spec: prerelase 0.93 for testing ihk_create_os_str

Change-Id: Id31646c88da0640a3d58e7805fa61f0e0583ff1c

CMakeLists.txt

@@ -10,7 +10,7 @@ project(mckernel C ASM)
 set(MCKERNEL_VERSION "1.7.0")
 
 # See "Fedora Packaging Guidlines -- Versioning"
-set(MCKERNEL_RELEASE "0.3")
+set(MCKERNEL_RELEASE "0.93")
 
 set(CMAKE_MODULE_PATH ${CMAKE_SOURCE_DIR}/cmake/modules)
 # for rpmbuild
@@ -136,17 +136,19 @@ if (NOT LIBIBERTY)
 	message(FATAL_ERROR "error: couldn't find libiberty")
 endif()
 
-# libdwarf-devel provides /usr/lib64/libdwarf.so
 find_library(LIBDWARF dwarf)
 
-# elfutils-devel provides /usr/include/dwarf.h
-find_library(LIBEBL ebl)
-
-if ((NOT LIBDWARF) OR (NOT LIBEBL))
+if (NOT LIBDWARF)
+	if (CMAKE_CROSSCOMPILING)
+		message(FATAL_ERROR "Could not find libdwarf.so, install libdwarf-devel to ${CMAKE_FIND_ROOT_PATH}")
+	endif()
 	message("WARNING: libdwarf will be compiled locally")
-	set(LIBDWARF LIBDWARF-NOTFOUND)
-	set(LIBEBL LIBEBL-NOTFOUND)
 	enable_language(CXX)
+else()
+	# Note that libdwarf-devel provides /usr/include/libdwarf/dwarf.h
+	# but elfutils-devel provides /usr/include/dwarf.h
+	# while mcinspect.c performs "#include <dwarf.h>"
+	find_path(DWARF_H dwarf.h PATH_SUFFIXES libdwarf)
 endif()
 
 if (ENABLE_QLMPI)

NEWS.md

@@ -1,537 +0,0 @@
-=============================================
-What's new in version 1.7.0rc4 (Apr 15, 2020)
-=============================================
-
-----------------------
-McKernel major updates
-----------------------
-1. arm64: Contiguous PTE support
-2. arm64: Scalable Vector Extension (SVE) support
-3. arm64: PMU overflow interrupt support
-4. xpmem: Support large page attachment
-5. arm64 port: Direct access to Mckernel memory from Linux
-6. arm64 port: utility thread offloading, which spawns thread onto
-   Linux CPU
-7. eclair: support for live debug
-8. Crash utility extension
-9. Replace mcoverlayfs with a soft userspace overlay
-10. Build system is switched to cmake
-11. Core dump includes thread information
-
-------------------------
-McKernel major bug fixes
-------------------------
-1. shmobj: Fix rusage counting for large page
-2. mcctrl control: task start_time changed to u64 nsec
-3. mcctrl: add handling for one more level of page tables
-4. Add kernel argument to turn on/off time sharing
-5. flatten_string/process env: realign env and clear trailing bits
-6. madvise: Add MADV_HUGEPAGE support
-8. mcctrl: remove in-kernel calls to syscalls
-9. arch_cpu_read_write_register: error return fix.
-10. set_cputime(): interrupt enable/disable fix.
-11. set_mempolicy(): Add mode check.
-12. mbind(): Fix memory_range_lock deadlock.
-13. ihk_ikc_recv: Record channel to packet for release
-14. Add set_cputime() kernel to kernel case and mode enum.
-15. execve: Call preempt_enable() before error-exit
-16. memory/x86_64: fix linux safe_kernel_map
-17. do_kill(): fix pids table when nr of threads is larger than num_processors
-18. shmget: Use transparent huge pages when page size isn't specified
-19. prctl: Add support for PR_SET_THP_DISABLE and PR_GET_THP_DISABLE
-20. monitor_init: fix undetected hang on highest numbered core
-21. init_process_stack: change premapped stack size based on arch
-22. x86 syscalls: add a bunch of XXat() delegated syscalls
-23. do_pageout: fix direct kernel-user access
-24. stack: add hwcap auxval
-25. perf counters: add arch-specific perf counters
-26. Added check of nohost to terminate_host().
-27. kmalloc: Fix address order in free list
-28. sysfs: use nr_cpu_ids for cpumasks (fixes libnuma parsing error on ARM)
-29. monitor_init: Use ihk_mc_cpu_info()
-30. Fix ThunderX2 write-combined PTE flag insanity
-31. ARM: eliminate zero page mapping (i.e, init_low_area())
-32. eliminate futex_cmpxchg_enabled check (not used and dereffed a NULL pointer)
-33. page_table: Fix return value of lookup_pte when ptl4 is blank
-34. sysfs: add missing symlinks for cpu/node
-35. Make Linux handler run when mmap to procfs.
-36. Separate mmap area from program loading (relocation) area
-37. move rusage into kernel ELF image (avoid dynamic alloc before NUMA init)
-38. arm: turn off cpu on panic
-39. page fault handler: protect thread accesses
-40. Register PPD and release_handler at the same time.
-41. fix to missing exclusive processing between terminate() and
-    finalize_process().
-42. perfctr_stop: add flags to no 'disable_intens'
-43. fileobj, shmobj: free pages in object destructor (as opposed to page_unmap())
-44. clear_range_l1, clear_range_middle: Fix handling contiguous PTE
-45. do_mmap: don't pre-populate the whole file when asked for smaller segment
-46. invalidate_one_page: Support shmobj and contiguous PTE
-47. ubsan: fix undefined shifts
-48. x86: disable zero mapping and add a boot pt for ap trampoline
-49. rusage: Don't count PF_PATCH change
-50. Fixed time processing.
-51. copy_user_pte: vmap area not owned by McKernel
-52. gencore: Zero-clear ELF header and memory range table
-53. rpm: ignore CMakeCache.txt in dist and relax BuildRequires on cross build
-54. gencore: Allocate ELF header to heap instead of stack
-55. nanosleep: add cpu_pause() in spinwait loop
-56. init_process: add missing initializations to proc struct
-57. rus_vm_fault: always use a packet on the stack
-58. process stack: use PAGE_SIZE in aux vector
-59. copy_user_pte: base memobj copy on range & VR_PRIVATE
-60. arm64: ptrace: Fix overwriting 1st argument with return value
-61. page fault: use cow for private device mappings
-62. reproductible builds: remove most install paths in c code
-63. page fault: clear writable bit for non-dirtying access to shared ranges
-64. mcreboot/mcstop+release: support for regular user execution
-65. irqbalance_mck: replace extra service with service drop-in
-66. do_mmap: give addr argument a chance even if not MAP_FIXED
-67. x86: fix xchg() and cmpxchg() macros
-68. IHK: support for using Linux work IRQ as IKC interrupt (optional)
-69. MCS: fix ARM64 issue by using smp_XXX() functions (i.e., barrier()s)
-70. procfs: add number of threads to stat and status
-71. memory_range_lock: Fix deadlock in procfs/sysfs handler
-72. flush instruction cache at context switch time if necessary
-73. arm64: Fix PMU related functions
-74. page_fault_process_memory_range: Disable COW for VM region with zeroobj
-75. extend_process_region: Fall back to demand paging when not contiguous
-76. munmap: fix deadlock with remote pagefault on vm range lock
-77. procfs: if memory_range_lock fails, process later
-78. migrate-cpu: Prevent migration target from calling schedule() twice
-79. sched_request_migrate(): fix race condition between migration req and IRQs
-80. get_one_cpu_topology: Renumber core_id (physical core id)
-81. bb7e140 procfs cpuinfo: use sequence number as processor
-82. set_host_vma(): do NOT read protect Linux VMA
-
-===========================================
-What's new in V1.6.0 (Nov 11, 2018)
-===========================================
-
------------------------------------------------
-McKernel new features, improvements and changes
------------------------------------------------
-1. McKernel and Linux share one unified kernel virtual address space.
-   That is, McKernel sections resides in Linux sections spared for
-   modules.  In this way, Linux can access the McKernel kernel memory
-   area.
-2. hugetlbfs support
-3. IHK is now included as a git submodule
-4. Debug messages are turned on/off in per souce file basis at run-time.
-5. It's prohibited for McKernel to access physical memory ranges which
-   Linux didn't give to McKernel.
-6. UTI (capability to spawn a thread on Linux CPU) improvement:
-   * System calls issued from the thread are hooked by modifying
-     binary in memory.
-
----------------------------
-McKernel bug fixes (digest)
----------------------------
-#<num> below corresponds to the redmine issue number
-(https://postpeta.pccluster.org/redmine/).
-
-1. #926: shmget: Hide object with IPC_RMID from shmget
-2. #1028: init_process: Inherit parent cpu_set
-3. #995: Fix shebang recorded in argv[0]
-4. #1024: Fix VMAP virtual address leak
-5. #1109: init_process_stack: Support "ulimit -s unlimited"
-6. x86 mem init: do not map identity mapping
-7. mcexec_wait_syscall: requeue potential request on interrupted wait
-8. mcctrl_ikc_send_wait: fix interrupt with do_frees == NULL
-9. pager_req_read: handle short read
-10. kprintf: only call eventfd() if it is safe to interrupt
-11. process_procfs_request: Add Pid to /proc/<PID>/status
-12. terminate: fix oversubscribe hang when waiting for other threads on same CPU to die
-13. mcexec: Do not close fd returned to mckernel side
-14. #976: execve: Clear sigaltstack and fp_regs
-15. #1002: perf_event: Specify counter by bit_mask on start/stop
-16. #1027: schedule: Don't reschedule immediately when wake up on migrate
-17. #mcctrl: lookup unexported symbols at runtime
-18. __sched_wakeup_thread: Notify interrupt_exit() of re-schedule
-19. futex_wait_queue_me: Spin-sleep when timeout and idle_halt is specified
-20. #1167: ihk_os_getperfevent,setperfevent: Timeout IKC sent by mcctrl
-21. devobj: fix object size (POSTK_DEBUG_TEMP_FIX_36)
-22. mcctrl: remove rus page cache
-23. #1021: procfs: Support multiple reads of e.g. /proc/*/maps
-24. #1006: wait: Delay wake-up parent within switch context
-25. #1164: mem: Check if phys-mem is within the range of McKernel memory
-26. #1039: page_fault_process_memory_range: Remove ihk_mc_map_virtual for CoW of device map
-27. partitioned execution: pass process rank to LWK
-28. process/vm: implement access_ok()
-29. spinlock: rewrite spinlock to use Linux ticket head/tail format
-30. #986: Fix deadlock involving mmap_sem and memory_range_lock
-31. Prevent one CPU from getting chosen by concurrent forks
-32. #1009: check_signal: system call restart is done only once
-33. #1176: syscall: the signal received during system call processing is not processed.
-34. #1036 syscall_time: Handle by McKernel
-35. #1165 do_syscall: Delegate system calls to the mcexec with the same pid
-36. #1194 execve: Fix calling ptrace_report_signal after preemption is disabled
-37. #1005 coredump: Exclude special areas
-38. #1018 procfs: Fix pread/pwrite to procfs fail when specified size is bigger than 4MB
-39. #1180 sched_setaffinity: Check migration after decrementing in_interrupt
-40. #771, #1179, #1143 ptrace supports threads
-41. #1189 procfs/do_fork: wait until procfs entries are registered
-42. #1114 procfs: add '/proc/pid/stat' to mckernel side and fix its comm
-43. #1116 mcctrl procfs: check entry was returned before using it
-44. #1167 ihk_os_getperfevent,setperfevent: Return -ETIME when IKC timeouts
-45. mcexec/execve: fix shebangs handling
-46. procfs: handle 'comm' on mckernel side
-47. ihk_os_setperfevent: Return number of registered events
-48. mcexec: fix terminating zero after readlink()
-
-===========================================
-What's new in V1.5.1 (July 9, 2018)
-===========================================
-
------------------------------------------------
-McKernel new features, improvements and changes
------------------------------------------------
-1. Watchdog timer to detect hang of McKernel
-   mcexec prints out the following line to its stderr when a hang of
-   McKernel is detected.
-
-       mcexec detected hang of McKernel
-
-   The watchdog timer is enabled by passing -i <timeout_in_sec> option
-   to mcreboot.sh. <timeout_in_sec> specifies the interval of checking
-   if McKernel is alive.
-   Example: mcreboot.sh -i 600: Detect the hang with 10 minutes interval
-
-   The detailed step of the hang detection is as follows.
-   (1) mcexec acquires eventfd for notification from IHK and perform
-       epoll() on it.
-   (2) A daemon called ihkmond monitors the state of McKernel periodically
-       with the interval specified by the -i option. It judges that
-       McKernel is hanging and notifies mcexec by the eventfd if its
-       state hasn't changed since the last check.
-
-2. Documentation
-   man page: Installed directory is changed to <install_dir>/share/man
-
----------------------------
-McKernel bug fixes (digest)
----------------------------
-1.  #1146: pager_req_map(): do not take mmap_sem if not needed
-2.  #1135: prepare_process_ranges_args_envs(): fix saving cmdline
-3.  #1144: fileobj/devobj: record path name
-4.  #1145: fileobj: use MCS locks for per-file page hash
-5.  #1076: mcctrl: refactor prepare_image into new generic ikc send&wait
-6.  #1072: execve: fix execve with oversubscribing
-7.  #1132: execve: use thread variable instead of cpu_local_var(current)
-8.  #1117: mprotect: do not set page table writable for cow pages
-9.  #1143: syscall wait4: add _WALL (POSTK_DEBUG_ARCH_DEP_44)
-10. #1064: rusage: Fix initialization of rusage->num_processors
-11. #1133: pager_req_unmap: Put per-process data at exit
-12. #731: do_fork: Propagate error code returned by mcexec
-13. #1149: execve: Reinitialize vm_regions's map area on execve
-14. #1065: procfs: Show file names in /proc/<PID>/maps
-15. #1112: mremap: Fix type of size arguments (from ssize_t to size_t)
-16. #1121: sched_getaffinity: Check arguments in the same order as in Linux
-17. #1137: mmap, mremap: Check arguments in the same order as in Linux
-18. #1122: fix return value of sched_getaffinity
-19. #732: fix: /proc/<PID>/maps outputs a unnecessary NULL character
-
-===================================
-What's new in V1.5.0 (Apr 5, 2018)
-===================================
-
---------------------------------------
-McKernel new features and improvements
---------------------------------------
-1. Aid for Linux version migration: Detect /proc, /sys format change
-   between two kernel verions
-2. Swap out
-   * Only swap-out anonymous pages for now
-3. Improve support of /proc/maps
-4. mcstat: Linux tool to show resource usage
-
----------------------------
-McKernel bug fixes (digest)
----------------------------
-1. #727: execve: Fix memory leak when receiving SIGKILL
-2. #829: perf_event_open: Support PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
-3. #906: mcexec: Check return code of fork()
-4. #1038: mcexec: Timeout when incorrect value is given to -n option
-5. #943 #945 #946 #960 $961: mcexec: Support strace
-6. #1029: struct thread is not released with stress-test involving signal
-          and futex
-7. #863 #870: Respond immediately to terminating signal when
-              offloading system call
-8. #1119: translate_rva_to_rpa(): use 2MB blocks in 1GB pages on x86
-11. #898: Shutdown OS only after no in-flight IKC exist
-12. #882: release_handler: Destroy objects as the process which opened it
-13. #882: mcexec: Make child process exit if the parent is killed during
-          fork()
-14. #925: XPMEM: Don't destroy per-process object of the parent
-15. #885: ptrace: Support the case where a process attaches its child
-16. #1031: sigaction: Support SA_RESETHAND
-17. #923: rus_vm_fault: Return error when a thread not performing
-          system call offloading causes remote page fault
-18. #1032 #1033 #1034: getrusage: Fix ru_maxrss, RUSAGE_CHILDREN,
-                       ru_stime related bugs
-19. #1120: getrusage: Fix deadlock on thread->times_update
-20. #1123: Fix deadlock related to wait_queue_head_list_node
-21. #1124: Fix deadlock of calling terminate() from terminate()
-22. #1125: Fix deadlock related to thread status
-    * Related functions are: hold_thread(), do_kill() and terminate()
-23. #1126: uti: Fix uti thread on the McKernel side blocks others in do_syscall()
-24. #1066: procfs: Show Linux /proc/self/cgroup
-25. #1127: prepare_process_ranges_args_envs(): fix generating saved_cmdline to
-           avoid PF in strlen()
-26. #1128: ihk_mc_map/unmap_virtual(): do proper TLB invalidation
-27. #1043: terminate(): fix update_lock and threads_lock order to avoid deadlock
-28. #1129: mcreboot.sh: Save /proc/irq/*/smp_affinity to /tmp/mcreboot
-29. #1130: mcexec: drop READ_IMPLIES_EXEC from personality
-
---------------------
-McKernel workarounds
---------------------
-1. Forbid CPU oversubscription
-   * It can be turned on by mcreboot.sh -O option
-
-
-===================================
-What's new in V1.4.0 (Oct 30, 2017)
-===================================
-
------------------------------------------------------------
-Feature: Abstracted event type support in perf_event_open()
------------------------------------------------------------
-PERF_TYPE_HARDWARE and PERF_TYPE_CACHE types are supported.
-
-----------------------------------
-Clean-up: Direct user-space access
-----------------------------------
-Code lines using direct user-space access (e.g. passing user-space
-pointer to memcpy()) becomes more portable across processor
-architectures. The modification follows the following rules.
-
-1. Move the code section as it is to the architecture dependent
-   directory if it is a part of the critical-path.
-2. Otherwise, rewrite the code section by using the portable methods.
-   The methods include copy_from_user(), copy_to_user(),
-   pte_get_phys() and phys_to_virt().
-
---------------------------------
-Test: MPI and OpenMP micro-bench
---------------------------------
-The performance figures of MPI and OpenMP primitives are compared with
-those of Linux by using Intel MPI Benchmarks and EPCC OpenMP Micro
-Benchmark.
-
-
-===================================
-What's new in V1.3.0 (Sep 30, 2017)
-===================================
-
---------------------
-Feature: Kernel dump
---------------------
-1. A dump level of "only kernel memory" is added.
-
-The following two levels are available now:
-   0: Dump all
-  24: Dump only kernel memory
-
-The dump level can be set by -d option in ihkosctl or the argument
-for ihk_os_makedumpfile(), as shown in the following examples:
-
-   Command:		ihkosctl 0 dump -d 24
-   Function call:	ihk_os_makedumpfile(0, NULL, 24, 0);
-
-2. Dump file is created when Linux panics.
-
-The dump level can be set by dump_level kernel argument, as shown in the
-following example:
-
-   ihkosctl 0 kargs "hidos dump_level=24"
-
-The IHK dump function is registered to panic_notifier_list when creating
-/dev/mcdX and called when Linux panics.
-
------------------------------
-Feature: Quick Process Launch
------------------------------
-
-MPI process launch time and some of the initialization time can be
-reduced in application consisting of multiple MPI programs which are
-launched in turn in the job script.
-
-The following two steps should be performed to use this feature:
-1. Replace mpiexec with ql_mpiexec_start and add some lines for
-   ql_mpiexec_finalize in the job script
-2. Modify the app so that it can repeat calculations and wait for the
-   instructions from ql_mpiexec_{start,finalize} at the end of the
-   loop
-
-The first step is explained using an example. Assume the original job
-script looks like this:
-
-/* Execute ensamble simulation and then data assimilation, and repeat this
-   ten times */
-for i in {1..10}; do
-
-     /* Each ensamble simulation execution uses 100 nodes, launch ten of them
-        in parallel */
-    for j in {1..10}; do
-         mpiexec -n 100 -machinefile ./list1_$j p1.out a1 & pids[$i]=$!;
-    done
-
-    /* Wait until the ten ensamble simulation programs finish */
-    for j in {1..10}; do wait ${pids[$j]}; done
-
-    /* Launch one data assimilation program using 1000 nodes */
-    mpiexec -n 1000 -machinefile ./list2 p2.out a2
-done
-
-The job script should be modified like this:
-
-for i in {1..10}; do
-    for j in {1..10}; do
-        /*  Replace mpiexec with ql_mpiexec_start */
-        ql_mpiexec_start -n 100 -machinefile ./list1_$j p1.out a1 & pids[$j]=$!;
-    done
-
-    for j in {1..10}; do wait ${pids[$j]}; done
-
-    ql_mpiexec_start -n 1000 -machinefile ./list2 p2.out a2
-done
-
-/* p1.out and p2.out don't exit but are waiting for the next calculation.
-   So tell them to exit */
-for j in {1..10}; do
-   ql_mpiexec_finalize -machinefile ./list1_$i p1.out a1;
-done
-ql_mpiexec_finalize -machinefile ./list2 p2.out a2;
-
-
-The second step is explained using a pseudo-code.
-
-    MPI_Init();
-    Prepare data exchange with preceding / following MPI programs
-loop:
-    foreach Fortran module
-        Initialize data using command-line argments, parameter files,
-	environment variables
-    Input data from preceding MPI programs / Read snap-shot
-    Perform main calculation
-    Output data to following MPI programs / Write snap-shot
-    /* ql_client() waits for command of ql_mpiexec_{start,finish} */
-    if (ql_client() == QL_CONTINUE) { goto loop; }
-    MPI_Finalize();
-
-qlmpilib.h should be included in the code and libql{mpi,fort}.so
-should be linked to the executable file.
-
-
-========================
-Restrictions on McKernel
-========================
-
- 1. Pseudo devices such as /dev/mem and /dev/zero are not mmap()ed
-    correctly even if the mmap() returns a success. An access of their
-    mapping receives the SIGSEGV signal.
-
- 2. clone() supports only the following flags. All the other flags
-    cause clone() to return error or are simply ignored.
-
-    * CLONE_CHILD_CLEARTID
-    * CLONE_CHILD_SETTID
-    * CLONE_PARENT_SETTID
-    * CLONE_SETTLS
-    * CLONE_SIGHAND
-    * CLONE_VM
-
- 3. PAPI has the following restriction.
-
-    * Number of counters a user can use at the same time is up to the
-      number of the physical counters in the processor.
-
- 4. msync writes back only the modified pages mapped by the calling process.
-
- 5. The following syscalls always return the ENOSYS error.
-
-    * migrate_pages()
-    * move_pages()
-    * set_robust_list()
-
- 6. The following syscalls always return the EOPNOTSUPP error.
-
-    * arch_prctl(ARCH_SET_GS)
-    * signalfd()
-
- 7. signalfd4() returns a fd, but signal is not notified through the
-    fd.
-
- 8. set_rlimit sets the limit values but they are not enforced.
-
- 9. Address randomization is not supported.
-
-10. brk() extends the heap more than requestd when -h
-    (--extend-heap-by=)<step> option of mcexec is used with the value
-    larger than 4 KiB.  syscall_pwrite02 of LTP would fail for this
-    reason. This is because the test expects that the end of the heap
-    is set to the same address as the argument of sbrk() and expects a
-    segmentation violation occurs when it tries to access the memory
-    area right next to the boundary. However, the optimization sets
-    the end to a value larger than the requested. Therefore, the
-    expected segmentation violation doesn't occur.
-
-11. setpriority()/getpriority() won't work. They might set/get the
-    priority of a random mcexec thread. This is because there's no
-    fixed correspondence between a McKernel thread which issues the
-    system call and a mcexec thread which handles the offload request.
-
-12. mbind() can set the policy but it is not used when allocating
-    physical pages.
-
-13. MPOL_F_RELATIVE_NODES and MPOL_INTERLEAVE flags for
-    set_mempolicy()/mbind() are not supported.
-
-14. The MPOL_BIND policy for set_mempolicy()/mbind() works as the same
-    as the MPOL_PREFERRED policy. That is, the physical page allocator
-    doesn't give up the allocation when the specified nodes are
-    running out of pages but continues to search pages in the other
-    nodes.
-
-15. Kernel dump on Linux panic requires Linux kernel CentOS-7.4 and
-    later. In addition, crash_kexec_post_notifiers kernel argument
-    must be given to Linux kernel.
-
-16. setfsuid()/setfsgid() cannot change the id of the calling thread.
-    Instead, it changes that of the mcexec worker thread which takes
-    the system-call offload request.
-
-17. mmap (hugeTLBfs): The physical pages corresponding to a map are
-    released when no McKernel process exist. The next map gets fresh
-    physical pages.
-
-18. Sticky bit on executable file has no effect.
-
-19. Linux (RHEL-7 for x86_64) could hang when offlining CPUs in the
-    process of booting McKernel due to the Linux bug, found in
-    Linux-3.10 and fixed in the later version.  One way to circumvent
-    this is to always assign the same CPU set to McKernel.
-
-20. madvise:
-    * MADV_HWPOISON and MADV_SOFT_OFFLINE always returns -EPERM.
-    * MADV_MERGEABLE and MADV_UNMERGEABLE always returns -EINVAL.
-    * MADV_HUGEPAGE and MADV_NOHUGEPAGE on file map returns -EINVAL
-      (It succeeds on RHEL-8 for aarch64).
-
-21. brk() and mmap() doesn't report out-of-memory through its return
-    value. Instead, page-fault reports the error.
-
-22. Anonymous mmap pre-maps requested number of pages when contiguous
-    pages are available. Demand paging is used when not available.
-
-23. Mixing page sizes in anonymous shared mapping is not allowed. mmap
-    creates vm_range with one page size. And munmap or mremap that
-    needs the reduced page size changes the sizes of all the pages of
-    the vm_range.
-
-24. ihk_os_getperfevent() could time-out when invoked from Fujitsu TCS
-    (job-scheduler).
-
-25. The behaviors of madvise and mbind are changed to do nothing and
-    report success as a workaround for Fugaku.

README.md

@@ -1,285 +0,0 @@
-![McKernel Logo](https://www.sys.r-ccs.riken.jp/members_files/bgerofi/mckernel-logo.png)
--------------------------
-
-IHK/McKernel is a light-weight multi-kernel operating system designed for high-end supercomputing. It runs Linux and McKernel, a light-weight kernel (LWK), side-by-side inside compute nodes and aims at the following:
-
-- Provide scalable and consistent execution of large-scale parallel scientific applications, but at the same time maintain the ability to rapidly adapt to new hardware features and emerging programming models
-- Provide efficient memory and device management so that resource contention and data movement are minimized at the system level
-- Eliminate OS noise by isolating OS services in Linux and provide jitter free execution on the LWK
-- Support the full POSIX/Linux APIs by selectively offloading (slow-path) system calls to Linux
-
-## Contents
-
-- [Background](#background-and-motivation)
-- [Architectural Overview](#architectural-overview)
-- [Installation](#installation)
-- [The Team](#the-team)
-
-## Background and Motivation
-
-With the growing complexity of high-end supercomputers, the current system software stack faces significant challenges as we move forward to exascale and beyond. The necessity to deal with extreme degree of parallelism, heterogeneous architectures, multiple levels of memory hierarchy, power constraints, etc., advocates operating systems that can rapidly adapt to new hardware requirements, and that can support novel programming paradigms and runtime systems. On the other hand, a new class of more dynamic and complex applications are also on the horizon, with an increasing demand for application constructs such as in-situ analysis, workflows, elaborate monitoring and performance tools. This complexity relies not only on the rich features of POSIX, but also on the Linux APIs (such as the */proc*, */sys* filesystems, etc.) in particular.
-
-
-##### Two Traditional HPC OS Approaches
-
-Traditionally, light-weight operating systems specialized for HPC followed two approaches to tackle scalable execution of large-scale applications. In the full weight kernel (FWK) approach, a full Linux environment is taken as the basis, and features that inhibit attaining HPC scalability are removed, i.e., making it light-weight. The pure light-weight kernel (LWK) approach, on the other hand, starts from scratch and effort is undertaken to add sufficient functionality so that it provides a familiar API, typically something close to that of a general purpose OS, while at the same time it retains the desired scalability and reliability attributes. Neither of these approaches yields a fully Linux compatible environment.
-
-
-##### The Multi-kernel Approach
-
-A hybrid approach recognized recently by the system software community is to run Linux simultaneously with a lightweight kernel on compute nodes and multiple research projects are now pursuing this direction. The basic idea is that simulations run on an HPC tailored lightweight kernel, ensuring the necessary isolation for noiseless execution of parallel applications, but Linux is leveraged so that the full POSIX API is supported. Additionally, the small code base of the LWK can also facilitate rapid prototyping for new, exotic hardware features. Nevertheless, the questions of how to share node resources between the two types of kernels, where do device drivers execute, how exactly do the two kernels interact with each other and to what extent are they integrated, remain subjects of ongoing debate.
-
-
-
-## Architectural Overview
-
-At the heart of the stack is a low-level software infrastructure called Interface for Heterogeneous Kernels (IHK). IHK is a general framework that provides capabilities for partitioning resources in a many-core environment (e.g.,CPU cores and physical memory) and it enables management of lightweight kernels. IHK can allocate and release host resources dynamically and no reboot of the host machine is required when altering configuration. IHK also provides a low-level inter-kernel messaging infrastructure, called the Inter-Kernel Communication (IKC) layer. An architectural overview of the main system components is shown below.
-
-
-![arch](https://www.sys.r-ccs.riken.jp/members_files/bgerofi/mckernel.png)
-
-
-McKernel is a lightweight kernel written from scratch. It is designed for HPC and is booted from IHK. McKernel retains a binary compatible ABI with Linux, however, it implements only a small set of performance sensitive system calls and the rest are offloaded to Linux. Specifically, McKernel has its own memory management, it supports processes and multi-threading with a simple round-robin cooperative (tick-less) scheduler, and it implements signaling. It also allows inter-process memory mappings and it provides interfaces to hardware performance counters.
-
-### Functionality
-
-An overview of some of the principal functionalities of the IHK/McKernel stack is provided below.
-
-#### System Call Offloading
-
-System call forwarding in McKernel is implemented as follows. When an offloaded system call occurs, McKernel marshals the system call number along with its arguments and sends a message to Linux via a dedicated IKC channel. The corresponding proxy process running on Linux is by default waiting for system call requests through an ioctl() call into IHK’s system call delegator kernel module. The delegator kernel module’s IKC interrupt handler wakes up the proxy process, which returns to userspace and simply invokes the requested system call. Once it obtains the return value, it instructs the delegator module to send the result back to McKernel, which subsequently passes the value to user-space.
-
-#### Unified Address Space
-
-The unified address space model in IHK/McKernel ensures that offloaded system calls can seamlessly resolve arguments even in case of pointers. This mechanism is depicted below and is implemented as follows.
-
-
-![unified_ap](https://www.sys.r-ccs.riken.jp/members_files/bgerofi/img/unified_address_space_en.png)
-
-
-First, the proxy process is compiled as a position independent binary, which enables us to map the code and data segments specific to the proxy process to an address range which is explicitly excluded from McKernel’s user space. The grey box on the right side of the figure demonstrates the excluded region. Second, the entire valid virtual address range of McKernel’s application user-space is covered by a special mapping in the proxy process for which we use a pseudo file mapping in Linux. This mapping is indicated by the blue box on the left side of the figure.
-
-
-## Installation
-
-For a smooth experience, we recommend the following combination of OS distributions and platforms:
-
-- CentOS 7.3+ running on Intel Xeon / Xeon Phi
-
-
-##### 1. Change SELinux settings
-Log in as the root and disable SELinux:
-
-~~~~
-vim /etc/selinux/config
-~~~~
-
-Change the file to SELINUX=disabled
-
-##### 2. Reboot the host machine
-~~~~
-sudo reboot
-~~~~
-
-##### 3. Prepare packages, kernel symbol table file
-You will need the following packages installed:
-
-~~~~
-sudo yum install cmake kernel-devel binutils-devel systemd-devel numactl-devel gcc make nasm git
-~~~~
-
-Grant read permission to the System.map file of your kernel version:
-
-~~~~
-sudo chmod a+r /boot/System.map-`uname -r`
-~~~~
-
-##### 4. Obtain sources and compile the kernel
-
-Clone the source code:
-
-~~~~
-mkdir -p ~/src/ihk+mckernel/
-cd ~/src/ihk+mckernel/
-git clone --recursive -b development https://github.com/RIKEN-SysSoft/mckernel.git
-~~~~
-
-(Optional) Checkout to the specific branch or version:
-
-~~~~
-cd mckernel
-git checkout <pathspec>
-git submodule update
-~~~~
-
-Foe example, if you want to try the development branch, use "development" as the pathspec. If you want to try the prerelease version 1.7.0-0.2, use "1.7.0-0.2".
-
-###### 4.1 Install with cmake
-
-Configure and compile:
-
-~~~~
-mkdir -p build && cd build
-cmake -DCMAKE_INSTALL_PREFIX=${HOME}/ihk+mckernel $HOME/src/ihk+mckernel/mckernel
-make -j install
-~~~~
-
-The IHK kernel modules and McKernel kernel image should be installed under the **ihk+mckernel** folder in your home directory.
-
-###### 4.2 Install with rpm
-
-Configure, compile and build rpm:
-
-~~~~
-mkdir -p build && cd build
-cmake $HOME/src/ihk+mckernel/mckernel
-make dist
-cp mckernel-<version>.tar.gz <rpmbuild>/SOURCES
-rpm -ba scripts/mckernel.spec
-sudo rpm -ivh <rpmbuild>/RPMS/<arch>/mckernel-<version>-<release>_<linux_kernel_ver>_<dist>.<arch>.rpm
-~~~~
-
-The IHK kernel modules and McKernel kernel image are installed under the system directory.
-
-##### 5. Boot McKernel
-
-A boot script called mcreboot.sh is provided under sbin in the install folder. To boot on logical CPU 1 with 512MB of memory, use the following invocation:
-
-~~~~
-export TOP=${HOME}/ihk+mckernel/
-cd ${TOP}
-sudo ./sbin/mcreboot.sh -c 1 -m 512m
-~~~~
-
-You should see something similar like this if you display the McKernel's kernel message log:
-
-
-~~~~
-./sbin/ihkosctl 0 kmsg
-
-IHK/McKernel started.
-[ -1]: no_execute_available: 1
-[ -1]: map_fixed: phys: 0xfee00000 => 0xffff860000009000 (1 pages)
-[ -1]: setup_x86 done.
-[ -1]: ns_per_tsc: 385
-[ -1]: KCommand Line: hidos    dump_level=24
-[ -1]: Physical memory: 0x1ad3000 - 0x21000000, 525520896 bytes, 128301 pages available @ NUMA: 0
-[ -1]: NUMA: 0, Linux NUMA: 0, type: 1, available bytes: 525520896, pages: 128301
-[ -1]: NUMA 0 distances: 0 (10),
-[ -1]: map_fixed: phys: 0x28000 => 0xffff86000000a000 (2 pages)
-[ -1]: Trampoline area: 0x28000
-[ -1]: map_fixed: phys: 0x0 => 0xffff86000000c000 (1 pages)
-[ -1]: # of cpus : 1
-[ -1]: locals = ffff880001af6000
-[  0]: BSP: 0 (HW ID: 1 @ NUMA 0)
-[  0]: BSP: booted 0 AP CPUs
-[  0]: Master channel init acked.
-[  0]: vdso is enabled
-IHK/McKernel booted.
-~~~~
-
-
-##### 5. Run a simple program on McKernel
-
-The mcexec command line tool (which is also the Linux proxy process) can be used for executing applications on McKernel:
-
-~~~~
-./bin/mcexec hostname
-centos-vm
-~~~~
-
-
-##### 6. Shutdown McKernel
-
-Finally, to shutdown McKernel and release CPU/memory resources back to Linux use the following command:
-
-~~~~
-sudo ./sbin/mcstop+release.sh
-~~~~
-
-##### 7. Advanced: Enable Utility Thread offloading Interface (UTI)
-
-UTI enables a runtime such as MPI runtime to spawn utility threads such as MPI asynchronous progress threads to Linux cores.
-
-1. Install capstone
-
-Install EPEL capstone-devel:
-
-~~~~
-sudo yum install epel-release
-sudo yum install capstone-devel
-~~~~
-
-2. Install syscall_intercept
-
-~~~~
-git clone https://github.com/RIKEN-SysSoft/syscall_intercept.git
-cmake ../arch/aarch64 -DCMAKE_INSTALL_PREFIX=<syscall-intercept-install> -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=gcc -DTREAT_WARNINGS_AS_ERRORS=OFF
-~~~~
-
-3. Install UTI for McKernel
-
-Install:
-
-~~~~
-git clone https://github.com/RIKEN-SysSoft/uti.git
-mkdir build && cd build
-../uti/configure --prefix=<mckernel-install> --with-rm=mckernel
-make && make install
-~~~~
-
-4. Install McKernel
-
-~~~~
-CMAKE_PREFIX_PATH=<syscall-intercept-install> cmake -DCMAKE_INSTALL_PREFIX=${HOME}/ihk+mckernel -DENABLE_UTI=ON $HOME/src/ihk+mckernel/mckernel
-~~~~
-
-5. Run executable
-
-~~~~
-mcexec --enable-uti <command>
-~~~~
-
-6. Install UTI for Linux for performance comparison
-
-Install by make:
-
-~~~~
-git clone https://github.com/RIKEN-SysSoft/uti.git
-mkdir build && cd build
-../uti/configure --prefix=<uti-install> --with-rm=linux
-make && make install
-~~~~
-
-Install by rpm:
-
-~~~~
-git clone https://github.com/RIKEN-SysSoft/uti.git
-mkdir build && cd build
-../uti/configure --prefix=<uti-install> --with-rm=linux
-rm -f ~/rpmbuild/SOURCES/<version>.tar.gz
-rpmbuild -ba ./scripts/uti.spec
-rpm -Uvh uti-<version>-<release>-<arch>.rpm
-~~~~
-
-## The Team
-
-The McKernel project was started at The University of Tokyo and currently it is mainly developed at RIKEN.
-Some of our collaborators include:
-
-- Hitachi
-- Fujitsu
-- CEA (France)
-- NEC
-
-
-## License
-
-McKernel is GPL licensed, as found in the LICENSE file.
-
-## Contact
-
-Please give your feedback to us via one of the following mailing lists. Subscription via [www.pccluster.org](http://www.pccluster.org/mailman/listinfo/mckernel-users) is needed.
-
-* English: mckernel-users@pccluster.org
-* Japanese: mckernel-users-jp@pccluster.org

