39 @@ secondary status without error (alert status) is presented, this indicates
successful completion for all overlapping ccw_device_start() requests that have
been issued since the last secondary (final) status.
-Channel programs that intend to set the suspend flag on a channel command word
-(CCW) must start the I/O operation with the DOIO_ALLOW_SUSPEND option or the
-suspend flag will cause a channel program check. At the time the channel program
-becomes suspended an intermediate interrupt will be generated by the channel
+Channel programs that intend to set the suspend flag on a channel command word
+(CCW) must start the I/O operation with the DOIO_ALLOW_SUSPEND option or the
+suspend flag will cause a channel program check. At the time the channel program
+becomes suspended an intermediate interrupt will be generated by the channel
subsystem.
-ccw_device_resume() - Resume Channel Program Execution
+ccw_device_resume() - Resume Channel Program Execution
-If a device driver chooses to suspend the current channel program execution by
-setting the CCW suspend flag on a particular CCW, the channel program execution
-is suspended. In order to resume channel program execution the CIO layer
-provides the ccw_device_resume() routine.
+If a device driver chooses to suspend the current channel program execution by
+setting the CCW suspend flag on a particular CCW, the channel program execution
+is suspended. In order to resume channel program execution the CIO layer
+provides the ccw_device_resume() routine.
-int ccw_device_resume(struct ccw_device *cdev);
+::
-cdev - ccw_device the resume operation is requested for
+ int ccw_device_resume(struct ccw_device *cdev);
+
+==== ================================================
+cdev ccw_device the resume operation is requested for
+==== ================================================
The ccw_device_resume() function returns:
- 0 - suspended channel program is resumed
--EBUSY - status pending
--ENODEV - cdev invalid or not-operational subchannel
--EINVAL - resume function not applicable
--ENOTCONN - there is no I/O request pending for completion
+========= ==============================================
+ 0 suspended channel program is resumed
+ -EBUSY status pending
+ -ENODEV cdev invalid or not-operational subchannel
+ -EINVAL resume function not applicable
+-ENOTCONN there is no I/O request pending for completion
+========= ==============================================
Usage Notes:
+
Please have a look at the ccw_device_start() usage notes for more details on
suspended channel programs.
@@ -412,22 +454,28 @@ command is provided.
ccw_device_halt() must be called disabled and with the ccw device lock held.
-int ccw_device_halt(struct ccw_device *cdev,
- unsigned long intparm);
+::
+
+ int ccw_device_halt(struct ccw_device *cdev,
+ unsigned long intparm);
-cdev : ccw_device the halt operation is requested for
-intparm : interruption parameter; value is only used if no I/O
- is outstanding, otherwise the intparm associated with
- the I/O request is returned
+======= =====================================================
+cdev ccw_device the halt operation is requested for
+intparm interruption parameter; value is only used if no I/O
+ is outstanding, otherwise the intparm associated with
+ the I/O request is returned
+======= =====================================================
-The ccw_device_halt() function returns :
+The ccw_device_halt() function returns:
- 0 - request successfully initiated
--EBUSY - the device is currently busy, or status pending.
--ENODEV - cdev invalid.
--EINVAL - The device is not operational or the ccw device is not online.
+======= ==============================================================
+ 0 request successfully initiated
+-EBUSY the device is currently busy, or status pending.
+-ENODEV cdev invalid.
+-EINVAL The device is not operational or the ccw device is not online.
+======= ==============================================================
-Usage Notes :
+Usage Notes:
A device driver may write a never-ending channel program by writing a channel
program that at its end loops back to its beginning by means of a transfer in
@@ -438,25 +486,34 @@ can then perform an appropriate action. Prior to interrupt of an outstanding
read to a network device (with or without PCI flag) a ccw_device_halt()
is required to end the pending operation.
-ccw_device_clear() - Terminage I/O Request Processing
+::
+
+ ccw_device_clear() - Terminage I/O Request Processing
In order to terminate all I/O processing at the subchannel, the clear subchannel
(CSCH) command is used. It can be issued via ccw_device_clear().
ccw_device_clear() must be called disabled and with the ccw device lock held.
-int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm);
+::
+
+ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm);
-cdev: ccw_device the clear operation is requested for
-intparm: interruption parameter (see ccw_device_halt())
+======= ===============================================
+cdev ccw_device the clear operation is requested for
+intparm interruption parameter (see ccw_device_halt())
+======= ===============================================
The ccw_device_clear() function returns:
- 0 - request successfully initiated
--ENODEV - cdev invalid
--EINVAL - The device is not operational or the ccw device is not online.
+======= ==============================================================
+ 0 request successfully initiated
+-ENODEV cdev invalid
+-EINVAL The device is not operational or the ccw device is not online.
+======= ==============================================================
Miscellaneous Support Routines
+------------------------------
This chapter describes various routines to be used in a Linux/390 device
driver programming environment.
@@ -466,7 +523,8 @@ get_ccwdev_lock()
Get the address of the device specific lock. This is then used in
spin_lock() / spin_unlock() calls.
+::
-__u8 ccw_device_get_path_mask(struct ccw_device *cdev);
+ __u8 ccw_device_get_path_mask(struct ccw_device *cdev);
Get the mask of the path currently available for cdev.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/common_io.rst
index 6e0f63f343b4..846485681ce7 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/common_io.rst
@@ -1,5 +1,9 @@
-S/390 common I/O-Layer - command line parameters, procfs and debugfs entries
-============================================================================
+======================
+S/390 common I/O-Layer
+======================
+
+command line parameters, procfs and debugfs entries
+===================================================
Command line parameters
-----------------------
@@ -13,7 +17,7 @@ Command line parameters
device := {all | [!]ipldev | [!]condev | [!]<devno> | [!]<devno>-<devno>}
The given devices will be ignored by the common I/O-layer; no detection
- and device sensing will be done on any of those devices. The subchannel to
+ and device sensing will be done on any of those devices. The subchannel to
which the device in question is attached will be treated as if no device was
attached.
@@ -28,14 +32,20 @@ Command line parameters
keywords can be used to refer to the CCW based boot device and CCW console
device respectively (these are probably useful only when combined with the '!'
operator). The '!' operator will cause the I/O-layer to _not_ ignore a device.
- The command line is parsed from left to right.
+ The command line
+ is parsed from left to right.
+
+ For example::
- For example,
cio_ignore=0.0.0023-0.0.0042,0.0.4711
+
will ignore all devices ranging from 0.0.0023 to 0.0.0042 and the device
0.0.4711, if detected.
- As another example,
+
+ As another example::
+
cio_ignore=all,!0.0.4711,!0.0.fd00-0.0.fd02
+
will ignore all devices but 0.0.4711, 0.0.fd00, 0.0.fd01, 0.0.fd02.
By default, no devices are ignored.
@@ -48,40 +58,45 @@ Command line parameters
Lists the ranges of devices (by bus id) which are ignored by common I/O.
- You can un-ignore certain or all devices by piping to /proc/cio_ignore.
- "free all" will un-ignore all ignored devices,
+ You can un-ignore certain or all devices by piping to /proc/cio_ignore.
+ "free all" will un-ignore all ignored devices,
"free <device range>, <device range>, ..." will un-ignore the specified
devices.
For example, if devices 0.0.0023 to 0.0.0042 and 0.0.4711 are ignored,
+
- echo free 0.0.0030-0.0.0032 > /proc/cio_ignore
will un-ignore devices 0.0.0030 to 0.0.0032 and will leave devices 0.0.0023
to 0.0.002f, 0.0.0033 to 0.0.0042 and 0.0.4711 ignored;
- echo free 0.0.0041 > /proc/cio_ignore will furthermore un-ignore device
0.0.0041;
- - echo free all > /proc/cio_ignore will un-ignore all remaining ignored
+ - echo free all > /proc/cio_ignore will un-ignore all remaining ignored
devices.
- When a device is un-ignored, device recognition and sensing is performed and
+ When a device is un-ignored, device recognition and sensing is performed and
the device driver will be notified if possible, so the device will become
available to the system. Note that un-ignoring is performed asynchronously.
- You can also add ranges of devices to be ignored by piping to
+ You can also add ranges of devices to be ignored by piping to
/proc/cio_ignore; "add <device range>, <device range>, ..." will ignore the
specified devices.
Note: While already known devices can be added to the list of devices to be
- ignored, there will be no effect on then. However, if such a device
+ ignored, there will be no effect on then. However, if such a device
disappears and then reappears, it will then be ignored. To make
known devices go away, you need the "purge" command (see below).
- For example,
+ For example::
+
"echo add 0.0.a000-0.0.accc, 0.0.af00-0.0.afff > /proc/cio_ignore"
+
will add 0.0.a000-0.0.accc and 0.0.af00-0.0.afff to the list of ignored
devices.
- You can remove already known but now ignored devices via
+ You can remove already known but now ignored devices via::
+
"echo purge > /proc/cio_ignore"
+
All devices ignored but still registered and not online (= not in use)
will be deregistered and thus removed from the system.
@@ -115,11 +130,11 @@ debugfs entries
Various debug messages from the common I/O-layer.
- /sys/kernel/debug/s390dbf/cio_trace/hex_ascii
- Logs the calling of functions in the common I/O-layer and, if applicable,
+ Logs the calling of functions in the common I/O-layer and, if applicable,
which subchannel they were called for, as well as dumps of some data
structures (like irb in an error case).
