diff mbox series

[10/20] fuse,virtiofs: Keep a list of free dax memory ranges

Message ID 20200304165845.3081-11-vgoyal@redhat.com (mailing list archive)
State New, archived
Headers show
Series virtiofs: Add DAX support | expand

Commit Message

Vivek Goyal March 4, 2020, 4:58 p.m. UTC
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    | 22 ++++++++++++
 fs/fuse/inode.c     | 88 ++++++++++++++++++++++++++++++++++++++++++++-
 fs/fuse/virtio_fs.c |  2 ++
 3 files changed, 111 insertions(+), 1 deletion(-)

Comments

Miklos Szeredi March 10, 2020, 7:29 p.m. UTC | #1
On Wed, Mar 4, 2020 at 5:59 PM Vivek Goyal <vgoyal@redhat.com> wrote:
>
> 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>

Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
diff mbox series

Patch

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1fe5065a2902..edd3136c11f7 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -47,6 +47,10 @@ 
 /** Number of dentries for each connection in the control filesystem */
 #define FUSE_CTL_NUM_DENTRIES 5
 
+/* 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;
 
@@ -63,6 +67,18 @@  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 */
@@ -765,6 +781,12 @@  struct fuse_conn {
 
 	/** DAX device, non-NULL if DAX is supported */
 	struct dax_device *dax_dev;
+
+	/*
+	 * DAX Window Free Ranges
+	 */
+	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 84295fac4ff3..0ba092bf0b6d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -23,6 +23,8 @@ 
 #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");
@@ -600,6 +602,76 @@  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,
 		    const struct fuse_iqueue_ops *fiq_ops, void *fiq_priv)
 {
@@ -627,6 +699,7 @@  void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns,
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 	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);
 
@@ -635,6 +708,8 @@  void fuse_conn_put(struct fuse_conn *fc)
 	if (refcount_dec_and_test(&fc->count)) {
 		struct fuse_iqueue *fiq = &fc->iq;
 
+		if (fc->dax_dev)
+			fuse_free_dax_mem_ranges(&fc->free_ranges);
 		if (fiq->ops->release)
 			fiq->ops->release(fiq);
 		put_pid_ns(fc->pid_ns);
@@ -1160,9 +1235,17 @@  int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 	if (sb->s_user_ns != &init_user_ns)
 		sb->s_xattr = fuse_no_acl_xattr_handlers;
 
+	if (ctx->dax_dev) {
+		err = fuse_dax_mem_range_init(fc, ctx->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;
+		goto err_free_ranges;
 
 	fc->dev = sb->s_dev;
 	fc->sb = sb;
@@ -1218,6 +1301,9 @@  int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 	dput(root_dentry);
  err_dev_free:
 	fuse_dev_free(fud);
+ err_free_ranges:
+	if (ctx->dax_dev)
+		fuse_free_dax_mem_ranges(&fc->free_ranges);
  err:
 	return err;
 }
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index b0574b208cd5..8423b674c81e 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -710,6 +710,8 @@  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)