12 files changed, 147 insertions, 30 deletions

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index e9e04376c52c..e80ad0c7c2a9 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -49,8 +49,9 @@
  * @page: structure to page
  *
  */
-static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
+static int v9fs_fid_readpage(void *data, struct page *page)
 {
+	struct p9_fid *fid = data;
 	struct inode *inode = page->mapping->host;
 	struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
 	struct iov_iter to;
@@ -121,7 +122,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		return ret;
 
-	ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp);
+	ret = read_cache_pages(mapping, pages, v9fs_fid_readpage,
+			filp->private_data);
 	p9_debug(P9_DEBUG_VFS, "  = %d\n", ret);
 	return ret;
 }
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index e7b54514d99a..e137ff6cd9da 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1072,20 +1072,23 @@ static int send_cap_msg(struct ceph_mds_session *session,
 }
 
 /*
- * Queue cap releases when an inode is dropped from our cache.  Since
- * inode is about to be destroyed, there is no need for i_ceph_lock.
+ * Queue cap releases when an inode is dropped from our cache.
  */
 void ceph_queue_caps_release(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct rb_node *p;
 
+	/* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
+	 * may call __ceph_caps_issued_mask() on a freeing inode. */
+	spin_lock(&ci->i_ceph_lock);
 	p = rb_first(&ci->i_caps);
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
 		p = rb_next(p);
 		__ceph_remove_cap(cap, true);
 	}
+	spin_unlock(&ci->i_ceph_lock);
 }
 
 /*
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 1da3805f3ddc..cbbd76f4098e 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -81,6 +81,41 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 	return ret;
 }
 
+struct coda_vm_ops {
+	atomic_t refcnt;
+	struct file *coda_file;
+	const struct vm_operations_struct *host_vm_ops;
+	struct vm_operations_struct vm_ops;
+};
+
+static void
+coda_vm_open(struct vm_area_struct *vma)
+{
+	struct coda_vm_ops *cvm_ops =
+		container_of(vma->vm_ops, struct coda_vm_ops, vm_ops);
+
+	atomic_inc(&cvm_ops->refcnt);
+
+	if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open)
+		cvm_ops->host_vm_ops->open(vma);
+}
+
+static void
+coda_vm_close(struct vm_area_struct *vma)
+{
+	struct coda_vm_ops *cvm_ops =
+		container_of(vma->vm_ops, struct coda_vm_ops, vm_ops);
+
+	if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close)
+		cvm_ops->host_vm_ops->close(vma);
+
+	if (atomic_dec_and_test(&cvm_ops->refcnt)) {
+		vma->vm_ops = cvm_ops->host_vm_ops;
+		fput(cvm_ops->coda_file);
+		kfree(cvm_ops);
+	}
+}
+
 static int
 coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 {
@@ -88,6 +123,8 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	struct coda_inode_info *cii;
 	struct file *host_file;
 	struct inode *coda_inode, *host_inode;
+	struct coda_vm_ops *cvm_ops;
+	int ret;
 
 	cfi = CODA_FTOC(coda_file);
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
@@ -96,6 +133,13 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	if (!host_file->f_op->mmap)
 		return -ENODEV;
 
+	if (WARN_ON(coda_file != vma->vm_file))
+		return -EIO;
+
+	cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL);
+	if (!cvm_ops)
+		return -ENOMEM;
+
 	coda_inode = file_inode(coda_file);
 	host_inode = file_inode(host_file);
 
@@ -109,6 +153,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	 * the container file on us! */
 	else if (coda_inode->i_mapping != host_inode->i_mapping) {
 		spin_unlock(&cii->c_lock);
+		kfree(cvm_ops);
 		return -EBUSY;
 	}
 
@@ -117,7 +162,29 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	cfi->cfi_mapcount++;
 	spin_unlock(&cii->c_lock);
 
-	return host_file->f_op->mmap(host_file, vma);
+	vma->vm_file = get_file(host_file);
+	ret = host_file->f_op->mmap(host_file, vma);
+
+	if (ret) {
+		/* if call_mmap fails, our caller will put coda_file so we
+		 * should drop the reference to the host_file that we got.
+		 */
+		fput(host_file);
+		kfree(cvm_ops);
+	} else {
+		/* here we add redirects for the open/close vm_operations */
+		cvm_ops->host_vm_ops = vma->vm_ops;
+		if (vma->vm_ops)
+			cvm_ops->vm_ops = *vma->vm_ops;
+
+		cvm_ops->vm_ops.open = coda_vm_open;
+		cvm_ops->vm_ops.close = coda_vm_close;
+		cvm_ops->coda_file = coda_file;
+		atomic_set(&cvm_ops->refcnt, 1);
+
+		vma->vm_ops = &cvm_ops->vm_ops;
+	}
+	return ret;
 }
 
