1811 lines · 48.8 KB · C
RawDownload
#include <linux/ceph/ceph_debug.h> #include <linux/module.h>#include <linux/fs.h>#include <linux/slab.h>#include <linux/string.h>#include <linux/uaccess.h>#include <linux/kernel.h>#include <linux/namei.h>#include <linux/writeback.h>#include <linux/vmalloc.h> #include "super.h"#include "mds_client.h"#include <linux/ceph/decode.h> /* * Ceph inode operations * * Implement basic inode helpers (get, alloc) and inode ops (getattr, * setattr, etc.), xattr helpers, and helpers for assimilating * metadata returned by the MDS into our cache. * * Also define helpers for doing asynchronous writeback, invalidation, * and truncation for the benefit of those who can't afford to block * (typically because they are in the message handler path). */ static const struct inode_operations ceph_symlink_iops; static void ceph_invalidate_work(struct work_struct *work);static void ceph_writeback_work(struct work_struct *work);static void ceph_vmtruncate_work(struct work_struct *work); /* * find or create an inode, given the ceph ino number */static int ceph_set_ino_cb(struct inode *inode, void *data){	ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;	inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);	return 0;} struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino){	struct inode *inode;	ino_t t = ceph_vino_to_ino(vino); 	inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino);	if (inode == NULL)		return ERR_PTR(-ENOMEM);	if (inode->i_state & I_NEW) {		dout("get_inode created new inode %p %llx.%llx ino %llx\n",		     inode, ceph_vinop(inode), (u64)inode->i_ino);		unlock_new_inode(inode);	} 	dout("get_inode on %lu=%llx.%llx got %p\n", inode->i_ino, vino.ino,	     vino.snap, inode);	return inode;} /* * get/constuct snapdir inode for a given directory */struct inode *ceph_get_snapdir(struct inode *parent){	struct ceph_vino vino = {		.ino = ceph_ino(parent),		.snap = CEPH_SNAPDIR,	};	struct inode *inode = ceph_get_inode(parent->i_sb, vino);	struct ceph_inode_info *ci = ceph_inode(inode); 	BUG_ON(!S_ISDIR(parent->i_mode));	if (IS_ERR(inode))		return inode;	inode->i_mode = parent->i_mode;	inode->i_uid = parent->i_uid;	inode->i_gid = parent->i_gid;	inode->i_op = &ceph_dir_iops;	inode->i_fop = &ceph_dir_fops;	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */	ci->i_rbytes = 0;	return inode;} const struct inode_operations ceph_file_iops = {	.permission = ceph_permission,	.setattr = ceph_setattr,	.getattr = ceph_getattr,	.setxattr = ceph_setxattr,	.getxattr = ceph_getxattr,	.listxattr = ceph_listxattr,	.removexattr = ceph_removexattr,};  /* * We use a 'frag tree' to keep track of the MDS's directory fragments * for a given inode (usually there is just a single fragment).  We * need to know when a child frag is delegated to a new MDS, or when * it is flagged as replicated, so we can direct our requests * accordingly. */ /* * find/create a frag in the tree */static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci,						    u32 f){	struct rb_node **p;	struct rb_node *parent = NULL;	struct ceph_inode_frag *frag;	int c; 	p = &ci->i_fragtree.rb_node;	while (*p) {		parent = *p;		frag = rb_entry(parent, struct ceph_inode_frag, node);		c = ceph_frag_compare(f, frag->frag);		if (c < 0)			p = &(*p)->rb_left;		else if (c > 0)			p = &(*p)->rb_right;		else			return frag;	} 	frag = kmalloc(sizeof(*frag), GFP_NOFS);	if (!frag) {		pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx "		       "frag %x\n", &ci->vfs_inode,		       ceph_vinop(&ci->vfs_inode), f);		return ERR_PTR(-ENOMEM);	}	frag->frag = f;	frag->split_by = 0;	frag->mds = -1;	frag->ndist = 0; 	rb_link_node(&frag->node, parent, p);	rb_insert_color(&frag->node, &ci->i_fragtree); 	dout("get_or_create_frag added %llx.%llx frag %x\n",	     ceph_vinop(&ci->vfs_inode), f);	return frag;} /* * find a specific frag @f */struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f){	struct rb_node *n = ci->i_fragtree.rb_node; 	while (n) {		struct ceph_inode_frag *frag =			rb_entry(n, struct ceph_inode_frag, node);		int c = ceph_frag_compare(f, frag->frag);		if (c < 0)			n = n->rb_left;		else if (c > 0)			n = n->rb_right;		else			return frag;	}	return NULL;} /* * Choose frag containing the given value @v.  