Linux-NVDIMM Archive on lore.kernel.org
 help / color / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: miklos@szeredi.hu, dgilbert@redhat.com,
	Peng Tao <tao.peng@linux.alibaba.com>,
	virtio-fs@redhat.com, stefanha@redhat.com
Subject: [PATCH 08/19] fuse: Keep a list of free dax memory ranges
Date: Wed, 21 Aug 2019 13:57:09 -0400
Message-ID: <20190821175720.25901-9-vgoyal@redhat.com> (raw)
In-Reply-To: <20190821175720.25901-1-vgoyal@redhat.com>

Divide the dax memory range into fixed size ranges (2MB for now) and put
them in a list. This will track free ranges. Once an inode requires a
free range, we will take one from here and put it in interval-tree
of ranges assigned to inode.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Peng Tao <tao.peng@linux.alibaba.com>
---
 fs/fuse/fuse_i.h    | 23 ++++++++++++
 fs/fuse/inode.c     | 86 +++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/virtio_fs.c |  2 ++
 3 files changed, 111 insertions(+)

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7b365a29b156..f1059b51c539 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -50,6 +50,10 @@
 /** Number of page pointers embedded in fuse_req */
 #define FUSE_REQ_INLINE_PAGES 1
 
+/* Default memory range size, 2MB */
+#define FUSE_DAX_MEM_RANGE_SZ	(2*1024*1024)
+#define FUSE_DAX_MEM_RANGE_PAGES	(FUSE_DAX_MEM_RANGE_SZ/PAGE_SIZE)
+
 /** List of active connections */
 extern struct list_head fuse_conn_list;
 
@@ -97,6 +101,18 @@ struct fuse_forget_link {
 	struct fuse_forget_link *next;
 };
 
+/** Translation information for file offsets to DAX window offsets */
+struct fuse_dax_mapping {
+	/* Will connect in fc->free_ranges to keep track of free memory */
+	struct list_head list;
+
+	/** Position in DAX window */
+	u64 window_offset;
+
+	/** Length of mapping, in bytes */
+	loff_t length;
+};
+
 /** FUSE inode */
 struct fuse_inode {
 	/** Inode data */
@@ -838,6 +854,13 @@ struct fuse_conn {
 
 	/** DAX device, non-NULL if DAX is supported */
 	struct dax_device *dax_dev;
+
+	/*
+	 * DAX Window Free Ranges. TODO: This might not be best place to store
+	 * this free list
+	 */
+	long nr_free_ranges;
+	struct list_head free_ranges;
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 0f58107a8269..0af147c70558 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -22,6 +22,8 @@
 #include <linux/exportfs.h>
 #include <linux/posix_acl.h>
 #include <linux/pid_namespace.h>
+#include <linux/dax.h>
+#include <linux/pfn_t.h>
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -598,6 +600,76 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq)
 	fpq->connected = 1;
 }
 
