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

Conflicts:
	drivers/net/usb/asix_common.c
	drivers/net/usb/sr9800.c
	drivers/net/usb/usbnet.c
	include/linux/usb/usbnet.h
	net/ipv4/tcp_ipv4.c
	net/ipv6/tcp_ipv6.c

The TCP conflicts were overlapping changes.  In 'net' we added a
READ_ONCE() to the socket cached RX route read, whilst in 'net-next'
Eric Dumazet touched the surrounding code dealing with how mini
sockets are handled.

With USB, it's a case of the same bug fix first going into net-next
and then I cherry picked it back into net.

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

11 files changed, 144 insertions, 45 deletions

diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf95669..a91795e01a7f 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -699,8 +699,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 	boff = tmp % bsize;
 	if (boff) {
 		bh = affs_bread_ino(inode, bidx, 0);
-		if (IS_ERR(bh))
-			return PTR_ERR(bh);
+		if (IS_ERR(bh)) {
+			written = PTR_ERR(bh);
+			goto err_first_bh;
+		}
 		tmp = min(bsize - boff, to - from);
 		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
@@ -712,14 +714,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		bidx++;
 	} else if (bidx) {
 		bh = affs_bread_ino(inode, bidx - 1, 0);
-		if (IS_ERR(bh))
-			return PTR_ERR(bh);
+		if (IS_ERR(bh)) {
+			written = PTR_ERR(bh);
+			goto err_first_bh;
+		}
 	}
 	while (from + bsize <= to) {
 		prev_bh = bh;
 		bh = affs_getemptyblk_ino(inode, bidx);
 		if (IS_ERR(bh))
-			goto out;
+			goto err_bh;
 		memcpy(AFFS_DATA(bh), data + from, bsize);
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
@@ -751,7 +755,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		prev_bh = bh;
 		bh = affs_bread_ino(inode, bidx, 1);
 		if (IS_ERR(bh))
-			goto out;
+			goto err_bh;
 		tmp = min(bsize, to - from);
 		BUG_ON(tmp > bsize);
 		memcpy(AFFS_DATA(bh), data + from, tmp);
@@ -790,12 +794,13 @@ done:
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+err_first_bh:
 	unlock_page(page);
 	page_cache_release(page);
 
 	return written;
 
-out:
+err_bh:
 	bh = prev_bh;
 	if (!written)
 		written = PTR_ERR(bh);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e907052eeadb..32a8bbd7a9ad 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -53,6 +53,18 @@ struct wb_writeback_work {
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * If an inode is constantly having its pages dirtied, but then the
+ * updates stop dirtytime_expire_interval seconds in the past, it's
+ * possible for the worst case time between when an inode has its
+ * timestamps updated and when they finally get written out to be two
+ * dirtytime_expire_intervals.  We set the default to 12 hours (in
+ * seconds), which means most of the time inodes will have their
+ * timestamps written to disk after 12 hours, but in the worst case a
+ * few inodes might not their timestamps updated for 24 hours.
+ */
+unsigned int dirtytime_expire_interval = 12 * 60 * 60;
+
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -275,8 +287,8 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 
 	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
 		older_than_this = work->older_than_this;
-	else if ((work->reason == WB_REASON_SYNC) == 0) {
-		expire_time = jiffies - (HZ * 86400);
+	else if (!work->for_sync) {
+		expire_time = jiffies - (dirtytime_expire_interval * HZ);
 		older_than_this = &expire_time;
 	}
 	while (!list_empty(delaying_queue)) {
@@ -458,6 +470,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		 */
 		redirty_tail(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
+		inode->dirtied_when = jiffies;
 		list_move(&inode->i_wb_list, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
@@ -505,12 +518,17 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	spin_lock(&inode->i_lock);
 
 	dirty = inode->i_state & I_DIRTY;
-	if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
-	     (inode->i_state & I_DIRTY_TIME)) ||
-	    (inode->i_state & I_DIRTY_TIME_EXPIRED)) {
-		dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
-		trace_writeback_lazytime(inode);
-	}
+	if (inode->i_state & I_DIRTY_TIME) {
+		if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
+		    unlikely(time_after(jiffies,
+					(inode->dirtied_time_when +
+					 dirtytime_expire_interval * HZ)))) {
+			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
+			trace_writeback_lazytime(inode);
+		}
+	} else
+		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
 	inode->i_state &= ~dirty;
 
 	/*
@@ -1131,6 +1149,56 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 	rcu_read_unlock();
 }
 
