LKML Archive on lore.kernel.org
 help / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	kvm@vger.kernel.org
Cc: vgoyal@redhat.com, miklos@szeredi.hu, stefanha@redhat.com,
	dgilbert@redhat.com, sweil@redhat.com, swhiteho@redhat.com
Subject: [PATCH 42/52] fuse: Wait for memory ranges to become free
Date: Mon, 10 Dec 2018 12:13:08 -0500
Message-ID: <20181210171318.16998-43-vgoyal@redhat.com> (raw)
In-Reply-To: <20181210171318.16998-1-vgoyal@redhat.com>

Sometimes we run out of memory ranges. So in that case, wait for memory
ranges to become free, instead of returning -EBUSY.

dax fault path is holding fuse_inode->i_mmap_sem and once that is being
held, memory reclaim can't be done. Its not safe to wait while holding
fuse_inode->i_mmap_sem for two reasons.

- Worker thread to free memory might block on fuse_inode->i_mmap_sem as well.
- This inode is holding all the memory and more memory can't be freed.

In both the cases, deadlock will ensue. So return -ENOSPC from iomap_begin()
in fault path if memory can't be allocated. Drop fuse_inode->i_mmap_sem,
and wait for a free range to become available and retry.

read/write path is a different story. We hold inode lock and lock ordering
allows to grab fuse_inode->immap_sem, if needed. That means we can do direct
reclaim in that path. But if there is no memory allocated to this inode,
then direct reclaim will not work and we need to wait for a memory range
to become free. So try following order.

A. Try to get a free range.
B. If not, try direct reclaim.
C. If not, wait for a memory range to become free

Here sleeping with locks held should be fine because in step B, we made
sure this inode is not holding any ranges. That means other inodes are
holding ranges and somebody should be able to free memory. Also, worker
thread does a trylock() on inode lock. That means worker tread will not
wait on this inode and move onto next memory range. Hence above sequence
should be deadlock free.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
 fs/fuse/file.c   | 60 +++++++++++++++++++++++++++++++++++++++++++-------------
 fs/fuse/fuse_i.h |  3 +++
 fs/fuse/inode.c  |  1 +
 3 files changed, 50 insertions(+), 14 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 709747458335..d0942ce0a6c3 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -220,6 +220,8 @@ static void __free_dax_mapping(struct fuse_conn *fc,
 {
 	list_add_tail(&dmap->list, &fc->free_ranges);
 	fc->nr_free_ranges++;
+	/* TODO: Wake up only when needed */
+	wake_up(&fc->dax_range_waitq);
 }
 
 static void free_dax_mapping(struct fuse_conn *fc,
@@ -1770,12 +1772,18 @@ static int fuse_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 			goto iomap_hole;
 
 		/* Can't do reclaim in fault path yet due to lock ordering */
-		if (flags & IOMAP_FAULT)
+		if (flags & IOMAP_FAULT) {
 			alloc_dmap = alloc_dax_mapping(fc);
-		else
+			if (!alloc_dmap)
+				return -ENOSPC;
+		} else {
 			alloc_dmap = alloc_dax_mapping_reclaim(fc, inode);
+			if (IS_ERR(alloc_dmap))
+				return PTR_ERR(alloc_dmap);
+		}
 
-		if (!alloc_dmap)
+		/* If we are here, we should have memory allocated */
+		if (WARN_ON(!alloc_dmap))
 			return -EBUSY;
 
 		/*
@@ -2596,14 +2604,24 @@ static ssize_t fuse_file_splice_read(struct file *in, loff_t *ppos,
 static int __fuse_dax_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 			    bool write)
 {
-	int ret;
+	int ret, error = 0;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	pfn_t pfn;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	bool retry = false;
 
 	if (write)
 		sb_start_pagefault(sb);
 