README.rst

@@ -0,0 +1,23 @@
+.. figure:: docs/mckernel-logo.png
+
+IHK/McKernel is a light-weight multi-kernel operating system designed
+for high-end supercomputing. It runs Linux and McKernel, a light-weight
+kernel (LWK), side-by-side inside compute nodes and aims at the
+following:
+
+-  Provide scalable and consistent execution of large-scale parallel
+   scientific applications, but at the same time maintain the ability to
+   rapidly adapt to new hardware features and emerging programming
+   models
+-  Provide efficient memory and device management so that resource
+   contention and data movement are minimized at the system level
+-  Eliminate OS noise by isolating OS services in Linux and provide
+   jitter free execution on the LWK
+-  Support the full POSIX/Linux APIs by selectively offloading
+   (slow-path) system calls to Linux
+
+Documentation
+=============
+
+Documentation is available
+`here <https://ihkmckernel.readthedocs.io>`__.

arch/arm64/kernel/cpu.c

@@ -1279,7 +1279,7 @@ long ihk_mc_show_cpuinfo(char *buf, size_t buf_size, unsigned long read_off, int
 
 		/* generate strings */
 		loff += scnprintf(lbuf + loff, lbuf_size - loff,
-				  "processor\t: %d\n", cpuinfo->hwid);
+				  "processor\t: %d\n", i);
 		loff += scnprintf(lbuf + loff, lbuf_size - loff, "Features\t:");
 
 		for (j = 0; hwcap_str[j]; j++) {

arch/arm64/kernel/include/rlimit.h

@@ -85,7 +85,11 @@ enum __rlimit_resource
   __RLIMIT_RTPRIO = 14,
 #define RLIMIT_RTPRIO __RLIMIT_RTPRIO
 
-  __RLIMIT_NLIMITS = 15,
+  /* timeout for RT tasks in us */
+  __RLIMIT_RTTIME = 15,
+#define RLIMIT_RTTIME __RLIMIT_RTTIME
+
+  __RLIMIT_NLIMITS = 16,
   __RLIM_NLIMITS = __RLIMIT_NLIMITS
 #define RLIMIT_NLIMITS __RLIMIT_NLIMITS
 #define RLIM_NLIMITS __RLIM_NLIMITS

arch/arm64/kernel/include/syscall_list.h

@@ -83,6 +83,7 @@ SYSCALL_HANDLED(175, geteuid)
 SYSCALL_HANDLED(176, getgid)
 SYSCALL_HANDLED(177, getegid)
 SYSCALL_HANDLED(178, gettid)
+SYSCALL_HANDLED(179, sysinfo)
 SYSCALL_DELEGATED(188, msgrcv)
 SYSCALL_DELEGATED(189, msgsnd)
 SYSCALL_DELEGATED(192, semtimedop)
@@ -117,6 +118,7 @@ SYSCALL_HANDLED(241, perf_event_open)
 SYSCALL_DELEGATED(241, perf_event_open)
 #endif // PERF_ENABLE
 SYSCALL_HANDLED(260, wait4)
+SYSCALL_HANDLED(261, prlimit64)
 SYSCALL_HANDLED(270, process_vm_readv)
 SYSCALL_HANDLED(271, process_vm_writev)
 SYSCALL_HANDLED(281, execveat)
@@ -143,3 +145,8 @@ SYSCALL_DELEGATED(1049, stat)
 SYSCALL_DELEGATED(1060, getpgrp)
 SYSCALL_HANDLED(1062, time)
 SYSCALL_DELEGATED(1069, epoll_wait)
+
+/* Do not edit the lines including this comment and
+ * EOF just after it because those are used as a
+ * robust marker for the autotest patch.
+ */

arch/arm64/kernel/syscall.c

@@ -142,17 +142,6 @@ int obtain_clone_cpuid(cpu_set_t *cpu_set, int use_last)
 	return min_cpu;
 }
 
-int
-arch_clear_host_user_space()
-{
-	struct thread *th = cpu_local_var(current);
-
-	/* XXX: might be unnecessary */
-	clear_host_pte(th->vm->region.user_start,
-			(th->vm->region.user_end - th->vm->region.user_start), 0);
-	return 0;
-}
-
 /* archtecture-depended syscall handlers */
 extern unsigned long do_fork(int clone_flags, unsigned long newsp,
 			     unsigned long parent_tidptr, unsigned long child_tidptr,
@@ -185,33 +174,6 @@ SYSCALL_DECLARE(clone)
 	return ret;
 }
 
-SYSCALL_DECLARE(rt_sigaction)
-{
-	int sig = ihk_mc_syscall_arg0(ctx);
-	const struct sigaction *act = (const struct sigaction *)ihk_mc_syscall_arg1(ctx);
-	struct sigaction *oact = (struct sigaction *)ihk_mc_syscall_arg2(ctx);
-	size_t sigsetsize = ihk_mc_syscall_arg3(ctx);
-	struct k_sigaction new_sa, old_sa;
-	int rc;
-
-	if (sigsetsize != sizeof(sigset_t))
-		return -EINVAL;
-
-	if(act)
-		if(copy_from_user(&new_sa.sa, act, sizeof new_sa.sa)){
-			goto fault;
-		}
-	rc = do_sigaction(sig, act? &new_sa: NULL, oact? &old_sa: NULL);
-	if(rc == 0 && oact)
-		if(copy_to_user(oact, &old_sa.sa, sizeof old_sa.sa)){
-			goto fault;
-		}
-
-	return rc;
-fault:
-	return -EFAULT;
-}
-
 SYSCALL_DECLARE(prctl)
 {
 	struct process *proc = cpu_local_var(current)->proc;
@@ -1368,70 +1330,6 @@ out:
 	return restart;
 }
 
-static struct sig_pending *
-getsigpending(struct thread *thread, int delflag){
-	struct list_head *head;
-	mcs_rwlock_lock_t *lock;
-	struct mcs_rwlock_node_irqsave mcs_rw_node;
-	struct sig_pending *next;
-	struct sig_pending *pending;
-	__sigset_t w;
-
-	w = thread->sigmask.__val[0];
-
-	lock = &thread->sigcommon->lock;
-	head = &thread->sigcommon->sigpending;
-	for(;;) {
-		if (delflag) {
-			mcs_rwlock_writer_lock(lock, &mcs_rw_node);
-		}
-		else {
-			mcs_rwlock_reader_lock(lock, &mcs_rw_node);
-		}
-
-		list_for_each_entry_safe(pending, next, head, list){
-			if(!(pending->sigmask.__val[0] & w)){
-				if(delflag) 
-					list_del(&pending->list);
-
-				if (delflag) {
-					mcs_rwlock_writer_unlock(lock, &mcs_rw_node);
-				}
-				else {
-					mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-				}
-				return pending;
-			}
-		}
-
-		if (delflag) {
-			mcs_rwlock_writer_unlock(lock, &mcs_rw_node);
-		}
-		else {
-			mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-		}
-
-		if(lock == &thread->sigpendinglock)
-			return NULL;
-
-		lock = &thread->sigpendinglock;
-		head = &thread->sigpending;
-	}
-
-	return NULL;
-}
-
-struct sig_pending *
-hassigpending(struct thread *thread)
-{
-	if (list_empty(&thread->sigpending) &&
-	    list_empty(&thread->sigcommon->sigpending)) {
-		return NULL;
-	}
-
-	return getsigpending(thread, 0);
-}
-
 int
 interrupt_from_user(void *regs0)
 {
@@ -1455,191 +1353,6 @@ void save_syscall_return_value(int num, unsigned long rc)
 	}
 }
 
-void
-check_signal(unsigned long rc, void *regs0, int num)
-{
-	__check_signal(rc, regs0, num, 0);
-}
-
-void
-check_signal_irq_disabled(unsigned long rc, void *regs0, int num)
-{
-	__check_signal(rc, regs0, num, 1);
-}
-
-static void
-__check_signal(unsigned long rc, void *regs0, int num, int irq_disabled)
-{
-	ihk_mc_user_context_t *regs = regs0;
-	struct thread *thread;
-	struct sig_pending *pending;
-	int	irqstate;
-
-	if(clv == NULL)
-		return;
-	thread = cpu_local_var(current);
-
-	if(thread == NULL || thread->proc->pid == 0){
-		struct thread *t;
-
-		irqstate = cpu_disable_interrupt_save();
-		ihk_mc_spinlock_lock_noirq(&(cpu_local_var(runq_lock)));
-		list_for_each_entry(t, &(cpu_local_var(runq)), sched_list){
-			if(t->proc->pid <= 0)
-				continue;
-			if(t->status == PS_INTERRUPTIBLE &&
-			   hassigpending(t)){
-				t->status = PS_RUNNING;
-				break;
-			}
-		}
-		ihk_mc_spinlock_unlock_noirq(&(cpu_local_var(runq_lock)));
-		cpu_restore_interrupt(irqstate);
-		goto out;
-	}
-
-	if(regs != NULL && !interrupt_from_user(regs)) {
-		goto out;
-	}
-
-	if (list_empty(&thread->sigpending) &&
-	    list_empty(&thread->sigcommon->sigpending)) {
-		goto out;
-	}
-
-	for(;;){
-		/* When this function called from check_signal_irq_disabled,
-		 * return with interrupt invalid.
-		 * This is to eliminate signal loss.
-		 */
-		if (irq_disabled == 1) {
-			irqstate = cpu_disable_interrupt_save();
-		}
-		pending = getsigpending(thread, 1);
-		if(!pending) {
-			dkprintf("check_signal,queue is empty\n");
-			goto out;
-		}
-		if (irq_disabled == 1) {
-			cpu_restore_interrupt(irqstate);
-		}
-		if (do_signal(rc, regs, thread, pending, num)) {
-			num = -1;
-		}
-	}
-
-out:
-	return;
-}
-
-static int
-check_sig_pending_thread(struct thread *thread)
-{
-	int found = 0;
-	struct list_head *head;
-	mcs_rwlock_lock_t *lock;
-	struct mcs_rwlock_node_irqsave mcs_rw_node;
-	struct sig_pending *next;
-	struct sig_pending *pending;
-	__sigset_t w;
-	__sigset_t x;
-	int sig = 0;
-	struct k_sigaction *k;
-	struct cpu_local_var *v;
-
-	v = get_this_cpu_local_var();
-	w = thread->sigmask.__val[0];
-
-	lock = &thread->sigcommon->lock;
-	head = &thread->sigcommon->sigpending;
-	for (;;) {
-		mcs_rwlock_reader_lock(lock, &mcs_rw_node);
-
-		list_for_each_entry_safe(pending, next, head, list) {
-			for (x = pending->sigmask.__val[0], sig = 0; x;
-			     sig++, x >>= 1)
-				;
-			k = thread->sigcommon->action + sig - 1;
-			if ((sig != SIGCHLD &&
-			     sig != SIGURG &&
-			     sig != SIGCONT) ||
-			    (k->sa.sa_handler != SIG_IGN &&
-			     k->sa.sa_handler != NULL)) {
-				if (!(pending->sigmask.__val[0] & w)) {
-					if (pending->interrupted == 0) {
-						pending->interrupted = 1;
-						found = 1;
-						if (sig != SIGCHLD &&
-						    sig != SIGURG &&
-						    sig != SIGCONT &&
-						    !k->sa.sa_handler) {
-							found = 2;
-							break;
-						}
-					}
-				}
-			}
-		}
-
-		mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-
-		if (found == 2) {
-			break;
-		}
-
-		if (lock == &thread->sigpendinglock) {
-			break;
-		}
-
-		lock = &thread->sigpendinglock;
-		head = &thread->sigpending;
-	}
-
-	if (found == 2) {
-		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-		terminate_mcexec(0, sig);
-		return 1;
-	}
-	else if (found == 1) {
-		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-		interrupt_syscall(thread, 0);
-		return 1;
-	}
-	return 0;
-}
-
-void
-check_sig_pending(void)
-{
-	struct thread *thread;
-	struct cpu_local_var *v;
-
-	if (clv == NULL)
-		return;
-
-	v = get_this_cpu_local_var();
-repeat:
-	v->runq_irqstate = ihk_mc_spinlock_lock(&v->runq_lock);
-	list_for_each_entry(thread, &(v->runq), sched_list) {
-
-		if (thread == NULL || thread == &cpu_local_var(idle)) {
-			continue;
-		}
-
-		if (thread->in_syscall_offload == 0) {
-			continue;
-		}
-
-		if (thread->proc->group_exit_status & 0x0000000100000000L) {
-			continue;
-		}
-
-		if (check_sig_pending_thread(thread))
-			goto repeat;
-	}
-	ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-}
-
 unsigned long
 do_kill(struct thread * thread, int pid, int tid, int sig, siginfo_t *info, int ptracecont)
 {

arch/x86_64/kernel/include/rlimit.h

@@ -84,7 +84,11 @@ enum __rlimit_resource
   __RLIMIT_RTPRIO = 14,
 #define RLIMIT_RTPRIO __RLIMIT_RTPRIO
 
-  __RLIMIT_NLIMITS = 15,
+  /* timeout for RT tasks in us */
+  __RLIMIT_RTTIME = 15,
+#define RLIMIT_RTTIME __RLIMIT_RTTIME
+
+  __RLIMIT_NLIMITS = 16,
   __RLIM_NLIMITS = __RLIMIT_NLIMITS
 #define RLIMIT_NLIMITS __RLIMIT_NLIMITS
 #define RLIM_NLIMITS __RLIM_NLIMITS

arch/x86_64/kernel/include/syscall_list.h

@@ -74,6 +74,7 @@ SYSCALL_DELEGATED(89, readlink)
 SYSCALL_HANDLED(96, gettimeofday)
 SYSCALL_HANDLED(97, getrlimit)
 SYSCALL_HANDLED(98, getrusage)
+SYSCALL_HANDLED(99, sysinfo)
 SYSCALL_HANDLED(100, times)
 SYSCALL_HANDLED(101, ptrace)
 SYSCALL_HANDLED(102, getuid)
@@ -157,6 +158,7 @@ SYSCALL_HANDLED(289, signalfd4)
 #ifdef ENABLE_PERF
 SYSCALL_HANDLED(298, perf_event_open)
 #endif
+SYSCALL_HANDLED(302, prlimit64)
 #ifdef DCFA_KMOD
 SYSCALL_HANDLED(303, mod_call)
 #endif
@@ -179,4 +181,8 @@ SYSCALL_HANDLED(802, linux_mlock)
 SYSCALL_HANDLED(803, suspend_threads)
 SYSCALL_HANDLED(804, resume_threads)
 SYSCALL_HANDLED(811, linux_spawn)
-/**** End of File ****/
+
+/* Do not edit the lines including this comment and
+ * EOF just after it because those are used as a
+ * robust marker for the autotest patch.
+ */

arch/x86_64/kernel/syscall.c

@@ -147,44 +147,6 @@ int obtain_clone_cpuid(cpu_set_t *cpu_set, int use_last) {
     return min_cpu;
 }
 
-int
-arch_clear_host_user_space()
-{
-	struct thread *th = cpu_local_var(current);
-
-	/* XXX: might be unnecessary */
-	clear_host_pte(th->vm->region.user_start,
-			(th->vm->region.user_end - th->vm->region.user_start), 0);
-	return 0;
-}
-
-SYSCALL_DECLARE(rt_sigaction)
-{
-	int sig = ihk_mc_syscall_arg0(ctx);
-	const struct sigaction *act = (const struct sigaction *)ihk_mc_syscall_arg1(ctx);
-	struct sigaction *oact = (struct sigaction *)ihk_mc_syscall_arg2(ctx);
-	size_t sigsetsize = ihk_mc_syscall_arg3(ctx);
-	struct k_sigaction new_sa, old_sa;
-	int rc;
-
-	if (sigsetsize != sizeof(sigset_t))
-		return -EINVAL;
-
-	if(act)
-		if(copy_from_user(&new_sa.sa, act, sizeof new_sa.sa)){
-			goto fault;
-		}
-	rc = do_sigaction(sig, act? &new_sa: NULL, oact? &old_sa: NULL);
-	if(rc == 0 && oact)
-		if(copy_to_user(oact, &old_sa.sa, sizeof old_sa.sa)){
-			goto fault;
-		}
-
-	return rc;
-fault:
-	return -EFAULT;
-}
-
 SYSCALL_DECLARE(prctl)
 {
 	struct process *proc = cpu_local_var(current)->proc;
@@ -1039,82 +1001,6 @@ out:
 	return restart;
 }
 
-static struct sig_pending *
-getsigpending(struct thread *thread, int delflag){
-	struct list_head *head;
-	mcs_rwlock_lock_t *lock;
-	struct mcs_rwlock_node_irqsave mcs_rw_node;
-	struct sig_pending *next;
-	struct sig_pending *pending;
-	__sigset_t w;
-	__sigset_t x;
-	int sig;
-	struct k_sigaction *k;
-
-	w = thread->sigmask.__val[0];
-
-	lock = &thread->sigcommon->lock;
-	head = &thread->sigcommon->sigpending;
-	for(;;) {
-		if (delflag) {
-			mcs_rwlock_writer_lock(lock, &mcs_rw_node);
-		}
-		else {
-			mcs_rwlock_reader_lock(lock, &mcs_rw_node);
-		}
-
-		list_for_each_entry_safe(pending, next, head, list){
-			for(x = pending->sigmask.__val[0], sig = 0; x; sig++, x >>= 1);
-			k = thread->sigcommon->action + sig - 1;
-			if(delflag ||
-			   (sig != SIGCHLD &&
-			    sig != SIGURG &&
-			    sig != SIGCONT) ||
-			   (k->sa.sa_handler != (void *)1 &&
-			    k->sa.sa_handler != NULL)){
-				if(!(pending->sigmask.__val[0] & w)){
-					if(delflag) 
-						list_del(&pending->list);
-
-					if (delflag) {
-						mcs_rwlock_writer_unlock(lock, &mcs_rw_node);
-					}
-					else {
-						mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-					}
-					return pending;
-				}
-			}
-		}
-
-		if (delflag) {
-			mcs_rwlock_writer_unlock(lock, &mcs_rw_node);
-		}
-		else {
-			mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-		}
-
-		if(lock == &thread->sigpendinglock)
-			return NULL;
-
-		lock = &thread->sigpendinglock;
-		head = &thread->sigpending;
-	}
-
-	return NULL;
-}
-
-struct sig_pending *
-hassigpending(struct thread *thread)
-{
-	if (list_empty(&thread->sigpending) &&
-	    list_empty(&thread->sigcommon->sigpending)) {
-		return NULL;
-	}
-
-	return getsigpending(thread, 0);
-}
-
 int
 interrupt_from_user(void *regs0)
 {
@@ -1129,175 +1015,6 @@ void save_syscall_return_value(int num, unsigned long rc)
 	return;
 }
 
-/** \brief check arrived signals and processing
- *
- * @param rc    return value of syscall
- * @param regs0 context
- * @param num   syscall number (-1: Not called on exiting system call)
- */
-void
-check_signal(unsigned long rc, void *regs0, int num)
-{
-	struct x86_user_context *regs = regs0;
-	struct thread *thread;
-	struct sig_pending *pending;
-	int	irqstate;
-
-	if(clv == NULL)
-		return;
-	thread = cpu_local_var(current);
-
-	if(thread == NULL || thread == &cpu_local_var(idle)){
-		struct thread *t;
-
-		irqstate = cpu_disable_interrupt_save();
-		ihk_mc_spinlock_lock_noirq(&(cpu_local_var(runq_lock)));
-		list_for_each_entry(t, &(cpu_local_var(runq)), sched_list){
-			if(t == &cpu_local_var(idle))
-				continue;
-			if(t->status == PS_INTERRUPTIBLE &&
-			   hassigpending(t)){
-				t->status = PS_RUNNING;
-				break;
-			}
-		}
-		ihk_mc_spinlock_unlock_noirq(&(cpu_local_var(runq_lock)));
-		cpu_restore_interrupt(irqstate);
-		goto out;
-	}
-
-	if(regs != NULL && !interrupt_from_user(regs)) {
-		goto out;
-	}
-
-	if (list_empty(&thread->sigpending) &&
-	    list_empty(&thread->sigcommon->sigpending)) {
-		goto out;
-	}
-
-	for(;;){
-		pending = getsigpending(thread, 1);
-		if(!pending) {
-			dkprintf("check_signal,queue is empty\n");
-			goto out;
-		}
-
-		if (do_signal(rc, regs, thread, pending, num)) {
-			num = -1;
-		}
-	}
-
-out:
-	return;
-}
-
-static int
-check_sig_pending_thread(struct thread *thread)
-{
-	int found = 0;
-	struct list_head *head;
-	mcs_rwlock_lock_t *lock;
-	struct mcs_rwlock_node_irqsave mcs_rw_node;
-	struct sig_pending *next;
-	struct sig_pending *pending;
-	__sigset_t w;
-	__sigset_t x;
-	int sig = 0;
-	struct k_sigaction *k;
-	struct cpu_local_var *v;
-
-	v = get_this_cpu_local_var();
-	w = thread->sigmask.__val[0];
-
-	lock = &thread->sigcommon->lock;
-	head = &thread->sigcommon->sigpending;
-	for (;;) {
-		mcs_rwlock_reader_lock(lock, &mcs_rw_node);
-
-		list_for_each_entry_safe(pending, next, head, list){
-			for (x = pending->sigmask.__val[0], sig = 0; x;
-			     sig++, x >>= 1);
-			k = thread->sigcommon->action + sig - 1;
-			if ((sig != SIGCHLD &&
-			     sig != SIGURG &&
-			     sig != SIGCONT) ||
-			    (k->sa.sa_handler != (void *)1 &&
-			     k->sa.sa_handler != NULL)) {
-				if (!(pending->sigmask.__val[0] & w)) {
-					if (pending->interrupted == 0) {
-						pending->interrupted = 1;
-						found = 1;
-						if (sig != SIGCHLD &&
-						    sig != SIGURG &&
-						    sig != SIGCONT &&
-						    !k->sa.sa_handler) {
-							found = 2;
-							break;
-						}
-					}
-				}
-			}
-		}
-
-		mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
-
-		if (found == 2) {
-			break;
-		}
-
-		if (lock == &thread->sigpendinglock) {
-			break;
-		}
-
-		lock = &thread->sigpendinglock;
-		head = &thread->sigpending;
-	}
-
-	if (found == 2) {
-		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-		terminate_mcexec(0, sig);
-		return 1;
-	}
-	else if (found == 1) {
-		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-		interrupt_syscall(thread, 0);
-		return 1;
-	}
-	return 0;
-}
-
-void
-check_sig_pending(void)
-{
-	struct thread *thread;
-	struct cpu_local_var *v;
-
-	if (clv == NULL)
-		return;
-
-	v = get_this_cpu_local_var();
-repeat:
-	v->runq_irqstate = ihk_mc_spinlock_lock(&v->runq_lock);
-	list_for_each_entry(thread, &(v->runq), sched_list) {
-
-		if (thread == NULL || thread == &cpu_local_var(idle)) {
-			continue;
-		}
-
-		if (thread->in_syscall_offload == 0) {
-			continue;
-		}
-
-		if (thread->proc->group_exit_status & 0x0000000100000000L) {
-			continue;
-		}
-
-		if (check_sig_pending_thread(thread))
-			goto repeat;
-	}
-	ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
-}
-
 unsigned long
 do_kill(struct thread *thread, int pid, int tid, int sig, siginfo_t *info,
         int ptracecont)

docs/Makefile

@@ -0,0 +1,29 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+po:
+	sphinx-build -b gettext . _build/gettext
+	/opt/local/Library/Frameworks/Python.framework/Versions/3.8/bin/sphinx-intl update -p _build/gettext -l ja
+
+ja:
+	sphinx-build -b html -D language=ja . _build/html/ja
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	echo ".. figure:: docs/mckernel-logo.png" > ../README.rst; echo >> ../README.rst
+	cat summary.rst >> ../README.rst; echo >> ../README.rst
+	cat doc.rst >> ../README.rst
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/NEWS.rst

@@ -0,0 +1,421 @@
+=============================================
+Version 1.7.0rc4 (Apr 15, 2020)
+=============================================
+
+----------------------
+McKernel major updates
+----------------------
+1. arm64: Contiguous PTE support
+2. arm64: Scalable Vector Extension (SVE) support
+3. arm64: PMU overflow interrupt support
+4. xpmem: Support large page attachment
+5. arm64 port: Direct access to Mckernel memory from Linux
+6. arm64 port: utility thread offloading, which spawns thread onto Linux CPU
+7. eclair: support for live debug
+8. Crash utility extension
+9. Replace mcoverlayfs with a soft userspace overlay
+10. Build system is switched to cmake
+11. Core dump includes thread information
+
+------------------------
+McKernel major bug fixes
+------------------------
+#. shmobj: Fix rusage counting for large page
+#. mcctrl control: task start_time changed to u64 nsec
+#. mcctrl: add handling for one more level of page tables
+#. Add kernel argument to turn on/off time sharing
+#. flatten_string / process env: realign env and clear trailing bits
+#. madvise: Add MADV_HUGEPAGE support
+#. mcctrl: remove in-kernel calls to syscalls
+#. arch_cpu_read_write_register: error return fix.
+#. set_cputime(): interrupt enable/disable fix.
+#. set_mempolicy(): Add mode check.
+#. mbind(): Fix memory_range_lock deadlock.
+#. ihk_ikc_recv: Record channel to packet for release
+#. Add set_cputime() kernel to kernel case and mode enum.
+#. execve: Call preempt_enable() before error-exit
+#. memory/x86_64: fix linux safe_kernel_map
+#. do_kill(): fix pids table when nr of threads is larger than num_processors
+#. shmget: Use transparent huge pages when page size isn't specified
+#. prctl: Add support for PR_SET_THP_DISABLE and PR_GET_THP_DISABLE
+#. monitor_init: fix undetected hang on highest numbered core
+#. init_process_stack: change premapped stack size based on arch
+#. x86 syscalls: add a bunch of XXat() delegated syscalls
+#. do_pageout: fix direct kernel-user access
+#. stack: add hwcap auxval
+#. perf counters: add arch-specific perf counters
+#. Added check of nohost to terminate_host().
+#. kmalloc: Fix address order in free list
+#. sysfs: use nr_cpu_ids for cpumasks (fixes libnuma parsing error on ARM)
+#. monitor_init: Use ihk_mc_cpu_info()
+#. Fix ThunderX2 write-combined PTE flag insanity
+#. ARM: eliminate zero page mapping (i.e, init_low_area())
+#. eliminate futex_cmpxchg_enabled check (not used and dereffed a NULL pointer)
+#. page_table: Fix return value of lookup_pte when ptl4 is blank
+#. sysfs: add missing symlinks for cpu/node
+#. Make Linux handler run when mmap to procfs.
+#. Separate mmap area from program loading (relocation) area
+#. move rusage into kernel ELF image (avoid dynamic alloc before NUMA init)
+#. arm: turn off cpu on panic
+#. page fault handler: protect thread accesses
+#. Register PPD and release_handler at the same time.
+#. fix to missing exclusive processing between terminate() and finalize_process().
+#. perfctr_stop: add flags to no 'disable_intens'
+#. fileobj, shmobj: free pages in object destructor (as opposed to page_unmap())
+#. clear_range_l1, clear_range_middle: Fix handling contiguous PTE
+#. do_mmap: don't pre-populate the whole file when asked for smaller segment
+#. invalidate_one_page: Support shmobj and contiguous PTE
+#. ubsan: fix undefined shifts
+#. x86: disable zero mapping and add a boot pt for ap trampoline
+#. rusage: Don't count PF_PATCH change
+#. Fixed time processing.
+#. copy_user_pte: vmap area not owned by McKernel
+#. gencore: Zero-clear ELF header and memory range table
+#. rpm: ignore CMakeCache.txt in dist and relax BuildRequires on cross build
+#. gencore: Allocate ELF header to heap instead of stack
+#. nanosleep: add cpu_pause() in spinwait loop
+#. init_process: add missing initializations to proc struct
+#. rus_vm_fault: always use a packet on the stack
+#. process stack: use PAGE_SIZE in aux vector
+#. copy_user_pte: base memobj copy on range & VR_PRIVATE
+#. arm64: ptrace: Fix overwriting 1st argument with return value
+#. page fault: use cow for private device mappings
+#. reproductible builds: remove most install paths in c code
+#. page fault: clear writable bit for non-dirtying access to shared ranges
+#. mcreboot/mcstop+release: support for regular user execution
+#. irqbalance_mck: replace extra service with service drop-in
+#. do_mmap: give addr argument a chance even if not MAP_FIXED
+#. x86: fix xchg() and cmpxchg() macros
+#. IHK: support for using Linux work IRQ as IKC interrupt (optional)
+#. MCS: fix ARM64 issue by using smp_XXX() functions (i.e., barrier()s)
+#. procfs: add number of threads to stat and status
+#. memory_range_lock: Fix deadlock in procfs/sysfs handler
+#. flush instruction cache at context switch time if necessary
+#. arm64: Fix PMU related functions
+#. page_fault_process_memory_range: Disable COW for VM region with zeroobj
+#. extend_process_region: Fall back to demand paging when not contiguous
+#. munmap: fix deadlock with remote pagefault on vm range lock
+#. procfs: if memory_range_lock fails, process later
+#. migrate-cpu: Prevent migration target from calling schedule() twice
+#. sched_request_migrate(): fix race condition between migration req and IRQs
+#. get_one_cpu_topology: Renumber core_id (physical core id)
+#. bb7e140 procfs cpuinfo: use sequence number as processor
+#. set_host_vma(): do NOT read protect Linux VMA
+
+===========================================
+Version 1.6.0 (Nov 11, 2018)
+===========================================
+
+-----------------------------------------------
+McKernel major updates
+-----------------------------------------------
+#. McKernel and Linux share one unified kernel virtual address space.
+   That is, McKernel sections resides in Linux sections spared for
+   modules.  In this way, Linux can access the McKernel kernel memory area.
+#. hugetlbfs support
+#. IHK is now included as a git submodule
+#. Debug messages are turned on/off in per souce file basis at run-time.
+#. It's prohibited for McKernel to access physical memory ranges which Linux didn't give to McKernel.
+#. UTI (capability to spawn a thread on Linux CPU) improvement:
+
+   * System calls issued from the thread are hooked by modifying binary in memory.
+
+---------------------------
+McKernel major bug fixes
+---------------------------
+#<digits> below denotes the redmine issue number (https://postpeta.pccluster.org/redmine/).
+
+1. #926: shmget: Hide object with IPC_RMID from shmget
+2. #1028: init_process: Inherit parent cpu_set
+3. #995: Fix shebang recorded in argv[0]
+4. #1024: Fix VMAP virtual address leak
+5. #1109: init_process_stack: Support "ulimit -s unlimited"
+6. x86 mem init: do not map identity mapping
+7. mcexec_wait_syscall: requeue potential request on interrupted wait
+8. mcctrl_ikc_send_wait: fix interrupt with do_frees == NULL
+9. pager_req_read: handle short read
+10. kprintf: only call eventfd() if it is safe to interrupt
+11. process_procfs_request: Add Pid to /proc/<PID>/status
+12. terminate: fix oversubscribe hang when waiting for other threads on same CPU to die
+13. mcexec: Do not close fd returned to mckernel side
+14. #976: execve: Clear sigaltstack and fp_regs
+15. #1002: perf_event: Specify counter by bit_mask on start/stop
+16. #1027: schedule: Don't reschedule immediately when wake up on migrate
+17. #mcctrl: lookup unexported symbols at runtime
+18. __sched_wakeup_thread: Notify interrupt_exit() of re-schedule
+19. futex_wait_queue_me: Spin-sleep when timeout and idle_halt is specified
+20. #1167: ihk_os_getperfevent,setperfevent: Timeout IKC sent by mcctrl
+21. devobj: fix object size (POSTK_DEBUG_TEMP_FIX_36)
+22. mcctrl: remove rus page cache
+23. #1021: procfs: Support multiple reads of e.g. ``/proc/*/maps``
+24. #1006: wait: Delay wake-up parent within switch context
+25. #1164: mem: Check if phys-mem is within the range of McKernel memory
+26. #1039: page_fault_process_memory_range: Remove ihk_mc_map_virtual for CoW of device map
+27. partitioned execution: pass process rank to LWK
+28. process/vm: implement access_ok()
+29. spinlock: rewrite spinlock to use Linux ticket head/tail format
+30. #986: Fix deadlock involving mmap_sem and memory_range_lock
+31. Prevent one CPU from getting chosen by concurrent forks
+32. #1009: check_signal: system call restart is done only once
+33. #1176: syscall: the signal received during system call processing is not processed.
+34. #1036 syscall_time: Handle by McKernel
+35. #1165 do_syscall: Delegate system calls to the mcexec with the same pid
+36. #1194 execve: Fix calling ptrace_report_signal after preemption is disabled
+37. #1005 coredump: Exclude special areas
+38. #1018 procfs: Fix pread/pwrite to procfs fail when specified size is bigger than 4MB
+39. #1180 sched_setaffinity: Check migration after decrementing in_interrupt
+40. #771, #1179, #1143 ptrace supports threads
+41. #1189 procfs/do_fork: wait until procfs entries are registered
+42. #1114 procfs: add '/proc/pid/stat' to mckernel side and fix its comm
+43. #1116 mcctrl procfs: check entry was returned before using it
+44. #1167 ihk_os_getperfevent,setperfevent: Return -ETIME when IKC timeouts
+45. mcexec/execve: fix shebangs handling
+46. procfs: handle 'comm' on mckernel side
+47. ihk_os_setperfevent: Return number of registered events
+48. mcexec: fix terminating zero after readlink()
+
+===========================================
+Version 1.5.1 (July 9, 2018)
+===========================================
+
+-----------------------------------------------
+McKernel major updates
+-----------------------------------------------
+
+Watchdog timer to detect hang of McKernel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+mcexec prints out the following line to its stderr when a hang of McKernel is detected.
+
+::
+   
+       mcexec detected hang of McKernel
+
+The watchdog timer is enabled by passing -i <timeout_in_sec> option to mcreboot.sh. <timeout_in_sec> specifies the interval of checking if McKernel is alive.
+
+For example, specify ``-i 600`` to detect the hang with 10 minutes interval:
+
+::
+
+   mcreboot.sh -i 600
+
+The detailed step of the hang detection is as follows.
+   #. mcexec acquires eventfd for notification from IHK and perform epoll() on it.
+   #. A daemon called ihkmond monitors the state of McKernel periodically with the interval specified by the -i option. It judges that McKernel is hanging and notifies mcexec by the eventfd if its state hasn't changed since the last check.
+
+---------------------------
+McKernel major bug fixes
+---------------------------
+1.  #1146: pager_req_map(): do not take mmap_sem if not needed
+2.  #1135: prepare_process_ranges_args_envs(): fix saving cmdline
+3.  #1144: fileobj/devobj: record path name
+4.  #1145: fileobj: use MCS locks for per-file page hash
+5.  #1076: mcctrl: refactor prepare_image into new generic ikc send&wait
+6.  #1072: execve: fix execve with oversubscribing
+7.  #1132: execve: use thread variable instead of cpu_local_var(current)
+8.  #1117: mprotect: do not set page table writable for cow pages
+9.  #1143: syscall wait4: add _WALL (POSTK_DEBUG_ARCH_DEP_44)
+10. #1064: rusage: Fix initialization of rusage->num_processors
+11. #1133: pager_req_unmap: Put per-process data at exit
+12. #731: do_fork: Propagate error code returned by mcexec
+13. #1149: execve: Reinitialize vm_regions's map area on execve
+14. #1065: procfs: Show file names in /proc/<PID>/maps
+15. #1112: mremap: Fix type of size arguments (from ssize_t to size_t)
+16. #1121: sched_getaffinity: Check arguments in the same order as in Linux
+17. #1137: mmap, mremap: Check arguments in the same order as in Linux
+18. #1122: fix return value of sched_getaffinity
+19. #732: fix: /proc/<PID>/maps outputs a unnecessary NULL character
+
+===================================
+Version 1.5.0 (Apr 5, 2018)
+===================================
+
+--------------------------------------
+McKernel major updates
+--------------------------------------
+1. Aid for Linux version migration: Detect /proc, /sys format change
+   between two kernel verions
+2. Swap out
+   * Only swap-out anonymous pages for now
+3. Improve support of /proc/maps
+4. mcstat: Linux tool to show resource usage
+
+---------------------------
+McKernel major bug fixes
+---------------------------
+#. #727: execve: Fix memory leak when receiving SIGKILL
+#. #829: perf_event_open: Support PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+#. #906: mcexec: Check return code of fork()
+#. #1038: mcexec: Timeout when incorrect value is given to -n option
+#. #943 #945 #946 #960 #961: mcexec: Support strace
+#. #1029: struct thread is not released with stress-test involving signal and futex
+#. #863 #870 : Respond immediately to terminating signal when offloading system call
+#. #1119: translate_rva_to_rpa(): use 2MB blocks in 1GB pages on x86
+#. #898: Shutdown OS only after no in-flight IKC exist
+#. #882: release_handler: Destroy objects as the process which opened it
+#. #882: mcexec: Make child process exit if the parent is killed during fork()
+#. #925: XPMEM: Don't destroy per-process object of the parent
+#. #885: ptrace: Support the case where a process attaches its child
+#. #1031: sigaction: Support SA_RESETHAND
+#. #923: rus_vm_fault: Return error when a thread not performing system call offloading causes remote page fault
+#. #1032 #1033 #1034: getrusage: Fix ru_maxrss, RUSAGE_CHILDREN, ru_stime related bugs
+#. #1120: getrusage: Fix deadlock on thread->times_update
+#. #1123: Fix deadlock related to wait_queue_head_list_node
+#. #1124: Fix deadlock of calling terminate() from terminate()
+#. #1125: Fix deadlock related to thread status
+
+   * Related functions are: hold_thread(), do_kill() and terminate()
+
+#. #1126: uti: Fix uti thread on the McKernel side blocks others in do_syscall()
+#. #1066: procfs: Show Linux /proc/self/cgroup
+#. #1127: prepare_process_ranges_args_envs(): fix generating saved_cmdline to avoid PF in strlen()
+#. #1128: ihk_mc_map/unmap_virtual(): do proper TLB invalidation
+#. #1043: terminate(): fix update_lock and threads_lock order to avoid deadlock
+#. #1129: mcreboot.sh: Save ``/proc/irq/*/smp_affinity`` to ``/tmp/mcreboot``
+#. #1130: mcexec: drop READ_IMPLIES_EXEC from personality
+
+--------------------
+McKernel workarounds
+--------------------
+#. Forbid CPU oversubscription
+
+   * It can be turned on by mcreboot.sh -O option
+
+
+===================================
+Version 1.4.0 (Oct 30, 2017)
+===================================
+
+-----------------------------------------------------------
+Abstracted event type support in perf_event_open()
+-----------------------------------------------------------
+
+PERF_TYPE_HARDWARE and PERF_TYPE_CACHE types are supported.
+
+----------------------------------
+Direct user-space access
+----------------------------------
+Code lines using direct user-space access (e.g. passing user-space
+pointer to memcpy()) becomes more portable across processor
+architectures. The modification follows the following rules.
+
+1. Move the code section as it is to the architecture dependent
+   directory if it is a part of the critical-path.
+2. Otherwise, rewrite the code section by using the portable methods.
+   The methods include copy_from_user(), copy_to_user(),
+   pte_get_phys() and phys_to_virt().
+
+--------------------------------
+MPI and OpenMP micro-bench tests
+--------------------------------
+The performance figures of MPI and OpenMP primitives are compared with
+those of Linux by using Intel MPI Benchmarks and EPCC OpenMP Micro
+Benchmark.
+
+
+===================================
+Version 1.3.0 (Sep 30, 2017)
+===================================
+
+--------------------
+Kernel dump
+--------------------
+#. A dump level of "only kernel memory" is added.
+
+The following two levels are available now:
+
++--+-----------------------+
+| 0|Dump all               |
++--+-----------------------+
+|24|Dump only kernel memory|
++--+-----------------------+
+
+The dump level can be set by -d option in ihkosctl or the argument
+for ihk_os_makedumpfile(), as shown in the following examples:
+
+::
+
+   Command:		ihkosctl 0 dump -d 24
+   Function call:	ihk_os_makedumpfile(0, NULL, 24, 0);
+
+#. Dump file is created when Linux panics.
+
+The dump level can be set by dump_level kernel argument, as shown in the
+following example:
+
+::
+
+   ihkosctl 0 kargs "hidos dump_level=24"
+
+The IHK dump function is registered to panic_notifier_list when creating /dev/mcdX and called when Linux panics.
+
+-----------------------------
+Quick Process Launch
+-----------------------------
+
+MPI process launch time and some of the initialization time can be
+reduced in application consisting of multiple MPI programs which are
+launched in turn in the job script.
+
+The following two steps should be performed to use this feature:
+#. Replace mpiexec with ql_mpiexec_start and add some lines for ql_mpiexec_finalize in the job script
+#. Modify the app so that it can repeat calculations and wait for the instructions from ql_mpiexec_{start,finalize} at the end of the loop
+
+The first step is explained using an example. Assume the original job script looks like this:
+
+.. code-block:: none
+   
+   /* Execute ensamble simulation and then data assimilation, and repeat this ten times */
+   for i in {1..10}; do
+   
+      /* Each ensamble simulation execution uses 100 nodes, launch ten of them in parallel */
+      for j in {1..10}; do
+         mpiexec -n 100 -machinefile ./list1_$j p1.out a1 & pids[$i]=$!;
+      done
+
+      /* Wait until the ten ensamble simulation programs finish */
+      for j in {1..10}; do wait ${pids[$j]}; done
+      
+      /* Launch one data assimilation program using 1000 nodes */
+      mpiexec -n 1000 -machinefile ./list2 p2.out a2
+   done
+   
+The job script should be modified like this:
+
+.. code-block:: none
+
+   for i in {1..10}; do
+      for j in {1..10}; do
+         /*  Replace mpiexec with ql_mpiexec_start */
+         ql_mpiexec_start -n 100 -machinefile ./list1_$j p1.out a1 & pids[$j]=$!;
+      done
+      
+      for j in {1..10}; do wait ${pids[$j]}; done
+      
+      ql_mpiexec_start -n 1000 -machinefile ./list2 p2.out a2
+   done
+   
+   /* p1.out and p2.out don't exit but are waiting for the next calculation. So tell them to exit */
+   for j in {1..10}; do
+      ql_mpiexec_finalize -machinefile ./list1_$i p1.out a1;
+   done
+   
+   ql_mpiexec_finalize -machinefile ./list2 p2.out a2;
+
+The second step is explained using a pseudo-code.
+
+.. code-block:: none
+
+   MPI_Init();
+   Prepare data exchange with preceding / following MPI programs
+   loop:
+   foreach Fortran module
+      Initialize data using command-line argments, parameter files, environment variables
+      Input data from preceding MPI programs / Read snap-shot
+      Perform main calculation
+      Output data to following MPI programs / Write snap-shot
+      /* ql_client() waits for command of ql_mpiexec_{start,finish} */
+      if (ql_client() == QL_CONTINUE) { goto loop; }
+      MPI_Finalize();
+
+qlmpilib.h should be included in the code and libql{mpi,fort}.so should be linked to the executable file.

