Merge 4.4.94 into android-4.4

Changes in 4.4.94
	percpu: make this_cpu_generic_read() atomic w.r.t. interrupts
	drm/dp/mst: save vcpi with payloads
	MIPS: Fix minimum alignment requirement of IRQ stack
	sctp: potential read out of bounds in sctp_ulpevent_type_enabled()
	bpf/verifier: reject BPF_ALU64|BPF_END
	udpv6: Fix the checksum computation when HW checksum does not apply
	ip6_gre: skb_push ipv6hdr before packing the header in ip6gre_header
	net: emac: Fix napi poll list corruption
	packet: hold bind lock when rebinding to fanout hook
	bpf: one perf event close won't free bpf program attached by another perf event
	isdn/i4l: fetch the ppp_write buffer in one shot
	vti: fix use after free in vti_tunnel_xmit/vti6_tnl_xmit
	l2tp: Avoid schedule while atomic in exit_net
	l2tp: fix race condition in l2tp_tunnel_delete
	tun: bail out from tun_get_user() if the skb is empty
	packet: in packet_do_bind, test fanout with bind_lock held
	packet: only test po->has_vnet_hdr once in packet_snd
	net: Set sk_prot_creator when cloning sockets to the right proto
	tipc: use only positive error codes in messages
	Revert "bsg-lib: don't free job in bsg_prepare_job"
	locking/lockdep: Add nest_lock integrity test
	watchdog: kempld: fix gcc-4.3 build
	irqchip/crossbar: Fix incorrect type of local variables
	mac80211_hwsim: check HWSIM_ATTR_RADIO_NAME length
	mac80211: fix power saving clients handling in iwlwifi
	net/mlx4_en: fix overflow in mlx4_en_init_timestamp()
	netfilter: nf_ct_expect: Change __nf_ct_expect_check() return value.
	iio: adc: xilinx: Fix error handling
	Btrfs: send, fix failure to rename top level inode due to name collision
	f2fs: do not wait for writeback in write_begin
	md/linear: shutup lockdep warnning
	sparc64: Migrate hvcons irq to panicked cpu
	net/mlx4_core: Fix VF overwrite of module param which disables DMFS on new probed PFs
	crypto: xts - Add ECB dependency
	ocfs2/dlmglue: prepare tracking logic to avoid recursive cluster lock
	slub: do not merge cache if slub_debug contains a never-merge flag
	scsi: scsi_dh_emc: return success in clariion_std_inquiry()
	net: mvpp2: release reference to txq_cpu[] entry after unmapping
	i2c: at91: ensure state is restored after suspending
	ceph: clean up unsafe d_parent accesses in build_dentry_path
	uapi: fix linux/rds.h userspace compilation errors
	uapi: fix linux/mroute6.h userspace compilation errors
	target/iscsi: Fix unsolicited data seq_end_offset calculation
	nfsd/callback: Cleanup callback cred on shutdown
	cpufreq: CPPC: add ACPI_PROCESSOR dependency
	Revert "tty: goldfish: Fix a parameter of a call to free_irq"
	Linux 4.4.94

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

8 files changed, 147 insertions, 10 deletions

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 63a6152be04b..c5bbb5300658 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1648,6 +1648,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
 {
 	int ret;
 
+	if (ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+
 	ret = get_cur_inode_state(sctx, ino, gen);
 	if (ret < 0)
 		goto out;
@@ -1833,7 +1836,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	 * not delted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
 	 */
-	if (sctx->parent_root) {
+	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
 				     NULL, NULL, NULL);
 		if (ret < 0 && ret != -ENOENT)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f54f77037d22..ead89489ae71 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1845,13 +1845,18 @@ static int build_dentry_path(struct dentry *dentry,
 			     int *pfreepath)
 {
 	char *path;
+	struct inode *dir;
 
-	if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) {
-		*pino = ceph_ino(d_inode(dentry->d_parent));
+	rcu_read_lock();
+	dir = d_inode_rcu(dentry->d_parent);
+	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
+		*pino = ceph_ino(dir);
+		rcu_read_unlock();
 		*ppath = dentry->d_name.name;
 		*ppathlen = dentry->d_name.len;
 		return 0;
 	}
+	rcu_read_unlock();
 	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 15bdc2d48cfe..24ace275160c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -696,6 +696,14 @@ int set_callback_cred(void)
 	return 0;
 }
 
+void cleanup_callback_cred(void)
+{
+	if (callback_cred) {
+		put_rpccred(callback_cred);
+		callback_cred = NULL;
+	}
+}
+
 static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
 {
 	if (clp->cl_minorversion == 0) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9e5a6842346e..ca9ebc3242d3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6792,23 +6792,24 @@ nfs4_state_start(void)
 
 	ret = set_callback_cred();
 	if (ret)
-		return -ENOMEM;
+		return ret;
+
 	laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
 	if (laundry_wq == NULL) {
 		ret = -ENOMEM;
-		goto out_recovery;
+		goto out_cleanup_cred;
 	}
 	ret = nfsd4_create_callback_queue();
 	if (ret)
 		goto out_free_laundry;
 
 	set_max_delegations();
-
 	return 0;
 
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
-out_recovery:
+out_cleanup_cred:
+	cleanup_callback_cred();
 	return ret;
 }
 
