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

Conflicts:
	drivers/net/ethernet/cavium/Kconfig

The cavium conflict was overlapping dependency
changes.

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

15 files changed, 88 insertions, 63 deletions

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e9ace099162c..8a8202956576 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1651,6 +1651,11 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 				/* Exclusive -> exclusive, nothing changed */
 			}
 		}
+
+		/* For exclusive extent, free its reserved bytes too */
+		if (nr_old_roots == 0 && nr_new_roots == 1 &&
+		    cur_new_count == nr_new_roots)
+			qg->reserved -= num_bytes;
 		if (dirty)
 			qgroup_dirty(fs_info, qg);
 	}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index dc10c9dd36c1..ddd5e9471290 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1506,7 +1506,6 @@ static int __mark_caps_flushing(struct inode *inode,
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
-	cf->kick = false;
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
@@ -2123,8 +2122,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
 
 static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 				struct ceph_mds_session *session,
-				struct ceph_inode_info *ci,
-				bool kick_all)
+				struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
@@ -2150,9 +2148,7 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
 			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			if (cf->tid < first_tid)
-				continue;
-			if (kick_all || cf->kick)
+			if (cf->tid >= first_tid)
 				break;
 		}
 		if (!n) {
@@ -2161,7 +2157,6 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 		}
 
 		cf = rb_entry(n, struct ceph_cap_flush, i_node);
-		cf->kick = false;
 
 		first_tid = cf->tid + 1;
 
@@ -2181,8 +2176,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 {
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
 
 	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
@@ -2205,16 +2198,11 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
 			spin_unlock(&ci->i_ceph_lock);
-			if (!__kick_flushing_caps(mdsc, session, ci, true))
+			if (!__kick_flushing_caps(mdsc, session, ci))
 				continue;
 			spin_lock(&ci->i_ceph_lock);
 		}
 
-		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			cf->kick = true;
-		}
-
 		spin_unlock(&ci->i_ceph_lock);
 	}
 }
@@ -2228,7 +2216,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		int delayed = __kick_flushing_caps(mdsc, session, ci, false);
+		int delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
@@ -2261,7 +2249,7 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
 
 		spin_unlock(&ci->i_ceph_lock);
 
-		delayed = __kick_flushing_caps(mdsc, session, ci, true);
+		delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 4347039ecc18..6706bde9ad1b 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -287,7 +287,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 860cc016e70d..2f2460d23a06 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -189,7 +189,6 @@ static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
 struct ceph_cap_flush {
 	u64 tid;
 	int caps;
-	bool kick;
 	struct rb_node g_node; // global
 	union {
 		struct rb_node i_node; // inode
diff --git a/fs/dcache.c b/fs/dcache.c
index 5c8ea15e73a5..9b5fe503f6cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void)
 	inode_init_early();
 }
 
-void __init vfs_caches_init(unsigned long mempages)
+void __init vfs_caches_init(void)
 {
-	unsigned long reserve;
-
-	/* Base hash sizes on available memory, with a reserve equal to
-           150% of current kernel size */
-
-	reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
-	mempages -= reserve;
-
 	names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	dcache_init();
 	inode_init();
-	files_init(mempages);
+	files_init();
+	files_maxfiles_init();
 	mnt_init();
 	bdev_cache_init();
 	chrdev_init();
diff --git a/fs/file_table.c b/fs/file_table.c
index 7f9d407c7595..ad17e05ebf95 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
+#include <linux/swap.h>
 
 #include <linux/atomic.h>
 
@@ -308,19 +309,24 @@ void put_filp(struct file *file)
 	}
 }
 
-void __init files_init(unsigned long mempages)
+void __init files_init(void)
 { 
-	unsigned long n;
-
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
 
-	/*
-	 * One file with associated inode and dcache is very roughly 1K.
-	 * Per default don't use more than 10% of our memory for files. 
-	 */ 
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+	unsigned long n;
+	unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
+
+	memreserve = min(memreserve, totalram_pages - 1);
+	n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
 
-	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 } 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cf74df68617..973c24ce59ad 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1010,6 +1010,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
+	if (creat_flags == HUGETLB_SHMFS_INODE)
+		inode->i_flags |= S_PRIVATE;
 
 	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
diff --git a/fs/namei.c b/fs/namei.c
index ae4e4c18b2ac..1c2105ed20c5 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -879,7 +879,7 @@ static inline int may_follow_link(struct nameidata *nd)
 		return 0;
 
 	/* Allowed if parent directory not sticky and world-writable. */
-	parent = nd->path.dentry->d_inode;
+	parent = nd->inode;
 	if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
 		return 0;
 
@@ -1954,8 +1954,13 @@ OK:
 				continue;
 			}
 		}
-		if (unlikely(!d_can_lookup(nd->path.dentry)))
+		if (unlikely(!d_can_lookup(nd->path.dentry))) {
+			if (nd->flags & LOOKUP_RCU) {
+				if (unlazy_walk(nd, NULL, 0))
+					return -ECHILD;
+			}
 			return -ENOTDIR;
+		}
 	}
 }
 
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 6904213a4363..ebf90e487c75 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -212,6 +212,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
+		fput(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 61dfb33f0559..95202719a1fd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4396,9 +4396,9 @@ laundromat_main(struct work_struct *laundry)
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
-static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
+static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
-	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4601,9 +4601,6 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags)
 {
 	__be32 status;
 
-	status = nfs4_check_fh(fhp, ols);
-	if (status)
-		return status;
 	status = nfsd4_check_openowner_confirmed(ols);
 	if (status)
 		return status;
@@ -4690,6 +4687,9 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		status = nfserr_bad_stateid;
 		break;
 	}
+	if (status)
+		goto out;
+	status = nfs4_check_fh(fhp, s);
 
 done:
 	if (!status && filpp)
@@ -4798,7 +4798,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status)
 		return status;
-	return nfs4_check_fh(current_fh, stp);
+	return nfs4_check_fh(current_fh, &stp->st_stid);
 }
 
 /* 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 54633858733a..75e0563c09d1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2143,6 +2143,7 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
 			      FATTR4_WORD0_RDATTR_ERROR)
 #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
+#define WORD2_ABSENT_FS_ATTRS 0
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 static inline __be32
@@ -2171,7 +2172,7 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 { return 0; }
 #endif
 
-static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
+static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err)
 {
 	/* As per referral draft:  */
 	if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS ||
@@ -2184,6 +2185,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
 	}
 	*bmval0 &= WORD0_ABSENT_FS_ATTRS;
 	*bmval1 &= WORD1_ABSENT_FS_ATTRS;
+	*bmval2 &= WORD2_ABSENT_FS_ATTRS;
 	return 0;
 }
 
@@ -2246,8 +2248,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion));
 
 	if (exp->ex_fslocs.migrated) {
-		BUG_ON(bmval[2]);
-		status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
+		status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err);
 		if (status)
 			goto out;
 	}
@@ -2286,8 +2287,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	}
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) ||
-			bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+	if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) ||
+	     bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
 		err = security_inode_getsecctx(d_inode(dentry),
 						&context, &contextlen);
 		contextsupport = (err == 0);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 92e48c70f0f0..39ddcaf0918f 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -412,16 +412,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
+	LIST_HEAD(to_free);
 
+	/*
+	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+	 * to_free list so we have to use mark_mutex even when accessing that
+	 * list. And freeing mark requires us to drop mark_mutex. So we can
+	 * reliably free only the first mark in the list. That's why we first
+	 * move marks to free to to_free list in one go and then free marks in
+	 * to_free list one by one.
+	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags) {
-			fsnotify_get_mark(mark);
-			fsnotify_destroy_mark_locked(mark, group);
-			fsnotify_put_mark(mark);
-		}
+		if (mark->flags & flags)
+			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
+
+	while (1) {
+		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+		if (list_empty(&to_free)) {
+			mutex_unlock(&group->mark_mutex);
+			break;
+		}
+		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		fsnotify_get_mark(mark);
+		fsnotify_destroy_mark_locked(mark, group);
+		mutex_unlock(&group->mark_mutex);
+		fsnotify_put_mark(mark);
+	}
 }
 
 /*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1a35c6139656..0f5fd9db8194 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -685,7 +685,7 @@ static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
 
 	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
 		u64 s = i_size_read(inode);
-		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
 			(do_div(s, osb->s_clustersize) >> 9);
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
@@ -910,7 +910,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				p_cpos << (osb->s_clustersize_bits - 9),
+				(u64)p_cpos << (osb->s_clustersize_bits - 9),
 				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8b23aa2f52dd..23157e40dd74 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -4025,9 +4025,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb)
 	osb->dc_work_sequence = osb->dc_wake_sequence;
 
 	processed = osb->blocked_lock_count;
-	while (processed) {
-		BUG_ON(list_empty(&osb->blocked_lock_list));
-
+	/*
+	 * blocked lock processing in this loop might call iput which can
+	 * remove items off osb->blocked_lock_list. Downconvert up to
+	 * 'processed' number of locks, but stop short if we had some
+	 * removed in ocfs2_mark_lockres_freeing when downconverting.
+	 */
+	while (processed && !list_empty(&osb->blocked_lock_list)) {
 		lockres = list_entry(osb->blocked_lock_list.next,
 				     struct ocfs2_lock_res, l_blocked_list);
 		list_del_init(&lockres->l_blocked_list);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 7e412ad74836..270221fcef42 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (kinfo->si_code == BUS_MCEERR_AR ||
-		    kinfo->si_code == BUS_MCEERR_AO)
+		if (kinfo->si_signo == SIGBUS &&
+		    (kinfo->si_code == BUS_MCEERR_AR ||
+		     kinfo->si_code == BUS_MCEERR_AO))
 			err |= __put_user((short) kinfo->si_addr_lsb,
 					  &uinfo->ssi_addr_lsb);
 #endif