fedora kernel: 5963c7872d2bee76ac20ba1ccd2ffbbfe9eb5f8bv3.3.5-2

Signed-off-by: Anton Arapov <anton@redhat.com>

9 files changed, 100 insertions, 140 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 4b4042f9bc6..46c8b14ebf0 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -818,25 +818,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	if (group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
-	/* Let father know we died
-	 *
-	 * Thread signals are configurable, but you aren't going to use
-	 * that to send signals to arbitrary processes.
-	 * That stops right now.
-	 *
-	 * If the parent exec id doesn't match the exec id we saved
-	 * when we started then we know the parent has changed security
-	 * domain.
-	 *
-	 * If our self_exec id doesn't match our parent_exec_id then
-	 * we have changed execution domain as these two values started
-	 * the same after a fork.
-	 */
-	if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
-	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
-	     tsk->self_exec_id != tsk->parent_exec_id))
-		tsk->exit_signal = SIGCHLD;
-
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
diff --git a/kernel/futex.c b/kernel/futex.c
index 06770233576..866c9d5959d 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -59,6 +59,7 @@
 #include <linux/magic.h>
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
+#include <linux/ptrace.h>
 
 #include <asm/futex.h>
 
@@ -2443,40 +2444,29 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
 {
 	struct robust_list_head __user *head;
 	unsigned long ret;
-	const struct cred *cred = current_cred(), *pcred;
+	struct task_struct *p;
 
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
 
+	rcu_read_lock();
+
+	ret = -ESRCH;
 	if (!pid)
-		head = current->robust_list;
+		p = current;
 	else {
-		struct task_struct *p;
-
-		ret = -ESRCH;
-		rcu_read_lock();
 		p = find_task_by_vpid(pid);
 		if (!p)
 			goto err_unlock;
-		ret = -EPERM;
-		pcred = __task_cred(p);
-		/* If victim is in different user_ns, then uids are not
-		   comparable, so we must have CAP_SYS_PTRACE */
-		if (cred->user->user_ns != pcred->user->user_ns) {
-			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-				goto err_unlock;
-			goto ok;
-		}
-		/* If victim is in same user_ns, then uids are comparable */
-		if (cred->euid != pcred->euid &&
-		    cred->euid != pcred->uid &&
-		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-			goto err_unlock;
-ok:
-		head = p->robust_list;
-		rcu_read_unlock();
 	}
 
+	ret = -EPERM;
+	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+		goto err_unlock;
+
+	head = p->robust_list;
+	rcu_read_unlock();
+
 	if (put_user(sizeof(*head), len_ptr))
 		return -EFAULT;
 	return put_user(head, head_ptr);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 5f9e689dc8f..a9642d52863 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -10,6 +10,7 @@
 #include <linux/compat.h>
 #include <linux/nsproxy.h>
 #include <linux/futex.h>
+#include <linux/ptrace.h>
 
 #include <asm/uaccess.h>
 
@@ -136,40 +137,29 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 {
 	struct compat_robust_list_head __user *head;
 	unsigned long ret;
-	const struct cred *cred = current_cred(), *pcred;
+	struct task_struct *p;
 
 	if (!futex_cmpxchg_enabled)
 		return -ENOSYS;
 
+	rcu_read_lock();
+
+	ret = -ESRCH;
 	if (!pid)
-		head = current->compat_robust_list;
+		p = current;
 	else {
-		struct task_struct *p;
-
-		ret = -ESRCH;
-		rcu_read_lock();
 		p = find_task_by_vpid(pid);
 		if (!p)
 			goto err_unlock;
-		ret = -EPERM;
-		pcred = __task_cred(p);
-		/* If victim is in different user_ns, then uids are not
-		   comparable, so we must have CAP_SYS_PTRACE */
-		if (cred->user->user_ns != pcred->user->user_ns) {
-			if (!ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-				goto err_unlock;
-			goto ok;
-		}
-		/* If victim is in same user_ns, then uids are comparable */
-		if (cred->euid != pcred->euid &&
-		    cred->euid != pcred->uid &&
-		    !ns_capable(pcred->user->user_ns, CAP_SYS_PTRACE))
-			goto err_unlock;
-ok:
-		head = p->compat_robust_list;
-		rcu_read_unlock();
 	}
 
+	ret = -EPERM;
+	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+		goto err_unlock;
+
+	head = p->compat_robust_list;
+	rcu_read_unlock();
+
 	if (put_user(sizeof(*head), len_ptr))
 		return -EFAULT;
 	return put_user(ptr_to_compat(head), head_ptr);
diff --git a/kernel/panic.c b/kernel/panic.c
index 80aed44e345..8ed89a175d7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -97,7 +97,7 @@ void panic(const char *fmt, ...)
 	/*
 	 * Avoid nested stack-dumping if a panic occurs during oops processing
 	 */
-	if (!oops_in_progress)
+	if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
 		dump_stack();
 #endif
 
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 8a1c293a7bf..eef311a58a6 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -6,7 +6,7 @@
  *
  * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
  * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- * Copyright (C) 2010-2012 Bojan Smojver <bojan@rexursive.com>
+ * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
  *
  * This file is released under the GPLv2.
  *
@@ -54,23 +54,10 @@
 /*
  * Number of free pages that are not high.
  */
-#ifdef CONFIG_HIGHMEM
-static unsigned long low_free_pages(void)
-{
-	struct zone *zone;
-	unsigned long free = 0;
-
-	for_each_populated_zone(zone)
-		if (!is_highmem(zone))
-			free += zone_page_state(zone, NR_FREE_PAGES);
-	return free;
-}
-#else
 static inline unsigned long low_free_pages(void)
 {
-	return nr_free_pages();
+	return nr_free_pages() - nr_free_highpages();
 }
-#endif
 
 /*
  * Number of pages required to be kept free while writing the image. Always
@@ -295,17 +282,14 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 		return -ENOSPC;
 
 	if (bio_chain) {
-		src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
-		                              __GFP_NORETRY);
+		src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
 		if (src) {
 			copy_page(src, buf);
 		} else {
 			ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
 			if (ret)
 				return ret;
-			src = (void *)__get_free_page(__GFP_WAIT |
-			                              __GFP_NOWARN |
-			                              __GFP_NORETRY);
+			src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
 			if (src) {
 				copy_page(src, buf);
 			} else {
@@ -383,17 +367,12 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		clear_page(handle->cur);
 		handle->cur_swap = offset;
 		handle->k = 0;
-
-		if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
-			error = hib_wait_on_bio_chain(bio_chain);
-			if (error)
-				goto out;
-			/*
-			 * Recalculate the number of required free pages, to
-			 * make sure we never take more than half.
-			 */
-			handle->reqd_free_pages = reqd_free_pages();
-		}
+	}
+	if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+		error = hib_wait_on_bio_chain(bio_chain);
+		if (error)
+			goto out;
+		handle->reqd_free_pages = reqd_free_pages();
 	}
  out:
 	return error;
@@ -441,7 +420,7 @@ static int swap_writer_finish(struct swap_map_handle *handle,
 #define LZO_THREADS	3
 
 /* Maximum number of pages for read buffering. */
-#define LZO_READ_PAGES	8192
+#define LZO_READ_PAGES	(MAP_PAGE_ENTRIES * 8)
 
 
 /**
@@ -652,8 +631,8 @@ static int save_image_lzo(struct swap_map_handle *handle,
 	}
 
 	/*
-	 * Adjust the number of required free pages after all allocations have
-	 * been done. We don't want to run out of pages when writing.
+	 * Adjust number of free pages after all allocations have been done.
+	 * We don't want to run out of pages when writing.
 	 */
 	handle->reqd_free_pages = reqd_free_pages();
 
@@ -1166,17 +1145,14 @@ static int load_image_lzo(struct swap_map_handle *handle,
 
 	/*
 	 * Adjust number of pages for read buffering, in case we are short.
-	 * Never take more than half of all available low pages.
 	 */
-	read_pages = (low_free_pages() - snapshot_get_image_size()) / 2;
+	read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1;
 	read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES);
 
 	for (i = 0; i < read_pages; i++) {
 		page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
 		                                  __GFP_WAIT | __GFP_HIGH :
-		                                  __GFP_WAIT | __GFP_NOWARN |
-		                                  __GFP_NORETRY);
-
+		                                  __GFP_WAIT);
 		if (!page[i]) {
 			if (i < LZO_CMP_PAGES) {
 				ring_size = i;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b342f57879e..478a04c534f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2266,13 +2266,10 @@ calc_load_n(unsigned long load, unsigned long exp,
  * Once we've updated the global active value, we need to apply the exponential
  * weights adjusted to the number of cycles missed.
  */
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
 {
 	long delta, active, n;
 
-	if (time_before(jiffies, calc_load_update))
-		return;
-
 	/*
 	 * If we crossed a calc_load_update boundary, make sure to fold
 	 * any pending idle changes, the respective CPUs might have
@@ -2284,31 +2281,25 @@ static void calc_global_nohz(unsigned long ticks)
 		atomic_long_add(delta, &calc_load_tasks);
 
 	/*
-	 * If we were idle for multiple load cycles, apply them.
+	 * It could be the one fold was all it took, we done!
 	 */
-	if (ticks >= LOAD_FREQ) {
-		n = ticks / LOAD_FREQ;
+	if (time_before(jiffies, calc_load_update + 10))
+		return;
 
-		active = atomic_long_read(&calc_load_tasks);
-		active = active > 0 ? active * FIXED_1 : 0;
+	/*
+	 * Catch-up, fold however many we are behind still
+	 */
+	delta = jiffies - calc_load_update - 10;
+	n = 1 + (delta / LOAD_FREQ);
 
-		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
-		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
-		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
 
-		calc_load_update += n * LOAD_FREQ;
-	}
+	avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+	avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+	avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
 
-	/*
-	 * Its possible the remainder of the above division also crosses
-	 * a LOAD_FREQ period, the regular check in calc_global_load()
-	 * which comes after this will take care of that.
-	 *
-	 * Consider us being 11 ticks before a cycle completion, and us
-	 * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
-	 * age us 4 cycles, and the test in calc_global_load() will
-	 * pick up the final one.
-	 */
+	calc_load_update += n * LOAD_FREQ;
 }
 #else
 void calc_load_account_idle(struct rq *this_rq)
@@ -2320,7 +2311,7 @@ static inline long calc_load_fold_idle(void)
 	return 0;
 }
 
-static void calc_global_nohz(unsigned long ticks)
+static void calc_global_nohz(void)
 {
 }
 #endif
@@ -2348,8 +2339,6 @@ void calc_global_load(unsigned long ticks)
 {
 	long active;
 
-	calc_global_nohz(ticks);
-
 	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
@@ -2361,6 +2350,16 @@ void calc_global_load(unsigned long ticks)
 	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
 
 	calc_load_update += LOAD_FREQ;
+
+	/*
+	 * Account one period with whatever state we found before
+	 * folding in the nohz state and ageing the entire idle period.
+	 *
+	 * This avoids loosing a sample when we go idle between
+	 * calc_load_account_active() (10 ticks ago) and now and thus
+	 * under-accounting.
+	 */
+	calc_global_nohz();
 }
 
 /*
@@ -6334,16 +6333,26 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
-			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
-			if (sd && (sd->flags & SD_OVERLAP))
-				free_sched_groups(sd->groups, 0);
-			kfree(*per_cpu_ptr(sdd->sd, j));
-			kfree(*per_cpu_ptr(sdd->sg, j));
-			kfree(*per_cpu_ptr(sdd->sgp, j));
+			struct sched_domain *sd;
+
+			if (sdd->sd) {
+				sd = *per_cpu_ptr(sdd->sd, j);
+				if (sd && (sd->flags & SD_OVERLAP))
+					free_sched_groups(sd->groups, 0);
+				kfree(*per_cpu_ptr(sdd->sd, j));
+			}
+
+			if (sdd->sg)
+				kfree(*per_cpu_ptr(sdd->sg, j));
+			if (sdd->sgp)
+				kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
 		free_percpu(sdd->sd);
+		sdd->sd = NULL;
 		free_percpu(sdd->sg);
+		sdd->sg = NULL;
 		free_percpu(sdd->sgp);
+		sdd->sgp = NULL;
 	}
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index c73c4284160..b09cf3b8a4d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1642,6 +1642,15 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	BUG_ON(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
+	if (sig != SIGCHLD) {
+		/*
+		 * This is only possible if parent == real_parent.
+		 * Check if it has changed security domain.
+		 */
+		if (tsk->parent_exec_id != tsk->parent->self_exec_id)
+			sig = SIGCHLD;
+	}
+
 	info.si_signo = sig;
 	info.si_errno = 0;
 	/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7656642e4b8..4aa1d7b7cfd 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -538,9 +538,9 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 				hrtimer_get_expires(&ts->sched_timer), 0))
 				break;
 		}
-		/* Update jiffies and reread time */
-		tick_do_update_jiffies64(now);
+		/* Reread time and update jiffies */
 		now = ktime_get();
+		tick_do_update_jiffies64(now);
 	}
 }
 
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 0d6ff355594..d9c07f02de6 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -650,6 +650,8 @@ int trace_print_lat_context(struct trace_iterator *iter)
 {
 	u64 next_ts;
 	int ret;
+	/* trace_find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
 	struct trace_seq *s = &iter->seq;
 	struct trace_entry *entry = iter->ent,
 			   *next_entry = trace_find_next_entry(iter, NULL,
@@ -658,6 +660,9 @@ int trace_print_lat_context(struct trace_iterator *iter)
 	unsigned long abs_usecs = ns2usecs(iter->ts - iter->tr->time_start);
 	unsigned long rel_usecs;
 
+	/* Restore the original ent_size */
+	iter->ent_size = ent_size;
+
 	if (!next_entry)
 		next_ts = iter->ts;
 	rel_usecs = ns2usecs(next_ts - iter->ts);