/*

 * Copyright (c) 2017, 2019, Oracle and/or its affiliates. All rights reserved.

 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

 *

 * This code is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License version 2 only, as

 * published by the Free Software Foundation.

 *

 * This code is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

 * version 2 for more details (a copy is included in the LICENSE file that

 * accompanied this code).

 *

 * You should have received a copy of the GNU General Public License version

 * 2 along with this work; if not, write to the Free Software Foundation,

 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

 *

 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

 * or visit www.oracle.com if you need additional information or have any

 * questions.

 *

 */

#include <string.h>

#include <math.h>

#include <errno.h>

#include "utilities/globalDefinitions.hpp"

#include "memory/allocation.hpp"

#include "runtime/os.hpp"

#include "logging/log.hpp"

#include "osContainer_linux.hpp"

/*

 * PER_CPU_SHARES has been set to 1024 because CPU shares' quota

 * is commonly used in cloud frameworks like Kubernetes[1],

 * AWS[2] and Mesos[3] in a similar way. They spawn containers with

 * --cpu-shares option values scaled by PER_CPU_SHARES. Thus, we do

 * the inverse for determining the number of possible available

 * CPUs to the JVM inside a container. See JDK-8216366.

 *

 * [1] https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/#meaning-of-cpu

 *     In particular:

 *        When using Docker:

 *          The spec.containers[].resources.requests.cpu is converted to its core value, which is potentially

 *          fractional, and multiplied by 1024. The greater of this number or 2 is used as the value of the

 *          --cpu-shares flag in the docker run command.

 * [2] https://docs.aws.amazon.com/AmazonECS/latest/APIReference/API_ContainerDefinition.html

 * [3] https://github.com/apache/mesos/blob/3478e344fb77d931f6122980c6e94cd3913c441d/src/docker/docker.cpp#L648

 *     https://github.com/apache/mesos/blob/3478e344fb77d931f6122980c6e94cd3913c441d/src/slave/containerizer/mesos/isolators/cgroups/constants.hpp#L30

 */

#define PER_CPU_SHARES 1024

bool  OSContainer::_is_initialized   = false;

bool  OSContainer::_is_containerized = false;

julong _unlimited_memory;

class CgroupSubsystem: CHeapObj<mtInternal> {

 friend class OSContainer;

 private:

    /* mountinfo contents */

    char *_root;

    char *_mount_point;

    /* Constructed subsystem directory */

    char *_path;

 public:

    CgroupSubsystem(char *root, char *mountpoint) {

      _root = os::strdup(root);

      _mount_point = os::strdup(mountpoint);

      _path = NULL;

    }

    /*

     * Set directory to subsystem specific files based

     * on the contents of the mountinfo and cgroup files.

     */

    void set_subsystem_path(char *cgroup_path) {

      char buf[MAXPATHLEN+1];

      if (_root != NULL && cgroup_path != NULL) {

        if (strcmp(_root, "/") == 0) {

          int buflen;

          strncpy(buf, _mount_point, MAXPATHLEN);

          buf[MAXPATHLEN-1] = '\0';

          if (strcmp(cgroup_path,"/") != 0) {

            buflen = strlen(buf);

            if ((buflen + strlen(cgroup_path)) > (MAXPATHLEN-1)) {

              return;

            }

            strncat(buf, cgroup_path, MAXPATHLEN-buflen);

            buf[MAXPATHLEN-1] = '\0';

          }

          _path = os::strdup(buf);

        } else {

          if (strcmp(_root, cgroup_path) == 0) {

            strncpy(buf, _mount_point, MAXPATHLEN);

            buf[MAXPATHLEN-1] = '\0';

            _path = os::strdup(buf);

          } else {

            char *p = strstr(cgroup_path, _root);

            if (p != NULL && p == _root) {

              if (strlen(cgroup_path) > strlen(_root)) {

                int buflen;

                strncpy(buf, _mount_point, MAXPATHLEN);

                buf[MAXPATHLEN-1] = '\0';

                buflen = strlen(buf);

                if ((buflen + strlen(cgroup_path) - strlen(_root)) > (MAXPATHLEN-1)) {

                  return;

                }

                strncat(buf, cgroup_path + strlen(_root), MAXPATHLEN-buflen);

                buf[MAXPATHLEN-1] = '\0';

                _path = os::strdup(buf);

              }

            }

          }

        }

      }

    }

    char *subsystem_path() { return _path; }

};

CgroupSubsystem* cpuset = NULL;

