linux/block/blk-cgroup.c

378 lines
9.8 KiB
C
Raw Normal View History

/*
* Common Block IO controller cgroup interface
*
* Based on ideas and code from CFQ, CFS and BFQ:
* Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
*
* Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
* Paolo Valente <paolo.valente@unimore.it>
*
* Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
* Nauman Rafique <nauman@google.com>
*/
#include <linux/ioprio.h>
#include <linux/seq_file.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/err.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include "blk-cgroup.h"
static DEFINE_SPINLOCK(blkio_list_lock);
static LIST_HEAD(blkio_list);
struct blkio_cgroup blkio_root_cgroup = { .weight = 2*BLKIO_WEIGHT_DEFAULT };
EXPORT_SYMBOL_GPL(blkio_root_cgroup);
static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,
struct cgroup *);
static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,
struct task_struct *, bool);
static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,
struct cgroup *, struct task_struct *, bool);
static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);
static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
struct cgroup_subsys blkio_subsys = {
.name = "blkio",
.create = blkiocg_create,
.can_attach = blkiocg_can_attach,
.attach = blkiocg_attach,
.destroy = blkiocg_destroy,
.populate = blkiocg_populate,
#ifdef CONFIG_BLK_CGROUP
/* note: blkio_subsys_id is otherwise defined in blk-cgroup.h */
.subsys_id = blkio_subsys_id,
#endif
.use_id = 1,
.module = THIS_MODULE,
};
EXPORT_SYMBOL_GPL(blkio_subsys);
struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
struct blkio_cgroup, css);
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
void blkiocg_update_blkio_group_stats(struct blkio_group *blkg,
unsigned long time, unsigned long sectors)
{
blkg->time += time;
blkg->sectors += sectors;
}
EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_stats);
void blkiocg_add_blkio_group(struct blkio_cgroup *blkcg,
struct blkio_group *blkg, void *key, dev_t dev)
{
unsigned long flags;
spin_lock_irqsave(&blkcg->lock, flags);
rcu_assign_pointer(blkg->key, key);
blkg->blkcg_id = css_id(&blkcg->css);
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
spin_unlock_irqrestore(&blkcg->lock, flags);
#ifdef CONFIG_DEBUG_BLK_CGROUP
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
#endif
blkg->dev = dev;
}
EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
static void __blkiocg_del_blkio_group(struct blkio_group *blkg)
{
hlist_del_init_rcu(&blkg->blkcg_node);
blkg->blkcg_id = 0;
}
/*
* returns 0 if blkio_group was still on cgroup list. Otherwise returns 1
* indicating that blk_group was unhashed by the time we got to it.
*/
int blkiocg_del_blkio_group(struct blkio_group *blkg)
{
struct blkio_cgroup *blkcg;
unsigned long flags;
struct cgroup_subsys_state *css;
int ret = 1;
rcu_read_lock();
css = css_lookup(&blkio_subsys, blkg->blkcg_id);
if (!css)
goto out;
blkcg = container_of(css, struct blkio_cgroup, css);
spin_lock_irqsave(&blkcg->lock, flags);
if (!hlist_unhashed(&blkg->blkcg_node)) {
__blkiocg_del_blkio_group(blkg);
ret = 0;
}
spin_unlock_irqrestore(&blkcg->lock, flags);
out:
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(blkiocg_del_blkio_group);
/* called under rcu_read_lock(). */