@@ -6847,6 +6848,7 @@ nfs4_state_shutdown(void)
 {
 	destroy_workqueue(laundry_wq);
 	nfsd4_destroy_callback_queue();
+	cleanup_callback_cred();
 }
 
 static void
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 5134eedcb16c..86af697c21d3 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -595,6 +595,7 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
 		struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
 extern int set_callback_cred(void);
+extern void cleanup_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 60a5f1548cd9..555b57a16499 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -531,6 +531,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
 	init_waitqueue_head(&res->l_event);
 	INIT_LIST_HEAD(&res->l_blocked_list);
 	INIT_LIST_HEAD(&res->l_mask_waiters);
+	INIT_LIST_HEAD(&res->l_holders);
 }
 
 void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
@@ -748,6 +749,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
 	res->l_flags = 0UL;
 }
 
+/*
+ * Keep a list of processes who have interest in a lockres.
+ * Note: this is now only uesed for check recursive cluster locking.
+ */
+static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
+				   struct ocfs2_lock_holder *oh)
+{
+	INIT_LIST_HEAD(&oh->oh_list);
+	oh->oh_owner_pid = get_pid(task_pid(current));
+
+	spin_lock(&lockres->l_lock);
+	list_add_tail(&oh->oh_list, &lockres->l_holders);
+	spin_unlock(&lockres->l_lock);
+}
+
+static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
+				       struct ocfs2_lock_holder *oh)
+{
+	spin_lock(&lockres->l_lock);
+	list_del(&oh->oh_list);
+	spin_unlock(&lockres->l_lock);
+
+	put_pid(oh->oh_owner_pid);
+}
+
+static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres)
+{
+	struct ocfs2_lock_holder *oh;
+	struct pid *pid;
+
+	/* look in the list of holders for one with the current task as owner */
+	spin_lock(&lockres->l_lock);
+	pid = task_pid(current);
+	list_for_each_entry(oh, &lockres->l_holders, oh_list) {
+		if (oh->oh_owner_pid == pid) {
+			spin_unlock(&lockres->l_lock);
+			return 1;
+		}
+	}
+	spin_unlock(&lockres->l_lock);
+
+	return 0;
+}
+
 static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres,
 				     int level)
 {
@@ -2343,8 +2388,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 		goto getbh;
 	}
 
-	if (ocfs2_mount_local(osb))
-		goto local;
+	if ((arg_flags & OCFS2_META_LOCK_GETBH) ||
+	    ocfs2_mount_local(osb))
+		goto update;
 
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
@@ -2373,7 +2419,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
 
-local:
+update:
 	/*
 	 * We only see this flag if we're being called from
 	 * ocfs2_read_locked_inode(). It means we're locking an inode
@@ -2515,6 +2561,59 @@ void ocfs2_inode_unlock(struct inode *inode,
 		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
 }
 
+/*
+ * This _tracker variantes are introduced to deal with the recursive cluster
+ * locking issue. The idea is to keep track of a lock holder on the stack of
+ * the current process. If there's a lock holder on the stack, we know the
+ * task context is already protected by cluster locking. Currently, they're
+ * used in some VFS entry routines.
+ *
+ * return < 0 on error, return == 0 if there's no lock holder on the stack
+ * before this call, return == 1 if this call would be a recursive locking.
+ */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh)
+{
+	int status;
+	int arg_flags = 0, has_locked;
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = ocfs2_is_locked_by_me(lockres);
+	/* Just get buffer head if the cluster lock has been taken */
+	if (has_locked)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+
+	if (likely(!has_locked || ret_bh)) {
+		status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags);
+		if (status < 0) {
+			if (status != -ENOENT)
+				mlog_errno(status);
+			return status;
+		}
+	}
+	if (!has_locked)
+		ocfs2_add_holder(lockres, oh);
+
+	return has_locked;
+}
+
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock)
+{
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	if (!had_lock) {
+		ocfs2_remove_holder(lockres, oh);
+		ocfs2_inode_unlock(inode, ex);
+	}
+}
+
 int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
 {
 	struct ocfs2_lock_res *lockres;
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index d293a22c32c5..a7fc18ba0dc1 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb {
 	__be32	lvb_os_seqno;
 };
 
+struct ocfs2_lock_holder {
+	struct list_head oh_list;
+	struct pid *oh_owner_pid;
+};
+
 /* ocfs2_inode_lock_full() 'arg_flags' flags */
 /* don't wait on recovery. */
 #define OCFS2_META_LOCK_RECOVERY	(0x01)
@@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb {
 #define OCFS2_META_LOCK_NOQUEUE		(0x02)
 /* don't block waiting for the downconvert thread, instead return -EAGAIN */
 #define OCFS2_LOCK_NONBLOCK		(0x04)
+/* just get back disk inode bh if we've got cluster lock. */
+#define OCFS2_META_LOCK_GETBH		(0x08)
 
 /* Locking subclasses of inode cluster lock */
 enum {
@@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
 
 /* To set the locking protocol on module initialization */
 void ocfs2_set_locking_protocol(void);
+
+/* The _tracker pair is used to avoid cluster recursive locking */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh);
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock);
+
 #endif	/* DLMGLUE_H */
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7a0126267847..2495066a9ca3 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -172,6 +172,7 @@ struct ocfs2_lock_res {
 
 	struct list_head         l_blocked_list;
 	struct list_head         l_mask_waiters;
+	struct list_head	 l_holders;
 
 	unsigned long		 l_flags;
 	char                     l_name[OCFS2_LOCK_ID_MAX_LEN];