 int coda_open(struct inode *coda_inode, struct file *coda_file)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 80d6901493cf..f246f1760ba2 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1041,8 +1041,10 @@ int ecryptfs_read_and_validate_header_region(struct inode *inode)
 
 	rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES,
 				 inode);
-	if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
-		return rc >= 0 ? -EINVAL : rc;
+	if (rc < 0)
+		return rc;
+	else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+		return -EINVAL;
 	rc = ecryptfs_validate_marker(marker);
 	if (!rc)
 		ecryptfs_i_size_init(file_size, inode);
@@ -1400,8 +1402,10 @@ int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
 	rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
 				     ECRYPTFS_XATTR_NAME, file_size,
 				     ECRYPTFS_SIZE_AND_MARKER_BYTES);
-	if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
-		return rc >= 0 ? -EINVAL : rc;
+	if (rc < 0)
+		return rc;
+	else if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+		return -EINVAL;
 	rc = ecryptfs_validate_marker(marker);
 	if (!rc)
 		ecryptfs_i_size_init(file_size, inode);
diff --git a/fs/exec.c b/fs/exec.c
index ab6e34e1de21..eba40240c0c5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1644,7 +1644,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	acct_update_integrals(current);
-	task_numa_free(current);
+	task_numa_free(current, false);
 	free_bprm(bprm);
 	kfree(pathbuf);
 	putname(filename);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1c7b75a760da..a022e2f9faf1 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3073,6 +3073,11 @@ static void read_compacted_summaries(struct f2fs_sb_info *sbi)
 		seg_i = CURSEG_I(sbi, i);
 		segno = le32_to_cpu(ckpt->cur_data_segno[i]);
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]);
+		if (blk_off > ENTRIES_IN_SUM) {
+			f2fs_bug_on(sbi, 1);
+			f2fs_put_page(page, 1);
+			return -EFAULT;
+		}
 		seg_i->next_segno = segno;
 		reset_curseg(sbi, i, 0);
 		seg_i->alloc_type = ckpt->alloc_type[i];
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 668ac19af58f..d25b55ceb9d5 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -935,6 +935,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 	nfs_fscache_open_file(inode, filp);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_open);
 
 /*
  * This function is called whenever some part of NFS notices that
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 679e003818b1..d3e3761eacfa 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 		return err;
 
 	if ((openflags & O_ACCMODE) == 3)
-		openflags--;
+		return nfs_open(inode, filp);
 
 	/* We can't create new files here */
 	openflags &= ~(O_CREAT|O_EXCL);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 41c8ddbc80dc..d1816ee0c11b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -997,6 +997,12 @@ struct nfs4_opendata {
 	int cancelled;
 };
 
+struct nfs4_open_createattrs {
+	struct nfs4_label *label;
+	struct iattr *sattr;
+	const __u32 verf[2];
+};
+
 static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
 		int err, struct nfs4_exception *exception)
 {
@@ -1066,8 +1072,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 
 static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 		struct nfs4_state_owner *sp, fmode_t fmode, int flags,
-		const struct iattr *attrs,
-		struct nfs4_label *label,
+		const struct nfs4_open_createattrs *c,
 		enum open_claim_type4 claim,
 		gfp_t gfp_mask)
 {
@@ -1075,6 +1080,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	struct inode *dir = d_inode(parent);
 	struct nfs_server *server = NFS_SERVER(dir);
 	struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t);
+	struct nfs4_label *label = (c != NULL) ? c->label : NULL;
 	struct nfs4_opendata *p;
 
 	p = kzalloc(sizeof(*p), gfp_mask);
@@ -1131,15 +1137,11 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
 		p->o_arg.fh = NFS_FH(d_inode(dentry));
 	}
-	if (attrs != NULL && attrs->ia_valid != 0) {
-		__u32 verf[2];
-
+	if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) {
 		p->o_arg.u.attrs = &p->attrs;
-		memcpy(&p->attrs, attrs, sizeof(p->attrs));
+		memcpy(&p->attrs, c->sattr, sizeof(p->attrs));
 
-		verf[0] = jiffies;
-		verf[1] = current->pid;
-		memcpy(p->o_arg.u.verifier.data, verf,
+		memcpy(p->o_arg.u.verifier.data, c->verf,
 				sizeof(p->o_arg.u.verifier.data));
 	}
 	p->c_arg.fh = &p->o_res.fh;
@@ -1653,7 +1655,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 	struct nfs4_opendata *opendata;
 
 	opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0,
-			NULL, NULL, claim, GFP_NOFS);
+			NULL, claim, GFP_NOFS);
 	if (opendata == NULL)
 		return ERR_PTR(-ENOMEM);
 	opendata->state = state;
@@ -2488,8 +2490,7 @@ out:
 static int _nfs4_do_open(struct inode *dir,
 			struct nfs_open_context *ctx,
 			int flags,
-			struct iattr *sattr,
-			struct nfs4_label *label,
+			const struct nfs4_open_createattrs *c,
 			int *opened)
 {
 	struct nfs4_state_owner  *sp;
@@ -2501,6 +2502,8 @@ static int _nfs4_do_open(struct inode *dir,
 	struct nfs4_threshold **ctx_th = &ctx->mdsthreshold;
 	fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC);
 	enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL;
+	struct iattr *sattr = c->sattr;
+	struct nfs4_label *label = c->label;
 	struct nfs4_label *olabel = NULL;
 	int status;
 
@@ -2519,8 +2522,8 @@ static int _nfs4_do_open(struct inode *dir,
 	status = -ENOMEM;
 	if (d_really_is_positive(dentry))
 		claim = NFS4_OPEN_CLAIM_FH;
-	opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr,
-			label, claim, GFP_KERNEL);
+	opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags,
+			c, claim, GFP_KERNEL);
 	if (opendata == NULL)
 		goto err_put_state_owner;
 
@@ -2596,10 +2599,18 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 	struct nfs_server *server = NFS_SERVER(dir);
 	struct nfs4_exception exception = { };
 	struct nfs4_state *res;
+	struct nfs4_open_createattrs c = {
+		.label = label,
+		.sattr = sattr,
+		.verf = {
+			[0] = (__u32)jiffies,
+			[1] = (__u32)current->pid,
+		},
+	};
 	int status;
 
 	do {
-		status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened);
+		status = _nfs4_do_open(dir, ctx, flags, &c, opened);
 		res = ctx->state;
 		trace_nfs4_open_file(ctx, flags, status);
 		if (status == 0)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ba27a5ff8677..ea5cb1ba282f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1391,11 +1391,16 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca)
 {
 	u32 slotsize = slot_bytes(ca);
 	u32 num = ca->maxreqs;
-	int avail;
+	unsigned long avail, total_avail;
 
 	spin_lock(&nfsd_drc_lock);
-	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION,
-		    nfsd_drc_max_mem - nfsd_drc_mem_used);
+	total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used;
+	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail);
+	/*
+	 * Never use more than a third of the remaining memory,
+	 * unless it's the only way to give this client a slot:
+	 */
+	avail = clamp_t(unsigned long, avail, slotsize, total_avail/3);
 	num = min_t(int, num, avail / slotsize);
 	nfsd_drc_mem_used += num * slotsize;
 	spin_unlock(&nfsd_drc_lock);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index b6eb56d18568..0fa990f08daf 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -360,7 +360,7 @@ void nfsd_reset_versions(void)
  */
 static void set_max_drc(void)
 {
-	#define NFSD_DRC_SIZE_SHIFT	10
+	#define NFSD_DRC_SIZE_SHIFT	7
 	nfsd_drc_max_mem = (nr_free_buffer_pages()
 					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
 	nfsd_drc_mem_used = 0;
diff --git a/fs/open.c b/fs/open.c
index e6a55dd45cba..b7e2889a710c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -373,6 +373,25 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 				override_cred->cap_permitted;
 	}
 
+	/*
+	 * The new set of credentials can *only* be used in
+	 * task-synchronous circumstances, and does not need
+	 * RCU freeing, unless somebody then takes a separate
+	 * reference to it.
+	 *
+	 * NOTE! This is _only_ true because this credential
+	 * is used purely for override_creds() that installs
+	 * it as the subjective cred. Other threads will be
+	 * accessing ->real_cred, not the subjective cred.
+	 *
+	 * If somebody _does_ make a copy of this (using the
+	 * 'get_current_cred()' function), that will clear the
+	 * non_rcu field, because now that other user may be
+	 * expecting RCU freeing. But normal thread-synchronous
+	 * cred accesses will keep things non-RCY.
+	 */
+	override_cred->non_rcu = 1;
+
 	old_cred = override_creds(override_cred);
 retry:
 	res = user_path_at(dfd, filename, lookup_flags, &path);