#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.h>
-#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directories start off with i_nlink == 2 (for "." entry) */
- inode->i_nlink++;
+ inc_nlink(inode);
} else {
return -ENOMEM;
}
*
*
* When reading/writing to a file:
- * - the cpuset to use in file->f_dentry->d_parent->d_fsdata
- * - the 'cftype' of the file is file->f_dentry->d_fsdata
+ * - the cpuset to use in file->f_path.dentry->d_parent->d_fsdata
+ * - the 'cftype' of the file is file->f_path.dentry->d_fsdata
*/
struct cftype {
}
/* Remaining checks don't apply to root cpuset */
- if ((par = cur->parent) == NULL)
+ if (cur == &top_cpuset)
return 0;
+ par = cur->parent;
+
/* We must be a subset of our parent cpuset */
if (!is_cpuset_subset(trial, par))
return -EACCES;
return -EACCES;
trialcs = *cs;
- retval = cpulist_parse(buf, trialcs.cpus_allowed);
- if (retval < 0)
- return retval;
+
+ /*
+ * We allow a cpuset's cpus_allowed to be empty; if it has attached
+ * tasks, we'll catch it later when we validate the change and return
+ * -ENOSPC.
+ */
+ if (!buf[0] || (buf[0] == '\n' && !buf[1])) {
+ cpus_clear(trialcs.cpus_allowed);
+ } else {
+ retval = cpulist_parse(buf, trialcs.cpus_allowed);
+ if (retval < 0)
+ return retval;
+ }
cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
- if (cpus_empty(trialcs.cpus_allowed))
+ /* cpus_allowed cannot be empty for a cpuset with attached tasks. */
+ if (atomic_read(&cs->count) && cpus_empty(trialcs.cpus_allowed))
return -ENOSPC;
retval = validate_change(cs, &trialcs);
if (retval < 0)
return -EACCES;
trialcs = *cs;
- retval = nodelist_parse(buf, trialcs.mems_allowed);
- if (retval < 0)
- goto done;
+
+ /*
+ * We allow a cpuset's mems_allowed to be empty; if it has attached
+ * tasks, we'll catch it later when we validate the change and return
+ * -ENOSPC.
+ */
+ if (!buf[0] || (buf[0] == '\n' && !buf[1])) {
+ nodes_clear(trialcs.mems_allowed);
+ } else {
+ retval = nodelist_parse(buf, trialcs.mems_allowed);
+ if (retval < 0)
+ goto done;
+ }
nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
oldmem = cs->mems_allowed;
if (nodes_equal(oldmem, trialcs.mems_allowed)) {
retval = 0; /* Too easy - nothing to do */
goto done;
}
- if (nodes_empty(trialcs.mems_allowed)) {
+ /* mems_allowed cannot be empty for a cpuset with attached tasks. */
+ if (atomic_read(&cs->count) && nodes_empty(trialcs.mems_allowed)) {
retval = -ENOSPC;
goto done;
}
cpu_exclusive_changed =
(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
mutex_lock(&callback_mutex);
- if (turning_on)
- set_bit(bit, &cs->flags);
- else
- clear_bit(bit, &cs->flags);
+ cs->flags = trialcs.flags;
mutex_unlock(&callback_mutex);
if (cpu_exclusive_changed)
task_lock(tsk);
oldcs = tsk->cpuset;
- if (!oldcs) {
+ /*
+ * After getting 'oldcs' cpuset ptr, be sure still not exiting.
+ * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
+ * then fail this attach_task(), to avoid breaking top_cpuset.count.