If @pfrag is * specified, copy the frag delegation info to the caller if * it is present. */u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,		     struct ceph_inode_frag *pfrag,		     int *found){	u32 t = ceph_frag_make(0, 0);	struct ceph_inode_frag *frag;	unsigned nway, i;	u32 n; 	if (found)		*found = 0; 	mutex_lock(&ci->i_fragtree_mutex);	while (1) {		WARN_ON(!ceph_frag_contains_value(t, v));		frag = __ceph_find_frag(ci, t);		if (!frag)			break; /* t is a leaf */		if (frag->split_by == 0) {			if (pfrag)				memcpy(pfrag, frag, sizeof(*pfrag));			if (found)				*found = 1;			break;		} 		/* choose child */		nway = 1 << frag->split_by;		dout("choose_frag(%x) %x splits by %d (%d ways)\n", v, t,		     frag->split_by, nway);		for (i = 0; i < nway; i++) {			n = ceph_frag_make_child(t, frag->split_by, i);			if (ceph_frag_contains_value(n, v)) {				t = n;				break;			}		}		BUG_ON(i == nway);	}	dout("choose_frag(%x) = %x\n", v, t); 	mutex_unlock(&ci->i_fragtree_mutex);	return t;} /* * Process dirfrag (delegation) info from the mds.  Include leaf * fragment in tree ONLY if ndist > 0.  Otherwise, only * branches/splits are included in i_fragtree) */static int ceph_fill_dirfrag(struct inode *inode,			     struct ceph_mds_reply_dirfrag *dirinfo){	struct ceph_inode_info *ci = ceph_inode(inode);	struct ceph_inode_frag *frag;	u32 id = le32_to_cpu(dirinfo->frag);	int mds = le32_to_cpu(dirinfo->auth);	int ndist = le32_to_cpu(dirinfo->ndist);	int i;	int err = 0; 	mutex_lock(&ci->i_fragtree_mutex);	if (ndist == 0) {		/* no delegation info needed. */		frag = __ceph_find_frag(ci, id);		if (!frag)			goto out;		if (frag->split_by == 0) {			/* tree leaf, remove */			dout("fill_dirfrag removed %llx.%llx frag %x"			     " (no ref)\n", ceph_vinop(inode), id);			rb_erase(&frag->node, &ci->i_fragtree);			kfree(frag);		} else {			/* tree branch, keep and clear */			dout("fill_dirfrag cleared %llx.%llx frag %x"			     " referral\n", ceph_vinop(inode), id);			frag->mds = -1;			frag->ndist = 0;		}		goto out;	}  	/* find/add this frag to store mds delegation info */	frag = __get_or_create_frag(ci, id);	if (IS_ERR(frag)) {		/* this is not the end of the world; we can continue		   with bad/inaccurate delegation info */		pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",		       ceph_vinop(inode), le32_to_cpu(dirinfo->frag));		err = -ENOMEM;		goto out;	} 	frag->mds = mds;	frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);	for (i = 0; i < frag->ndist; i++)		frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);	dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",	     ceph_vinop(inode), frag->frag, frag->ndist); out:	mutex_unlock(&ci->i_fragtree_mutex);	return err;}  /* * initialize a newly allocated inode. */struct inode *ceph_alloc_inode(struct super_block *sb){	struct ceph_inode_info *ci;	int i; 	ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS);	if (!ci)		return NULL; 	dout("alloc_inode %p\n", &ci->vfs_inode); 	spin_lock_init(&ci->i_ceph_lock); 	ci->i_version = 0;	ci->i_time_warp_seq = 0;	ci->i_ceph_flags = 0;	ci->i_release_count = 0;	ci->i_symlink = NULL; 	memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); 	ci->i_fragtree = RB_ROOT;	mutex_init(&ci->i_fragtree_mutex); 	ci->i_xattrs.blob = NULL;	ci->i_xattrs.prealloc_blob = NULL;	ci->i_xattrs.dirty = false;	ci->i_xattrs.index = RB_ROOT;	ci->i_xattrs.count = 0;	ci->i_xattrs.names_size = 0;	ci->i_xattrs.vals_size = 0;	ci->i_xattrs.version = 0;	ci->i_xattrs.index_version = 0; 	ci->i_caps = RB_ROOT;	ci->i_auth_cap = NULL;	ci->i_dirty_caps = 0;	ci->i_flushing_caps = 0;	INIT_LIST_HEAD(&ci->i_dirty_item);	INIT_LIST_HEAD(&ci->i_flushing_item);	ci->i_cap_flush_seq = 0;	ci->i_cap_flush_last_tid = 0;	memset(&ci->i_cap_flush_tid, 0, sizeof(ci->i_cap_flush_tid));	init_waitqueue_head(&ci->i_cap_wq);	ci->i_hold_caps_min = 0;	ci->i_hold_caps_max = 0;	INIT_LIST_HEAD(&ci->i_cap_delay_list);	ci->i_cap_exporting_mds = 0;	ci->i_cap_exporting_mseq = 0;	ci->i_cap_exporting_issued = 0;	INIT_LIST_HEAD(&ci->i_cap_snaps);	ci->i_head_snapc = NULL;	ci->i_snap_caps = 0; 	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)		ci->i_nr_by_mode[i] = 0; 	ci->i_truncate_seq = 0;	ci->i_truncate_size = 0;	ci->i_truncate_pending = 0; 	ci->i_max_size = 0;	ci->i_reported_size = 0;	ci->i_wanted_max_size = 0;	ci->i_requested_max_size = 0; 	ci->i_pin_ref = 0;	ci->i_rd_ref = 0;	ci->i_rdcache_ref = 0;	ci->i_wr_ref = 0;	ci->i_wb_ref = 0;	ci->i_wrbuffer_ref = 0;	ci->i_wrbuffer_ref_head = 0;	ci->i_shared_gen = 0;	ci->i_rdcache_gen = 0;	ci->i_rdcache_revoking = 0; 	INIT_LIST_HEAD(&ci->i_unsafe_writes);	INIT_LIST_HEAD(&ci->i_unsafe_dirops);	spin_lock_init(&ci->i_unsafe_lock); 	ci->i_snap_realm = NULL;	INIT_LIST_HEAD(&ci->i_snap_realm_item);	INIT_LIST_HEAD(&ci->i_snap_flush_item); 	INIT_WORK(&ci->i_wb_work, ceph_writeback_work);	INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work); 	INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work); 	return &ci->vfs_inode;} static void ceph_i_callback(struct rcu_head *head){	struct inode *inode = container_of(head, struct inode, i_rcu);	struct ceph_inode_info *ci = ceph_inode(inode); 	kmem_cache_free(ceph_inode_cachep, ci);} void ceph_destroy_inode(struct inode *inode){	struct ceph_inode_info *ci = ceph_inode(inode);	struct ceph_inode_frag *frag;	struct rb_node *n; 	dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode)); 	ceph_queue_caps_release(inode); 	/*	 * we may still have a snap_realm reference if there are stray	 * caps in i_cap_exporting_issued or i_snap_caps.	 */	if (ci->i_snap_realm) {		struct ceph_mds_client *mdsc =			ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;		struct ceph_snap_realm *realm = ci->i_snap_realm; 		dout(" dropping residual ref to snap realm %p\n", realm);		spin_lock(&realm->inodes_with_caps_lock);		list_del_init(&ci->i_snap_realm_item);		spin_unlock(&realm->inodes_with_caps_lock);		ceph_put_snap_realm(mdsc, realm);	} 	kfree(ci->i_symlink);	while ((n = rb_first(&ci->i_fragtree)) != NULL) {		frag = rb_entry(n, struct ceph_inode_frag, node);		rb_erase(n, &ci->i_fragtree);		kfree(frag);	} 	__ceph_destroy_xattrs(ci);	if (ci->i_xattrs.blob)		ceph_buffer_put(ci->i_xattrs.blob);	if (ci->i_xattrs.prealloc_blob)		ceph_buffer_put(ci->i_xattrs.prealloc_blob); 	call_rcu(&inode->i_rcu, ceph_i_callback);}  /* * Helpers to fill in size, ctime, mtime, and atime.  We have to be * careful because either the client or MDS may have more up to date * info, depending on which capabilities are held, and whether * time_warp_seq or truncate_seq have increased.  (Ordinarily, mtime * and size are monotonically increasing, except when utimes() or * truncate() increments the corresponding _seq values.) */int ceph_fill_file_size(struct inode *inode, int issued,			u32 truncate_seq, u64 truncate_size, u64 size){	struct ceph_inode_info *ci = ceph_inode(inode);	int queue_trunc = 0; 	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||	    (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {		dout("size %lld -> %llu\n", inode->i_size, size);		inode->i_size = size;		inode->i_blocks = (size + (1<<9) - 1) >> 9;		ci->i_reported_size = size;		if (truncate_seq != ci->i_truncate_seq) {			dout("truncate_seq %u -> %u\n",			     ci->i_truncate_seq, truncate_seq);			ci->i_truncate_seq = truncate_seq;			/*			 * If we hold relevant caps, or in the case where we're			 * not the only client referencing this file and we			 * don't hold those caps, then we need to check whether			 * the file is either opened or mmaped			 */			if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD|				       CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER|				       CEPH_CAP_FILE_EXCL|				       CEPH_CAP_FILE_LAZYIO)) ||			    mapping_mapped(inode->i_mapping) ||			    __ceph_caps_file_wanted(ci)) {				ci->i_truncate_pending++;				queue_trunc = 1;			}		}	}	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 &&	    ci->i_truncate_size != truncate_size) {		dout("truncate_size %lld -> %llu\n", ci->i_truncate_size,		     truncate_size);		ci->i_truncate_size = truncate_size;	}	return queue_trunc;} void ceph_fill_file_time(struct inode *inode, int issued,			 u64 time_warp_seq, struct timespec *ctime,			 struct timespec *mtime, struct timespec *atime){	struct ceph_inode_info *ci = ceph_inode(inode);	int warn = 0; 	if (issued & (CEPH_CAP_FILE_EXCL|		      CEPH_CAP_FILE_WR|		      CEPH_CAP_FILE_BUFFER|		      CEPH_CAP_AUTH_EXCL|		      CEPH_CAP_XATTR_EXCL)) {		if (timespec_compare(ctime, &inode->i_ctime) > 0) {			dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n",			     inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,			     ctime->tv_sec, ctime->tv_nsec);			inode->i_ctime = *ctime;		}

Lines 1–500 of 1811.

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t