+static void fuse_free_dax_mem_ranges(struct list_head *mem_list)
+{
+	struct fuse_dax_mapping *range, *temp;
+
+	/* Free All allocated elements */
+	list_for_each_entry_safe(range, temp, mem_list, list) {
+		list_del(&range->list);
+		kfree(range);
+	}
+}
+
+#ifdef CONFIG_FS_DAX
+static int fuse_dax_mem_range_init(struct fuse_conn *fc,
+				   struct dax_device *dax_dev)
+{
+	long nr_pages, nr_ranges;
+	void *kaddr;
+	pfn_t pfn;
+	struct fuse_dax_mapping *range;
+	LIST_HEAD(mem_ranges);
+	phys_addr_t phys_addr;
+	int ret = 0, id;
+	size_t dax_size = -1;
+	unsigned long i;
+
+	id = dax_read_lock();
+	nr_pages = dax_direct_access(dax_dev, 0, PHYS_PFN(dax_size), &kaddr,
+					&pfn);
+	dax_read_unlock(id);
+	if (nr_pages < 0) {
+		pr_debug("dax_direct_access() returned %ld\n", nr_pages);
+		return nr_pages;
+	}
+
+	phys_addr = pfn_t_to_phys(pfn);
+	nr_ranges = nr_pages/FUSE_DAX_MEM_RANGE_PAGES;
+	printk("fuse_dax_mem_range_init(): dax mapped %ld pages. nr_ranges=%ld\n", nr_pages, nr_ranges);
+
+	for (i = 0; i < nr_ranges; i++) {
+		range = kzalloc(sizeof(struct fuse_dax_mapping), GFP_KERNEL);
+		if (!range) {
+			pr_debug("memory allocation for mem_range failed.\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		/* TODO: This offset only works if virtio-fs driver is not
+		 * having some memory hidden at the beginning. This needs
+		 * better handling
+		 */
+		range->window_offset = i * FUSE_DAX_MEM_RANGE_SZ;
+		range->length = FUSE_DAX_MEM_RANGE_SZ;
+		list_add_tail(&range->list, &mem_ranges);
+	}
+
+	list_replace_init(&mem_ranges, &fc->free_ranges);
+	fc->nr_free_ranges = nr_ranges;
+	return 0;
+out_err:
+	/* Free All allocated elements */
+	fuse_free_dax_mem_ranges(&mem_ranges);
+	return ret;
+}
+#else /* !CONFIG_FS_DAX */
+static inline int fuse_dax_mem_range_init(struct fuse_conn *fc,
+					  struct dax_device *dax_dev)
+{
+	return 0;
+}
+#endif /* CONFIG_FS_DAX */
+
 void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
 			struct dax_device *dax_dev,
 			const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv)
@@ -628,6 +700,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
 	fc->dax_dev = dax_dev;
 	fc->user_ns = get_user_ns(user_ns);
 	fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
+	INIT_LIST_HEAD(&fc->free_ranges);
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
@@ -636,6 +709,8 @@ void fuse_conn_put(struct fuse_conn *fc)
 	if (refcount_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
+		if (fc->dax_dev)
+			fuse_free_dax_mem_ranges(&fc->free_ranges);
 		put_pid_ns(fc->pid_ns);
 		put_user_ns(fc->user_ns);
 		fc->release(fc);
@@ -1147,6 +1222,14 @@ int fuse_fill_super_common(struct super_block *sb,
 		fc->release = fuse_free_conn;
 	}
 
+	if (mount_data->dax_dev) {
+		err = fuse_dax_mem_range_init(fc, mount_data->dax_dev);
+		if (err) {
+			pr_debug("fuse_dax_mem_range_init() returned %d\n", err);
+			goto err_free_ranges;
+		}
+	}
+
 	fud = fuse_dev_alloc_install(fc);
 	if (!fud)
 		goto err_put_conn;
@@ -1208,6 +1291,9 @@ int fuse_fill_super_common(struct super_block *sb,
 	dput(root_dentry);
  err_dev_free:
 	fuse_dev_free(fud);
+ err_free_ranges:
+	if (mount_data->dax_dev)
+		fuse_free_dax_mem_ranges(&fc->free_ranges);
  err_put_conn:
 	fuse_conn_put(fc);
 	sb->s_fs_info = NULL;
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 32604722a7fb..9198c2b84677 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -453,6 +453,8 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	phys_addr_t offset = PFN_PHYS(pgoff);
 	size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
 
+	pr_debug("virtio_fs_direct_access(): called. nr_pages=%ld max_nr_pages=%zu\n", nr_pages, max_nr_pages);
+
 	if (kaddr)
 		*kaddr = fs->window_kaddr + offset;
 	if (pfn)
-- 
2.20.1

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply index

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-21 17:57 [PATCH v3 00/19][RFC] virtio-fs: Enable DAX support Vivek Goyal
2019-08-21 17:57 ` [PATCH 01/19] dax: remove block device dependencies Vivek Goyal
2019-08-26 11:51   ` Christoph Hellwig
2019-08-27 16:38     ` Vivek Goyal
2019-08-28  6:58       ` Christoph Hellwig
2019-08-28 17:58         ` Vivek Goyal
2019-08-28 22:53           ` Dave Chinner
2019-08-29  0:04             ` Dan Williams
2019-08-29  9:32               ` Christoph Hellwig
2019-12-16 18:10               ` Vivek Goyal
2020-01-07 12:51                 ` Christoph Hellwig
2020-01-07 14:22                   ` Dan Williams
2020-01-07 17:07                     ` Darrick J. Wong
2020-01-07 17:29                       ` Dan Williams
2020-01-07 18:01                         ` Vivek Goyal
2020-01-07 18:07                           ` Dan Williams
2020-01-07 18:33                             ` Vivek Goyal
2020-01-07 18:49                               ` Dan Williams
2020-01-07 19:02                                 ` Darrick J. Wong
2020-01-07 19:46                                   ` Dan Williams
2020-01-07 23:38                                     ` Dan Williams
2020-01-09 11:24                                 ` Jan Kara
2020-01-09 20:03                                   ` Dan Williams
2020-01-10 12:36                                     ` Christoph Hellwig
2020-01-14 20:31                                     ` Vivek Goyal
2020-01-14 20:39                                       ` Dan Williams
2020-01-14 21:28                                         ` Vivek Goyal
2020-01-14 22:23                                           ` Dan Williams
2020-01-15 19:56                                             ` Vivek Goyal
2020-01-15 20:17                                               ` Dan Williams
2020-01-15 21:08                                                 ` Jeff Moyer
2020-01-16 18:09                                                   ` Dan Williams
2020-01-16 18:39                                                     ` Vivek Goyal
2020-01-16 19:09                                                       ` Dan Williams
2020-01-16 19:23                                                         ` Vivek Goyal
2020-02-11 17:33                                                     ` Vivek Goyal
2020-01-15  9:03                                           ` Jan Kara
2019-08-21 17:57 ` [PATCH 02/19] dax: Pass dax_dev to dax_writeback_mapping_range() Vivek Goyal
2019-08-26 11:53   ` Christoph Hellwig
2019-08-26 20:33     ` Vivek Goyal
2019-08-26 20:58       ` Vivek Goyal
2019-08-26 21:33         ` Dan Williams
2019-08-28  6:58         ` Christoph Hellwig
2020-01-03 14:12         ` Vivek Goyal
2020-01-03 18:12           ` Dan Williams
2020-01-03 18:18             ` Dan Williams
2020-01-03 18:33               ` Vivek Goyal
2020-01-03 19:30                 ` Dan Williams
2020-01-03 18:43               ` Vivek Goyal
2019-08-27 13:45       ` Jan Kara
2019-08-21 17:57 ` [PATCH 03/19] virtio: Add get_shm_region method Vivek Goyal
2019-08-21 17:57 ` [PATCH 04/19] virtio: Implement get_shm_region for PCI transport Vivek Goyal
2019-08-26  1:43   ` [Virtio-fs] " piaojun
2019-08-26 13:06     ` Vivek Goyal
2019-08-27  9:41       ` piaojun
2019-08-27  8:34   ` Cornelia Huck
2019-08-27  8:46     ` Cornelia Huck
2019-08-27 11:53     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 05/19] virtio: Implement get_shm_region for MMIO transport Vivek Goyal
2019-08-27  8:39   ` Cornelia Huck
2019-08-27 11:54     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 06/19] fuse, dax: add fuse_conn->dax_dev field Vivek Goyal
2019-08-21 17:57 ` [PATCH 07/19] virtio_fs, dax: Set up virtio_fs dax_device Vivek Goyal
2019-08-21 17:57 ` Vivek Goyal [this message]
2019-08-21 17:57 ` [PATCH 09/19] fuse: implement FUSE_INIT map_alignment field Vivek Goyal
2019-08-21 17:57 ` [PATCH 10/19] fuse: Introduce setupmapping/removemapping commands Vivek Goyal
2019-08-21 17:57 ` [PATCH 11/19] fuse, dax: Implement dax read/write operations Vivek Goyal
2019-08-21 19:49   ` Liu Bo
2019-08-22 12:59     ` Vivek Goyal
2019-08-21 17:57 ` [PATCH 12/19] fuse, dax: add DAX mmap support Vivek Goyal
2019-08-21 17:57 ` [PATCH 13/19] fuse: Define dax address space operations Vivek Goyal
2019-08-21 17:57 ` [PATCH 14/19] fuse, dax: Take ->i_mmap_sem lock during dax page fault Vivek Goyal
2019-08-21 17:57 ` [PATCH 15/19] fuse: Maintain a list of busy elements Vivek Goyal
2019-08-21 17:57 ` [PATCH 16/19] dax: Create a range version of dax_layout_busy_page() Vivek Goyal
2019-08-21 17:57 ` [PATCH 17/19] fuse: Add logic to free up a memory range Vivek Goyal
2019-08-21 17:57 ` [PATCH 18/19] fuse: Release file in process context Vivek Goyal
2019-08-21 17:57 ` [PATCH 19/19] fuse: Take inode lock for dax inode truncation 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=20190821175720.25901-9-vgoyal@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=miklos@szeredi.hu \
    --cc=stefanha@redhat.com \
    --cc=tao.peng@linux.alibaba.com \
    --cc=virtio-fs@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

Linux-NVDIMM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvdimm/0 linux-nvdimm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvdimm linux-nvdimm/ https://lore.kernel.org/linux-nvdimm \
		linux-nvdimm@lists.01.org
	public-inbox-index linux-nvdimm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.01.lists.linux-nvdimm


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