Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	net/ipv4/ip_gre.c

Minor conflicts between tunnel bug fixes in net and
ipv6 tunnel cleanups in net-next.

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 188 insertions, 63 deletions

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index f2ece3c..8f94ca1 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
 {
 	switch (type) {
 	case BPF_TYPE_PROG:
-		atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
+		raw = bpf_prog_inc(raw);
 		break;
 	case BPF_TYPE_MAP:
-		bpf_map_inc(raw, true);
+		raw = bpf_map_inc(raw, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		goto out;
 
 	raw = bpf_any_get(inode->i_private, *type);
-	touch_atime(&path);
+	if (!IS_ERR(raw))
+		touch_atime(&path);
 
 	path_put(&path);
 	return raw;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index adc5e4b..cf5e9f7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -218,11 +218,18 @@ struct bpf_map *__bpf_map_get(struct fd f)
 	return f.file->private_data;
 }
 
-void bpf_map_inc(struct bpf_map *map, bool uref)
+/* prog's and map's refcnt limit */
+#define BPF_MAX_REFCNT 32768
+
+struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
 {
-	atomic_inc(&map->refcnt);
+	if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&map->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
 	if (uref)
 		atomic_inc(&map->usercnt);
+	return map;
 }
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
@@ -234,7 +241,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	if (IS_ERR(map))
 		return map;
 
-	bpf_map_inc(map, true);
+	map = bpf_map_inc(map, true);
 	fdput(f);
 
 	return map;
@@ -658,6 +665,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f)
 	return f.file->private_data;
 }
 
+struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
+{
+	if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) {
+		atomic_dec(&prog->aux->refcnt);
+		return ERR_PTR(-EBUSY);
+	}
+	return prog;
+}
+
 /* called by sockets/tracing/seccomp before attaching program to an event
  * pairs with bpf_prog_put()
  */
@@ -670,7 +686,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	if (IS_ERR(prog))
 		return prog;
 
-	atomic_inc(&prog->aux->refcnt);
+	prog = bpf_prog_inc(prog);
 	fdput(f);
 
 	return prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 56f1806..63554b6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -249,16 +249,6 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
-static const struct {
-	int map_type;
-	int func_id;
-} func_limit[] = {
-	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
-	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output},
-	{BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid},
-};
-
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -943,27 +933,52 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 
 static int check_map_func_compatibility(struct bpf_map *map, int func_id)
 {
-	bool bool_map, bool_func;
-	int i;
-
 	if (!map)
 		return 0;
 
-	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
-		bool_map = (map->map_type == func_limit[i].map_type);
-		bool_func = (func_id == func_limit[i].func_id);
-		/* only when map & func pair match it can continue.
-		 * don't allow any other map type to be passed into
-		 * the special func;
-		 */
-		if (bool_func && bool_map != bool_func) {
-			verbose("cannot pass map_type %d into func %d\n",
-				map->map_type, func_id);
-			return -EINVAL;
-		}
+	/* We need a two way check, first is from map perspective ... */
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_PROG_ARRAY:
+		if (func_id != BPF_FUNC_tail_call)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		if (func_id != BPF_FUNC_perf_event_read &&
+		    func_id != BPF_FUNC_perf_event_output)
+			goto error;
+		break;
+	case BPF_MAP_TYPE_STACK_TRACE:
+		if (func_id != BPF_FUNC_get_stackid)
+			goto error;
+		break;
+	default:
+		break;
+	}
+
+	/* ... and second from the function itself. */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_perf_event_read:
+	case BPF_FUNC_perf_event_output:
+		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+			goto error;
+		break;
+	case BPF_FUNC_get_stackid:
+		if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
+			goto error;
+		break;
+	default:
+		break;
 	}
 
 	return 0;
+error:
+	verbose("cannot pass map_type %d into func %d\n",
+		map->map_type, func_id);
+	return -EINVAL;
 }
 
 static int check_raw_mode(const struct bpf_func_proto *fn)
@@ -2111,15 +2126,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 				return -E2BIG;
 			}
 
-			/* remember this map */
-			env->used_maps[env->used_map_cnt++] = map;
-
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
 			 * and all maps are released in free_bpf_prog_info()
 			 */
-			bpf_map_inc(map, false);
+			map = bpf_map_inc(map, false);
+			if (IS_ERR(map)) {
+				fdput(f);
+				return PTR_ERR(map);
+			}
+			env->used_maps[env->used_map_cnt++] = map;
+
 			fdput(f);
 next_insn:
 			insn++;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 671dc05..909a7d3 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2825,9 +2825,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 				    size_t nbytes, loff_t off, bool threadgroup)
 {
 	struct task_struct *tsk;
+	struct cgroup_subsys *ss;
 	struct cgroup *cgrp;
 	pid_t pid;
-	int ret;
+	int ssid, ret;
 
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return -EINVAL;
@@ -2875,8 +2876,10 @@ out_unlock_rcu:
 	rcu_read_unlock();
 out_unlock_threadgroup:
 	percpu_up_write(&cgroup_threadgroup_rwsem);
+	for_each_subsys(ss, ssid)
+		if (ss->post_attach)
+			ss->post_attach();
 	cgroup_kn_unlock(of->kn);
-	cpuset_post_attach_flush();
 	return ret ?: nbytes;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 00ab5c2..1902956 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -58,7 +58,6 @@
 #include <asm/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
@@ -1016,7 +1015,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 	}
 }
 
-void cpuset_post_attach_flush(void)
+static void cpuset_post_attach(void)
 {
 	flush_workqueue(cpuset_migrate_mm_wq);
 }
@@ -2087,6 +2086,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.can_attach	= cpuset_can_attach,
 	.cancel_attach	= cpuset_cancel_attach,
 	.attach		= cpuset_attach,
+	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
 	.legacy_cftypes	= files,
 	.early_init	= true,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9eb23dc..0bdc6e7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -412,7 +412,8 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 	if (ret || !write)
 		return ret;
 
-	if (sysctl_perf_cpu_time_max_percent == 100) {
+	if (sysctl_perf_cpu_time_max_percent == 100 ||
+	    sysctl_perf_cpu_time_max_percent == 0) {
 		printk(KERN_WARNING
 		       "perf: Dynamic interrupt throttling disabled, can hang your system!\n");
 		WRITE_ONCE(perf_sample_allowed_ns, 0);
@@ -1105,6 +1106,7 @@ static void put_ctx(struct perf_event_context *ctx)
  * function.
  *
  * Lock order:
+ *    cred_guard_mutex
  *	task_struct::perf_event_mutex
  *	  perf_event_context::mutex
  *	    perf_event::child_mutex;
@@ -3420,7 +3422,6 @@ static struct task_struct *
 find_lively_task_by_vpid(pid_t vpid)
 {
 	struct task_struct *task;
-	int err;
 
 	rcu_read_lock();
 	if (!vpid)
@@ -3434,16 +3435,7 @@ find_lively_task_by_vpid(pid_t vpid)
 	if (!task)
 		return ERR_PTR(-ESRCH);
 
-	/* Reuse ptrace permission checks for now. */
-	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
-		goto errout;
-
 	return task;
-errout:
-	put_task_struct(task);
-	return ERR_PTR(err);
-
 }
 
 /*
@@ -8446,6 +8438,24 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	get_online_cpus();
 
+	if (task) {
+		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+		if (err)
+			goto err_cpus;
+
+		/*
+		 * Reuse ptrace permission checks for now.
+		 *
+		 * We must hold cred_guard_mutex across this and any potential
+		 * perf_install_in_context() call for this new event to
+		 * serialize against exec() altering our credentials (and the
+		 * perf_event_exit_task() that could imply).
+		 */
+		err = -EACCES;
+		if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+			goto err_cred;
+	}
+
 	if (flags & PERF_FLAG_PID_CGROUP)
 		cgroup_fd = pid;
 
@@ -8453,7 +8463,7 @@ SYSCALL_DEFINE5(perf_event_open,
 				 NULL, NULL, cgroup_fd);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_cpus;
+		goto err_cred;
 	}
 
 	if (is_sampling_event(event)) {
@@ -8512,11 +8522,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
-	if (task) {
-		put_task_struct(task);
-		task = NULL;
-	}
-
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -8614,6 +8619,11 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 
+	/*
+	 * This is the point on no return; we cannot fail hereafter. This is
+	 * where we start modifying current state.
+	 */
+
 	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
@@ -8685,6 +8695,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		mutex_unlock(&gctx->mutex);
 	mutex_unlock(&ctx->mutex);
 
+	if (task) {
+		mutex_unlock(&task->signal->cred_guard_mutex);
+		put_task_struct(task);
+	}
+
 	put_online_cpus();
 
 	mutex_lock(&current->perf_event_mutex);
@@ -8717,6 +8732,9 @@ err_alloc:
 	 */
 	if (!event_file)
 		free_event(event);
+err_cred:
+	if (task)
+		mutex_unlock(&task->signal->cred_guard_mutex);
 err_cpus:
 	put_online_cpus();
 err_task:
@@ -9001,6 +9019,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 
 /*
  * When a child task exits, feed back event values to parent events.
+ *
+ * Can be called with cred_guard_mutex held when called from
+ * install_exec_creds().
  */
 void perf_event_exit_task(struct task_struct *child)
 {
diff --git a/kernel/kcov.c b/kernel/kcov.c
index 3efbee0..a02f2dd 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -1,5 +1,6 @@
 #define pr_fmt(fmt) "kcov: " fmt
 
