Merge commit 'osd/linux-next'

Documentation/filesystems/00-INDEX

@@ -36,6 +36,8 @@ dnotify.txt
 	- info about directory notification in Linux.
 ecryptfs.txt
 	- docs on eCryptfs: stacked cryptographic filesystem for Linux.
+exofs.txt
+	- info, usage, mount options, design about EXOFS.
 ext2.txt
 	- info, mount options and specifications for the Ext2 filesystem.
 ext3.txt

Documentation/filesystems/exofs.txt

@@ -60,13 +60,13 @@ USAGE
 
    mkfs.exofs --pid=65536 --format /dev/osd0
 
-   The --format is optional if not specified no OSD_FORMAT will be
-   preformed and a clean file system will be created in the specified pid,
+   The --format is optional. If not specified, no OSD_FORMAT will be
+   performed and a clean file system will be created in the specified pid,
    in the available space of the target. (Use --format=size_in_meg to limit
    the total LUN space available)
 
-   If pid already exist it will be deleted and a new one will be created in it's
-   place. Be careful.
+   If pid already exists, it will be deleted and a new one will be created in
+   its place. Be careful.
 
    An exofs lives inside a single OSD partition. You can create multiple exofs
    filesystems on the same device using multiple pids.
@@ -104,8 +104,8 @@ Where:
     exofs specific options: Options are separated by commas (,)
 		pid=<integer> - The partition number to mount/create as
                                 container of the filesystem.
-                                This option is mandatory
-                to=<integer>  - Timeout in ticks for a single command
+                                This option is mandatory.
+                to=<integer>  - Timeout in ticks for a single command.
                                 default is (60 * HZ) [for debugging only]
 
 ===============================================================================
@@ -116,7 +116,7 @@ DESIGN
   with a special ID (defined in common.h).
   Information included in the file system control block is used to fill the
   in-memory superblock structure at mount time. This object is created before
-  the file system is used by mkexofs.c It contains information such as:
+  the file system is used by mkexofs.c. It contains information such as:
 	- The file system's magic number
 	- The next inode number to be allocated
 
@@ -134,8 +134,8 @@ DESIGN
   attributes. This applies to both regular files and other types (directories,
   device files, symlinks, etc.).
 
-* Credentials are generated per object (inode and superblock) when they is
-  created in memory (read off disk or created). The credential works for all
+* Credentials are generated per object (inode and superblock) when they are
+  created in memory (read from disk or created). The credential works for all
   operations and is used as long as the object remains in memory.
 
 * Async OSD operations are used whenever possible, but the target may execute
@@ -145,7 +145,8 @@ DESIGN
   from executing in reverse order:
 	- The following are handled with the OBJ_CREATED and OBJ_2BCREATED
 	  flags. OBJ_CREATED is set when we know the object exists on the OSD -
-	  in create's callback function, and when we successfully do a read_inode.
+	  in create's callback function, and when we successfully do a
+	  read_inode.
 	  OBJ_2BCREATED is set in the beginning of the create function, so we
 	  know that we should wait.
 		- create/delete: delete should wait until the object is created

drivers/scsi/osd/osd_initiator.c

@@ -73,7 +73,8 @@ static const char *_osd_ver_desc(struct osd_request *or)
 
 #define ATTR_DEF_RI(id, len) ATTR_DEF(OSD_APAGE_ROOT_INFORMATION, id, len)
 
-static int _osd_print_system_info(struct osd_dev *od, void *caps)
+static int _osd_get_print_system_info(struct osd_dev *od,
+	void *caps, struct osd_dev_info *odi)
 {
 	struct osd_request *or;
 	struct osd_attr get_attrs[] = {
@@ -137,8 +138,13 @@ static int _osd_print_system_info(struct osd_dev *od, void *caps)
 	OSD_INFO("PRODUCT_SERIAL_NUMBER  [%s]\n",
 		(char *)pFirst);
 