docs/archtecture.rst

@@ -0,0 +1,65 @@
+Architectural Overview
+======================
+
+At the heart of the stack is a low-level software infrastructure called
+Interface for Heterogeneous Kernels (IHK). IHK is a general framework
+that provides capabilities for partitioning resources in a many-core
+environment (e.g.,CPU cores and physical memory) and it enables
+management of lightweight kernels. IHK can allocate and release host
+resources dynamically and no reboot of the host machine is required when
+altering configuration. IHK also provides a low-level inter-kernel
+messaging infrastructure, called the Inter-Kernel Communication (IKC)
+layer. An architectural overview of the main system components is shown
+below.
+
+.. figure:: mckernel.png
+   :alt: arch
+
+McKernel is a lightweight kernel written from scratch. It is designed
+for HPC and is booted from IHK. McKernel retains a binary compatible ABI
+with Linux, however, it implements only a small set of performance
+sensitive system calls and the rest are offloaded to Linux.
+Specifically, McKernel has its own memory management, it supports
+processes and multi-threading with a simple round-robin cooperative
+(tick-less) scheduler, and it implements signaling. It also allows
+inter-process memory mappings and it provides interfaces to hardware
+performance counters.
+
+Functionality
+-------------
+
+An overview of some of the principal functionalities of the IHK/McKernel
+stack is provided below.
+
+System Call Offloading
+~~~~~~~~~~~~~~~~~~~~~~
+
+System call forwarding in McKernel is implemented as follows. When an
+offloaded system call occurs, McKernel marshals the system call number
+along with its arguments and sends a message to Linux via a dedicated
+IKC channel. The corresponding proxy process running on Linux is by
+default waiting for system call requests through an ioctl() call into
+IHK’s system call delegator kernel module. The delegator kernel module’s
+IKC interrupt handler wakes up the proxy process, which returns to
+userspace and simply invokes the requested system call. Once it obtains
+the return value, it instructs the delegator module to send the result
+back to McKernel, which subsequently passes the value to user-space.
+
+Unified Address Space
+~~~~~~~~~~~~~~~~~~~~~
+
+The unified address space model in IHK/McKernel ensures that offloaded
+system calls can seamlessly resolve arguments even in case of pointers.
+This mechanism is depicted below and is implemented as follows.
+
+.. figure:: unified_address_space_en.png
+   :alt: unified_ap
+
+First, the proxy process is compiled as a position independent binary,
+which enables us to map the code and data segments specific to the proxy
+process to an address range which is explicitly excluded from McKernel’s
+user space. The grey box on the right side of the figure demonstrates
+the excluded region. Second, the entire valid virtual address range of
+McKernel’s application user-space is covered by a special mapping in the
+proxy process for which we use a pseudo file mapping in Linux. This
+mapping is indicated by the blue box on the left side of the figure.

docs/background.rst

@@ -0,0 +1,47 @@
+Background and Motivation
+=========================
+
+With the growing complexity of high-end supercomputers, the current
+system software stack faces significant challenges as we move forward to
+exascale and beyond. The necessity to deal with extreme degree of
+parallelism, heterogeneous architectures, multiple levels of memory
+hierarchy, power constraints, etc., advocates operating systems that can
+rapidly adapt to new hardware requirements, and that can support novel
+programming paradigms and runtime systems. On the other hand, a new
+class of more dynamic and complex applications are also on the horizon,
+with an increasing demand for application constructs such as in-situ
+analysis, workflows, elaborate monitoring and performance tools. This
+complexity relies not only on the rich features of POSIX, but also on
+the Linux APIs (such as the */proc*, */sys* filesystems, etc.) in
+particular.
+
+Two Traditional HPC OS Approaches
+---------------------------------
+
+Traditionally, light-weight operating systems specialized for HPC
+followed two approaches to tackle scalable execution of large-scale
+applications. In the full weight kernel (FWK) approach, a full Linux
+environment is taken as the basis, and features that inhibit attaining
+HPC scalability are removed, i.e., making it light-weight. The pure
+light-weight kernel (LWK) approach, on the other hand, starts from
+scratch and effort is undertaken to add sufficient functionality so that
+it provides a familiar API, typically something close to that of a
+general purpose OS, while at the same time it retains the desired
+scalability and reliability attributes. Neither of these approaches
+yields a fully Linux compatible environment.
+
+The Multi-kernel Approach
+-------------------------
+
+A hybrid approach recognized recently by the system software community
+is to run Linux simultaneously with a lightweight kernel on compute
+nodes and multiple research projects are now pursuing this direction.
+The basic idea is that simulations run on an HPC tailored lightweight
+kernel, ensuring the necessary isolation for noiseless execution of
+parallel applications, but Linux is leveraged so that the full POSIX API
+is supported. Additionally, the small code base of the LWK can also
+facilitate rapid prototyping for new, exotic hardware features.
+Nevertheless, the questions of how to share node resources between the
+two types of kernels, where do device drivers execute, how exactly do
+the two kernels interact with each other and to what extent are they
+integrated, remain subjects of ongoing debate.

docs/boot_run_shutdown.rst

@@ -0,0 +1,60 @@
+Boot McKernel
+----------------
+
+A boot script called ``mcreboot.sh`` is provided under ``sbin`` in the install
+folder. To boot on logical CPU 1 with 512MB of memory, use the following
+invocation:
+
+::
+
+   export TOP=${HOME}/ihk+mckernel/
+   cd ${TOP}
+   sudo ./sbin/mcreboot.sh -c 1 -m 512m
+
+You should see something similar like this if you display the McKernel’s
+kernel message log:
+
+.. code-block:: none
+
+   ./sbin/ihkosctl 0 kmsg
+
+   IHK/McKernel started.
+   [ -1]: no_execute_available: 1
+   [ -1]: map_fixed: phys: 0xfee00000 => 0xffff860000009000 (1 pages)
+   [ -1]: setup_x86 done.
+   [ -1]: ns_per_tsc: 385
+   [ -1]: KCommand Line: hidos    dump_level=24
+   [ -1]: Physical memory: 0x1ad3000 - 0x21000000, 525520896 bytes, 128301 pages available @ NUMA: 0
+   [ -1]: NUMA: 0, Linux NUMA: 0, type: 1, available bytes: 525520896, pages: 128301
+   [ -1]: NUMA 0 distances: 0 (10),
+   [ -1]: map_fixed: phys: 0x28000 => 0xffff86000000a000 (2 pages)
+   [ -1]: Trampoline area: 0x28000
+   [ -1]: map_fixed: phys: 0x0 => 0xffff86000000c000 (1 pages)
+   [ -1]: # of cpus : 1
+   [ -1]: locals = ffff880001af6000
+   [  0]: BSP: 0 (HW ID: 1 @ NUMA 0)
+   [  0]: BSP: booted 0 AP CPUs
+   [  0]: Master channel init acked.
+   [  0]: vdso is enabled
+   IHK/McKernel booted.
+
+Run a simple program on McKernel
+-----------------------------------
+
+The mcexec command line tool (which is also the Linux proxy process) can
+be used for executing applications on McKernel:
+
+::
+
+   ./bin/mcexec hostname
+   centos-vm
+
+Shutdown McKernel
+--------------------
+
+Finally, to shutdown McKernel and release CPU/memory resources back to
+Linux use the following command:
+
+::
+
+   sudo ./sbin/mcstop+release.sh

docs/conf.py

@@ -0,0 +1,173 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = u'IHK/McKernel'
+copyright = u'2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa'
+author = u'Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa'
+
+# The short X.Y version
+version = u''
+# The full version, including alpha/beta/rc tags
+release = u''
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'recommonmark',
+]
+numfig = True
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+source_suffix = ['.rst', '.md']
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = [u'_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = None
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'IHKMcKerneldoc'
+
+
+# -- Options for LaTeX output ------------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'IHKMcKernel.tex', u'IHK/McKernel Documentation',
+     u'Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'ihkmckernel', u'IHK/McKernel Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output ----------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'IHKMcKernel', u'IHK/McKernel Documentation',
+     author, 'IHKMcKernel', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for Epub output -------------------------------------------------
+
+# Bibliographic Dublin Core info.
+epub_title = project
+
+# The unique identifier of the text. This can be a ISBN number
+# or the project homepage.
+#
+# epub_identifier = ''
+
+# A unique identification for the text.
+#
+# epub_uid = ''
+
+# A list of files that should not be packed into the epub file.
+epub_exclude_files = ['search.html']

docs/contact.rst

@@ -0,0 +1,11 @@
+Contact
+=======
+
+Please give your feedback to us via one of the following mailing lists.
+Subscription via
+`www.pccluster.org <http://www.pccluster.org/mailman/listinfo/mckernel-users>`__
+is needed.
+
+-  English: mckernel-users@pccluster.org
+-  Japanese: mckernel-users-jp@pccluster.org
+

docs/cover.rst

@@ -0,0 +1,5 @@
+.. include:: logo.rst
+
+.. include:: summary.rst
+
+See `Quick Guide -- Installation <quick.html#installation>`__ for jump start.

docs/doc.rst

@@ -0,0 +1,5 @@
+Documentation
+=============
+
+Documentation is available
+`here <https://ihkmckernel.readthedocs.io>`__.

docs/ihk_developers.rst

@@ -0,0 +1,18 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+External Specs
+==============
+
+Overview
+--------
+
+Function Specs
+--------------
+
+Command / Daemon Specs
+----------------------
+
+Booting LWK
+===========

docs/index.rst

@@ -0,0 +1,58 @@
+.. IHK/McKernel documentation master file, created by
+   sphinx-quickstart on Mon Jul 27 15:57:24 2020.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+===================
+IHK/McKernel
+===================
+
+.. include:: cover.rst
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Quick Guide
+
+   quick
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Users' Guide
+
+   users
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Operators' Guide
+
+   operators
+
+.. toctree::
+   :maxdepth: 2
+   :caption: IHK Developers' Guide
+
+   ihk_developers
+
+.. toctree::
+   :maxdepth: 2
+   :caption: McKernel Developers' Guide
+
+   mckernel_developers
+
+.. toctree::
+   :maxdepth: 2
+   :caption: IHK Specifications
+
+   spec/ihk
+
+.. toctree::
+   :maxdepth: 2
+   :caption: McKernel Specifications
+
+   spec/mckernel
+
+.. toctree::
+   :maxdepth: 2
+   :caption: What's New
+
+   NEWS

docs/install.rst

@@ -0,0 +1,202 @@
+.. highlight:: bash
+
+Installation
+============
+
+The following OS distributions and platforms are recommended:
+
+* OS distribution
+
+  * CentOS 7.3 or later
+  * RHEL 7.3 or later
+
+* Platform
+
+  * Intel Xeon
+  * Intel Xeon Phi
+  * Fujitsu A64FX
+
+Prepare files for building McKernel
+-----------------------------------
+
+Grant read permission to the System.map file of your kernel version on the build machine:
+
+::
+
+   sudo chmod a+r /boot/System.map-`uname -r`
+
+Install the following packages to the build machine:
+
+::
+
+   cmake kernel-devel binutils-devel systemd-devel numactl-devel gcc make nasm git libdwarf-devel
+
+When having access to repositories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:
+
+::
+
+   sudo subscription-manager repos --enable codeready-builder-for-rhel-8-$(/bin/arch)-rpms
+
+On CentOS 8, enable the PowerTools repository:
+
+::
+
+   sudo dnf config-manager --set-enabled PowerTools
+
+Install with yum:
+
+::
+
+   sudo yum install cmake kernel-devel binutils-devel systemd-devel numactl-devel gcc make nasm git libdwarf-devel
+
+When not having access to repositories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Ask the system administrator to install them. Note that ``libdwarf-devel`` is in the CodeReady Linux Builder repository on RHEL 8 or in the PowerTools repository on CentOS 8.
+
+Clone, compile, install
+--------------------------
+
+Clone the source code:
+
+::
+
+   mkdir -p ~/src/ihk+mckernel/
+   cd ~/src/ihk+mckernel/
+   git clone --recursive -b development https://github.com/RIKEN-SysSoft/mckernel.git
+
+(Optional) Checkout to the specific branch or version:
+
+::
+
+   cd mckernel
+   git checkout <pathspec>
+   git submodule update
+
+Foe example, if you want to try the development branch, use
+“development” as the pathspec. If you want to try the prerelease version
+1.7.0-0.2, use “1.7.0-0.2”.
+
+Move to build directory:
+
+::
+
+   mkdir -p ~/src/ihk+mckernel/build && cd ~/src/ihk+mckernel/build
+
+Run cmake:
+
+When not cross-compiling:
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+::
+
+   cmake -DCMAKE_INSTALL_PREFIX=${HOME}/ihk+mckernel ../mckernel
+
+When cross-compiling:
+~~~~~~~~~~~~~~~~~~~~~
+
+::
+
+   cmake -DCMAKE_INSTALL_PREFIX=${HOME}/ihk+mckernel \
+     -DUNAME_R=<target_uname_r> \
+     -DKERNEL_DIR=<kernnel_dir> \
+     -DBUILD_TARGET=smp-arm64 \
+     -DCMAKE_TOOLCHAIN_FILE=../mckernel/cmake/cross-aarch64.cmake \
+     ../mckernel
+
+Install with cmake
+~~~~~~~~~~~~~~~~~~~~~~
+
+Install with make:
+
+::
+
+   make -j install
+
+The kernel modules and McKernel kernel image should be installed
+under the **ihk+mckernel** folder in your home directory.
+
+Install with rpm
+~~~~~~~~~~~~~~~~~~~~
+
+Create the tarball and the spec file:
+
+::
+
+   make dist
+   cp mckernel-<version>.tar.gz <rpmbuild>/SOURCES
+
+Create the rpm package:
+
+When not cross-compiling:
+"""""""""""""""""""""""""
+
+::
+
+   rpmbuild -ba scripts/mckernel.spec
+
+When cross-compiling:
+"""""""""""""""""""""
+
+::
+
+   rpmbuild -ba scripts/mckernel.spec --target <target_uname_m> -D 'kernel_version <target_uname_r>' -D 'kernel_dir <kernel_source>'
+
+Install the rpm package:
+
+::
+
+   sudo rpm -ivh <rpmbuild>/RPMS/<arch>/mckernel-<version>-<release>_<linux_kernel_ver>_<dist>.<arch>.rpm
+
+The kernel modules and McKernel kernel image are installed under the
+standard system directories.
+
+Prepare files and change settings for installing McKernel
+---------------------------------------------------------
+
+Disable SELinux of the compute nodes:
+
+::
+
+   sudo vim /etc/selinux/config
+
+Change the file to SELINUX=disabled. And then reboot the compute nodes:
+
+::
+
+   sudo reboot
+
+Install the following packages to the compute nodes:
+
+::
+
+   systemd-libs numactl-libs libdwarf
+
+When having access to repositories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:
+
+::
+
+   sudo subscription-manager repos --enable codeready-builder-for-rhel-8-$(/bin/arch)-rpms
+
+On CentOS 8, enable the PowerTools repository:
+
+::
+
+   sudo dnf config-manager --set-enabled PowerTools
+
+Install with yum:
+
+::
+
+   sudo yum install systemd-libs numactl-libs libdwarf
+
+When not having access to repositories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Ask the system administrator to install them. Note that ``libdwarf`` is in the CodeReady Linux Builder repository on RHEL 8 or in the PowerTools repository on CentOS 8.

docs/license.rst

@@ -0,0 +1,5 @@
+License
+=======
+
+McKernel is GPL licensed, as found in the LICENSE file.
+

docs/locales/ja/LC_MESSAGES/README_.po

@@ -0,0 +1,469 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../README_.rst:2
+msgid "|McKernel Logo|"
+msgstr ""
+
+#: ../../README_.rst:4
+msgid ""
+"IHK/McKernel is a light-weight multi-kernel operating system designed for"
+" high-end supercomputing. It runs Linux and McKernel, a light-weight "
+"kernel (LWK), side-by-side inside compute nodes and aims at the "
+"following:"
+msgstr ""
+
+#: ../../README_.rst:9
+msgid ""
+"Provide scalable and consistent execution of large-scale parallel "
+"scientific applications, but at the same time maintain the ability to "
+"rapidly adapt to new hardware features and emerging programming models"
+msgstr ""
+
+#: ../../README_.rst:13
+msgid ""
+"Provide efficient memory and device management so that resource "
+"contention and data movement are minimized at the system level"
+msgstr ""
+
+#: ../../README_.rst:15
+msgid ""
+"Eliminate OS noise by isolating OS services in Linux and provide jitter "
+"free execution on the LWK"
+msgstr ""
+
+#: ../../README_.rst:17
+msgid ""
+"Support the full POSIX/Linux APIs by selectively offloading (slow-path) "
+"system calls to Linux"
+msgstr ""
+
+#: ../../README_.rst:21
+msgid "Documentation"
+msgstr ""
+
+#: ../../README_.rst:23
+msgid "Documentation is available `here <https://ihkmckernel.readthedocs.io>`__."
+msgstr ""
+
+#: ../../README_.rst:27
+msgid "Contents"
+msgstr ""
+
+#: ../../README_.rst:29
+msgid "`Background <#background-and-motivation>`__"
+msgstr ""
+
+#: ../../README_.rst:30
+msgid "`Architectural Overview <#architectural-overview>`__"
+msgstr ""
+
+#: ../../README_.rst:31
+msgid "`Installation <#installation>`__"
+msgstr ""
+
+#: ../../README_.rst:32
+msgid "`The Team <#the-team>`__"
+msgstr ""
+
+#: ../../README_.rst:35
+msgid "Background and Motivation"
+msgstr ""
+
+#: ../../README_.rst:37
+msgid ""
+"With the growing complexity of high-end supercomputers, the current "
+"system software stack faces significant challenges as we move forward to "
+"exascale and beyond. The necessity to deal with extreme degree of "
+"parallelism, heterogeneous architectures, multiple levels of memory "
+"hierarchy, power constraints, etc., advocates operating systems that can "
+"rapidly adapt to new hardware requirements, and that can support novel "
+"programming paradigms and runtime systems. On the other hand, a new class"
+" of more dynamic and complex applications are also on the horizon, with "
+"an increasing demand for application constructs such as in-situ analysis,"
+" workflows, elaborate monitoring and performance tools. This complexity "
+"relies not only on the rich features of POSIX, but also on the Linux APIs"
+" (such as the */proc*, */sys* filesystems, etc.) in particular."
+msgstr ""
+
+#: ../../README_.rst:52
+msgid "Two Traditional HPC OS Approaches"
+msgstr ""
+
+#: ../../README_.rst:54
+msgid ""
+"Traditionally, light-weight operating systems specialized for HPC "
+"followed two approaches to tackle scalable execution of large-scale "
+"applications. In the full weight kernel (FWK) approach, a full Linux "
+"environment is taken as the basis, and features that inhibit attaining "
+"HPC scalability are removed, i.e., making it light-weight. The pure "
+"light-weight kernel (LWK) approach, on the other hand, starts from "
+"scratch and effort is undertaken to add sufficient functionality so that "
+"it provides a familiar API, typically something close to that of a "
+"general purpose OS, while at the same time it retains the desired "
+"scalability and reliability attributes. Neither of these approaches "
+"yields a fully Linux compatible environment."
+msgstr ""
+
+#: ../../README_.rst:67
+msgid "The Multi-kernel Approach"
+msgstr ""
+
+#: ../../README_.rst:69
+msgid ""
+"A hybrid approach recognized recently by the system software community is"
+" to run Linux simultaneously with a lightweight kernel on compute nodes "
+"and multiple research projects are now pursuing this direction. The basic"
+" idea is that simulations run on an HPC tailored lightweight kernel, "
+"ensuring the necessary isolation for noiseless execution of parallel "
+"applications, but Linux is leveraged so that the full POSIX API is "
+"supported. Additionally, the small code base of the LWK can also "
+"facilitate rapid prototyping for new, exotic hardware features. "
+"Nevertheless, the questions of how to share node resources between the "
+"two types of kernels, where do device drivers execute, how exactly do the"
+" two kernels interact with each other and to what extent are they "
+"integrated, remain subjects of ongoing debate."
+msgstr ""
+
+#: ../../README_.rst:83
+msgid "Architectural Overview"
+msgstr ""
+
+#: ../../README_.rst:85
+msgid ""
+"At the heart of the stack is a low-level software infrastructure called "
+"Interface for Heterogeneous Kernels (IHK). IHK is a general framework "
+"that provides capabilities for partitioning resources in a many-core "
+"environment (e.g.,CPU cores and physical memory) and it enables "
+"management of lightweight kernels. IHK can allocate and release host "
+"resources dynamically and no reboot of the host machine is required when "
+"altering configuration. IHK also provides a low-level inter-kernel "
+"messaging infrastructure, called the Inter-Kernel Communication (IKC) "
+"layer. An architectural overview of the main system components is shown "
+"below."
+msgstr ""
+
+#: ../../README_.rst:99
+msgid "arch"
+msgstr ""
+
+#: ../../README_.rst:101
+msgid ""
+"McKernel is a lightweight kernel written from scratch. It is designed for"
+" HPC and is booted from IHK. McKernel retains a binary compatible ABI "
+"with Linux, however, it implements only a small set of performance "
+"sensitive system calls and the rest are offloaded to Linux. Specifically,"
+" McKernel has its own memory management, it supports processes and multi-"
+"threading with a simple round-robin cooperative (tick-less) scheduler, "
+"and it implements signaling. It also allows inter-process memory mappings"
+" and it provides interfaces to hardware performance counters."
+msgstr ""
+
+#: ../../README_.rst:112
+msgid "Functionality"
+msgstr ""
+
+#: ../../README_.rst:114
+msgid ""
+"An overview of some of the principal functionalities of the IHK/McKernel "
+"stack is provided below."
+msgstr ""
+
+#: ../../README_.rst:118
+msgid "System Call Offloading"
+msgstr ""
+
+#: ../../README_.rst:120
+msgid ""
+"System call forwarding in McKernel is implemented as follows. When an "
+"offloaded system call occurs, McKernel marshals the system call number "
+"along with its arguments and sends a message to Linux via a dedicated IKC"
+" channel. The corresponding proxy process running on Linux is by default "
+"waiting for system call requests through an ioctl() call into IHK’s "
+"system call delegator kernel module. The delegator kernel module’s IKC "
+"interrupt handler wakes up the proxy process, which returns to userspace "
+"and simply invokes the requested system call. Once it obtains the return "
+"value, it instructs the delegator module to send the result back to "
+"McKernel, which subsequently passes the value to user-space."
+msgstr ""
+
+#: ../../README_.rst:132
+msgid "Unified Address Space"
+msgstr ""
+
+#: ../../README_.rst:134
+msgid ""
+"The unified address space model in IHK/McKernel ensures that offloaded "
+"system calls can seamlessly resolve arguments even in case of pointers. "
+"This mechanism is depicted below and is implemented as follows."
+msgstr ""
+
+#: ../../README_.rst:141
+msgid "unified_ap"
+msgstr ""
+
+#: ../../README_.rst:143
+msgid ""
+"First, the proxy process is compiled as a position independent binary, "
+"which enables us to map the code and data segments specific to the proxy "
+"process to an address range which is explicitly excluded from McKernel’s "
+"user space. The grey box on the right side of the figure demonstrates the"
+" excluded region. Second, the entire valid virtual address range of "
+"McKernel’s application user-space is covered by a special mapping in the "
+"proxy process for which we use a pseudo file mapping in Linux. This "
+"mapping is indicated by the blue box on the left side of the figure."
+msgstr ""
+
+#: ../../README_.rst:153
+msgid "Installation"
+msgstr ""
+
+#: ../../README_.rst:155
+msgid ""
+"For a smooth experience, we recommend the following combination of OS "
+"distributions and platforms:"
+msgstr ""
+
+#: ../../README_.rst:158
+msgid "CentOS 7.3+ running on Intel Xeon, Xeon Phi, Fujitsu A64FX"
+msgstr ""
+
+#: ../../README_.rst:161
+msgid "1. Change SELinux settings"
+msgstr ""
+
+#: ../../README_.rst:163
+msgid "Log in as the root and disable SELinux:"
+msgstr ""
+
+#: ../../README_.rst:169
+msgid "Change the file to SELINUX=disabled"
+msgstr ""
+
+#: ../../README_.rst:172
+msgid "2. Reboot the host machine"
+msgstr ""
+
+#: ../../README_.rst:179
+msgid "3. Prepare packages, kernel symbol table file"
+msgstr ""
+
+#: ../../README_.rst:181
+msgid "You will need the following packages installed:"
+msgstr ""
+
+#: ../../README_.rst:187
+msgid ""
+"Note that to install libdwarf-devel to RHEL-8.2, you need to enable the "
+"CodeReady Linux Builder (CLB) repository and the EPEL repository with the"
+" following commands:"
+msgstr ""
+
+#: ../../README_.rst:195
+msgid "Grant read permission to the System.map file of your kernel version:"
+msgstr ""
+
+#: ../../README_.rst:202
+msgid "4. Obtain sources and compile the kernel"
+msgstr ""
+
+#: ../../README_.rst:204
+msgid "Clone the source code:"
+msgstr ""
+
+#: ../../README_.rst:212
+msgid "(Optional) Checkout to the specific branch or version:"
+msgstr ""
+
+#: ../../README_.rst:220
+msgid ""
+"Foe example, if you want to try the development branch, use “development”"
+" as the pathspec. If you want to try the prerelease version 1.7.0-0.2, "
+"use “1.7.0-0.2”."
+msgstr ""
+
+#: ../../README_.rst:225
+msgid "4.1 Install with cmake"
+msgstr ""
+
+#: ../../README_.rst:227
+msgid "Configure and compile:"
+msgstr ""
+
+#: ../../README_.rst:235
+msgid ""
+"The IHK kernel modules and McKernel kernel image should be installed "
+"under the **ihk+mckernel** folder in your home directory."
+msgstr ""
+
+#: ../../README_.rst:239
+msgid "4.2 Install with rpm"
+msgstr ""
+
+#: ../../README_.rst:241
+msgid "Build rpm:"
+msgstr ""
+
+#: ../../README_.rst:252
+msgid ""
+"The IHK kernel modules and McKernel kernel image are installed under the "
+"system directory."
+msgstr ""
+
+#: ../../README_.rst:256
+msgid "5. Boot McKernel"
+msgstr ""
+
+#: ../../README_.rst:258
+msgid ""
+"A boot script called mcreboot.sh is provided under sbin in the install "
+"folder. To boot on logical CPU 1 with 512MB of memory, use the following "
+"invocation:"
+msgstr ""
+
+#: ../../README_.rst:268
+msgid ""
+"You should see something similar like this if you display the McKernel’s "
+"kernel message log:"
+msgstr ""
+
+#: ../../README_.rst:296
+msgid "6. Run a simple program on McKernel"
+msgstr ""
+
+#: ../../README_.rst:298
+msgid ""
+"The mcexec command line tool (which is also the Linux proxy process) can "
+"be used for executing applications on McKernel:"
+msgstr ""
+
+#: ../../README_.rst:307
+msgid "7. Shutdown McKernel"
+msgstr ""
+
+#: ../../README_.rst:309
+msgid ""
+"Finally, to shutdown McKernel and release CPU/memory resources back to "
+"Linux use the following command:"
+msgstr ""
+
+#: ../../README_.rst:317
+msgid "8. Advanced: Enable Utility Thread offloading Interface (UTI)"
+msgstr ""
+
+#: ../../README_.rst:319
+msgid ""
+"UTI enables a runtime such as MPI runtime to spawn utility threads such "
+"as MPI asynchronous progress threads to Linux cores."
+msgstr ""
+
+#: ../../README_.rst:323
+msgid "8.1 Install capstone"
+msgstr ""
+
+#: ../../README_.rst:325
+msgid "Install EPEL capstone-devel:"
+msgstr ""
+
+#: ../../README_.rst:333
+msgid "8.2 Install syscall_intercept"
+msgstr ""
+
+#: ../../README_.rst:342
+msgid "8.3 Install UTI for McKernel"
+msgstr ""
+
+#: ../../README_.rst:344
+msgid "Install:"
+msgstr ""
+
+#: ../../README_.rst:354
+msgid "8.4 Install McKernel"
+msgstr ""
+
+#: ../../README_.rst:361
+msgid "8.5 Run executable"
+msgstr ""
+
+#: ../../README_.rst:368
+msgid "8.6 Install UTI for Linux for performance comparison"
+msgstr ""
+
+#: ../../README_.rst:370
+msgid "Install by make:"
+msgstr ""
+
+#: ../../README_.rst:379
+msgid "Install by rpm:"
+msgstr ""
+
+#: ../../README_.rst:391
+msgid "The Team"
+msgstr ""
+
+#: ../../README_.rst:393
+msgid ""
+"The McKernel project was started at The University of Tokyo and currently"
+" it is mainly developed at RIKEN. Some of our collaborators include:"
+msgstr ""
+
+#: ../../README_.rst:397
+msgid "Hitachi"
+msgstr ""
+
+#: ../../README_.rst:398
+msgid "Fujitsu"
+msgstr ""
+
+#: ../../README_.rst:399
+msgid "CEA (France)"
+msgstr ""
+
+#: ../../README_.rst:400
+msgid "NEC"
+msgstr ""
+
+#: ../../README_.rst:403
+msgid "License"
+msgstr ""
+
+#: ../../README_.rst:405
+msgid "McKernel is GPL licensed, as found in the LICENSE file."
+msgstr ""
+
+#: ../../README_.rst:408
+msgid "Contact"
+msgstr ""
+
+#: ../../README_.rst:410
+msgid ""
+"Please give your feedback to us via one of the following mailing lists. "
+"Subscription via `www.pccluster.org "
+"<http://www.pccluster.org/mailman/listinfo/mckernel-users>`__ is needed."
+msgstr ""
+
+#: ../../README_.rst:415
+msgid "English: mckernel-users@pccluster.org"
+msgstr ""
+
+#: ../../README_.rst:416
+msgid "Japanese: mckernel-users-jp@pccluster.org"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/archtecture.po

@@ -0,0 +1,101 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../archtecture.rst:2
+msgid "Architectural Overview"
+msgstr ""
+
+#: ../../archtecture.rst:4
+msgid ""
+"At the heart of the stack is a low-level software infrastructure called "
+"Interface for Heterogeneous Kernels (IHK). IHK is a general framework "
+"that provides capabilities for partitioning resources in a many-core "
+"environment (e.g.,CPU cores and physical memory) and it enables "
+"management of lightweight kernels. IHK can allocate and release host "
+"resources dynamically and no reboot of the host machine is required when "
+"altering configuration. IHK also provides a low-level inter-kernel "
+"messaging infrastructure, called the Inter-Kernel Communication (IKC) "
+"layer. An architectural overview of the main system components is shown "
+"below."
+msgstr ""
+
+#: ../../archtecture.rst:18
+msgid ""
+"McKernel is a lightweight kernel written from scratch. It is designed for"
+" HPC and is booted from IHK. McKernel retains a binary compatible ABI "
+"with Linux, however, it implements only a small set of performance "
+"sensitive system calls and the rest are offloaded to Linux. Specifically,"
+" McKernel has its own memory management, it supports processes and multi-"
+"threading with a simple round-robin cooperative (tick-less) scheduler, "
+"and it implements signaling. It also allows inter-process memory mappings"
+" and it provides interfaces to hardware performance counters."
+msgstr ""
+
+#: ../../archtecture.rst:29
+msgid "Functionality"
+msgstr ""
+
+#: ../../archtecture.rst:31
+msgid ""
+"An overview of some of the principal functionalities of the IHK/McKernel "
+"stack is provided below."
+msgstr ""
+
+#: ../../archtecture.rst:35
+msgid "System Call Offloading"
+msgstr ""
+
+#: ../../archtecture.rst:37
+msgid ""
+"System call forwarding in McKernel is implemented as follows. When an "
+"offloaded system call occurs, McKernel marshals the system call number "
+"along with its arguments and sends a message to Linux via a dedicated IKC"
+" channel. The corresponding proxy process running on Linux is by default "
+"waiting for system call requests through an ioctl() call into IHK’s "
+"system call delegator kernel module. The delegator kernel module’s IKC "
+"interrupt handler wakes up the proxy process, which returns to userspace "
+"and simply invokes the requested system call. Once it obtains the return "
+"value, it instructs the delegator module to send the result back to "
+"McKernel, which subsequently passes the value to user-space."
+msgstr ""
+
+#: ../../archtecture.rst:49
+msgid "Unified Address Space"
+msgstr ""
+
+#: ../../archtecture.rst:51
+msgid ""
+"The unified address space model in IHK/McKernel ensures that offloaded "
+"system calls can seamlessly resolve arguments even in case of pointers. "
+"This mechanism is depicted below and is implemented as follows."
+msgstr ""
+
+#: ../../archtecture.rst:58
+msgid ""
+"First, the proxy process is compiled as a position independent binary, "
+"which enables us to map the code and data segments specific to the proxy "
+"process to an address range which is explicitly excluded from McKernel’s "
+"user space. The grey box on the right side of the figure demonstrates the"
+" excluded region. Second, the entire valid virtual address range of "
+"McKernel’s application user-space is covered by a special mapping in the "
+"proxy process for which we use a pseudo file mapping in Linux. This "
+"mapping is indicated by the blue box on the left side of the figure."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/background.po