+retry:
+	if (retry && !(fc->nr_free_ranges > 0)) {
+		ret = -EINTR;
+		if (wait_event_killable_exclusive(fc->dax_range_waitq,
+					(fc->nr_free_ranges > 0)))
+			goto out;
+	}
+
 	/*
 	 * We need to serialize against not only truncate but also against
 	 * fuse dax memory range reclaim. While a range is being reclaimed,
@@ -2611,13 +2629,20 @@ static int __fuse_dax_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 	 * to populate page cache or access memory we are trying to free.
 	 */
 	down_read(&get_fuse_inode(inode)->i_mmap_sem);
-	ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &fuse_iomap_ops);
+	ret = dax_iomap_fault(vmf, pe_size, &pfn, &error, &fuse_iomap_ops);
+	if ((ret & VM_FAULT_ERROR) && error == -ENOSPC) {
+		error = 0;
+		retry = true;
+		up_read(&get_fuse_inode(inode)->i_mmap_sem);
+		goto retry;
+	}
 
 	if (ret & VM_FAULT_NEEDDSYNC)
 		ret = dax_finish_sync_fault(vmf, pe_size, pfn);
 
 	up_read(&get_fuse_inode(inode)->i_mmap_sem);
 
+out:
 	if (write)
 		sb_end_pagefault(sb);
 
@@ -3828,16 +3853,23 @@ static struct fuse_dax_mapping *alloc_dax_mapping_reclaim(struct fuse_conn *fc,
 	struct fuse_dax_mapping *dmap;
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
-	dmap = alloc_dax_mapping(fc);
-	if (dmap)
-		return dmap;
-
-	/* There are no mappings which can be reclaimed */
-	if (!fi->nr_dmaps)
-		return NULL;
+	while(1) {
+		dmap = alloc_dax_mapping(fc);
+		if (dmap)
+			return dmap;
 
-	/* Try reclaim a fuse dax memory range */
-	return fuse_dax_reclaim_first_mapping(fc, inode);
+		if (fi->nr_dmaps)
+			return fuse_dax_reclaim_first_mapping(fc, inode);
+		/*
+		 * There are no mappings which can be reclaimed.
+		 * Wait for one.
+		 */
+		if (!(fc->nr_free_ranges > 0)) {
+			if (wait_event_killable_exclusive(fc->dax_range_waitq,
+					(fc->nr_free_ranges > 0)))
+				return ERR_PTR(-EINTR);
+		}
+	}
 }
 
 int fuse_dax_free_one_mapping_locked(struct fuse_conn *fc, struct inode *inode,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index bbefa7c11078..7b2db87c6ead 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -886,6 +886,9 @@ struct fuse_conn {
 	/* Worker to free up memory ranges */
 	struct delayed_work dax_free_work;
 
+	/* Wait queue for a dax range to become free */
+	wait_queue_head_t dax_range_waitq;
+
 	/*
 	 * DAX Window Free Ranges. TODO: This might not be best place to store
 	 * this free list
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d31acb97eede..178ac3171564 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -695,6 +695,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
 	atomic_set(&fc->dev_count, 1);
 	init_waitqueue_head(&fc->blocked_waitq);
 	init_waitqueue_head(&fc->reserved_req_waitq);
+	init_waitqueue_head(&fc->dax_range_waitq);
 	fuse_iqueue_init(&fc->iq, fiq_ops, fiq_priv);
 	INIT_LIST_HEAD(&fc->bg_queue);
 	INIT_LIST_HEAD(&fc->entry);
-- 
2.13.6


  parent reply index

Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-10 17:12 [PATCH 00/52] [RFC] virtio-fs: shared file system for virtual machines Vivek Goyal
2018-12-10 17:12 ` [PATCH 01/52] fuse: add skeleton virtio_fs.ko module Vivek Goyal
2018-12-10 17:12 ` [PATCH 02/52] fuse: add probe/remove virtio driver Vivek Goyal
2018-12-10 17:12 ` [PATCH 03/52] fuse: rely on mutex_unlock() barrier instead of fput() Vivek Goyal
2018-12-10 17:12 ` [PATCH 04/52] fuse: extract fuse_fill_super_common() Vivek Goyal
2018-12-10 17:12 ` [PATCH 05/52] virtio_fs: get mount working Vivek Goyal
2018-12-10 17:12 ` [PATCH 06/52] fuse: export fuse_end_request() Vivek Goyal
2018-12-10 17:12 ` [PATCH 07/52] fuse: export fuse_len_args() Vivek Goyal
2018-12-10 17:12 ` [PATCH 08/52] fuse: add fuse_iqueue_ops callbacks Vivek Goyal
2018-12-10 17:12 ` [PATCH 09/52] fuse: process requests queues Vivek Goyal
2018-12-10 17:12 ` [PATCH 10/52] fuse: export fuse_get_unique() Vivek Goyal
2018-12-10 17:12 ` [PATCH 11/52] fuse: implement FUSE_FORGET for virtio-fs Vivek Goyal
2018-12-10 17:12 ` [PATCH 12/52] virtio_fs: Set up dax_device Vivek Goyal
2018-12-10 17:12 ` [PATCH 13/52] dax: remove block device dependencies Vivek Goyal
2018-12-10 17:12 ` [PATCH 14/52] fuse: add fuse_conn->dax_dev field Vivek Goyal
2018-12-10 17:12 ` [PATCH 15/52] fuse: map virtio_fs DAX window BAR Vivek Goyal
2018-12-12 16:37   ` Christian Borntraeger
2018-12-13 11:55     ` Stefan Hajnoczi
2018-12-13 16:06   ` kbuild test robot
2018-12-13 19:55   ` Dan Williams
2018-12-13 20:09     ` Dr. David Alan Gilbert
2018-12-13 20:15       ` Dan Williams
2018-12-13 20:40         ` Vivek Goyal
2018-12-13 21:18           ` Vivek Goyal
2018-12-14 10:09             ` Dr. David Alan Gilbert
2018-12-10 17:12 ` [PATCH 16/52] virtio-fs: Add VIRTIO_PCI_CAP_SHARED_MEMORY_CFG and utility to find them Vivek Goyal
2018-12-12 16:36   ` [PATCH] virtio-fs: fix semicolon.cocci warnings kbuild test robot
2018-12-12 16:36   ` [PATCH 16/52] virtio-fs: Add VIRTIO_PCI_CAP_SHARED_MEMORY_CFG and utility to find them kbuild test robot
2018-12-10 17:12 ` [PATCH 17/52] virtio-fs: Retrieve shm capabilities for cache Vivek Goyal
2018-12-10 17:12 ` [PATCH 18/52] virtio-fs: Map cache using the values from the capabilities Vivek Goyal
2018-12-13  9:10   ` David Hildenbrand
2018-12-13  9:13     ` Dr. David Alan Gilbert
2018-12-13  9:34       ` David Hildenbrand
2018-12-13 10:00         ` Dr. David Alan Gilbert
2018-12-13 11:26           ` David Hildenbrand
2018-12-13 12:15             ` Dr. David Alan Gilbert
2018-12-13 12:24               ` David Hildenbrand
2018-12-13 12:38                 ` Cornelia Huck
2018-12-14 13:44                   ` Stefan Hajnoczi
2018-12-14 13:50                     ` Cornelia Huck
2018-12-14 14:06                       ` Dr. David Alan Gilbert
2018-12-17 11:25                       ` Stefan Hajnoczi
2018-12-17 10:53                     ` David Hildenbrand
2018-12-17 14:56                       ` Stefan Hajnoczi
2018-12-18 17:13                         ` Cornelia Huck
2018-12-18 17:25                           ` David Hildenbrand
2019-01-02 10:24                             ` Stefan Hajnoczi
2019-03-17  0:33   ` Liu Bo
2019-03-20 10:42     ` Dr. David Alan Gilbert
2019-03-17  0:35   ` [PATCH] virtio-fs: fix multiple tag support Liu Bo
2019-03-19 20:26     ` Vivek Goyal
2019-03-20  2:04       ` Liu Bo
2018-12-10 17:12 ` [PATCH 19/52] virito-fs: Make dax optional Vivek Goyal
2018-12-10 17:12 ` [PATCH 20/52] Limit number of pages returned by direct_access() Vivek Goyal
2018-12-10 17:12 ` [PATCH 21/52] fuse: Introduce fuse_dax_mapping Vivek Goyal
2018-12-10 17:12 ` [PATCH 22/52] Create a list of free memory ranges Vivek Goyal
2018-12-11 17:44   ` kbuild test robot
2018-12-15 19:22   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 23/52] fuse: simplify fuse_fill_super_common() calling Vivek Goyal
2018-12-10 17:12 ` [PATCH 24/52] fuse: Introduce setupmapping/removemapping commands Vivek Goyal
2018-12-10 17:12 ` [PATCH 25/52] Introduce interval tree basic data structures Vivek Goyal
2018-12-10 17:12 ` [PATCH 26/52] fuse: Implement basic DAX read/write support commands Vivek Goyal
2018-12-10 17:12 ` [PATCH 27/52] fuse: Maintain a list of busy elements Vivek Goyal
2018-12-10 17:12 ` [PATCH 28/52] Do fallocate() to grow file before mapping for file growing writes Vivek Goyal
2018-12-11  6:13   ` kbuild test robot
2018-12-11  6:20   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 29/52] fuse: add DAX mmap support Vivek Goyal
2018-12-10 17:12 ` [PATCH 30/52] fuse: delete dentry if timeout is zero Vivek Goyal
2018-12-10 17:12 ` [PATCH 31/52] dax: Pass dax_dev to dax_writeback_mapping_range() Vivek Goyal
2018-12-11  6:12   ` kbuild test robot
2018-12-11 17:38   ` kbuild test robot
2018-12-10 17:12 ` [PATCH 32/52] fuse: Define dax address space operations Vivek Goyal
2018-12-10 17:12 ` [PATCH 33/52] fuse, dax: Take ->i_mmap_sem lock during dax page fault Vivek Goyal
2018-12-10 17:13 ` [PATCH 34/52] fuse: Add logic to free up a memory range Vivek Goyal
2018-12-10 17:13 ` [PATCH 35/52] fuse: Add logic to do direct reclaim of memory Vivek Goyal
2018-12-10 17:13 ` [PATCH 36/52] fuse: Kick worker when free memory drops below 20% of total ranges Vivek Goyal
2018-12-10 17:13 ` [PATCH 37/52] fuse: multiplex cached/direct_io/dax file operations Vivek Goyal
2018-12-10 17:13 ` [PATCH 38/52] Dispatch FORGET requests later instead of dropping them Vivek Goyal
2018-12-10 17:13 ` [PATCH 39/52] Release file in process context Vivek Goyal
2018-12-10 17:13 ` [PATCH 40/52] fuse: Do not block on inode lock while freeing memory range Vivek Goyal
2018-12-10 17:13 ` [PATCH 41/52] fuse: Reschedule dax free work if too many EAGAIN attempts Vivek Goyal
2018-12-10 17:13 ` Vivek Goyal [this message]
2018-12-10 17:13 ` [PATCH 43/52] fuse: Take inode lock for dax inode truncation Vivek Goyal
2018-12-10 17:13 ` [PATCH 44/52] fuse: Clear setuid bit even in direct I/O path Vivek Goyal
2018-12-10 17:13 ` [PATCH 45/52] virtio: Free fuse devices on umount Vivek Goyal
2018-12-10 17:13 ` [PATCH 46/52] virtio-fs: Retrieve shm capabilities for version table Vivek Goyal
2018-12-10 17:13 ` [PATCH 47/52] virtio-fs: Map using the values from the capabilities Vivek Goyal
2018-12-10 17:13 ` [PATCH 48/52] virtio-fs: pass version table pointer to fuse Vivek Goyal
2018-12-10 17:13 ` [PATCH 49/52] fuse: don't crash if version table is NULL Vivek Goyal
2018-12-10 17:13 ` [PATCH 50/52] fuse: add shared version support (virtio-fs only) Vivek Goyal
2018-12-10 17:13 ` [PATCH 51/52] fuse: shared version cleanups Vivek Goyal
2018-12-10 17:13 ` [PATCH 52/52] fuse: fix fuse_permission() for the default_permissions case Vivek Goyal
2018-12-19 21:25   ` kbuild test robot
2018-12-11 12:54 ` [PATCH 00/52] [RFC] virtio-fs: shared file system for virtual machines Stefan Hajnoczi
2018-12-12 20:30 ` Konrad Rzeszutek Wilk
2018-12-12 21:22   ` Vivek Goyal
2019-02-12 15:56 ` Aneesh Kumar K.V
2019-02-12 18:57   ` Vivek Goyal

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20181210171318.16998-43-vgoyal@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    --cc=stefanha@redhat.com \
    --cc=sweil@redhat.com \
    --cc=swhiteho@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox