diff options
Diffstat (limited to 'init')
-rw-r--r-- | init/Kconfig | 122 | ||||
-rw-r--r-- | init/Makefile | 4 | ||||
-rw-r--r-- | init/do_mounts.c | 1 | ||||
-rw-r--r-- | init/do_mounts.h | 10 | ||||
-rw-r--r-- | init/do_mounts_dm.c | 426 | ||||
-rw-r--r-- | init/initramfs.c | 19 | ||||
-rw-r--r-- | init/noinitramfs.c | 9 |
7 files changed, 586 insertions, 5 deletions
diff --git a/init/Kconfig b/init/Kconfig index 34407f15e6d3..2e15b932aeea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -400,6 +400,15 @@ config IRQ_TIME_ACCOUNTING If in doubt, say N here. +config SCHED_WALT + bool "Support window based load tracking" + depends on SMP + help + This feature will allow the scheduler to maintain a tunable window + based set of metrics for tasks and runqueues. These metrics can be + used to guide task placement as well as task frequency requirements + for cpufreq governors. + config BSD_PROCESS_ACCT bool "BSD Process Accounting" depends on MULTIUSER @@ -971,6 +980,82 @@ menuconfig CGROUPS if CGROUPS +config CGROUP_DEBUG + bool "Example debug cgroup subsystem" + default n + help + This option enables a simple cgroup subsystem that + exports useful debugging information about the cgroups + framework. + + Say N if unsure. + +config CGROUP_FREEZER + bool "Freezer cgroup subsystem" + help + Provides a way to freeze and unfreeze all tasks in a + cgroup. + +config CGROUP_PIDS + bool "PIDs cgroup subsystem" + help + Provides enforcement of process number limits in the scope of a + cgroup. Any attempt to fork more processes than is allowed in the + cgroup will fail. PIDs are fundamentally a global resource because it + is fairly trivial to reach PID exhaustion before you reach even a + conservative kmemcg limit. As a result, it is possible to grind a + system to halt without being limited by other cgroup policies. The + PIDs cgroup subsystem is designed to stop this from happening. + + It should be noted that organisational operations (such as attaching + to a cgroup hierarchy will *not* be blocked by the PIDs subsystem), + since the PIDs limit only affects a process's ability to fork, not to + attach to a cgroup. + +config CGROUP_DEVICE + bool "Device controller for cgroups" + help + Provides a cgroup implementing whitelists for devices which + a process in the cgroup can mknod or open. + +config CPUSETS + bool "Cpuset support" + help + This option will let you create and manage CPUSETs which + allow dynamically partitioning a system into sets of CPUs and + Memory Nodes and assigning tasks to run only within those sets. + This is primarily useful on large SMP or NUMA systems. + + Say N if unsure. + +config PROC_PID_CPUSET + bool "Include legacy /proc/<pid>/cpuset file" + depends on CPUSETS + default y + +config CGROUP_CPUACCT + bool "Simple CPU accounting cgroup subsystem" + help + Provides a simple Resource Controller for monitoring the + total CPU consumed by the tasks in a cgroup. + +config CGROUP_SCHEDTUNE + bool "CFS tasks boosting cgroup subsystem (EXPERIMENTAL)" + depends on SCHED_TUNE + help + This option provides the "schedtune" controller which improves the + flexibility of the task boosting mechanism by introducing the support + to define "per task" boost values. + + This new controller: + 1. allows only a two layers hierarchy, where the root defines the + system-wide boost value and its direct childrens define each one a + different "class of tasks" to be boosted with a different value + 2. supports up to 16 different task classes, each one which could be + configured with a different boost value + + Say N if unsure. + config PAGE_COUNTER bool @@ -1248,6 +1333,43 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TUNE + bool "Boosting for CFS tasks (EXPERIMENTAL)" + depends on SMP + help + This option enables the system-wide support for task boosting. + When this support is enabled a new sysctl interface is exposed to + userspace via: + /proc/sys/kernel/sched_cfs_boost + which allows to set a system-wide boost value in range [0..100]. + + The currently boosting strategy is implemented in such a way that: + - a 0% boost value requires to operate in "standard" mode by + scheduling all tasks at the minimum capacities required by their + workload demand + - a 100% boost value requires to push at maximum the task + performances, "regardless" of the incurred energy consumption + + A boost value in between these two boundaries is used to bias the + power/performance trade-off, the higher the boost value the more the + scheduler is biased toward performance boosting instead of energy + efficiency. + + Since this support exposes a single system-wide knob, the specified + boost