Commit 95846ecf authored by Gargi Sharma's avatar Gargi Sharma Committed by Linus Torvalds

pid: replace pid bitmap implementation with IDR API

Patch series "Replacing PID bitmap implementation with IDR API", v4.

This series replaces kernel bitmap implementation of PID allocation with
IDR API.  These patches are written to simplify the kernel by replacing
custom code with calls to generic code.

The following are the stats for pid and pid_namespace object files
before and after the replacement.  There is a noteworthy change between
the IDR and bitmap implementation.

Before
   text       data        bss        dec        hex    filename
   8447       3894         64      12405       3075    kernel/pid.o
After
   text       data        bss        dec        hex    filename
   3397        304          0       3701        e75    kernel/pid.o

Before
   text       data        bss        dec        hex    filename
   5692       1842        192       7726       1e2e    kernel/pid_namespace.o
After
   text       data        bss        dec        hex    filename
   2854        216         16       3086        c0e    kernel/pid_namespace.o

The following are the stats for ps, pstree and calling readdir on /proc
for 10,000 processes.

ps:
        With IDR API    With bitmap
real    0m1.479s        0m2.319s
user    0m0.070s        0m0.060s
sys     0m0.289s        0m0.516s

pstree:
        With IDR API    With bitmap
real    0m1.024s        0m1.794s
user    0m0.348s        0m0.612s
sys     0m0.184s        0m0.264s

proc:
        With IDR API    With bitmap
real    0m0.059s        0m0.074s
user    0m0.000s        0m0.004s
sys     0m0.016s        0m0.016s

This patch (of 2):

Replace the current bitmap implementation for Process ID allocation.
Functions that are no longer required, for example, free_pidmap(),
alloc_pidmap(), etc.  are removed.  The rest of the functions are
modified to use the IDR API.  The change was made to make the PID
allocation less complex by replacing custom code with calls to generic
API.