@@ -0,0 +1,79 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../background.rst:2
+msgid "Background and Motivation"
+msgstr ""
+
+#: ../../background.rst:4
+msgid ""
+"With the growing complexity of high-end supercomputers, the current "
+"system software stack faces significant challenges as we move forward to "
+"exascale and beyond. The necessity to deal with extreme degree of "
+"parallelism, heterogeneous architectures, multiple levels of memory "
+"hierarchy, power constraints, etc., advocates operating systems that can "
+"rapidly adapt to new hardware requirements, and that can support novel "
+"programming paradigms and runtime systems. On the other hand, a new class"
+" of more dynamic and complex applications are also on the horizon, with "
+"an increasing demand for application constructs such as in-situ analysis,"
+" workflows, elaborate monitoring and performance tools. This complexity "
+"relies not only on the rich features of POSIX, but also on the Linux APIs"
+" (such as the */proc*, */sys* filesystems, etc.) in particular."
+msgstr ""
+
+#: ../../background.rst:19
+msgid "Two Traditional HPC OS Approaches"
+msgstr ""
+
+#: ../../background.rst:21
+msgid ""
+"Traditionally, light-weight operating systems specialized for HPC "
+"followed two approaches to tackle scalable execution of large-scale "
+"applications. In the full weight kernel (FWK) approach, a full Linux "
+"environment is taken as the basis, and features that inhibit attaining "
+"HPC scalability are removed, i.e., making it light-weight. The pure "
+"light-weight kernel (LWK) approach, on the other hand, starts from "
+"scratch and effort is undertaken to add sufficient functionality so that "
+"it provides a familiar API, typically something close to that of a "
+"general purpose OS, while at the same time it retains the desired "
+"scalability and reliability attributes. Neither of these approaches "
+"yields a fully Linux compatible environment."
+msgstr ""
+
+#: ../../background.rst:34
+msgid "The Multi-kernel Approach"
+msgstr ""
+
+#: ../../background.rst:36
+msgid ""
+"A hybrid approach recognized recently by the system software community is"
+" to run Linux simultaneously with a lightweight kernel on compute nodes "
+"and multiple research projects are now pursuing this direction. The basic"
+" idea is that simulations run on an HPC tailored lightweight kernel, "
+"ensuring the necessary isolation for noiseless execution of parallel "
+"applications, but Linux is leveraged so that the full POSIX API is "
+"supported. Additionally, the small code base of the LWK can also "
+"facilitate rapid prototyping for new, exotic hardware features. "
+"Nevertheless, the questions of how to share node resources between the "
+"two types of kernels, where do device drivers execute, how exactly do the"
+" two kernels interact with each other and to what extent are they "
+"integrated, remain subjects of ongoing debate."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/boot_run_shutdown.po

@@ -0,0 +1,57 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../boot_run_shutdown.rst:2
+msgid "Boot McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:4
+msgid ""
+"A boot script called ``mcreboot.sh`` is provided under ``sbin`` in the "
+"install folder. To boot on logical CPU 1 with 512MB of memory, use the "
+"following invocation:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:14
+msgid ""
+"You should see something similar like this if you display the McKernel’s "
+"kernel message log:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:42
+msgid "Run a simple program on McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:44
+msgid ""
+"The mcexec command line tool (which is also the Linux proxy process) can "
+"be used for executing applications on McKernel:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:53
+msgid "Shutdown McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:55
+msgid ""
+"Finally, to shutdown McKernel and release CPU/memory resources back to "
+"Linux use the following command:"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/contact.po

@@ -0,0 +1,39 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../contact.rst:2
+msgid "Contact"
+msgstr ""
+
+#: ../../contact.rst:4
+msgid ""
+"Please give your feedback to us via one of the following mailing lists. "
+"Subscription via `www.pccluster.org "
+"<http://www.pccluster.org/mailman/listinfo/mckernel-users>`__ is needed."
+msgstr ""
+
+#: ../../contact.rst:9
+msgid "English: mckernel-users@pccluster.org"
+msgstr ""
+
+#: ../../contact.rst:10
+msgid "Japanese: mckernel-users-jp@pccluster.org"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/cover.po

@@ -0,0 +1,59 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../summary.rst:1
+msgid ""
+"IHK/McKernel is a light-weight multi-kernel operating system designed for"
+" high-end supercomputing. It runs Linux and McKernel, a light-weight "
+"kernel (LWK), side-by-side inside compute nodes and aims at the "
+"following:"
+msgstr ""
+
+#: ../../summary.rst:6
+msgid ""
+"Provide scalable and consistent execution of large-scale parallel "
+"scientific applications, but at the same time maintain the ability to "
+"rapidly adapt to new hardware features and emerging programming models"
+msgstr ""
+
+#: ../../summary.rst:10
+msgid ""
+"Provide efficient memory and device management so that resource "
+"contention and data movement are minimized at the system level"
+msgstr ""
+
+#: ../../summary.rst:12
+msgid ""
+"Eliminate OS noise by isolating OS services in Linux and provide jitter "
+"free execution on the LWK"
+msgstr ""
+
+#: ../../summary.rst:14
+msgid ""
+"Support the full POSIX/Linux APIs by selectively offloading (slow-path) "
+"system calls to Linux"
+msgstr ""
+
+#: ../../cover.rst:5
+msgid ""
+"See `Quick Guide -- Installation <quick.html#installation>`__ for jump "
+"start."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/doc.po

@@ -0,0 +1,28 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../doc.rst:2
+msgid "Documentation"
+msgstr ""
+
+#: ../../doc.rst:4
+msgid "Documentation is available `here <https://ihkmckernel.readthedocs.io>`__."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/ihk_developers.po

@@ -0,0 +1,40 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../ihk_developers.rst:6
+msgid "External Specs"
+msgstr ""
+
+#: ../../ihk_developers.rst:9
+msgid "Overview"
+msgstr ""
+
+#: ../../ihk_developers.rst:12
+msgid "Function Specs"
+msgstr ""
+
+#: ../../ihk_developers.rst:15
+msgid "Command / Daemon Specs"
+msgstr ""
+
+#: ../../ihk_developers.rst:18
+msgid "Booting LWK"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/index.po

@@ -0,0 +1,95 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-07 10:00+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../index.rst:12
+msgid "Quick Guide"
+msgstr "クイックガイド"
+
+#: ../../index.rst:18
+msgid "Users' Guide"
+msgstr "ユーザガイド"
+
+#: ../../index.rst:24
+msgid "Operators' Guide"
+msgstr "運用ガイド"
+
+#: ../../index.rst:30
+msgid "IHK Developers' Guide"
+msgstr ""
+
+#: ../../index.rst:36
+msgid "McKernel Developers' Guide"
+msgstr ""
+
+#: ../../index.rst:42
+msgid "IHK Specifications"
+msgstr ""
+
+#: ../../index.rst:48
+msgid "McKernel Specifications"
+msgstr ""
+
+#: ../../index.rst:54
+msgid "What's New"
+msgstr ""
+
+#: ../../index.rst:8
+msgid "IHK/McKernel"
+msgstr ""
+
+#: ../../summary.rst:1
+msgid ""
+"IHK/McKernel is a light-weight multi-kernel operating system designed for"
+" high-end supercomputing. It runs Linux and McKernel, a light-weight "
+"kernel (LWK), side-by-side inside compute nodes and aims at the "
+"following:"
+msgstr ""
+
+#: ../../summary.rst:6
+msgid ""
+"Provide scalable and consistent execution of large-scale parallel "
+"scientific applications, but at the same time maintain the ability to "
+"rapidly adapt to new hardware features and emerging programming models"
+msgstr ""
+
+#: ../../summary.rst:10
+msgid ""
+"Provide efficient memory and device management so that resource "
+"contention and data movement are minimized at the system level"
+msgstr ""
+
+#: ../../summary.rst:12
+msgid ""
+"Eliminate OS noise by isolating OS services in Linux and provide jitter "
+"free execution on the LWK"
+msgstr ""
+
+#: ../../summary.rst:14
+msgid ""
+"Support the full POSIX/Linux APIs by selectively offloading (slow-path) "
+"system calls to Linux"
+msgstr ""
+
+#: ../../cover.rst:5
+msgid ""
+"See `Quick Guide -- Installation <quick.html#installation>`__ for jump "
+"start."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/install.po

@@ -0,0 +1,191 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../install.rst:4
+msgid "Installation"
+msgstr "インストール"
+
+#: ../../install.rst:6
+msgid "The following OS distributions and platforms are recommended:"
+msgstr "推奨OSディストリビューションとプロセッサは以下の通り。"
+
+#: ../../install.rst:8
+msgid "OS distribution"
+msgstr ""
+
+#: ../../install.rst:10
+msgid "CentOS 7.3 or later"
+msgstr ""
+
+#: ../../install.rst:11
+msgid "RHEL 7.3 or later"
+msgstr ""
+
+#: ../../install.rst:13
+msgid "Platform"
+msgstr ""
+
+#: ../../install.rst:15
+msgid "Intel Xeon"
+msgstr ""
+
+#: ../../install.rst:16
+msgid "Intel Xeon Phi"
+msgstr ""
+
+#: ../../install.rst:17
+msgid "Fujitsu A64FX"
+msgstr ""
+
+#: ../../install.rst:20
+msgid "Prepare files for building McKernel"
+msgstr ""
+
+#: ../../install.rst:22
+msgid ""
+"Grant read permission to the System.map file of your kernel version on "
+"the build machine:"
+msgstr ""
+
+#: ../../install.rst:28
+msgid "Install the following packages to the build machine:"
+msgstr ""
+
+#: ../../install.rst:35 ../../install.rst:179
+msgid "When having access to repositories"
+msgstr ""
+
+#: ../../install.rst:37 ../../install.rst:181
+msgid "On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:"
+msgstr ""
+
+#: ../../install.rst:43 ../../install.rst:187
+msgid "On CentOS 8, enable the PowerTools repository:"
+msgstr ""
+
+#: ../../install.rst:49 ../../install.rst:193
+msgid "Install with yum:"
+msgstr ""
+
+#: ../../install.rst:56 ../../install.rst:200
+msgid "When not having access to repositories"
+msgstr ""
+
+#: ../../install.rst:58
+msgid ""
+"Ask the system administrator to install them. Note that ``libdwarf-"
+"devel`` is in the CodeReady Linux Builder repository on RHEL 8 or in the "
+"PowerTools repository on CentOS 8."
+msgstr ""
+
+#: ../../install.rst:61
+msgid "Clone, compile, install"
+msgstr ""
+
+#: ../../install.rst:63
+msgid "Clone the source code:"
+msgstr ""
+
+#: ../../install.rst:71
+msgid "(Optional) Checkout to the specific branch or version:"
+msgstr ""
+
+#: ../../install.rst:79
+msgid ""
+"Foe example, if you want to try the development branch, use “development”"
+" as the pathspec. If you want to try the prerelease version 1.7.0-0.2, "
+"use “1.7.0-0.2”."
+msgstr ""
+
+#: ../../install.rst:83
+msgid "Move to build directory:"
+msgstr ""
+
+#: ../../install.rst:89
+msgid "Run cmake:"
+msgstr ""
+
+#: ../../install.rst:92 ../../install.rst:135
+msgid "When not cross-compiling:"
+msgstr ""
+
+#: ../../install.rst:99 ../../install.rst:142
+msgid "When cross-compiling:"
+msgstr ""
+
+#: ../../install.rst:111
+msgid "Install with cmake"
+msgstr ""
+
+#: ../../install.rst:113
+msgid "Install with make:"
+msgstr ""
+
+#: ../../install.rst:119
+msgid ""
+"The kernel modules and McKernel kernel image should be installed under "
+"the **ihk+mckernel** folder in your home directory."
+msgstr ""
+
+#: ../../install.rst:123
+msgid "Install with rpm"
+msgstr ""
+
+#: ../../install.rst:125
+msgid "Create the tarball and the spec file:"
+msgstr ""
+
+#: ../../install.rst:132
+msgid "Create the rpm package:"
+msgstr ""
+
+#: ../../install.rst:148
+msgid "Install the rpm package:"
+msgstr ""
+
+#: ../../install.rst:154
+msgid ""
+"The kernel modules and McKernel kernel image are installed under the "
+"standard system directories."
+msgstr ""
+
+#: ../../install.rst:158
+msgid "Prepare files and change settings for installing McKernel"
+msgstr ""
+
+#: ../../install.rst:160
+msgid "Disable SELinux of the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:166
+msgid "Change the file to SELINUX=disabled. And then reboot the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:172
+msgid "Install the following packages to the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:202
+msgid ""
+"Ask the system administrator to install them. Note that ``libdwarf`` is "
+"in the CodeReady Linux Builder repository on RHEL 8 or in the PowerTools "
+"repository on CentOS 8."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/license.po

@@ -0,0 +1,28 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../license.rst:2
+msgid "License"
+msgstr ""
+
+#: ../../license.rst:4
+msgid "McKernel is GPL licensed, as found in the LICENSE file."
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/logo.po

@@ -0,0 +1,20 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+

docs/locales/ja/LC_MESSAGES/mckernel_developers.po

@@ -0,0 +1,28 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../mckernel_developers.rst:6
+msgid "Interfaces"
+msgstr ""
+
+#: ../../mckernel_developers.rst:9
+msgid "Interface details"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/operators.po

@@ -0,0 +1,886 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-07 10:26+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../operators.rst:5
+#, fuzzy
+msgid "This document will explain how to operate system with McKernel."
+msgstr "McKernelを用いたシステムを運用するシステム管理者を対象として、運用手順を説明する。"
+
+#: ../../operators.rst:8
+msgid "Installation"
+msgstr "インストール"
+
+#: ../../operators.rst:10
+msgid "See `Quick Guide -- Installation <quick.html#installation>`__."
+msgstr "`クイックガイド ―  インストール <quick.html#installation>`__ に記載する。"
+
+#: ../../uti.rst:2
+msgid "Advanced: Enable Utility Thread offloading Interface (UTI)"
+msgstr ""
+
+#: ../../uti.rst:4
+msgid ""
+"UTI enables a runtime such as MPI runtime to spawn utility threads such "
+"as MPI asynchronous progress threads to Linux cores."
+msgstr ""
+
+#: ../../uti.rst:8
+msgid "Install capstone"
+msgstr ""
+
+#: ../../uti.rst:11 ../../uti.rst:22
+msgid "When compute nodes don't have access to repositories"
+msgstr ""
+
+#: ../../uti.rst:13
+msgid "Install EPEL capstone-devel:"
+msgstr ""
+
+#: ../../uti.rst:24
+msgid ""
+"Ask the system administrator to install ``capstone-devel``. Note that it "
+"is in the EPEL repository."
+msgstr ""
+
+#: ../../uti.rst:28
+msgid "Install syscall_intercept"
+msgstr ""
+
+#: ../../uti.rst:37
+msgid "Install UTI for McKernel"
+msgstr ""
+
+#: ../../uti.rst:39
+msgid "Install:"
+msgstr ""
+
+#: ../../uti.rst:49
+msgid "Install McKernel"
+msgstr ""
+
+#: ../../uti.rst:51
+msgid "Add ``-DENABLE_UTI=ON`` option to ``cmake``:"
+msgstr ""
+
+#: ../../uti.rst:58
+msgid "Run programs"
+msgstr ""
+
+#: ../../uti.rst:60
+msgid "Add ``--enable-uti`` option to ``mcexec``:"
+msgstr ""
+
+#: ../../uti.rst:67
+msgid "Install UTI for Linux"
+msgstr ""
+
+#: ../../uti.rst:69
+msgid ""
+"You should skip this step if it's already installed as with, for example,"
+" Fujitsu Technical Computing Suite."
+msgstr ""
+
+#: ../../uti.rst:72
+msgid "Install by make"
+msgstr ""
+
+#: ../../uti.rst:82
+msgid "Install by rpm"
+msgstr ""
+
+#: ../../operators.rst:15
+msgid "Boot and Shut-down"
+msgstr "起動停止"
+
+#: ../../operators.rst:18
+msgid "Related files"
+msgstr "関連ファイル"
+
+#: ../../operators.rst:20
+msgid ""
+"In the followings, the install directory of IHK/McKernel is shown as "
+"``<install>`` . The kernel modules and their locations are as follows."
+msgstr "以降、IHK/McKernelのインストールディレクトリを<install>とする。SMPプロセッサ向け、x86_64アーキ向けの関連ファイルの場所は以下の通り。"
+
+#: ../../operators.rst:24
+msgid "<install>/kmod/ihk.ko"
+msgstr ""
+
+#: ../../operators.rst:24
+msgid "IHK-master core"
+msgstr ""
+
+#: ../../operators.rst:26
+msgid "|ihk-smp|"
+msgstr ""
+
+#: ../../operators.rst:26
+msgid "IHK-master driver"
+msgstr ""
+
+#: ../../operators.rst:29
+msgid "|mcctrl|"
+msgstr ""
+
+#: ../../operators.rst:29
+msgid "Delegator module"
+msgstr ""
+
+#: ../../operators.rst:32
+msgid "|mckernel.img|"
+msgstr ""
+
+#: ../../operators.rst:32
+msgid "Kernel Image"
+msgstr "カーネルイメージ"
+
+#: ../../operators.rst:40
+msgid "The commands and daemons for operation and their locations are as follows."
+msgstr "運用向けコマンド・デーモンのファイルの場所は以下の通り。"
+
+#: ../../operators.rst:43
+msgid "|mcreboot|"
+msgstr ""
+
+#: ../../operators.rst:43
+msgid "Boot script"
+msgstr "起動スクリプト"
+
+#: ../../operators.rst:46
+msgid "|mcstop|"
+msgstr ""
+
+#: ../../operators.rst:46
+msgid "Shutdown script"
+msgstr "シャットダウンスクリプト"
+
+#: ../../operators.rst:49
+msgid "<install>/bin/mcexec"
+msgstr ""
+
+#: ../../operators.rst:49
+msgid "Process invocation command"
+msgstr "プロセス起動コマンド"
+
+#: ../../operators.rst:51
+msgid "<install>/bin/eclair"
+msgstr ""
+
+#: ../../operators.rst:51
+msgid "Kernel dump analysis tool"
+msgstr "カーネルダンプ解析ツール"
+
+#: ../../operators.rst:53
+msgid "|vmcore2mckdump|"
+msgstr ""
+
+#: ../../operators.rst:53
+msgid "Kernel dump format conversion tool"
+msgstr "カーネルダンプ形式変換ツール"
+
+#: ../../operators.rst:60
+msgid "以下、関連コマンドおよび関連関数のインターフェイスを説明する。"
+msgstr ""
+
+#: ../../operators.rst:63
+msgid "インターフェイス"
+msgstr ""
+
+#: ../../operators.rst:66
+msgid "カーネル引数"
+msgstr ""
+
+#: ../../operators.rst:68
+msgid "McKernelのカーネル引数を表 :numref:`tab-kargs` に示す。"
+msgstr ""
+
+#: ../../operators.rst:72
+msgid "McKernelのカーネル引数"
+msgstr ""
+
+#: ../../operators.rst:75
+msgid "hidos"
+msgstr ""
+
+#: ../../operators.rst:75
+msgid "IKCを有効にする。"
+msgstr ""
+
+#: ../../operators.rst:77
+msgid "|dlv|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "Linuxのpanicハンドラ経由でダンプを行った場合の、ダ"
+msgstr ""
+
+#: ../../operators.rst
+msgid "ンプ対象とするメモリ領域の種類を<level>に設定する。"
+msgstr ""
+
+#: ../../operators.rst
+msgid "設定可能な値は以下の通り。"
+msgstr ""
+
+#: ../../operators.rst:83 ../../operators.rst:164 ../../operators.rst:196
+#: ../../operators.rst:234
+msgid "0"
+msgstr ""
+
+#: ../../operators.rst:84 ../../operators.rst:165
+msgid "IHKがMcKernelに割り当てたメモリ領域を出力する"
+msgstr ""
+
+#: ../../operators.rst:85 ../../operators.rst:166
+msgid "24"
+msgstr ""
+
+#: ../../operators.rst:86 ../../operators.rst:167
+msgid "カーネルが使用しているメモリ領域を出力する"
+msgstr ""
+
+#: ../../operators.rst:88 ../../operators.rst:169
+msgid "指定がなかった場合は24が用いられる。"
+msgstr ""
+
+#: ../../operators.rst:90
+msgid "|allow|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "McKernelに割り当てられたCPU数より大きい数のスレッド"
+msgstr ""
+
+#: ../../operators.rst
+msgid "またはプロセスの生成を許可する。この引数が指定され"
+msgstr ""
+
+#: ../../operators.rst
+msgid "ない場合に、CPU数より大きい数のスレッドまたはプロセ"
+msgstr ""
+
+#: ../../operators.rst
+msgid "スをclone(), fork(), vfork()などで生成しようとする"
+msgstr ""
+
+#: ../../operators.rst
+msgid "と、当該システムコールがEINVALエラーを返す。"
+msgstr ""
+
+#: ../../operators.rst:102
+msgid "ブートスクリプト"
+msgstr "ブートスクリプト"
+
+#: ../../operators.rst:105 ../../operators.rst:207
+msgid "書式"
+msgstr ""
+
+#: ../../operators.rst:113 ../../operators.rst:217
+msgid "オプション"
+msgstr ""
+
+#: ../../operators.rst:116
+msgid "|opt-c|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "McKernelに割り当てるCPUのリストを指定する。フォー"
+msgstr ""
+
+#: ../../operators.rst
+msgid "マットは以下の通り。"
+msgstr ""
+
+#: ../../operators.rst
+msgid "<CPU logical id>,<CPU logical id>...または"
+msgstr ""
+
+#: ../../operators.rst
+msgid "<CPU logical id>-<CPU logical id>,<CPU logical id>"
+msgstr ""
+
+#: ../../operators.rst
+msgid "-<CPU logical id>...または両者の混合。"
+msgstr ""
+
+#: ../../operators.rst:122
+msgid "|opt-r|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "McKernelのCPUがIKCメッセージを送るLinux"
+msgstr ""
+
+#: ../../operators.rst
+msgid "CPUを指定する。フォーマットは以下の通り。"
+msgstr ""
+
+#: ../../operators.rst
+msgid "<CPU list>:<CPU id>+<CPU list>:<CPU id>..."
+msgstr ""
+
+#: ../../operators.rst
+msgid "<CPU list>のフォーマットは-cオプションにおけるもの"
+msgstr ""
+
+#: ../../operators.rst
+msgid "と同じである。"
+msgstr ""
+
+#: ../../operators.rst
+msgid "各<CPU list>:<CPU id>は<CPU list>で示されるMcKernel"
+msgstr ""
+
+#: ../../operators.rst
+msgid "のCPUが<CPU logical id>で示されるLinuxのCPUにIKC"
+msgstr ""
+
+#: ../../operators.rst
+msgid "メッセージを送信することを意味する。"
+msgstr ""
+
+#: ../../operators.rst:131
+msgid "|opt-m|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "McKernelに割り当てるメモリ領域を指定する。フォーマッ"
+msgstr ""
+
+#: ../../operators.rst
+msgid "トは以下の通り。"
+msgstr ""
+
+#: ../../operators.rst
+msgid "<size>@<NUMA-id>, <size>@<NUMA-id>..."
+msgstr ""
+
+#: ../../operators.rst:135
+msgid "|opt-f|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "ihkmondが使用するsyslogプロトコルのfacilityを指定す"
+msgstr ""
+
+#: ../../operators.rst
+msgid "る。デフォルトはLOG_LOCAL6。"
+msgstr ""
+
+#: ../../operators.rst:138
+msgid "|opt-o|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "IHKのデバイスファイル(/dev/mcd*, /dev/mcos*)のオー"
+msgstr ""
+
+#: ../../operators.rst
+msgid "ナーとグループの値を<user>[:<group>]の形式で指定す"
+msgstr ""
+
+#: ../../operators.rst
+msgid "る。デフォルトはmcreboot.shを実行したユーザ。"
+msgstr ""
+
+#: ../../operators.rst:142
+msgid "|opt-i|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "ihkmondがハングアップ検知のためにOS状態を確認する時"
+msgstr ""
+
+#: ../../operators.rst
+msgid "間間隔を秒単位で指定する。-1が指定された場合はハン"
+msgstr ""
+
+#: ../../operators.rst
+msgid "グアップ検知を行わない。指定がない場合はハングアッ"
+msgstr ""
+
+#: ../../operators.rst
+msgid "プ検知を行わない。"
+msgstr ""
+
+#: ../../operators.rst:147
+msgid "|opt-k|"
+msgstr ""
+
+#: ../../operators.rst
+msgid "カーネルメッセージの/dev/logへのリダイレクト有無を"
+msgstr ""
+
+#: ../../operators.rst
+msgid "指定する。0が指定された場合はリダイレクトを行わず、"
+msgstr ""
+
+#: ../../operators.rst
+msgid "0以外が指定された場合はリダイレクトを行う。指定がな"
+msgstr ""
+
+#: ../../operators.rst
+msgid "い場合はリダイレクトを行わない。"
+msgstr ""
+
+#: ../../operators.rst:152
+msgid "-q <irq>"
+msgstr ""
+
+#: ../../operators.rst
+msgid "IHKが使用するIRQ番号を指定する。指定がない場合は"
+msgstr ""
+
+#: ../../operators.rst
+msgid "64-255の範囲で空いているものを使用する。"
+msgstr ""
+
+#: ../../operators.rst:155
+msgid "-t"
+msgstr ""
+
+#: ../../operators.rst
+msgid "（x86_64アーキテクチャのみ）Turbo"
+msgstr ""
+
+#: ../../operators.rst
+msgid "Boostをオンにする。デフォルトはオフ。"
+msgstr ""
+
+#: ../../operators.rst:158
+msgid "-d <level>"
+msgstr ""
+
+#: ../../operators.rst:171
+msgid "-O"
+msgstr ""
+
+#: ../../operators.rst
+msgid "またはプロセスの生成を許可する。指定がない場合は許可"
+msgstr ""
+
+#: ../../operators.rst
+msgid "しない。すなわち、CPU数より大きい数のスレッドまたは"
+msgstr ""
+
+#: ../../operators.rst
+msgid "プロセスを生成しようとするとエラーとなる。"
+msgstr ""
+
+#: ../../operators.rst:187 ../../operators.rst:224
+msgid "説明"
+msgstr ""
+
+#: ../../operators.rst:189
+msgid ""
+"McKernel関連カーネルモジュールをinsmodし、<cpulist>で指定されたCPUと<memlist>で指定されたメモリ領域からなるパーティションを作成し、IKC"
+" mapを<ikcmap>に設定し、前記パーティションにMcKernelをブートする。"
+msgstr ""
+
+#: ../../operators.rst:193 ../../operators.rst:231
+msgid "戻り値"
+msgstr ""
+
+#: ../../operators.rst:196 ../../operators.rst:234
+msgid "正常終了"
+msgstr ""
+
+#: ../../operators.rst:198 ../../operators.rst:236
+msgid "0以外"
+msgstr ""
+
+#: ../../operators.rst:198 ../../operators.rst:236
+msgid "エラー"
+msgstr ""
+
+#: ../../operators.rst:202
+msgid "シャットダウンスクリプト"
+msgstr "シャットダウンスクリプト"
+
+#: ../../operators.rst:219
+msgid "なし"
+msgstr ""
+
+#: ../../operators.rst:226
+msgid "McKernelをシャットダウンし、McKernel用パーティションを削除し、関連カーネルモジュールをrmmodする。"
+msgstr ""
+
+#: ../../operators.rst:240
+msgid "プロセス起動コマンド"
+msgstr ""
+
+#: ../../operators.rst:245
+msgid "ダンプ解析コマンド"
+msgstr ""
+
+#: ../../operators.rst:250
+msgid "ダンプ形式変換コマンド"
+msgstr ""
+
+#: ../../operators.rst:255
+msgid "ブート手順"
+msgstr ""
+
+#: ../../operators.rst:257
+msgid "mcreboot.shを用いてブート手順を説明する。"
+msgstr ""
+
+#: ../../operators.rst:259 ../../operators.rst:906
+msgid "スクリプトは以下の通り。"
+msgstr ""
+
+#: ../../operators.rst:852 ../../operators.rst:1050
+msgid "手順は以下の通り。"
+msgstr ""
+
+#: ../../operators.rst:854
+msgid "ihkmondを起動する。ihkmondは任意のタイミングで起動してよい。これは、ihkmondはOSインスタンスの作成を検知して動作を開始するためである。（83行目）"
+msgstr ""
+
+#: ../../operators.rst:856
+msgid "Linuxのカーネルバージョンが、mcoverlayfsが動作するものであるかを確認する。（200–216行目）"
+msgstr ""
+
+#: ../../operators.rst:858
+msgid "irqbalanceを停止する。（251–257行目）"
+msgstr ""
+
+#: ../../operators.rst:860
+msgid ""
+"/proc/irq/[n]/affinityの設定を保存した上でMcKernel "
+"CPUを担当から外す。担当CPUが無くなる場合は、全てのLinux CPUを指定する。（269–303行目）"
+msgstr ""
+
+#: ../../operators.rst:864
+msgid "ihk.koをinsmodする。（307行目）"
+msgstr ""
+
+#: ../../operators.rst:866
+msgid "Linuxによるメモリフラグメンテーションを緩和するために以下を実施する。（313–320行目）"
+msgstr ""
+
+#: ../../operators.rst:868
+msgid "アクティブでないプロセスを積極的にスワップアウトするように設定する"
+msgstr ""
+
+#: ../../operators.rst:870
+msgid "クリーンなページキャッシュを無効化し、またdentriesやinodeのslabオブジェクトのうち可能なものを破棄する"
+msgstr ""
+
+#: ../../operators.rst:872
+msgid "連続する空き領域を結合してより大きな空き領域にまとめる"
+msgstr ""
+
+#: ../../operators.rst:874
+msgid ""
+"ihk-smp-x86.koをinsmodする。（340行目）ihk-smp-x86.koは関数をihk.koに登録する。このため、ihk-"
+"smp-x86.koはihk.koをinsmodした後にinsmodする必要がある。"
+msgstr ""
+
+#: ../../operators.rst:876
+msgid "メモリを予約する。（370行目）"
+msgstr ""
+
+#: ../../operators.rst:878
+msgid "CPUを予約する。（374行目）"
+msgstr ""
+
+#: ../../operators.rst:880
+msgid "McKernelのカーネルモジュールmcctrl.koをinsmodする。（382行目）mcctrl.koはMcKernelブート時に呼ばれる関数をihk.koに登録する。このため、mcctrl.koのinsmodはihk.koのinsmodの後に、またブートの前に行う必要がある。"
+msgstr ""
+
+#: ../../operators.rst:882
+msgid "OSインスタンスを作成する。（406行目）"
+msgstr ""
+
+#: ../../operators.rst:884
+msgid "OSインスタンスにCPUを割り当てる。（412行目）"
+msgstr ""
+
+#: ../../operators.rst:886
+msgid "McKernel CPUのIKCメッセージ送信先のLinux CPUを設定する。（419行目）"
+msgstr ""
+
+#: ../../operators.rst:888
+msgid "OSインスタンスにメモリを割り当てる。（426行目）"
+msgstr ""
+
+#: ../../operators.rst:890
+msgid "カーネルイメージをロードする。（432行目）"
+msgstr ""
+
+#: ../../operators.rst:892
+msgid "カーネル引数をカーネルに渡す。（438行目）"
+msgstr ""
+
+#: ../../operators.rst:894
+msgid "カーネルをブートする。（444行目）"
+msgstr ""
+
+#: ../../operators.rst:896
+msgid ""
+"/proc, "
+"/sysファイルの準備をする。また、その中でmcoverlayfs.koをinsmodする。mcoverlayfs.koは他モジュールとの依存関係を持たない。（454行目から567行目）なお、関数インターフェイスでの対応関数はihk_os_create_pseudofs()である。"
+msgstr ""
+
+#: ../../operators.rst:898
+msgid "irqbalanceを、Linux CPUのみを対象とする設定で開始する。（569–587行目）"
+msgstr ""
+
+#: ../../operators.rst:902
+msgid "シャットダウン手順"
+msgstr ""
+
+#: ../../operators.rst:904
+msgid "mcstop+release.shを用いてシャットダウン手順を説明する。"
+msgstr ""
+
+#: ../../operators.rst:1052
+msgid "ブート時にLinux CPUのみを対象とする設定で開始されたirqbalanceを停止する。（24–33行目）"
+msgstr ""
+
+#: ../../operators.rst:1055
+msgid "全てのOSインスタンスを破壊する。OSインスタンスに割り当てられていた資源はIHKがLWKのために予約した状態に移行する。（35–50行目）"
+msgstr ""
+
+#: ../../operators.rst:1057
+msgid "IHKがLWKのために予約していた資源を開放する。（52–77行目）"
+msgstr ""
+
+#: ../../operators.rst:1059
+msgid "mcctrl.koをrmmodする。（81行目）"
+msgstr ""
+
+#: ../../operators.rst:1061
+msgid ""
+"/proc, "
+"/sysファイルの準備をする。また、その中でmcoverlayfs.koをrmmodする。（87–100行目）なお、関数インターフェイスでの対応関数はihk_os_destroy_pseudofs()である。"
+msgstr ""
+
+#: ../../operators.rst:1063
+msgid "ihk-smp-x86.koをrmmodする。（104行目）"
+msgstr ""
+
+#: ../../operators.rst:1065
+msgid "ihk.koをrmmodする。（112行目）"
+msgstr ""
+
+#: ../../operators.rst:1067
+msgid "ihkmondを停止する。（121行目）"
+msgstr ""
+
+#: ../../operators.rst:1069
+msgid "/proc/irq/[n]/affinityの設定をブート時に保存しておいたものに戻し、ブート前の設定でirqbalanceを開始する。（124–135行目）"
+msgstr ""
+
+#: ../../operators.rst:1071
+msgid "Linuxカーネルのスワップアウト積極度の設定をデフォルトの値に戻す。（138行目）"
+msgstr ""
+
+#~ msgid "The following OS distributions and platforms are recommended:"
+#~ msgstr ""
+
+#~ msgid "OS distribution"
+#~ msgstr ""
+
+#~ msgid "CentOS 7.3 or later"
+#~ msgstr ""
+
+#~ msgid "RHEL 7.3 or later"
+#~ msgstr ""
+
+#~ msgid "Platform"
+#~ msgstr ""
+
+#~ msgid "Intel Xeon"
+#~ msgstr ""
+
+#~ msgid "Intel Xeon Phi"
+#~ msgstr ""
+
+#~ msgid "Fujitsu A64FX"
+#~ msgstr ""
+
+#~ msgid "Prepare files for building McKernel"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Grant read permission to the System.map"
+#~ " file of your kernel version on "
+#~ "the build machine:"
+#~ msgstr ""
+
+#~ msgid "Install the following packages to the build machine:"
+#~ msgstr ""
+
+#~ msgid "When having access to repositories"
+#~ msgstr ""
+
+#~ msgid "On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:"
+#~ msgstr ""
+
+#~ msgid "On CentOS 8, enable the PowerTools repository:"
+#~ msgstr ""
+
+#~ msgid "Install with yum:"
+#~ msgstr ""
+
+#~ msgid "When not having access to repositories"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Ask the system administrator to install"
+#~ " them. Note that ``libdwarf-devel`` "
+#~ "is in the CodeReady Linux Builder "
+#~ "repository on RHEL 8 or in the "
+#~ "PowerTools repository on CentOS 8."
+#~ msgstr ""
+
+#~ msgid "Clone, compile, install"
+#~ msgstr ""
+
+#~ msgid "Clone the source code:"
+#~ msgstr ""
+
+#~ msgid "(Optional) Checkout to the specific branch or version:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Foe example, if you want to try"
+#~ " the development branch, use “development”"
+#~ " as the pathspec. If you want "
+#~ "to try the prerelease version 1.7.0-0.2,"
+#~ " use “1.7.0-0.2”."
+#~ msgstr ""
+
+#~ msgid "Move to build directory:"
+#~ msgstr ""
+
+#~ msgid "Run cmake:"
+#~ msgstr ""
+
+#~ msgid "When not cross-compiling:"
+#~ msgstr ""
+
+#~ msgid "When cross-compiling:"
+#~ msgstr ""
+
+#~ msgid "Install with cmake"
+#~ msgstr ""
+
+#~ msgid "Install with make:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The kernel modules and McKernel kernel"
+#~ " image should be installed under the"
+#~ " **ihk+mckernel** folder in your home "
+#~ "directory."
+#~ msgstr ""
+
+#~ msgid "Install with rpm"
+#~ msgstr ""
+
+#~ msgid "Create the tarball and the spec file:"
+#~ msgstr ""
+
+#~ msgid "Create the rpm package:"
+#~ msgstr ""
+
+#~ msgid "Install the rpm package:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The kernel modules and McKernel kernel"
+#~ " image are installed under the "
+#~ "standard system directories."
+#~ msgstr ""
+
+#~ msgid "Prepare files and change settings for installing McKernel"
+#~ msgstr ""
+
+#~ msgid "Disable SELinux of the compute nodes:"
+#~ msgstr ""
+
+#~ msgid "Change the file to SELINUX=disabled. And then reboot the compute nodes:"
+#~ msgstr ""
+
+#~ msgid "Install the following packages to the compute nodes:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Ask the system administrator to install"
+#~ " them. Note that ``libdwarf`` is in"
+#~ " the CodeReady Linux Builder repository "
+#~ "on RHEL 8 or in the PowerTools "
+#~ "repository on CentOS 8."
+#~ msgstr ""
+
+#~ msgid "起動停止"
+#~ msgstr "起動停止"
+
+#~ msgid "関連ファイル"
+#~ msgstr "関連ファイル"
+
+#~ msgid "McKernelを用いたシステムを運用するシステム管理者を対象として、運用手順を説明する。"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "SMPプロセッサ向け、x86_64アーキ向けの関連ファイルの場所は以下の通り。 "
+#~ "なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+#~ msgstr "運用向けコマンド・デーモンのファイルの場所は以下の通り。 なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+
+#~ msgid ""
+#~ "SMPプロセッサ向け、x86_64アーキ向けの関連ファイルの場所は以下の通り。 "
+#~ "なお、IHK/McKernelのインストールディレクトリを<install>とする。 The related "
+#~ "files and their locations are as "
+#~ "follows. Denote by ``<install>`` the "
+#~ "install directory of IHK/McKernel."
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The related files and their locations"
+#~ " are as follows. Denote by "
+#~ "``<install>`` the install directory of "
+#~ "IHK/McKernel."
+#~ msgstr ""
+#~ "SMPプロセッサ向け、x86_64アーキ向けの関連ファイルの場所は以下の通り。 "
+#~ "なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+
+#~ msgid "運用向けコマンド・デーモンのファイルの場所は以下の通り。 なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+#~ msgstr "運用向けコマンド・デーモンのファイルの場所は以下の通り。 なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+
+#~ msgid "運用向けコマンド・デーモンのファイルの場所は以下の通り。"
+#~ msgstr ""
+#~ "The commands and daemons for operation"
+#~ " and their locations are as follows."
+
+#~ msgid "カーネルイメージ"
+#~ msgstr ""
+
+#~ msgid "ダンプ解析ツール"
+#~ msgstr ""
+
+#~ msgid "ダンプ形式変換ツール"
+#~ msgstr ""
+
+#~ msgid "tool"
+#~ msgstr "ツール"
+

docs/locales/ja/LC_MESSAGES/ops.po

@@ -0,0 +1,821 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-06 10:10+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../ops.rst:5
+msgid "McKernelを用いたシステムを運用するシステム管理者を対象として、運用手順を説明する。"
+msgstr ""
+
+#: ../../ops.rst:8
+msgid "Installation"
+msgstr "インストール"
+
+#: ../../ops.rst:10
+msgid "See `Quick Guide -- Installation <quick.html#installation>`__."
+msgstr ""
+
+#: ../../uti.rst:2
+msgid "Advanced: Enable Utility Thread offloading Interface (UTI)"
+msgstr ""
+
+#: ../../uti.rst:4
+msgid ""
+"UTI enables a runtime such as MPI runtime to spawn utility threads such "
+"as MPI asynchronous progress threads to Linux cores."
+msgstr ""
+
+#: ../../uti.rst:8
+msgid "Install capstone"
+msgstr ""
+
+#: ../../uti.rst:11 ../../uti.rst:22
+msgid "When compute nodes don't have access to repositories"
+msgstr ""
+
+#: ../../uti.rst:13
+msgid "Install EPEL capstone-devel:"
+msgstr ""
+
+#: ../../uti.rst:24
+msgid ""
+"Ask the system administrator to install ``capstone-devel``. Note that it "
+"is in the EPEL repository."
+msgstr ""
+
+#: ../../uti.rst:28
+msgid "Install syscall_intercept"
+msgstr ""
+
+#: ../../uti.rst:37
+msgid "Install UTI for McKernel"
+msgstr ""
+
+#: ../../uti.rst:39
+msgid "Install:"
+msgstr ""
+
+#: ../../uti.rst:49
+msgid "Install McKernel"
+msgstr ""
+
+#: ../../uti.rst:51
+msgid "Add ``-DENABLE_UTI=ON`` option to ``cmake``:"
+msgstr ""
+
+#: ../../uti.rst:58
+msgid "Run programs"
+msgstr ""
+
+#: ../../uti.rst:60
+msgid "Add ``--enable-uti`` option to ``mcexec``:"
+msgstr ""
+
+#: ../../uti.rst:67
+msgid "Install UTI for Linux"
+msgstr ""
+
+#: ../../uti.rst:69
+msgid ""
+"You should skip this step if it's already installed as with, for example,"
+" Fujitsu Technical Computing Suite."
+msgstr ""
+
+#: ../../uti.rst:72
+msgid "Install by make"
+msgstr ""
+
+#: ../../uti.rst:82
+msgid "Install by rpm"
+msgstr ""
+
+#: ../../ops.rst:15
+msgid "起動停止"
+msgstr ""
+
+#: ../../ops.rst:18
+msgid "関連ファイル"
+msgstr ""
+
+#: ../../ops.rst:20
+msgid ""
+"SMPプロセッサ向け、x86_64アーキ向けの関連ファイルの場所は以下の通り。 "
+"なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+msgstr ""
+
+#: ../../ops.rst:24
+msgid "<install>/kmod/ihk.ko"
+msgstr ""
+
+#: ../../ops.rst:24
+msgid "IHK-master core"
+msgstr ""
+
+#: ../../ops.rst:26
+msgid "|ihk-smp|"
+msgstr ""
+
+#: ../../ops.rst:26
+msgid "IHK-master driver"
+msgstr ""
+
+#: ../../ops.rst:29
+msgid "|mcctrl|"
+msgstr ""
+
+#: ../../ops.rst:29
+msgid "Delegator module"
+msgstr ""
+
+#: ../../ops.rst:32
+msgid "|mckernel.img|"
+msgstr ""
+
+#: ../../ops.rst:32
+msgid "カーネルイメージ"
+msgstr ""
+
+#: ../../ops.rst:40
+msgid "運用向けコマンド・デーモンのファイルの場所は以下の通り。 なお、IHK/McKernelのインストールディレクトリを<install>とする。"
+msgstr ""
+
+#: ../../ops.rst:44
+msgid "|mcreboot|"
+msgstr ""
+
+#: ../../ops.rst:44 ../../ops.rst:104
+msgid "ブートスクリプト"
+msgstr ""
+
+#: ../../ops.rst:47
+msgid "|mcstop|"
+msgstr ""
+
+#: ../../ops.rst:47 ../../ops.rst:204
+msgid "シャットダウンスクリプト"
+msgstr ""
+
+#: ../../ops.rst:50
+msgid "<install>/bin/mcexec"
+msgstr ""
+
+#: ../../ops.rst:50 ../../ops.rst:242
+msgid "プロセス起動コマンド"
+msgstr ""
+
+#: ../../ops.rst:52
+msgid "<install>/bin/eclair"
+msgstr ""
+
+#: ../../ops.rst:52
+msgid "ダンプ解析ツール"
+msgstr ""
+
+#: ../../ops.rst:54
+msgid "|vmcore2mckdump|"
+msgstr ""
+
+#: ../../ops.rst:54
+msgid "ダンプ形式変換ツール"
+msgstr ""
+
+#: ../../ops.rst:62
+msgid "以下、関連コマンドおよび関連関数のインターフェイスを説明する。"
+msgstr ""
+
+#: ../../ops.rst:65
+msgid "インターフェイス"
+msgstr ""
+
+#: ../../ops.rst:68
+msgid "カーネル引数"
+msgstr ""
+
+#: ../../ops.rst:70
+msgid "McKernelのカーネル引数を表 :numref:`tab-kargs` に示す。"
+msgstr ""
+
+#: ../../ops.rst:74
+msgid "McKernelのカーネル引数"
+msgstr ""
+
+#: ../../ops.rst:77
+msgid "hidos"
+msgstr ""
+
+#: ../../ops.rst:77
+msgid "IKCを有効にする。"
+msgstr ""
+
+#: ../../ops.rst:79
+msgid "|dlv|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "Linuxのpanicハンドラ経由でダンプを行った場合の、ダ"
+msgstr ""
+
+#: ../../ops.rst
+msgid "ンプ対象とするメモリ領域の種類を<level>に設定する。"
+msgstr ""
+
+#: ../../ops.rst
+msgid "設定可能な値は以下の通り。"
+msgstr ""
+
+#: ../../ops.rst:85 ../../ops.rst:166 ../../ops.rst:198 ../../ops.rst:236
+msgid "0"
+msgstr ""
+
+#: ../../ops.rst:86 ../../ops.rst:167
+msgid "IHKがMcKernelに割り当てたメモリ領域を出力する"
+msgstr ""
+
+#: ../../ops.rst:87 ../../ops.rst:168
+msgid "24"
+msgstr ""
+
+#: ../../ops.rst:88 ../../ops.rst:169
+msgid "カーネルが使用しているメモリ領域を出力する"
+msgstr ""
+
+#: ../../ops.rst:90 ../../ops.rst:171
+msgid "指定がなかった場合は24が用いられる。"
+msgstr ""
+
+#: ../../ops.rst:92
+msgid "|allow|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "McKernelに割り当てられたCPU数より大きい数のスレッド"
+msgstr ""
+
+#: ../../ops.rst
+msgid "またはプロセスの生成を許可する。この引数が指定され"
+msgstr ""
+
+#: ../../ops.rst
+msgid "ない場合に、CPU数より大きい数のスレッドまたはプロセ"
+msgstr ""
+
+#: ../../ops.rst
+msgid "スをclone(), fork(), vfork()などで生成しようとする"
+msgstr ""
+
+#: ../../ops.rst
+msgid "と、当該システムコールがEINVALエラーを返す。"
+msgstr ""
+
+#: ../../ops.rst:107 ../../ops.rst:209
+msgid "書式"
+msgstr ""
+
+#: ../../ops.rst:115 ../../ops.rst:219
+msgid "オプション"
+msgstr ""
+
+#: ../../ops.rst:118
+msgid "|opt-c|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "McKernelに割り当てるCPUのリストを指定する。フォー"
+msgstr ""
+
+#: ../../ops.rst
+msgid "マットは以下の通り。"
+msgstr ""
+
+#: ../../ops.rst
+msgid "<CPU logical id>,<CPU logical id>...または"
+msgstr ""
+
+#: ../../ops.rst
+msgid "<CPU logical id>-<CPU logical id>,<CPU logical id>"
+msgstr ""
+
+#: ../../ops.rst
+msgid "-<CPU logical id>...または両者の混合。"
+msgstr ""
+
+#: ../../ops.rst:124
+msgid "|opt-r|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "McKernelのCPUがIKCメッセージを送るLinux"
+msgstr ""
+
+#: ../../ops.rst
+msgid "CPUを指定する。フォーマットは以下の通り。"
+msgstr ""
+
+#: ../../ops.rst
+msgid "<CPU list>:<CPU id>+<CPU list>:<CPU id>..."
+msgstr ""
+
+#: ../../ops.rst
+msgid "<CPU list>のフォーマットは-cオプションにおけるもの"
+msgstr ""
+
+#: ../../ops.rst
+msgid "と同じである。"
+msgstr ""
+
+#: ../../ops.rst
+msgid "各<CPU list>:<CPU id>は<CPU list>で示されるMcKernel"
+msgstr ""
+
+#: ../../ops.rst
+msgid "のCPUが<CPU logical id>で示されるLinuxのCPUにIKC"
+msgstr ""
+
+#: ../../ops.rst
+msgid "メッセージを送信することを意味する。"
+msgstr ""
+
+#: ../../ops.rst:133
+msgid "|opt-m|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "McKernelに割り当てるメモリ領域を指定する。フォーマッ"
+msgstr ""
+
+#: ../../ops.rst
+msgid "トは以下の通り。"
+msgstr ""
+
+#: ../../ops.rst
+msgid "<size>@<NUMA-id>, <size>@<NUMA-id>..."
+msgstr ""
+
+#: ../../ops.rst:137
+msgid "|opt-f|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "ihkmondが使用するsyslogプロトコルのfacilityを指定す"
+msgstr ""
+
+#: ../../ops.rst
+msgid "る。デフォルトはLOG_LOCAL6。"
+msgstr ""
+
+#: ../../ops.rst:140
+msgid "|opt-o|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "IHKのデバイスファイル(/dev/mcd*, /dev/mcos*)のオー"
+msgstr ""
+
+#: ../../ops.rst
+msgid "ナーとグループの値を<user>[:<group>]の形式で指定す"
+msgstr ""
+
+#: ../../ops.rst
+msgid "る。デフォルトはmcreboot.shを実行したユーザ。"
+msgstr ""
+
+#: ../../ops.rst:144
+msgid "|opt-i|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "ihkmondがハングアップ検知のためにOS状態を確認する時"
+msgstr ""
+
+#: ../../ops.rst
+msgid "間間隔を秒単位で指定する。-1が指定された場合はハン"
+msgstr ""
+
+#: ../../ops.rst
+msgid "グアップ検知を行わない。指定がない場合はハングアッ"
+msgstr ""
+
+#: ../../ops.rst
+msgid "プ検知を行わない。"
+msgstr ""
+
+#: ../../ops.rst:149
+msgid "|opt-k|"
+msgstr ""
+
+#: ../../ops.rst
+msgid "カーネルメッセージの/dev/logへのリダイレクト有無を"
+msgstr ""
+
+#: ../../ops.rst
+msgid "指定する。0が指定された場合はリダイレクトを行わず、"
+msgstr ""
+
+#: ../../ops.rst
+msgid "0以外が指定された場合はリダイレクトを行う。指定がな"
+msgstr ""
+
+#: ../../ops.rst
+msgid "い場合はリダイレクトを行わない。"
+msgstr ""
+
+#: ../../ops.rst:154
+msgid "-q <irq>"
+msgstr ""
+
+#: ../../ops.rst
+msgid "IHKが使用するIRQ番号を指定する。指定がない場合は"
+msgstr ""
+
+#: ../../ops.rst
+msgid "64-255の範囲で空いているものを使用する。"
+msgstr ""
+
+#: ../../ops.rst:157
+msgid "-t"
+msgstr ""
+
+#: ../../ops.rst
+msgid "（x86_64アーキテクチャのみ）Turbo"
+msgstr ""
+
+#: ../../ops.rst
+msgid "Boostをオンにする。デフォルトはオフ。"
+msgstr ""
+
+#: ../../ops.rst:160
+msgid "-d <level>"
+msgstr ""
+
+#: ../../ops.rst:173
+msgid "-O"
+msgstr ""
+
+#: ../../ops.rst
+msgid "またはプロセスの生成を許可する。指定がない場合は許可"
+msgstr ""
+
+#: ../../ops.rst
+msgid "しない。すなわち、CPU数より大きい数のスレッドまたは"
+msgstr ""
+
+#: ../../ops.rst
+msgid "プロセスを生成しようとするとエラーとなる。"
+msgstr ""
+
+#: ../../ops.rst:189 ../../ops.rst:226
+msgid "説明"
+msgstr ""
+
+#: ../../ops.rst:191
+msgid ""
+"McKernel関連カーネルモジュールをinsmodし、<cpulist>で指定されたCPUと<memlist>で指定されたメモリ領域からなるパーティションを作成し、IKC"
+" mapを<ikcmap>に設定し、前記パーティションにMcKernelをブートする。"
+msgstr ""
+
+#: ../../ops.rst:195 ../../ops.rst:233
+msgid "戻り値"
+msgstr ""
+
+#: ../../ops.rst:198 ../../ops.rst:236
+msgid "正常終了"
+msgstr ""
+
+#: ../../ops.rst:200 ../../ops.rst:238
+msgid "0以外"
+msgstr ""
+
+#: ../../ops.rst:200 ../../ops.rst:238
+msgid "エラー"
+msgstr ""
+
+#: ../../ops.rst:221
+msgid "なし"
+msgstr ""
+
+#: ../../ops.rst:228
+msgid "McKernelをシャットダウンし、McKernel用パーティションを削除し、関連カーネルモジュールをrmmodする。"
+msgstr ""
+
+#: ../../ops.rst:247
+msgid "ダンプ解析コマンド"
+msgstr ""
+
+#: ../../ops.rst:252
+msgid "ダンプ形式変換コマンド"
+msgstr ""
+
+#: ../../ops.rst:257
+msgid "ブート手順"
+msgstr ""
+
+#: ../../ops.rst:259
+msgid "mcreboot.shを用いてブート手順を説明する。"
+msgstr ""
+
+#: ../../ops.rst:261 ../../ops.rst:908
+msgid "スクリプトは以下の通り。"
+msgstr ""
+
+#: ../../ops.rst:854 ../../ops.rst:1052
+msgid "手順は以下の通り。"
+msgstr ""
+
+#: ../../ops.rst:856
+msgid "ihkmondを起動する。ihkmondは任意のタイミングで起動してよい。これは、ihkmondはOSインスタンスの作成を検知して動作を開始するためである。（83行目）"
+msgstr ""
+
+#: ../../ops.rst:858
+msgid "Linuxのカーネルバージョンが、mcoverlayfsが動作するものであるかを確認する。（200–216行目）"
+msgstr ""
+
+#: ../../ops.rst:860
+msgid "irqbalanceを停止する。（251–257行目）"
+msgstr ""
+
+#: ../../ops.rst:862
+msgid ""
+"/proc/irq/[n]/affinityの設定を保存した上でMcKernel "
+"CPUを担当から外す。担当CPUが無くなる場合は、全てのLinux CPUを指定する。（269–303行目）"
+msgstr ""
+
+#: ../../ops.rst:866
+msgid "ihk.koをinsmodする。（307行目）"
+msgstr ""
+
+#: ../../ops.rst:868
+msgid "Linuxによるメモリフラグメンテーションを緩和するために以下を実施する。（313–320行目）"
+msgstr ""
+
+#: ../../ops.rst:870
+msgid "アクティブでないプロセスを積極的にスワップアウトするように設定する"
+msgstr ""
+
+#: ../../ops.rst:872
+msgid "クリーンなページキャッシュを無効化し、またdentriesやinodeのslabオブジェクトのうち可能なものを破棄する"
+msgstr ""
+
+#: ../../ops.rst:874
+msgid "連続する空き領域を結合してより大きな空き領域にまとめる"
+msgstr ""
+
+#: ../../ops.rst:876
+msgid ""
+"ihk-smp-x86.koをinsmodする。（340行目）ihk-smp-x86.koは関数をihk.koに登録する。このため、ihk-"
+"smp-x86.koはihk.koをinsmodした後にinsmodする必要がある。"
+msgstr ""
+
+#: ../../ops.rst:878
+msgid "メモリを予約する。（370行目）"
+msgstr ""
+
+#: ../../ops.rst:880
+msgid "CPUを予約する。（374行目）"
+msgstr ""
+
+#: ../../ops.rst:882
+msgid "McKernelのカーネルモジュールmcctrl.koをinsmodする。（382行目）mcctrl.koはMcKernelブート時に呼ばれる関数をihk.koに登録する。このため、mcctrl.koのinsmodはihk.koのinsmodの後に、またブートの前に行う必要がある。"
+msgstr ""
+
+#: ../../ops.rst:884
+msgid "OSインスタンスを作成する。（406行目）"
+msgstr ""
+
+#: ../../ops.rst:886
+msgid "OSインスタンスにCPUを割り当てる。（412行目）"
+msgstr ""
+
+#: ../../ops.rst:888
+msgid "McKernel CPUのIKCメッセージ送信先のLinux CPUを設定する。（419行目）"
+msgstr ""
+
+#: ../../ops.rst:890
+msgid "OSインスタンスにメモリを割り当てる。（426行目）"
+msgstr ""
+
+#: ../../ops.rst:892
+msgid "カーネルイメージをロードする。（432行目）"
+msgstr ""
+
+#: ../../ops.rst:894
+msgid "カーネル引数をカーネルに渡す。（438行目）"
+msgstr ""
+
+#: ../../ops.rst:896
+msgid "カーネルをブートする。（444行目）"
+msgstr ""
+
+#: ../../ops.rst:898
+msgid ""
+"/proc, "
+"/sysファイルの準備をする。また、その中でmcoverlayfs.koをinsmodする。mcoverlayfs.koは他モジュールとの依存関係を持たない。（454行目から567行目）なお、関数インターフェイスでの対応関数はihk_os_create_pseudofs()である。"
+msgstr ""
+
+#: ../../ops.rst:900
+msgid "irqbalanceを、Linux CPUのみを対象とする設定で開始する。（569–587行目）"
+msgstr ""
+
+#: ../../ops.rst:904
+msgid "シャットダウン手順"
+msgstr ""
+
+#: ../../ops.rst:906
+msgid "mcstop+release.shを用いてシャットダウン手順を説明する。"
+msgstr ""
+
+#: ../../ops.rst:1054
+msgid "ブート時にLinux CPUのみを対象とする設定で開始されたirqbalanceを停止する。（24–33行目）"
+msgstr ""
+
+#: ../../ops.rst:1057
+msgid "全てのOSインスタンスを破壊する。OSインスタンスに割り当てられていた資源はIHKがLWKのために予約した状態に移行する。（35–50行目）"
+msgstr ""
+
+#: ../../ops.rst:1059
+msgid "IHKがLWKのために予約していた資源を開放する。（52–77行目）"
+msgstr ""
+
+#: ../../ops.rst:1061
+msgid "mcctrl.koをrmmodする。（81行目）"
+msgstr ""
+
+#: ../../ops.rst:1063
+msgid ""
+"/proc, "
+"/sysファイルの準備をする。また、その中でmcoverlayfs.koをrmmodする。（87–100行目）なお、関数インターフェイスでの対応関数はihk_os_destroy_pseudofs()である。"
+msgstr ""
+
+#: ../../ops.rst:1065
+msgid "ihk-smp-x86.koをrmmodする。（104行目）"
+msgstr ""
+
+#: ../../ops.rst:1067
+msgid "ihk.koをrmmodする。（112行目）"
+msgstr ""
+
+#: ../../ops.rst:1069
+msgid "ihkmondを停止する。（121行目）"
+msgstr ""
+
+#: ../../ops.rst:1071
+msgid "/proc/irq/[n]/affinityの設定をブート時に保存しておいたものに戻し、ブート前の設定でirqbalanceを開始する。（124–135行目）"
+msgstr ""
+
+#: ../../ops.rst:1073
+msgid "Linuxカーネルのスワップアウト積極度の設定をデフォルトの値に戻す。（138行目）"
+msgstr ""
+
+#~ msgid "The following OS distributions and platforms are recommended:"
+#~ msgstr "推奨OSディストリビューションとプロセッサは以下の通り。"
+
+#~ msgid "OS distribution"
+#~ msgstr ""
+
+#~ msgid "CentOS 7.3 or later"
+#~ msgstr ""
+
+#~ msgid "RHEL 7.3 or later"
+#~ msgstr ""
+
+#~ msgid "Platform"
+#~ msgstr ""
+
+#~ msgid "Intel Xeon"
+#~ msgstr ""
+
+#~ msgid "Intel Xeon Phi"
+#~ msgstr ""
+
+#~ msgid "Fujitsu A64FX"
+#~ msgstr ""
+
+#~ msgid "Prepare files for building McKernel"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Grant read permission to the System.map"
+#~ " file of your kernel version on "
+#~ "the build machine:"
+#~ msgstr ""
+
+#~ msgid "Install the following packages to the build machine:"
+#~ msgstr ""
+
+#~ msgid "When having access to repositories"
+#~ msgstr ""
+
+#~ msgid "On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:"
+#~ msgstr ""
+
+#~ msgid "On CentOS 8, enable the PowerTools repository:"
+#~ msgstr ""
+
+#~ msgid "Install with yum:"
+#~ msgstr ""
+
+#~ msgid "When not having access to repositories"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Ask the system administrator to install"
+#~ " them. Note that ``libdwarf-devel`` "
+#~ "is in the CodeReady Linux Builder "
+#~ "repository on RHEL 8 or in the "
+#~ "PowerTools repository on CentOS 8."
+#~ msgstr ""
+
+#~ msgid "Clone, compile, install"
+#~ msgstr ""
+
+#~ msgid "Clone the source code:"
+#~ msgstr ""
+
+#~ msgid "(Optional) Checkout to the specific branch or version:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Foe example, if you want to try"
+#~ " the development branch, use “development”"
+#~ " as the pathspec. If you want "
+#~ "to try the prerelease version 1.7.0-0.2,"
+#~ " use “1.7.0-0.2”."
+#~ msgstr ""
+
+#~ msgid "Move to build directory:"
+#~ msgstr ""
+
+#~ msgid "Run cmake:"
+#~ msgstr ""
+
+#~ msgid "When not cross-compiling:"
+#~ msgstr ""
+
+#~ msgid "When cross-compiling:"
+#~ msgstr ""
+
+#~ msgid "Install with cmake"
+#~ msgstr ""
+
+#~ msgid "Install with make:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The kernel modules and McKernel kernel"
+#~ " image should be installed under the"
+#~ " **ihk+mckernel** folder in your home "
+#~ "directory."
+#~ msgstr ""
+
+#~ msgid "Install with rpm"
+#~ msgstr ""
+
+#~ msgid "Create the tarball and the spec file:"
+#~ msgstr ""
+
+#~ msgid "Create the rpm package:"
+#~ msgstr ""
+
+#~ msgid "Install the rpm package:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The kernel modules and McKernel kernel"
+#~ " image are installed under the "
+#~ "standard system directories."
+#~ msgstr ""
+
+#~ msgid "Prepare files and change settings for installing McKernel"
+#~ msgstr ""
+
+#~ msgid "Disable SELinux of the compute nodes:"
+#~ msgstr ""
+
+#~ msgid "Change the file to SELINUX=disabled. And then reboot the compute nodes:"
+#~ msgstr ""
+
+#~ msgid "Install the following packages to the compute nodes:"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "Ask the system administrator to install"
+#~ " them. Note that ``libdwarf`` is in"
+#~ " the CodeReady Linux Builder repository "
+#~ "on RHEL 8 or in the PowerTools "
+#~ "repository on CentOS 8."
+#~ msgstr ""
+

docs/locales/ja/LC_MESSAGES/quick.po

@@ -0,0 +1,458 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../quick.rst:6
+msgid "Introduction"
+msgstr ""
+
+#: ../../summary.rst:1
+msgid ""
+"IHK/McKernel is a light-weight multi-kernel operating system designed for"
+" high-end supercomputing. It runs Linux and McKernel, a light-weight "
+"kernel (LWK), side-by-side inside compute nodes and aims at the "
+"following:"
+msgstr ""
+
+#: ../../summary.rst:6
+msgid ""
+"Provide scalable and consistent execution of large-scale parallel "
+"scientific applications, but at the same time maintain the ability to "
+"rapidly adapt to new hardware features and emerging programming models"
+msgstr ""
+
+#: ../../summary.rst:10
+msgid ""
+"Provide efficient memory and device management so that resource "
+"contention and data movement are minimized at the system level"
+msgstr ""
+
+#: ../../summary.rst:12
+msgid ""
+"Eliminate OS noise by isolating OS services in Linux and provide jitter "
+"free execution on the LWK"
+msgstr ""
+
+#: ../../summary.rst:14
+msgid ""
+"Support the full POSIX/Linux APIs by selectively offloading (slow-path) "
+"system calls to Linux"
+msgstr ""
+
+#: ../../background.rst:2
+msgid "Background and Motivation"
+msgstr ""
+
+#: ../../background.rst:4
+msgid ""
+"With the growing complexity of high-end supercomputers, the current "
+"system software stack faces significant challenges as we move forward to "
+"exascale and beyond. The necessity to deal with extreme degree of "
+"parallelism, heterogeneous architectures, multiple levels of memory "
+"hierarchy, power constraints, etc., advocates operating systems that can "
+"rapidly adapt to new hardware requirements, and that can support novel "
+"programming paradigms and runtime systems. On the other hand, a new class"
+" of more dynamic and complex applications are also on the horizon, with "
+"an increasing demand for application constructs such as in-situ analysis,"
+" workflows, elaborate monitoring and performance tools. This complexity "
+"relies not only on the rich features of POSIX, but also on the Linux APIs"
+" (such as the */proc*, */sys* filesystems, etc.) in particular."
+msgstr ""
+
+#: ../../background.rst:19
+msgid "Two Traditional HPC OS Approaches"
+msgstr ""
+
+#: ../../background.rst:21
+msgid ""
+"Traditionally, light-weight operating systems specialized for HPC "
+"followed two approaches to tackle scalable execution of large-scale "
+"applications. In the full weight kernel (FWK) approach, a full Linux "
+"environment is taken as the basis, and features that inhibit attaining "
+"HPC scalability are removed, i.e., making it light-weight. The pure "
+"light-weight kernel (LWK) approach, on the other hand, starts from "
+"scratch and effort is undertaken to add sufficient functionality so that "
+"it provides a familiar API, typically something close to that of a "
+"general purpose OS, while at the same time it retains the desired "
+"scalability and reliability attributes. Neither of these approaches "
+"yields a fully Linux compatible environment."
+msgstr ""
+
+#: ../../background.rst:34
+msgid "The Multi-kernel Approach"
+msgstr ""
+
+#: ../../background.rst:36
+msgid ""
+"A hybrid approach recognized recently by the system software community is"
+" to run Linux simultaneously with a lightweight kernel on compute nodes "
+"and multiple research projects are now pursuing this direction. The basic"
+" idea is that simulations run on an HPC tailored lightweight kernel, "
+"ensuring the necessary isolation for noiseless execution of parallel "
+"applications, but Linux is leveraged so that the full POSIX API is "
+"supported. Additionally, the small code base of the LWK can also "
+"facilitate rapid prototyping for new, exotic hardware features. "
+"Nevertheless, the questions of how to share node resources between the "
+"two types of kernels, where do device drivers execute, how exactly do the"
+" two kernels interact with each other and to what extent are they "
+"integrated, remain subjects of ongoing debate."
+msgstr ""
+
+#: ../../archtecture.rst:2
+msgid "Architectural Overview"
+msgstr ""
+
+#: ../../archtecture.rst:4
+msgid ""
+"At the heart of the stack is a low-level software infrastructure called "
+"Interface for Heterogeneous Kernels (IHK). IHK is a general framework "
+"that provides capabilities for partitioning resources in a many-core "
+"environment (e.g.,CPU cores and physical memory) and it enables "
+"management of lightweight kernels. IHK can allocate and release host "
+"resources dynamically and no reboot of the host machine is required when "
+"altering configuration. IHK also provides a low-level inter-kernel "
+"messaging infrastructure, called the Inter-Kernel Communication (IKC) "
+"layer. An architectural overview of the main system components is shown "
+"below."
+msgstr ""
+
+#: ../../archtecture.rst:18
+msgid ""
+"McKernel is a lightweight kernel written from scratch. It is designed for"
+" HPC and is booted from IHK. McKernel retains a binary compatible ABI "
+"with Linux, however, it implements only a small set of performance "
+"sensitive system calls and the rest are offloaded to Linux. Specifically,"
+" McKernel has its own memory management, it supports processes and multi-"
+"threading with a simple round-robin cooperative (tick-less) scheduler, "
+"and it implements signaling. It also allows inter-process memory mappings"
+" and it provides interfaces to hardware performance counters."
+msgstr ""
+
+#: ../../archtecture.rst:29
+msgid "Functionality"
+msgstr ""
+
+#: ../../archtecture.rst:31
+msgid ""
+"An overview of some of the principal functionalities of the IHK/McKernel "
+"stack is provided below."
+msgstr ""
+
+#: ../../archtecture.rst:35
+msgid "System Call Offloading"
+msgstr ""
+
+#: ../../archtecture.rst:37
+msgid ""
+"System call forwarding in McKernel is implemented as follows. When an "
+"offloaded system call occurs, McKernel marshals the system call number "
+"along with its arguments and sends a message to Linux via a dedicated IKC"
+" channel. The corresponding proxy process running on Linux is by default "
+"waiting for system call requests through an ioctl() call into IHK’s "
+"system call delegator kernel module. The delegator kernel module’s IKC "
+"interrupt handler wakes up the proxy process, which returns to userspace "
+"and simply invokes the requested system call. Once it obtains the return "
+"value, it instructs the delegator module to send the result back to "
+"McKernel, which subsequently passes the value to user-space."
+msgstr ""
+
+#: ../../archtecture.rst:49
+msgid "Unified Address Space"
+msgstr ""
+
+#: ../../archtecture.rst:51
+msgid ""
+"The unified address space model in IHK/McKernel ensures that offloaded "
+"system calls can seamlessly resolve arguments even in case of pointers. "
+"This mechanism is depicted below and is implemented as follows."
+msgstr ""
+
+#: ../../archtecture.rst:58
+msgid ""
+"First, the proxy process is compiled as a position independent binary, "
+"which enables us to map the code and data segments specific to the proxy "
+"process to an address range which is explicitly excluded from McKernel’s "
+"user space. The grey box on the right side of the figure demonstrates the"
+" excluded region. Second, the entire valid virtual address range of "
+"McKernel’s application user-space is covered by a special mapping in the "
+"proxy process for which we use a pseudo file mapping in Linux. This "
+"mapping is indicated by the blue box on the left side of the figure."
+msgstr ""
+
+#: ../../install.rst:4
+msgid "Installation"
+msgstr "インストール"
+
+#: ../../install.rst:6
+msgid "The following OS distributions and platforms are recommended:"
+msgstr "推奨OSディストリビューションとプロセッサは以下の通り。"
+
+#: ../../install.rst:8
+msgid "OS distribution"
+msgstr ""
+
+#: ../../install.rst:10
+msgid "CentOS 7.3 or later"
+msgstr ""
+
+#: ../../install.rst:11
+msgid "RHEL 7.3 or later"
+msgstr ""
+
+#: ../../install.rst:13
+msgid "Platform"
+msgstr ""
+
+#: ../../install.rst:15
+msgid "Intel Xeon"
+msgstr ""
+
+#: ../../install.rst:16
+msgid "Intel Xeon Phi"
+msgstr ""
+
+#: ../../install.rst:17
+msgid "Fujitsu A64FX"
+msgstr ""
+
+#: ../../install.rst:20
+msgid "Prepare files for building McKernel"
+msgstr ""
+
+#: ../../install.rst:22
+msgid ""
+"Grant read permission to the System.map file of your kernel version on "
+"the build machine:"
+msgstr ""
+
+#: ../../install.rst:28
+msgid "Install the following packages to the build machine:"
+msgstr ""
+
+#: ../../install.rst:35 ../../install.rst:179
+msgid "When having access to repositories"
+msgstr ""
+
+#: ../../install.rst:37 ../../install.rst:181
+msgid "On RHEL 8, enable the CodeReady Linux Builder (CLB) repository:"
+msgstr ""
+
+#: ../../install.rst:43 ../../install.rst:187
+msgid "On CentOS 8, enable the PowerTools repository:"
+msgstr ""
+
+#: ../../install.rst:49 ../../install.rst:193
+msgid "Install with yum:"
+msgstr ""
+
+#: ../../install.rst:56 ../../install.rst:200
+msgid "When not having access to repositories"
+msgstr ""
+
+#: ../../install.rst:58
+msgid ""
+"Ask the system administrator to install them. Note that ``libdwarf-"
+"devel`` is in the CodeReady Linux Builder repository on RHEL 8 or in the "
+"PowerTools repository on CentOS 8."
+msgstr ""
+
+#: ../../install.rst:61
+msgid "Clone, compile, install"
+msgstr ""
+
+#: ../../install.rst:63
+msgid "Clone the source code:"
+msgstr ""
+
+#: ../../install.rst:71
+msgid "(Optional) Checkout to the specific branch or version:"
+msgstr ""
+
+#: ../../install.rst:79
+msgid ""
+"Foe example, if you want to try the development branch, use “development”"
+" as the pathspec. If you want to try the prerelease version 1.7.0-0.2, "
+"use “1.7.0-0.2”."
+msgstr ""
+
+#: ../../install.rst:83
+msgid "Move to build directory:"
+msgstr ""
+
+#: ../../install.rst:89
+msgid "Run cmake:"
+msgstr ""
+
+#: ../../install.rst:92 ../../install.rst:135
+msgid "When not cross-compiling:"
+msgstr ""
+
+#: ../../install.rst:99 ../../install.rst:142
+msgid "When cross-compiling:"
+msgstr ""
+
+#: ../../install.rst:111
+msgid "Install with cmake"
+msgstr ""
+
+#: ../../install.rst:113
+msgid "Install with make:"
+msgstr ""
+
+#: ../../install.rst:119
+msgid ""
+"The kernel modules and McKernel kernel image should be installed under "
+"the **ihk+mckernel** folder in your home directory."
+msgstr ""
+
+#: ../../install.rst:123
+msgid "Install with rpm"
+msgstr ""
+
+#: ../../install.rst:125
+msgid "Create the tarball and the spec file:"
+msgstr ""
+
+#: ../../install.rst:132
+msgid "Create the rpm package:"
+msgstr ""
+
+#: ../../install.rst:148
+msgid "Install the rpm package:"
+msgstr ""
+
+#: ../../install.rst:154
+msgid ""
+"The kernel modules and McKernel kernel image are installed under the "
+"standard system directories."
+msgstr ""
+
+#: ../../install.rst:158
+msgid "Prepare files and change settings for installing McKernel"
+msgstr ""
+
+#: ../../install.rst:160
+msgid "Disable SELinux of the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:166
+msgid "Change the file to SELINUX=disabled. And then reboot the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:172
+msgid "Install the following packages to the compute nodes:"
+msgstr ""
+
+#: ../../install.rst:202
+msgid ""
+"Ask the system administrator to install them. Note that ``libdwarf`` is "
+"in the CodeReady Linux Builder repository on RHEL 8 or in the PowerTools "
+"repository on CentOS 8."
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:2
+msgid "Boot McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:4
+msgid ""
+"A boot script called ``mcreboot.sh`` is provided under ``sbin`` in the "
+"install folder. To boot on logical CPU 1 with 512MB of memory, use the "
+"following invocation:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:14
+msgid ""
+"You should see something similar like this if you display the McKernel’s "
+"kernel message log:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:42
+msgid "Run a simple program on McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:44
+msgid ""
+"The mcexec command line tool (which is also the Linux proxy process) can "
+"be used for executing applications on McKernel:"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:53
+msgid "Shutdown McKernel"
+msgstr ""
+
+#: ../../boot_run_shutdown.rst:55
+msgid ""
+"Finally, to shutdown McKernel and release CPU/memory resources back to "
+"Linux use the following command:"
+msgstr ""
+
+#: ../../team.rst:2
+msgid "The Team"
+msgstr ""
+
+#: ../../team.rst:4
+msgid ""
+"The McKernel project was started at The University of Tokyo and currently"
+" it is mainly developed at RIKEN. Some of our collaborators include:"
+msgstr ""
+
+#: ../../team.rst:8
+msgid "Hitachi"
+msgstr ""
+
+#: ../../team.rst:9
+msgid "Fujitsu"
+msgstr ""
+
+#: ../../team.rst:10
+msgid "CEA (France)"
+msgstr ""
+
+#: ../../team.rst:11
+msgid "NEC"
+msgstr ""
+
+#: ../../license.rst:2
+msgid "License"
+msgstr ""
+
+#: ../../license.rst:4
+msgid "McKernel is GPL licensed, as found in the LICENSE file."
+msgstr ""
+
+#: ../../contact.rst:2
+msgid "Contact"
+msgstr ""
+
+#: ../../contact.rst:4
+msgid ""
+"Please give your feedback to us via one of the following mailing lists. "
+"Subscription via `www.pccluster.org "
+"<http://www.pccluster.org/mailman/listinfo/mckernel-users>`__ is needed."
+msgstr ""
+
+#: ../../contact.rst:9
+msgid "English: mckernel-users@pccluster.org"
+msgstr ""
+
+#: ../../contact.rst:10
+msgid "Japanese: mckernel-users-jp@pccluster.org"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/spec-ihk.po

@@ -0,0 +1,28 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../spec-ihk.md:1
+msgid "hi"
+msgstr ""
+
+#: ../../spec-ihk.md:3
+msgid ":download:IHK Spec <ihk.pdf>"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/spec-mckernel.po

@@ -0,0 +1,24 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../spec-mckernel.md:1
+msgid "Hello"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/spec.po

@@ -0,0 +1,48 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-07 10:00+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../spec/ihk.rst:6
+msgid "External Specs"
+msgstr ""
+
+#: ../../spec/ihk.rst:9
+msgid "Overview"
+msgstr ""
+
+#: ../../spec/ihk.rst:12
+msgid "Function Specs"
+msgstr ""
+
+#: ../../spec/ihk.rst:15
+msgid "Command / Daemon Specs"
+msgstr ""
+
+#: ../../spec/ihk.rst:18
+msgid "Booting LWK"
+msgstr ""
+
+#: ../../spec/mckernel.rst:6
+msgid "Interfaces"
+msgstr ""
+
+#: ../../spec/mckernel.rst:9
+msgid "Interface details"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/summary.po

@@ -0,0 +1,53 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../summary.rst:1
+msgid ""
+"IHK/McKernel is a light-weight multi-kernel operating system designed for"
+" high-end supercomputing. It runs Linux and McKernel, a light-weight "
+"kernel (LWK), side-by-side inside compute nodes and aims at the "
+"following:"
+msgstr ""
+
+#: ../../summary.rst:6
+msgid ""
+"Provide scalable and consistent execution of large-scale parallel "
+"scientific applications, but at the same time maintain the ability to "
+"rapidly adapt to new hardware features and emerging programming models"
+msgstr ""
+
+#: ../../summary.rst:10
+msgid ""
+"Provide efficient memory and device management so that resource "
+"contention and data movement are minimized at the system level"
+msgstr ""
+
+#: ../../summary.rst:12
+msgid ""
+"Eliminate OS noise by isolating OS services in Linux and provide jitter "
+"free execution on the LWK"
+msgstr ""
+
+#: ../../summary.rst:14
+msgid ""
+"Support the full POSIX/Linux APIs by selectively offloading (slow-path) "
+"system calls to Linux"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/team.po

@@ -0,0 +1,46 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../team.rst:2
+msgid "The Team"
+msgstr ""
+
+#: ../../team.rst:4
+msgid ""
+"The McKernel project was started at The University of Tokyo and currently"
+" it is mainly developed at RIKEN. Some of our collaborators include:"
+msgstr ""
+
+#: ../../team.rst:8
+msgid "Hitachi"
+msgstr ""
+
+#: ../../team.rst:9
+msgid "Fujitsu"
+msgstr ""
+
+#: ../../team.rst:10
+msgid "CEA (France)"
+msgstr ""
+
+#: ../../team.rst:11
+msgid "NEC"
+msgstr ""
+

docs/locales/ja/LC_MESSAGES/users.po

@@ -0,0 +1,454 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-07 10:00+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../users.rst:6
+msgid "Architectural Overview"
+msgstr ""
+
+#: ../../users.rst:8
+msgid ""
+"See `Quick Guide -- Architectural Overview <quick.html#architectural-"
+"overview>`__."
+msgstr ""
+
+#: ../../users.rst:11
+msgid "Running Programs"
+msgstr ""
+
+#: ../../users.rst:13
+msgid ""
+"You need to check if your application and pre-/post-processing programs "
+"are suited to run with McKernel. Follow the guide below to choose to run "
+"the whole on McKernel, or run the whole on Linux, or run pre-/post-"
+"processing on Linux and the application on McKernel:"
+msgstr ""
+
+#: ../../users.rst:16
+msgid "Application"
+msgstr ""
+
+#: ../../users.rst:18
+msgid ""
+"Run the whole on Linux if it issues system calls frequently and becoming "
+"the bottleneck with McKernel. For example, it's better to run on Linux "
+"those programs performing many file I/O operations."
+msgstr ""
+
+#: ../../users.rst:19
+msgid "Otherwise, run it on McKernel."
+msgstr ""
+
+#: ../../users.rst:21
+msgid "Pre-/Post-processing"
+msgstr ""
+
+#: ../../users.rst:23
+msgid ""
+"Run it on McKernel if it consumes a large amount of memory or the "
+"execution time isn't prolonged prohivitively with McKernel. The reason "
+"for the first condition is that the resource could be limited for Linux "
+"CPUs in the nodes for McKernel."
+msgstr ""
+
+#: ../../users.rst:24
+msgid "Otherwise, run it on Linux."
+msgstr ""
+
+#: ../../users.rst:28
+msgid "Modify job script"
+msgstr ""
+
+#: ../../users.rst:30
+msgid ""
+"When using job submission system, you need to modify the job scripts so "
+"that the job script itself is going to run on Linux. For example, with "
+"Fujitsu Technical Computing Suite (TCS), you need to specify "
+"``jobenv=linux`` by inserting the following line into the job script:"
+msgstr ""
+
+#: ../../users.rst:38
+msgid "Insert ``mcexec`` into the command line"
+msgstr ""
+
+#: ../../users.rst:40
+msgid ""
+"You need to insert ``mcexec`` into the command lines invoking the "
+"programs that you chose to run on McKernel:"
+msgstr ""
+
+#: ../../users.rst:43
+msgid "Non-MPI programs"
+msgstr ""
+
+#: ../../users.rst:45
+msgid "Insert ``mcexec`` before an executable:"
+msgstr ""
+
+#: ../../users.rst:52
+msgid "MPI programs"
+msgstr ""
+
+#: ../../users.rst:54
+msgid ""
+"Insert ``mcexec -n <processes-per-node>`` **after mpirun** and before an "
+"executable:"
+msgstr ""
+
+#: ../../users.rst:61
+msgid ""
+"``<processes-per-node>`` is the number of the processes per node and "
+"calculated by (number of MPI processes) / (number of nodes)."
+msgstr ""
+
+#: ../../users.rst:64
+msgid ""
+"For example, ``<processes-per-node>`` equals to 4 (=32/8) when specifying"
+" the number of processes and nodes as follows with Fujitsu Technical "
+"Computing Suite."
+msgstr ""
+
+#: ../../users.rst:74
+msgid "Limitations"
+msgstr ""
+
+#: ../../users.rst:76
+msgid ""
+"Pseudo devices such as /dev/mem and /dev/zero are not mmap()ed correctly "
+"even if the mmap() returns a success. An access of their mapping receives"
+" the SIGSEGV signal."
+msgstr ""
+
+#: ../../users.rst:80
+msgid ""
+"clone() supports only the following flags. All the other flags cause "
+"clone() to return error or are simply ignored."
+msgstr ""
+
+#: ../../users.rst:83
+msgid "CLONE_CHILD_CLEARTID"
+msgstr ""
+
+#: ../../users.rst:84
+msgid "CLONE_CHILD_SETTID"
+msgstr ""
+
+#: ../../users.rst:85
+msgid "CLONE_PARENT_SETTID"
+msgstr ""
+
+#: ../../users.rst:86
+msgid "CLONE_SETTLS"
+msgstr ""
+
+#: ../../users.rst:87
+msgid "CLONE_SIGHAND"
+msgstr ""
+
+#: ../../users.rst:88
+msgid "CLONE_VM"
+msgstr ""
+
+#: ../../users.rst:90
+msgid "PAPI has the following restriction."
+msgstr ""
+
+#: ../../users.rst:92
+msgid ""
+"Number of counters a user can use at the same time is up to the number of"
+" the physical counters in the processor."
+msgstr ""
+
+#: ../../users.rst:95
+msgid "msync writes back only the modified pages mapped by the calling process."
+msgstr ""
+
+#: ../../users.rst:98
+msgid "The following syscalls always return the ENOSYS error."
+msgstr ""
+
+#: ../../users.rst:100
+msgid "migrate_pages()"
+msgstr ""
+
+#: ../../users.rst:101
+msgid "move_pages()"
+msgstr ""
+
+#: ../../users.rst:102
+msgid "set_robust_list()"
+msgstr ""
+
+#: ../../users.rst:104
+msgid "The following syscalls always return the EOPNOTSUPP error."
+msgstr ""
+
+#: ../../users.rst:106
+msgid "arch_prctl(ARCH_SET_GS)"
+msgstr ""
+
+#: ../../users.rst:107
+msgid "signalfd()"
+msgstr ""
+
+#: ../../users.rst:109
+msgid "signalfd4() returns a fd, but signal is not notified through the fd."
+msgstr ""
+
+#: ../../users.rst:111
+msgid "set_rlimit sets the limit values but they are not enforced."
+msgstr ""
+
+#: ../../users.rst:113
+msgid "Address randomization is not supported."
+msgstr ""
+
+#: ../../users.rst:115
+msgid ""
+"brk() extends the heap more than requestd when -h (–extend-heap-by=) "
+"option of mcexec is used with the value larger than 4 KiB. "
+"syscall_pwrite02 of LTP would fail for this reason. This is because the "
+"test expects that the end of the heap is set to the same address as the "
+"argument of sbrk() and expects a segmentation violation occurs when it "
+"tries to access the memory area right next to the boundary. However, the "
+"optimization sets the end to a value larger than the requested. "
+"Therefore, the expected segmentation violation doesn’t occur."
+msgstr ""
+
+#: ../../users.rst:125
+msgid ""
+"setpriority()/getpriority() won’t work. They might set/get the priority "
+"of a random mcexec thread. This is because there’s no fixed "
+"correspondence between a McKernel thread which issues the system call and"
+" a mcexec thread which handles the offload request."
+msgstr ""
+
+#: ../../users.rst:130
+msgid ""
+"mbind() can set the policy but it is not used when allocating physical "
+"pages."
+msgstr ""
+
+#: ../../users.rst:133
+msgid ""
+"MPOL_F_RELATIVE_NODES and MPOL_INTERLEAVE flags for "
+"set_mempolicy()/mbind() are not supported."
+msgstr ""
+
+#: ../../users.rst:136
+msgid ""
+"The MPOL_BIND policy for set_mempolicy()/mbind() works as the same as the"
+" MPOL_PREFERRED policy. That is, the physical page allocator doesn’t give"
+" up the allocation when the specified nodes are running out of pages but "
+"continues to search pages in the other nodes."
+msgstr ""
+
+#: ../../users.rst:141
+msgid ""
+"Kernel dump on Linux panic requires Linux kernel CentOS-7.4 and later. In"
+" addition, crash_kexec_post_notifiers kernel argument must be given to "
+"Linux kernel."
+msgstr ""
+
+#: ../../users.rst:145
+msgid ""
+"setfsuid()/setfsgid() cannot change the id of the calling thread. "
+"Instead, it changes that of the mcexec worker thread which takes the "
+"system-call offload request."
+msgstr ""
+
+#: ../../users.rst:149
+msgid ""
+"mmap (hugeTLBfs): The physical pages corresponding to a map are released "
+"when no McKernel process exist. The next map gets fresh physical pages."
+msgstr ""
+
+#: ../../users.rst:153
+msgid "Sticky bit on executable file has no effect."
+msgstr ""
+
+#: ../../users.rst:155
+msgid ""
+"Linux (RHEL-7 for x86_64) could hang when offlining CPUs in the process "
+"of booting McKernel due to the Linux bug, found in Linux-3.10 and fixed "
+"in the later version. One way to circumvent this is to always assign the "
+"same CPU set to McKernel."
+msgstr ""
+
+#: ../../users.rst:160
+msgid "madvise:"
+msgstr ""
+
+#: ../../users.rst:162
+msgid "MADV_HWPOISON and MADV_SOFT_OFFLINE always returns -EPERM."
+msgstr ""
+
+#: ../../users.rst:163
+msgid "MADV_MERGEABLE and MADV_UNMERGEABLE always returns -EINVAL."
+msgstr ""
+
+#: ../../users.rst:164
+msgid ""
+"MADV_HUGEPAGE and MADV_NOHUGEPAGE on file map returns -EINVAL except on "
+"RHEL-8 for aarch64."
+msgstr ""
+
+#: ../../users.rst:167
+msgid ""
+"brk() and mmap() doesn’t report out-of-memory through its return value. "
+"Instead, page-fault reports the error."
+msgstr ""
+
+#: ../../users.rst:170
+msgid ""
+"Anonymous mmap pre-maps requested number of pages when contiguous pages "
+"are available. Demand paging is used when not available."
+msgstr ""
+
+#: ../../users.rst:173
+msgid ""
+"Mixing page sizes in anonymous shared mapping is not allowed. mmap "
+"creates vm_range with one page size. And munmap or mremap that needs the "
+"reduced page size changes the sizes of all the pages of the vm_range."
+msgstr ""
+
+#: ../../users.rst:178
+msgid ""
+"ihk_os_getperfevent() could time-out when invoked from Fujitsu TCS (job-"
+"scheduler)."
+msgstr ""
+
+#: ../../users.rst:181
+msgid ""
+"The behaviors of madvise and mbind are changed to do nothing and report "
+"success as a workaround for Fugaku."
+msgstr ""
+
+#: ../../users.rst:184
+msgid ""
+"mmap() allows unlimited overcommit. Note that it corresponds to setting "
+"sysctl ``vm.overcommit_memory`` to 1."
+msgstr ""
+
+#~ msgid ""
+#~ "At the heart of the stack is "
+#~ "a low-level software infrastructure "
+#~ "called Interface for Heterogeneous Kernels "
+#~ "(IHK). IHK is a general framework "
+#~ "that provides capabilities for partitioning"
+#~ " resources in a many-core environment"
+#~ " (e.g.,CPU cores and physical memory) "
+#~ "and it enables management of lightweight"
+#~ " kernels. IHK can allocate and "
+#~ "release host resources dynamically and "
+#~ "no reboot of the host machine is"
+#~ " required when altering configuration. IHK"
+#~ " also provides a low-level inter-"
+#~ "kernel messaging infrastructure, called the"
+#~ " Inter-Kernel Communication (IKC) layer."
+#~ " An architectural overview of the "
+#~ "main system components is shown below."
+#~ msgstr ""
+
+#~ msgid ""
+#~ "McKernel is a lightweight kernel written"
+#~ " from scratch. It is designed for "
+#~ "HPC and is booted from IHK. "
+#~ "McKernel retains a binary compatible ABI"
+#~ " with Linux, however, it implements "
+#~ "only a small set of performance "
+#~ "sensitive system calls and the rest "
+#~ "are offloaded to Linux. Specifically, "
+#~ "McKernel has its own memory management,"
+#~ " it supports processes and multi-"
+#~ "threading with a simple round-robin "
+#~ "cooperative (tick-less) scheduler, and "
+#~ "it implements signaling. It also allows"
+#~ " inter-process memory mappings and it"
+#~ " provides interfaces to hardware "
+#~ "performance counters."
+#~ msgstr ""
+
+#~ msgid "Functionality"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "An overview of some of the "
+#~ "principal functionalities of the IHK/McKernel"
+#~ " stack is provided below."
+#~ msgstr ""
+
+#~ msgid "System Call Offloading"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "System call forwarding in McKernel is"
+#~ " implemented as follows. When an "
+#~ "offloaded system call occurs, McKernel "
+#~ "marshals the system call number along"
+#~ " with its arguments and sends a "
+#~ "message to Linux via a dedicated "
+#~ "IKC channel. The corresponding proxy "
+#~ "process running on Linux is by "
+#~ "default waiting for system call requests"
+#~ " through an ioctl() call into IHK’s"
+#~ " system call delegator kernel module. "
+#~ "The delegator kernel module’s IKC "
+#~ "interrupt handler wakes up the proxy "
+#~ "process, which returns to userspace and"
+#~ " simply invokes the requested system "
+#~ "call. Once it obtains the return "
+#~ "value, it instructs the delegator module"
+#~ " to send the result back to "
+#~ "McKernel, which subsequently passes the "
+#~ "value to user-space."
+#~ msgstr ""
+
+#~ msgid "Unified Address Space"
+#~ msgstr ""
+
+#~ msgid ""
+#~ "The unified address space model in "
+#~ "IHK/McKernel ensures that offloaded system "
+#~ "calls can seamlessly resolve arguments "
+#~ "even in case of pointers. This "
+#~ "mechanism is depicted below and is "
+#~ "implemented as follows."
+#~ msgstr ""
+
+#~ msgid ""
+#~ "First, the proxy process is compiled "
+#~ "as a position independent binary, which"
+#~ " enables us to map the code and"
+#~ " data segments specific to the proxy"
+#~ " process to an address range which"
+#~ " is explicitly excluded from McKernel’s "
+#~ "user space. The grey box on the"
+#~ " right side of the figure "
+#~ "demonstrates the excluded region. Second, "
+#~ "the entire valid virtual address range"
+#~ " of McKernel’s application user-space "
+#~ "is covered by a special mapping in"
+#~ " the proxy process for which we "
+#~ "use a pseudo file mapping in "
+#~ "Linux. This mapping is indicated by "
+#~ "the blue box on the left side "
+#~ "of the figure."
+#~ msgstr ""
+

docs/locales/ja/LC_MESSAGES/uti.po

@@ -0,0 +1,94 @@
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) 2020, Masamichi Takagi, Balazs Gerofi, Yutaka Ishikawa
+# This file is distributed under the same license as the IHK/McKernel
+# package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2020.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: IHK/McKernel \n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2020-08-04 16:40+0900\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.7.0\n"
+
+#: ../../uti.rst:2
+msgid "Advanced: Enable Utility Thread offloading Interface (UTI)"
+msgstr ""
+
+#: ../../uti.rst:4
+msgid ""
+"UTI enables a runtime such as MPI runtime to spawn utility threads such "
+"as MPI asynchronous progress threads to Linux cores."
+msgstr ""
+
+#: ../../uti.rst:8
+msgid "Install capstone"
+msgstr ""
+
+#: ../../uti.rst:11 ../../uti.rst:22
+msgid "When compute nodes don't have access to repositories"
+msgstr ""
+
+#: ../../uti.rst:13
+msgid "Install EPEL capstone-devel:"
+msgstr ""
+
+#: ../../uti.rst:24
+msgid ""
+"Ask the system administrator to install ``capstone-devel``. Note that it "
+"is in the EPEL repository."
+msgstr ""
+
+#: ../../uti.rst:28
+msgid "Install syscall_intercept"
+msgstr ""
+
+#: ../../uti.rst:37
+msgid "Install UTI for McKernel"
+msgstr ""
+
+#: ../../uti.rst:39
+msgid "Install:"
+msgstr ""
+
+#: ../../uti.rst:49
+msgid "Install McKernel"
+msgstr ""
+
+#: ../../uti.rst:51
+msgid "Add ``-DENABLE_UTI=ON`` option to ``cmake``:"
+msgstr ""
+
+#: ../../uti.rst:58
+msgid "Run programs"
+msgstr ""
+
+#: ../../uti.rst:60
+msgid "Add ``--enable-uti`` option to ``mcexec``:"
+msgstr ""
+
+#: ../../uti.rst:67
+msgid "Install UTI for Linux"
+msgstr ""
+
+#: ../../uti.rst:69
+msgid ""
+"You should skip this step if it's already installed as with, for example,"
+" Fujitsu Technical Computing Suite."
+msgstr ""
+
+#: ../../uti.rst:72
+msgid "Install by make"
+msgstr ""
+
+#: ../../uti.rst:82
+msgid "Install by rpm"
+msgstr ""
+

docs/logo.rst

@@ -0,0 +1 @@
+.. figure:: mckernel-logo.png

docs/mckernel_developers.rst

@@ -0,0 +1,9 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+Interfaces
+==========
+
+Interface details
+=================

docs/quick.rst

@@ -0,0 +1,22 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+Introduction
+============
+
+.. include:: summary.rst
+
+.. include:: background.rst
+
+.. include:: archtecture.rst
+
+.. include:: install.rst
+
+.. include:: boot_run_shutdown.rst
+
+.. include:: team.rst
+
+.. include:: license.rst
+
+.. include:: contact.rst

docs/requirements.txt

@@ -0,0 +1,30 @@
+alabaster==0.7.12
+attrs==19.3.0
+Babel==2.7.0
+certifi==2019.11.28
+chardet==3.0.4
+commonmark==0.9.1
+docutils==0.15
+idna==2.8
+imagesize==1.1.0
+Jinja2==2.10.3
+MarkupSafe==1.1.1
+mistune==0.8.4
+packaging==19.2
+Pygments==2.5.2
+pyparsing==2.4.5
+pytz==2019.3
+recommonmark==0.6.0
+requests==2.22.0
+roman==3.2
+six==1.13.0
+snowballstemmer==2.0.0
+Sphinx==2.2.2
+sphinx-rtd-theme==0.5.0
+sphinxcontrib-applehelp==1.0.1
+sphinxcontrib-devhelp==1.0.1
+sphinxcontrib-htmlhelp==1.0.2
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.2
+sphinxcontrib-serializinghtml==1.1.3
+urllib3==1.25.7

docs/spec-ihk.md

@@ -0,0 +1,3 @@
+## hi
+
+:download:`IHK Spec <ihk.pdf>`

docs/spec-mckernel.md

@@ -0,0 +1 @@
+## Hello

docs/spec/ihk.rst

@@ -0,0 +1,18 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+External Specs
+==============
+
+Overview
+--------
+
+Function Specs
+--------------
+
+Command / Daemon Specs
+----------------------
+
+Booting LWK
+===========

docs/spec/mckernel.rst

@@ -0,0 +1,9 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+Interfaces
+==========
+
+Interface details
+=================

docs/summary.rst

@@ -0,0 +1,15 @@
+IHK/McKernel is a light-weight multi-kernel operating system designed
+for high-end supercomputing. It runs Linux and McKernel, a light-weight
+kernel (LWK), side-by-side inside compute nodes and aims at the
+following:
+
+-  Provide scalable and consistent execution of large-scale parallel
+   scientific applications, but at the same time maintain the ability to
+   rapidly adapt to new hardware features and emerging programming
+   models
+-  Provide efficient memory and device management so that resource
+   contention and data movement are minimized at the system level
+-  Eliminate OS noise by isolating OS services in Linux and provide
+   jitter free execution on the LWK
+-  Support the full POSIX/Linux APIs by selectively offloading
+   (slow-path) system calls to Linux

docs/team.rst

@@ -0,0 +1,12 @@
+The Team
+========
+
+The McKernel project was started at The University of Tokyo and
+currently it is mainly developed at RIKEN. Some of our collaborators
+include:
+
+-  Hitachi
+-  Fujitsu
+-  CEA (France)
+-  NEC
+

docs/users.rst

@@ -0,0 +1,185 @@
+.. sectnum::
+   :suffix: .
+   :depth: 3
+
+Architectural Overview
+======================
+
+See `Quick Guide -- Architectural Overview <quick.html#architectural-overview>`__.
+
+Running Programs
+================
+
+You need to check if your application and pre-/post-processing programs are suited to run with McKernel.
+Follow the guide below to choose to run the whole on McKernel, or run the whole on Linux, or run pre-/post-processing on Linux and the application on McKernel:
+
+* Application
+
+  - Run the whole on Linux if it issues system calls frequently and becoming the bottleneck with McKernel, e.g., those performing many file I/O operations.
+  - Otherwise, run it on McKernel.
+
+* Pre-/Post-processing
+
+  - Run it on McKernel if it consumes a large amount of memory or the execution time isn't prolonged prohivitively with McKernel. The reason for the first condition is that the resource could be limited for Linux CPUs in the nodes for McKernel.
+  - Otherwise, run it on Linux.
+
+
+Modify job script
+-----------------
+
+When using job submission system, you need to modify the job scripts so that the job script itself is going to run on Linux.
+For example, with Fujitsu Technical Computing Suite (TCS), you need to specify ``jobenv=mck1`` by inserting the following line into the job script:
+
+.. code-block:: none
+
+   #PJM -L jobenv=mck1
+
+Insert ``mcexec`` into the command line
+---------------------------------------
+
+You need to insert ``mcexec`` into the command lines invoking the programs that you chose to run on McKernel:
+
+Non-MPI programs
+~~~~~~~~~~~~~~~~
+
+Insert ``mcexec`` before an executable:
+
+::
+
+   mcexec ./a.out
+
+MPI programs
+~~~~~~~~~~~~
+
+Insert ``mcexec -n <processes-per-node>`` **after mpirun** and before an
+executable:
+
+::
+
+   mpirun -n <number-of-MPI-processes> mcexec -n <processes-per-node> ./a.out
+
+``<processes-per-node>`` is the number of the processes per node and
+calculated by (number of MPI processes) / (number of nodes).
+
+For example, ``<processes-per-node>`` equals to 4 (=32/8) when
+specifying the number of processes and nodes as follows with
+Fujitsu Technical Computing Suite.
+
+.. code-block:: none
+
+   #PJM --mpi "proc=32"
+   #PJM -L "node=8"
+
+Limitations
+===========
+
+1.  Pseudo devices such as /dev/mem and /dev/zero are not mmap()ed
+    correctly even if the mmap() returns a success. An access of their
+    mapping receives the SIGSEGV signal.
+
+2.  clone() supports only the following flags. All the other flags cause
+    clone() to return error or are simply ignored.
+
+    -  CLONE_CHILD_CLEARTID
+    -  CLONE_CHILD_SETTID
+    -  CLONE_PARENT_SETTID
+    -  CLONE_SETTLS
+    -  CLONE_SIGHAND
+    -  CLONE_VM
+
+3.  PAPI has the following restriction.
+
+    -  Number of counters a user can use at the same time is up to the
+       number of the physical counters in the processor.
+
+4.  msync writes back only the modified pages mapped by the calling
+    process.
+
+5.  The following syscalls always return the ENOSYS error.
+
+    -  migrate_pages()
+    -  move_pages()
+    -  set_robust_list()
+
+6.  The following syscalls always return the EOPNOTSUPP error.
+
+    -  arch_prctl(ARCH_SET_GS)
+    -  signalfd()
+
+7.  signalfd4() returns a fd, but signal is not notified through the fd.
+
+8.  set_rlimit sets the limit values but they are not enforced.
+
+9.  Address randomization is not supported.
+
+10. brk() extends the heap more than requestd when -h (–extend-heap-by=)
+    option of mcexec is used with the value larger than 4 KiB.
+    syscall_pwrite02 of LTP would fail for this reason. This is because
+    the test expects that the end of the heap is set to the same address
+    as the argument of sbrk() and expects a segmentation violation
+    occurs when it tries to access the memory area right next to the
+    boundary. However, the optimization sets the end to a value larger
+    than the requested. Therefore, the expected segmentation violation
+    doesn’t occur.
+
+11. setpriority()/getpriority() won’t work. They might set/get the
+    priority of a random mcexec thread. This is because there’s no fixed
+    correspondence between a McKernel thread which issues the system
+    call and a mcexec thread which handles the offload request.
+
+12. mbind() can set the policy but it is not used when allocating
+    physical pages.
+
+13. MPOL_F_RELATIVE_NODES and MPOL_INTERLEAVE flags for
+    set_mempolicy()/mbind() are not supported.
+
+14. The MPOL_BIND policy for set_mempolicy()/mbind() works as the same
+    as the MPOL_PREFERRED policy. That is, the physical page allocator
+    doesn’t give up the allocation when the specified nodes are running
+    out of pages but continues to search pages in the other nodes.
+
+15. Kernel dump on Linux panic requires Linux kernel CentOS-7.4 and
+    later. In addition, crash_kexec_post_notifiers kernel argument must
+    be given to Linux kernel.
+
+16. setfsuid()/setfsgid() cannot change the id of the calling thread.
+    Instead, it changes that of the mcexec worker thread which takes the
+    system-call offload request.
+
+17. mmap (hugeTLBfs): The physical pages corresponding to a map are
+    released when no McKernel process exist. The next map gets fresh
+    physical pages.
+
+18. Sticky bit on executable file has no effect.
+
+19. Linux (RHEL-7 for x86_64) could hang when offlining CPUs in the
+    process of booting McKernel due to the Linux bug, found in
+    Linux-3.10 and fixed in the later version. One way to circumvent
+    this is to always assign the same CPU set to McKernel.
+
+20. madvise:
+
+    -  MADV_HWPOISON and MADV_SOFT_OFFLINE always returns -EPERM.
+    -  MADV_MERGEABLE and MADV_UNMERGEABLE always returns -EINVAL.
+    -  MADV_HUGEPAGE and MADV_NOHUGEPAGE on file map returns -EINVAL
+       except on RHEL-8 for aarch64.
+
+21. brk() and mmap() doesn’t report out-of-memory through its return
+    value. Instead, page-fault reports the error.
+
+22. Anonymous mmap pre-maps requested number of pages when contiguous
+    pages are available. Demand paging is used when not available.
+
+23. Mixing page sizes in anonymous shared mapping is not allowed. mmap
+    creates vm_range with one page size. And munmap or mremap that needs
+    the reduced page size changes the sizes of all the pages of the
+    vm_range.
+
+24. ihk_os_getperfevent() could time-out when invoked from Fujitsu TCS
+    (job-scheduler).
+
+25. The behaviors of madvise and mbind are changed to do nothing and
+    report success as a workaround for Fugaku.
+
+26. mmap() allows unlimited overcommit. Note that it corresponds to
+    setting sysctl ``vm.overcommit_memory`` to 1.

docs/uti.rst

@@ -0,0 +1,91 @@
+Advanced: Enable Utility Thread offloading Interface (UTI)
+-------------------------------------------------------------
+
+UTI enables a runtime such as MPI runtime to spawn utility threads such
+as MPI asynchronous progress threads to Linux cores.
+
+Install capstone
+~~~~~~~~~~~~~~~~~~~~
+
+When compute nodes don't have access to repositories
+""""""""""""""""""""""""""""""""""""""""""""""""""""
+
+Install EPEL capstone-devel:
+
+::
+
+   sudo yum install https://dl.fedoraproject.org/pub/epel/epel-release-latest-8.noarch.rpm
+   sudo yum install capstone-devel
+
+
+When compute nodes don't have access to repositories
+""""""""""""""""""""""""""""""""""""""""""""""""""""
+
+Ask the system administrator to install ``capstone-devel``. Note that it is in the EPEL repository.
+
+
+Install syscall_intercept
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+::
+
+   git clone https://github.com/RIKEN-SysSoft/syscall_intercept.git
+   mkdir build && cd build
+   cmake <syscall_intercept>/arch/aarch64 -DCMAKE_INSTALL_PREFIX=<syscall-intercept-install> -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=gcc -DTREAT_WARNINGS_AS_ERRORS=OFF
+
+Install UTI for McKernel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Install:
+
+.. code-block:: none
+
+   git clone https://github.com/RIKEN-SysSoft/uti.git
+   mkdir build && cd build
+   ../uti/configure --prefix=<mckernel-install> --with-rm=mckernel
+   make && make install
+
+Install McKernel
+~~~~~~~~~~~~~~~~~~~~
+
+Add ``-DENABLE_UTI=ON`` option to ``cmake``:
+
+::
+
+   CMAKE_PREFIX_PATH=<syscall-intercept-install> cmake -DCMAKE_INSTALL_PREFIX=${HOME}/ihk+mckernel -DENABLE_UTI=ON $HOME/src/ihk+mckernel/mckernel
+
+Run programs
+~~~~~~~~~~~~~~~~
+
+Add ``--enable-uti`` option to ``mcexec``:
+
+::
+
+   mcexec --enable-uti <command>
+
+Install UTI for Linux
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+You should skip this step if it's already installed as with, for example, Fujitsu Technical Computing Suite.
+
+Install by make
+"""""""""""""""
+
+.. code-block:: none
+
+   git clone https://github.com/RIKEN-SysSoft/uti.git
+   mkdir build && cd build
+   ../uti/configure --prefix=<uti-install> --with-rm=linux
+   make && make install
+
+Install by rpm
+""""""""""""""
+
+.. code-block:: none
+
+   git clone https://github.com/RIKEN-SysSoft/uti.git
+   mkdir build && cd build
+   ../uti/configure --prefix=<uti-install> --with-rm=linux
+   rm -f ~/rpmbuild/SOURCES/<version>.tar.gz
+   rpmbuild -ba ./scripts/uti.spec
+   rpm -Uvh uti-<version>-<release>-<arch>.rpm

executer/include/uprotocol.h

@@ -91,6 +91,8 @@ struct program_image_section {
 
 struct get_cpu_set_arg {
 	int nr_processes;
+	char *req_cpu_list;   // Requested by user-space
+	int req_cpu_list_len; // Lenght of request string
 	int *process_rank;
 	void *cpu_set;
 	size_t cpu_set_size;	// Size in bytes

executer/kernel/mcctrl/control.c

@@ -613,16 +613,88 @@ static long mcexec_get_cpuset(ihk_os_t os, unsigned long arg)
 		return -EINVAL;
 	}
 
-	pe = &udp->part_exec;
-
-	mutex_lock(&pe->lock);
-
 	if (copy_from_user(&req, (void *)arg, sizeof(req))) {
 		printk("%s: error copying user request\n", __FUNCTION__);
 		ret = -EINVAL;
-		goto put_and_unlock_out;
+		goto put_out;
 	}
 
+	/* User requested CPU mask? */
+	if (req.req_cpu_list && req.req_cpu_list_len) {
+		char *cpu_list = NULL;
+
+		cpu_list = kmalloc(req.req_cpu_list_len, GFP_KERNEL);
+		if (!cpu_list) {
+			printk("%s: error: allocating CPU list\n", __FUNCTION__);
+			ret = -ENOMEM;
+			goto put_out;
+		}
+
+		if (copy_from_user(cpu_list,
+					req.req_cpu_list, req.req_cpu_list_len)) {
+			printk("%s: error copying CPU list request\n", __FUNCTION__);
+			kfree(cpu_list);
+			ret = -EINVAL;
+			goto put_out;
+		}
+
+		cpus_used = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		cpus_to_use = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		if (!cpus_to_use || !cpus_used) {
+			printk("%s: error: allocating CPU mask\n", __FUNCTION__);
+			ret = -ENOMEM;
+			kfree(cpu_list);
+			goto put_out;
+		}
+		memset(cpus_used, 0, sizeof(cpumask_t));
+		memset(cpus_to_use, 0, sizeof(cpumask_t));
+
+		/* Parse CPU list */
+		if (cpulist_parse(cpu_list, cpus_to_use) < 0) {
+			printk("%s: invalid CPUs requested: %s\n",
+				__FUNCTION__, cpu_list);
+			ret = -EINVAL;
+			kfree(cpu_list);
+			goto put_out;
+		}
+
+		memcpy(cpus_used, cpus_to_use, sizeof(cpumask_t));
+
+		/* Copy mask to user-space */
+		if (copy_to_user(req.cpu_set, cpus_used,
+					(req.cpu_set_size < sizeof(cpumask_t) ?
+					 req.cpu_set_size : sizeof(cpumask_t)))) {
+			printk("%s: error copying mask to user\n", __FUNCTION__);
+			ret = -EINVAL;
+			kfree(cpu_list);
+			goto put_out;
+		}
+
+		/* Copy IKC target core */
+		cpu = cpumask_next(-1, cpus_used);
+		if (copy_to_user(req.target_core, &cpu, sizeof(cpu))) {
+			printk("%s: error copying target core to user\n",
+					__FUNCTION__);
+			ret = -EINVAL;
+			kfree(cpu_list);
+			goto put_out;
+		}
+
+		/* Save in per-process structure */
+		memcpy(&ppd->cpu_set, cpus_used, sizeof(cpumask_t));
+		ppd->ikc_target_cpu = cpu;
+		printk("%s: %s -> target McKernel CPU: %d\n",
+			__func__, cpu_list, cpu);
+
+		ret = 0;
+		kfree(cpu_list);
+		goto put_out;
+	}
+
+	pe = &udp->part_exec;
+
+	mutex_lock(&pe->lock);
+
 	/* First process to enter CPU partitioning */
 	if (pe->nr_processes == -1) {
 		pe->nr_processes = req.nr_processes;
@@ -997,11 +1069,14 @@ next_cpu:
 	ret = 0;
 
 put_and_unlock_out:
+	mutex_unlock(&pe->lock);
+
+put_out:
+	mcctrl_put_per_proc_data(ppd);
+
 	kfree(cpus_to_use);
 	kfree(cpus_used);
 	kfree(mcexec_cpu_set);
-	mcctrl_put_per_proc_data(ppd);
-	mutex_unlock(&pe->lock);
 
 	return ret;
 }

executer/kernel/mcctrl/syscall.c

@@ -539,7 +539,11 @@ retry_alloc:
 #define	USE_VM_INSERT_PFN	1
 
 #if LINUX_VERSION_CODE >= KERNEL_VERSION(4, 11, 0)
+#if defined(RHEL_RELEASE_CODE) && RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(8, 2)
+static vm_fault_t rus_vm_fault(struct vm_fault *vmf)
+#else
 static int rus_vm_fault(struct vm_fault *vmf)
+#endif
 {
 	struct vm_area_struct *vma = vmf->vma;
 #else

executer/user/CMakeLists.txt

@@ -27,6 +27,7 @@ if (NOT LIBDWARF)
 		"${CMAKE_CURRENT_SOURCE_DIR}/lib/libdwarf/libdwarf/libdwarf/")
 	target_link_libraries(mcinspect dwarf z elf)
 else()
+	target_include_directories(mcinspect PRIVATE ${DWARF_H})
 	target_link_libraries(mcinspect ${LIBDWARF})
 endif()
 target_link_libraries(mcinspect ${LIBBFD})

executer/user/mcexec.c

@@ -1322,7 +1322,8 @@ void init_sigaction(void)
 
 	master_tid = gettid();
 	for (i = 1; i <= 64; i++) {
-		if (i != SIGKILL && i != SIGSTOP && i != SIGCHLD) {
+		if (i != SIGKILL && i != SIGSTOP && i != SIGCHLD &&
+				i != SIGTSTP && i != SIGTTIN && i != SIGTTOU) {
 			struct sigaction act;
 
 			sigaction(i, NULL, &act);
@@ -2211,6 +2212,64 @@ int main(int argc, char **argv)
 
 	pthread_spin_init(&overlay_fd_lock, 0);
 
+	/* XXX: Fugaku: Fujitsu process placement fix */
+	if (getenv("FLIB_AFFINITY_ON_PROCESS")) {
+		char *cpu_s;
+		int flib_size;
+		char *flib_aff_orig, *flib_aff;
+		int cpu, off = 0;
+
+		flib_aff_orig = strdup(getenv("FLIB_AFFINITY_ON_PROCESS"));
+		if (!flib_aff_orig) {
+			fprintf(stderr, "error: dupping FLIB_AFFINITY_ON_PROCESS\n");
+			exit(EXIT_FAILURE);
+		}
+
+		flib_size = strlen(flib_aff_orig) * 2;
+
+		flib_aff = malloc(flib_size);
+		if (!flib_aff) {
+			fprintf(stderr, "error: allocating memory for "
+					"FLIB_AFFINITY_ON_PROCESS\n");
+			exit(EXIT_FAILURE);
+		}
+		memset(flib_aff, 0, flib_size);
+
+		cpu_s = strtok(flib_aff_orig, ",");
+		while (cpu_s) {
+			int ret;
+
+			/* "Shift" left by 12 CPUs */
+			cpu = atoi(cpu_s) - 12;
+
+			/* Prepend "," */
+			if (off > 0) {
+				ret = snprintf(flib_aff + off, flib_size - off, "%s", ",");
+				if (ret < 0) {
+					fprintf(stderr, "error: constructing "
+							"FLIB_AFFINITY_ON_PROCESS\n");
+					exit(EXIT_FAILURE);
+				}
+
+				off += ret;
+			}
+
+			ret = snprintf(flib_aff + off, flib_size - off, "%d", cpu);
+			if (ret < 0) {
+				fprintf(stderr, "error: constructing "
+						"FLIB_AFFINITY_ON_PROCESS\n");
+				exit(EXIT_FAILURE);
+			}
+
+			off += ret;
+			cpu_s = strtok(NULL, ",");
+		}
+
+		__dprintf("FLIB_AFFINITY_ON_PROCESS: %s -> %s\n",
+				getenv("FLIB_AFFINITY_ON_PROCESS"), flib_aff);
+		setenv("FLIB_AFFINITY_ON_PROCESS", flib_aff, 1);
+	}
+
 	ld_preload_init();
 
 #ifdef ADD_ENVS_OPTION
@@ -2385,6 +2444,13 @@ int main(int argc, char **argv)
 		}
 	}
 
+	/* Fugaku: use FLIB_NUM_PROCESS_ON_NODE if -n is not specified */
+	if (getenv("FLIB_NUM_PROCESS_ON_NODE") && nr_processes == 0) {
+		nr_processes = atoi(getenv("FLIB_NUM_PROCESS_ON_NODE"));
+		__dprintf("%s: using FLIB_NUM_PROCESS_ON_NODE: %d\n",
+			__func__, nr_processes);
+	}
+
 	if (nr_processes > ncpu) {
 		fprintf(stderr, "error: nr_processes can't exceed nr. of CPUs\n");
 		return EINVAL;
@@ -2483,6 +2549,8 @@ int main(int argc, char **argv)
 
 		CPU_ZERO(&mcexec_cpu_set);
 
+		cpu_set_arg.req_cpu_list = NULL;
+		cpu_set_arg.req_cpu_list_len = 0;
 		cpu_set_arg.cpu_set = (void *)&desc->cpu_set;
 		cpu_set_arg.cpu_set_size = sizeof(desc->cpu_set);
 		cpu_set_arg.nr_processes = nr_processes;
@@ -2493,6 +2561,16 @@ int main(int argc, char **argv)
 		cpu_set_arg.mcexec_cpu_set_size = sizeof(mcexec_cpu_set);
 		cpu_set_arg.ikc_mapped = &ikc_mapped;
 
+		/* Fugaku specific: Fujitsu CPU binding */
+		if (getenv("FLIB_AFFINITY_ON_PROCESS")) {
+			cpu_set_arg.req_cpu_list =
+				getenv("FLIB_AFFINITY_ON_PROCESS");
+			cpu_set_arg.req_cpu_list_len =
+				strlen(cpu_set_arg.req_cpu_list) + 1;
+			__dprintf("%s: requesting CPUs: %s\n",
+				__func__, cpu_set_arg.req_cpu_list);
+		}
+
 		if (ioctl(fd, MCEXEC_UP_GET_CPUSET, (void *)&cpu_set_arg) != 0) {
 			perror("getting CPU set for partitioned execution");
 			close(fd);
@@ -2502,6 +2580,13 @@ int main(int argc, char **argv)
 		desc->cpu = target_core;
 		desc->process_rank = process_rank;
 
+		/* Fugaku specific: Fujitsu node-local rank */
+		if (getenv("FLIB_RANK_ON_NODE")) {
+			desc->process_rank = atoi(getenv("FLIB_RANK_ON_NODE"));
+			__dprintf("%s: rank: %d, target CPU: %d\n",
+				__func__, desc->process_rank, desc->cpu);
+		}
+
 		/* Bind to CPU cores where the LWK process' IKC target maps to */
 		if (ikc_mapped && !no_bind_ikc_map) {
 			/* This call may not succeed, but that is fine */

kernel/hugefileobj.c

@@ -139,7 +139,6 @@ static void hugefileobj_free(struct memobj *memobj)
 struct memobj_ops hugefileobj_ops = {
 	.free = hugefileobj_free,
 	.get_page = hugefileobj_get_page,
-
 };
 
 void hugefileobj_cleanup(void)

kernel/include/mman.h

@@ -72,4 +72,11 @@
 #define	MS_INVALIDATE	0x02
 #define	MS_SYNC		0x04
 
+/* include/uapi/linux/mman.h */
+#define OVERCOMMIT_GUESS		0
+#define OVERCOMMIT_ALWAYS		1
+#define OVERCOMMIT_NEVER		2
+
+extern int sysctl_overcommit_memory;
+
 #endif /* HEADER_MMAN_H */

kernel/include/process.h

@@ -505,10 +505,12 @@ struct process {
 			// PS_STOPPED -----+
 			// (PS_TRACED)
 
-	/* Store exit_status for a group of threads when stopped by SIGSTOP.
-	   exit_status can't be used because values of exit_status of threads
-	   might divert while the threads are exiting by group_exit(). */
-	int group_exit_status;
+	/* Store exit_status for a group of threads when stopped by SIGSTOP.  */
+	/* exit_status can't be used because values of exit_status of threads */
+	/* might divert while the threads are exiting by group_exit().	      */
+	/* The upper 4 bytes of group_exit_status is the confirmation flag of */
+	/* exit status. The lower 4 bytes is the exit status.		      */
+	unsigned long group_exit_status;
 
 	/* Manage ptraced processes in the separate list to make it easy to
 	   restore the orginal parent child relationship when 

kernel/include/rusage_private.h

@@ -11,6 +11,7 @@
 #include <ihk/ihk_monitor.h>
 #include <ihk/debug.h>
 #include <memory.h>
+#include <mman.h>
 
 #ifdef ENABLE_RUSAGE
 
@@ -56,6 +57,24 @@ rusage_total_memory_add(unsigned long size)
 #endif
 }
 
+static inline unsigned long
+rusage_get_total_memory()
+{
+	return rusage.total_memory;
+}
+
+static inline unsigned long
+rusage_get_free_memory()
+{
+	return rusage.total_memory - rusage.total_memory_usage;
+}
+
+static inline unsigned long
+rusage_get_usage_memory()
+{
+	return rusage.total_memory_usage;
+}
+
 static inline void
 rusage_rss_add(unsigned long size)
 {
@@ -293,6 +312,9 @@ rusage_check_overmap(size_t len, int pgshift)
 {
 	int npages = 0, remain_pages = 0;
 
+	if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+		return 0;
+
 	npages = (len + (1UL << pgshift) - 1) >> pgshift;
 	remain_pages = (rusage.total_memory - rusage.total_memory_usage)
 			>> pgshift;
@@ -399,6 +421,24 @@ rusage_rss_add(unsigned long size)
 {
 }
 
+static inline unsigned long
+rusage_get_total_memory()
+{
+	return 0;
+}
+
+static inline unsigned long
+rusage_get_free_memory()
+{
+	return 0;
+}
+
+static inline unsigned long
+rusage_get_usage_memory()
+{
+	return 0;
+}
+
 static inline void
 rusage_rss_sub(unsigned long size)
 {

kernel/include/syscall.h

@@ -443,6 +443,22 @@ struct rusage {
 	long   ru_nivcsw;
 };
 
+struct sysinfo {
+	long uptime;             /* Seconds since boot */
+	unsigned long loads[3];  /* 1, 5, and 15 minute load averages */
+	unsigned long totalram;  /* Total usable main memory size */
+	unsigned long freeram;   /* Available memory size */
+	unsigned long sharedram; /* Amount of shared memory */
+	unsigned long bufferram; /* Memory used by buffers */
+	unsigned long totalswap; /* Total swap space size */
+	unsigned long freeswap;  /* swap space still available */
+	unsigned short procs;    /* Number of current processes */
+	unsigned long totalhigh; /* Total high memory size */
+	unsigned long freehigh;  /* Available high memory size */
+	unsigned int mem_unit;   /* Memory unit size in bytes */
+	char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding for libc5 */
+};
+
 extern void terminate(int, int);
 
 struct tod_data_s {
@@ -635,4 +651,6 @@ extern int (*linux_clock_gettime)(clockid_t clk_id, struct timespec *tp);
 #define COREDUMP_TO_BE_WOKEN      2
 
 extern void terminate_host(int pid, struct thread *thread);
+struct sig_pending *getsigpending(struct thread *thread, int delflag);
+int interrupt_from_user(void *regs0);
 #endif

kernel/mem.c

@@ -62,6 +62,7 @@ extern int interrupt_from_user(void *);
 struct tlb_flush_entry tlb_flush_vector[IHK_TLB_FLUSH_IRQ_VECTOR_SIZE];
 
 int anon_on_demand = 0;
+int sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
 
 static struct ihk_mc_pa_ops *pa_ops;
 

kernel/process.c

@@ -2176,13 +2176,62 @@ static int do_page_fault_process_vm(struct process_vm *vm, void *fault_addr0, ui
 {
 	int error;
 	const uintptr_t fault_addr = (uintptr_t)fault_addr0;
-	struct vm_range *range;
+	struct vm_range *range = NULL;
 	struct thread *thread = cpu_local_var(current);
 	int locked = 0;
 
 	dkprintf("[%d]do_page_fault_process_vm(%p,%lx,%lx)\n",
 			ihk_mc_get_processor_id(), vm, fault_addr0, reason);
 	
+	/* grow stack */
+	if (fault_addr >= thread->vm->region.stack_start &&
+	    fault_addr < thread->vm->region.stack_end) {
+		range = lookup_process_memory_range(vm,
+						    thread->vm->region.stack_end - 1,
+						    thread->vm->region.stack_end);
+		if (range == NULL) {
+			error = -EFAULT;
+			ekprintf("%s: vm: %p, addr: %p, reason: %lx):"
+				 "stack not found: %d\n",
+				 __func__, vm, fault_addr0, reason, error);
+			goto out;
+		}
+
+		/* don't grow if replaced with hugetlbfs */
+		if (range->memobj) {
+			goto skip;
+		}
+
+		if (fault_addr >= range->start) {
+			goto skip;
+		}
+
+		if (thread->vm->is_memory_range_lock_taken == -1 ||
+		    thread->vm->is_memory_range_lock_taken !=
+		    ihk_mc_get_processor_id()) {
+			ihk_rwspinlock_write_lock_noirq(&vm->memory_range_lock);
+			locked = 1;
+		}
+
+		if (range->pgshift) {
+			range->start = fault_addr &
+				~((1UL << range->pgshift) - 1);
+		} else {
+			range->start = fault_addr & PAGE_MASK;
+		}
+
+		if (locked) {
+			ihk_rwspinlock_write_unlock_noirq(&vm->memory_range_lock);
+			locked = 0;
+		}
+
+		dkprintf("%s: addr: %lx, reason: %lx, range: %lx-%lx:"
+			 "stack found\n",
+			 __func__, (unsigned long)fault_addr, reason,
+			 range->start, range->end);
+	}
+skip:
+
 	if (thread->vm->is_memory_range_lock_taken == -1 ||
 			thread->vm->is_memory_range_lock_taken != ihk_mc_get_processor_id()) {
 		ihk_rwspinlock_read_lock_noirq(&vm->memory_range_lock);
@@ -2197,13 +2246,16 @@ static int do_page_fault_process_vm(struct process_vm *vm, void *fault_addr0, ui
 		goto out;
 	}
 
-	range = lookup_process_memory_range(vm, fault_addr, fault_addr+1);
-	if (range == NULL) {
-		error = -EFAULT;
-		dkprintf("do_page_fault_process_vm(): vm: %p, addr: %p, reason: %lx):"
-				"out of range: %d\n",
-				vm, fault_addr0, reason, error);
-		goto out;
+	if (!range) {
+		range = lookup_process_memory_range(vm, fault_addr,
+						    fault_addr+1);
+		if (range == NULL) {
+			error = -EFAULT;
+			dkprintf("%s: vm: %p, addr: %p, reason: %lx):"
+				 "out of range: %d\n",
+				 __func__, vm, fault_addr0, reason, error);
+			goto out;
+		}
 	}
 
 	if (((range->flag & VR_PROT_MASK) == VR_PROT_NONE)
@@ -2367,16 +2419,15 @@ int init_process_stack(struct thread *thread, struct program_load_desc *pn,
 		size = minsz;
 	}
 	size = (size + USER_STACK_PREPAGE_SIZE - 1) & USER_STACK_PAGE_MASK;
-	dkprintf("%s: stack_premap: %lu, rlim_cur: %lu, minsz: %lu, size: %lu\n",
-			__FUNCTION__,
-			pn->stack_premap,
-			proc->rlimit[MCK_RLIMIT_STACK].rlim_cur,
-			minsz, size);
-	start = (end - size) & USER_STACK_PAGE_MASK;
+	dkprintf("%s: stack_premap: %lu, rlim_cur: %lu, minsz: %lu, size: %lu, maxsz: %lx\n",
+		 __func__, pn->stack_premap,
+		 proc->rlimit[MCK_RLIMIT_STACK].rlim_cur,
+		 minsz, size, maxsz);
+	start = (end - minsz) & USER_STACK_PAGE_MASK;
 
 	/* Apply user allocation policy to stacks */
 	/* TODO: make threshold kernel or mcexec argument */
-	ap_flag = (size >= proc->mpol_threshold &&
+	ap_flag = (minsz >= proc->mpol_threshold &&
 		!(proc->mpol_flags & MPOL_NO_STACK)) ? IHK_MC_AP_USER : 0;
 	dkprintf("%s: max size: %lu, mapped size: %lu %s\n",
 			__FUNCTION__, size, minsz,
@@ -2508,7 +2559,7 @@ int init_process_stack(struct thread *thread, struct program_load_desc *pn,
 	ihk_mc_modify_user_context(thread->uctx, IHK_UCR_STACK_POINTER,
 	                           end + sizeof(unsigned long) * s_ind);
 	thread->vm->region.stack_end = end;
-	thread->vm->region.stack_start = start;
+	thread->vm->region.stack_start = (end - size) & USER_STACK_PAGE_MASK;
 
 	return 0;
 }

kernel/syscall.c

@@ -120,7 +120,6 @@ extern int num_processors;
 extern unsigned long ihk_mc_get_ns_per_tsc(void);
 extern int ptrace_detach(int pid, int data);
 extern void debug_log(unsigned long);
-extern int arch_clear_host_user_space();
 extern long arch_ptrace(long request, int pid, long addr, long data);
 extern struct cpu_local_var *clv;
 
@@ -242,11 +241,6 @@ long do_syscall(struct syscall_request *req, int cpu)
 			unsigned long flags;
 			DECLARE_WAITQ_ENTRY(scd_wq_entry, cpu_local_var(current));
 
-			if (req->number == __NR_epoll_wait ||
-				req->number == __NR_epoll_pwait ||
-				req->number == __NR_ppoll)
-				goto schedule;
-
 			cpu_pause();
 
 			/* Spin if not preemptable */
@@ -275,7 +269,6 @@ long do_syscall(struct syscall_request *req, int cpu)
 				continue;
 			}
 
-schedule:
 			flags = cpu_disable_interrupt_save();
 
 			/* Try to sleep until notified */
@@ -455,34 +448,59 @@ static int wait_stopped(struct thread *thread, struct process *child, struct thr
 			 thread->proc->pid, child->pid, options);
 	int ret;
 
-	/* Copy exit_status created in do_signal */
-	int *exit_status;
-
 	if (c_thread) {
-		exit_status = &c_thread->exit_status;
+		/* Skip this process because exit_status has been reaped. */
+		if (!c_thread->exit_status) {
+			ret = 0;
+			goto out;
+		}
+
+		/* TODO: define 0x7f in kernel/include/process.h */
+		if (status) {
+			*status =  (c_thread->exit_status << 8) | 0x7f;
+		}
+
+		/* Reap exit_status. signal_flags is reaped on receiving */
+		/* signal in do_kill(). */
+		if (!(options & WNOWAIT)) {
+			c_thread->exit_status = 0;
+		}
 	}
 	else if (child->status & (PS_STOPPED | PS_DELAY_STOPPED)) {
-		exit_status = &child->group_exit_status;
+		/* Skip this process because exit_status has been reaped. */
+		if (!child->group_exit_status) {
+			ret = 0;
+			goto out;
+		}
+
+		/* TODO: define 0x7f in kernel/include/process.h */
+		if (status) {
+			*status = (child->group_exit_status << 8) | 0x7f;
+		}
+
+		/* Reap exit_status. signal_flags is reaped on receiving */
+		/* signal in do_kill(). */
+		if (!(options & WNOWAIT)) {
+			child->group_exit_status = 0;
+		}
 	}
 	else {
-		exit_status = &child->main_thread->exit_status;
-	}
+		/* Skip this process because exit_status has been reaped. */
+		if (!child->main_thread->exit_status) {
+			ret = 0;
+			goto out;
+		}
 
-	/* Skip this process because exit_status has been reaped. */
-	if (!*exit_status) {
-		ret = 0;
-		goto out;
-	}
+		/* TODO: define 0x7f in kernel/include/process.h */
+		if (status) {
+			*status = (child->main_thread->exit_status << 8) | 0x7f;
+		}
 
-	/* TODO: define 0x7f in kernel/include/process.h */
-	if (status) {
-		*status =  (*exit_status << 8) | 0x7f;
-	}
-
-	/* Reap exit_status. signal_flags is reaped on receiving signal
-	   in do_kill(). */
-	if(!(options & WNOWAIT)) {
-		*exit_status = 0;
+		/* Reap exit_status. signal_flags is reaped on receiving */
+		/* signal in do_kill(). */
+		if (!(options & WNOWAIT)) {
+			child->main_thread->exit_status = 0;
+		}
 	}
 
 	dkprintf("wait_stopped,child->pid=%d,status=%08x\n",
@@ -2660,10 +2678,8 @@ static int do_execveat(ihk_mc_user_context_t *ctx, int dirfd,
 	}
 	
 	/* Clear host user space PTEs */
-	if (arch_clear_host_user_space()) {
-		kprintf("execve(): ERROR: clearing PTEs in host process\n");
-		panic("");
-	}		
+	clear_host_pte(vm->region.user_start,
+			(vm->region.user_end - vm->region.user_start), 0);
 
 	/* Request host to transfer ELF image */
 	request.number = __NR_execve;
@@ -3224,7 +3240,6 @@ SYSCALL_DECLARE(kill)
 	return error;
 }
 
-// see linux-2.6.34.13/kernel/signal.c
 SYSCALL_DECLARE(tgkill)
 {
 	int tgid = ihk_mc_syscall_arg0(ctx);
@@ -3233,16 +3248,15 @@ SYSCALL_DECLARE(tgkill)
 	struct thread *thread = cpu_local_var(current);
 	struct siginfo info;
 
+	if (tgid <= 0 || tid <= 0) {
+		return -EINVAL;
+	}
+
 	memset(&info, '\0', sizeof info);
 	info.si_signo = sig;
 	info.si_code = SI_TKILL;
 	info._sifields._kill.si_pid = thread->proc->pid;
 
-	if(tid <= 0)
-		return -EINVAL;
-	if(tgid <= 0 && tgid != -1)
-		return -EINVAL;
-
 	return do_kill(thread, tgid, tid, sig, &info, 0);
 }
 
@@ -3517,9 +3531,15 @@ SYSCALL_DECLARE(setpgid)
 
 /* Ignore the registration by start_thread() (in pthread_create.c)
    because McKernel doesn't unlock mutex-es held by the thread which has been killed. */
+#define ROBUST_LIST_HEAD_SIZE 24
 SYSCALL_DECLARE(set_robust_list)
 {
-	// Palliative fix. wait for impl.
+	size_t len = (size_t)ihk_mc_syscall_arg1(ctx);
+
+	if (len != ROBUST_LIST_HEAD_SIZE) {
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -5140,6 +5160,37 @@ SYSCALL_DECLARE(rt_sigsuspend)
 	return do_sigsuspend(thread, &wset);
 }
 
+SYSCALL_DECLARE(rt_sigaction)
+{
+	int sig = ihk_mc_syscall_arg0(ctx);
+	const struct sigaction *act =
+		(const struct sigaction *)ihk_mc_syscall_arg1(ctx);
+	struct sigaction *oact = (struct sigaction *)ihk_mc_syscall_arg2(ctx);
+	size_t sigsetsize = ihk_mc_syscall_arg3(ctx);
+	struct k_sigaction new_sa, old_sa;
+	int rc;
+
+	if (sigsetsize != sizeof(sigset_t))
+		return -EINVAL;
+
+	if (act) {
+		if (copy_from_user(&new_sa.sa, act, sizeof(new_sa.sa))) {
+			goto fault;
+		}
+	}
+
+	rc = do_sigaction(sig, act ? &new_sa : NULL, oact ? &old_sa : NULL);
+	if (rc == 0 && oact) {
+		if (copy_to_user(oact, &old_sa.sa, sizeof(old_sa.sa))) {
+			goto fault;
+		}
+	}
+
+	return rc;
+fault:
+	return -EFAULT;
+}
+
 SYSCALL_DECLARE(sigaltstack)
 {
 	struct thread *thread = cpu_local_var(current);
@@ -6544,71 +6595,162 @@ static int rlimits[] = {
 #endif
 };
 
-SYSCALL_DECLARE(setrlimit)
+static int do_prlimit64(int pid, int resource, struct rlimit *_new_limit,
+			struct rlimit *old_limit)
 {
-	int rc;
-	int resource = ihk_mc_syscall_arg0(ctx);
-	struct rlimit *rlm = (struct rlimit *)ihk_mc_syscall_arg1(ctx);
-	struct thread *thread = cpu_local_var(current);
-	int	i;
-	struct rlimit new_rlim;
-	int	mcresource;
+	struct rlimit new_limit;
+	int resource_found;
+	int i;
+	int mcresource;
+	struct process *proc;
+	struct resource_set *rset = cpu_local_var(resource_set);
+	int hash;
+	struct process_hash *phash = rset->process_hash;
+	struct mcs_rwlock_node exist_lock;
+	struct mcs_rwlock_node update_lock;
+	unsigned long irqstate;
+	int found;
+	int ret;
+	ihk_mc_user_context_t ctx;
 
-	if (copy_from_user(&new_rlim, rlm, sizeof(*rlm))) {
-		return -EFAULT;
-	}
-	if (new_rlim.rlim_cur > new_rlim.rlim_max) {
+	if (resource < 0 || resource >= RLIMIT_NLIMITS) {
 		return -EINVAL;
 	}
 
-	switch(resource){
-	    case RLIMIT_FSIZE:
-	    case RLIMIT_NOFILE:
-	    case RLIMIT_LOCKS:
-	    case RLIMIT_MSGQUEUE:
-		rc = syscall_generic_forwarding(__NR_setrlimit, ctx);
-		if(rc < 0)
-			return rc;
-		break;
-	}
+	if (_new_limit) {
+		if (copy_from_user(&new_limit, _new_limit,
+				   sizeof(struct rlimit))) {
+			return -EFAULT;
+		}
 
-	for(i = 0; i < sizeof(rlimits) / sizeof(int); i += 2)
-		if(rlimits[i] == resource){
-			mcresource = rlimits[i + 1];
+		if (new_limit.rlim_cur > new_limit.rlim_max) {
+			return -EINVAL;
+		}
+
+		/* update Linux side value as well */
+		switch (resource) {
+		case RLIMIT_FSIZE:
+		case RLIMIT_NOFILE:
+		case RLIMIT_LOCKS:
+		case RLIMIT_MSGQUEUE:
+			ihk_mc_syscall_arg0(&ctx) = pid;
+			ihk_mc_syscall_arg1(&ctx) = resource;
+			ihk_mc_syscall_arg2(&ctx) =
+				(unsigned long)_new_limit;
+			ihk_mc_syscall_arg3(&ctx) =
+				(unsigned long)old_limit;
+			ret = syscall_generic_forwarding(__NR_prlimit64, &ctx);
+			if (ret < 0)
+				return ret;
 			break;
 		}
-	if(i >= sizeof(rlimits) / sizeof(int)){
-		return syscall_generic_forwarding(__NR_setrlimit, ctx);
 	}
 
-	memcpy(thread->proc->rlimit + mcresource, &new_rlim,
-		sizeof(new_rlim));
+	/* translate resource */
+	resource_found = 0;
+	for (i = 0; i < sizeof(rlimits) / sizeof(int); i += 2) {
+		if (rlimits[i] == resource) {
+			mcresource = rlimits[i + 1];
+			resource_found = 1;
+			break;
+		}
+	}
 
-	return 0;
+	if (!resource_found) {
+		ihk_mc_syscall_arg0(&ctx) = pid;
+		ihk_mc_syscall_arg1(&ctx) = resource;
+		ihk_mc_syscall_arg2(&ctx) =
+			(unsigned long)_new_limit;
+		ihk_mc_syscall_arg3(&ctx) =
+			(unsigned long)old_limit;
+		return syscall_generic_forwarding(__NR_prlimit64, &ctx);
+	}
+
+	/* find process */
+	found = 0;
+
+	if (pid == 0) {
+		struct thread *thread = cpu_local_var(current);
+
+		pid = thread->proc->pid;
+	}
+
+	irqstate = cpu_disable_interrupt_save();
+	hash = process_hash(pid);
+	mcs_rwlock_reader_lock_noirq(&phash->lock[hash], &exist_lock);
+
+	list_for_each_entry(proc, &phash->list[hash], hash_list) {
+		if (proc->pid == pid) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		mcs_rwlock_reader_unlock_noirq(&phash->lock[hash], &exist_lock);
+		cpu_restore_interrupt(irqstate);
+		return -ESRCH;
+	}
+
+	if (_new_limit) {
+		mcs_rwlock_writer_lock_noirq(&proc->update_lock, &update_lock);
+	} else {
+		mcs_rwlock_reader_lock_noirq(&proc->update_lock, &update_lock);
+	}
+
+	if (old_limit) {
+		if (copy_to_user(old_limit, proc->rlimit + mcresource,
+				 sizeof(struct rlimit))) {
+			ret = -EFAULT;
+			goto out;
+		}
+	}
+
+	if (_new_limit) {
+		memcpy(proc->rlimit + mcresource, &new_limit,
+		       sizeof(struct rlimit));
+	}
+
+	ret = 0;
+ out:
+	if (_new_limit) {
+		mcs_rwlock_writer_unlock_noirq(&proc->update_lock,
+					       &update_lock);
+	} else {
+		mcs_rwlock_reader_unlock_noirq(&proc->update_lock,
+					       &update_lock);
+	}
+
+	mcs_rwlock_reader_unlock_noirq(&phash->lock[hash], &exist_lock);
+	cpu_restore_interrupt(irqstate);
+
+	return ret;
+}
+
+SYSCALL_DECLARE(setrlimit)
+{
+	int resource = ihk_mc_syscall_arg0(ctx);
+	struct rlimit *new_limit = (struct rlimit *)ihk_mc_syscall_arg1(ctx);
+
+	return do_prlimit64(0, resource, new_limit, NULL);
 }
 
 SYSCALL_DECLARE(getrlimit)
 {
 	int resource = ihk_mc_syscall_arg0(ctx);
-	struct rlimit *rlm = (struct rlimit *)ihk_mc_syscall_arg1(ctx);
-	struct thread *thread = cpu_local_var(current);
-	int	i;
-	int	mcresource;
+	struct rlimit *old_limit = (struct rlimit *)ihk_mc_syscall_arg1(ctx);
 
-	for(i = 0; i < sizeof(rlimits) / sizeof(int); i += 2)
-		if(rlimits[i] == resource){
-			mcresource = rlimits[i + 1];
-			break;
-		}
-	if(i >= sizeof(rlimits) / sizeof(int)){
-		return syscall_generic_forwarding(__NR_getrlimit, ctx);
-	}
+	return do_prlimit64(0, resource, NULL, old_limit);
+}
 
-// TODO: check limit
-	if(copy_to_user(rlm, thread->proc->rlimit + mcresource, sizeof(struct rlimit)))
-		return -EFAULT;
+SYSCALL_DECLARE(prlimit64)
+{
+	int pid = ihk_mc_syscall_arg0(ctx);
+	int resource = ihk_mc_syscall_arg1(ctx);
+	struct rlimit *new_limit = (struct rlimit *)ihk_mc_syscall_arg2(ctx);
+	struct rlimit *old_limit = (struct rlimit *)ihk_mc_syscall_arg3(ctx);
 
-	return 0;
+	return do_prlimit64(pid, resource, new_limit, old_limit);
 }
 
 SYSCALL_DECLARE(getrusage)
@@ -6686,6 +6828,27 @@ SYSCALL_DECLARE(getrusage)
 	return 0;
 }
 
+SYSCALL_DECLARE(sysinfo)
+{
+	struct sysinfo *sysinfo = (struct sysinfo *)ihk_mc_syscall_arg0(ctx);
+	struct sysinfo __sysinfo;
+	int ret = 0;
+
+	memset(&__sysinfo, '\0', sizeof(struct sysinfo));
+
+	__sysinfo.totalram = rusage_get_total_memory();
+	__sysinfo.freeram = rusage_get_free_memory();
+	__sysinfo.mem_unit = 1; // always one unit for McKernel
+
+	if (copy_to_user(sysinfo, &__sysinfo, sizeof(struct sysinfo))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+out:
+	return ret;
+}
+
 extern int ptrace_traceme(void);
 extern void set_single_step(struct thread *thread);
 
@@ -10320,11 +10483,7 @@ long syscall(int num, ihk_mc_user_context_t *ctx)
 	}
 #endif // PROFILE_ENABLE
 
-	/* Do not deschedule when returning from an event (e.g., MPI) */
-	if (!(num == __NR_epoll_wait ||
-				num == __NR_epoll_pwait ||
-				num == __NR_ppoll) &&
-			smp_load_acquire(&v->flags) & CPU_FLAG_NEED_RESCHED) {
+	if (smp_load_acquire(&v->flags) & CPU_FLAG_NEED_RESCHED) {
 		check_need_resched();
 	}
 
@@ -10345,3 +10504,275 @@ long syscall(int num, ihk_mc_user_context_t *ctx)
 
 	return l;
 }
+
+static int
+check_sig_pending_thread(struct thread *thread)
+{
+	int found = 0;
+	struct list_head *head;
+	mcs_rwlock_lock_t *lock;
+	struct mcs_rwlock_node_irqsave mcs_rw_node;
+	struct sig_pending *next;
+	struct sig_pending *pending;
+	__sigset_t w;
+	__sigset_t x;
+	int sig = 0;
+	struct k_sigaction *k;
+	struct cpu_local_var *v;
+
+	v = get_this_cpu_local_var();
+	w = thread->sigmask.__val[0];
+
+	lock = &thread->sigcommon->lock;
+	head = &thread->sigcommon->sigpending;
+	for (;;) {
+		mcs_rwlock_reader_lock(lock, &mcs_rw_node);
+
+		list_for_each_entry_safe(pending, next, head, list) {
+			for (x = pending->sigmask.__val[0], sig = 0; x;
+				 sig++, x >>= 1) {
+			}
+			k = thread->sigcommon->action + sig - 1;
+			if ((sig != SIGCHLD &&
+				 sig != SIGURG &&
+				 sig != SIGCONT) ||
+				(k->sa.sa_handler != SIG_IGN &&
+				 k->sa.sa_handler != NULL)) {
+				if (!(pending->sigmask.__val[0] & w)) {
+					if (pending->interrupted == 0) {
+						pending->interrupted = 1;
+						found = 1;
+						if (sig != SIGCHLD &&
+							sig != SIGURG &&
+							sig != SIGCONT &&
+							!k->sa.sa_handler) {
+							found = 2;
+							break;
+						}
+					}
+				}
+			}
+		}
+
+		mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
+
+		if (found == 2) {
+			break;
+		}
+
+		if (lock == &thread->sigpendinglock) {
+			break;
+		}
+
+		lock = &thread->sigpendinglock;
+		head = &thread->sigpending;
+	}
+
+	if (found == 2) {
+		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
+		terminate_mcexec(0, sig);
+		return 1;
+	}
+	else if (found == 1) {
+		ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
+		interrupt_syscall(thread, 0);
+		return 1;
+	}
+	return 0;
+}
+
+struct sig_pending *
+getsigpending(struct thread *thread, int delflag)
+{
+	struct list_head *head;
+	mcs_rwlock_lock_t *lock;
+	struct mcs_rwlock_node_irqsave mcs_rw_node;
+	struct sig_pending *next;
+	struct sig_pending *pending;
+	__sigset_t w;
+	__sigset_t x;
+	int sig;
+	struct k_sigaction *k;
+
+	w = thread->sigmask.__val[0];
+
+	lock = &thread->sigcommon->lock;
+	head = &thread->sigcommon->sigpending;
+	for (;;) {
+		if (delflag) {
+			mcs_rwlock_writer_lock(lock, &mcs_rw_node);
+		}
+		else {
+			mcs_rwlock_reader_lock(lock, &mcs_rw_node);
+		}
+
+		list_for_each_entry_safe(pending, next, head, list) {
+			for (x = pending->sigmask.__val[0], sig = 0; x;
+					sig++, x >>= 1) {
+			}
+			k = thread->sigcommon->action + sig - 1;
+			if (delflag ||
+			   (sig != SIGCHLD &&
+				sig != SIGURG &&
+				sig != SIGCONT) ||
+			   (k->sa.sa_handler != (void *)1 &&
+				k->sa.sa_handler != NULL)){
+				if (!(pending->sigmask.__val[0] & w)) {
+					if (delflag)
+						list_del(&pending->list);
+
+					if (delflag) {
+						mcs_rwlock_writer_unlock(
+							lock,
+							&mcs_rw_node);
+					}
+					else {
+						mcs_rwlock_reader_unlock(
+							lock,
+							&mcs_rw_node);
+					}
+					return pending;
+				}
+			}
+		}
+
+		if (delflag) {
+			mcs_rwlock_writer_unlock(lock, &mcs_rw_node);
+		}
+		else {
+			mcs_rwlock_reader_unlock(lock, &mcs_rw_node);
+		}
+
+		if (lock == &thread->sigpendinglock) {
+			return NULL;
+		}
+
+		lock = &thread->sigpendinglock;
+		head = &thread->sigpending;
+	}
+
+	return NULL;
+}
+
+struct sig_pending *
+hassigpending(struct thread *thread)
+{
+	if (list_empty(&thread->sigpending) &&
+		list_empty(&thread->sigcommon->sigpending)) {
+		return NULL;
+	}
+
+	return getsigpending(thread, 0);
+}
+
+void
+check_sig_pending(void)
+{
+	struct thread *thread;
+	struct cpu_local_var *v;
+
+	if (clv == NULL)
+		return;
+
+	v = get_this_cpu_local_var();
+repeat:
+	v->runq_irqstate = ihk_mc_spinlock_lock(&v->runq_lock);
+	list_for_each_entry(thread, &(v->runq), sched_list) {
+
+		if (thread == NULL || thread == &cpu_local_var(idle)) {
+			continue;
+		}
+
+		if (thread->in_syscall_offload == 0) {
+			continue;
+		}
+
+		if (thread->proc->group_exit_status & 0x0000000100000000L) {
+			continue;
+		}
+
+		if (check_sig_pending_thread(thread))
+			goto repeat;
+	}
+	ihk_mc_spinlock_unlock(&v->runq_lock, v->runq_irqstate);
+}
+
+static void
+__check_signal(unsigned long rc, void *regs0, int num, int irq_disabled)
+{
+	ihk_mc_user_context_t *regs = regs0;
+	struct thread *thread;
+	struct sig_pending *pending;
+	int irqstate;
+
+	if (clv == NULL) {
+		return;
+	}
+	thread = cpu_local_var(current);
+
+	if (thread == NULL || thread->proc->pid == 0) {
+		struct thread *t;
+
+		irqstate = cpu_disable_interrupt_save();
+		ihk_mc_spinlock_lock_noirq(&(cpu_local_var(runq_lock)));
+		list_for_each_entry(t, &(cpu_local_var(runq)), sched_list) {
+			if (t->proc->pid <= 0) {
+				continue;
+			}
+			if (t->status == PS_INTERRUPTIBLE &&
+			   hassigpending(t)) {
+				t->status = PS_RUNNING;
+				break;
+			}
+		}
+		ihk_mc_spinlock_unlock_noirq(&(cpu_local_var(runq_lock)));
+		cpu_restore_interrupt(irqstate);
+		goto out;
+	}
+
+	if (regs != NULL && !interrupt_from_user(regs)) {
+		goto out;
+	}
+
+	if (list_empty(&thread->sigpending) &&
+		list_empty(&thread->sigcommon->sigpending)) {
+		goto out;
+	}
+
+	for (;;) {
+		/* When this function called from check_signal_irq_disabled,
+		 * return with interrupt invalid.
+		 * This is to eliminate signal loss.
+		 */
+		if (irq_disabled == 1) {
+			irqstate = cpu_disable_interrupt_save();
+		}
+		pending = getsigpending(thread, 1);
+		if (!pending) {
+			dkprintf("check_signal,queue is empty\n");
+			goto out;
+		}
+		if (irq_disabled == 1) {
+			cpu_restore_interrupt(irqstate);
+		}
+		if (do_signal(rc, regs, thread, pending, num)) {
+			num = -1;
+		}
+	}
+
+out:
+	return;
+}
+
+void
+check_signal(unsigned long rc, void *regs0, int num)
+{
+	__check_signal(rc, regs0, num, 0);
+}
+
+void
+check_signal_irq_disabled(unsigned long rc, void *regs0, int num)
+{
+	__check_signal(rc, regs0, num, 1);
+}
+

scripts/mckernel.spec.in

@@ -23,6 +23,8 @@ Summary: IHK/McKernel
 License: GPLv2
 Source0: mckernel-%{version}.tar.gz
 
+Requires: systemd-libs numactl-libs libdwarf
+
 # kernel_module_package macro does not handle cross build...
 %if "%{?_host_cpu}" == "x86_64" && "%{?_target_cpu}" == "aarch64"
 %define cross_compile 1
@@ -34,7 +36,7 @@ Requires: kernel = %{krequires}
 Requires(post):   /usr/sbin/depmod
 Requires(postun): /usr/sbin/depmod
 %else
-BuildRequires: systemd-devel numactl-devel binutils-devel kernel-devel
+BuildRequires: systemd-devel numactl-devel binutils-devel kernel-devel libdwarf-devel
 # Friendly reminder of the fact that kernel-rpm-macros is no longer included in kernel-devel
 %if 0%{?rhel} >= 8
 BuildRequires: redhat-rpm-config kernel-rpm-macros elfutils-libelf-devel kmod
@@ -99,7 +101,6 @@ This package contains headers and libraries required for build apps using IHK/Mc
 %{_bindir}/eclair-dump-backtrace.exp
 %{_bindir}/mcinspect
 %{_bindir}/mcps
-/usr/lib/debug/usr/bin/mcinspect-%{version}-%{release}.%{_arch}.debug
 %{_bindir}/vmcore2mckdump
 %{_bindir}/mcstat
 %{_libdir}/libihk.so

test/issues/1377/C1377.sh

@@ -0,0 +1,56 @@
+#!/bin/sh
+USELTP=1
+USEOSTEST=0
+
+. ../../common.sh
+
+################################################################################
+if [ ! -f "$LTPBIN/dirtyc0w" ]; then
+	echo BAD environment: LTP is too old >&2
+	exit 1
+fi
+
+echo "*** C1377T01 start"
+ng=0
+ok=0
+tp=dirtyc0w
+for ((i=0; i<20; i++)); do
+	for ((j=0; j<50; j++)); do
+		sudo PATH=$PATH:$LTPBIN $MCEXEC $LTPBIN/$tp > $tp.txt 2>&1
+		wok=`grep PASS $tp.txt | wc -l`
+		wng=`grep FAIL $tp.txt | wc -l`
+		if [ $wng != 0 ]; then
+			echo -n '*'
+			ng=`expr $ng + 1`
+		elif [ $wok == 0 ]; then
+			echo -n '?'
+		else
+			echo -n '.'
+			ok=`expr $ok + 1`
+		fi
+	done
+	echo
+done
+
+if [ $ng != 0 ]; then
+	echo "*** C1377T01 FAILED ok: $ok, ng: $ng"
+else
+	echo "*** C1377T01 PASS ok: $ok"
+fi
+
+
+
+for i in wait02:02 wait401:03 waitpid01:04 waitpid02:05 waitpid04:06 \
+	 waitpid05:07 waitpid06:08 waitpid07:09 waitpid08:10 waitpid09:11 \
+	 waitpid10:12 waitpid11:13 waitpid12:14 waitpid13:15; do
+	tp=`echo $i|sed 's/:.*//'`
+	id=`echo $i|sed 's/.*://'`
+	sudo PATH=$PATH:$LTPBIN $MCEXEC $LTPBIN/$tp 2>&1 | tee $tp.txt
+	ok=`grep PASS $tp.txt | wc -l`
+	ng=`grep FAIL $tp.txt | wc -l`
+	if [ $ng = 0 ]; then
+		echo "*** C1377T$id: $tp PASS ($ok)"
+	else
+		echo "*** C1377T$id: $tp FAIL (ok=$ok ng=$ng)"
+	fi
+done

test/issues/1377/C1377_arm64.txt

@@ -0,0 +1,179 @@
+Script started on Tue 16 Jun 2020 02:42:48 PM JST
+[shirasawa@apollo04 1377]$ make test
+sh ./C1377.sh
+mcstop+release.sh ... done
+mcreboot.sh -c 2-31 -m 2G@0,2G@1 -O ... done
+*** C1377T01 start
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+*** C1377T01 PASS ok: 1000
+wait02      1  TPASS  :  wait(&status) returned 78343
+*** C1377T02: wait02 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+wait401.c:55: PASS: waitpid() returned correct pid 78457
+wait401.c:64: PASS: WIFEXITED() is set in status
+wait401.c:69: PASS: WEXITSTATUS() == 0
+
+Summary:
+passed   3
+failed   0
+skipped  0
+warnings 0
+*** C1377T03: wait401 PASS (3)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid01.c:51: PASS: waitpid() returned correct pid 78571
+waitpid01.c:60: PASS: WIFSIGNALED() set in status
+waitpid01.c:68: PASS: WTERMSIG() == SIGALRM
+
+Summary:
+passed   3
+failed   0
+skipped  0
+warnings 0
+*** C1377T04: waitpid01 PASS (3)
+waitpid02    1  TPASS  :  received expected pid
+waitpid02    2  TPASS  :  received expected signal
+waitpid02    3  TPASS  :  received expected exit value
+*** C1377T05: waitpid02 PASS (3)
+waitpid04    1  TPASS  :  condition 1 test passed
+waitpid04    2  TPASS  :  condition 2 test passed
+waitpid04    3  TPASS  :  condition 3 test passed
+*** C1377T06: waitpid04 PASS (3)
+waitpid05    1  TPASS  :  received expected pid.
+waitpid05    2  TPASS  :  received expected exit number.
+waitpid05    3  TPASS  :  received expected pid.
+waitpid05    4  TPASS  :  received expected exit number.
+waitpid05    5  TPASS  :  received expected pid.
+waitpid05    6  TPASS  :  received expected exit number.
+waitpid05    7  TPASS  :  received expected pid.
+waitpid05    8  TPASS  :  received expected exit number.
+waitpid05    9  TPASS  :  received expected pid.
+waitpid05   10  TPASS  :  received expected exit number.
+waitpid05   11  TPASS  :  received expected pid.
+waitpid05   12  TPASS  :  received expected exit number.
+waitpid05   13  TPASS  :  received expected pid.
+waitpid05   14  TPASS  :  received expected exit number.
+waitpid05   15  TPASS  :  received expected pid.
+waitpid05   16  TPASS  :  received expected exit number.
+waitpid05   17  TPASS  :  received expected pid.
+waitpid05   18  TPASS  :  received expected exit number.
+waitpid05   19  TPASS  :  received expected pid.
+waitpid05   20  TPASS  :  received expected exit number.
+waitpid05   21  TPASS  :  received expected pid.
+waitpid05   22  TPASS  :  received expected exit number.
+waitpid05   23  TPASS  :  received expected pid.
+waitpid05   24  TPASS  :  received expected exit number.
+*** C1377T07: waitpid05 PASS (24)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid06.c:54: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T08: waitpid06 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid07.c:59: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T09: waitpid07 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid_common.h:142: INFO: Sending SIGCONT to 80073
+waitpid_common.h:142: INFO: Sending SIGCONT to 80105
+waitpid_common.h:142: INFO: Sending SIGCONT to 80137
+waitpid_common.h:142: INFO: Sending SIGCONT to 80169
+waitpid_common.h:142: INFO: Sending SIGCONT to 80201
+waitpid_common.h:142: INFO: Sending SIGCONT to 80233
+waitpid_common.h:142: INFO: Sending SIGCONT to 80266
+waitpid_common.h:142: INFO: Sending SIGCONT to 80298
+waitpid08.c:62: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T10: waitpid08 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid09.c:83: PASS: waitpid(pid, WNOHANG) = 0 for a running child
+waitpid09.c:123: PASS: waitpid(pid, WNOHANG) = pid for an exited child
+waitpid09.c:143: PASS: waitpid(-1, 0) = -1 with ECHILD if no children
+waitpid09.c:162: PASS: waitpid(-1, WNOHANG) = -1 with ECHILD if no children
+
+Summary:
+passed   4
+failed   0
+skipped  0
+warnings 0
+*** C1377T11: waitpid09 PASS (4)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid10.c:62: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T12: waitpid10 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid11.c:60: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T13: waitpid11 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid12.c:70: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T14: waitpid12 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid_common.h:142: INFO: Sending SIGCONT to 85038
+waitpid_common.h:142: INFO: Sending SIGCONT to 85070
+waitpid_common.h:142: INFO: Sending SIGCONT to 85102
+waitpid_common.h:142: INFO: Sending SIGCONT to 85134
+waitpid_common.h:142: INFO: Sending SIGCONT to 84910
+waitpid_common.h:142: INFO: Sending SIGCONT to 84942
+waitpid_common.h:142: INFO: Sending SIGCONT to 84974
+waitpid_common.h:142: INFO: Sending SIGCONT to 85006
+waitpid13.c:70: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T15: waitpid13 PASS (1)
+[shirasawa@apollo04 1377]$ exit
+exit
+
+Script done on Tue 16 Jun 2020 03:02:48 PM JST

test/issues/1377/C1377_x86_64.txt

@@ -0,0 +1,179 @@
+Script started on Tue Jun 16 15:36:06 2020
+bash-4.2$ make test
+sh ./C1377.sh
+mcstop+release.sh ... done
+mcreboot.sh -c 1-7,9-15,17-23,25-31 -m 10G@0,10G@1 -r 1-7:0+9-15:8+17-23:16+25-31:24 ... done
+*** C1377T01 start
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+..................................................
+*** C1377T01 PASS ok: 1000
+wait02      1  TPASS  :  wait(&status) returned 32240
+*** C1377T02: wait02 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+wait401.c:55: PASS: waitpid() returned correct pid 32347
+wait401.c:64: PASS: WIFEXITED() is set in status
+wait401.c:69: PASS: WEXITSTATUS() == 0
+
+Summary:
+passed   3
+failed   0
+skipped  0
+warnings 0
+*** C1377T03: wait401 PASS (3)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid01.c:51: PASS: waitpid() returned correct pid 32454
+waitpid01.c:60: PASS: WIFSIGNALED() set in status
+waitpid01.c:68: PASS: WTERMSIG() == SIGALRM
+
+Summary:
+passed   3
+failed   0
+skipped  0
+warnings 0
+*** C1377T04: waitpid01 PASS (3)
+waitpid02    1  TPASS  :  received expected pid
+waitpid02    2  TPASS  :  received expected signal
+waitpid02    3  TPASS  :  received expected exit value
+*** C1377T05: waitpid02 PASS (3)
+waitpid04    1  TPASS  :  condition 1 test passed
+waitpid04    2  TPASS  :  condition 2 test passed
+waitpid04    3  TPASS  :  condition 3 test passed
+*** C1377T06: waitpid04 PASS (3)
+waitpid05    1  TPASS  :  received expected pid.
+waitpid05    2  TPASS  :  received expected exit number.
+waitpid05    3  TPASS  :  received expected pid.
+waitpid05    4  TPASS  :  received expected exit number.
+waitpid05    5  TPASS  :  received expected pid.
+waitpid05    6  TPASS  :  received expected exit number.
+waitpid05    7  TPASS  :  received expected pid.
+waitpid05    8  TPASS  :  received expected exit number.
+waitpid05    9  TPASS  :  received expected pid.
+waitpid05   10  TPASS  :  received expected exit number.
+waitpid05   11  TPASS  :  received expected pid.
+waitpid05   12  TPASS  :  received expected exit number.
+waitpid05   13  TPASS  :  received expected pid.
+waitpid05   14  TPASS  :  received expected exit number.
+waitpid05   15  TPASS  :  received expected pid.
+waitpid05   16  TPASS  :  received expected exit number.
+waitpid05   17  TPASS  :  received expected pid.
+waitpid05   18  TPASS  :  received expected exit number.
+waitpid05   19  TPASS  :  received expected pid.
+waitpid05   20  TPASS  :  received expected exit number.
+waitpid05   21  TPASS  :  received expected pid.
+waitpid05   22  TPASS  :  received expected exit number.
+waitpid05   23  TPASS  :  received expected pid.
+waitpid05   24  TPASS  :  received expected exit number.
+*** C1377T07: waitpid05 PASS (24)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid06.c:54: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T08: waitpid06 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid07.c:59: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T09: waitpid07 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid_common.h:142: INFO: Sending SIGCONT to 1524
+waitpid_common.h:142: INFO: Sending SIGCONT to 1554
+waitpid_common.h:142: INFO: Sending SIGCONT to 1584
+waitpid_common.h:142: INFO: Sending SIGCONT to 1614
+waitpid_common.h:142: INFO: Sending SIGCONT to 1644
+waitpid_common.h:142: INFO: Sending SIGCONT to 1674
+waitpid_common.h:142: INFO: Sending SIGCONT to 1704
+waitpid_common.h:142: INFO: Sending SIGCONT to 1734
+waitpid08.c:62: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T10: waitpid08 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid09.c:83: PASS: waitpid(pid, WNOHANG) = 0 for a running child
+waitpid09.c:123: PASS: waitpid(pid, WNOHANG) = pid for an exited child
+waitpid09.c:143: PASS: waitpid(-1, 0) = -1 with ECHILD if no children
+waitpid09.c:162: PASS: waitpid(-1, WNOHANG) = -1 with ECHILD if no children
+
+Summary:
+passed   4
+failed   0
+skipped  0
+warnings 0
+*** C1377T11: waitpid09 PASS (4)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid10.c:62: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T12: waitpid10 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid11.c:60: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T13: waitpid11 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid12.c:70: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T14: waitpid12 PASS (1)
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+waitpid_common.h:142: INFO: Sending SIGCONT to 6219
+waitpid_common.h:142: INFO: Sending SIGCONT to 6249
+waitpid_common.h:142: INFO: Sending SIGCONT to 6279
+waitpid_common.h:142: INFO: Sending SIGCONT to 6309
+waitpid_common.h:142: INFO: Sending SIGCONT to 6099
+waitpid_common.h:142: INFO: Sending SIGCONT to 6129
+waitpid_common.h:142: INFO: Sending SIGCONT to 6159
+waitpid_common.h:142: INFO: Sending SIGCONT to 6189
+waitpid13.c:70: PASS: Test PASSED
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1377T15: waitpid13 PASS (1)
+bash-4.2$ exit
+exit
+
+Script done on Tue Jun 16 15:55:52 2020

test/issues/1377/Makefile

@@ -0,0 +1,9 @@
+CC = gcc
+
+all::
+
+test:: all
+	sh ./C1377.sh
+
+clean::
+	rm -f $(TARGET) *.o

test/issues/1377/README

@@ -0,0 +1,38 @@
+【Issue#1377 動作確認】
+□ テスト内容
+1. Issue 指摘事項の再現確認
+   現象はタイミングに依存し、ARM64環境でdirtyc0wを繰り返し実行した際に、
+   数回〜数十回に１回程度発生する。
+   問題の発生はタイミングに依存するため、dirtyc0wを十分な回数繰り返し
+   実行し、問題が再発しないことを確認する。
+
+C1377T01 dirtyc0wを1000回連続実行し、全てPASSすることを確認
+
+2. LTP を用いて既存処理に影響しないことを確認
+   プロセスの終了ステータスを変更したため、修正が既存処理に影響しないことを
+   wait系システムコールのLTPを用いて確認する。
+C1377T02 wait02: waitの基本機能の確認
+C1377T03 wait401: wait4の基本機能の確認
+C1377T04 waitpid01: waitpidの基本機能の確認
+C1377T05 waitpid02: waitpidの基本機能の確認
+C1377T06 waitpid04: waitpidの基本機能の確認
+C1377T07 waitpid05: waitpidの基本機能の確認
+C1377T08 waitpid06: waitpidの基本機能の確認
+C1377T09 waitpid07: waitpidの基本機能の確認
+C1377T10 waitpid08: waitpidの基本機能の確認
+C1377T11 waitpid09: waitpidの基本機能の確認
+C1377T12 waitpid10: waitpidの基本機能の確認
+C1377T13 waitpid11: waitpidの基本機能の確認
+C1377T14 waitpid12: waitpidの基本機能の確認
+C1377T15 waitpid13: waitpidの基本機能の確認
+
+□ 実行手順
+$ make test
+
+McKernelのインストール先や LTP の配置場所は、$HOME/.mck_test_config を
+参照する。.mck_test_config は、McKernel をビルドした際に生成される
+mck_test_config.sample ファイルを $HOME にコピーし、適宜編集すること。
+
+□ 実行結果
+C1377_x86_64.txt(x86_64実行結果)、C1377_arm64.txt(arm64実行結果)参照。
+全ての項目が PASS していることを確認。

test/issues/1380/C1380.sh

@@ -0,0 +1,26 @@
+#/bin/sh
+
+USELTP=1
+USEOSTEST=0
+
+. ../../common.sh
+
+issue="1380"
+tid=01
+
+for tp in tgkill03 tgkill01 tkill01 tkill02
+do
+	tname=`printf "C${issue}T%02d" ${tid}`
+	echo "*** ${tname} start *******************************"
+	sudo $MCEXEC $LTPBIN/$tp 2>&1 | tee $tp.txt
+	ok=`grep PASS $tp.txt | wc -l`
+	ng=`grep FAIL $tp.txt | wc -l`
+	if [ $ng = 0 ]; then
+		echo "*** ${tname} PASSED ($ok)"
+	else
+		echo "*** ${tname} FAILED (ok=$ok ng=$ng)"
+	fi
+	let tid++
+	echo ""
+done
+

test/issues/1380/Makefile

@@ -0,0 +1,11 @@
+CFLAGS=-g
+LDFLAGS=
+
+TARGET=
+
+all: $(TARGET)
+
+test: all
+	./C1380.sh
+clean:
+	rm -f $(TARGET) *.o *.txt

test/issues/1380/README

@@ -0,0 +1,21 @@
+【Issue#1324 動作確認】
+□ テスト内容
+1. 以下のLTPを用いてIssueで報告された症状が発生しないことを確認
+  - tgkill03
+
+3. 以下のLTPを用いて既存機能に影響が無いことを確認
+  - tgkill01
+  - tkill01
+  - tkill02
+
+□ 実行手順
+$ make test
+
+McKernelのインストール先や、OSTEST, LTPの配置場所は、
+$HOME/.mck_test_config を参照している
+.mck_test_config は、McKernelをビルドした際に生成されるmck_test_config.sample ファイルを
+$HOMEにコピーし、適宜編集する
+
+□ 実行結果
+x86_64_result.log aarch64_result.log 参照。
+すべての項目をPASSしていることを確認。

test/issues/1380/aarch64_result.log

@@ -0,0 +1,37 @@
+*** C1380T01 start *******************************
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+tgkill03.c:92: PASS: Invalid tgid failed as expected: EINVAL
+tgkill03.c:92: PASS: Invalid tid failed as expected: EINVAL
+tgkill03.c:92: PASS: Invalid signal failed as expected: EINVAL
+tgkill03.c:92: PASS: Defunct tid failed as expected: ESRCH
+tgkill03.c:92: PASS: Defunct tgid failed as expected: ESRCH
+tgkill03.c:99: PASS: Valid tgkill call succeeded
+
+Summary:
+passed   6
+failed   0
+skipped  0
+warnings 0
+*** C1380T01 PASSED (6)
+
+*** C1380T02 start *******************************
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+tgkill01.c:99: PASS: SIGUSR1 delivered to correct threads
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1380T02 PASSED (1)
+
+*** C1380T03 start *******************************
+tkill01     1  TPASS  :  tkill call succeeded
+tkill01     2  TPASS  :  tkill call succeeded
+*** C1380T03 PASSED (2)
+
+*** C1380T04 start *******************************
+tkill02     1  TPASS  :  tkill(-1, SIGUSR1) failed as expected: TEST_ERRNO=EINVAL(22): Invalid argument
+tkill02     2  TPASS  :  tkill(29822, SIGUSR1) failed as expected: TEST_ERRNO=ESRCH(3): No such process
+*** C1380T04 PASSED (2)
+

test/issues/1380/x86_64_result.log

@@ -0,0 +1,37 @@
+*** C1380T01 start *******************************
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+tgkill03.c:92: PASS: Invalid tgid failed as expected: EINVAL
+tgkill03.c:92: PASS: Invalid tid failed as expected: EINVAL
+tgkill03.c:92: PASS: Invalid signal failed as expected: EINVAL
+tgkill03.c:92: PASS: Defunct tid failed as expected: ESRCH
+tgkill03.c:92: PASS: Defunct tgid failed as expected: ESRCH
+tgkill03.c:99: PASS: Valid tgkill call succeeded
+
+Summary:
+passed   6
+failed   0
+skipped  0
+warnings 0
+*** C1380T01 PASSED (6)
+
+*** C1380T02 start *******************************
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+tgkill01.c:99: PASS: SIGUSR1 delivered to correct threads
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1380T02 PASSED (1)
+
+*** C1380T03 start *******************************
+tkill01     1  TPASS  :  tkill call succeeded
+tkill01     2  TPASS  :  tkill call succeeded
+*** C1380T03 PASSED (2)
+
+*** C1380T04 start *******************************
+tkill02     1  TPASS  :  tkill(-1, SIGUSR1) failed as expected: TEST_ERRNO=EINVAL(22): Invalid argument
+tkill02     2  TPASS  :  tkill(32768, SIGUSR1) failed as expected: TEST_ERRNO=ESRCH(3): No such process
+*** C1380T04 PASSED (2)
+

test/issues/1389/C1389.sh

@@ -0,0 +1,43 @@
+#/bin/sh
+
+USELTP=1
+USEOSTEST=0
+
+BOOTPARAM="-c 1-7 -m 10G@0,10G@1 -O"
+. ../../common.sh
+
+issue="1389"
+tid=01
+
+for tsuf in "01" "02.sh"
+do
+	tname=`printf "C${issue}T%02d" ${tid}`
+	echo "*** ${tname} start *******************************"
+	${MCEXEC} ./C1389T${tsuf}
+
+	if [ $? -eq 0 ]; then
+		echo "*** ${tname} PASSED ******************************"
+	else
+		echo "*** ${tname} FAILED ******************************"
+	fi
+	let tid++
+	echo ""
+done
+
+for tp in "mtest01 -p80" "mtest01 -p80 -w" "mem01"
+do
+	tname=`printf "C${issue}T%02d" ${tid}`
+	echo "*** ${tname} start *******************************"
+echo ${tp}
+	sudo $MCEXEC $LTPBIN/$tp 2>&1 | tee ${tname}.txt
+	ok=`grep PASS ${tname}.txt | wc -l`
+	ng=`grep FAIL ${tname}.txt | wc -l`
+	if [ $ng = 0 ]; then
+		echo "*** ${tname} PASSED ($ok)"
+	else
+		echo "*** ${tname} FAILED (ok=$ok ng=$ng)"
+	fi
+	let tid++
+	echo ""
+done
+

test/issues/1389/C1389T01.c

@@ -0,0 +1,65 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+#include <sys/sysinfo.h>
+#include <errno.h>
+
+int main(void)
+{
+	struct sysinfo *info;
+	int ret = 0, rc = 0;
+	unsigned long assigned_mem = (20UL << 30);
+	unsigned long _totalram, _freeram;
+	unsigned int _mem_unit;
+
+	info = malloc(sizeof(struct sysinfo));
+	rc = sysinfo(info);
+	if (rc) {
+		perror("sysinfo fail: ");
+		ret = -1;
+		goto out;
+	}
+
+	_totalram = info->totalram;
+	_freeram = info->freeram;
+	_mem_unit = info->mem_unit;
+
+	// Check totalram
+	if (0.95 * assigned_mem < _totalram &&
+			_totalram < assigned_mem) {
+		printf("[OK] totalram: %ld\n", _totalram);
+	}
+	else {
+		printf("[NG] unexpected totalram: %ld\n", _totalram);
+		printf("  expected range: %ld - %ld\n",
+			(unsigned long)(0.95 * assigned_mem),
+			assigned_mem);
+		ret = -1;
+		goto out;
+	}
+
+	// Check freeram
+	if (0.95 * _totalram < _freeram &&
+			_freeram < _totalram) {
+		printf("[OK] freeram: %ld\n", _freeram);
+	}
+	else {
+		printf("[NG] unexpected freeram: %ld\n", _freeram);
+		ret = -1;
+		goto out;
+	}
+
+	// Check mem_unit
+	if (_mem_unit == 1) {
+		printf("[OK] mem_unit: %ld\n", _mem_unit);
+	}
+	else {
+		printf("[NG] unexpected mem_unit: %ld\n", _mem_unit);
+		ret = -1;
+		goto out;
+	}
+
+	free(info);
+out:
+	return ret;
+}

test/issues/1389/C1389T02.sh

@@ -0,0 +1,88 @@
+#!/bin/sh
+
+ASSIGNED_MEM=`echo '1024 * 1024 * 1024 * 20' | bc`
+cat /proc/meminfo > ./cur_meminfo.txt
+
+# Check MemTotal
+MemTotalTxt=`cat ./cur_meminfo.txt | grep MemTotal | awk '{print $(NF-1)}'`
+MemTotal=`echo "1024 * ${MemTotalTxt}" | bc`
+
+lower_limit=`echo "${ASSIGNED_MEM} * 0.95" | bc`
+lower_limit=${lower_limit%.*}
+upper_limit=${ASSIGNED_MEM}
+tgt=${MemTotal}
+
+if [ ${tgt} -ge ${lower_limit} -a ${tgt} -lt ${upper_limit} ]; then
+	echo "[OK] MemTotal: ${tgt}"
+else
+	echo "[NG] unexpected MemTotal: ${tgt}"
+	exit 1
+fi
+
+# Check MemFree
+MemFreeTxt=`cat ./cur_meminfo.txt | grep MemFree | awk '{print $(NF-1)}'`
+MemFree=`echo "1024 * ${MemFreeTxt}" | bc`
+
+lower_limit=`echo "${MemTotal} * 0.95" | bc`
+lower_limit=${lower_limit%.*}
+upper_limit=${MemTotal}
+tgt=${MemFree}
+
+if [ ${tgt} -ge ${lower_limit} -a ${tgt} -lt ${upper_limit} ]; then
+	echo "[OK] MemFree: ${tgt}"
+else
+	echo "[NG] unexpected MemFree: ${tgt}"
+	exit 1
+fi
+
+# Check SwapTotal
+SwapTotalTxt=`cat ./cur_meminfo.txt | grep SwapTotal | awk '{print $(NF-1)}'`
+SwapTotal=`echo "1024 * ${SwapTotalTxt}" | bc`
+
+tgt=${SwapTotal}
+
+if [ ${tgt} -eq 0 ]; then
+	echo "[OK] SwapTotal: ${tgt}"
+else
+	echo "[NG] unexpected SwapTotal: ${tgt}"
+	exit 1
+fi
+
+# Check SwapFree
+SwapFreeTxt=`cat ./cur_meminfo.txt | grep SwapFree | awk '{print $(NF-1)}'`
+SwapFree=`echo "1024 * ${SwapFreeTxt}" | bc`
+
+tgt=${SwapFree}
+
+if [ ${tgt} -eq 0 ]; then
+	echo "[OK] SwapFree: ${tgt}"
+else
+	echo "[NG] unexpected SwapFree: ${tgt}"
+	exit 1
+fi
+
+# Check CommitLimit
+CommitLimitTxt=`cat ./cur_meminfo.txt | grep CommitLimit | awk '{print $(NF-1)}'`
+CommitLimit=`echo "1024 * ${CommitLimitTxt}" | bc`
+
+tgt=${CommitLimit}
+
+if [ ${tgt} -eq ${MemFree} ]; then
+	echo "[OK] CommitLimit: ${tgt}"
+else
+	echo "[NG] unexpected CommitLimit: ${tgt}"
+	exit 1
+fi
+
+# Check Committed_AS
+Committed_ASTxt=`cat ./cur_meminfo.txt | grep Committed_AS | awk '{print $(NF-1)}'`
+Committed_AS=`echo "1024 * ${Committed_ASTxt}" | bc`
+
+tgt=${Committed_AS}
+
+if [ ${tgt} -eq $((${MemTotal} - ${MemFree})) ]; then
+	echo "[OK] Committed_AS: ${tgt}"
+else
+	echo "[NG] unexpected Committed_AS: ${tgt}"
+	exit 1
+fi

test/issues/1389/Makefile

@@ -0,0 +1,11 @@
+CFLAGS=-g
+LDFLAGS=
+
+TARGET=C1389T01
+
+all: $(TARGET)
+
+test: all
+	sh ./C1389.sh
+clean:
+	rm -f $(TARGET) *.o *.txt

test/issues/1389/README

@@ -0,0 +1,46 @@
+【Issue#1389 動作確認】
+□ テスト内容
+本Issueの対応で、sysinfo()と/proc/meminfo の下記項目においてMcKernelの情報を
+返すようにした。
+[sysinfo]
+  totalram : rusage_global の total_memory
+  freeram : rusage_global の total_memory - usage_memory
+  mem_unit : 常に1
+[/proc/meminfo]
+  MemTotal : rusage_global の total_memory
+  MemFree : rusage_global の total_memory - usage_memory
+  SwapTotal : 常に0
+  SwapFree : 常に0
+  CommitLimit : rusage_global の total_memory - usage_memory
+  Committed_AS : rusage_global の usage_memory
+
+1. 本Issueで対応したsysinfo() と /proc/meminfo の値が想定どおりとなっていることを確認
+McKernelへのメモリ割り当てを 10G@0,10G@1 とした状態で下記プログラムを実行
+C1389T01: sysinfo() で取得される値が下記のとおりであることを確認
+  totalram : 20GiB * 0.95 以上、20GiB 未満であること
+  freeram : totralram * 0.95 以上、totalram 未満であること
+  mem_unit : 1 であること
+C1389T02: /proc/meminfo から取得される値が下記のとおりであることを確認
+  MemTotal : 20GiB * 0.95 以上、20GiB 未満であること
+  MemFree : MemTotal * 0.95 以上、MemTotal 未満であること
+  SwapTotal : 0 であること
+  SwapFree : 0 であること
+  CommitLimit : MemFreeと同値であること
+  Committed_AS : MemTotal - MemFree と同値であること
+
+2. 本Issueで対応したsysinfo() の項目を利用する以下のLTPを実行し、PASSすることを確認
+  - mtest01 -p80
+  - mtest01 -p80 -w
+  - mem01
+
+□ 実行手順
+$ make test
+
+McKernelのインストール先や、OSTEST, LTPの配置場所は、
+$HOME/.mck_test_config を参照している
+.mck_test_config は、McKernelをビルドした際に生成されるmck_test_config.sample ファイルを
+$HOMEにコピーし、適宜編集する
+
+□ 実行結果
+x86_64_result.log aarch64_result.log 参照。
+すべての項目をPASSしていることを確認。

test/issues/1389/aarch64_result.log

@@ -0,0 +1,77 @@
+sh ./C1389.sh
+mcstop+release.sh ... done
+mcreboot.sh -c 1-7 -m 10G@0,10G@1 -O ... done
+*** C1389T01 start *******************************
+[OK] totalram: 21472215040
+[OK] freeram: 21461794816
+[OK] mem_unit: 1
+*** C1389T01 PASSED ******************************
+
+*** C1389T02 start *******************************
+[OK] MemTotal: 21472215040
+[OK] MemFree: 21452750848
+[OK] SwapTotal: 0
+[OK] SwapFree: 0
+[OK] CommitLimit: 21452750848
+[OK] Committed_AS: 19464192
+*** C1389T02 PASSED ******************************
+
+*** C1389T03 start *******************************
+mtest01 -p80
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+mtest01.c:134: INFO: Filling up 80% of free ram which is 16760729 kbytes
+mtest01.c:149: INFO: ... child 50935 starting
+mtest01.c:149: INFO: ... child 50944 starting
+mtest01.c:149: INFO: ... child 50953 starting
+mtest01.c:149: INFO: ... child 50962 starting
+mtest01.c:149: INFO: ... child 50971 starting
+mtest01.c:149: INFO: ... child 50980 starting
+mtest01.c:169: INFO: ... [t=300] 1434451968 bytes allocated only in child 50980
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 50935
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 50944
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 50953
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 50962
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 50971
+mtest01.c:221: PASS: 16760729 kbytes allocated
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1389T03 PASSED (1)
+
+*** C1389T04 start *******************************
+mtest01 -p80 -w
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+mtest01.c:134: INFO: Filling up 80% of free ram which is 16759654 kbytes
+mtest01.c:149: INFO: ... child 51017 starting
+mtest01.c:149: INFO: ... child 51026 starting
+mtest01.c:149: INFO: ... child 51035 starting
+mtest01.c:149: INFO: ... child 51044 starting
+mtest01.c:149: INFO: ... child 51053 starting
+mtest01.c:149: INFO: ... child 51062 starting
+mtest01.c:166: INFO: ... [t=300] 1433403392 bytes allocated and used in child 51062
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 51017
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 51026
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 51035
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 51044
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 51053
+mtest01.c:221: PASS: 16759654 kbytes allocated (and written to)
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1389T04 PASSED (1)
+
+*** C1389T05 start *******************************
+mem01
+mem01       0  TINFO  :  Free Mem:      20465 Mb
+mem01       0  TINFO  :  Free Swap:     0 Mb
+mem01       0  TINFO  :  Total Free:    20465 Mb
+mem01       0  TINFO  :  Total Tested:  3056 Mb
+mem01       0  TINFO  :  touching 3056MB of malloc'ed memory (linear)
+mem01       1  TPASS  :  malloc - alloc of 3056MB succeeded
+*** C1389T05 PASSED (1)

test/issues/1389/x86_64_result.log

@@ -0,0 +1,77 @@
+sh ./C1389.sh
+mcstop+release.sh ... done
+mcreboot.sh -c 1-7 -m 10G@0,10G@1 -O ... done
+*** C1389T01 start *******************************
+[OK] totalram: 21463240704
+[OK] freeram: 21459673088
+[OK] mem_unit: 1
+*** C1389T01 PASSED ******************************
+
+*** C1389T02 start *******************************
+[OK] MemTotal: 21463240704
+[OK] MemFree: 21453983744
+[OK] SwapTotal: 0
+[OK] SwapFree: 0
+[OK] CommitLimit: 21453983744
+[OK] Committed_AS: 9256960
+*** C1389T02 PASSED ******************************
+
+*** C1389T03 start *******************************
+mtest01 -p80
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+mtest01.c:134: INFO: Filling up 80% of free ram which is 16762396 kbytes
+mtest01.c:149: INFO: ... child 20718 starting
+mtest01.c:149: INFO: ... child 20727 starting
+mtest01.c:149: INFO: ... child 20736 starting
+mtest01.c:149: INFO: ... child 20745 starting
+mtest01.c:149: INFO: ... child 20754 starting
+mtest01.c:149: INFO: ... child 20763 starting
+mtest01.c:169: INFO: ... [t=300] 1436549120 bytes allocated only in child 20763
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 20718
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 20727
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 20736
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 20745
+mtest01.c:169: INFO: ... [t=299] 3145728000 bytes allocated only in child 20754
+mtest01.c:221: PASS: 16762396 kbytes allocated
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1389T03 PASSED (1)
+
+*** C1389T04 start *******************************
+mtest01 -p80 -w
+tst_test.c:1096: INFO: Timeout per run is 0h 05m 00s
+mtest01.c:134: INFO: Filling up 80% of free ram which is 16761132 kbytes
+mtest01.c:149: INFO: ... child 20802 starting
+mtest01.c:149: INFO: ... child 20811 starting
+mtest01.c:149: INFO: ... child 20820 starting
+mtest01.c:149: INFO: ... child 20829 starting
+mtest01.c:149: INFO: ... child 20838 starting
+mtest01.c:149: INFO: ... child 20847 starting
+mtest01.c:166: INFO: ... [t=300] 1435500544 bytes allocated and used in child 20847
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 20802
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 20811
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 20820
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 20829
+mtest01.c:166: INFO: ... [t=299] 3145728000 bytes allocated and used in child 20838
+mtest01.c:221: PASS: 16761132 kbytes allocated (and written to)
+
+Summary:
+passed   1
+failed   0
+skipped  0
+warnings 0
+*** C1389T04 PASSED (1)
+
+*** C1389T05 start *******************************
+mem01
+mem01       0  TINFO  :  Free Mem:      20463 Mb
+mem01       0  TINFO  :  Free Swap:     0 Mb
+mem01       0  TINFO  :  Total Free:    20463 Mb
+mem01       0  TINFO  :  Total Tested:  3056 Mb
+mem01       0  TINFO  :  touching 3056MB of malloc'ed memory (linear)
+mem01       1  TPASS  :  malloc - alloc of 3056MB succeeded
+*** C1389T05 PASSED (1)

test/issues/1399/C1399.sh

@@ -0,0 +1,41 @@
+#/bin/sh
+
+USELTP=1
+USEOSTEST=0
+
+. ../../common.sh
+
+issue="1399"
+tid=01
+
+for tno in 01
+do
+	tname=`printf "C${issue}T%02d" ${tid}`
+	echo "*** ${tname} start *******************************"
+	sudo ${MCEXEC} ./C1399T${tno}
+
+	if [ $? -eq 0 ]; then
+		echo "*** ${tname} PASSED ******************************"
+	else
+		echo "*** ${tname} FAILED ******************************"
+	fi
+	let tid++
+	echo ""
+done
+
+for tp in set_robust_list01 get_robust_list01
+do
+	tname=`printf "C${issue}T%02d" ${tid}`
+	echo "*** ${tname} start *******************************"
+	sudo $MCEXEC $LTPBIN/$tp 2>&1 | tee $tp.txt
+	ok=`grep PASS $tp.txt | wc -l`
+	ng=`grep FAIL $tp.txt | wc -l`
+	if [ $ng = 0 ]; then
+		echo "*** ${tname} PASSED ($ok)"
+	else
+		echo "*** ${tname} FAILED (ok=$ok ng=$ng)"
+	fi
+	let tid++
+	echo ""
+done
+

test/issues/1399/C1399T01.c

@@ -0,0 +1,36 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/futex.h>
+#include <syscall.h>
+#include <errno.h>
+
+int main(int argc, void *argv[])
+{
+	struct robust_list_head rlh;
+	size_t len = sizeof(struct robust_list_head);
+	int rc = 0, ret = 0;
+
+	errno = 0;
+	rc = syscall(__NR_set_robust_list, &rlh, len + 1);
+	if (rc == -1 && errno == EINVAL) {
+		printf("[OK] invalid len (1 greater than correct): EINVAL\n");
+	} else {
+		printf("[NG] invalid len (1 greater than correct): Succeed\n");
+		ret = -1;
+		goto out;
+	}
+
+	errno = 0;
+	rc = syscall(__NR_set_robust_list, &rlh, len - 1);
+	if (rc == -1 && errno == EINVAL) {
+		printf("[OK] invalid len (1 less than correct): EINVAL\n");
+	} else {
+		printf("[NG] invalid len (1 less than correct): Succeed\n");
+		ret = -1;
+		goto out;
+	}
+
+out:
+	return ret;
+}
+