Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+37
View File
@@ -0,0 +1,37 @@
config CEPH_FS
tristate "Ceph distributed file system"
depends on INET
select CEPH_LIB
select LIBCRC32C
select CRYPTO_AES
select CRYPTO
default n
help
Choose Y or M here to include support for mounting the
experimental Ceph distributed file system. Ceph is an extremely
scalable file system designed to provide high performance,
reliable access to petabytes of storage.
More information at http://ceph.newdream.net/.
If unsure, say N.
if CEPH_FS
config CEPH_FSCACHE
bool "Enable Ceph client caching support"
depends on CEPH_FS=m && FSCACHE || CEPH_FS=y && FSCACHE=y
help
Choose Y here to enable persistent, read-only local
caching support for Ceph clients using FS-Cache
endif
config CEPH_FS_POSIX_ACL
bool "Ceph POSIX Access Control Lists"
depends on CEPH_FS
select FS_POSIX_ACL
help
POSIX Access Control Lists (ACLs) support permissions for users and
groups beyond the owner/group/world scheme.
If you don't know what Access Control Lists are, say N
+14
View File
@@ -0,0 +1,14 @@
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for CEPH filesystem.
#
obj-$(CONFIG_CEPH_FS) += ceph.o
ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
export.o caps.o snap.o xattr.o quota.o \
mds_client.o mdsmap.o strings.o ceph_frag.o \
debugfs.o
ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
ceph-$(CONFIG_CEPH_FS_POSIX_ACL) += acl.o
+279
View File
@@ -0,0 +1,279 @@
/*
* linux/fs/ceph/acl.c
*
* Copyright (C) 2013 Guangliang Zhao, <lucienchao@gmail.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/ceph/ceph_debug.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/xattr.h>
#include <linux/posix_acl_xattr.h>
#include <linux/posix_acl.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include "super.h"
static inline void ceph_set_cached_acl(struct inode *inode,
int type, struct posix_acl *acl)
{
struct ceph_inode_info *ci = ceph_inode(inode);
spin_lock(&ci->i_ceph_lock);
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
set_cached_acl(inode, type, acl);
else
forget_cached_acl(inode, type);
spin_unlock(&ci->i_ceph_lock);
}
struct posix_acl *ceph_get_acl(struct inode *inode, int type)
{
int size;
unsigned int retry_cnt = 0;
const char *name;
char *value = NULL;
struct posix_acl *acl;
switch (type) {
case ACL_TYPE_ACCESS:
name = XATTR_NAME_POSIX_ACL_ACCESS;
break;
case ACL_TYPE_DEFAULT:
name = XATTR_NAME_POSIX_ACL_DEFAULT;
break;
default:
BUG();
}
retry:
size = __ceph_getxattr(inode, name, "", 0);
if (size > 0) {
value = kzalloc(size, GFP_NOFS);
if (!value)
return ERR_PTR(-ENOMEM);
size = __ceph_getxattr(inode, name, value, size);
}
if (size == -ERANGE && retry_cnt < 10) {
retry_cnt++;
kfree(value);
value = NULL;
goto retry;
}
if (size > 0) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
} else if (size == -ENODATA || size == 0) {
acl = NULL;
} else {
pr_err_ratelimited("get acl %llx.%llx failed, err=%d\n",
ceph_vinop(inode), size);
acl = ERR_PTR(-EIO);
}
kfree(value);
if (!IS_ERR(acl))
ceph_set_cached_acl(inode, type, acl);
return acl;
}
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int ret = 0, size = 0;
const char *name = NULL;
char *value = NULL;
struct iattr newattrs;
struct timespec64 old_ctime = inode->i_ctime;
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
switch (type) {
case ACL_TYPE_ACCESS:
name = XATTR_NAME_POSIX_ACL_ACCESS;
if (acl) {
ret = posix_acl_update_mode(inode, &new_mode, &acl);
if (ret)
goto out;
}
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode)) {
ret = acl ? -EINVAL : 0;
goto out;
}
name = XATTR_NAME_POSIX_ACL_DEFAULT;
break;
default:
ret = -EINVAL;
goto out;
}
if (acl) {
size = posix_acl_xattr_size(acl->a_count);
value = kmalloc(size, GFP_NOFS);
if (!value) {
ret = -ENOMEM;
goto out;
}
ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
if (ret < 0)
goto out_free;
}
if (ceph_snap(inode) != CEPH_NOSNAP) {
ret = -EROFS;
goto out_free;
}
if (new_mode != old_mode) {
newattrs.ia_ctime = current_time(inode);