value is applied to all (CFS) tasks in the system. + + If unsure, say N. + +config DEFAULT_USE_ENERGY_AWARE + bool "Default to enabling the Energy Aware Scheduler feature" + default n + help + This option defaults the ENERGY_AWARE scheduling feature to true, + as without SCHED_DEBUG set this feature can't be enabled or disabled + via sysctl. + + Say N if unsure. + config SYSFS_DEPRECATED bool "Enable deprecated sysfs features to support old userspace tools" depends on SYSFS diff --git a/init/Makefile b/init/Makefile index c4fb45525d08..d210b235c5d7 100644 --- a/init/Makefile +++ b/init/Makefile @@ -5,11 +5,8 @@ ccflags-y := -fno-function-sections -fno-data-sections obj-y := main.o version.o mounts.o -ifneq ($(CONFIG_BLK_DEV_INITRD),y) obj-y += noinitramfs.o -else obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o -endif obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o ifneq ($(CONFIG_ARCH_INIT_TASK),y) @@ -20,6 +17,7 @@ mounts-y := do_mounts.o mounts-$(CONFIG_BLK_DEV_RAM) += do_mounts_rd.o mounts-$(CONFIG_BLK_DEV_INITRD) += do_mounts_initrd.o mounts-$(CONFIG_BLK_DEV_MD) += do_mounts_md.o +mounts-$(CONFIG_BLK_DEV_DM) += do_mounts_dm.o # dependencies on generated files need to be listed explicitly $(obj)/version.o: include/generated/compile.h diff --git a/init/do_mounts.c b/init/do_mounts.c index dea5de95c2dd..1902a1c80831 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -566,6 +566,7 @@ void __init prepare_namespace(void) wait_for_device_probe(); md_run_setup(); + dm_run_setup(); if (saved_root_name[0]) { root_device_name = saved_root_name; diff --git a/init/do_mounts.h b/init/do_mounts.h index 067af1d9e8b6..ecb275782c03 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -74,3 +74,13 @@ void md_run_setup(void); static inline void md_run_setup(void) {} #endif + +#ifdef CONFIG_BLK_DEV_DM + +void dm_run_setup(void); + +#else + +static inline void dm_run_setup(void) {} + +#endif diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c new file mode 100644 index 000000000000..a557c5ee00a7 --- /dev/null +++ b/init/do_mounts_dm.c @@ -0,0 +1,426 @@ +/* do_mounts_dm.c + * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@chromium.org> + * All Rights Reserved. + * Based on do_mounts_md.c + * + * This file is released under the GPL. + */ +#include <linux/device-mapper.h> +#include <linux/fs.h> +#include <linux/string.h> + +#include "do_mounts.h" +#include "../drivers/md/dm.h" + +#define DM_MAX_NAME 32 +#define DM_MAX_UUID 129 +#define DM_NO_UUID "none" + +#define DM_MSG_PREFIX "init" + +/* Separators used for parsing the dm= argument. */ +#define DM_FIELD_SEP ' ' +#define DM_LINE_SEP ',' + +/* + * When the device-mapper and any targets are compiled into the kernel + * (not a module), one target may be created and used as the root device at + * boot time with the parameters given with the boot line dm=... + * The code for that is here. + */ + +struct dm_setup_target { + sector_t begin; + sector_t length; + char *type; + char *params; + /* simple singly linked list */ + struct dm_setup_target *next; +}; + +static struct { + int minor; + int ro; + char name[DM_MAX_NAME]; + char uuid[DM_MAX_UUID]; + char *targets; + struct dm_setup_target *target; + int target_count; +} dm_setup_args __initdata; + +static __initdata int dm_early_setup; + +static size_t __init get_dm_option(char *str, char **next, char sep) +{ + size_t len = 0; + char *endp = NULL; + + if (!str) + return 0; + + endp = strchr(str, sep); + if (!endp) { /* act like strchrnul */ + len = strlen(str); + endp = str + len; + } else { + len = endp - str; + } + + if (endp == str) + return 0; + + if (!next) + return len; + + if (*endp == 0) { + /* Don't advance past the nul. */ + *next = endp; + } else { + *next = endp + 1; + } + return len; +} + +static int __init dm_setup_args_init(void) +{ + dm_setup_args.minor = 0; + dm_setup_args.ro = 0; + dm_setup_args.target = NULL; + dm_setup_args.target_count = 0; + return 0; +} + +static int __init dm_setup_cleanup(void) +{ + struct dm_setup_target *target = dm_setup_args.target; + struct dm_setup_target *old_target = NULL; + while (target) { + kfree(target->type); + kfree(target->params); + old_target = target; + target = target->next; + kfree(old_target); + dm_setup_args.target_count--; + } + BUG_ON(dm_setup_args.target_count); + return 0; +} + +static char * __init dm_setup_parse_device_args(char *str) +{ + char *next = NULL; + size_t len = 0; + + /* Grab the logical name of the device to be exported to udev */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device name"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.name)); + strlcpy(dm_setup_args.name, str, len); /* includes nul */ + str = skip_spaces(next); + + /* Grab the UUID value or "none" */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device uuid"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.uuid)); + strlcpy(dm_setup_args.uuid, str, len); + str = skip_spaces(next); + + /* Determine if the table/device will be read only or read-write */ + if (!strncmp("ro,", str, 3)) { + dm_setup_args.ro = 1; + } else if (!strncmp("rw,", str, 3)) { + dm_setup_args.ro = 0; + } else { + DMERR("failed to parse table mode"); + goto parse_fail; + } + str = skip_spaces(str + 3); + + return str; + +parse_fail: + return NULL; +} + +static void __init dm_substitute_devices(char *str, size_t str_len) +{ + char *candidate = str; + char *candidate_end = str; + char old_char; + size_t len = 0; + dev_t dev; + + if (str_len < 3) + return; + + while (str && *str) { + candidate = strchr(str, '/'); + if (!candidate) + break; + + /* Avoid embedded slashes */ + if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) { + str = strchr(candidate, DM_FIELD_SEP); + continue; + } + + len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP); + str = skip_spaces(candidate_end); + if (len < 3 || len > 37) /* name_to_dev_t max; maj:mix min */ + continue; + + /* Temporarily terminate with a nul */ + if (*candidate_end) + candidate_end--; + old_char = *candidate_end; + *candidate_end = '\0'; + + DMDEBUG("converting candidate device '%s' to dev_t", candidate); + /* Use the boot-time specific device naming */ + dev = name_to_dev_t(candidate); + *candidate_end = old_char; + + DMDEBUG(" -> %u", dev); + /* No suitable replacement found */ + if (!dev) + continue; + + /* Rewrite the /dev/path as a major:minor */ + len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev)); + if (!len) { + DMERR("error substituting device major/minor."); + break; + } + candidate += len; + /* Pad out with spaces (fixing our nul) */ + while (candidate < candidate_end) + *(candidate++) = DM_FIELD_SEP; + } +} + +static int __init dm_setup_parse_targets(char *str) +{ + char *next = NULL; + size_t len = 0; + struct dm_setup_target **target = NULL; + + /* Targets are defined as per the table format but with a + * comma as a newline separator. */ + target = &dm_setup_args.target; + while (str && *str) { + *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL); + if (!*target) { + DMERR("failed to allocate memory for target %d", + dm_setup_args.target_count); + goto parse_fail; + } + dm_setup_args.target_count++; + + (*target)->begin = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse starting sector for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + (*target)->length = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse length for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len || + !((*target)->type = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse type for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + len = get_dm_option(str, &next, DM_LINE_SEP); + if (!len || + !((*target)->params = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse params for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + /* Before moving on, walk through the copied target and + * attempt to replace all /dev/xxx with the major:minor number. + * It may not be possible to resolve them traditionally at + * boot-time. */ + dm_substitute_devices((*target)->params, len); + + target = &((*target)->next); + } + DMDEBUG("parsed %d targets", dm_setup_args.target_count); + + return 0; + +parse_fail: + return 1; +} + +/* + * Parse the command-line parameters given our kernel, but do not + * actually try to invoke the DM device now; that is handled by + * dm_setup_drive after the low-level disk drivers have initialised. + * dm format is as follows: + * dm="name uuid fmode,[table line 1],[table line 2],..." + * May be used with root=/dev/dm-0 as it always uses the first dm minor. + */ + +static int __init dm_setup(char *str) +{ + dm_setup_args_init(); + + str = dm_setup_parse_device_args(str); + if (!str) { + DMDEBUG("str is NULL"); + goto parse_fail; + } + + /* Target parsing is delayed until we have dynamic memory */ + dm_setup_args.targets = str; + + printk(KERN_INFO "dm: will configure '%s' on dm-%d\n", + dm_setup_args.name, dm_setup_args.minor); + + dm_early_setup = 1; + return 1; + +parse_fail: + printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n"); + return 0; +} + + +static void __init dm_setup_drive(void) +{ + struct mapped_device *md = NULL; + struct dm_table *table = NULL; + struct dm_setup_target *target; + char *uuid = dm_setup_args.uuid; + fmode_t fmode = FMODE_READ; + + /* Finish parsing the targets. */ + if (dm_setup_parse_targets(dm_setup_args.targets)) + goto parse_fail; + + if (dm_create(dm_setup_args.minor, &md)) { + DMDEBUG("failed to create the device"); + goto dm_create_fail; + } + DMDEBUG("created device '%s'", dm_device_name(md)); + + /* In addition to flagging the table below, the disk must be + * set explicitly ro/rw. */ + set_disk_ro(dm_disk(md), dm_setup_args.ro); + + if (!dm_setup_args.ro) + fmode |= FMODE_WRITE; + if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) { + DMDEBUG("failed to create the table"); + goto dm_table_create_fail; + } + + dm_lock_md_type(md); + target = dm_setup_args.target; + while (target) { + DMINFO("adding target '%llu %llu %s %s'", + (unsigned long long) target->begin, + (unsigned long long) target->length, target->type, + target->params); + if (dm_table_add_target(table, target->type, target->begin, + target->length, target->params)) { + DMDEBUG("failed to add the target to the table"); + goto add_target_fail; + } + target = target->next; + } + + if (dm_table_complete(table)) { + DMDEBUG("failed to complete the table"); + goto table_complete_fail; + } + + if (dm_get_md_type(md) == DM_TYPE_NONE) { + dm_set_md_type(md, dm_table_get_type(table)); + if (dm_setup_md_queue(md, table)) { + DMWARN("unable to set up device queue for new table."); + goto setup_md_queue_fail; + } + } else if (dm_get_md_type(md) != dm_table_get_type(table)) { + DMWARN("can't change device type after initial table load."); + goto setup_md_queue_fail; + } + + /* Suspend the device so that we can bind it to the table. */ + if (dm_suspend(md, 0)) { + DMDEBUG("failed to suspend the device pre-bind"); + goto suspend_fail; + } + + /* Bind the table to the device. This is the only way to associate + * md->map with the table and set the disk capacity directly. */ + if (dm_swap_table(md, table)) { /* should return NULL. */ + DMDEBUG("failed to bind the device to the table"); + goto table_bind_fail; + } + + /* Finally, resume and the device should be ready. */ + if (dm_resume(md)) { + DMDEBUG("failed to resume the device"); + goto resume_fail; + } + + /* Export the dm device via the ioctl interface */ + if (!strcmp(DM_NO_UUID, dm_setup_args.uuid)) + uuid = NULL; + if (dm_ioctl_export(md, dm_setup_args.name, uuid)) { + DMDEBUG("failed to export device with given name and uuid"); + goto export_fail; + } + printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor); + + dm_unlock_md_type(md); + dm_setup_cleanup(); + return; + +export_fail: +resume_fail: +table_bind_fail: +suspend_fail: +setup_md_queue_fail: +table_complete_fail: +add_target_fail: + dm_unlock_md_type(md); +dm_table_create_fail: + dm_put(md); +dm_create_fail: + dm_setup_cleanup(); +parse_fail: + printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n", + dm_setup_args.minor, dm_setup_args.name); +} + +__setup("dm=", dm_setup); + +void __init dm_run_setup(void) +{ + if (!dm_early_setup) + return; + printk(KERN_INFO "dm: attempting early device configuration.\n"); + dm_setup_drive(); +} diff --git a/init/initramfs.c b/init/initramfs.c index b32ad7d97ac9..f8ce812ba43e 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -18,6 +18,7 @@ #include <linux/dirent.h> #include <linux/syscalls.h> #include <linux/utime.h> +#include <linux/initramfs.h> static ssize_t __init xwrite(int fd, const char *p, size_t count) { @@ -605,9 +606,25 @@ static void __init clean_rootfs(void) } #endif +static int __initdata do_skip_initramfs; + +static int __init skip_initramfs_param(char *str) +{ + if (*str) + return 0; + do_skip_initramfs = 1; + return 1; +} +__setup("skip_initramfs", skip_initramfs_param); + static int __init populate_rootfs(void) { - char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); + char *err; + + if (do_skip_initramfs) + return default_rootfs(); + + err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) panic("%s", err); /* Failed to decompress INTERNAL initramfs */ if (initrd_start) { diff --git a/init/noinitramfs.c b/init/noinitramfs.c index 267739d85179..bcc8bcb053ee 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -21,11 +21,16 @@ #include <linux/stat.h> #include <linux/kdev_t.h> #include <linux/syscalls.h> +#include <linux/kconfig.h> +#include <linux/initramfs.h> /* * Create a simple rootfs that is similar to the default initramfs */ -static int __init default_rootfs(void) +#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD) +static +#endif +int __init default_rootfs(void) { int err; @@ -49,4 +54,6 @@ out: printk(KERN_WARNING "Failed to create a rootfs\n"); return err; } +#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD) rootfs_initcall(default_rootfs); +#endif |