/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+/* Notifier list called when a task struct is freed */
+static ATOMIC_NOTIFIER_HEAD(task_free_notifier);
+
static void account_kernel_stack(struct thread_info *ti, int account)
{
struct zone *zone = page_zone(virt_to_page(ti));
free_signal_struct(sig);
}
+int task_free_register(struct notifier_block *n)
+{
+ return atomic_notifier_chain_register(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_register);
+
+int task_free_unregister(struct notifier_block *n)
+{
+ return atomic_notifier_chain_unregister(&task_free_notifier, n);
+}
+EXPORT_SYMBOL(task_free_unregister);
+
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
+ atomic_notifier_call_chain(&task_free_notifier, 0, tsk);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
mm = get_task_mm(task);
if (mm && mm != current->mm &&
- !ptrace_may_access(task, mode)) {
+ !ptrace_may_access(task, mode) &&
+ !capable(CAP_SYS_RESOURCE)) {
mmput(mm);
mm = ERR_PTR(-EACCES);
}
*/
if (!IS_ERR(p)) {
struct completion vfork;
+ struct pid *pid;
trace_sched_process_fork(current, p);
- nr = task_pid_vnr(p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
- ptrace_event(trace, nr);
+ ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
- ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
} else {
nr = PTR_ERR(p);
}
#include <linux/sysctl.h>
#include <linux/oom.h>
#include <linux/prefetch.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
}
+struct dentry *debug_file;
+
+static int debug_shrinker_show(struct seq_file *s, void *unused)
+{
+ struct shrinker *shrinker;
+ struct shrink_control sc;
+
+ sc.gfp_mask = -1;
+ sc.nr_to_scan = 0;
+
+ down_read(&shrinker_rwsem);
+ list_for_each_entry(shrinker, &shrinker_list, list) {
+ int num_objs;
+
+ num_objs = shrinker->shrink(shrinker, &sc);
+ seq_printf(s, "%pf %d\n", shrinker->shrink, num_objs);
+ }
+ up_read(&shrinker_rwsem);
+ return 0;
+}
+
+static int debug_shrinker_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, debug_shrinker_show, inode->i_private);
+}
+
+static const struct file_operations debug_shrinker_fops = {
+ .open = debug_shrinker_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
/*
* Add a shrinker callback to be called from the vm
*/
}
EXPORT_SYMBOL(register_shrinker);
+static int __init add_shrinker_debug(void)
+{
+ debugfs_create_file("shrinker", 0644, NULL, NULL,
+ &debug_shrinker_fops);
+ return 0;
+}
+
+late_initcall(add_shrinker_debug);
+
/*
* Remove one
*/
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
+ if (!populated_zone(zone))
+ continue;
+
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
+ /* If there are no reserves (unexpected config) then do not throttle */
+ if (!pfmemalloc_reserve)
+ return true;
+
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
+ struct zoneref *z;
struct zone *zone;
- int high_zoneidx = gfp_zone(gfp_mask);
- pg_data_t *pgdat;
+ pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
if (fatal_signal_pending(current))
goto out;
- /* Check if the pfmemalloc reserves are ok */
- first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
- pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ /*
+ * Check if the pfmemalloc reserves are ok by finding the first node
+ * with a usable ZONE_NORMAL or lower zone. The expectation is that
+ * GFP_KERNEL will be required for allocating network buffers when
+ * swapping over the network so ZONE_HIGHMEM is unusable.
+ *
+ * Throttling is based on the first usable node and throttled processes
+ * wait on a queue until kswapd makes progress and wakes them. There
+ * is an affinity then between processes waking up and where reclaim
+ * progress has been made assuming the process wakes on the same node.
+ * More importantly, processes running on remote nodes will not compete
+ * for remote pfmemalloc reserves and processes on different nodes
+ * should make reasonable progress.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_mask, nodemask) {
+ if (zone_idx(zone) > ZONE_NORMAL)
+ continue;
+
+ /* Throttle based on the first usable node */
+ pgdat = zone->zone_pgdat;
+ if (pfmemalloc_watermark_ok(pgdat))
+ goto out;
+ break;
+ }
+
+ /* If no zone was usable by the allocation flags then do not throttle */
+ if (!pgdat)
goto out;
/* Account for the throttling */
}
}
+ tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+
return 0;
}
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_DEFAULT_INIT_RCVWND;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
static void tcp_fixup_rcvbuf(struct sock *sk)
{
u32 mss = tcp_sk(sk)->advmss;
- u32 icwnd = TCP_DEFAULT_INIT_RCVWND;
+ u32 icwnd = sysctl_tcp_default_init_rwnd;
int rcvmem;
/* Limit to 10 segments if mss <= 1460,
* or 14600/mss segments, with a minimum of two segments.
*/
if (mss > 1460)
- icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
+ icwnd = max_t(u32, (1460 * icwnd) / mss, 2);
rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER);
while (tcp_win_from_space(rcvmem) < mss)
bool recovered = !before(tp->snd_una, tp->high_seq);
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
- if (flag & FLAG_ORIG_SACK_ACKED) {
- /* Step 3.b. A timeout is spurious if not all data are
- * lost, i.e., never-retransmitted data are (s)acked.
- */
- tcp_try_undo_loss(sk, true);
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
return;
- }
+
if (after(tp->snd_nxt, tp->high_seq) &&
(flag & FLAG_DATA_SACKED || is_dupack)) {
tp->frto = 0; /* Loss was real: 2nd part of step 3.a */