- The level of logging can be changed to be more or less verbose by piping to
+ The level of logging can be changed to be more or less verbose by piping to
/sys/kernel/debug/s390dbf/cio_*/level a number between 0 and 6; see the
- documentation on the S/390 debug feature (Documentation/s390/s390dbf.txt)
+ documentation on the S/390 debug feature (Documentation/s390/s390dbf.rst)
for details.
diff --git a/Documentation/s390/DASD b/Documentation/s390/dasd.rst
index 9963f1e9c98a..9e22247285c8 100644
--- a/Documentation/s390/DASD
+++ b/Documentation/s390/dasd.rst
@@ -1,4 +1,6 @@
+==================
DASD device driver
+==================
S/390's disk devices (DASDs) are managed by Linux via the DASD device
driver. It is valid for all types of DASDs and represents them to
@@ -14,14 +16,14 @@ parameters are to be given in hexadecimal notation without a leading
If you supply kernel parameters the different instances are processed
in order of appearance and a minor number is reserved for any device
covered by the supplied range up to 64 volumes. Additional DASDs are
-ignored. If you do not supply the 'dasd=' kernel parameter at all, the
+ignored. If you do not supply the 'dasd=' kernel parameter at all, the
DASD driver registers all supported DASDs of your system to a minor
number in ascending order of the subchannel number.
The driver currently supports ECKD-devices and there are stubs for
support of the FBA and CKD architectures. For the FBA architecture
only some smart data structures are missing to make the support
-complete.
+complete.
We performed our testing on 3380 and 3390 type disks of different
sizes, under VM and on the bare hardware (LPAR), using internal disks
of the multiprise as well as a RAMAC virtual array. Disks exported by
@@ -34,19 +36,22 @@ accessibility of the DASD from other OSs. In a later stage we will
provide support of partitions, maybe VTOC oriented or using a kind of
partition table in the label record.
-USAGE
+Usage
+=====
-Low-level format (?CKD only)
For using an ECKD-DASD as a Linux harddisk you have to low-level
format the tracks by issuing the BLKDASDFORMAT-ioctl on that
device. This will erase any data on that volume including IBM volume
-labels, VTOCs etc. The ioctl may take a 'struct format_data *' or
-'NULL' as an argument.
-typedef struct {
+labels, VTOCs etc. The ioctl may take a `struct format_data *` or
+'NULL' as an argument::
+
+ typedef struct {
int start_unit;
int stop_unit;
int blksize;
-} format_data_t;
+ } format_data_t;
+
When a NULL argument is passed to the BLKDASDFORMAT ioctl the whole
disk is formatted to a blocksize of 1024 bytes. Otherwise start_unit
and stop_unit are the first and last track to be formatted. If
@@ -56,17 +61,23 @@ up to the last track. blksize can be any power of two between 512 and
1kB blocks anyway and you gain approx. 50% of capacity increasing your
blksize from 512 byte to 1kB.
--Make a filesystem
+Make a filesystem
+=================
+
Then you can mk??fs the filesystem of your choice on that volume or
partition. For reasons of sanity you should build your filesystem on
-the partition /dev/dd?1 instead of the whole volume. You only lose 3kB
+the partition /dev/dd?1 instead of the whole volume. You only lose 3kB
but may be sure that you can reuse your data after introduction of a
real partition table.
-BUGS:
+Bugs
+====
+
- Performance sometimes is rather low because we don't fully exploit clustering
-TODO-List:
+TODO-List
+=========
+
- Add IBM'S Disk layout to genhd
- Enhance driver to use more than one major number
- Enable usage as a module
diff --git a/Documentation/s390/debugging390.rst b/Documentation/s390/debugging390.rst
new file mode 100644
index 000000000000..d49305fd5e1a
--- /dev/null
+++ b/Documentation/s390/debugging390.rst
@@ -0,0 +1,2613 @@
+=============================================
+Debugging on Linux for s/390 & z/Architecture
+=============================================
+
+Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+
+Copyright (C) 2000-2001 IBM Deutschland Entwicklung GmbH, IBM Corporation
+
+.. Best viewed with fixed width fonts
+
+Overview of Document:
+=====================
+This document is intended to give a good overview of how to debug Linux for
+s/390 and z/Architecture. It is not intended as a complete reference and not a
+tutorial on the fundamentals of C & assembly. It doesn't go into
+390 IO in any detail. It is intended to complement the documents in the
+reference section below & any other worthwhile references you get.
+
+It is intended like the Enterprise Systems Architecture/390 Reference Summary
+to be printed out & used as a quick cheat sheet self help style reference when
+problems occur.
+
+.. Contents
+ ========
+ Register Set
+ Address Spaces on Intel Linux
+ Address Spaces on Linux for s/390 & z/Architecture
+ The Linux for s/390 & z/Architecture Kernel Task Structure
+ Register Usage & Stackframes on Linux for s/390 & z/Architecture
+ A sample program with comments
+ Compiling programs for debugging on Linux for s/390 & z/Architecture
+ Debugging under VM
+ s/390 & z/Architecture IO Overview
+ Debugging IO on s/390 & z/Architecture under VM
+ GDB on s/390 & z/Architecture
+ Stack chaining in gdb by hand
+ Examining core dumps
+ ldd
+ Debugging modules
+ The proc file system
+ SysRq
+ References
+ Special Thanks
+
+Register Set
+============
+The current architectures have the following registers.
+
+16 General propose registers, 32 bit on s/390 and 64 bit on z/Architecture,
+r0-r15 (or gpr0-gpr15), used for arithmetic and addressing.
+
+16 Control registers, 32 bit on s/390 and 64 bit on z/Architecture, cr0-cr15,
+kernel usage only, used for memory management, interrupt control, debugging
+control etc.
+
+16 Access registers (ar0-ar15), 32 bit on both s/390 and z/Architecture,
+normally not used by normal programs but potentially could be used as
+temporary storage. These registers have a 1:1 association with general
+purpose registers and are designed to be used in the so-called access
+register mode to select different address spaces.
+Access register 0 (and access register 1 on z/Architecture, which needs a
+64 bit pointer) is currently used by the pthread library as a pointer to
+the current running threads private area.
+
+16 64-bit floating point registers (fp0-fp15 ) IEEE & HFP floating
+point format compliant on G5 upwards & a Floating point control reg (FPC)
+
+4 64-bit registers (fp0,fp2,fp4 & fp6) HFP only on older machines.
+
+Note:
+ Linux (currently) always uses IEEE & emulates G5 IEEE format on older
+ machines, ( provided the kernel is configured for this ).
+
+
+The PSW is the most important register on the machine it
+is 64 bit on s/390 & 128 bit on z/Architecture & serves the roles of
+a program counter (pc), condition code register,memory space designator.
+In IBM standard notation I am counting bit 0 as the MSB.
+It has several advantages over a normal program counter
+in that you can change address translation & program counter
+in a single instruction. To change address translation,
+e.g. switching address translation off requires that you
+have a logical=physical mapping for the address you are
+currently running at.
+
++-------------------------+-------------------------------------------------+
+| Bit | |
++--------+----------------+ Value |
+| s/390 | z/Architecture | |
++========+================+=================================================+
+| 0 | 0 | Reserved (must be 0) otherwise specification |
+| | | exception occurs. |
++--------+----------------+-------------------------------------------------+
+| 1 | 1 | Program Event Recording 1 PER enabled, |
+| | | PER is used to facilitate debugging e.g. |
+| | | single stepping. |
++--------+----------------+-------------------------------------------------+
+| 2-4 | 2-4 | Reserved (must be 0). |
++--------+----------------+-------------------------------------------------+
+| 5 | 5 | Dynamic address translation 1=DAT on. |
++--------+----------------+-------------------------------------------------+
+| 6 | 6 | Input/Output interrupt Mask |
++--------+----------------+-------------------------------------------------+
+| 7 | 7 | External interrupt Mask used primarily for |
+| | | interprocessor signalling and clock interrupts. |
++--------+----------------+-------------------------------------------------+
+| 8-11 | 8-11 | PSW Key used for complex memory protection |
+| | | mechanism (not used under linux) |
++--------+----------------+-------------------------------------------------+
+| 12 | 12 | 1 on s/390 0 on z/Architecture |
++--------+----------------+-------------------------------------------------+
+| 13 | 13 | Machine Check Mask 1=enable machine check |
+| | | interrupts |
++--------+----------------+-------------------------------------------------+
+| 14 | 14 | Wait State. Set this to 1 to stop the processor |
+| | | except for interrupts and give time to other |
+| | | LPARS. Used in CPU idle in the kernel to |
+| | | increase overall usage of processor resources. |
++--------+----------------+-------------------------------------------------+
+| 15 | 15 | Problem state (if set to 1 certain instructions |
+| | | are disabled). All linux user programs run with |
+| | | this bit 1 (useful info for debugging under VM).|
++--------+----------------+-------------------------------------------------+
+| 16-17 | 16-17 | Address Space Control |
+| | | |
+| | | 00 Primary Space Mode: |
+| | | |
+| | | The register CR1 contains the primary |
+| | | address-space control element (PASCE), which |
+| | | points to the primary space region/segment |
+| | | table origin. |
+| | | |
+| | | 01 Access register mode |
+| | | |
+| | | 10 Secondary Space Mode: |
+| | | |
+| | | The register CR7 contains the secondary |
+| | | address-space control element (SASCE), which |
+| | | points to the secondary space region or |
+| | | segment table origin. |
+| | | |
+| | | 11 Home Space Mode: |
+| | | |
+| | | The register CR13 contains the home space |
+| | | address-space control element (HASCE), which |
+| | | points to the home space region/segment |
+| | | table origin. |
+| | | |
+| | | See "Address Spaces on Linux for s/390 & |
+| | | z/Architecture" below for more information |
+| | | about address space usage in Linux. |
++--------+----------------+-------------------------------------------------+
+| 18-19 | 18-19 | Condition codes (CC) |
++--------+----------------+-------------------------------------------------+
+| 20 | 20 | Fixed point overflow mask if 1=FPU exceptions |
+| | | for this event occur (normally 0) |
++--------+----------------+-------------------------------------------------+
+| 21 | 21 | Decimal overflow mask if 1=FPU exceptions for |
+| | | this event occur (normally 0) |
++--------+----------------+-------------------------------------------------+
+| 22 | 22 | Exponent underflow mask if 1=FPU exceptions |
+| | | for this event occur (normally 0) |
++--------+----------------+-------------------------------------------------+
+| 23 | 23 | Significance Mask if 1=FPU exceptions for this |
+| | | event occur (normally 0) |
++--------+----------------+-------------------------------------------------+
+| 24-31 | 24-30 | Reserved Must be 0. |
+| +----------------+-------------------------------------------------+
+| | 31 | Extended Addressing Mode |
+| +----------------+-------------------------------------------------+
+| | 32 | Basic Addressing Mode |
+| | | |
+| | | Used to set addressing mode |
+| | | |
+| | | +---------+----------+----------+ |
+| | | | PSW 31 | PSW 32 | | |
+| | | +---------+----------+----------+ |
+| | | | 0 | 0 | 24 bit | |
+| | | +---------+----------+----------+ |
+| | | | 0 | 1 | 31 bit | |
+| | | +---------+----------+----------+ |
+| | | | 1 | 1 | 64 bit | |
+| | | +---------+----------+----------+ |
++--------+----------------+-------------------------------------------------+
+| 32 | | 1=31 bit addressing mode 0=24 bit addressing |
+| | | mode (for backward compatibility), linux |
+| | | always runs with this bit set to 1 |
++--------+----------------+-------------------------------------------------+
+| 33-64 | | Instruction address. |
+| +----------------+-------------------------------------------------+
+| | 33-63 | Reserved must be 0 |
+| +----------------+-------------------------------------------------+
+| | 64-127 | Address |
+| | | |
+| | | - In 24 bits mode bits 64-103=0 bits 104-127 |
+| | | Address |
+| | | - In 31 bits mode bits 64-96=0 bits 97-127 |
+| | | Address |
+| | | |
+| | | Note: |
+| | | unlike 31 bit mode on s/390 bit 96 must be |
+| | | zero when loading the address with LPSWE |
+| | | otherwise a specification exception occurs, |
+| | | LPSW is fully backward compatible. |
++--------+----------------+-------------------------------------------------+
+
+Prefix Page(s)
+--------------
+This per cpu memory area is too intimately tied to the processor not to mention.
+It exists between the real addresses 0-4096 on s/390 and between 0-8192 on
+z/Architecture and is exchanged with one page on s/390 or two pages on
+z/Architecture in absolute storage by the set prefix instruction during Linux
+startup.
+
+This page is mapped to a different prefix for each processor in an SMP
+configuration (assuming the OS designer is sane of course).
+
+Bytes 0-512 (200 hex) on s/390 and 0-512, 4096-4544, 4604-5119 currently on
+z/Architecture are used by the processor itself for holding such information
+as exception indications and entry points for exceptions.
+
+Bytes after 0xc00 hex are used by linux for per processor globals on s/390 and
+z/Architecture (there is a gap on z/Architecture currently between 0xc00 and
+0x1000, too, which is used by Linux).
+
+The closest thing to this on traditional architectures is the interrupt
+vector table. This is a good thing & does simplify some of the kernel coding
+however it means that we now cannot catch stray NULL pointers in the
+kernel without hard coded checks.
+
+
+
+Address Spaces on Intel Linux
+=============================
+
+The traditional Intel Linux is approximately mapped as follows forgive
+the ascii art::
+
+ 0xFFFFFFFF 4GB Himem *****************
+ * *
+ * Kernel Space *
+ * *
+ ***************** ****************
+ User Space Himem * User Stack * * *
+ (typically 0xC0000000 3GB ) ***************** * *
+ * Shared Libs * * Next Process *
+ ***************** * to *
+ * * <== * Run * <==
+ * User Program * * *
+ * Data BSS * * *
+ * Text * * *
+ * Sections * * *
+ 0x00000000 ***************** ****************
+
+Now it is easy to see that on Intel it is quite easy to recognise a kernel
+address as being one greater than user space himem (in this case 0xC0000000),
+and addresses of less than this are the ones in the current running program on
+this processor (if an smp box).
+
+If using the virtual machine ( VM ) as a debugger it is quite difficult to
+know which user process is running as the address space you are looking at
+could be from any process in the run queue.
+
+The limitation of Intels addressing technique is that the linux
+kernel uses a very simple real address to virtual addressing technique
+of Real Address=Virtual Address-User Space Himem.
+This means that on Intel the kernel linux can typically only address
+Himem=0xFFFFFFFF-0xC0000000=1GB & this is all the RAM these machines
+can typically use.
+
+They can lower User Himem to 2GB or lower & thus be
+able to use 2GB of RAM however this shrinks the maximum size
+of User Space from 3GB to 2GB they have a no win limit of 4GB unless
+they go to 64 Bit.
+
+
+On 390 our limitations & strengths make us slightly different.
+For backward compatibility we are only allowed use 31 bits (2GB)
+of our 32 bit addresses, however, we use entirely separate address
+spaces for the user & kernel.
+
+This means we can support 2GB of non Extended RAM on s/390, & more
+with the Extended memory management swap device &
+currently 4TB of physical memory currently on z/Architecture.
+
+
+Address Spaces on Linux for s/390 & z/Architecture
+==================================================
+
+Our addressing scheme is basically as follows::
+
+ Primary Space Home Space
+ Himem 0x7fffffff 2GB on s/390 ***************** ****************
+ currently 0x3ffffffffff (2^42)-1 * User Stack * * *
+ on z/Architecture. ***************** * *
+ * Shared Libs * * *
+ ***************** * *
+ * * * Kernel *
+ * User Program * * *
+ * Data BSS * * *
+ * Text * * *
+ * Sections * * *
+ 0x00000000 ***************** ****************
+
+This also means that we need to look at the PSW problem state bit and the
+addressing mode to decide whether we are looking at user or kernel space.
+
+User space runs in primary address mode (or access register mode within
+the vdso code).
+
+The kernel usually also runs in home space mode, however when accessing
+user space the kernel switches to primary or secondary address mode if
+the mvcos instruction is not available or if a compare-and-swap (futex)
+instruction on a user space address is performed.
+
+When also looking at the ASCE control registers, this means:
+
+User space:
+
+- runs in primary or access register mode
+- cr1 contains the user asce
+- cr7 contains the user asce
+- cr13 contains the kernel asce
+
+Kernel space:
+
+- runs in home space mode
+- cr1 contains the user or kernel asce
+
+ - the kernel asce is loaded when a uaccess requires primary or
+ secondary address mode
+
+- cr7 contains the user or kernel asce, (changed with set_fs())
+- cr13 contains the kernel asce
+
+In case of uaccess the kernel changes to:
+
+- primary space mode in case of a uaccess (copy_to_user) and uses
+ e.g. the mvcp instruction to access user space. However the kernel
+ will stay in home space mode if the mvcos instruction is available
+- secondary space mode in case of futex atomic operations, so that the
+ instructions come from primary address space and data from secondary
+ space
+
+In case of KVM, the kernel runs in home space mode, but cr1 gets switched
+to contain the gmap asce before the SIE instruction gets executed. When
+the SIE instruction is finished, cr1 will be switched back to contain the
+user asce.
+
+
+Virtual Addresses on s/390 & z/Architecture
+===========================================
+
+A virtual address on s/390 is made up of 3 parts
+The SX (segment index, roughly corresponding to the PGD & PMD in Linux
+terminology) being bits 1-11.
+
+The PX (page index, corresponding to the page table entry (pte) in Linux
+terminology) being bits 12-19.
+
+The remaining bits BX (the byte index are the offset in the page )
+i.e. bits 20 to 31.
+
+On z/Architecture in linux we currently make up an address from 4 parts.
+
+- The region index bits (RX) 0-32 we currently use bits 22-32
+- The segment index (SX) being bits 33-43
+- The page index (PX) being bits 44-51
+- The byte index (BX) being bits 52-63
+
+Notes:
+ 1) s/390 has no PMD so the PMD is really the PGD also.
+ A lot of this stuff is defined in pgtable.h.
+
+ 2) Also seeing as s/390's page indexes are only 1k in size
+ (bits 12-19 x 4 bytes per pte ) we use 1 ( page 4k )
+ to make the best use of memory by updating 4 segment indices
+ entries each time we mess with a PMD & use offsets
+ 0,1024,2048 & 3072 in this page as for our segment indexes.
+ On z/Architecture our page indexes are now 2k in size
+ ( bits 12-19 x 8 bytes per pte ) we do a similar trick
+ but only mess with 2 segment indices each time we mess with
+ a PMD.
+
+ 3) As z/Architecture supports up to a massive 5-level page table lookup we
+ can only use 3 currently on Linux ( as this is all the generic kernel
+ currently supports ) however this may change in future
+ this allows us to access ( according to my sums )
+ 4TB of virtual storage per process i.e.
+ 4096*512(PTES)*1024(PMDS)*2048(PGD) = 4398046511104 bytes,
+ enough for another 2 or 3 of years I think :-).
+ to do this we use a region-third-table designation type in
+ our address space control registers.
+
+
+The Linux for s/390 & z/Architecture Kernel Task Structure
+==========================================================
+Each process/thread under Linux for S390 has its own kernel task_struct
+defined in linux/include/linux/sched.h
+The S390 on initialisation & resuming of a process on a cpu sets
+the __LC_KERNEL_STACK variable in the spare prefix area for this cpu
+(which we use for per-processor globals).
+
+The kernel stack pointer is intimately tied with the task structure for
+each processor as follows::
+
+ s/390
+ ************************
+ * 1 page kernel stack *
+ * ( 4K ) *
+ ************************
+ * 1 page task_struct *
+ * ( 4K ) *
+ 8K aligned ************************
+
+ z/Architecture
+ ************************
+ * 2 page kernel stack *
+ * ( 8K ) *
+ ************************
+ * 2 page task_struct *
+ * ( 8K ) *
+ 16K aligned ************************
+
+What this means is that we don't need to dedicate any register or global
+variable to point to the current running process & can retrieve it with the
+following very simple construct for s/390 & one very similar for
+z/Architecture::
+
+ static inline struct task_struct * get_current(void)
+ {
+ struct task_struct *current;
+ __asm__("lhi %0,-8192\n\t"
+ "nr %0,15"
+ : "=r" (current) );
+ return current;
+ }
+
+i.e. just anding the current kernel stack pointer with the mask -8192.
+Thankfully because Linux doesn't have support for nested IO interrupts
+& our devices have large buffers can survive interrupts being shut for
+short amounts of time we don't need a separate stack for interrupts.
+
+
+
+
+Register Usage & Stackframes on Linux for s/390 & z/Architecture
+=================================================================
+Overview:
+---------
+This is the code that gcc produces at the top & the bottom of
+each function. It usually is fairly consistent & similar from
+function to function & if you know its layout you can probably
+make some headway in finding the ultimate cause of a problem
+after a crash without a source level debugger.
+
+Note: To follow stackframes requires a knowledge of C or Pascal &
+limited knowledge of one assembly language.
+
+It should be noted that there are some differences between the
+s/390 and z/Architecture stack layouts as the z/Architecture stack layout
+didn't have to maintain compatibility with older linkage formats.
+
+Glossary:
+---------
+alloca:
+ This is a built in compiler function for runtime allocation
+ of extra space on the callers stack which is obviously freed
+ up on function exit ( e.g. the caller may choose to allocate nothing
+ of a buffer of 4k if required for temporary purposes ), it generates
+ very efficient code ( a few cycles ) when compared to alternatives
+ like malloc.
+
+automatics:
+ These are local variables on the stack, i.e they aren't in registers &
+ they aren't static.
+
+back-chain:
+ This is a pointer to the stack pointer before entering a
+ framed functions ( see frameless function ) prologue got by
+ dereferencing the address of the current stack pointer,
+ i.e. got by accessing the 32 bit value at the stack pointers
+ current location.
+
+base-pointer:
+ This is a pointer to the back of the literal pool which
+ is an area just behind each procedure used to store constants
+ in each function.
+
+call-clobbered:
+ The caller probably needs to save these registers if there
+ is something of value in them, on the stack or elsewhere before making a
+ call to another procedure so that it can restore it later.
+
+epilogue:
+ The code generated by the compiler to return to the caller.
+
+frameless-function:
+ A frameless function in Linux for s390 & z/Architecture is one which doesn't
+ need more than the register save area (96 bytes on s/390, 160 on z/Architecture)
+ given to it by the caller.
+
+ A frameless function never:
+
+ 1) Sets up a back chain.
+ 2) Calls alloca.
+ 3) Calls other normal functions
+ 4) Has automatics.
+
+GOT-pointer:
+ This is a pointer to the global-offset-table in ELF
+ ( Executable Linkable Format, Linux'es most common executable format ),
+ all globals & shared library objects are found using this pointer.
+
+lazy-binding
+ ELF shared libraries are typically only loaded when routines in the shared
+ library are actually first called at runtime. This is lazy binding.
+
+procedure-linkage-table
+ This is a table found from the GOT which contains pointers to routines
+ in other shared libraries which can't be called to by easier means.
+
+prologue:
+ The code generated by the compiler to set up the stack frame.
+
+outgoing-args:
+ This is extra area allocated on the stack of the calling function if the
+ parameters for the callee's cannot all be put in registers, the same
+ area can be reused by each function the caller calls.
+
+routine-descriptor:
+ A COFF executable format based concept of a procedure reference
+ actually being 8 bytes or more as opposed to a simple pointer to the routine.
+ This is typically defined as follows:
+
+ - Routine Descriptor offset 0=Pointer to Function
+ - Routine Descriptor offset 4=Pointer to Table of Contents
+
+ The table of contents/TOC is roughly equivalent to a GOT pointer.
+ & it means that shared libraries etc. can be shared between several
+ environments each with their own TOC.
+
+static-chain:
+ This is used in nested functions a concept adopted from pascal
+ by gcc not used in ansi C or C++ ( although quite useful ), basically it
+ is a pointer used to reference local variables of enclosing functions.
+ You might come across this stuff once or twice in your lifetime.
+
+ e.g.
+
+ The function below should return 11 though gcc may get upset & toss warnings
+ about unused variables::
+
+ int FunctionA(int a)
+ {
+ int b;
+ FunctionC(int c)
+ {
+ b=c+1;
+ }
+ FunctionC(10);
+ return(b);
+ }
+
+
+s/390 & z/Architecture Register usage
+=====================================
+
+======== ========================================== ===============
+r0 used by syscalls/assembly call-clobbered
+r1 used by syscalls/assembly call-clobbered
+r2 argument 0 / return value 0 call-clobbered
+r3 argument 1 / return value 1 (if long long) call-clobbered
+r4 argument 2 call-clobbered
+r5 argument 3 call-clobbered
+r6 argument 4 saved
+r7 pointer-to arguments 5 to ... saved
+r8 this & that saved
+r9 this & that saved
+r10 static-chain ( if nested function ) saved
+r11 frame-pointer ( if function used alloca ) saved
+r12 got-pointer saved
+r13 base-pointer saved
+r14 return-address saved
+r15 stack-pointer saved
+
+f0 argument 0 / return value ( float/double ) call-clobbered
+f2 argument 1 call-clobbered
+f4 z/Architecture argument 2 saved
+f6 z/Architecture argument 3 saved
+======== ========================================== ===============
+
+The remaining floating points
+f1,f3,f5 f7-f15 are call-clobbered.
+
+Notes:
+------
+1) The only requirement is that registers which are used
+ by the callee are saved, e.g. the compiler is perfectly
+ capable of using r11 for purposes other than a frame a
+ frame pointer if a frame pointer is not needed.
+2) In functions with variable arguments e.g. printf the calling procedure
+ is identical to one without variable arguments & the same number of
+ parameters. However, the prologue of this function is somewhat more
+ hairy owing to it having to move these parameters to the stack to
+ get va_start, va_arg & va_end to work.
+3) Access registers are currently unused by gcc but are used in
+ the kernel. Possibilities exist to use them at the moment for
+ temporary storage but it isn't recommended.
+4) Only 4 of the floating point registers are used for
+ parameter passing as older machines such as G3 only have only 4
+ & it keeps the stack frame compatible with other compilers.
+ However with IEEE floating point emulation under linux on the
+ older machines you are free to use the other 12.
+5) A long long or double parameter cannot be have the
+ first 4 bytes in a register & the second four bytes in the
+ outgoing args area. It must be purely in the outgoing args
+ area if crossing this boundary.
+6) Floating point parameters are mixed with outgoing args
+ on the outgoing args area in the order the are passed in as parameters.
+7) Floating point arguments 2 & 3 are saved in the outgoing args area for
+ z/Architecture
+
+
+Stack Frame Layout
+------------------
+
+========= ============== ======================================================
+s/390 z/Architecture
+========= ============== ======================================================
+0 0 back chain ( a 0 here signifies end of back chain )
+4 8 eos ( end of stack, not used on Linux for S390 used
+ in other linkage formats )
+8 16 glue used in other s/390 linkage formats for saved
+ routine descriptors etc.
+12 24 glue used in other s/390 linkage formats for saved
+ routine descriptors etc.
+16 32 scratch area
+20 40 scratch area
+24 48 saved r6 of caller function
+28 56 saved r7 of caller function
+32 64 saved r8 of caller function
+36 72 saved r9 of caller function
+40 80 saved r10 of caller function
+44 88 saved r11 of caller function
+48 96 saved r12 of caller function
+52 104 saved r13 of caller function
+56 112 saved r14 of caller function
+60 120 saved r15 of caller function
+64 128 saved f4 of caller function
+72 132 saved f6 of caller function
+80 undefined
+96 160 outgoing args passed from caller to callee
+96+x 160+x possible stack alignment ( 8 bytes desirable )
+96+x+y 160+x+y alloca space of caller ( if used )
+96+x+y+z 160+x+y+z automatics of caller ( if used )
+0 back-chain
+========= ============== ======================================================
+
+A sample program with comments.
+===============================
+
+Comments on the function test
+-----------------------------
+1) It didn't need to set up a pointer to the constant pool gpr13 as it is not
+ used ( :-( ).
+2) This is a frameless function & no stack is bought.
+3) The compiler was clever enough to recognise that it could return the
+ value in r2 as well as use it for the passed in parameter ( :-) ).
+4) The basr ( branch relative & save ) trick works as follows the instruction
+ has a special case with r0,r0 with some instruction operands is understood as
+ the literal value 0, some risc architectures also do this ). So now
+ we are branching to the next address & the address new program counter is
+ in r13,so now we subtract the size of the function prologue we have executed
+ the size of the literal pool to get to the top of the literal pool::
+
+
+ 0040037c int test(int b)
+ { # Function prologue below
+ 40037c: 90 de f0 34 stm %r13,%r14,52(%r15) # Save registers r13 & r14
+ 400380: 0d d0 basr %r13,%r0 # Set up pointer to constant pool using
+ 400382: a7 da ff fa ahi %r13,-6 # basr trick
+ return(5+b);
+ # Huge main program
+ 400386: a7 2a 00 05 ahi %r2,5 # add 5 to r2
+
+ # Function epilogue below
+ 40038a: 98 de f0 34 lm %r13,%r14,52(%r15) # restore registers r13 & 14
+ 40038e: 07 fe br %r14 # return
+ }
+
+Comments on the function main
+-----------------------------
+1) The compiler did this function optimally ( 8-) )::
+
+ Literal pool for main.
+ 400390: ff ff ff ec .long 0xffffffec
+ main(int argc,char *argv[])
+ { # Function prologue below
+ 400394: 90 bf f0 2c stm %r11,%r15,44(%r15) # Save necessary registers
+ 400398: 18 0f lr %r0,%r15 # copy stack pointer to r0
+ 40039a: a7 fa ff a0 ahi %r15,-96 # Make area for callee saving
+ 40039e: 0d d0 basr %r13,%r0 # Set up r13 to point to
+ 4003a0: a7 da ff f0 ahi %r13,-16 # literal pool
+ 4003a4: 50 00 f0 00 st %r0,0(%r15) # Save backchain
+
+ return(test(5)); # Main Program Below
+ 4003a8: 58 e0 d0 00 l %r14,0(%r13) # load relative address of test from
+ # literal pool
+ 4003ac: a7 28 00 05 lhi %r2,5 # Set first parameter to 5
+ 4003b0: 4d ee d0 00 bas %r14,0(%r14,%r13) # jump to test setting r14 as return
+ # address using branch & save instruction.
+
+ # Function Epilogue below
+ 4003b4: 98 bf f0 8c lm %r11,%r15,140(%r15)# Restore necessary registers.
+ 4003b8: 07 fe br %r14 # return to do program exit
+ }
+
+
+Compiler updates
+----------------
+
+::
+
+ main(int argc,char *argv[])
+ {
+ 4004fc: 90 7f f0 1c stm %r7,%r15,28(%r15)
+ 400500: a7 d5 00 04 bras %r13,400508 <main+0xc>
+ 400504: 00 40 04 f4 .long 0x004004f4
+ # compiler now puts constant pool in code to so it saves an instruction
+ 400508: 18 0f lr %r0,%r15
+ 40050a: a7 fa ff a0 ahi %r15,-96
+ 40050e: 50 00 f0 00 st %r0,0(%r15)
+ return(test(5));
+ 400512: 58 10 d0 00 l %r1,0(%r13)
+ 400516: a7 28 00 05 lhi %r2,5
+ 40051a: 0d e1 basr %r14,%r1
+ # compiler adds 1 extra instruction to epilogue this is done to
+ # avoid processor pipeline stalls owing to data dependencies on g5 &
+ # above as register 14 in the old code was needed directly after being loaded
+ # by the lm %r11,%r15,140(%r15) for the br %14.
+ 40051c: 58 40 f0 98 l %r4,152(%r15)
+ 400520: 98 7f f0 7c lm %r7,%r15,124(%r15)
+ 400524: 07 f4 br %r4
+ }
+
+
+Hartmut ( our compiler developer ) also has been threatening to take out the
+stack backchain in optimised code as this also causes pipeline stalls, you
+have been warned.
+
+64 bit z/Architecture code disassembly
+--------------------------------------
+
+If you understand the stuff above you'll understand the stuff
+below too so I'll avoid repeating myself & just say that
+some of the instructions have g's on the end of them to indicate
+they are 64 bit & the stack offsets are a bigger,
+the only other difference you'll find between 32 & 64 bit is that
+we now use f4 & f6 for floating point arguments on 64 bit::
+
+ 00000000800005b0 <test>:
+ int test(int b)
+ {
+ return(5+b);
+ 800005b0: a7 2a 00 05 ahi %r2,5
+ 800005b4: b9 14 00 22 lgfr %r2,%r2 # downcast to integer
+ 800005b8: 07 fe br %r14
+ 800005ba: 07 07 bcr 0,%r7
+
+
+ }
+
+ 00000000800005bc <main>:
+ main(int argc,char *argv[])
+ {
+ 800005bc: eb bf f0 58 00 24 stmg %r11,%r15,88(%r15)
+ 800005c2: b9 04 00 1f lgr %r1,%r15
+ 800005c6: a7 fb ff 60 aghi %r15,-160
+ 800005ca: e3 10 f0 00 00 24 stg %r1,0(%r15)
+ return(test(5));
+ 800005d0: a7 29 00 05 lghi %r2,5
+ # brasl allows jumps > 64k & is overkill here bras would do fune
+ 800005d4: c0 e5 ff ff ff ee brasl %r14,800005b0 <test>
+ 800005da: e3 40 f1 10 00 04 lg %r4,272(%r15)
+ 800005e0: eb bf f0 f8 00 04 lmg %r11,%r15,248(%r15)
+ 800005e6: 07 f4 br %r4
+ }
+
+
+
+Compiling programs for debugging on Linux for s/390 & z/Architecture
+====================================================================
+-gdwarf-2 now works it should be considered the default debugging
+format for s/390 & z/Architecture as it is more reliable for debugging
+shared libraries, normal -g debugging works much better now
+Thanks to the IBM java compiler developers bug reports.
+
+This is typically done adding/appending the flags -g or -gdwarf-2 to the
+CFLAGS & LDFLAGS variables Makefile of the program concerned.
+
+If using gdb & you would like accurate displays of registers &
+stack traces compile without optimisation i.e make sure
+that there is no -O2 or similar on the CFLAGS line of the Makefile &
+the emitted gcc commands, obviously this will produce worse code
+( not advisable for shipment ) but it is an aid to the debugging process.
+
+This aids debugging because the compiler will copy parameters passed in
+in registers onto the stack so backtracing & looking at passed in
+parameters will work, however some larger programs which use inline functions
+will not compile without optimisation.
+
+Debugging with optimisation has since much improved after fixing
+some bugs, please make sure you are using gdb-5.0 or later developed
+after Nov'2000.
+
+
+
+Debugging under VM
+==================
+
+Notes
+-----
+Addresses & values in the VM debugger are always hex never decimal
+Address ranges are of the format <HexValue1>-<HexValue2> or
+<HexValue1>.<HexValue2>
+For example, the address range 0x2000 to 0x3000 can be described as 2000-3000
+or 2000.1000
+
+The VM Debugger is case insensitive.
+
+VM's strengths are usually other debuggers weaknesses you can get at any
+resource no matter how sensitive e.g. memory management resources, change
+address translation in the PSW. For kernel hacking you will reap dividends if
+you get good at it.
+
+The VM Debugger displays operators but not operands, and also the debugger
+displays useful information on the same line as the author of the code probably
+felt that it was a good idea not to go over the 80 columns on the screen.
+This isn't as unintuitive as it may seem as the s/390 instructions are easy to
+decode mentally and you can make a good guess at a lot of them as all the
+operands are nibble (half byte aligned).
+So if you have an objdump listing by hand, it is quite easy to follow, and if
+you don't have an objdump listing keep a copy of the s/390 Reference Summary
+or alternatively the s/390 principles of operation next to you.
+e.g. even I can guess that
+0001AFF8' LR 180F CC 0
+is a ( load register ) lr r0,r15
+
+Also it is very easy to tell the length of a 390 instruction from the 2 most
+significant bits in the instruction (not that this info is really useful except
+if you are trying to make sense of a hexdump of code).
+Here is a table
+
+======================= ==================
+Bits Instruction Length
+======================= ==================
+00 2 Bytes
+01 4 Bytes
+10 4 Bytes
+11 6 Bytes
+======================= ==================
+
+The debugger also displays other useful info on the same line such as the
+addresses being operated on destination addresses of branches & condition codes.
+e.g.::
+
+ 00019736' AHI A7DAFF0E CC 1
+ 000198BA' BRC A7840004 -> 000198C2' CC 0
+ 000198CE' STM 900EF068 >> 0FA95E78 CC 2
+
+
+
+Useful VM debugger commands
+---------------------------
+
+I suppose I'd better mention this before I start
+to list the current active traces do::
+
+ Q TR
+
+there can be a maximum of 255 of these per set
+( more about trace sets later ).
+
+To stop traces issue a::
+
+ TR END.
+
+To delete a particular breakpoint issue::
+
+ TR DEL <breakpoint number>
+
+The PA1 key drops to CP mode so you can issue debugger commands,
+Doing alt c (on my 3270 console at least ) clears the screen.
+
+hitting b <enter> comes back to the running operating system
+from cp mode ( in our case linux ).