[gs051095@gmail.com: v6]
  Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com
[avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl]
  Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org
Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.comSigned-off-by: default avatarGargi Sharma <gs051095@gmail.com>
Reviewed-by: default avatarRik van Riel <riel@redhat.com>
Acked-by: default avatarOleg Nesterov <oleg@redhat.com>
Cc: Julia Lawall <julia.lawall@lip6.fr>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f9eb2fdd
...@@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private) ...@@ -1093,7 +1093,7 @@ static int show_spu_loadavg(struct seq_file *s, void *private)
LOAD_INT(c), LOAD_FRAC(c), LOAD_INT(c), LOAD_FRAC(c),
count_active_contexts(), count_active_contexts(),
atomic_read(&nr_spu_contexts), atomic_read(&nr_spu_contexts),
task_active_pid_ns(current)->last_pid); idr_get_cursor(&task_active_pid_ns(current)->idr));
return 0; return 0;
} }
......
...@@ -24,7 +24,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v) ...@@ -24,7 +24,7 @@ static int loadavg_proc_show(struct seq_file *m, void *v)
LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]), LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]),
LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]), LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]),
nr_running(), nr_threads, nr_running(), nr_threads,
task_active_pid_ns(current)->last_pid); idr_get_cursor(&task_active_pid_ns(current)->idr));
return 0; return 0;
} }
......
...@@ -10,15 +10,8 @@ ...@@ -10,15 +10,8 @@
#include <linux/nsproxy.h> #include <linux/nsproxy.h>
#include <linux/kref.h> #include <linux/kref.h>
#include <linux/ns_common.h> #include <linux/ns_common.h>
#include <linux/idr.h>
struct pidmap {
atomic_t nr_free;
void *page;
};
#define BITS_PER_PAGE (PAGE_SIZE * 8)
#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
#define PIDMAP_ENTRIES ((PID_MAX_LIMIT+BITS_PER_PAGE-1)/BITS_PER_PAGE)
struct fs_pin; struct fs_pin;
...@@ -30,9 +23,8 @@ enum { /* definitions for pid_namespace's hide_pid field */ ...@@ -30,9 +23,8 @@ enum { /* definitions for pid_namespace's hide_pid field */
struct pid_namespace { struct pid_namespace {
struct kref kref; struct kref kref;
struct pidmap pidmap[PIDMAP_ENTRIES]; struct idr idr;
struct rcu_head rcu; struct rcu_head rcu;
int last_pid;
unsigned int nr_hashed; unsigned int nr_hashed;
struct task_struct *child_reaper; struct task_struct *child_reaper;
struct kmem_cache *pid_cachep; struct kmem_cache *pid_cachep;
...@@ -106,6 +98,6 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) ...@@ -106,6 +98,6 @@ static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
void pidhash_init(void); void pidhash_init(void);
void pidmap_init(void); void pid_idr_init(void);
#endif /* _LINUX_PID_NS_H */ #endif /* _LINUX_PID_NS_H */
...@@ -669,7 +669,7 @@ asmlinkage __visible void __init start_kernel(void) ...@@ -669,7 +669,7 @@ asmlinkage __visible void __init start_kernel(void)
if (late_time_init) if (late_time_init)
late_time_init(); late_time_init();
calibrate_delay(); calibrate_delay();
pidmap_init(); pid_idr_init();
anon_vma_init(); anon_vma_init();
#ifdef CONFIG_X86 #ifdef CONFIG_X86
if (efi_enabled(EFI_RUNTIME_SERVICES)) if (efi_enabled(EFI_RUNTIME_SERVICES))
......
...@@ -39,6 +39,7 @@ ...@@ -39,6 +39,7 @@
#include <linux/proc_ns.h> #include <linux/proc_ns.h>
#include <linux/proc_fs.h> #include <linux/proc_fs.h>
#include <linux/sched/task.h> #include <linux/sched/task.h>
#include <linux/idr.h>
#define pid_hashfn(nr, ns) \ #define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift) hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
...@@ -53,14 +54,6 @@ int pid_max = PID_MAX_DEFAULT; ...@@ -53,14 +54,6 @@ int pid_max = PID_MAX_DEFAULT;
int pid_max_min = RESERVED_PIDS + 1; int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT; int pid_max_max = PID_MAX_LIMIT;
static inline int mk_pid(struct pid_namespace *pid_ns,
struct pidmap *map, int off)
{
return (map - pid_ns->pidmap)*BITS_PER_PAGE + off;
}
#define find_next_offset(map, off) \
find_next_zero_bit((map)->page, BITS_PER_PAGE, off)
/* /*
* PID-map pages start out as NULL, they get allocated upon * PID-map pages start out as NULL, they get allocated upon
...@@ -70,10 +63,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns, ...@@ -70,10 +63,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
*/ */
