Merge branch 'kvm-ppc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

This fix was intended for 4.13, but didn't get in because both
maintainers were on vacation.

Paul Mackerras:
 "It adds mutual exclusion between list_add_rcu and list_del_rcu calls
  on the kvm->arch.spapr_tce_tables list.  Without this, userspace could
  potentially trigger corruption of the list and cause a host crash or
  worse."

17 files changed, 63 insertions, 41 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 879ff9c7ffd0..6466153f2bf0 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -664,8 +664,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top)
 {
 	unsigned long random_variable = 0;
 
-	if ((current->flags & PF_RANDOMIZE) &&
-		!(current->personality & ADDR_NO_RANDOMIZE)) {
+	if (current->flags & PF_RANDOMIZE) {
 		random_variable = get_random_long();
 		random_variable &= STACK_RND_MASK;
 		random_variable <<= PAGE_SHIFT;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 108df2e3602c..44dfbca9306f 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -133,7 +133,7 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-struct pts_fs_info *devpts_acquire(struct file *filp)
+struct pts_fs_info *devpts_acquire(struct file *filp, struct vfsmount **ptsmnt)
 {
 	struct pts_fs_info *result;
 	struct path path;
@@ -142,6 +142,7 @@ struct pts_fs_info *devpts_acquire(struct file *filp)
 
 	path = filp->f_path;
 	path_get(&path);
+	*ptsmnt = NULL;
 
 	/* Has the devpts filesystem already been found? */
 	sb = path.mnt->mnt_sb;
@@ -165,6 +166,7 @@ struct pts_fs_info *devpts_acquire(struct file *filp)
 	 * pty code needs to hold extra references in case of last /dev/tty close
 	 */
 	atomic_inc(&sb->s_active);
+	*ptsmnt = mntget(path.mnt);
 	result = DEVPTS_SB(sb);
 
 out:
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3ee4fdc3da9e..ab60051be6e5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
 {
 	struct fuse_file *ff;
 
-	ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
+	ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL);
 	if (unlikely(!ff))
 		return NULL;
 
@@ -609,7 +609,7 @@ static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
 	struct fuse_io_priv *io = req->io;
 	ssize_t pos = -1;
 
-	fuse_release_user_pages(req, !io->write);
+	fuse_release_user_pages(req, io->should_dirty);
 
 	if (io->write) {
 		if (req->misc.write.in.size != req->misc.write.out.size)
@@ -1316,7 +1316,6 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
-	bool should_dirty = !write && iter_is_iovec(iter);
 	int cuse = flags & FUSE_DIO_CUSE;
 	struct file *file = io->file;
 	struct inode *inode = file->f_mapping->host;
@@ -1346,6 +1345,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			inode_unlock(inode);
 	}
 
+	io->should_dirty = !write && iter_is_iovec(iter);
 	while (count) {
 		size_t nres;
 		fl_owner_t owner = current->files;
@@ -1360,7 +1360,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			nres = fuse_send_read(req, io, pos, nbytes, owner);
 
 		if (!io->async)
-			fuse_release_user_pages(req, should_dirty);
+			fuse_release_user_pages(req, io->should_dirty);
 		if (req->out.h.error) {
 			err = req->out.h.error;
 			break;
@@ -1669,6 +1669,7 @@ err_nofile:
 err_free:
 	fuse_request_free(req);
 err:
+	mapping_set_error(page->mapping, error);
 	end_page_writeback(page);
 	return error;
 }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1bd7ffdad593..bd4d2a3e1ec1 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -249,6 +249,7 @@ struct fuse_io_priv {
 	size_t size;
 	__u64 offset;
 	bool write;
+	bool should_dirty;
 	int err;
 	struct kiocb *iocb;
 	struct file *file;
diff --git a/fs/iomap.c b/fs/iomap.c
index 039266128b7f..59cc98ad7577 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -278,7 +278,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long bytes;	/* Bytes to write to page */
 
 		offset = (pos & (PAGE_SIZE - 1));
-		bytes = min_t(unsigned long, PAGE_SIZE - offset, length);
+		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 
 		rpage = __iomap_read_page(inode, pos);
 		if (IS_ERR(rpage))
@@ -373,7 +373,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 		unsigned offset, bytes;
 
 		offset = pos & (PAGE_SIZE - 1); /* Within page */
-		bytes = min_t(unsigned, PAGE_SIZE - offset, count);
+		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
 			status = iomap_dax_zero(pos, offset, bytes, iomap);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 69d02cf8cf37..5f93cfacb3d1 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT
 config PNFS_BLOCK
 	tristate
 	depends on NFS_V4_1 && BLK_DEV_DM
+	depends on 64BIT || LBDAF
 	default NFS_V4
 
 config PNFS_FLEXFILE_LAYOUT
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 6df7a0cf5660..f32c58bbe556 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -32,6 +32,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
 {
 	nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
 	nfs4_pnfs_ds_put(mirror_ds->ds);
+	kfree(mirror_ds->ds_versions);
 	kfree_rcu(mirror_ds, id_node.rcu);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ffd2e712595d..d90132642340 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2553,9 +2553,8 @@ static int nfs41_check_open_stateid(struct nfs4_state *state)
 		clear_bit(NFS_O_RDWR_STATE, &state->flags);
 		clear_bit(NFS_OPEN_STATE, &state->flags);
 		stateid->type = NFS4_INVALID_STATEID_TYPE;
-	}
-	if (status != NFS_OK)
 		return status;
+	}
 	if (nfs_open_stateid_recover_openmode(state))
 		return -NFS4ERR_OPENMODE;
 	return NFS_OK;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8a428498d6b2..509a61668d90 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -106,13 +106,13 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		    global_node_page_state(NR_FILE_MAPPED));
 	show_val_kb(m, "Shmem:          ", i.sharedram);
 	show_val_kb(m, "Slab:           ",
-		    global_page_state(NR_SLAB_RECLAIMABLE) +
-		    global_page_state(NR_SLAB_UNRECLAIMABLE));
+		    global_node_page_state(NR_SLAB_RECLAIMABLE) +
+		    global_node_page_state(NR_SLAB_UNRECLAIMABLE));
 
 	show_val_kb(m, "SReclaimable:   ",
-		    global_page_state(NR_SLAB_RECLAIMABLE));
+		    global_node_page_state(NR_SLAB_RECLAIMABLE));
 	show_val_kb(m, "SUnreclaim:     ",
-		    global_page_state(NR_SLAB_UNRECLAIMABLE));
+		    global_node_page_state(NR_SLAB_UNRECLAIMABLE));
 	seq_printf(m, "KernelStack:    %8lu kB\n",
 		   global_page_state(NR_KERNEL_STACK_KB));
 	show_val_kb(m, "PageTables:     ",
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b836fd61ed87..fe8f3265e877 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -16,9 +16,10 @@
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
 #include <linux/shmem_fs.h>
+#include <linux/uaccess.h>
 
 #include <asm/elf.h>
-#include <linux/uaccess.h>
+#include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
 
@@ -1008,6 +1009,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	enum clear_refs_types type;
+	struct mmu_gather tlb;
 	int itype;
 	int rv;
 
@@ -1054,6 +1056,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		}
 
 		down_read(&mm->mmap_sem);
+		tlb_gather_mmu(&tlb, mm, 0, -1);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
@@ -1075,7 +1078,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		walk_page_range(0, mm->highest_vm_end, &clear_refs_walk);
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(mm, 0, -1);
-		flush_tlb_mm(mm);
+		tlb_finish_mmu(&tlb, 0, -1);
 		up_read(&mm->mmap_sem);
 out_mm:
 		mmput(mm);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 53a17496c5c5..566e6ef99f07 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1124,6 +1124,10 @@ void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
 		WARN_ON_ONCE(1);
 		dquot->dq_dqb.dqb_rsvspace = 0;
 	}
+	if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <=
+	    dquot->dq_dqb.dqb_bsoftlimit)
+		dquot->dq_dqb.dqb_btime = (time64_t) 0;
+	clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 }
 
 static void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
@@ -1145,7 +1149,8 @@ static void dquot_decr_space(struct dquot *dquot, qsize_t number)
 		dquot->dq_dqb.dqb_curspace -= number;
 	else
 		dquot->dq_dqb.dqb_curspace = 0;
-	if (dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
+	if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <=
+	    dquot->dq_dqb.dqb_bsoftlimit)
 		dquot->dq_dqb.dqb_btime = (time64_t) 0;
 	clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 }
@@ -1381,14 +1386,18 @@ static int info_idq_free(struct dquot *dquot, qsize_t inodes)
 
 static int info_bdq_free(struct dquot *dquot, qsize_t space)
 {
+	qsize_t tspace;
+
+	tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace;
+
 	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
-	    dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
+	    tspace <= dquot->dq_dqb.dqb_bsoftlimit)
 		return QUOTA_NL_NOWARN;
 
-	if (dquot->dq_dqb.dqb_curspace - space <= dquot->dq_dqb.dqb_bsoftlimit)
+	if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit)
 		return QUOTA_NL_BSOFTBELOW;
-	if (dquot->dq_dqb.dqb_curspace >= dquot->dq_dqb.dqb_bhardlimit &&
-	    dquot->dq_dqb.dqb_curspace - space < dquot->dq_dqb.dqb_bhardlimit)
+	if (tspace >= dquot->dq_dqb.dqb_bhardlimit &&
+	    tspace - space < dquot->dq_dqb.dqb_bhardlimit)
 		return QUOTA_NL_BHARDBELOW;
 	return QUOTA_NL_NOWARN;
 }
@@ -2681,7 +2690,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 
 	if (check_blim) {
 		if (!dm->dqb_bsoftlimit ||
-		    dm->dqb_curspace < dm->dqb_bsoftlimit) {
+		    dm->dqb_curspace + dm->dqb_rsvspace < dm->dqb_bsoftlimit) {
 			dm->dqb_btime = 0;
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 		} else if (!(di->d_fieldmask & QC_SPC_TIMER))
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 06ea26b8c996..b0d5897bc4e6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1600,7 +1600,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 				   uffdio_copy.len);
 		mmput(ctx->mm);
 	} else {
-		return -ENOSPC;
+		return -ESRCH;
 	}
 	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
 		return -EFAULT;
@@ -1647,7 +1647,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 				     uffdio_zeropage.range.len);
 		mmput(ctx->mm);
 	} else {
-		return -ENOSPC;
+		return -ESRCH;
 	}
 	if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
 		return -EFAULT;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index ffd5a15d1bb6..abf5beaae907 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1246,13 +1246,13 @@ xfs_dialloc_ag_inobt(
 
 			/* free inodes to the left? */
 			if (useleft && trec.ir_freecount) {
-				rec = trec;
 				xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 				cur = tcur;
 
 				pag->pagl_leftrec = trec.ir_startino;
 				pag->pagl_rightrec = rec.ir_startino;
 				pag->pagl_pagino = pagino;
+				rec = trec;
 				goto alloc_inode;
 			}
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ceef77c0416a..ff48f0096810 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -874,7 +874,6 @@ xfs_ialloc(
 	case S_IFREG:
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint64_t	di_flags2 = 0;
 			uint		di_flags = 0;
 
 			if (S_ISDIR(mode)) {
@@ -911,20 +910,23 @@ xfs_ialloc(
 				di_flags |= XFS_DIFLAG_NODEFRAG;
 			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
 				di_flags |= XFS_DIFLAG_FILESTREAM;
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				di_flags2 |= XFS_DIFLAG2_DAX;
 
 			ip->i_d.di_flags |= di_flags;
-			ip->i_d.di_flags2 |= di_flags2;
 		}
 		if (pip &&
 		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
 		    pip->i_d.di_version == 3 &&
 		    ip->i_d.di_version == 3) {
+			uint64_t	di_flags2 = 0;
+
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
 			}
+			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+				di_flags2 |= XFS_DIFLAG2_DAX;
+
+			ip->i_d.di_flags2 |= di_flags2;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 0053bcf2b10a..4ebd0bafc914 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -749,9 +749,20 @@ xfs_log_mount_finish(
 		return 0;
 	}
 
+	/*
+	 * During the second phase of log recovery, we need iget and
+	 * iput to behave like they do for an active filesystem.
+	 * xfs_fs_drop_inode needs to be able to prevent the deletion
+	 * of inodes before we're done replaying log items on those
+	 * inodes.  Turn it off immediately after recovery finishes
+	 * so that we don't leak the quota inodes if subsequent mount
+	 * activities fail.
+	 */
+	mp->m_super->s_flags |= MS_ACTIVE;
 	error = xlog_recover_finish(mp->m_log);
 	if (!error)
 		xfs_log_work_queue(mp);
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 
 	return error;
 }
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index fbe72b134bef..43aa42a3a5d3 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -539,6 +539,7 @@ xlog_discard_endio(
 
 	INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
 	queue_work(xfs_discard_wq, &ctx->discard_endio_work);
+	bio_put(bio);
 }
 
 static void
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 40d4e8b4e193..ea7d4b4e50d0 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -945,15 +945,6 @@ xfs_mountfs(
 	}
 
 	/*
-	 * During the second phase of log recovery, we need iget and
-	 * iput to behave like they do for an active filesystem.
-	 * xfs_fs_drop_inode needs to be able to prevent the deletion
-	 * of inodes before we're done replaying log items on those
-	 * inodes.
-	 */
-	mp->m_super->s_flags |= MS_ACTIVE;
-
-	/*
 	 * Finish recovering the file system.  This part needed to be delayed
 	 * until after the root and real-time bitmap inodes were consistently
 	 * read in.
@@ -1028,12 +1019,13 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
-	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);
 	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
+	/* Clean out dquots that might be in memory after quotacheck. */
+	xfs_qm_unmount(mp);
  out_log_dealloc:
 	mp->m_flags |= XFS_MOUNT_UNMOUNTING;
 	xfs_log_mount_cancel(mp);