Merge tag 'ceph-for-5.17-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "The highlight is the new mount "device" string syntax implemented by
  Venky Shankar. It solves some long-standing issues with using
  different auth entities and/or mounting different CephFS filesystems
  from the same cluster, remounting and also misleading /proc/mounts
  contents. The existing syntax of course remains to be maintained.

  On top of that, there is a couple of fixes for edge cases in quota and
  a new mount option for turning on unbuffered I/O mode globally instead
  of on a per-file basis with ioctl(CEPH_IOC_SYNCIO)"

* tag 'ceph-for-5.17-rc1' of git://github.com/ceph/ceph-client:
  ceph: move CEPH_SUPER_MAGIC definition to magic.h
  ceph: remove redundant Lsx caps check
  ceph: add new "nopagecache" option
  ceph: don't check for quotas on MDS stray dirs
  ceph: drop send metrics debug message
  rbd: make const pointer spaces a static const array
  ceph: Fix incorrect statfs report for small quota
  ceph: mount syntax module parameter
  doc: document new CephFS mount device syntax
  ceph: record updated mon_addr on remount
  ceph: new device mount syntax
  libceph: rename parse_fsid() to ceph_parse_fsid() and export
  libceph: generalize addr/ip parsing based on delimiter

1 files changed, 159 insertions, 10 deletions

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bea89bdb534a..bf79f369aec6 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,8 @@
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
 
+#include <uapi/linux/magic.h>
+
 static DEFINE_SPINLOCK(ceph_fsc_lock);
 static LIST_HEAD(ceph_fsc_list);
 
@@ -146,6 +148,7 @@ enum {
 	Opt_mds_namespace,
 	Opt_recover_session,
 	Opt_source,
+	Opt_mon_addr,
 	/* string args above */
 	Opt_dirstat,
 	Opt_rbytes,
@@ -159,6 +162,7 @@ enum {
 	Opt_quotadf,
 	Opt_copyfrom,
 	Opt_wsync,
+	Opt_pagecache,
 };
 
 enum ceph_recover_session_mode {
@@ -197,8 +201,10 @@ static const struct fs_parameter_spec ceph_mount_parameters[] = {
 	fsparam_u32	("rsize",			Opt_rsize),
 	fsparam_string	("snapdirname",			Opt_snapdirname),
 	fsparam_string	("source",			Opt_source),
+	fsparam_string	("mon_addr",			Opt_mon_addr),
 	fsparam_u32	("wsize",			Opt_wsize),
 	fsparam_flag_no	("wsync",			Opt_wsync),
+	fsparam_flag_no	("pagecache",			Opt_pagecache),
 	{}
 };
 
@@ -228,9 +234,92 @@ static void canonicalize_path(char *path)
 }
 
 /*
- * Parse the source parameter.  Distinguish the server list from the path.
+ * Check if the mds namespace in ceph_mount_options matches
+ * the passed in namespace string. First time match (when
+ * ->mds_namespace is NULL) is treated specially, since
+ * ->mds_namespace needs to be initialized by the caller.
+ */
+static int namespace_equals(struct ceph_mount_options *fsopt,
+			    const char *namespace, size_t len)
+{
+	return !(fsopt->mds_namespace &&
+		 (strlen(fsopt->mds_namespace) != len ||
+		  strncmp(fsopt->mds_namespace, namespace, len)));
+}
+
+static int ceph_parse_old_source(const char *dev_name, const char *dev_name_end,
+				 struct fs_context *fc)
+{
+	int r;
+	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+	struct ceph_mount_options *fsopt = pctx->opts;
+
+	if (*dev_name_end != ':')
+		return invalfc(fc, "separator ':' missing in source");
+
+	r = ceph_parse_mon_ips(dev_name, dev_name_end - dev_name,
+			       pctx->copts, fc->log.log, ',');
+	if (r)
+		return r;
+
+	fsopt->new_dev_syntax = false;
+	return 0;
+}
+
+static int ceph_parse_new_source(const char *dev_name, const char *dev_name_end,
+				 struct fs_context *fc)
+{
+	size_t len;
+	struct ceph_fsid fsid;
+	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+	struct ceph_mount_options *fsopt = pctx->opts;
+	char *fsid_start, *fs_name_start;
+
+	if (*dev_name_end != '=') {
+		dout("separator '=' missing in source");
+		return -EINVAL;
+	}
+
+	fsid_start = strchr(dev_name, '@');
+	if (!fsid_start)
+		return invalfc(fc, "missing cluster fsid");
+	++fsid_start; /* start of cluster fsid */
+
+	fs_name_start = strchr(fsid_start, '.');
+	if (!fs_name_start)
+		return invalfc(fc, "missing file system name");
+
+	if (ceph_parse_fsid(fsid_start, &fsid))
+		return invalfc(fc, "Invalid FSID");
+
+	++fs_name_start; /* start of file system name */
+	len = dev_name_end - fs_name_start;
+
+	if (!namespace_equals(fsopt, fs_name_start, len))
+		return invalfc(fc, "Mismatching mds_namespace");
+	kfree(fsopt->mds_namespace);
+	fsopt->mds_namespace = kstrndup(fs_name_start, len, GFP_KERNEL);
+	if (!fsopt->mds_namespace)
+		return -ENOMEM;
+	dout("file system (mds namespace) '%s'\n", fsopt->mds_namespace);
+
+	fsopt->new_dev_syntax = true;
+	return 0;
+}
+
+/*
+ * Parse the source parameter for new device format. Distinguish the device
+ * spec from the path. Try parsing new device format and fallback to old
+ * format if needed.
+ *
+ * New device syntax will looks like:
+ *     <device_spec>=/<path>
+ * where
+ *     <device_spec> is name@fsid.fsname
+ *     <path> is optional, but if present must begin with '/'
+ * (monitor addresses are passed via mount option)
  *
- * The source will look like:
+ * Old device syntax is:
  *     <server_spec>[,<server_spec>...]:[<path>]
  * where
  *     <server_spec> is <ip>[:<port>]
@@ -263,24 +352,44 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc)
 		dev_name_end = dev_name + strlen(dev_name);
 	}
 
-	dev_name_end--;		/* back up to ':' separator */
-	if (dev_name_end < dev_name || *dev_name_end != ':')
-		return invalfc(fc, "No path or : separator in source");
+	dev_name_end--;		/* back up to separator */
+	if (dev_name_end < dev_name)
+		return invalfc(fc, "Path missing in source");
 
 	dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
 	if (fsopt->server_path)
 		dout("server path '%s'\n", fsopt->server_path);
 
-	ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name,
-				 pctx->copts, fc->log.log);
-	if (ret)
-		return ret;
+	dout("trying new device syntax");
+	ret = ceph_parse_new_source(dev_name, dev_name_end, fc);
+	if (ret) {
+		if (ret != -EINVAL)
+			return ret;
+		dout("trying old device syntax");
+		ret = ceph_parse_old_source(dev_name, dev_name_end, fc);
+		if (ret)
+			return ret;
+	}
 
 	fc->source = param->string;
 	param->string = NULL;
 	return 0;
 }
 
+static int ceph_parse_mon_addr(struct fs_parameter *param,
+			       struct fs_context *fc)
+{
+	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+	struct ceph_mount_options *fsopt = pctx->opts;
+
+	kfree(fsopt->mon_addr);
+	fsopt->mon_addr = param->string;
+	param->string = NULL;
+
+	return ceph_parse_mon_ips(fsopt->mon_addr, strlen(fsopt->mon_addr),
+				  pctx->copts, fc->log.log, '/');
+}
+
 static int ceph_parse_mount_param(struct fs_context *fc,
 				  struct fs_parameter *param)
 {
@@ -306,6 +415,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		param->string = NULL;
 		break;
 	case Opt_mds_namespace:
+		if (!namespace_equals(fsopt, param->string, strlen(param->string)))
+			return invalfc(fc, "Mismatching mds_namespace");
 		kfree(fsopt->mds_namespace);
 		fsopt->mds_namespace = param->string;
 		param->string = NULL;
@@ -323,6 +434,8 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		if (fc->source)
 			return invalfc(fc, "Multiple sources specified");
 		return ceph_parse_source(param, fc);
+	case Opt_mon_addr:
+		return ceph_parse_mon_addr(param, fc);
 	case Opt_wsize:
 		if (result.uint_32 < PAGE_SIZE ||
 		    result.uint_32 > CEPH_MAX_WRITE_SIZE)
@@ -455,6 +568,12 @@ static int ceph_parse_mount_param(struct fs_context *fc,
 		else
 			fsopt->flags |= CEPH_MOUNT_OPT_ASYNC_DIROPS;
 		break;
+	case Opt_pagecache:
+		if (result.negated)
+			fsopt->flags |= CEPH_MOUNT_OPT_NOPAGECACHE;
+		else
+			fsopt->flags &= ~CEPH_MOUNT_OPT_NOPAGECACHE;
+		break;
 	default:
 		BUG();
 	}
@@ -474,6 +593,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
 	kfree(args->mds_namespace);
 	kfree(args->server_path);
 	kfree(args->fscache_uniq);
+	kfree(args->mon_addr);
 	kfree(args);
 }
 
@@ -517,6 +637,10 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
 	if (ret)
 		return ret;
 
+	ret = strcmp_null(fsopt1->mon_addr, fsopt2->mon_addr);
+	if (ret)
+		return ret;
+
 	return ceph_compare_options(new_opt, fsc->client);
 }
 
@@ -572,15 +696,22 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 	if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0)
 		seq_puts(m, ",copyfrom");
 
-	if (fsopt->mds_namespace)
+	/* dump mds_namespace when old device syntax is in use */
+	if (fsopt->mds_namespace && !fsopt->new_dev_syntax)
 		seq_show_option(m, "mds_namespace", fsopt->mds_namespace);
 
+	if (fsopt->mon_addr)
+		seq_printf(m, ",mon_addr=%s", fsopt->mon_addr);
+
 	if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER)
 		seq_show_option(m, "recover_session", "clean");
 
 	if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
 		seq_puts(m, ",wsync");
 
+	if (fsopt->flags & CEPH_MOUNT_OPT_NOPAGECACHE)
+		seq_puts(m, ",nopagecache");
+
 	if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
 		seq_printf(m, ",wsize=%u", fsopt->wsize);
 	if (fsopt->rsize != CEPH_MAX_READ_SIZE)
@@ -1052,6 +1183,7 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
 static int ceph_get_tree(struct fs_context *fc)
 {
 	struct ceph_parse_opts_ctx *pctx = fc->fs_private;
+	struct ceph_mount_options *fsopt = pctx->opts;
 	struct super_block *sb;
 	struct ceph_fs_client *fsc;
 	struct dentry *res;
@@ -1063,6 +1195,8 @@ static int ceph_get_tree(struct fs_context *fc)
 
 	if (!fc->source)
 		return invalfc(fc, "No source");
+	if (fsopt->new_dev_syntax && !fsopt->mon_addr)
+		return invalfc(fc, "No monitor address");
 
 	/* create client (which we may/may not use) */
 	fsc = create_fs_client(pctx->opts, pctx->copts);
@@ -1148,6 +1282,13 @@ static int ceph_reconfigure_fc(struct fs_context *fc)
 	else
 		ceph_clear_mount_opt(fsc, ASYNC_DIROPS);
 
+	if (strcmp_null(fsc->mount_options->mon_addr, fsopt->mon_addr)) {
+		kfree(fsc->mount_options->mon_addr);
+		fsc->mount_options->mon_addr = fsopt->mon_addr;
+		fsopt->mon_addr = NULL;
+		pr_notice("ceph: monitor addresses recorded, but not used for reconnection");
+	}
+
 	sync_filesystem(fc->root->d_sb);
 	return 0;
 }
@@ -1325,6 +1466,14 @@ bool disable_send_metrics = false;
 module_param_cb(disable_send_metrics, &param_ops_metrics, &disable_send_metrics, 0644);
 MODULE_PARM_DESC(disable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
 
+/* for both v1 and v2 syntax */
+static bool mount_support = true;
+static const struct kernel_param_ops param_ops_mount_syntax = {
+	.get = param_get_bool,
+};
+module_param_cb(mount_syntax_v1, &param_ops_mount_syntax, &mount_support, 0444);
+module_param_cb(mount_syntax_v2, &param_ops_mount_syntax, &mount_support, 0444);
+
 module_init(init_ceph);
 module_exit(exit_ceph);