struct pid_namespace init_pid_ns = { struct pid_namespace init_pid_ns = {
.kref = KREF_INIT(2), .kref = KREF_INIT(2),
.pidmap = { .idr = IDR_INIT,
[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
},
.last_pid = 0,
.nr_hashed = PIDNS_HASH_ADDING, .nr_hashed = PIDNS_HASH_ADDING,
.level = 0, .level = 0,
.child_reaper = &init_task, .child_reaper = &init_task,
...@@ -101,138 +91,6 @@ EXPORT_SYMBOL_GPL(init_pid_ns); ...@@ -101,138 +91,6 @@ EXPORT_SYMBOL_GPL(init_pid_ns);
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
static void free_pidmap(struct upid *upid)
{
int nr = upid->nr;
struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE;
int offset = nr & BITS_PER_PAGE_MASK;
clear_bit(offset, map->page);
atomic_inc(&map->nr_free);
}
/*
* If we started walking pids at 'base', is 'a' seen before 'b'?
*/
static int pid_before(int base, int a, int b)
{
/*
* This is the same as saying
*
* (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT
* and that mapping orders 'a' and 'b' with respect to 'base'.
*/
return (unsigned)(a - base) < (unsigned)(b - base);
}
/*
* We might be racing with someone else trying to set pid_ns->last_pid
* at the pid allocation time (there's also a sysctl for this, but racing
* with this one is OK, see comment in kernel/pid_namespace.c about it).
* We want the winner to have the "later" value, because if the
* "earlier" value prevails, then a pid may get reused immediately.
*
* Since pids rollover, it is not sufficient to just pick the bigger
* value. We have to consider where we started counting from.
*
* 'base' is the value of pid_ns->last_pid that we observed when
* we started looking for a pid.
*
* 'pid' is the pid that we eventually found.
*/
static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid)
{
int prev;
int last_write = base;
do {
prev = last_write;
last_write = cmpxchg(&pid_ns->last_pid, prev, pid);
} while ((prev != last_write) && (pid_before(base, last_write, pid)));
}
static int alloc_pidmap(struct pid_namespace *pid_ns)
{
int i, offset, max_scan, pid, last = pid_ns->last_pid;
struct pidmap *map;
pid = last + 1;
if (pid >= pid_max)
pid = RESERVED_PIDS;
offset = pid & BITS_PER_PAGE_MASK;
map = &pid_ns->pidmap[pid/BITS_PER_PAGE];
/*
* If last_pid points into the middle of the map->page we
* want to scan this bitmap block twice, the second time
* we start with offset == 0 (or RESERVED_PIDS).
*/
max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset;
for (i = 0; i <= max_scan; ++i) {
if (unlikely(!map->page)) {
void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
/*
* Free the page if someone raced with us
* installing it:
*/
spin_lock_irq(&pidmap_lock);
if (!map->page) {
map->page = page;
page = NULL;
}
spin_unlock_irq(&pidmap_lock);
kfree(page);
if (unlikely(!map->page))
return -ENOMEM;
}
if (likely(atomic_read(&map->nr_free))) {
for ( ; ; ) {
if (!test_and_set_bit(offset, map->page)) {
atomic_dec(&map->nr_free);
set_last_pid(pid_ns, last, pid);
return pid;
}
offset = find_next_offset(map, offset);
if (offset >= BITS_PER_PAGE)
break;
pid = mk_pid(pid_ns, map, offset);
if (pid >= pid_max)
break;
}
}
if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
map = &pid_ns->pidmap[0];
offset = RESERVED_PIDS;
if (unlikely(last == offset))
break;
}
pid = mk_pid(pid_ns, map, offset);
}
return -EAGAIN;
}
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
{
int offset;
struct pidmap *map, *end;
if (last >= PID_MAX_LIMIT)
return -1;
offset = (last + 1) & BITS_PER_PAGE_MASK;
map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE];
end = &pid_ns->pidmap[PIDMAP_ENTRIES];
for (; map < end; map++, offset = 0) {
if (unlikely(!map->page))
continue;
offset = find_next_bit((map)->page, BITS_PER_PAGE, offset);
if (offset < BITS_PER_PAGE)
return mk_pid(pid_ns, map, offset);
}
return -1;
}
void put_pid(struct pid *pid) void put_pid(struct pid *pid)
{ {
struct pid_namespace *ns; struct pid_namespace *ns;
...@@ -266,7 +124,7 @@ void free_pid(struct pid *pid) ...@@ -266,7 +124,7 @@ void free_pid(struct pid *pid)
struct upid *upid = pid->numbers + i; struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns; struct pid_namespace *ns = upid->ns;
hlist_del_rcu(&upid->pid_chain); hlist_del_rcu(&upid->pid_chain);
switch(--ns->nr_hashed) { switch (--ns->nr_hashed) {
case 2: case 2:
case 1: case 1:
/* When all that is left in the pid namespace /* When all that is left in the pid namespace
...@@ -284,12 +142,11 @@ void free_pid(struct pid *pid) ...@@ -284,12 +142,11 @@ void free_pid(struct pid *pid)
schedule_work(&ns->proc_work); schedule_work(&ns->proc_work);
break; break;
} }
idr_remove(&ns->idr, upid->nr);
} }
spin_unlock_irqrestore(&pidmap_lock, flags); spin_unlock_irqrestore(&pidmap_lock, flags);
for (i = 0; i <= pid->level; i++)
free_pidmap(pid->numbers + i);
call_rcu(&pid->rcu, delayed_put_pid); call_rcu(&pid->rcu, delayed_put_pid);
} }
...@@ -308,8 +165,29 @@ struct pid *alloc_pid(struct pid_namespace *ns) ...@@ -308,8 +165,29 @@ struct pid *alloc_pid(struct pid_namespace *ns)
tmp = ns; tmp = ns;
pid->level = ns->level; pid->level = ns->level;
for (i = ns->level; i >= 0; i--) { for (i = ns->level; i >= 0; i--) {
nr = alloc_pidmap(tmp); int pid_min = 1;
idr_preload(GFP_KERNEL);
spin_lock_irq(&pidmap_lock);
/*
* init really needs pid 1, but after reaching the maximum
* wrap back to RESERVED_PIDS
*/
if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
pid_min = RESERVED_PIDS;
/*
* Store a null pointer so find_pid_ns does not find
* a partially initialized PID (see below).
*/
nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
pid_max, GFP_ATOMIC);
spin_unlock_irq(&pidmap_lock);
idr_preload_end();
if (nr < 0) { if (nr < 0) {
retval = nr; retval = nr;
goto out_free; goto out_free;
...@@ -339,6 +217,8 @@ struct pid *alloc_pid(struct pid_namespace *ns) ...@@ -339,6 +217,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
for ( ; upid >= pid->numbers; --upid) { for ( ; upid >= pid->numbers; --upid) {
hlist_add_head_rcu(&upid->pid_chain, hlist_add_head_rcu(&upid->pid_chain,
&pid_hash[pid_hashfn(upid->nr, upid->ns)]); &pid_hash[pid_hashfn(upid->nr, upid->ns)]);
/* Make the PID visible to find_pid_ns. */
idr_replace(&upid->ns->idr, pid, upid->nr);
upid->ns->nr_hashed++; upid->ns->nr_hashed++;
} }
spin_unlock_irq(&pidmap_lock); spin_unlock_irq(&pidmap_lock);
...@@ -350,8 +230,11 @@ struct pid *alloc_pid(struct pid_namespace *ns) ...@@ -350,8 +230,11 @@ struct pid *alloc_pid(struct pid_namespace *ns)
put_pid_ns(ns); put_pid_ns(ns);
out_free: out_free:
spin_lock_irq(&pidmap_lock);
while (++i <= ns->level) while (++i <= ns->level)
free_pidmap(pid->numbers + i); idr_remove(&ns->idr, (pid->numbers + i)->nr);
spin_unlock_irq(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid); kmem_cache_free(ns->pid_cachep, pid);
return ERR_PTR(retval); return ERR_PTR(retval);
...@@ -553,16 +436,7 @@ EXPORT_SYMBOL_GPL(task_active_pid_ns); ...@@ -553,16 +436,7 @@ EXPORT_SYMBOL_GPL(task_active_pid_ns);
*/ */
struct pid *find_ge_pid(int nr, struct pid_namespace *ns) struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{ {
struct pid *pid; return idr_get_next(&ns->idr, &nr);
do {
pid = find_pid_ns(nr, ns);
if (pid)
break;
nr = next_pidmap(ns, nr);
} while (nr > 0);
return pid;
} }
/* /*
...@@ -578,7 +452,7 @@ void __init pidhash_init(void) ...@@ -578,7 +452,7 @@ void __init pidhash_init(void)
0, 4096); 0, 4096);
} }
void __init pidmap_init(void) void __init pid_idr_init(void)
{ {
/* Verify no one has done anything silly: */ /* Verify no one has done anything silly: */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
...@@ -590,10 +464,7 @@ void __init pidmap_init(void) ...@@ -590,10 +464,7 @@ void __init pidmap_init(void)
PIDS_PER_CPU_MIN * num_possible_cpus()); PIDS_PER_CPU_MIN * num_possible_cpus());
pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); idr_init(&init_pid_ns.idr);
/* Reserve PID 0. We never call free_pidmap(0) */
set_bit(0, init_pid_ns.pidmap[0].page);
atomic_dec(&init_pid_ns.pidmap[0].nr_free);
init_pid_ns.pid_cachep = KMEM_CACHE(pid, init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
......
...@@ -21,6 +21,7 @@ ...@@ -21,6 +21,7 @@
#include <linux/export.h> #include <linux/export.h>
#include <linux/sched/task.h> #include <linux/sched/task.h>
#include <linux/sched/signal.h> #include <linux/sched/signal.h>
#include <linux/idr.h>
struct pid_cache { struct pid_cache {
int nr_ids; int nr_ids;
...@@ -98,7 +99,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ...@@ -98,7 +99,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
struct pid_namespace *ns; struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1; unsigned int level = parent_pid_ns->level + 1;
struct ucounts *ucounts; struct ucounts *ucounts;
int i;
int err; int err;
err = -EINVAL; err = -EINVAL;
...@@ -117,17 +117,15 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ...@@ -117,17 +117,15 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
if (ns == NULL) if (ns == NULL)
goto out_dec; goto out_dec;
ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); idr_init(&ns->idr);
if (!ns->pidmap[0].page)
goto out_free;
ns->pid_cachep = create_pid_cachep(level + 1); ns->pid_cachep = create_pid_cachep(level + 1);
if (ns->pid_cachep == NULL) if (ns->pid_cachep == NULL)
goto out_free_map; goto out_free_idr;
err = ns_alloc_inum(&ns->ns); err = ns_alloc_inum(&ns->ns);
if (err) if (err)
goto out_free_map; goto out_free_idr;
ns->ns.ops = &pidns_operations; ns->ns.ops = &pidns_operations;
kref_init(&ns->kref); kref_init(&ns->kref);
...@@ -138,17 +136,10 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ...@@ -138,17 +136,10 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
ns->nr_hashed = PIDNS_HASH_ADDING; ns->nr_hashed = PIDNS_HASH_ADDING;
INIT_WORK(&ns->proc_work, proc_cleanup_work); INIT_WORK(&ns->proc_work, proc_cleanup_work);
set_bit(0, ns->pidmap[0].page);
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
for (i = 1; i < PIDMAP_ENTRIES; i++)
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
return ns; return ns;
out_free_map: out_free_idr:
kfree(ns->pidmap[0].page); idr_destroy(&ns->idr);
out_free:
kmem_cache_free(pid_ns_cachep, ns); kmem_cache_free(pid_ns_cachep, ns);
out_dec: out_dec:
dec_pid_namespaces(ucounts); dec_pid_namespaces(ucounts);
...@@ -168,11 +159,9 @@ static void delayed_free_pidns(struct rcu_head *p) ...@@ -168,11 +159,9 @@ static void delayed_free_pidns(struct rcu_head *p)
static void destroy_pid_namespace(struct pid_namespace *ns) static void destroy_pid_namespace(struct pid_namespace *ns)
{ {
int i;
ns_free_inum(&ns->ns); ns_free_inum(&ns->ns);
for (i = 0; i < PIDMAP_ENTRIES; i++)
kfree(ns->pidmap[i].page); idr_destroy(&ns->idr);
call_rcu(&ns->rcu, delayed_free_pidns); call_rcu(&ns->rcu, delayed_free_pidns);
} }
...@@ -213,6 +202,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) ...@@ -213,6 +202,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
int rc; int rc;
struct task_struct *task, *me = current; struct task_struct *task, *me = current;
int init_pids = thread_group_leader(me) ? 1 : 2; int init_pids = thread_group_leader(me) ? 1 : 2;
struct pid *pid;
/* Don't allow any more processes into the pid namespace */ /* Don't allow any more processes into the pid namespace */
disable_pid_allocation(pid_ns); disable_pid_allocation(pid_ns);
...@@ -239,20 +229,16 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) ...@@ -239,20 +229,16 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
* maintain a tasklist for each pid namespace. * maintain a tasklist for each pid namespace.
* *
*/ */
rcu_read_lock();
read_lock(&tasklist_lock); read_lock(&tasklist_lock);
nr = next_pidmap(pid_ns, 1); nr = 2;
while (nr > 0) { idr_for_each_entry_continue(&pid_ns->idr, pid, nr) {
rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID);
task = pid_task(find_vpid(nr), PIDTYPE_PID);
if (task && !__fatal_signal_pending(task)) if (task && !__fatal_signal_pending(task))
send_sig_info(SIGKILL, SEND_SIG_FORCED, task); send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
rcu_read_unlock();
nr = next_pidmap(pid_ns, nr);
} }
read_unlock(&tasklist_lock); read_unlock(&tasklist_lock);
rcu_read_unlock();
/* /*
* Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD. * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
...@@ -301,6 +287,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, ...@@ -301,6 +287,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
{ {
struct pid_namespace *pid_ns = task_active_pid_ns(current); struct pid_namespace *pid_ns = task_active_pid_ns(current);
struct ctl_table tmp = *table; struct ctl_table tmp = *table;
int ret, next;
if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN)) if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM; return -EPERM;
...@@ -311,8 +298,14 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, ...@@ -311,8 +298,14 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
* it should synchronize its usage with external means. * it should synchronize its usage with external means.
*/ */
tmp.data = &pid_ns->last_pid; next = idr_get_cursor(&pid_ns->idr) - 1;
return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
tmp.data = &next;
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (!ret && write)
idr_set_cursor(&pid_ns->idr, next + 1);
return ret;
} }
extern int pid_max; extern int pid_max;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment