[PATCH AUTOSEL 4.19 25/65] iomap: get/put the page in iomap_page_create/release()

[PATCH AUTOSEL 4.19 25/65] iomap: get/put the page in iomap_page_create/release()

[Sasha Levin]

From: Piotr Jaroszynski <pjaroszynski@nvidia.com>

[ Upstream commit 8e47a457321ca1a74ad194ab5dcbca764bc70731 ]

migrate_page_move_mapping() expects pages with private data set to have
a page_count elevated by 1.  This is what used to happen for xfs through
the buffer_heads code before the switch to iomap in commit 82cb14175e7d
("xfs: add support for sub-pagesize writeback without buffer_heads").
Not having the count elevated causes move_pages() to fail on memory
mapped files coming from xfs.

Make iomap compatible with the migrate_page_move_mapping() assumption by
elevating the page count as part of iomap_page_create() and lowering it
in iomap_page_release().

It causes the move_pages() syscall to misbehave on memory mapped files
from xfs.  It does not not move any pages, which I suppose is "just" a
perf issue, but it also ends up returning a positive number which is out
of spec for the syscall.  Talking to Michal Hocko, it sounds like
returning positive numbers might be a necessary update to move_pages()
anyway though.

Fixes: 82cb14175e7d ("xfs: add support for sub-pagesize writeback without buffer_heads")
Signed-off-by: Piotr Jaroszynski <pjaroszynski@nvidia.com>
[hch: actually get/put the page iomap_migrate_page() to make it work
      properly]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/iomap.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index e57fb1e534c5a..2e3e64012db7e 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -117,6 +117,12 @@ iomap_page_create(struct inode *inode, struct page *page)
 	atomic_set(&iop->read_count, 0);
 	atomic_set(&iop->write_count, 0);
 	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+	/*
+	 * migrate_page_move_mapping() assumes that pages with private data have
+	 * their count elevated by 1.
+	 */
+	get_page(page);
 	set_page_private(page, (unsigned long)iop);
 	SetPagePrivate(page);
 	return iop;
@@ -133,6 +139,7 @@ iomap_page_release(struct page *page)
 	WARN_ON_ONCE(atomic_read(&iop->write_count));
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
+	put_page(page);
 	kfree(iop);
 }
 
@@ -565,8 +572,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
 
 	if (page_has_private(page)) {
 		ClearPagePrivate(page);
+		get_page(newpage);
 		set_page_private(newpage, page_private(page));
 		set_page_private(page, 0);
+		put_page(page);
 		SetPagePrivate(newpage);
 	}
 
-- 
2.19.1

[PATCH AUTOSEL 4.19 26/65] iomap: fix a use after free in iomap_dio_rw

[Sasha Levin]

From: Christoph Hellwig <hch@lst.de>

[ Upstream commit 4ea899ead2786a30aaa8181fefa81a3df4ad28f6 ]

Introduce a local wait_for_completion variable to avoid an access to the
potentially freed dio struture after dropping the last reference count.

Also use the chance to document the completion behavior to make the
refcounting clear to the reader of the code.

Fixes: ff6a9292e6 ("iomap: implement direct I/O")
Reported-by: Chandan Rajendra <chandan@linux.ibm.com>
Reported-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Chandan Rajendra <chandan@linux.ibm.com>
Tested-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/iomap.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 2e3e64012db7e..fac45206418a2 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1787,6 +1787,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, start = pos;
 	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
+	bool wait_for_completion = is_sync_kiocb(iocb);
 	struct blk_plug plug;
 	struct iomap_dio *dio;
 
@@ -1806,7 +1807,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
-	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
@@ -1861,7 +1861,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+	if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1877,7 +1877,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
 			if (ret == -ENOTBLK) {
-				dio->wait_for_completion = true;
+				wait_for_completion = true;
 				ret = 0;
 			}
 			break;
@@ -1899,8 +1899,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (dio->flags & IOMAP_DIO_WRITE_FUA)
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
+	/*
+	 * We are about to drop our additional submission reference, which
+	 * might be the last reference to the dio.  There are three three
+	 * different ways we can progress here:
+	 *
+	 *  (a) If this is the last reference we will always complete and free
+	 *	the dio ourselves.
+	 *  (b) If this is not the last reference, and we serve an asynchronous
+	 *	iocb, we must never touch the dio after the decrement, the
+	 *	I/O completion handler will complete and free it.
+	 *  (c) If this is not the last reference, but we serve a synchronous
+	 *	iocb, the I/O completion handler will wake us up on the drop
+	 *	of the final reference, and we will complete and free it here
+	 *	after we got woken by the I/O completion handler.
+	 */
+	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!dio->wait_for_completion)
+		if (!wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
@@ -1917,9 +1933,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	ret = iomap_dio_complete(dio);
-
-	return ret;
+	return iomap_dio_complete(dio);
 
 out_free_dio:
 	kfree(dio);
-- 
2.19.1

[PATCH AUTOSEL 4.19 58/65] proc: fix /proc/net/* after setns(2)

[Sasha Levin]

From: Alexey Dobriyan <adobriyan@gmail.com>

[ Upstream commit 1fde6f21d90f8ba5da3cb9c54ca991ed72696c43 ]

/proc entries under /proc/net/* can't be cached into dcache because
setns(2) can change current net namespace.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: avoid vim miscolorization]
[adobriyan@gmail.com: write test, add dummy ->d_revalidate hook: necessary if /proc/net/* is pinned at setns time]
  Link: http://lkml.kernel.org/r/20190108192350.GA12034@avx2
Link: http://lkml.kernel.org/r/20190107162336.GA9239@avx2
Fixes: 1da4d377f943fe4194ffb9fb9c26cc58fad4dd24 ("proc: revalidate misc dentries")
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Reported-by: Mateusz Stępień <mateusz.stepien@netrounds.com>
Reported-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/proc/generic.c                           |   4 +-
 fs/proc/internal.h                          |   1 +
 fs/proc/proc_net.c                          |  20 +++
 tools/testing/selftests/proc/.gitignore     |   1 +
 tools/testing/selftests/proc/Makefile       |   1 +
 tools/testing/selftests/proc/setns-dcache.c | 129 ++++++++++++++++++++
 6 files changed, 155 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/proc/setns-dcache.c

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ae109429a883..e39bac94dead0 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, &proc_misc_dentry_ops);
+		d_set_d_op(dentry, de->proc_dops);
 		return d_splice_alias(inode, dentry);
 	}
 	read_unlock(&proc_subdir_lock);
@@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	INIT_LIST_HEAD(&ent->pde_openers);
 	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
 
+	ent->proc_dops = &proc_misc_dentry_ops;
+
 out:
 	return ent;
 }
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5185d7f6a51ee..95b14196f2842 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,6 +44,7 @@ struct proc_dir_entry {
 	struct completion *pde_unload_completion;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
+	const struct dentry_operations *proc_dops;
 	union {
 		const struct seq_operations *seq_ops;
 		int (*single_show)(struct seq_file *, void *);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index d5e0fcb3439e9..a7b12435519e0 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode)
 	return maybe_get_net(PDE_NET(PDE(inode)));
 }
 
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+	.d_revalidate	= proc_net_d_revalidate,
+	.d_delete	= always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+	pde->proc_dops = &proc_net_dentry_ops;
+}
+
 static int seq_open_net(struct inode *inode, struct file *file)
 {
 	unsigned int state_size = PDE(inode)->state_size;
@@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_seq_fops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
@@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	return proc_register(parent, p);
@@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
+	pde_force_lookup(p);
 	p->proc_fops = &proc_net_single_fops;
 	p->single_show = show;
 	p->write = write;
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 82121a81681f7..29bac5ef9a93d 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,4 +10,5 @@
 /proc-uptime-002
 /read
 /self
+/setns-dcache
 /thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 1c12c34cf85d8..434d033ee0677 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001
 TEST_GEN_PROGS += proc-uptime-002
 TEST_GEN_PROGS += read
 TEST_GEN_PROGS += self
+TEST_GEN_PROGS += setns-dcache
 TEST_GEN_PROGS += thread-self
 
 include ../lib.mk
diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c
new file mode 100644
index 0000000000000..60ab197a73fc9
--- /dev/null
+++ b/tools/testing/selftests/proc/setns-dcache.c
@@ -0,0 +1,129 @@
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWNET) points to new /proc/net content even
+ * if old one is in dcache.
+ *
+ * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+	if (pid > 0) {
+		kill(pid, SIGTERM);
+	}
+}
+
+int main(void)
+{
+	int fd[2];
+	char _ = 0;
+	int nsfd;
+
+	atexit(f);
+
+	/* Check for priviledges and syscall availability straight away. */
+	if (unshare(CLONE_NEWNET) == -1) {
+		if (errno == ENOSYS || errno == EPERM) {
+			return 4;
+		}
+		return 1;
+	}
+	/* Distinguisher between two otherwise empty net namespaces. */
+	if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) {
+		return 1;
+	}
+
+	if (pipe(fd) == -1) {
+		return 1;
+	}
+
+	pid = fork();
+	if (pid == -1) {
+		return 1;
+	}
+
+	if (pid == 0) {
+		if (unshare(CLONE_NEWNET) == -1) {
+			return 1;
+		}
+
+		if (write(fd[1], &_, 1) != 1) {
+			return 1;
+		}
+
+		pause();
+
+		return 0;
+	}
+
+	if (read(fd[0], &_, 1) != 1) {
+		return 1;
+	}
+
+	{
+		char buf[64];
+		snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid);
+		nsfd = open(buf, O_RDONLY);
+		if (nsfd == -1) {
+			return 1;
+		}
+	}
+
+	/* Reliably pin dentry into dcache. */
+	(void)open("/proc/net/unix", O_RDONLY);
+
+	if (setns(nsfd, CLONE_NEWNET) == -1) {
+		return 1;
+	}
+
+	kill(pid, SIGTERM);
+	pid = 0;
+
+	{
+		char buf[4096];
+		ssize_t rv;
+		int fd;
+
+		fd = open("/proc/net/unix", O_RDONLY);
+		if (fd == -1) {
+			return 1;
+		}
+
+#define S "Num       RefCount Protocol Flags    Type St Inode Path\n"
+		rv = read(fd, buf, sizeof(buf));
+
+		assert(rv == strlen(S));
+		assert(memcmp(buf, S, strlen(S)) == 0);
+	}
+
+	return 0;
+}
-- 
2.19.1

[PATCH AUTOSEL 4.19 63/65] fs/drop_caches.c: avoid softlockups in drop_pagecache_sb()

[Sasha Levin]

From: Jan Kara <jack@suse.cz>

[ Upstream commit c27d82f52f75fc9d8d9d40d120d2a96fdeeada5e ]

When superblock has lots of inodes without any pagecache (like is the
case for /proc), drop_pagecache_sb() will iterate through all of them
without dropping sb->s_inode_list_lock which can lead to softlockups
(one of our customers hit this).

Fix the problem by going to the slow path and doing cond_resched() in
case the process needs rescheduling.

Link: http://lkml.kernel.org/r/20190114085343.15011-1-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/drop_caches.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 82377017130f0..d31b6c72b4764 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
+		/*
+		 * We must skip inodes in unusual state. We may also skip
+		 * inodes without pages but we deliberately won't in case
+		 * we need to reschedule to avoid softlockups.
+		 */
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (inode->i_mapping->nrpages == 0)) {
+		    (inode->i_mapping->nrpages == 0 && !need_resched())) {
 			spin_unlock(&inode->i_lock);
 			continue;
 		}
@@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb->s_inode_list_lock);
 
+		cond_resched();
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
-- 
2.19.1