newattrs.ia_mode = new_mode;
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
ret = __ceph_setattr(inode, &newattrs);
if (ret)
goto out_free;
}
ret = __ceph_setxattr(inode, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_ctime = old_ctime;
newattrs.ia_mode = old_mode;
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
__ceph_setattr(inode, &newattrs);
}
goto out_free;
}
ceph_set_cached_acl(inode, type, acl);
out_free:
kfree(value);
out:
return ret;
}
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info)
{
struct posix_acl *acl, *default_acl;
size_t val_size1 = 0, val_size2 = 0;
struct ceph_pagelist *pagelist = NULL;
void *tmp_buf = NULL;
int err;
err = posix_acl_create(dir, mode, &default_acl, &acl);
if (err)
return err;
if (acl) {
err = posix_acl_equiv_mode(acl, mode);
if (err < 0)
goto out_err;
if (err == 0) {
posix_acl_release(acl);
acl = NULL;
}
}
if (!default_acl && !acl)
return 0;
if (acl)
val_size1 = posix_acl_xattr_size(acl->a_count);
if (default_acl)
val_size2 = posix_acl_xattr_size(default_acl->a_count);
err = -ENOMEM;
tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL);
if (!tmp_buf)
goto out_err;
pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_KERNEL);
if (!pagelist)
goto out_err;
ceph_pagelist_init(pagelist);
err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
if (err)
goto out_err;
ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
if (acl) {
size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
if (err)
goto out_err;
ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
len);
err = posix_acl_to_xattr(&init_user_ns, acl,
tmp_buf, val_size1);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size1);
ceph_pagelist_append(pagelist, tmp_buf, val_size1);
}
if (default_acl) {
size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
if (err)
goto out_err;
err = ceph_pagelist_encode_string(pagelist,
XATTR_NAME_POSIX_ACL_DEFAULT, len);
err = posix_acl_to_xattr(&init_user_ns, default_acl,
tmp_buf, val_size2);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size2);
ceph_pagelist_append(pagelist, tmp_buf, val_size2);
}
kfree(tmp_buf);
info->acl = acl;
info->default_acl = default_acl;
info->pagelist = pagelist;
return 0;
out_err:
posix_acl_release(acl);
posix_acl_release(default_acl);
kfree(tmp_buf);
if (pagelist)
ceph_pagelist_release(pagelist);
return err;
}
void ceph_init_inode_acls(struct inode* inode, struct ceph_acls_info *info)
{
if (!inode)
return;
ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, info->acl);
ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, info->default_acl);
}
void ceph_release_acls_info(struct ceph_acls_info *info)
{
posix_acl_release(info->acl);
posix_acl_release(info->default_acl);
if (info->pagelist)
ceph_pagelist_release(info->pagelist);
}
+2070
View File
File diff suppressed because it is too large. Load diff
+364
View File
@@ -0,0 +1,364 @@
/*
* Ceph cache definitions.
*
* Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
* Written by Milosz Tanski (milosz@adfin.com)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#include "super.h"
#include "cache.h"
struct ceph_aux_inode {
u64 version;
u64 mtime_sec;
u64 mtime_nsec;
};
struct fscache_netfs ceph_cache_netfs = {
.name = "ceph",
.version = 0,
};
static DEFINE_MUTEX(ceph_fscache_lock);
static LIST_HEAD(ceph_fscache_list);
struct ceph_fscache_entry {
struct list_head list;
struct fscache_cookie *fscache;
size_t uniq_len;
/* The following members must be last */
struct ceph_fsid fsid;
char uniquifier[0];
};
static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
.name = "CEPH.fsid",
.type = FSCACHE_COOKIE_TYPE_INDEX,
};
int __init ceph_fscache_register(void)
{
return fscache_register_netfs(&ceph_cache_netfs);
}
void ceph_fscache_unregister(void)
{
fscache_unregister_netfs(&ceph_cache_netfs);
}
int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
{
const struct ceph_fsid *fsid = &fsc->client->fsid;
const char *fscache_uniq = fsc->mount_options->fscache_uniq;
size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0;
struct ceph_fscache_entry *ent;
int err = 0;
mutex_lock(&ceph_fscache_lock);
list_for_each_entry(ent, &ceph_fscache_list, list) {
if (memcmp(&ent->fsid, fsid, sizeof(*fsid)))
continue;
if (ent->uniq_len != uniq_len)
continue;
if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len))
continue;
pr_err("fscache cookie already registered for fsid %pU\n", fsid);
pr_err(" use fsc=%%s mount option to specify a uniquifier\n");
err = -EBUSY;
goto out_unlock;
}
ent = kzalloc(sizeof(*ent) + uniq_len, GFP_KERNEL);
if (!ent) {
err = -ENOMEM;
goto out_unlock;
}
memcpy(&ent->fsid, fsid, sizeof(*fsid));
if (uniq_len > 0) {
memcpy(&ent->uniquifier, fscache_uniq, uniq_len);
ent->uniq_len = uniq_len;
}
fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
&ceph_fscache_fsid_object_def,
&ent->fsid, sizeof(ent->fsid) + uniq_len,
NULL, 0,
fsc, 0, true);
if (fsc->fscache) {
ent->fscache = fsc->fscache;
list_add_tail(&ent->list, &ceph_fscache_list);
} else {
kfree(ent);
pr_err("unable to register fscache cookie for fsid %pU\n",
fsid);
/* all other fs ignore this error */
}
out_unlock:
mutex_unlock(&ceph_fscache_lock);
return err;
}
static enum fscache_checkaux ceph_fscache_inode_check_aux(
void *cookie_netfs_data, const void *data, uint16_t dlen,
loff_t object_size)
{
struct ceph_aux_inode aux;
struct ceph_inode_info* ci = cookie_netfs_data;
struct inode* inode = &ci->vfs_inode;
if (dlen != sizeof(aux) ||
i_size_read(inode) != object_size)
return FSCACHE_CHECKAUX_OBSOLETE;
memset(&aux, 0, sizeof(aux));
aux.version = ci->i_version;
aux.mtime_sec = inode->i_mtime.tv_sec;
aux.mtime_nsec = inode->i_mtime.tv_nsec;
if (memcmp(data, &aux, sizeof(aux)) != 0)
return FSCACHE_CHECKAUX_OBSOLETE;
dout("ceph inode 0x%p cached okay\n", ci);
return FSCACHE_CHECKAUX_OKAY;
}
static const struct fscache_cookie_def ceph_fscache_inode_object_def = {
.name = "CEPH.inode",
.type = FSCACHE_COOKIE_TYPE_DATAFILE,
.check_aux = ceph_fscache_inode_check_aux,
};
void ceph_fscache_register_inode_cookie(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_aux_inode aux;
/* No caching for filesystem */
if (!fsc->fscache)
return;
/* Only cache for regular files that are read only */
if (!S_ISREG(inode->i_mode))
return;
inode_lock_nested(inode, I_MUTEX_CHILD);
if (!ci->fscache) {
memset(&aux, 0, sizeof(aux));
aux.version = ci->i_version;
aux.mtime_sec = inode->i_mtime.tv_sec;
aux.mtime_nsec = inode->i_mtime.tv_nsec;
ci->fscache = fscache_acquire_cookie(fsc->fscache,
&ceph_fscache_inode_object_def,
&ci->i_vino, sizeof(ci->i_vino),
&aux, sizeof(aux),
ci, i_size_read(inode), false);
}
inode_unlock(inode);
}
void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
{
struct fscache_cookie* cookie;
if ((cookie = ci->fscache) == NULL)
return;
ci->fscache = NULL;
fscache_uncache_all_inode_pages(cookie, &ci->vfs_inode);
fscache_relinquish_cookie(cookie, &ci->i_vino, false);
}
static bool ceph_fscache_can_enable(void *data)
{
struct inode *inode = data;
return !inode_is_open_for_write(inode);
}
void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (!fscache_cookie_valid(ci->fscache))
return;
if (inode_is_open_for_write(inode)) {
dout("fscache_file_set_cookie %p %p disabling cache\n",
inode, filp);
fscache_disable_cookie(ci->fscache, &ci->i_vino, false);
fscache_uncache_all_inode_pages(ci->fscache, inode);
} else {
fscache_enable_cookie(ci->fscache, &ci->i_vino, i_size_read(inode),
ceph_fscache_can_enable, inode);
if (fscache_cookie_enabled(ci->fscache)) {
dout("fscache_file_set_cookie %p %p enabling cache\n",
inode, filp);
}
}
}
static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
{
if (!error)
SetPageUptodate(page);
unlock_page(page);
}
static inline bool cache_valid(struct ceph_inode_info *ci)
{
return ci->i_fscache_gen == ci->i_rdcache_gen;
}
/* Atempt to read from the fscache,
*
* This function is called from the readpage_nounlock context. DO NOT attempt to
* unlock the page here (or in the callback).
