summaryrefslogtreecommitdiff
path: root/init
diff options
context:
space:
mode:
Diffstat (limited to 'init')
-rw-r--r--init/Kconfig291
-rw-r--r--init/do_mounts.c2
-rw-r--r--init/do_mounts.h4
-rw-r--r--init/do_mounts_initrd.c12
-rw-r--r--init/do_mounts_rd.c7
-rw-r--r--init/main.c12
6 files changed, 149 insertions, 179 deletions
diff --git a/init/Kconfig b/init/Kconfig
index 6ce1eaf2b..ec251fadb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -34,18 +34,26 @@ config PCK_INTERACTIVE
help
Tunes the kernel for responsiveness at the cost of throughput and power usage.
- --- VM ---
+ --- Virtual Memory Subsystem ---------------------------
+
Mem dirty before bg writeback..: 10 % -> 20 %
Mem dirty before sync writeback: 20 % -> 50 %
- --- CPU Scheduler ---
+ --- Block Layer ----------------------------------------
+
+ NCQ Queue Depth................: 31 -> 8
+ Block Layer Queue Depth........: 128 -> 16
+
+ --- CPU Scheduler --------------------------------------
+
Scheduling latency.............: 6 -> 3 ms
Minimal granularity............: 0.75 -> 0.3 ms
Wakeup granularity.............: 1 -> 0.5 ms
CPU migration cost.............: 0.5 -> 0.25 ms
Bandwidth slice size...........: 5 -> 3 ms
- --- CPU Frequency Scaling ---
+ --- CPU Frequency Scaling ------------------------------
+
Ondemand down scaling factor...: 1 -> 10
config BROKEN
@@ -305,7 +313,7 @@ config FHANDLE
config USELIB
bool "uselib syscall"
- default y
+ def_bool ALPHA || M68K || SPARC || X86_32 || IA32_EMULATION
help
This option enables the uselib syscall, a system call used in the
dynamic linker from libc5 and earlier. glibc does not use this
@@ -319,20 +327,15 @@ config AUDIT
help
Enable auditing infrastructure that can be used with another
kernel subsystem, such as SELinux (which requires this for
- logging of avc messages output). Does not do system-call
- auditing without CONFIG_AUDITSYSCALL.
+ logging of avc messages output). System call auditing is included
+ on architectures which support it.
config HAVE_ARCH_AUDITSYSCALL
bool
config AUDITSYSCALL
- bool "Enable system-call auditing support"
+ def_bool y
depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
- default y if SECURITY_SELINUX
- help
- Enable low-overhead system-call auditing infrastructure that
- can be used independently or with another kernel subsystem,
- such as SELinux.
config AUDIT_WATCH
def_bool y
@@ -960,95 +963,24 @@ 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 PAGE_COUNTER
bool
config MEMCG
- bool "Memory Resource Controller for Control Groups"
+ bool "Memory controller"
select PAGE_COUNTER
select EVENTFD
help
- Provides a memory resource controller that manages both anonymous
- memory and page cache. (See Documentation/cgroups/memory.txt)
+ Provides control over the memory footprint of tasks in a cgroup.
config MEMCG_SWAP
- bool "Memory Resource Controller Swap Extension"
+ bool "Swap controller"
depends on MEMCG && SWAP
help
- Add swap management feature to memory resource controller. When you
- enable this, you can limit mem+swap usage per cgroup. In other words,
- when you disable this, memory resource controller has no cares to
- usage of swap...a process can exhaust all of the swap. This extension
- is useful when you want to avoid exhaustion swap but this itself
- adds more overheads and consumes memory for remembering information.
- Especially if you use 32bit system or small memory system, please
- be careful about enabling this. When memory resource controller
- is disabled by boot option, this will be automatically disabled and
- there will be no overhead from this. Even when you set this config=y,
- if boot option "swapaccount=0" is set, swap will not be accounted.
- Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
- size is 4096bytes, 512k per 1Gbytes of swap.
+ Provides control over the swap space consumed by tasks in a cgroup.
+
config MEMCG_SWAP_ENABLED
- bool "Memory Resource Controller Swap Extension enabled by default"
+ bool "Swap controller enabled by default"
depends on MEMCG_SWAP
default y
help
@@ -1060,46 +992,44 @@ config MEMCG_SWAP_ENABLED
For those who want to have the feature enabled by default should
select this option (if, for some reason, they need to disable it
then swapaccount=0 does the trick).
-config MEMCG_KMEM
- bool "Memory Resource Controller Kernel Memory accounting"
- depends on MEMCG
- depends on SLUB || SLAB
- help
- The Kernel Memory extension for Memory Resource Controller can limit
- the amount of memory used by kernel objects in the system. Those are
- fundamentally different from the entities handled by the standard
- Memory Controller, which are page-based, and can be swapped. Users of
- the kmem extension can use it to guarantee that no group of processes
- will ever exhaust kernel resources alone.
-config CGROUP_HUGETLB
- bool "HugeTLB Resource Controller for Control Groups"
- depends on HUGETLB_PAGE
- select PAGE_COUNTER
+config BLK_CGROUP
+ bool "IO controller"
+ depends on BLOCK
default n
- help
- Provides a cgroup Resource Controller for HugeTLB pages.
- When you enable this, you can put a per cgroup limit on HugeTLB usage.
- The limit is enforced during page fault. Since HugeTLB doesn't
- support page reclaim, enforcing the limit at page fault time implies
- that, the application will get SIGBUS signal if it tries to access
- HugeTLB pages beyond its limit. This requires the application to know
- beforehand how much HugeTLB pages it would require for its use. The
- control group is tracked in the third page lru pointer. This means
- that we cannot use the controller with huge page less than 3 pages.
+ ---help---
+ Generic block IO controller cgroup interface. This is the common
+ cgroup interface which should be used by various IO controlling
+ policies.
-config CGROUP_PERF
- bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
- depends on PERF_EVENTS && CGROUPS
- help
- This option extends the per-cpu mode to restrict monitoring to
- threads which belong to the cgroup specified and run on the
- designated cpu.
+ Currently, CFQ IO scheduler uses it to recognize task groups and
+ control disk bandwidth allocation (proportional time slice allocation)
+ to such task groups. It is also used by bio throttling logic in
+ block layer to implement upper limit in IO rates on a device.
- Say N if unsure.
+ This option only enables generic Block IO controller infrastructure.
+ One needs to also enable actual IO controlling logic/policy. For
+ enabling proportional weight division of disk bandwidth in CFQ, set
+ CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
+ CONFIG_BLK_DEV_THROTTLING=y.
+
+ See Documentation/cgroups/blkio-controller.txt for more information.
+
+config DEBUG_BLK_CGROUP
+ bool "IO controller debugging"
+ depends on BLK_CGROUP
+ default n
+ ---help---
+ Enable some debugging help. Currently it exports additional stat
+ files in a cgroup which can be useful for debugging.
+
+config CGROUP_WRITEBACK
+ bool
+ depends on MEMCG && BLK_CGROUP
+ default y
menuconfig CGROUP_SCHED
- bool "Group CPU scheduler"
+ bool "CPU controller"
default n
help
This feature lets CPU scheduler recognize task groups and control CPU
@@ -1136,41 +1066,95 @@ config RT_GROUP_SCHED
endif #CGROUP_SCHED
-config BLK_CGROUP
- bool "Block IO controller"
- depends on BLOCK
- default n
- ---help---
- Generic block IO controller cgroup interface. This is the common
- cgroup interface which should be used by various IO controlling
- policies.
+config CGROUP_PIDS
+ bool "PIDs controller"
+ 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.
- Currently, CFQ IO scheduler uses it to recognize task groups and
- control disk bandwidth allocation (proportional time slice allocation)
- to such task groups. It is also used by bio throttling logic in
- block layer to implement upper limit in IO rates on a device.
+ 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.
- This option only enables generic Block IO controller infrastructure.
- One needs to also enable actual IO controlling logic/policy. For
- enabling proportional weight division of disk bandwidth in CFQ, set
- CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
- CONFIG_BLK_DEV_THROTTLING=y.
+config CGROUP_FREEZER
+ bool "Freezer controller"
+ help
+ Provides a way to freeze and unfreeze all tasks in a
+ cgroup.
- See Documentation/cgroups/blkio-controller.txt for more information.
+ This option affects the ORIGINAL cgroup interface. The cgroup2 memory
+ controller includes important in-kernel memory consumers per default.
-config DEBUG_BLK_CGROUP
- bool "Enable Block IO controller debugging"
- depends on BLK_CGROUP
+ If you're using cgroup2, say N.
+
+config CGROUP_HUGETLB
+ bool "HugeTLB controller"
+ depends on HUGETLB_PAGE
+ select PAGE_COUNTER
default n
- ---help---
- Enable some debugging help. Currently it exports additional stat
- files in a cgroup which can be useful for debugging.
+ help
+ Provides a cgroup controller for HugeTLB pages.
+ When you enable this, you can put a per cgroup limit on HugeTLB usage.
+ The limit is enforced during page fault. Since HugeTLB doesn't
+ support page reclaim, enforcing the limit at page fault time implies
+ that, the application will get SIGBUS signal if it tries to access
+ HugeTLB pages beyond its limit. This requires the application to know
+ beforehand how much HugeTLB pages it would require for its use. The
+ control group is tracked in the third page lru pointer. This means
+ that we cannot use the controller with huge page less than 3 pages.
-config CGROUP_WRITEBACK
- bool
- depends on MEMCG && BLK_CGROUP
+config CPUSETS
+ bool "Cpuset controller"
+ 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_DEVICE
+ bool "Device controller"
+ help
+ Provides a cgroup controller implementing whitelists for
+ devices which a process in the cgroup can mknod or open.
+
+config CGROUP_CPUACCT
+ bool "Simple CPU accounting controller"
+ help
+ Provides a simple controller for monitoring the
+ total CPU consumed by the tasks in a cgroup.
+
+config CGROUP_PERF
+ bool "Perf controller"
+ depends on PERF_EVENTS
+ help
+ This option extends the perf per-cpu mode to restrict monitoring
+ to threads which belong to the cgroup specified and run on the
+ designated cpu.
+
+ Say N if unsure.
+
+config CGROUP_DEBUG
+ bool "Example controller"
+ default n
+ help
+ This option enables a simple controller that exports
+ debugging information about the cgroups framework.
+
+ Say N.
+
endif # CGROUPS
config CHECKPOINT_RESTORE
@@ -1220,10 +1204,9 @@ config USER_NS
to provide different user info for different servers.
When user namespaces are enabled in the kernel it is
- recommended that the MEMCG and MEMCG_KMEM options also be
- enabled and that user-space use the memory control groups to
- limit the amount of memory a memory unprivileged users can
- use.
+ recommended that the MEMCG option also be enabled and that
+ user-space use the memory control groups to limit the amount
+ of memory a memory unprivileged users can use.
If unsure, say N.
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 1fed72621..dea5de95c 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -597,8 +597,6 @@ void __init prepare_namespace(void)
if (is_floppy && rd_doload && rd_load_disk(0))
ROOT_DEV = Root_RAM0;
- check_resume_attempted();
-
mount_root();
out:
devtmpfs_mount("dev");
diff --git a/init/do_mounts.h b/init/do_mounts.h
index f5b978a9b..067af1d9e 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -57,11 +57,11 @@ static inline int rd_load_image(char *from) { return 0; }
#ifdef CONFIG_BLK_DEV_INITRD
-int __init initrd_load(void);
+bool __init initrd_load(void);
#else
-static inline int initrd_load(void) { return 0; }
+static inline bool initrd_load(void) { return false; }
#endif
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index a49c59680..a1000ca29 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -15,7 +15,6 @@
#include <linux/romfs_fs.h>
#include <linux/initrd.h>
#include <linux/sched.h>
-#include <linux/suspend.h>
#include <linux/freezer.h>
#include <linux/kmod.h>
@@ -80,11 +79,6 @@ static void __init handle_initrd(void)
current->flags &= ~PF_FREEZER_SKIP;
- if (!resume_attempted)
- printk(KERN_ERR "TuxOnIce: No attempt was made to resume from "
- "any image that might exist.\n");
- clear_toi_state(TOI_BOOT_TIME);
-
/* move initrd to rootfs' /old */
sys_mount("..", ".", NULL, MS_MOVE, NULL);
/* switch root and cwd back to / of rootfs */
@@ -122,7 +116,7 @@ static void __init handle_initrd(void)
}
}
-int __init initrd_load(void)
+bool __init initrd_load(void)
{
if (mount_initrd) {
create_dev("/dev/ram", Root_RAM0);
@@ -135,9 +129,9 @@ int __init initrd_load(void)
if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) {
sys_unlink("/initrd.image");
handle_initrd();
- return 1;
+ return true;
}
}
sys_unlink("/initrd.image");
- return 0;
+ return false;
}
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index e5d059e8a..8a09b32e0 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -216,13 +216,6 @@ int __init rd_load_image(char *from)
/*
* NOTE NOTE: nblocks is not actually blocks but
* the number of kibibytes of data to load into a ramdisk.
- * So any ramdisk block size that is a multiple of 1KiB should
- * work when the appropriate ramdisk_blocksize is specified
- * on the command line.
- *
- * The default ramdisk_blocksize is 1KiB and it is generally
- * silly to use anything else, so make sure to use 1KiB
- * blocksize while generating ext2fs ramdisk-images.
*/
if (sys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0)
rd_blocks = 0;
diff --git a/init/main.c b/init/main.c
index 9e64d7097..58c9e3747 100644
--- a/init/main.c
+++ b/init/main.c
@@ -164,10 +164,10 @@ static const char *panic_later, *panic_param;
extern const struct obs_kernel_param __setup_start[], __setup_end[];
-static int __init obsolete_checksetup(char *line)
+static bool __init obsolete_checksetup(char *line)
{
const struct obs_kernel_param *p;
- int had_early_param = 0;
+ bool had_early_param = false;
p = __setup_start;
do {
@@ -179,13 +179,13 @@ static int __init obsolete_checksetup(char *line)
* Keep iterating, as we can have early
* params and __setups of same names 8( */
if (line[n] == '\0' || line[n] == '=')
- had_early_param = 1;
+ had_early_param = true;
} else if (!p->setup_func) {
pr_warn("Parameter %s is obsolete, ignored\n",
p->str);
- return 1;
+ return true;
} else if (p->setup_func(line + n))
- return 1;
+ return true;
}
p++;
} while (p < __setup_end);
@@ -943,6 +943,8 @@ static int __ref kernel_init(void *unused)
flush_delayed_fput();
+ rcu_end_inkernel_boot();
+
if (ramdisk_execute_command) {
ret = run_init_process(ramdisk_execute_command);
if (!ret)