-	pFirst = get_attrs[a].val_ptr;
-	OSD_INFO("OSD_NAME               [%s]\n", (char *)pFirst);
+	odi->osdname_len = get_attrs[a].len;
+	if (odi->osdname_len) {
+		odi->osdname = kzalloc(odi->osdname_len + 1, GFP_KERNEL);
+		memcpy(odi->osdname, get_attrs[a].val_ptr, odi->osdname_len);
+	} else
+		odi->osdname = NULL;
+	OSD_INFO("OSD_NAME               [%s]\n", odi->osdname);
 	a++;
 
 	pFirst = get_attrs[a++].val_ptr;
@@ -171,6 +177,9 @@ static int _osd_print_system_info(struct osd_dev *od, void *caps)
 				   sid_dump, sizeof(sid_dump), true);
 		OSD_INFO("OSD_SYSTEM_ID(%d)\n"
 			 "        [%s]\n", len, sid_dump);
+
+		odi->systemid_len = len;
+		memcpy(odi->systemid, get_attrs[a].val_ptr, len);
 		a++;
 	}
 out:
@@ -178,16 +187,17 @@ out:
 	return ret;
 }
 
-int osd_auto_detect_ver(struct osd_dev *od, void *caps)
+int osd_auto_detect_ver(struct osd_dev *od,
+	void *caps, struct osd_dev_info *odi)
 {
 	int ret;
 
 	/* Auto-detect the osd version */
-	ret = _osd_print_system_info(od, caps);
+	ret = _osd_get_print_system_info(od, caps, odi);
 	if (ret) {
 		osd_dev_set_ver(od, OSD_VER1);
 		OSD_DEBUG("converting to OSD1\n");
-		ret = _osd_print_system_info(od, caps);
+		ret = _osd_get_print_system_info(od, caps, odi);
 	}
 
 	return ret;

drivers/scsi/osd/osd_uld.c

@@ -87,6 +87,7 @@ struct osd_uld_device {
 	struct osd_dev od;
 	struct gendisk *disk;
 	struct device *class_member;
+	struct osd_dev_info odi;
 };
 
 static void __uld_get(struct osd_uld_device *oud);
@@ -216,6 +217,48 @@ free_od:
 }
 EXPORT_SYMBOL(osduld_path_lookup);
 
+static inline bool _the_same_or_null(const u8 *a1, unsigned a1_len,
+				     const u8 *a2, unsigned a2_len)
+{
+	if (!a2_len) /* User string is Empty means don't care */
+		return true;
+
+	if (a1_len != a2_len)
+		return false;
+
+	return 0 == memcmp(a1, a2, a1_len);
+}
+
+struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi)
+{
+	unsigned i;
+
+	for (i = 0; i < SCSI_OSD_MAX_MINOR; i++) {
+		char dev_str[16];
+		struct osd_uld_device *oud;
+		struct osd_dev *od;
+
+		sprintf(dev_str, "/dev/osd%d", i);
+		od = osduld_path_lookup(dev_str);
+		if (IS_ERR(od))
+			continue;
+
+		oud = od->file->private_data;
+		if (_the_same_or_null(oud->odi.systemid, oud->odi.systemid_len,
+				      odi->systemid, odi->systemid_len) &&
+		    _the_same_or_null(oud->odi.osdname, oud->odi.osdname_len,
+				      odi->osdname, odi->osdname_len)) {
+			OSD_DEBUG("found device sysid_len=%d osdname=%d\n",
+				  odi->systemid_len, odi->osdname_len);
+			return od;
+		}
+		osduld_put_device(od);
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL(osduld_info_lookup);
+
 void osduld_put_device(struct osd_dev *od)
 {
 
@@ -230,6 +273,13 @@ void osduld_put_device(struct osd_dev *od)
 }
 EXPORT_SYMBOL(osduld_put_device);
 
+const struct osd_dev_info *osduld_device_info(struct osd_dev *od)
+{
+	struct osd_uld_device *oud = od->file->private_data;
+	return &oud->odi;
+}
+EXPORT_SYMBOL(osduld_device_info);
+
 /*
  * Scsi Device operations
  */
@@ -250,7 +300,7 @@ static int __detect_osd(struct osd_uld_device *oud)
 		OSD_ERR("warning: scsi_test_unit_ready failed\n");
 
 	osd_sec_init_nosec_doall_caps(caps, &osd_root_object, false, true);
-	if (osd_auto_detect_ver(&oud->od, caps))
+	if (osd_auto_detect_ver(&oud->od, caps, &oud->odi))
 		return -ENODEV;
 
 	return 0;
@@ -402,6 +452,7 @@ static void __remove(struct kref *kref)
 		put_disk(oud->disk);
 
 	ida_remove(&osd_minor_ida, oud->minor);
+	kfree(oud->odi.osdname);
 	kfree(oud);
 }
 

fs/exofs/inode.c

@@ -906,6 +906,12 @@ out:
 	return ret;
 }
 
+
+static void __oi_init(struct exofs_i_info *oi)
+{
+	init_waitqueue_head(&oi->i_wq);
+	oi->i_flags = 0;
+}
 /*
  * Fill in an inode read from the OSD and set it up for use
  */
@@ -923,13 +929,13 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 	if (!(inode->i_state & I_NEW))
 		return inode;
 	oi = exofs_i(inode);
+	__oi_init(oi);
 
 	/* read the inode from the osd */
 	ret = exofs_get_inode(sb, oi, &fcb, &sanity);
 	if (ret)
 		goto bad_inode;
 
-	init_waitqueue_head(&oi->i_wq);
 	set_obj_created(oi);
 
 	/* copy stuff from on-disk struct to in-memory struct */
@@ -950,8 +956,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 #ifdef EXOFS_DEBUG_OBJ_ISIZE
 	if ((inode->i_size != sanity) &&
 		(!exofs_inode_is_fast_symlink(inode))) {
-		EXOFS_ERR("WARNING: Size of object from inode and "
-			  "attributes differ (%lld != %llu)\n",
+		EXOFS_ERR("WARNING: Size of inode=%llu != object=%llu\n",
 			  inode->i_size, _LLU(sanity));
 	}
 #endif
@@ -1061,8 +1066,8 @@ struct inode *exofs_new_inode(struct inode *dir, int mode)
 		return ERR_PTR(-ENOMEM);
 
 	oi = exofs_i(inode);
+	__oi_init(oi);
 
-	init_waitqueue_head(&oi->i_wq);
 	set_obj_2bcreated(oi);
 
 	sbi = sb->s_fs_info;

fs/exofs/super.c

@@ -214,7 +214,6 @@ int exofs_sync_fs(struct super_block *sb, int wait)
 	}
 
 	lock_super(sb);
-	lock_kernel();
 	sbi = sb->s_fs_info;
 	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
 	fscb->s_numfiles = cpu_to_le32(sbi->s_numfiles);
@@ -245,7 +244,6 @@ int exofs_sync_fs(struct super_block *sb, int wait)
 out:
 	if (or)
 		osd_end_request(or);
-	unlock_kernel();
 	unlock_super(sb);
 	kfree(fscb);
 	return ret;
@@ -259,6 +257,15 @@ static void exofs_write_super(struct super_block *sb)
 		sb->s_dirt = 0;
 }
 
+static void _exofs_print_device(const char *msg, const char *dev_path,
+				struct osd_dev *od, u64 pid)
+{
+	const struct osd_dev_info *odi = osduld_device_info(od);
+
+	printk(KERN_NOTICE "exofs: %s %s osd_name-%s pid-0x%llx\n",
+		msg, dev_path ?: "", odi->osdname, _LLU(pid));
+}
+
 /*
  * This function is called when the vfs is freeing the superblock.  We just
  * need to free our own part.
@@ -268,8 +275,6 @@ static void exofs_put_super(struct super_block *sb)
 	int num_pend;
 	struct exofs_sb_info *sbi = sb->s_fs_info;
 
-	lock_kernel();
-
 	if (sb->s_dirt)
 		exofs_write_super(sb);
 
@@ -283,11 +288,10 @@ static void exofs_put_super(struct super_block *sb)
 				  msecs_to_jiffies(100));
 	}
 
+	_exofs_print_device("Unmounting", NULL, sbi->s_dev, sbi->s_pid);
 	osduld_put_device(sbi->s_dev);
 	kfree(sb->s_fs_info);
 	sb->s_fs_info = NULL;
-
-	unlock_kernel();
 }
 
 /*
@@ -401,6 +405,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
+	_exofs_print_device("Mounting", opts->dev_name, sbi->s_dev, sbi->s_pid);
 	ret = 0;
 out:
 	if (or)

include/scsi/osd_initiator.h

@@ -56,10 +56,23 @@ struct osd_dev {
 #endif
 };
 
-/* Retrieve/return osd_dev(s) for use by Kernel clients */
-struct osd_dev *osduld_path_lookup(const char *dev_name); /*Use IS_ERR/ERR_PTR*/
+/* Unique Identification of an OSD device */
+struct osd_dev_info {
+	unsigned systemid_len;
+	u8 systemid[OSD_SYSTEMID_LEN];
+	unsigned osdname_len;
+	u8 *osdname;
+};
+
+/* Retrieve/return osd_dev(s) for use by Kernel clients
+ * Use IS_ERR/ERR_PTR on returned "osd_dev *".
+ */
+struct osd_dev *osduld_path_lookup(const char *dev_name);
+struct osd_dev *osduld_info_lookup(const struct osd_dev_info *odi);
 void osduld_put_device(struct osd_dev *od);
 
+const struct osd_dev_info *osduld_device_info(struct osd_dev *od);
+
 /* Add/remove test ioctls from external modules */
 typedef int (do_test_fn)(struct osd_dev *od, unsigned cmd, unsigned long arg);
 int osduld_register_test(unsigned ioctl, do_test_fn *do_test);
@@ -69,8 +82,24 @@ void osduld_unregister_test(unsigned ioctl);
 void osd_dev_init(struct osd_dev *od, struct scsi_device *scsi_device);
 void osd_dev_fini(struct osd_dev *od);
 
-/* some hi level device operations */
-int osd_auto_detect_ver(struct osd_dev *od, void *caps);    /* GFP_KERNEL */
+/**
+ * osd_auto_detect_ver - Detect the OSD version, return Unique Identification
+ *
+ * @od:     OSD target lun handle
+ * @caps:   Capabilities authorizing OSD root read attributes access
+ * @odi:    Retrieved information uniquely identifying the osd target lun
+ *          Note: odi->osdname must be kfreed by caller.
+ *
+ * Auto detects the OSD version of the OSD target and sets the @od
+ * accordingly. Meanwhile also returns the "system id" and "osd name" root
+ * attributes which uniquely identify the OSD target. This member is usually
+ * called by the ULD. ULD users should call osduld_device_info().
+ * This rutine allocates osd requests and memory at GFP_KERNEL level and might
+ * sleep.
+ */
+int osd_auto_detect_ver(struct osd_dev *od,
+	void *caps, struct osd_dev_info *odi);
+
 static inline struct request_queue *osd_request_queue(struct osd_dev *od)
 {
 	return od->scsi_device->request_queue;
@@ -84,6 +113,15 @@ static inline void osd_dev_set_ver(struct osd_dev *od, enum osd_std_version v)
 #endif
 }
 
+static inline bool osd_dev_is_ver1(struct osd_dev *od)
+{
+#ifdef OSD_VER1_SUPPORT
+	return od->version == OSD_VER1;
+#else
+	return false;
+#endif
+}
+
 struct osd_request;
 typedef void (osd_req_done_fn)(struct osd_request *or, void *private);
 
@@ -120,14 +158,9 @@ struct osd_request {
 	int async_error;
 };
 
-/* OSD Version control */
 static inline bool osd_req_is_ver1(struct osd_request *or)
 {
-#ifdef OSD_VER1_SUPPORT
-	return or->osd_dev->version == OSD_VER1;
-#else
-	return false;
-#endif
+	return osd_dev_is_ver1(or->osd_dev);
 }
 
 /*

include/scsi/osd_sense.h

@@ -255,6 +255,9 @@ enum osdv2_cdb_field_offset {
 	OSD_CFO_STARTING_BYTE	= OSD_CDB_OFFSET(v2.start_address),
 	OSD_CFO_PARTITION_ID	= OSD_CDB_OFFSET(partition),
 	OSD_CFO_OBJECT_ID	= OSD_CDB_OFFSET(object),
+	OSD_CFO_PERMISSIONS	= sizeof(struct osd_cdb_head) +
+					offsetof(struct osd_capability_head,
+						 permissions_bit_mask),
 };
 
 #endif /* ndef __OSD_SENSE_H__ */