*/
int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int ret;
if (!cache_valid(ci))
return -ENOBUFS;
ret = fscache_read_or_alloc_page(ci->fscache, page,
ceph_readpage_from_fscache_complete, NULL,
GFP_KERNEL);
switch (ret) {
case 0: /* Page found */
dout("page read submitted\n");
return 0;
case -ENOBUFS: /* Pages were not found, and can't be */
case -ENODATA: /* Pages were not found */
dout("page/inode not in cache\n");
return ret;
default:
dout("%s: unknown error ret = %i\n", __func__, ret);
return ret;
}
}
int ceph_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int ret;
if (!cache_valid(ci))
return -ENOBUFS;
ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
ceph_readpage_from_fscache_complete,
NULL, mapping_gfp_mask(mapping));
switch (ret) {
case 0: /* All pages found */
dout("all-page read submitted\n");
return 0;
case -ENOBUFS: /* Some pages were not found, and can't be */
case -ENODATA: /* some pages were not found */
dout("page/inode not in cache\n");
return ret;
default:
dout("%s: unknown error ret = %i\n", __func__, ret);
return ret;
}
}
void ceph_readpage_to_fscache(struct inode *inode, struct page *page)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int ret;
if (!PageFsCache(page))
return;
if (!cache_valid(ci))
return;
ret = fscache_write_page(ci->fscache, page, i_size_read(inode),
GFP_KERNEL);
if (ret)
fscache_uncache_page(ci->fscache, page);
}
void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (!PageFsCache(page))
return;
fscache_wait_on_page_write(ci->fscache, page);
fscache_uncache_page(ci->fscache, page);
}
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
{
if (fscache_cookie_valid(fsc->fscache)) {
struct ceph_fscache_entry *ent;
bool found = false;
mutex_lock(&ceph_fscache_lock);
list_for_each_entry(ent, &ceph_fscache_list, list) {
if (ent->fscache == fsc->fscache) {
list_del(&ent->list);
kfree(ent);
found = true;
break;
}
}
WARN_ON_ONCE(!found);
mutex_unlock(&ceph_fscache_lock);
__fscache_relinquish_cookie(fsc->fscache, NULL, false);
}
fsc->fscache = NULL;
}
/*
* caller should hold CEPH_CAP_FILE_{RD,CACHE}
*/
void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
{
if (cache_valid(ci))
return;
/* resue i_truncate_mutex. There should be no pending
* truncate while the caller holds CEPH_CAP_FILE_RD */
mutex_lock(&ci->i_truncate_mutex);
if (!cache_valid(ci)) {
if (fscache_check_consistency(ci->fscache, &ci->i_vino))
fscache_invalidate(ci->fscache);
spin_lock(&ci->i_ceph_lock);
ci->i_fscache_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
}
mutex_unlock(&ci->i_truncate_mutex);
}
+190
View File
@@ -0,0 +1,190 @@
/*
* Ceph cache definitions.
*
* Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
* Written by Milosz Tanski (milosz@adfin.com)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#ifndef _CEPH_CACHE_H
#define _CEPH_CACHE_H
#ifdef CONFIG_CEPH_FSCACHE
extern struct fscache_netfs ceph_cache_netfs;
int ceph_fscache_register(void);
void ceph_fscache_unregister(void);
int ceph_fscache_register_fs(struct ceph_fs_client* fsc);
void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc);
void ceph_fscache_register_inode_cookie(struct inode *inode);
void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci);
void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp);
void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci);
int ceph_readpage_from_fscache(struct inode *inode, struct page *page);
int ceph_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages);
void ceph_readpage_to_fscache(struct inode *inode, struct page *page);
void ceph_invalidate_fscache_page(struct inode* inode, struct page *page);
static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
ci->fscache = NULL;
ci->i_fscache_gen = 0;
}
static inline void ceph_fscache_invalidate(struct inode *inode)
{
fscache_invalidate(ceph_inode(inode)->fscache);
}
static inline void ceph_fscache_uncache_page(struct inode *inode,
struct page *page)
{
struct ceph_inode_info *ci = ceph_inode(inode);
return fscache_uncache_page(ci->fscache, page);
}
static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
{
struct inode* inode = page->mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
return fscache_maybe_release_page(ci->fscache, page, gfp);
}
static inline void ceph_fscache_readpage_cancel(struct inode *inode,
struct page *page)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (fscache_cookie_valid(ci->fscache) && PageFsCache(page))
__fscache_uncache_page(ci->fscache, page);
}
static inline void ceph_fscache_readpages_cancel(struct inode *inode,
struct list_head *pages)
{
struct ceph_inode_info *ci = ceph_inode(inode);
return fscache_readpages_cancel(ci->fscache, pages);
}
static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
{
ci->i_fscache_gen = ci->i_rdcache_gen - 1;
}
#else
static inline int ceph_fscache_register(void)
{
return 0;
}
static inline void ceph_fscache_unregister(void)
{
}
static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
{
return 0;
}
static inline void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
{
}
static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci)
{
}
static inline void ceph_fscache_register_inode_cookie(struct inode *inode)
{
}
static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
{
}
static inline void ceph_fscache_file_set_cookie(struct inode *inode,
struct file *filp)
{
}
static inline void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci)
{
}
static inline void ceph_fscache_uncache_page(struct inode *inode,
struct page *pages)
{
}
static inline int ceph_readpage_from_fscache(struct inode* inode,
struct page *page)
{
return -ENOBUFS;
}
static inline int ceph_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
return -ENOBUFS;
}
static inline void ceph_readpage_to_fscache(struct inode *inode,
struct page *page)
{
}
static inline void ceph_fscache_invalidate(struct inode *inode)
{
}
static inline void ceph_invalidate_fscache_page(struct inode *inode,
struct page *page)
{
}
static inline int ceph_release_fscache_page(struct page *page, gfp_t gfp)
{
return 1;
}
static inline void ceph_fscache_readpage_cancel(struct inode *inode,
struct page *page)
{
}
static inline void ceph_fscache_readpages_cancel(struct inode *inode,
struct list_head *pages)
{
}
static inline void ceph_disable_fscache_readpage(struct ceph_inode_info *ci)
{
}
#endif
#endif
+4238
View File
File diff suppressed because it is too large. Load diff
+23
View File
@@ -0,0 +1,23 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Ceph 'frag' type
*/
#include <linux/module.h>
#include <linux/ceph/types.h>
int ceph_frag_compare(__u32 a, __u32 b)
{
unsigned va = ceph_frag_value(a);
unsigned vb = ceph_frag_value(b);
if (va < vb)
return -1;
if (va > vb)
return 1;
va = ceph_frag_bits(a);
vb = ceph_frag_bits(b);
if (va < vb)
return -1;
if (va > vb)
return 1;
return 0;
}
+321
View File
@@ -0,0 +1,321 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/ceph/libceph.h>
#include <linux/ceph/mon_client.h>
#include <linux/ceph/auth.h>
#include <linux/ceph/debugfs.h>
#include "super.h"
#ifdef CONFIG_DEBUG_FS
#include "mds_client.h"
static int mdsmap_show(struct seq_file *s, void *p)
{
int i;
struct ceph_fs_client *fsc = s->private;
struct ceph_mdsmap *mdsmap;
if (!fsc->mdsc || !fsc->mdsc->mdsmap)
return 0;
mdsmap = fsc->mdsc->mdsmap;
seq_printf(s, "epoch %d\n", mdsmap->m_epoch);
seq_printf(s, "root %d\n", mdsmap->m_root);
seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
for (i = 0; i < mdsmap->m_num_mds; i++) {
struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
int state = mdsmap->m_info[i].state;
seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
ceph_pr_addr(&addr->in_addr),
ceph_mds_state_name(state));
}
return 0;
}
/*
* mdsc debugfs
*/
static int mdsc_show(struct seq_file *s, void *p)
{
struct ceph_fs_client *fsc = s->private;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct rb_node *rp;
int pathlen;
u64 pathbase;
char *path;
mutex_lock(&mdsc->mutex);
for (rp = rb_first(&mdsc->request_tree); rp; rp = rb_next(rp)) {
req = rb_entry(rp, struct ceph_mds_request, r_node);
if (req->r_request && req->r_session)
seq_printf(s, "%lld\tmds%d\t", req->r_tid,
req->r_session->s_mds);
else if (!req->r_request)
seq_printf(s, "%lld\t(no request)\t", req->r_tid);
else
seq_printf(s, "%lld\t(no session)\t", req->r_tid);
seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
seq_puts(s, "\t(unsafe)");
else
seq_puts(s, "\t");
if (req->r_inode) {
seq_printf(s, " #%llx", ceph_ino(req->r_inode));
} else if (req->r_dentry) {
path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
&pathbase, 0);
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_dentry->d_lock);
seq_printf(s, " #%llx/%pd (%s)",
ceph_ino(d_inode(req->r_dentry->d_parent)),
req->r_dentry,
path ? path : "");
spin_unlock(&req->r_dentry->d_lock);
kfree(path);
} else if (req->r_path1) {
seq_printf(s, " #%llx/%s", req->r_ino1.ino,
req->r_path1);
} else {
seq_printf(s, " #%llx", req->r_ino1.ino);
}
if (req->r_old_dentry) {
path = ceph_mdsc_build_path(req->r_old_dentry, &pathlen,
&pathbase, 0);
if (IS_ERR(path))
path = NULL;
spin_lock(&req->r_old_dentry->d_lock);
seq_printf(s, " #%llx/%pd (%s)",
req->r_old_dentry_dir ?
ceph_ino(req->r_old_dentry_dir) : 0,
req->r_old_dentry,
path ? path : "");
spin_unlock(&req->r_old_dentry->d_lock);
kfree(path);
} else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) {
if (req->r_ino2.ino)
seq_printf(s, " #%llx/%s", req->r_ino2.ino,
req->r_path2);
else
seq_printf(s, " %s", req->r_path2);
}
seq_puts(s, "\n");
}
mutex_unlock(&mdsc->mutex);
return 0;
}
static int caps_show(struct seq_file *s, void *p)
{
struct ceph_fs_client *fsc = s->private;
int total, avail, used, reserved, min;
ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
seq_printf(s, "total\t\t%d\n"
"avail\t\t%d\n"
"used\t\t%d\n"
"reserved\t%d\n"
"min\t%d\n",
total, avail, used, reserved, min);
return 0;
}
static int dentry_lru_show(struct seq_file *s, void *ptr)
{
struct ceph_fs_client *fsc = s->private;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_dentry_info *di;
spin_lock(&mdsc->dentry_lru_lock);
list_for_each_entry(di, &mdsc->dentry_lru, lru) {
struct dentry *dentry = di->dentry;
seq_printf(s, "%p %p\t%pd\n",
di, dentry, dentry);
}
spin_unlock(&mdsc->dentry_lru_lock);
return 0;
}
static int mds_sessions_show(struct seq_file *s, void *ptr)
{
struct ceph_fs_client *fsc = s->private;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_auth_client *ac = fsc->client->monc.auth;
struct ceph_options *opt = fsc->client->options;
int mds = -1;
mutex_lock(&mdsc->mutex);
/* The 'num' portion of an 'entity name' */
seq_printf(s, "global_id %llu\n", ac->global_id);
/* The -o name mount argument */
seq_printf(s, "name \"%s\"\n", opt->name ? opt->name : "");
/* The list of MDS session rank+state */
for (mds = 0; mds < mdsc->max_sessions; mds++) {
struct ceph_mds_session *session =
__ceph_lookup_mds_session(mdsc, mds);
if (!session) {
continue;
}
mutex_unlock(&mdsc->mutex);
seq_printf(s, "mds.%d %s\n",
session->s_mds,
ceph_session_state_name(session->s_state));
ceph_put_mds_session(session);
mutex_lock(&mdsc->mutex);
}
mutex_unlock(&mdsc->mutex);
return 0;
}
CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
CEPH_DEFINE_SHOW_FUNC(mdsc_show)
CEPH_DEFINE_SHOW_FUNC(caps_show)
CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
CEPH_DEFINE_SHOW_FUNC(mds_sessions_show)
/*
* debugfs
*/
static int congestion_kb_set(void *data, u64 val)
{
struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
fsc->mount_options->congestion_kb = (int)val;
return 0;
}
static int congestion_kb_get(void *data, u64 *val)
{
struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
*val = (u64)fsc->mount_options->congestion_kb;
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
congestion_kb_set, "%llu\n");
void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
{
dout("ceph_fs_debugfs_cleanup\n");
debugfs_remove(fsc->debugfs_bdi);
debugfs_remove(fsc->debugfs_congestion_kb);
debugfs_remove(fsc->debugfs_mdsmap);
debugfs_remove(fsc->debugfs_mds_sessions);
debugfs_remove(fsc->debugfs_caps);
debugfs_remove(fsc->debugfs_mdsc);
debugfs_remove(fsc->debugfs_dentry_lru);
}
int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
{
char name[100];
int err = -ENOMEM;
dout("ceph_fs_debugfs_init\n");
BUG_ON(!fsc->client->debugfs_dir);
fsc->debugfs_congestion_kb =
debugfs_create_file("writeback_congestion_kb",
0600,
fsc->client->debugfs_dir,
fsc,
&congestion_kb_fops);
if (!fsc->debugfs_congestion_kb)
goto out;
snprintf(name, sizeof(name), "../../bdi/%s",
dev_name(fsc->sb->s_bdi->dev));
fsc->debugfs_bdi =
debugfs_create_symlink("bdi",
fsc->client->debugfs_dir,
name);
if (!fsc->debugfs_bdi)
goto out;
fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
0400,
fsc->client->debugfs_dir,
fsc,
&mdsmap_show_fops);
if (!fsc->debugfs_mdsmap)
goto out;
fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions",
0400,
fsc->client->debugfs_dir,
fsc,
&mds_sessions_show_fops);
if (!fsc->debugfs_mds_sessions)
goto out;
fsc->debugfs_mdsc = debugfs_create_file("mdsc",
0400,
fsc->client->debugfs_dir,
fsc,
&mdsc_show_fops);
if (!fsc->debugfs_mdsc)
goto out;
fsc->debugfs_caps = debugfs_create_file("caps",
0400,
fsc->client->debugfs_dir,
fsc,
&caps_show_fops);
if (!fsc->debugfs_caps)
goto out;
fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
0400,
fsc->client->debugfs_dir,
fsc,
&dentry_lru_show_fops);
if (!fsc->debugfs_dentry_lru)
goto out;
return 0;
out:
ceph_fs_debugfs_cleanup(fsc);
return err;
}
#else /* CONFIG_DEBUG_FS */
int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
{
return 0;
}
void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
{
}
#endif /* CONFIG_DEBUG_FS */
+1541
View File
File diff suppressed because it is too large. Load diff
+248
View File
@@ -0,0 +1,248 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/exportfs.h>
#include <linux/slab.h>
#include <asm/unaligned.h>
#include "super.h"
#include "mds_client.h"
/*
* Basic fh
*/
struct ceph_nfs_fh {
u64 ino;
} __attribute__ ((packed));
/*
* Larger fh that includes parent ino.
*/
struct ceph_nfs_confh {
u64 ino, parent_ino;
} __attribute__ ((packed));
static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
struct inode *parent_inode)
{
int type;
struct ceph_nfs_fh *fh = (void *)rawfh;
struct ceph_nfs_confh *cfh = (void *)rawfh;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
if (parent_inode && (*max_len < connected_handle_length)) {
*max_len = connected_handle_length;
return FILEID_INVALID;
} else if (*max_len < handle_length) {
*max_len = handle_length;
return FILEID_INVALID;
}
if (parent_inode) {
dout("encode_fh %llx with parent %llx\n",
ceph_ino(inode), ceph_ino(parent_inode));
cfh->ino = ceph_ino(inode);
cfh->parent_ino = ceph_ino(parent_inode);
*max_len = connected_handle_length;
type = FILEID_INO32_GEN_PARENT;
} else {
dout("encode_fh %llx\n", ceph_ino(inode));
fh->ino = ceph_ino(inode);
*max_len = handle_length;
type = FILEID_INO32_GEN;
}
return type;
}
static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct inode *inode;
struct ceph_vino vino;
int err;
vino.ino = ino;
vino.snap = CEPH_NOSNAP;
inode = ceph_find_inode(sb, vino);
if (!inode) {
struct ceph_mds_request *req;
int mask;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
mask = CEPH_STAT_CAP_INODE;
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.getattr.mask = cpu_to_le32(mask);
req->r_ino1 = vino;
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ESTALE);
if (inode->i_nlink == 0) {
iput(inode);
return ERR_PTR(-ESTALE);
}
}
return d_obtain_alias(inode);
}
/*
* convert regular fh to dentry
*/
static struct dentry *ceph_fh_to_dentry(struct super_block *sb,
struct fid *fid,
int fh_len, int fh_type)
{
struct ceph_nfs_fh *fh = (void *)fid->raw;
if (fh_type != FILEID_INO32_GEN &&
fh_type != FILEID_INO32_GEN_PARENT)
return NULL;
if (fh_len < sizeof(*fh) / 4)
return NULL;
dout("fh_to_dentry %llx\n", fh->ino);
return __fh_to_dentry(sb, fh->ino);
}
static struct dentry *__get_parent(struct super_block *sb,
struct dentry *child, u64 ino)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
struct ceph_mds_request *req;
struct inode *inode;
int mask;
int err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPPARENT,
USE_ANY_MDS);
if (IS_ERR(req))
return ERR_CAST(req);
if (child) {
req->r_inode = d_inode(child);
ihold(d_inode(child));
} else {
req->r_ino1 = (struct ceph_vino) {
.ino = ino,
.snap = CEPH_NOSNAP,
};
}
mask = CEPH_STAT_CAP_INODE;
if (ceph_security_xattr_wanted(d_inode(sb->s_root)))
mask |= CEPH_CAP_XATTR_SHARED;
req->r_args.getattr.mask = cpu_to_le32(mask);
req->r_num_caps = 1;
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err) {
ceph_mdsc_put_request(req);
return ERR_PTR(err);
}
inode = req->r_target_inode;
if (inode)
ihold(inode);
ceph_mdsc_put_request(req);
if (!inode)
return ERR_PTR(-ENOENT);
return d_obtain_alias(inode);
}
static struct dentry *ceph_get_parent(struct dentry *child)
{
/* don't re-export snaps */
if (ceph_snap(d_inode(child)) != CEPH_NOSNAP)
return ERR_PTR(-EINVAL);
dout("get_parent %p ino %llx.%llx\n",
child, ceph_vinop(d_inode(child)));
return __get_parent(child->d_sb, child, 0);
}
/*
* convert regular fh to parent
*/
static struct dentry *ceph_fh_to_parent(struct super_block *sb,
struct fid *fid,
int fh_len, int fh_type)
{
struct ceph_nfs_confh *cfh = (void *)fid->raw;
struct dentry *dentry;
if (fh_type != FILEID_INO32_GEN_PARENT)
return NULL;
if (fh_len < sizeof(*cfh) / 4)
return NULL;
dout("fh_to_parent %llx\n", cfh->parent_ino);
dentry = __get_parent(sb, NULL, cfh->ino);
if (unlikely(dentry == ERR_PTR(-ENOENT)))
dentry = __fh_to_dentry(sb, cfh->parent_ino);
return dentry;
}
static int ceph_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
struct ceph_mds_client *mdsc;
struct ceph_mds_request *req;
int err;
mdsc = ceph_inode_to_client(d_inode(child))->mdsc;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
USE_ANY_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