CgroupSubsystem* cpu = NULL;

CgroupSubsystem* cpuacct = NULL;

typedef char * cptr;

PRAGMA_DIAG_PUSH

PRAGMA_FORMAT_NONLITERAL_IGNORED

                                              const char *filename,

                                              const char *scan_fmt,

                                              T returnval) {

  FILE *fp = NULL;

  char *p;

  char file[MAXPATHLEN+1];

  char buf[MAXPATHLEN+1];

  if (c == NULL) {

    return OSCONTAINER_ERROR;

  }

  if (c->subsystem_path() == NULL) {

    return OSCONTAINER_ERROR;

  }

  strncpy(file, c->subsystem_path(), MAXPATHLEN);

  file[MAXPATHLEN-1] = '\0';

  int filelen = strlen(file);

  if ((filelen + strlen(filename)) > (MAXPATHLEN-1)) {

    log_debug(os, container)("File path too long %s, %s", file, filename);

    return OSCONTAINER_ERROR;

  }

  strncat(file, filename, MAXPATHLEN-filelen);

  log_trace(os, container)("Path to %s is %s", filename, file);

  fp = fopen(file, "r");

  if (fp != NULL) {

        fclose(fp);

        return 0;

      } else {

        log_debug(os, container)("Type %s not found in file %s", scan_fmt, file);

      }

      log_debug(os, container)("Empty file %s", file);

    }

  } else {

    log_debug(os, container)("Open of file %s failed, %s", file, os::strerror(errno));

  }

  if (fp != NULL)

    fclose(fp);

  return OSCONTAINER_ERROR;

}

PRAGMA_DIAG_POP

#define GET_CONTAINER_INFO(return_type, subsystem, filename,              \

                           logstring, scan_fmt, variable)                 \

  return_type variable;                                                   \

{                                                                         \

  int err;                                                                \

  if (err != 0)                                                           \

    return (return_type) OSCONTAINER_ERROR;                               \

                                                                          \

  log_trace(os, container)(logstring, variable);                          \

}

#define GET_CONTAINER_INFO_CPTR(return_type, subsystem, filename,         \

                               logstring, scan_fmt, variable, bufsize)    \

  char variable[bufsize];                                                 \

{                                                                         \

  int err;                                                                \

  if (err != 0)                                                           \

    return (return_type) NULL;                                            \

                                                                          \

  log_trace(os, container)(logstring, variable);                          \

}

/* init

 *

 * Initialize the container support and determine if

 * we are running under cgroup control.

 */

void OSContainer::init() {

  FILE *mntinfo = NULL;

  FILE *cgroup = NULL;

  char buf[MAXPATHLEN+1];

  char tmproot[MAXPATHLEN+1];

  char tmpmount[MAXPATHLEN+1];

  char *p;

  jlong mem_limit;

  assert(!_is_initialized, "Initializing OSContainer more than once");

  _is_initialized = true;

  _is_containerized = false;

  _unlimited_memory = (LONG_MAX / os::vm_page_size()) * os::vm_page_size();

  log_trace(os, container)("OSContainer::init: Initializing Container Support");

  if (!UseContainerSupport) {

    log_trace(os, container)("Container Support not enabled");

    return;

  }

  /*

   * Find the cgroup mount point for memory and cpuset

   * by reading /proc/self/mountinfo

   *

   * Example for docker:

   * 219 214 0:29 /docker/7208cebd00fa5f2e342b1094f7bed87fa25661471a4637118e65f1c995be8a34 /sys/fs/cgroup/memory ro,nosuid,nodev,noexec,relatime - cgroup cgroup rw,memory

   *

   * Example for host:

   * 34 28 0:29 / /sys/fs/cgroup/memory rw,nosuid,nodev,noexec,relatime shared:16 - cgroup cgroup rw,memory

   */

  mntinfo = fopen("/proc/self/mountinfo", "r");

  if (mntinfo == NULL) {

      log_debug(os, container)("Can't open /proc/self/mountinfo, %s",

                               os::strerror(errno));

      return;

  }

  while ((p = fgets(buf, MAXPATHLEN, mntinfo)) != NULL) {

    char tmpcgroups[MAXPATHLEN+1];

    char *cptr = tmpcgroups;

    char *token;

    // mountinfo format is documented at https://www.kernel.org/doc/Documentation/filesystems/proc.txt

    if (sscanf(p, "%*d %*d %*d:%*d %s %s %*[^-]- cgroup %*s %s", tmproot, tmpmount, tmpcgroups) != 3) {

      continue;

