summaryrefslogtreecommitdiff
path: root/kernel/pid.c
diff options
context:
space:
mode:
authorGargi Sharma <gs051095@gmail.com>2017-11-17 15:30:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-17 16:10:03 -0800
commit95846ecf9dac5089aed4b144d912225f8ef86ae4 (patch)
tree35da897650335522531d4d4ed37afd2fc26539ec /kernel/pid.c
parentf9eb2fdd04d4e68fbea18970bbf65ace716d25b6 (diff)
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.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg 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: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/pid.c')
-rw-r--r--kernel/pid.c201
1 files changed, 36 insertions, 165 deletions
diff --git a/kernel/pid.c b/kernel/pid.c
index 020dedbdf066..0ce59369632f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -39,6 +39,7 @@
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>
#include <linux/sched/task.h>
+#include <linux/idr.h>
#define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
@@ -53,14 +54,6 @@ int pid_max = PID_MAX_DEFAULT;
int pid_max_min = RESERVED_PIDS + 1;
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
@@ -70,10 +63,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
*/
struct pid_namespace init_pid_ns = {
.kref = KREF_INIT(2),
- .pidmap = {
- [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
- },
- .last_pid = 0,
+ .idr = IDR_INIT,
.nr_hashed = PIDNS_HASH_ADDING,
.level = 0,
.child_reaper = &init_task,
@@ -101,138 +91,6 @@ EXPORT_SYMBOL_GPL(init_pid_ns);
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)
{
struct pid_namespace *ns;
@@ -266,7 +124,7 @@ void free_pid(struct pid *pid)
struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns;
hlist_del_rcu(&upid->pid_chain);
- switch(--ns->nr_hashed) {
+ switch (--ns->nr_hashed) {
case 2:
case 1:
/* When all that is left in the pid namespace
@@ -284,12 +142,11 @@ void free_pid(struct pid *pid)
schedule_work(&ns->proc_work);
break;
}
+
+ idr_remove(&ns->idr, upid->nr);
}
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);
}
@@ -308,8 +165,29 @@ struct pid *alloc_pid(struct pid_namespace *ns)
tmp = ns;
pid->level = ns->level;
+
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) {
retval = nr;
goto out_free;
@@ -339,6 +217,8 @@ struct pid *alloc_pid(struct pid_namespace *ns)
for ( ; upid >= pid->numbers; --upid) {
hlist_add_head_rcu(&upid->pid_chain,
&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++;
}
spin_unlock_irq(&pidmap_lock);
@@ -350,8 +230,11 @@ out_unlock:
put_pid_ns(ns);
out_free:
+ spin_lock_irq(&pidmap_lock);
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);
return ERR_PTR(retval);
@@ -553,16 +436,7 @@ EXPORT_SYMBOL_GPL(task_active_pid_ns);
*/
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
- struct pid *pid;
-
- do {
- pid = find_pid_ns(nr, ns);
- if (pid)
- break;
- nr = next_pidmap(ns, nr);
- } while (nr > 0);
-
- return pid;
+ return idr_get_next(&ns->idr, &nr);
}
/*
@@ -578,7 +452,7 @@ void __init pidhash_init(void)
0, 4096);
}
-void __init pidmap_init(void)
+void __init pid_idr_init(void)
{
/* Verify no one has done anything silly: */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING);
@@ -590,10 +464,7 @@ void __init pidmap_init(void)
PIDS_PER_CPU_MIN * num_possible_cpus());
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);
- /* 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);
+ idr_init(&init_pid_ns.idr);
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);