+ */
+ if (tsk->flags & PF_EXITING) {
task_unlock(tsk);
mutex_unlock(&callback_mutex);
put_task_struct(tsk);
FILE_TASKLIST,
} cpuset_filetype_t;
-static ssize_t cpuset_common_file_write(struct file *file, const char __user *userbuf,
+static ssize_t cpuset_common_file_write(struct file *file,
+ const char __user *userbuf,
size_t nbytes, loff_t *unused_ppos)
{
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
- struct cftype *cft = __d_cft(file->f_dentry);
+ struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
+ struct cftype *cft = __d_cft(file->f_path.dentry);
cpuset_filetype_t type = cft->private;
char *buffer;
char *pathbuf = NULL;
int retval = 0;
/* Crude upper limit on largest legitimate cpulist user might write. */
- if (nbytes > 100 + 6 * NR_CPUS)
+ if (nbytes > 100 + 6 * max(NR_CPUS, MAX_NUMNODES))
return -E2BIG;
/* +1 for nul-terminator */
size_t nbytes, loff_t *ppos)
{
ssize_t retval = 0;
- struct cftype *cft = __d_cft(file->f_dentry);
+ struct cftype *cft = __d_cft(file->f_path.dentry);
if (!cft)
return -ENODEV;
static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
size_t nbytes, loff_t *ppos)
{
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
+ struct cftype *cft = __d_cft(file->f_path.dentry);
+ struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
cpuset_filetype_t type = cft->private;
char *page;
ssize_t retval = 0;
loff_t *ppos)
{
ssize_t retval = 0;
- struct cftype *cft = __d_cft(file->f_dentry);
+ struct cftype *cft = __d_cft(file->f_path.dentry);
if (!cft)
return -ENODEV;
if (err)
return err;
- cft = __d_cft(file->f_dentry);
+ cft = __d_cft(file->f_path.dentry);
if (!cft)
return -ENODEV;
if (cft->open)
static int cpuset_file_release(struct inode *inode, struct file *file)
{
- struct cftype *cft = __d_cft(file->f_dentry);
+ struct cftype *cft = __d_cft(file->f_path.dentry);
if (cft->release)
return cft->release(inode, file);
return 0;
return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}
-static struct file_operations cpuset_file_operations = {
+static const struct file_operations cpuset_file_operations = {
.read = cpuset_file_read,
.write = cpuset_file_write,
.llseek = generic_file_llseek,
.release = cpuset_file_release,
};
-static struct inode_operations cpuset_dir_inode_operations = {
+static const struct inode_operations cpuset_dir_inode_operations = {
.lookup = simple_lookup,
.mkdir = cpuset_mkdir,
.rmdir = cpuset_rmdir,
inode->i_fop = &simple_dir_operations;
/* start off with i_nlink == 2 (for "." entry) */
- inode->i_nlink++;
+ inc_nlink(inode);
} else if (S_ISREG(mode)) {
inode->i_size = 0;
inode->i_fop = &cpuset_file_operations;
error = cpuset_create_file(dentry, S_IFDIR | mode);
if (!error) {
dentry->d_fsdata = cs;
- parent->d_inode->i_nlink++;
+ inc_nlink(parent->d_inode);
cs->dentry = dentry;
}
dput(dentry);
*/
static int cpuset_tasks_open(struct inode *unused, struct file *file)
{
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
+ struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
struct ctr_struct *ctr;
pid_t *pidarray;
int npids;
}
root = cpuset_mount->mnt_sb->s_root;
root->d_fsdata = &top_cpuset;
- root->d_inode->i_nlink++;
+ inc_nlink(root->d_inode);
top_cpuset.dentry = root;
root->d_inode->i_op = &cpuset_dir_inode_operations;
number_of_cpusets = 1;
}
/*
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets. If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes. Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes. It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
+ */
+
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+ struct cpuset *c;
+
+ /* Each of our child cpusets mems must be online */
+ list_for_each_entry(c, &cur->children, sibling) {
+ guarantee_online_cpus_mems_in_subtree(c);
+ if (!cpus_empty(c->cpus_allowed))
+ guarantee_online_cpus(c, &c->cpus_allowed);
+ if (!nodes_empty(c->mems_allowed))
+ guarantee_online_mems(c, &c->mems_allowed);
+ }
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map. Force the top cpuset to track
+ * whats online after any CPU or memory node hotplug or unplug event.
+ *
+ * To ensure that we don't remove a CPU or node from the top cpuset
+ * that is currently in use by a child cpuset (which would violate
+ * the rule that cpusets must be subsets of their parent), we first
+ * call the recursive routine guarantee_online_cpus_mems_in_subtree().
+ *
+ * Since there are two callers of this routine, one for CPU hotplug
+ * events and one for memory node hotplug events, we could have coded
+ * two separate routines here. We code it as a single common routine
+ * in order to minimize text size.