    }

    while ((token = strsep(&cptr, ",")) != NULL) {

      if (strcmp(token, "memory") == 0) {

      } else if (strcmp(token, "cpuset") == 0) {

        cpuset = new CgroupSubsystem(tmproot, tmpmount);

      } else if (strcmp(token, "cpu") == 0) {

        cpu = new CgroupSubsystem(tmproot, tmpmount);

      } else if (strcmp(token, "cpuacct") == 0) {

        cpuacct= new CgroupSubsystem(tmproot, tmpmount);

      }

    }

  }

  fclose(mntinfo);

  if (memory == NULL) {

    log_debug(os, container)("Required cgroup memory subsystem not found");

    return;

  }

  if (cpuset == NULL) {

    log_debug(os, container)("Required cgroup cpuset subsystem not found");

    return;

  }

  if (cpu == NULL) {

    log_debug(os, container)("Required cgroup cpu subsystem not found");

    return;

  }

  if (cpuacct == NULL) {

    log_debug(os, container)("Required cgroup cpuacct subsystem not found");

    return;

  }

  /*

   * Read /proc/self/cgroup and map host mount point to

   * local one via /proc/self/mountinfo content above

   *

   * Docker example:

   * 5:memory:/docker/6558aed8fc662b194323ceab5b964f69cf36b3e8af877a14b80256e93aecb044

   *

   * Host example:

   * 5:memory:/user.slice

   *

   * Construct a path to the process specific memory and cpuset

   * cgroup directory.

   *

   * For a container running under Docker from memory example above

   * the paths would be:

   *

   * /sys/fs/cgroup/memory

   *

   * For a Host from memory example above the path would be:

   *

   * /sys/fs/cgroup/memory/user.slice

   *

   */

  cgroup = fopen("/proc/self/cgroup", "r");

  if (cgroup == NULL) {

    log_debug(os, container)("Can't open /proc/self/cgroup, %s",

                             os::strerror(errno));

    return;

  }

  while ((p = fgets(buf, MAXPATHLEN, cgroup)) != NULL) {

    char *controllers;

    char *token;

    char *base;

    /* Skip cgroup number */

    strsep(&p, ":");

    /* Get controllers and base */

    controllers = strsep(&p, ":");

    base = strsep(&p, "\n");

    if (controllers == NULL) {

      continue;

    }

    while ((token = strsep(&controllers, ",")) != NULL) {

      if (strcmp(token, "memory") == 0) {

        memory->set_subsystem_path(base);

      } else if (strcmp(token, "cpuset") == 0) {

        cpuset->set_subsystem_path(base);

      } else if (strcmp(token, "cpu") == 0) {

        cpu->set_subsystem_path(base);

      } else if (strcmp(token, "cpuacct") == 0) {

        cpuacct->set_subsystem_path(base);

      }

    }

  }

  fclose(cgroup);

  // We need to update the amount of physical memory now that

  // command line arguments have been processed.

  if ((mem_limit = memory_limit_in_bytes()) > 0) {

    os::Linux::set_physical_memory(mem_limit);

  }

  _is_containerized = true;

}

const char * OSContainer::container_type() {

  if (is_containerized()) {

    return "cgroupv1";

  } else {

    return NULL;

  }

}

/* memory_limit_in_bytes

 *

 * Return the limit of available memory for this process.

 *

 * return:

 *    memory limit in bytes or

 *    -1 for unlimited

 *    OSCONTAINER_ERROR for not supported

 */

jlong OSContainer::memory_limit_in_bytes() {

  GET_CONTAINER_INFO(julong, memory, "/memory.limit_in_bytes",

                     "Memory Limit is: " JULONG_FORMAT, JULONG_FORMAT, memlimit);

  if (memlimit >= _unlimited_memory) {

    return (jlong)-1;

  }

  else {

    return (jlong)memlimit;

  }

}

jlong OSContainer::memory_and_swap_limit_in_bytes() {

  GET_CONTAINER_INFO(julong, memory, "/memory.memsw.limit_in_bytes",

                     "Memory and Swap Limit is: " JULONG_FORMAT, JULONG_FORMAT, memswlimit);

  if (memswlimit >= _unlimited_memory) {

    return (jlong)-1;

  } else {

    return (jlong)memswlimit;

  }

}

jlong OSContainer::memory_soft_limit_in_bytes() {