struct blkio_group *blkiocg_lookup_group(struct blkio_cgroup *blkcg, void *key)
{
struct blkio_group *blkg;
struct hlist_node *n;
void *__key;
hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
__key = blkg->key;
if (__key == key)
return blkg;
}
return NULL;
}
EXPORT_SYMBOL_GPL(blkiocg_lookup_group);
#define SHOW_FUNCTION(__VAR) \
static u64 blkiocg_##__VAR##_read(struct cgroup *cgroup, \
struct cftype *cftype) \
{ \
struct blkio_cgroup *blkcg; \
\
blkcg = cgroup_to_blkio_cgroup(cgroup); \
return (u64)blkcg->__VAR; \
}
SHOW_FUNCTION(weight);
#undef SHOW_FUNCTION
static int
blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
{
struct blkio_cgroup *blkcg;
struct blkio_group *blkg;
struct hlist_node *n;
struct blkio_policy_type *blkiop;
if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
return -EINVAL;
blkcg = cgroup_to_blkio_cgroup(cgroup);
blk-cgroup: Fix potential deadlock in blk-cgroup I triggered a lockdep warning as following. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.33-rc2 #1 ------------------------------------------------------- test_io_control/7357 is trying to acquire lock: (blkio_list_lock){+.+...}, at: [<c053a990>] blkiocg_weight_write+0x82/0x9e but task is already holding lock: (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&(&blkcg->lock)->rlock){......}: [<c04583b7>] validate_chain+0x8bc/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a [<c053a4e1>] blkiocg_add_blkio_group+0x1a/0x6d [<c053cac7>] cfq_get_queue+0x225/0x3de [<c053eec2>] cfq_set_request+0x217/0x42d [<c052c8a6>] elv_set_request+0x17/0x26 [<c0532a0f>] get_request+0x203/0x2c5 [<c0532ae9>] get_request_wait+0x18/0x10e [<c0533470>] __make_request+0x2ba/0x375 [<c0531985>] generic_make_request+0x28d/0x30f [<c0532da7>] submit_bio+0x8a/0x8f [<c04d827a>] submit_bh+0xf0/0x10f [<c04d91d2>] ll_rw_block+0xc0/0xf9 [<f86e9705>] ext3_find_entry+0x319/0x544 [ext3] [<f86eae58>] ext3_lookup+0x2c/0xb9 [ext3] [<c04c3e1b>] do_lookup+0xd3/0x172 [<c04c56c8>] link_path_walk+0x5fb/0x95c [<c04c5a65>] path_walk+0x3c/0x81 [<c04c5b63>] do_path_lookup+0x21/0x8a [<c04c66cc>] do_filp_open+0xf0/0x978 [<c04c0c7e>] open_exec+0x1b/0xb7 [<c04c1436>] do_execve+0xbb/0x266 [<c04081a9>] sys_execve+0x24/0x4a [<c04028a2>] ptregs_execve+0x12/0x18 -> #1 (&(&q->__queue_lock)->rlock){..-.-.}: [<c04583b7>] validate_chain+0x8bc/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a [<c053dd2a>] cfq_unlink_blkio_group+0x17/0x41 [<c053a6eb>] blkiocg_destroy+0x72/0xc7 [<c0467df0>] cgroup_diput+0x4a/0xb2 [<c04ca473>] dentry_iput+0x93/0xb7 [<c04ca4b3>] d_kill+0x1c/0x36 [<c04cb5c5>] dput+0xf5/0xfe [<c04c6084>] do_rmdir+0x95/0xbe [<c04c60ec>] sys_rmdir+0x10/0x12 [<c04027cc>] sysenter_do_call+0x12/0x32 -> #0 (blkio_list_lock){+.+...}: [<c0458117>] validate_chain+0x61c/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c06929fd>] _raw_spin_lock+0x1e/0x4e [<c053a990>] blkiocg_weight_write+0x82/0x9e [<c0467f1e>] cgroup_file_write+0xc6/0x1c0 [<c04bd2f3>] vfs_write+0x8c/0x116 [<c04bd7c6>] sys_write+0x3b/0x60 [<c04027cc>] sysenter_do_call+0x12/0x32 other info that might help us debug this: 1 lock held by test_io_control/7357: #0: (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e stack backtrace: Pid: 7357, comm: test_io_control Not tainted 2.6.33-rc2 #1 Call Trace: [<c045754f>] print_circular_bug+0x91/0x9d [<c0458117>] validate_chain+0x61c/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c053a990>] ? blkiocg_weight_write+0x82/0x9e [<c06929fd>] _raw_spin_lock+0x1e/0x4e [<c053a990>] ? blkiocg_weight_write+0x82/0x9e [<c053a990>] blkiocg_weight_write+0x82/0x9e [<c0467f1e>] cgroup_file_write+0xc6/0x1c0 [<c0454df5>] ? trace_hardirqs_off+0xb/0xd [<c044d93a>] ? cpu_clock+0x2e/0x44 [<c050e6ec>] ? security_file_permission+0xf/0x11 [<c04bcdda>] ? rw_verify_area+0x8a/0xad [<c0467e58>] ? cgroup_file_write+0x0/0x1c0 [<c04bd2f3>] vfs_write+0x8c/0x116 [<c04bd7c6>] sys_write+0x3b/0x60 [<c04027cc>] sysenter_do_call+0x12/0x32 To prevent deadlock, we should take locks as following sequence: blkio_list_lock -> queue_lock -> blkcg_lock. The following patch should fix this bug. Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-02-01 08:58:54 +00:00
spin_lock(&blkio_list_lock);
spin_lock_irq(&blkcg->lock);
blkcg->weight = (unsigned int)val;
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
list_for_each_entry(blkiop, &blkio_list, list)
blkiop->ops.blkio_update_group_weight_fn(blkg,
blkcg->weight);
}
spin_unlock_irq(&blkcg->lock);
blk-cgroup: Fix potential deadlock in blk-cgroup I triggered a lockdep warning as following. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.33-rc2 #1 ------------------------------------------------------- test_io_control/7357 is trying to acquire lock: (blkio_list_lock){+.+...}, at: [<c053a990>] blkiocg_weight_write+0x82/0x9e but task is already holding lock: (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&(&blkcg->lock)->rlock){......}: [<c04583b7>] validate_chain+0x8bc/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a [<c053a4e1>] blkiocg_add_blkio_group+0x1a/0x6d [<c053cac7>] cfq_get_queue+0x225/0x3de [<c053eec2>] cfq_set_request+0x217/0x42d [<c052c8a6>] elv_set_request+0x17/0x26 [<c0532a0f>] get_request+0x203/0x2c5 [<c0532ae9>] get_request_wait+0x18/0x10e [<c0533470>] __make_request+0x2ba/0x375 [<c0531985>] generic_make_request+0x28d/0x30f [<c0532da7>] submit_bio+0x8a/0x8f [<c04d827a>] submit_bh+0xf0/0x10f [<c04d91d2>] ll_rw_block+0xc0/0xf9 [<f86e9705>] ext3_find_entry+0x319/0x544 [ext3] [<f86eae58>] ext3_lookup+0x2c/0xb9 [ext3] [<c04c3e1b>] do_lookup+0xd3/0x172 [<c04c56c8>] link_path_walk+0x5fb/0x95c [<c04c5a65>] path_walk+0x3c/0x81 [<c04c5b63>] do_path_lookup+0x21/0x8a [<c04c66cc>] do_filp_open+0xf0/0x978 [<c04c0c7e>] open_exec+0x1b/0xb7 [<c04c1436>] do_execve+0xbb/0x266 [<c04081a9>] sys_execve+0x24/0x4a [<c04028a2>] ptregs_execve+0x12/0x18 -> #1 (&(&q->__queue_lock)->rlock){..-.-.}: [<c04583b7>] validate_chain+0x8bc/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c0692b0a>] _raw_spin_lock_irqsave+0x27/0x5a [<c053dd2a>] cfq_unlink_blkio_group+0x17/0x41 [<c053a6eb>] blkiocg_destroy+0x72/0xc7 [<c0467df0>] cgroup_diput+0x4a/0xb2 [<c04ca473>] dentry_iput+0x93/0xb7 [<c04ca4b3>] d_kill+0x1c/0x36 [<c04cb5c5>] dput+0xf5/0xfe [<c04c6084>] do_rmdir+0x95/0xbe [<c04c60ec>] sys_rmdir+0x10/0x12 [<c04027cc>] sysenter_do_call+0x12/0x32 -> #0 (blkio_list_lock){+.+...}: [<c0458117>] validate_chain+0x61c/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c06929fd>] _raw_spin_lock+0x1e/0x4e [<c053a990>] blkiocg_weight_write+0x82/0x9e [<c0467f1e>] cgroup_file_write+0xc6/0x1c0 [<c04bd2f3>] vfs_write+0x8c/0x116 [<c04bd7c6>] sys_write+0x3b/0x60 [<c04027cc>] sysenter_do_call+0x12/0x32 other info that might help us debug this: 1 lock held by test_io_control/7357: #0: (&(&blkcg->lock)->rlock){......}, at: [<c053a949>] blkiocg_weight_write+0x3b/0x9e stack backtrace: Pid: 7357, comm: test_io_control Not tainted 2.6.33-rc2 #1 Call Trace: [<c045754f>] print_circular_bug+0x91/0x9d [<c0458117>] validate_chain+0x61c/0xb9c [<c0458dba>] __lock_acquire+0x723/0x789 [<c0458eb0>] lock_acquire+0x90/0xa7 [<c053a990>] ? blkiocg_weight_write+0x82/0x9e [<c06929fd>] _raw_spin_lock+0x1e/0x4e [<c053a990>] ? blkiocg_weight_write+0x82/0x9e [<c053a990>] blkiocg_weight_write+0x82/0x9e [<c0467f1e>] cgroup_file_write+0xc6/0x1c0 [<c0454df5>] ? trace_hardirqs_off+0xb/0xd [<c044d93a>] ? cpu_clock+0x2e/0x44 [<c050e6ec>] ? security_file_permission+0xf/0x11 [<c04bcdda>] ? rw_verify_area+0x8a/0xad [<c0467e58>] ? cgroup_file_write+0x0/0x1c0 [<c04bd2f3>] vfs_write+0x8c/0x116 [<c04bd7c6>] sys_write+0x3b/0x60 [<c04027cc>] sysenter_do_call+0x12/0x32 To prevent deadlock, we should take locks as following sequence: blkio_list_lock -> queue_lock -> blkcg_lock. The following patch should fix this bug. Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-02-01 08:58:54 +00:00
spin_unlock(&blkio_list_lock);
return 0;
}
#define SHOW_FUNCTION_PER_GROUP(__VAR) \
static int blkiocg_##__VAR##_read(struct cgroup *cgroup, \
struct cftype *cftype, struct seq_file *m) \
{ \
struct blkio_cgroup *blkcg; \
struct blkio_group *blkg; \
struct hlist_node *n; \
\
if (!cgroup_lock_live_group(cgroup)) \
return -ENODEV; \
\
blkcg = cgroup_to_blkio_cgroup(cgroup); \
rcu_read_lock(); \
hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {\
if (blkg->dev) \
seq_printf(m, "%u:%u %lu\n", MAJOR(blkg->dev), \
MINOR(blkg->dev), blkg->__VAR); \
} \
rcu_read_unlock(); \
cgroup_unlock(); \
return 0; \
}
SHOW_FUNCTION_PER_GROUP(time);
SHOW_FUNCTION_PER_GROUP(sectors);
#ifdef CONFIG_DEBUG_BLK_CGROUP
SHOW_FUNCTION_PER_GROUP(dequeue);
#endif
#undef SHOW_FUNCTION_PER_GROUP
#ifdef CONFIG_DEBUG_BLK_CGROUP
void blkiocg_update_blkio_group_dequeue_stats(struct blkio_group *blkg,
unsigned long dequeue)
{
blkg->dequeue += dequeue;
}
EXPORT_SYMBOL_GPL(blkiocg_update_blkio_group_dequeue_stats);
#endif
struct cftype blkio_files[] = {
{
.name = "weight",
.read_u64 = blkiocg_weight_read,
.write_u64 = blkiocg_weight_write,
},
{
.name = "time",
.read_seq_string = blkiocg_time_read,
},
{
.name = "sectors",
.read_seq_string = blkiocg_sectors_read,
},
#ifdef CONFIG_DEBUG_BLK_CGROUP
{
.name = "dequeue",
.read_seq_string = blkiocg_dequeue_read,
},
#endif
};
static int blkiocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
return cgroup_add_files(cgroup, subsys, blkio_files,
ARRAY_SIZE(blkio_files));
}
static void blkiocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
unsigned long flags;
struct blkio_group *blkg;
void *key;
struct blkio_policy_type *blkiop;
rcu_read_lock();
remove_entry:
spin_lock_irqsave(&blkcg->lock, flags);
if (hlist_empty(&blkcg->blkg_list)) {
spin_unlock_irqrestore(&blkcg->lock, flags);
goto done;
}
blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
blkcg_node);
key = rcu_dereference(blkg->key);
__blkiocg_del_blkio_group(blkg);
spin_unlock_irqrestore(&blkcg->lock, flags);
/*
* This blkio_group is being unlinked as associated cgroup is going
* away. Let all the IO controlling policies know about this event.
*
* Currently this is static call to one io controlling policy. Once
* we have more policies in place, we need some dynamic registration
* of callback function.
*/
spin_lock(&blkio_list_lock);
list_for_each_entry(blkiop, &blkio_list, list)
blkiop->ops.blkio_unlink_group_fn(key, blkg);
spin_unlock(&blkio_list_lock);
goto remove_entry;
done:
free_css_id(&blkio_subsys, &blkcg->css);
rcu_read_unlock();
if (blkcg != &blkio_root_cgroup)
kfree(blkcg);
}
static struct cgroup_subsys_state *
blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
struct blkio_cgroup *blkcg, *parent_blkcg;
if (!cgroup->parent) {
blkcg = &blkio_root_cgroup;
goto done;
}
/* Currently we do not support hierarchy deeper than two level (0,1) */
parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
if (css_depth(&parent_blkcg->css) > 0)
return ERR_PTR(-EINVAL);
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
if (!blkcg)
return ERR_PTR(-ENOMEM);
blkcg->weight = BLKIO_WEIGHT_DEFAULT;
done:
spin_lock_init(&blkcg->lock);
INIT_HLIST_HEAD(&blkcg->blkg_list);
return &blkcg->css;
}
/*
* We cannot support shared io contexts, as we have no mean to support
* two tasks with the same ioc in two different groups without major rework
* of the main cic data structures. For now we allow a task to change
* its cgroup only if it's the only owner of its ioc.
*/
static int blkiocg_can_attach(struct cgroup_subsys *subsys,
struct cgroup *cgroup, struct task_struct *tsk,
bool threadgroup)
{
struct io_context *ioc;
int ret = 0;
/* task_lock() is needed to avoid races with exit_io_context() */
task_lock(tsk);
ioc = tsk->io_context;
if (ioc && atomic_read(&ioc->nr_tasks) > 1)
ret = -EINVAL;
task_unlock(tsk);
return ret;
}
static void blkiocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
struct cgroup *prev, struct task_struct *tsk,
bool threadgroup)
{
struct io_context *ioc;
task_lock(tsk);
ioc = tsk->io_context;
if (ioc)
ioc->cgroup_changed = 1;
task_unlock(tsk);
}
void blkio_policy_register(struct blkio_policy_type *blkiop)
{
spin_lock(&blkio_list_lock);
list_add_tail(&blkiop->list, &blkio_list);
spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_register);
void blkio_policy_unregister(struct blkio_policy_type *blkiop)
{
spin_lock(&blkio_list_lock);
list_del_init(&blkiop->list);
spin_unlock(&blkio_list_lock);
}
EXPORT_SYMBOL_GPL(blkio_policy_unregister);
static int __init init_cgroup_blkio(void)
{
return cgroup_load_subsys(&blkio_subsys);
}
static void __exit exit_cgroup_blkio(void)
{
cgroup_unload_subsys(&blkio_subsys);
}
module_init(init_cgroup_blkio);
module_exit(exit_cgroup_blkio);
MODULE_LICENSE("GPL");