+#define DISABLE_BRANCH_PROFILING
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/file.h>
@@ -43,7 +44,7 @@ struct kcov {
  * Entry point from instrumented code.
  * This is called once per basic-block/edge.
  */
-void __sanitizer_cov_trace_pc(void)
+void notrace __sanitizer_cov_trace_pc(void)
 {
 	struct task_struct *t;
 	enum kcov_mode mode;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 8d34308..1391d3e 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1415,6 +1415,9 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(page, lru);
 	VMCOREINFO_OFFSET(page, _mapcount);
 	VMCOREINFO_OFFSET(page, private);
+	VMCOREINFO_OFFSET(page, compound_dtor);
+	VMCOREINFO_OFFSET(page, compound_order);
+	VMCOREINFO_OFFSET(page, compound_head);
 	VMCOREINFO_OFFSET(pglist_data, node_zones);
 	VMCOREINFO_OFFSET(pglist_data, nr_zones);
 #ifdef CONFIG_FLAT_NODE_MEM_MAP
@@ -1447,8 +1450,8 @@ static int __init crash_save_vmcoreinfo_init(void)
 #ifdef CONFIG_X86
 	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
 #endif
-#ifdef CONFIG_HUGETLBFS
-	VMCOREINFO_SYMBOL(free_huge_page);
+#ifdef CONFIG_HUGETLB_PAGE
+	VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
 #endif
 
 	arch_crash_save_vmcoreinfo();
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ed94109..78c1c0e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2176,15 +2176,37 @@ cache_hit:
 	chain->irq_context = hlock->irq_context;
 	i = get_first_held_lock(curr, hlock);
 	chain->depth = curr->lockdep_depth + 1 - i;
+
+	BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks));
+	BUILD_BUG_ON((1UL << 6)  <= ARRAY_SIZE(curr->held_locks));
+	BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes));
+
 	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
 		chain->base = nr_chain_hlocks;
-		nr_chain_hlocks += chain->depth;
 		for (j = 0; j < chain->depth - 1; j++, i++) {
 			int lock_id = curr->held_locks[i].class_idx - 1;
 			chain_hlocks[chain->base + j] = lock_id;
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
 	}
+
+	if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS)
+		nr_chain_hlocks += chain->depth;
+
+#ifdef CONFIG_DEBUG_LOCKDEP
+	/*
+	 * Important for check_no_collision().
+	 */
+	if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
+		if (debug_locks_off_graph_unlock())
+			return 0;
+
+		print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
+		dump_stack();
+		return 0;
+	}
+#endif
+
 	hlist_add_head_rcu(&chain->entry, hash_head);
 	debug_atomic_inc(chain_lookup_misses);
 	inc_chains();
@@ -2932,6 +2954,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 	return 1;
 }
 
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+	return 2 * !!task->hardirq_context + !!task->softirq_context;
+}
+
 static int separate_irq_context(struct task_struct *curr,
 		struct held_lock *hlock)
 {
@@ -2940,8 +2967,6 @@ static int separate_irq_context(struct task_struct *curr,
 	/*
 	 * Keep track of points where we cross into an interrupt context:
 	 */
-	hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) +
-				curr->softirq_context;
 	if (depth) {
 		struct held_lock *prev_hlock;
 
@@ -2973,6 +2998,11 @@ static inline int mark_irqflags(struct task_struct *curr,
 	return 1;
 }
 
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+	return 0;
+}
+
 static inline int separate_irq_context(struct task_struct *curr,
 		struct held_lock *hlock)
 {
@@ -3241,6 +3271,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->acquire_ip = ip;
 	hlock->instance = lock;
 	hlock->nest_lock = nest_lock;
+	hlock->irq_context = task_irq_context(curr);
 	hlock->trylock = trylock;
 	hlock->read = read;
 	hlock->check = check;
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index dbb61a3..a0f61ef 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v)
 	int i;
 
 	if (v == SEQ_START_TOKEN) {
+		if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)
+			seq_printf(m, "(buggered) ");
 		seq_printf(m, "all lock chains:\n");
 		return 0;
 	}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2232ae3..3bfdff0 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -666,6 +666,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work,
 	 */
 	smp_wmb();
 	set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0);
+	/*
+	 * The following mb guarantees that previous clear of a PENDING bit
+	 * will not be reordered with any speculative LOADS or STORES from
+	 * work->current_func, which is executed afterwards.  This possible
+	 * reordering can lead to a missed execution on attempt to qeueue
+	 * the same @work.  E.g. consider this case:
+	 *
+	 *   CPU#0                         CPU#1
+	 *   ----------------------------  --------------------------------
+	 *
+	 * 1  STORE event_indicated
+	 * 2  queue_work_on() {
+	 * 3    test_and_set_bit(PENDING)
+	 * 4 }                             set_..._and_clear_pending() {
+	 * 5                                 set_work_data() # clear bit
+	 * 6                                 smp_mb()
+	 * 7                               work->current_func() {
+	 * 8				      LOAD event_indicated
+	 *				   }
+	 *
+	 * Without an explicit full barrier speculative LOAD on line 8 can
+	 * be executed before CPU#0 does STORE on line 1.  If that happens,
+	 * CPU#0 observes the PENDING bit is still set and new execution of
+	 * a @work is not queued in a hope, that CPU#1 will eventually
+	 * finish the queued @work.  Meanwhile CPU#1 does not see
+	 * event_indicated is set, because speculative LOAD was executed
+	 * before actual STORE.
+	 */
+	smp_mb();
 }
 
 static void clear_work_data(struct work_struct *work)