+/*
+ * Wake up bdi's periodically to make sure dirtytime inodes gets
+ * written back periodically.  We deliberately do *not* check the
+ * b_dirtytime list in wb_has_dirty_io(), since this would cause the
+ * kernel to be constantly waking up once there are any dirtytime
+ * inodes on the system.  So instead we define a separate delayed work
+ * function which gets called much more rarely.  (By default, only
+ * once every 12 hours.)
+ *
+ * If there is any other write activity going on in the file system,
+ * this function won't be necessary.  But if the only thing that has
+ * happened on the file system is a dirtytime inode caused by an atime
+ * update, we need this infrastructure below to make sure that inode
+ * eventually gets pushed out to disk.
+ */
+static void wakeup_dirtytime_writeback(struct work_struct *w);
+static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback);
+
+static void wakeup_dirtytime_writeback(struct work_struct *w)
+{
+	struct backing_dev_info *bdi;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+		if (list_empty(&bdi->wb.b_dirty_time))
+			continue;
+		bdi_wakeup_thread(bdi);
+	}
+	rcu_read_unlock();
+	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+}
+
+static int __init start_dirtytime_writeback(void)
+{
+	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+	return 0;
+}
+__initcall(start_dirtytime_writeback);
+
+int dirtytime_interval_handler(struct ctl_table *table, int write,
+			       void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		mod_delayed_work(system_wq, &dirtytime_work, 0);
+	return ret;
+}
+
 static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 {
 	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1269,8 +1337,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_wb_list, dirtytime ?
-				  &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
+			if (dirtytime)
+				inode->dirtied_time_when = jiffies;
+			if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES))
+				list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+			else
+				list_move(&inode->i_wb_list,
+					  &bdi->wb.b_dirty_time);
 			spin_unlock(&bdi->wb.list_lock);
 			trace_writeback_dirty_inode_enqueue(inode);
 
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d56094b..754fdf8c6356 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@ skip:
 	hfs_bnode_write(node, entry, data_off + key_len, entry_len);
 	hfs_bnode_dump(node);
 
-	if (new_node) {
-		/* update parent key if we inserted a key
-		 * at the start of the first node
-		 */
-		if (!rec && new_node != node)
-			hfs_brec_update_parent(fd);
+	/*
+	 * update parent key if we inserted a key
+	 * at the start of the node and it is not the new node
+	 */
+	if (!rec && new_node != node) {
+		hfs_bnode_read_key(node, fd->search_key, data_off + size);
+		hfs_brec_update_parent(fd);
+	}
 
+	if (new_node) {
 		hfs_bnode_put(fd->bnode);
 		if (!new_node->parent) {
 			hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@ skip:
 		goto again;
 	}
 
-	if (!rec)
-		hfs_brec_update_parent(fd);
-
 	return 0;
 }
 
@@ -370,6 +370,8 @@ again:
 	if (IS_ERR(parent))
 		return PTR_ERR(parent);
 	__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+	if (fd->record < 0)
+		return -ENOENT;
 	hfs_bnode_dump(parent);
 	rec = fd->record;
 
diff --git a/fs/locks.c b/fs/locks.c
index 528fedfda15e..40bc384728c0 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1388,9 +1388,8 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker)
 int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
-	struct file_lock *new_fl;
 	struct file_lock_context *ctx = inode->i_flctx;
-	struct file_lock *fl;
+	struct file_lock *new_fl, *fl, *tmp;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1420,7 +1419,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index cdbc78c72542..03d647bf195d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -137,7 +137,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 	seg->offset = iomap.offset;
 	seg->length = iomap.length;
 
-	dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
+	dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es);
 	return 0;
 
 out_error:
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 9da89fddab33..9aa2796da90d 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -122,19 +122,19 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
 
 		p = xdr_decode_hyper(p, &bex.foff);
 		if (bex.foff & (block_size - 1)) {
-			dprintk("%s: unaligned offset %lld\n",
+			dprintk("%s: unaligned offset 0x%llx\n",
 				__func__, bex.foff);
 			goto fail;
 		}
 		p = xdr_decode_hyper(p, &bex.len);
 		if (bex.len & (block_size - 1)) {
-			dprintk("%s: unaligned length %lld\n",
+			dprintk("%s: unaligned length 0x%llx\n",
 				__func__, bex.foff);
 			goto fail;
 		}
 		p = xdr_decode_hyper(p, &bex.soff);
 		if (bex.soff & (block_size - 1)) {
-			dprintk("%s: unaligned disk offset %lld\n",
+			dprintk("%s: unaligned disk offset 0x%llx\n",
 				__func__, bex.soff);
 			goto fail;
 		}
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 1028a0629543..6904213a4363 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -118,7 +118,7 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
 {
 	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
 
-	if (exp->ex_flags & NFSEXP_NOPNFS)
+	if (!(exp->ex_flags & NFSEXP_PNFS))
 		return;
 
 	if (sb->s_export_op->get_uuid &&
@@ -440,15 +440,14 @@ nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
 			list_move_tail(&lp->lo_perstate, reaplist);
 			return;
 		}
-		end = seg->offset;
+		lo->offset = layout_end(seg);
 	} else {
 		/* retain the whole layout segment on a split. */
 		if (layout_end(seg) < end) {
 			dprintk("%s: split not supported\n", __func__);
 			return;
 		}
-
-		lo->offset = layout_end(seg);
+		end = seg->offset;
 	}
 
 	layout_update_len(lo, end);
@@ -513,6 +512,9 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp,
 
 	spin_lock(&clp->cl_lock);
 	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (ls->ls_layout_type != lrp->lr_layout_type)
+			continue;
+
 		if (lrp->lr_return_type == RETURN_FSID &&
 		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
 				   &cstate->current_fh.fh_handle))
@@ -587,6 +589,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 
 	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
 
+	trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
+
 	printk(KERN_WARNING
 		"nfsd: client %s failed to respond to layout recall. "
 		"  Fencing..\n", addr_str);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d30bea8d0277..92b9d97aff4f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1237,8 +1237,8 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
 		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
 
 	gdp->gd_notify_types &= ops->notify_types;
-	exp_put(exp);
 out:
+	exp_put(exp);
 	return nfserr;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d2f2c37dc2db..8ba1d888f1e6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3221,7 +3221,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 	} else
 		nfs4_free_openowner(&oo->oo_owner);
 	spin_unlock(&clp->cl_lock);
-	return oo;
+	return ret;
 }
 
 static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
@@ -5062,7 +5062,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
 	} else
 		nfs4_free_lockowner(&lo->lo_owner);
 	spin_unlock(&clp->cl_lock);
-	return lo;
+	return ret;
 }
 
 static void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index df5e66caf100..5fb7e78169a6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1562,7 +1562,11 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
 	p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
 	p = xdr_decode_hyper(p, &lgp->lg_seg.length);
 	p = xdr_decode_hyper(p, &lgp->lg_minlength);
-	nfsd4_decode_stateid(argp, &lgp->lg_sid);
+
+	status = nfsd4_decode_stateid(argp, &lgp->lg_sid);
+	if (status)
+		return status;
+
 	READ_BUF(4);
 	lgp->lg_maxcount = be32_to_cpup(p++);
 
@@ -1580,7 +1584,11 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
 	p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
 	p = xdr_decode_hyper(p, &lcp->lc_seg.length);
 	lcp->lc_reclaim = be32_to_cpup(p++);
-	nfsd4_decode_stateid(argp, &lcp->lc_sid);
+
+	status = nfsd4_decode_stateid(argp, &lcp->lc_sid);
+	if (status)
+		return status;
+
 	READ_BUF(4);
 	lcp->lc_newoffset = be32_to_cpup(p++);
 	if (lcp->lc_newoffset) {
@@ -1628,7 +1636,11 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
 		READ_BUF(16);
 		p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
 		p = xdr_decode_hyper(p, &lrp->lr_seg.length);
-		nfsd4_decode_stateid(argp, &lrp->lr_sid);
+
+		status = nfsd4_decode_stateid(argp, &lrp->lr_sid);
+		if (status)
+			return status;
+
 		READ_BUF(4);
 		lrp->lrf_body_len = be32_to_cpup(p++);
 		if (lrp->lrf_body_len > 0) {
@@ -4123,7 +4135,7 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
 		return nfserr_resource;
 	*p++ = cpu_to_be32(lrp->lrs_present);
 	if (lrp->lrs_present)
-		nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+		return nfsd4_encode_stateid(xdr, &lrp->lr_sid);
 	return nfs_ok;
 }
 #endif /* CONFIG_NFSD_PNFS */
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 83a9694ec485..46ec934f5dee 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -165,13 +165,17 @@ int nfsd_reply_cache_init(void)
 {
 	unsigned int hashsize;
 	unsigned int i;
+	int status = 0;
 
 	max_drc_entries = nfsd_cache_size_limit();
 	atomic_set(&num_drc_entries, 0);
 	hashsize = nfsd_hashsize(max_drc_entries);
 	maskbits = ilog2(hashsize);
 
-	register_shrinker(&nfsd_reply_cache_shrinker);
+	status = register_shrinker(&nfsd_reply_cache_shrinker);
+	if (status)
+		return status;
+
 	drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
 					0, 0, NULL);
 	if (!drc_slab)