+ */
+
+static void common_cpu_mem_hotplug_unplug(void)
+{
+ mutex_lock(&manage_mutex);
+ mutex_lock(&callback_mutex);
+
+ guarantee_online_cpus_mems_in_subtree(&top_cpuset);
+ top_cpuset.cpus_allowed = cpu_online_map;
+ top_cpuset.mems_allowed = node_online_map;
+
+ mutex_unlock(&callback_mutex);
+ mutex_unlock(&manage_mutex);
+}
+
+/*
* The top_cpuset tracks what CPUs and Memory Nodes are online,
* period. This is necessary in order to make cpusets transparent
* (of no affect) on systems that are actively using CPU hotplug
* cpu_online_map on each CPU hotplug (cpuhp) event.
*/
-#ifdef CONFIG_HOTPLUG_CPU
static int cpuset_handle_cpuhp(struct notifier_block *nb,
unsigned long phase, void *cpu)
{
- mutex_lock(&manage_mutex);
- mutex_lock(&callback_mutex);
-
- top_cpuset.cpus_allowed = cpu_online_map;
-
- mutex_unlock(&callback_mutex);
- mutex_unlock(&manage_mutex);
-
+ common_cpu_mem_hotplug_unplug();
return 0;
}
-#endif
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Keep top_cpuset.mems_allowed tracking node_online_map.
* Call this routine anytime after you change node_online_map.
* See also the previous routine cpuset_handle_cpuhp().
*/
-#ifdef CONFIG_MEMORY_HOTPLUG
-void cpuset_track_online_nodes()
+void cpuset_track_online_nodes(void)
{
- mutex_lock(&manage_mutex);
- mutex_lock(&callback_mutex);
-
- top_cpuset.mems_allowed = node_online_map;
-
- mutex_unlock(&callback_mutex);
- mutex_unlock(&manage_mutex);
+ common_cpu_mem_hotplug_unplug();
}
#endif
* it is holding that mutex while calling check_for_release(),
* which calls kmalloc(), so can't be called holding callback_mutex().
*
- * We don't need to task_lock() this reference to tsk->cpuset,
- * because tsk is already marked PF_EXITING, so attach_task() won't
- * mess with it, or task is a failed fork, never visible to attach_task.
- *
* the_top_cpuset_hack:
*
* Set the exiting tasks cpuset to the root cpuset (top_cpuset).
{
struct cpuset *cs;
+ task_lock(current);
cs = tsk->cpuset;
tsk->cpuset = &top_cpuset; /* the_top_cpuset_hack - see above */
+ task_unlock(current);
if (notify_on_release(cs)) {
char *pathbuf = NULL;
}
/**
- * cpuset_zone_allowed - Can we allocate memory on zone z's memory node?
+ * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node?
* @z: is this zone on an allowed node?
- * @gfp_mask: memory allocation flags (we use __GFP_HARDWALL)
+ * @gfp_mask: memory allocation flags
*
- * If we're in interrupt, yes, we can always allocate. If zone
+ * If we're in interrupt, yes, we can always allocate. If
+ * __GFP_THISNODE is set, yes, we can always allocate. If zone
* z's node is in our tasks mems_allowed, yes. If it's not a
* __GFP_HARDWALL request and this zone's nodes is in the nearest
* mem_exclusive cpuset ancestor to this tasks cpuset, yes.
+ * If the task has been OOM killed and has access to memory reserves
+ * as specified by the TIF_MEMDIE flag, yes.
* Otherwise, no.
*
+ * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall()
+ * reduces to cpuset_zone_allowed_hardwall(). Otherwise,
+ * cpuset_zone_allowed_softwall() might sleep, and might allow a zone
+ * from an enclosing cpuset.
+ *
+ * cpuset_zone_allowed_hardwall() only handles the simpler case of
+ * hardwall cpusets, and never sleeps.
+ *
+ * The __GFP_THISNODE placement logic is really handled elsewhere,
+ * by forcibly using a zonelist starting at a specified node, and by
+ * (in get_page_from_freelist()) refusing to consider the zones for
+ * any node on the zonelist except the first. By the time any such
+ * calls get to this routine, we should just shut up and say 'yes'.
+ *
* GFP_USER allocations are marked with the __GFP_HARDWALL bit,
- * and do not allow allocations outside the current tasks cpuset.
+ * and do not allow allocations outside the current tasks cpuset
+ * unless the task has been OOM killed as is marked TIF_MEMDIE.
* GFP_KERNEL allocations are not so marked, so can escape to the
- * nearest mem_exclusive ancestor cpuset.
+ * nearest enclosing mem_exclusive ancestor cpuset.
*
- * Scanning up parent cpusets requires callback_mutex. The __alloc_pages()
- * routine only calls here with __GFP_HARDWALL bit _not_ set if
- * it's a GFP_KERNEL allocation, and all nodes in the current tasks
- * mems_allowed came up empty on the first pass over the zonelist.
- * So only GFP_KERNEL allocations, if all nodes in the cpuset are
- * short of memory, might require taking the callback_mutex mutex.
+ * Scanning up parent cpusets requires callback_mutex. The
+ * __alloc_pages() routine only calls here with __GFP_HARDWALL bit
+ * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the
+ * current tasks mems_allowed came up empty on the first pass over
+ * the zonelist. So only GFP_KERNEL allocations, if all nodes in the
+ * cpuset are short of memory, might require taking the callback_mutex
+ * mutex.
*
* The first call here from mm/page_alloc:get_page_from_freelist()
- * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, so
- * no allocation on a node outside the cpuset is allowed (unless in
- * interrupt, of course).
+ * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets,
+ * so no allocation on a node outside the cpuset is allowed (unless
+ * in interrupt, of course).
*
* The second pass through get_page_from_freelist() doesn't even call
* here for GFP_ATOMIC calls. For those calls, the __alloc_pages()
* affect that:
* in_interrupt - any node ok (current task context irrelevant)
* GFP_ATOMIC - any node ok
+ * TIF_MEMDIE - any node ok
* GFP_KERNEL - any node in enclosing mem_exclusive cpuset ok
* GFP_USER - only nodes in current tasks mems allowed ok.
*
* Rule:
- * Don't call cpuset_zone_allowed() if you can't sleep, unless you
+ * Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you
* pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
* the code that might scan up ancestor cpusets and sleep.
- **/
+ */
-int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
+int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
{
int node; /* node that zone z is on */
const struct cpuset *cs; /* current cpuset ancestors */
might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
if (node_isset(node, current->mems_allowed))
return 1;
+ /*
+ * Allow tasks that have access to memory reserves because they have
+ * been OOM killed to get memory anywhere.
+ */
+ if (unlikely(test_thread_flag(TIF_MEMDIE)))
+ return 1;
if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */
return 0;
return allowed;
}
+/*
+ * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node?
+ * @z: is this zone on an allowed node?
+ * @gfp_mask: memory allocation flags
+ *
+ * If we're in interrupt, yes, we can always allocate.
+ * If __GFP_THISNODE is set, yes, we can always allocate. If zone
+ * z's node is in our tasks mems_allowed, yes. If the task has been
+ * OOM killed and has access to memory reserves as specified by the
+ * TIF_MEMDIE flag, yes. Otherwise, no.
+ *
+ * The __GFP_THISNODE placement logic is really handled elsewhere,
+ * by forcibly using a zonelist starting at a specified node, and by
+ * (in get_page_from_freelist()) refusing to consider the zones for
+ * any node on the zonelist except the first. By the time any such
+ * calls get to this routine, we should just shut up and say 'yes'.
+ *
+ * Unlike the cpuset_zone_allowed_softwall() variant, above,
+ * this variant requires that the zone be in the current tasks
+ * mems_allowed or that we're in interrupt. It does not scan up the
+ * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
+ * It never sleeps.
+ */
+
+int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+{
+ int node; /* node that zone z is on */
+
+ if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
+ return 1;
+ node = zone_to_nid(z);
+ if (node_isset(node, current->mems_allowed))
+ return 1;
+ /*
+ * Allow tasks that have access to memory reserves because they have
+ * been OOM killed to get memory anywhere.
+ */
+ if (unlikely(test_thread_flag(TIF_MEMDIE)))
+ return 1;
+ return 0;
+}
+
/**
* cpuset_lock - lock out any changes to cpuset structures
*
return single_open(file, proc_cpuset_show, pid);
}
-struct file_operations proc_cpuset_operations = {
+const struct file_operations proc_cpuset_operations = {
.open = cpuset_open,
.read = seq_read,
.llseek = seq_lseek,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff