Merge commit 'nfs-for-3.3-4' into nfs-for-next

Conflicts:
	fs/nfs/nfs4proc.c

Back-merge of the upstream kernel in order to fix a conflict with the
slotid type conversion and implementation id patches...

10 files changed, 117 insertions, 166 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b60fc8bfb3e9..620daad201db 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -641,10 +641,10 @@ static int __cap_is_valid(struct ceph_cap *cap)
 	unsigned long ttl;
 	u32 gen;
 
-	spin_lock(&cap->session->s_cap_lock);
+	spin_lock(&cap->session->s_gen_ttl_lock);
 	gen = cap->session->s_cap_gen;
 	ttl = cap->session->s_cap_ttl;
-	spin_unlock(&cap->session->s_cap_lock);
+	spin_unlock(&cap->session->s_gen_ttl_lock);
 
 	if (cap->cap_gen < gen || time_after_eq(jiffies, ttl)) {
 		dout("__cap_is_valid %p cap %p issued %s "
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 618246bc2196..3e8094be4604 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -975,10 +975,10 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 	di = ceph_dentry(dentry);
 	if (di->lease_session) {
 		s = di->lease_session;
-		spin_lock(&s->s_cap_lock);
+		spin_lock(&s->s_gen_ttl_lock);
 		gen = s->s_cap_gen;
 		ttl = s->s_cap_ttl;
-		spin_unlock(&s->s_cap_lock);
+		spin_unlock(&s->s_gen_ttl_lock);
 
 		if (di->lease_gen == gen &&
 		    time_before(jiffies, dentry->d_time) &&
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 23ab6a3f1825..866e8d7ca37d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -262,6 +262,7 @@ static int parse_reply_info(struct ceph_msg *msg,
 	/* trace */
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
+		ceph_decode_need(&p, end, len, bad);
 		err = parse_reply_info_trace(&p, p+len, info, features);
 		if (err < 0)
 			goto out_bad;
@@ -270,6 +271,7 @@ static int parse_reply_info(struct ceph_msg *msg,
 	/* extra */
 	ceph_decode_32_safe(&p, end, len, bad);
 	if (len > 0) {
+		ceph_decode_need(&p, end, len, bad);
 		err = parse_reply_info_extra(&p, p+len, info, features);
 		if (err < 0)
 			goto out_bad;
@@ -398,9 +400,11 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
 	s->s_con.peer_name.num = cpu_to_le64(mds);
 
-	spin_lock_init(&s->s_cap_lock);
+	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
 	s->s_cap_ttl = 0;
+
+	spin_lock_init(&s->s_cap_lock);
 	s->s_renew_requested = 0;
 	s->s_renew_seq = 0;
 	INIT_LIST_HEAD(&s->s_caps);
@@ -2326,10 +2330,10 @@ static void handle_session(struct ceph_mds_session *session,
 	case CEPH_SESSION_STALE:
 		pr_info("mds%d caps went stale, renewing\n",
 			session->s_mds);
-		spin_lock(&session->s_cap_lock);
+		spin_lock(&session->s_gen_ttl_lock);
 		session->s_cap_gen++;
 		session->s_cap_ttl = 0;
-		spin_unlock(&session->s_cap_lock);
+		spin_unlock(&session->s_gen_ttl_lock);
 		send_renew_caps(mdsc, session);
 		break;
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index a50ca0e39475..8c7c04ebb595 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -117,10 +117,13 @@ struct ceph_mds_session {
 	void             *s_authorizer_buf, *s_authorizer_reply_buf;
 	size_t            s_authorizer_buf_len, s_authorizer_reply_buf_len;
 
-	/* protected by s_cap_lock */
-	spinlock_t        s_cap_lock;
+	/* protected by s_gen_ttl_lock */
+	spinlock_t        s_gen_ttl_lock;
 	u32               s_cap_gen;  /* inc each time we get mds stale msg */
 	unsigned long     s_cap_ttl;  /* when session caps expire */
+
+	/* protected by s_cap_lock */
+	spinlock_t        s_cap_lock;
 	struct list_head  s_caps;     /* all caps issued by this session */
 	int               s_nr_caps, s_trim_caps;
 	int               s_num_cap_releases;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 857214ae8c08..a76f697303d9 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -111,8 +111,10 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
 }
 
 static struct ceph_vxattr_cb ceph_file_vxattrs[] = {
+	{ true, "ceph.file.layout", ceph_vxattrcb_layout},
+	/* The following extended attribute name is deprecated */
 	{ true, "ceph.layout", ceph_vxattrcb_layout},
-	{ NULL, NULL }
+	{ true, NULL, NULL }
 };
 
 static struct ceph_vxattr_cb *ceph_inode_vxattrs(struct inode *inode)
diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c
index e97404d611e0..9c501449450d 100644
--- a/fs/logfs/dev_mtd.c
+++ b/fs/logfs/dev_mtd.c
@@ -152,9 +152,6 @@ static struct page *logfs_mtd_find_first_sb(struct super_block *sb, u64 *ofs)
 	filler_t *filler = logfs_mtd_readpage;
 	struct mtd_info *mtd = super->s_mtd;
 
-	if (!mtd_can_have_bb(mtd))
-		return NULL;
-
 	*ofs = 0;
 	while (mtd_block_isbad(mtd, *ofs)) {
 		*ofs += mtd->erasesize;
@@ -172,9 +169,6 @@ static struct page *logfs_mtd_find_last_sb(struct super_block *sb, u64 *ofs)
 	filler_t *filler = logfs_mtd_readpage;
 	struct mtd_info *mtd = super->s_mtd;
 
-	if (!mtd_can_have_bb(mtd))
-		return NULL;
-
 	*ofs = mtd->size - mtd->erasesize;
 	while (mtd_block_isbad(mtd, *ofs)) {
 		*ofs -= mtd->erasesize;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 87b9b91f76cf..ea7adfc868c2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3621,8 +3621,8 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	}
 	if (npages > 1) {
 		/* for decoding across pages */
-		args.acl_scratch = alloc_page(GFP_KERNEL);
-		if (!args.acl_scratch)
+		res.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!res.acl_scratch)
 			goto out_free;
 	}
 	args.acl_len = npages * PAGE_SIZE;
@@ -3658,8 +3658,8 @@ out_free:
 	for (i = 0; i < npages; i++)
 		if (pages[i])
 			__free_page(pages[i]);
-	if (args.acl_scratch)
-		__free_page(args.acl_scratch);
+	if (res.acl_scratch)
+		__free_page(res.acl_scratch);
 	return ret;
 }
 
@@ -5104,37 +5104,53 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 	return status;
 }
 
+static struct nfs4_slot *nfs4_alloc_slots(u32 max_slots, gfp_t gfp_flags)
+{
+	return kcalloc(max_slots, sizeof(struct nfs4_slot), gfp_flags);
+}
+
+static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
+		struct nfs4_slot *new,
+		u32 max_slots,
+		u32 ivalue)
+{
+	struct nfs4_slot *old = NULL;
+	u32 i;
+
+	spin_lock(&tbl->slot_tbl_lock);
+	if (new) {
+		old = tbl->slots;
+		tbl->slots = new;
+		tbl->max_slots = max_slots;
+	}
+	tbl->highest_used_slotid = -1;	/* no slot is currently used */
+	for (i = 0; i < tbl->max_slots; i++)
+		tbl->slots[i].seq_nr = ivalue;
+	spin_unlock(&tbl->slot_tbl_lock);
+	kfree(old);
+}
+
 /*
- * Reset a slot table
+ * (re)Initialise a slot table
  */
-static int nfs4_reset_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
-				 int ivalue)
+static int nfs4_realloc_slot_table(struct nfs4_slot_table *tbl, u32 max_reqs,
+				 u32 ivalue)
 {
 	struct nfs4_slot *new = NULL;
-	int i;
-	int ret = 0;
+	int ret = -ENOMEM;
 
 	dprintk("--> %s: max_reqs=%u, tbl->max_slots %d\n", __func__,
 		max_reqs, tbl->max_slots);
 
 	/* Does the newly negotiated max_reqs match the existing slot table? */
 	if (max_reqs != tbl->max_slots) {
-		ret = -ENOMEM;
-		new = kmalloc(max_reqs * sizeof(struct nfs4_slot),
-			      GFP_NOFS);
+		new = nfs4_alloc_slots(max_reqs, GFP_NOFS);
 		if (!new)
 			goto out;
-		ret = 0;
-		kfree(tbl->slots);
-	}
-	spin_lock(&tbl->slot_tbl_lock);
-	if (new) {
-		tbl->slots = new;
-		tbl->max_slots = max_reqs;
 	}
-	for (i = 0; i < tbl->max_slots; ++i)
-		tbl->slots[i].seq_nr = ivalue;
-	spin_unlock(&tbl->slot_tbl_lock);
+	ret = 0;
+
+	nfs4_add_and_init_slots(tbl, new, max_reqs, ivalue);
 	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
 		tbl, tbl->slots, tbl->max_slots);
 out:
@@ -5157,36 +5173,6 @@ static void nfs4_destroy_slot_tables(struct nfs4_session *session)
 }
 
 /*
- * Initialize slot table
- */
-static int nfs4_init_slot_table(struct nfs4_slot_table *tbl,
-		int max_slots, int ivalue)
-{
-	struct nfs4_slot *slot;
-	int ret = -ENOMEM;
-
-	BUG_ON(max_slots > NFS4_MAX_SLOT_TABLE);
-
-	dprintk("--> %s: max_reqs=%u\n", __func__, max_slots);
-
-	slot = kcalloc(max_slots, sizeof(struct nfs4_slot), GFP_NOFS);
-	if (!slot)
-		goto out;
-	ret = 0;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	tbl->max_slots = max_slots;
-	tbl->slots = slot;
-	tbl->highest_used_slotid = NFS4_NO_SLOT;  /* no slot is currently used */
-	spin_unlock(&tbl->slot_tbl_lock);
-	dprintk("%s: tbl=%p slots=%p max_slots=%d\n", __func__,
-		tbl, tbl->slots, tbl->max_slots);
-out:
-	dprintk("<-- %s: return %d\n", __func__, ret);
-	return ret;
-}
-
-/*
  * Initialize or reset the forechannel and backchannel tables
  */
 static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
@@ -5197,25 +5183,16 @@ static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 	dprintk("--> %s\n", __func__);
 	/* Fore channel */
 	tbl = &ses->fc_slot_table;
-	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
-		if (status) /* -ENOMEM */
-			return status;
-	} else {
-		status = nfs4_reset_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
-		if (status)
-			return status;
-	}
+	status = nfs4_realloc_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
+	if (status) /* -ENOMEM */
+		return status;
 	/* Back channel */
 	tbl = &ses->bc_slot_table;
-	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
-		if (status)
-			/* Fore and back channel share a connection so get
-			 * both slot tables or neither */
-			nfs4_destroy_slot_tables(ses);
-	} else
-		status = nfs4_reset_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
+	status = nfs4_realloc_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
+	if (status && tbl->slots == NULL)
+		/* Fore and back channel share a connection so get
+		 * both slot tables or neither */
+		nfs4_destroy_slot_tables(ses);
 	return status;
 }
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index bae959e294cd..2f760604246f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1106,6 +1106,8 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
 {
 	struct nfs_client *clp = server->nfs_client;
 
+	if (test_and_clear_bit(NFS_DELEGATED_STATE, &state->flags))
+		nfs_async_inode_return_delegation(state->inode, &state->stateid);
 	nfs4_state_mark_reclaim_nograce(clp, state);
 	nfs4_schedule_state_manager(clp);
 }
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 7d3ba1ff787c..bca8c77e5fe0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2563,7 +2563,6 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
-	xdr_set_scratch_buffer(xdr, page_address(args->acl_scratch), PAGE_SIZE);
 
 	encode_nops(&hdr);
 }
@@ -6132,6 +6131,10 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	struct compound_hdr hdr;
 	int status;
 
+	if (res->acl_scratch != NULL) {
+		void *p = page_address(res->acl_scratch);
+		xdr_set_scratch_buffer(xdr, p, PAGE_SIZE);
+	}
 	status = decode_compound_hdr(xdr, &hdr);
 	if (status)
 		goto out;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9cde9edf9c4d..d4548dd49b02 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -198,26 +198,6 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
 	return result;
 }
 
-static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
-{
-	struct mm_struct *mm;
-	int err;
-
-	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
-	if (err)
-		return ERR_PTR(err);
-
-	mm = get_task_mm(task);
-	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, mode)) {
-		mmput(mm);
-		mm = ERR_PTR(-EACCES);
-	}
-	mutex_unlock(&task->signal->cred_guard_mutex);
-
-	return mm;
-}
-
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
 	return mm_access(task, PTRACE_MODE_READ);
@@ -711,6 +691,13 @@ static int mem_open(struct inode* inode, struct file* file)
 	if (IS_ERR(mm))
 		return PTR_ERR(mm);
 
+	if (mm) {
+		/* ensure this mm_struct can't be freed */
+		atomic_inc(&mm->mm_count);
+		/* but do not pin its memory */
+		mmput(mm);
+	}
+
 	/* OK to pass negative loff_t, we can catch out-of-range */
 	file->f_mode |= FMODE_UNSIGNED_OFFSET;
 	file->private_data = mm;
@@ -718,57 +705,13 @@ static int mem_open(struct inode* inode, struct file* file)
 	return 0;
 }
 
-static ssize_t mem_read(struct file * file, char __user * buf,
-			size_t count, loff_t *ppos)
+static ssize_t mem_rw(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos, int write)
 {
-	int ret;
-	char *page;
-	unsigned long src = *ppos;
 	struct mm_struct *mm = file->private_data;
-
-	if (!mm)
-		return 0;
-
-	page = (char *)__get_free_page(GFP_TEMPORARY);
-	if (!page)
-		return -ENOMEM;
-
-	ret = 0;
- 
-	while (count > 0) {
-		int this_len, retval;
-
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		retval = access_remote_vm(mm, src, page, this_len, 0);
-		if (!retval) {
-			if (!ret)
-				ret = -EIO;
-			break;
-		}
-
-		if (copy_to_user(buf, page, retval)) {
-			ret = -EFAULT;
-			break;
-		}
- 
-		ret += retval;
-		src += retval;
-		buf += retval;
-		count -= retval;
-	}
-	*ppos = src;
-
-	free_page((unsigned long) page);
-	return ret;
-}
-
-static ssize_t mem_write(struct file * file, const char __user *buf,
-			 size_t count, loff_t *ppos)
-{
-	int copied;
+	unsigned long addr = *ppos;
+	ssize_t copied;
 	char *page;
-	unsigned long dst = *ppos;
-	struct mm_struct *mm = file->private_data;
 
 	if (!mm)
 		return 0;
@@ -778,31 +721,54 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 		return -ENOMEM;
 
 	copied = 0;
+	if (!atomic_inc_not_zero(&mm->mm_users))
+		goto free;
+
 	while (count > 0) {
-		int this_len, retval;
+		int this_len = min_t(int, count, PAGE_SIZE);
 
-		this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-		if (copy_from_user(page, buf, this_len)) {
+		if (write && copy_from_user(page, buf, this_len)) {
 			copied = -EFAULT;
 			break;
 		}
-		retval = access_remote_vm(mm, dst, page, this_len, 1);
-		if (!retval) {
+
+		this_len = access_remote_vm(mm, addr, page, this_len, write);
+		if (!this_len) {
 			if (!copied)
 				copied = -EIO;
 			break;
 		}
-		copied += retval;
-		buf += retval;
-		dst += retval;
-		count -= retval;			
+
+		if (!write && copy_to_user(buf, page, this_len)) {
+			copied = -EFAULT;
+			break;
+		}
+
+		buf += this_len;
+		addr += this_len;
+		copied += this_len;
+		count -= this_len;
 	}
-	*ppos = dst;
+	*ppos = addr;
 
+	mmput(mm);
+free:
 	free_page((unsigned long) page);
 	return copied;
 }
 
+static ssize_t mem_read(struct file *file, char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	return mem_rw(file, buf, count, ppos, 0);
+}
+
+static ssize_t mem_write(struct file *file, const char __user *buf,
+			 size_t count, loff_t *ppos)
+{
+	return mem_rw(file, (char __user*)buf, count, ppos, 1);
+}
+
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 {
 	switch (orig) {
@@ -822,8 +788,8 @@ loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 static int mem_release(struct inode *inode, struct file *file)
 {
 	struct mm_struct *mm = file->private_data;
-
-	mmput(mm);
+	if (mm)
+		mmdrop(mm);
 	return 0;
 }