+
+It is typically useful to add shortcuts to your profile.exec file
+if you have one ( this is roughly equivalent to autoexec.bat in DOS ).
+file here are a few from mine::
+
+ /* this gives me command history on issuing f12 */
+ set pf12 retrieve
+ /* this continues */
+ set pf8 imm b
+ /* goes to trace set a */
+ set pf1 imm tr goto a
+ /* goes to trace set b */
+ set pf2 imm tr goto b
+ /* goes to trace set c */
+ set pf3 imm tr goto c
+
+
+
+Instruction Tracing
+-------------------
+Setting a simple breakpoint::
+
+ TR I PSWA <address>
+
+To debug a particular function try::
+
+ TR I R <function address range>
+ TR I on its own will single step.
+ TR I DATA <MNEMONIC> <OPTIONAL RANGE> will trace for particular mnemonics
+
+e.g.::
+
+ TR I DATA 4D R 0197BC.4000
+
+will trace for BAS'es ( opcode 4D ) in the range 0197BC.4000
+
+if you were inclined you could add traces for all branch instructions &
+suffix them with the run prefix so you would have a backtrace on screen
+when a program crashes::
+
+ TR BR <INTO OR FROM> will trace branches into or out of an address.
+
+e.g.::
+
+ TR BR INTO 0
+
+is often quite useful if a program is getting awkward & deciding
+to branch to 0 & crashing as this will stop at the address before in jumps to 0.
+
+::
+
+ TR I R <address range> RUN cmd d g
+
+single steps a range of addresses but stays running &
+displays the gprs on each step.
+
+
+
+Displaying & modifying Registers
+--------------------------------
+D G
+ will display all the gprs
+
+Adding a extra G to all the commands is necessary to access the full 64 bit
+content in VM on z/Architecture. Obviously this isn't required for access
+registers as these are still 32 bit.
+
+e.g.
+
+DGG
+ instead of DG
+
+D X
+ will display all the control registers
+D AR
+ will display all the access registers
+D AR4-7
+ will display access registers 4 to 7
+CPU ALL D G
+ will display the GRPS of all CPUS in the configuration
+D PSW
+ will display the current PSW
+st PSW 2000
+ will put the value 2000 into the PSW & cause crash your machine.
+D PREFIX
+ displays the prefix offset
+
+
+Displaying Memory
+-----------------
+To display memory mapped using the current PSW's mapping try::
+
+ D <range>
+
+To make VM display a message each time it hits a particular address and
+continue try:
+
+D I<range>
+ will disassemble/display a range of instructions.
+
+ST addr 32 bit word
+ will store a 32 bit aligned address
+D T<range>
+ will display the EBCDIC in an address (if you are that way inclined)
+D R<range>
+ will display real addresses ( without DAT ) but with prefixing.
+
+There are other complex options to display if you need to get at say home space
+but are in primary space the easiest thing to do is to temporarily
+modify the PSW to the other addressing mode, display the stuff & then
+restore it.
+
+
+
+Hints
+-----
+If you want to issue a debugger command without halting your virtual machine
+with the PA1 key try prefixing the command with #CP e.g.::
+
+ #cp tr i pswa 2000
+
+also suffixing most debugger commands with RUN will cause them not
+to stop just display the mnemonic at the current instruction on the console.
+
+If you have several breakpoints you want to put into your program &
+you get fed up of cross referencing with System.map
+you can do the following trick for several symbols.
+
+::
+
+ grep do_signal System.map
+
+which emits the following among other things::
+
+ 0001f4e0 T do_signal
+
+now you can do::
+
+ TR I PSWA 0001f4e0 cmd msg * do_signal
+
+This sends a message to your own console each time do_signal is entered.
+( As an aside I wrote a perl script once which automatically generated a REXX
+script with breakpoints on every kernel procedure, this isn't a good idea
+because there are thousands of these routines & VM can only set 255 breakpoints
+at a time so you nearly had to spend as long pruning the file down as you would
+entering the msgs by hand), however, the trick might be useful for a single
+object file. In the 3270 terminal emulator x3270 there is a very useful option
+in the file menu called "Save Screen In File" - this is very good for keeping a
+copy of traces.
+
+From CMS help <command name> will give you online help on a particular command.
+e.g.::
+
+ HELP DISPLAY
+
+Also CP has a file called profile.exec which automatically gets called
+on startup of CMS ( like autoexec.bat ), keeping on a DOS analogy session
+CP has a feature similar to doskey, it may be useful for you to
+use profile.exec to define some keystrokes.
+
+SET PF9 IMM B
+ This does a single step in VM on pressing F8.
+
+SET PF10 ^
+ This sets up the ^ key.
+ which can be used for ^c (ctrl-c),^z (ctrl-z) which can't be typed
+ directly into some 3270 consoles.
+
+SET PF11 ^-
+ This types the starting keystrokes for a sysrq see SysRq below.
+SET PF12 RETRIEVE
+ This retrieves command history on pressing F12.
+
+
+Sometimes in VM the display is set up to scroll automatically this
+can be very annoying if there are messages you wish to look at
+to stop this do
+
+TERM MORE 255 255
+ This will nearly stop automatic screen updates, however it will
+ cause a denial of service if lots of messages go to the 3270 console,
+ so it would be foolish to use this as the default on a production machine.
+
+
+Tracing particular processes
+----------------------------
+The kernel's text segment is intentionally at an address in memory that it will
+very seldom collide with text segments of user programs ( thanks Martin ),
+this simplifies debugging the kernel.
+However it is quite common for user processes to have addresses which collide
+this can make debugging a particular process under VM painful under normal
+circumstances as the process may change when doing a::
+
+ TR I R <address range>.
+
+Thankfully after reading VM's online help I figured out how to debug
+I particular process.
+
+Your first problem is to find the STD ( segment table designation )
+of the program you wish to debug.
+There are several ways you can do this here are a few
+
+Run::
+
+ objdump --syms <program to be debugged> | grep main
+
+To get the address of main in the program. Then::
+
+ tr i pswa <address of main>
+
+Start the program, if VM drops to CP on what looks like the entry
+point of the main function this is most likely the process you wish to debug.
+Now do a D X13 or D XG13 on z/Architecture.
+
+On 31 bit the STD is bits 1-19 ( the STO segment table origin )
+& 25-31 ( the STL segment table length ) of CR13.
+
+now type::
+
+ TR I R STD <CR13's value> 0.7fffffff
+
+e.g.::
+
+ TR I R STD 8F32E1FF 0.7fffffff
+
+Another very useful variation is::
+
+ TR STORE INTO STD <CR13's value> <address range>
+
+for finding out when a particular variable changes.
+
+An alternative way of finding the STD of a currently running process
+is to do the following, ( this method is more complex but
+could be quite convenient if you aren't updating the kernel much &
+so your kernel structures will stay constant for a reasonable period of
+time ).
+
+::
+
+ grep task /proc/<pid>/status
+
+from this you should see something like::
+
+ task: 0f160000 ksp: 0f161de8 pt_regs: 0f161f68
+
+This now gives you a pointer to the task structure.
+
+Now make::
+
+ CC:="s390-gcc -g" kernel/sched.s
+
+To get the task_struct stabinfo.
+
+( task_struct is defined in include/linux/sched.h ).
+
+Now we want to look at
+task->active_mm->pgd
+
+on my machine the active_mm in the task structure stab is
+active_mm:(4,12),672,32
+
+its offset is 672/8=84=0x54
+
+the pgd member in the mm_struct stab is
+pgd:(4,6)=*(29,5),96,32
+so its offset is 96/8=12=0xc
+
+so we'll::
+
+ hexdump -s 0xf160054 /dev/mem | more
+
+i.e. task_struct+active_mm offset
+to look at the active_mm member::
+
+ f160054 0fee cc60 0019 e334 0000 0000 0000 0011
+
+::
+
+ hexdump -s 0x0feecc6c /dev/mem | more
+
+i.e. active_mm+pgd offset::
+
+ feecc6c 0f2c 0000 0000 0001 0000 0001 0000 0010
+
+we get something like
+now do::
+
+ TR I R STD <pgd|0x7f> 0.7fffffff
+
+i.e. the 0x7f is added because the pgd only
+gives the page table origin & we need to set the low bits
+to the maximum possible segment table length.
+
+::
+
+ TR I R STD 0f2c007f 0.7fffffff
+
+on z/Architecture you'll probably need to do::
+
+ TR I R STD <pgd|0x7> 0.ffffffffffffffff
+
+to set the TableType to 0x1 & the Table length to 3.
+
+
+
+Tracing Program Exceptions
+--------------------------
+If you get a crash which says something like
+illegal operation or specification exception followed by a register dump
+You can restart linux & trace these using the tr prog <range or value> trace
+option.
+
+
+The most common ones you will normally be tracing for is:
+
+- 1=operation exception
+- 2=privileged operation exception
+- 4=protection exception
+- 5=addressing exception
+- 6=specification exception
+- 10=segment translation exception
+- 11=page translation exception
+
+The full list of these is on page 22 of the current s/390 Reference Summary.
+e.g.
+
+tr prog 10 will trace segment translation exceptions.
+
+tr prog on its own will trace all program interruption codes.
+
+Trace Sets
+----------
+On starting VM you are initially in the INITIAL trace set.
+You can do a Q TR to verify this.
+If you have a complex tracing situation where you wish to wait for instance
+till a driver is open before you start tracing IO, but know in your
+heart that you are going to have to make several runs through the code till you
+have a clue whats going on.
+
+What you can do is::
+
+ TR I PSWA <Driver open address>
+
+hit b to continue till breakpoint
+
+reach the breakpoint
+
+now do your::
+
+ TR GOTO B
+ TR IO 7c08-7c09 inst int run
+
+or whatever the IO channels you wish to trace are & hit b
+
+To got back to the initial trace set do::
+
+ TR GOTO INITIAL
+
+& the TR I PSWA <Driver open address> will be the only active breakpoint again.
+
+
+Tracing linux syscalls under VM
+-------------------------------
+Syscalls are implemented on Linux for S390 by the Supervisor call instruction
+(SVC). There 256 possibilities of these as the instruction is made up of a 0xA
+opcode and the second byte being the syscall number. They are traced using the
+simple command::
+
+ TR SVC <Optional value or range>
+
+the syscalls are defined in linux/arch/s390/include/asm/unistd.h
+e.g. to trace all file opens just do::
+
+ TR SVC 5 ( as this is the syscall number of open )
+
+
+SMP Specific commands
+---------------------
+To find out how many cpus you have
+Q CPUS displays all the CPU's available to your virtual machine
+To find the cpu that the current cpu VM debugger commands are being directed at
+do Q CPU to change the current cpu VM debugger commands are being directed at
+do::
+
+ CPU <desired cpu no>
+
+On a SMP guest issue a command to all CPUs try prefixing the command with cpu
+all. To issue a command to a particular cpu try cpu <cpu number> e.g.::
+
+ CPU 01 TR I R 2000.3000
+
+If you are running on a guest with several cpus & you have a IO related problem
+& cannot follow the flow of code but you know it isn't smp related.
+
+from the bash prompt issue::
+
+ shutdown -h now or halt.
+
+do a::
+
+ Q CPUS
+
+to find out how many cpus you have detach each one of them from cp except
+cpu 0 by issuing a::
+
+ DETACH CPU 01-(number of cpus in configuration)
+
+& boot linux again.
+
+TR SIGP
+ will trace inter processor signal processor instructions.
+
+DEFINE CPU 01-(number in configuration)
+ will get your guests cpus back.
+
+
+Help for displaying ascii textstrings
+-------------------------------------
+On the very latest VM Nucleus'es VM can now display ascii
+( thanks Neale for the hint ) by doing::
+
+ D TX<lowaddr>.<len>
+
+e.g.::
+
+ D TX0.100
+
+Alternatively
+=============
+Under older VM debuggers (I love EBDIC too) you can use following little
+program which converts a command line of hex digits to ascii text. It can be
+compiled under linux and you can copy the hex digits from your x3270 terminal
+to your xterm if you are debugging from a linuxbox.
+
+This is quite useful when looking at a parameter passed in as a text string
+under VM ( unless you are good at decoding ASCII in your head ).
+
+e.g. consider tracing an open syscall::
+
+ TR SVC 5
+
+We have stopped at a breakpoint::
+
+ 000151B0' SVC 0A05 -> 0001909A' CC 0
+
+D 20.8 to check the SVC old psw in the prefix area and see was it from userspace
+(for the layout of the prefix area consult the "Fixed Storage Locations"
+chapter of the s/390 Reference Summary if you have it available).
+
+::
+
+ V00000020 070C2000 800151B2
+
+The problem state bit wasn't set & it's also too early in the boot sequence
+for it to be a userspace SVC if it was we would have to temporarily switch the
+psw to user space addressing so we could get at the first parameter of the open
+in gpr2.
+
+Next do a::
+
+ D G2
+ GPR 2 = 00014CB4
+
+Now display what gpr2 is pointing to::
+
+ D 00014CB4.20
+ V00014CB4 2F646576 2F636F6E 736F6C65 00001BF5
+ V00014CC4 FC00014C B4001001 E0001000 B8070707
+
+Now copy the text till the first 00 hex ( which is the end of the string
+to an xterm & do hex2ascii on it::
+
+ hex2ascii 2F646576 2F636F6E 736F6C65 00
+
+outputs::
+
+ Decoded Hex:=/ d e v / c o n s o l e 0x00
+
+We were opening the console device,
+
+You can compile the code below yourself for practice :-),
+
+::
+
+ /*
+ * hex2ascii.c
+ * a useful little tool for converting a hexadecimal command line to ascii
+ *
+ * Author(s): Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
+ * (C) 2000 IBM Deutschland Entwicklung GmbH, IBM Corporation.
+ */
+ #include <stdio.h>
+
+ int main(int argc,char *argv[])
+ {
+ int cnt1,cnt2,len,toggle=0;
+ int startcnt=1;
+ unsigned char c,hex;
+
+ if(argc>1&&(strcmp(argv[1],"-a")==0))
+ startcnt=2;
+ printf("Decoded Hex:=");
+ for(cnt1=startcnt;cnt1<argc;cnt1++)
+ {
+ len=strlen(argv[cnt1]);
+ for(cnt2=0;cnt2<len;cnt2++)
+ {
+ c=argv[cnt1][cnt2];
+ if(c>='0'&&c<='9')
+ c=c-'0';
+ if(c>='A'&&c<='F')
+ c=c-'A'+10;
+ if(c>='a'&&c<='f')
+ c=c-'a'+10;
+ switch(toggle)
+ {
+ case 0:
+ hex=c<<4;
+ toggle=1;
+ break;
+ case 1:
+ hex+=c;
+ if(hex<32||hex>127)
+ {
+ if(startcnt==1)
+ printf("0x%02X ",(int)hex);
+ else
+ printf(".");
+ }
+ else
+ {
+ printf("%c",hex);
+ if(startcnt==1)
+ printf(" ");
+ }
+ toggle=0;
+ break;
+ }
+ }
+ }
+ printf("\n");
+ }
+
+
+
+
+Stack tracing under VM
+----------------------
+A basic backtrace
+-----------------
+
+Here are the tricks I use 9 out of 10 times it works pretty well,
+
+When your backchain reaches a dead end
+--------------------------------------
+This can happen when an exception happens in the kernel and the kernel is
+entered twice. If you reach the NULL pointer at the end of the back chain you
+should be able to sniff further back if you follow the following tricks.
+1) A kernel address should be easy to recognise since it is in
+primary space & the problem state bit isn't set & also
+The Hi bit of the address is set.
+2) Another backchain should also be easy to recognise since it is an
+address pointing to another address approximately 100 bytes or 0x70 hex
+behind the current stackpointer.
+
+
+Here is some practice.
+
+boot the kernel & hit PA1 at some random time
+
+d g to display the gprs, this should display something like::
+
+ GPR 0 = 00000001 00156018 0014359C 00000000
+ GPR 4 = 00000001 001B8888 000003E0 00000000
+ GPR 8 = 00100080 00100084 00000000 000FE000
+ GPR 12 = 00010400 8001B2DC 8001B36A 000FFED8
+
+Note that GPR14 is a return address but as we are real men we are going to
+trace the stack.
+display 0x40 bytes after the stack pointer::
+
+ V000FFED8 000FFF38 8001B838 80014C8E 000FFF38
+ V000FFEE8 00000000 00000000 000003E0 00000000
+ V000FFEF8 00100080 00100084 00000000 000FE000
+ V000FFF08 00010400 8001B2DC 8001B36A 000FFED8
+
+
+Ah now look at whats in sp+56 (sp+0x38) this is 8001B36A our saved r14 if
+you look above at our stackframe & also agrees with GPR14.
+
+now backchain::
+
+ d 000FFF38.40
+
+we now are taking the contents of SP to get our first backchain::
+
+ V000FFF38 000FFFA0 00000000 00014995 00147094
+ V000FFF48 00147090 001470A0 000003E0 00000000
+ V000FFF58 00100080 00100084 00000000 001BF1D0
+ V000FFF68 00010400 800149BA 80014CA6 000FFF38
+
+This displays a 2nd return address of 80014CA6
+
+now do::
+
+ d 000FFFA0.40
+
+for our 3rd backchain::
+
+ V000FFFA0 04B52002 0001107F 00000000 00000000
+ V000FFFB0 00000000 00000000 FF000000 0001107F
+ V000FFFC0 00000000 00000000 00000000 00000000
+ V000FFFD0 00010400 80010802 8001085A 000FFFA0
+
+
+our 3rd return address is 8001085A
+
+as the 04B52002 looks suspiciously like rubbish it is fair to assume that the
+kernel entry routines for the sake of optimisation don't set up a backchain.
+
+now look at System.map to see if the addresses make any sense::
+
+ grep -i 0001b3 System.map
+
+outputs among other things::
+
+ 0001b304 T cpu_idle
+
+so 8001B36A
+is cpu_idle+0x66 ( quiet the cpu is asleep, don't wake it )
+
+::
+
+ grep -i 00014 System.map
+
+produces among other things::
+
+ 00014a78 T start_kernel
+
+so 0014CA6 is start_kernel+some hex number I can't add in my head.
+
+::
+
+ grep -i 00108 System.map
+
+this produces::
+
+ 00010800 T _stext
+
+so 8001085A is _stext+0x5a
+
+Congrats you've done your first backchain.
+
+
+
+s/390 & z/Architecture IO Overview
+==================================
+
+I am not going to give a course in 390 IO architecture as this would take me
+quite a while and I'm no expert. Instead I'll give a 390 IO architecture
+summary for Dummies. If you have the s/390 principles of operation available
+read this instead. If nothing else you may find a few useful keywords in here
+and be able to use them on a web search engine to find more useful information.
+
+Unlike other bus architectures modern 390 systems do their IO using mostly
+fibre optics and devices such as tapes and disks can be shared between several
+mainframes. Also S390 can support up to 65536 devices while a high end PC based
+system might be choking with around 64.
+
+Here is some of the common IO terminology:
+
+Subchannel:
+ This is the logical number most IO commands use to talk to an IO device. There
+ can be up to 0x10000 (65536) of these in a configuration, typically there are a
+ few hundred. Under VM for simplicity they are allocated contiguously, however
+ on the native hardware they are not. They typically stay consistent between
+ boots provided no new hardware is inserted or removed.
+
+ Under Linux for s390 we use these as IRQ's and also when issuing an IO command
+ (CLEAR SUBCHANNEL, HALT SUBCHANNEL, MODIFY SUBCHANNEL, RESUME SUBCHANNEL,
+ START SUBCHANNEL, STORE SUBCHANNEL and TEST SUBCHANNEL). We use this as the ID
+ of the device we wish to talk to. The most important of these instructions are
+ START SUBCHANNEL (to start IO), TEST SUBCHANNEL (to check whether the IO
+ completed successfully) and HALT SUBCHANNEL (to kill IO). A subchannel can have
+ up to 8 channel paths to a device, this offers redundancy if one is not
+ available.
+
+Device Number:
+ This number remains static and is closely tied to the hardware. There are 65536
+ of these, made up of a CHPID (Channel Path ID, the most significant 8 bits) and
+ another lsb 8 bits. These remain static even if more devices are inserted or
+ removed from the hardware. There is a 1 to 1 mapping between subchannels and
+ device numbers, provided devices aren't inserted or removed.
+
+Channel Control Words:
+ CCWs are linked lists of instructions initially pointed to by an operation
+ request block (ORB), which is initially given to Start Subchannel (SSCH)
+ command along with the subchannel number for the IO subsystem to process
+ while the CPU continues executing normal code.
+ CCWs come in two flavours, Format 0 (24 bit for backward compatibility) and
+ Format 1 (31 bit). These are typically used to issue read and write (and many
+ other) instructions. They consist of a length field and an absolute address
+ field.
+
+ Each IO typically gets 1 or 2 interrupts, one for channel end (primary status)
+ when the channel is idle, and the second for device end (secondary status).
+ Sometimes you get both concurrently. You check how the IO went on by issuing a
+ TEST SUBCHANNEL at each interrupt, from which you receive an Interruption
+ response block (IRB). If you get channel and device end status in the IRB
+ without channel checks etc. your IO probably went okay. If you didn't you
+ probably need to examine the IRB, extended status word etc.
+ If an error occurs, more sophisticated control units have a facility known as
+ concurrent sense. This means that if an error occurs Extended sense information
+ will be presented in the Extended status word in the IRB. If not you have to
+ issue a subsequent SENSE CCW command after the test subchannel.
+
+
+TPI (Test pending interrupt) can also be used for polled IO, but in
+multitasking multiprocessor systems it isn't recommended except for
+checking special cases (i.e. non looping checks for pending IO etc.).
+
+Store Subchannel and Modify Subchannel can be used to examine and modify
+operating characteristics of a subchannel (e.g. channel paths).
+
+Other IO related Terms:
+
+Sysplex:
+ S390's Clustering Technology
+QDIO:
+ S390's new high speed IO architecture to support devices such as gigabit
+ ethernet, this architecture is also designed to be forward compatible with
+ upcoming 64 bit machines.
+
+
+General Concepts
+----------------
+
+Input Output Processors (IOP's) are responsible for communicating between
+the mainframe CPU's & the channel & relieve the mainframe CPU's from the
+burden of communicating with IO devices directly, this allows the CPU's to
+concentrate on data processing.
+
+IOP's can use one or more links ( known as channel paths ) to talk to each
+IO device. It first checks for path availability & chooses an available one,
+then starts ( & sometimes terminates IO ).
+There are two types of channel path: ESCON & the Parallel IO interface.
+
+IO devices are attached to control units, control units provide the
+logic to interface the channel paths & channel path IO protocols to
+the IO devices, they can be integrated with the devices or housed separately
+& often talk to several similar devices ( typical examples would be raid
+controllers or a control unit which connects to 1000 3270 terminals )::
+
+
+ +---------------------------------------------------------------+
+ | +-----+ +-----+ +-----+ +-----+ +----------+ +----------+ |
+ | | CPU | | CPU | | CPU | | CPU | | Main | | Expanded | |
+ | | | | | | | | | | Memory | | Storage | |
+ | +-----+ +-----+ +-----+ +-----+ +----------+ +----------+ |
+ |---------------------------------------------------------------+
+ | IOP | IOP | IOP |
+ |---------------------------------------------------------------
+ | C | C | C | C | C | C | C | C | C | C | C | C | C | C | C | C |
+ ----------------------------------------------------------------
+ || ||
+ || Bus & Tag Channel Path || ESCON
+ || ====================== || Channel
+ || || || || Path
+ +----------+ +----------+ +----------+
+ | | | | | |
+ | CU | | CU | | CU |
+ | | | | | |
+ +----------+ +----------+ +----------+
+ | | | | |
+ +----------+ +----------+ +----------+ +----------+ +----------+
+ |I/O Device| |I/O Device| |I/O Device| |I/O Device| |I/O Device|
+ +----------+ +----------+ +----------+ +----------+ +----------+
+ CPU = Central Processing Unit
+ C = Channel
+ IOP = IP Processor
+ CU = Control Unit
+
+The 390 IO systems come in 2 flavours the current 390 machines support both
+
+The Older 360 & 370 Interface,sometimes called the Parallel I/O interface,
+sometimes called Bus-and Tag & sometimes Original Equipment Manufacturers
+Interface (OEMI).
+
+This byte wide Parallel channel path/bus has parity & data on the "Bus" cable
+and control lines on the "Tag" cable. These can operate in byte multiplex mode
+for sharing between several slow devices or burst mode and monopolize the
+channel for the whole burst. Up to 256 devices can be addressed on one of these
+cables. These cables are about one inch in diameter. The maximum unextended
+length supported by these cables is 125 Meters but this can be extended up to
+2km with a fibre optic channel extended such as a 3044. The maximum burst speed
+supported is 4.5 megabytes per second. However, some really old processors
+support only transfer rates of 3.0, 2.0 & 1.0 MB/sec.
+One of these paths can be daisy chained to up to 8 control units.
+
+
+ESCON if fibre optic it is also called FICON
+Was introduced by IBM in 1990. Has 2 fibre optic cables and uses either leds or
+lasers for communication at a signaling rate of up to 200 megabits/sec. As
+10bits are transferred for every 8 bits info this drops to 160 megabits/sec
+and to 18.6 Megabytes/sec once control info and CRC are added. ESCON only
+operates in burst mode.
+
+ESCONs typical max cable length is 3km for the led version and 20km for the
+laser version known as XDF (extended distance facility). This can be further
+extended by using an ESCON director which triples the above mentioned ranges.
+Unlike Bus & Tag as ESCON is serial it uses a packet switching architecture,
+the standard Bus & Tag control protocol is however present within the packets.
+Up to 256 devices can be attached to each control unit that uses one of these
+interfaces.
+
+Common 390 Devices include:
+Network adapters typically OSA2,3172's,2116's & OSA-E gigabit ethernet adapters,
+Consoles 3270 & 3215 (a teletype emulated under linux for a line mode console).
+DASD's direct access storage devices ( otherwise known as hard disks ).
+Tape Drives.
+CTC ( Channel to Channel Adapters ),
+ESCON or Parallel Cables used as a very high speed serial link
+between 2 machines.
+
+
+Debugging IO on s/390 & z/Architecture under VM
+===============================================
+
+Now we are ready to go on with IO tracing commands under VM
+
+A few self explanatory queries::
+
+ Q OSA
+ Q CTC
+ Q DISK ( This command is CMS specific )
+ Q DASD
+
+Q OSA on my machine returns::
+
+ OSA 7C08 ON OSA 7C08 SUBCHANNEL = 0000
+ OSA 7C09 ON OSA 7C09 SUBCHANNEL = 0001
+ OSA 7C14 ON OSA 7C14 SUBCHANNEL = 0002
+ OSA 7C15 ON OSA 7C15 SUBCHANNEL = 0003
+
+If you have a guest with certain privileges you may be able to see devices
+which don't belong to you. To avoid this, add the option V.
+e.g.::
+
+ Q V OSA
+
+Now using the device numbers returned by this command we will
+Trace the io starting up on the first device 7c08 & 7c09
+In our simplest case we can trace the
+start subchannels
+like TR SSCH 7C08-7C09
+or the halt subchannels
+or TR HSCH 7C08-7C09
+MSCH's ,STSCH's I think you can guess the rest
+
+A good trick is tracing all the IO's and CCWS and spooling them into the reader
+of another VM guest so he can ftp the logfile back to his own machine. I'll do
+a small bit of this and give you a look at the output.
+
+1) Spool stdout to VM reader::
+
+ SP PRT TO (another vm guest ) or * for the local vm guest
+
+2) Fill the reader with the trace::
+
+ TR IO 7c08-7c09 INST INT CCW PRT RUN
+
+3) Start up linux::
+
+ i 00c
+4) Finish the trace::
+
+ TR END
+
+5) close the reader::
+
+ C PRT
+
+6) list reader contents::
+
+ RDRLIST
+
+7) copy it to linux4's minidisk::
+
+ RECEIVE / LOG TXT A1 ( replace