inode_lock(d_inode(parent));
req->r_inode = d_inode(child);
ihold(d_inode(child));
req->r_ino2 = ceph_vino(d_inode(parent));
req->r_parent = d_inode(parent);
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_num_caps = 2;
err = ceph_mdsc_do_request(mdsc, NULL, req);
inode_unlock(d_inode(parent));
if (!err) {
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
memcpy(name, rinfo->dname, rinfo->dname_len);
name[rinfo->dname_len] = 0;
dout("get_name %p ino %llx.%llx name %s\n",
child, ceph_vinop(d_inode(child)), name);
} else {
dout("get_name %p ino %llx.%llx err %d\n",
child, ceph_vinop(d_inode(child)), err);
}
ceph_mdsc_put_request(req);
return err;
}
const struct export_operations ceph_export_ops = {
.encode_fh = ceph_encode_fh,
.fh_to_dentry = ceph_fh_to_dentry,
.fh_to_parent = ceph_fh_to_parent,
.get_parent = ceph_get_parent,
.get_name = ceph_get_name,
};
+1830
View File
File diff suppressed because it is too large. Load diff
+2312
View File
File diff suppressed because it is too large. Load diff
+293
View File
@@ -0,0 +1,293 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/in.h>
#include "super.h"
#include "mds_client.h"
#include "ioctl.h"
#include <linux/ceph/striper.h>
/*
* ioctls
*/
/*
* get and set the file layout
*/
static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
{
struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout l;
int err;
err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
if (!err) {
l.stripe_unit = ci->i_layout.stripe_unit;
l.stripe_count = ci->i_layout.stripe_count;
l.object_size = ci->i_layout.object_size;
l.data_pool = ci->i_layout.pool_id;
l.preferred_osd = -1;
if (copy_to_user(arg, &l, sizeof(l)))
return -EFAULT;
}
return err;
}
static long __validate_layout(struct ceph_mds_client *mdsc,
struct ceph_ioctl_layout *l)
{
int i, err;
/* validate striping parameters */
if ((l->object_size & ~PAGE_MASK) ||
(l->stripe_unit & ~PAGE_MASK) ||
((unsigned)l->stripe_unit != 0 &&
((unsigned)l->object_size % (unsigned)l->stripe_unit)))
return -EINVAL;
/* make sure it's a valid data pool */
mutex_lock(&mdsc->mutex);
err = -EINVAL;
for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) {
err = 0;
break;
}
mutex_unlock(&mdsc->mutex);
if (err)
return err;
return 0;
}
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout nl;
int err;
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
/* validate changed params against current layout */
err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT, false);
if (err)
return err;
memset(&nl, 0, sizeof(nl));
if (l.stripe_count)
nl.stripe_count = l.stripe_count;
else
nl.stripe_count = ci->i_layout.stripe_count;
if (l.stripe_unit)
nl.stripe_unit = l.stripe_unit;
else
nl.stripe_unit = ci->i_layout.stripe_unit;
if (l.object_size)
nl.object_size = l.object_size;
else
nl.object_size = ci->i_layout.object_size;
if (l.data_pool)
nl.data_pool = l.data_pool;
else
nl.data_pool = ci->i_layout.pool_id;
/* this is obsolete, and always -1 */
nl.preferred_osd = -1;
err = __validate_layout(mdsc, &nl);
if (err)
return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
req->r_args.setlayout.layout.fl_stripe_count =
cpu_to_le32(l.stripe_count);
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
err = ceph_mdsc_do_request(mdsc, NULL, req);
ceph_mdsc_put_request(req);
return err;
}
/*
* Set a layout policy on a directory inode. All items in the tree
* rooted at this inode will inherit this layout on creation,
* (It doesn't apply retroactively )
* unless a subdirectory has its own layout policy.
*/
static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
{
struct inode *inode = file_inode(file);
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
int err;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
/* copy and validate */
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
err = __validate_layout(mdsc, &l);
if (err)
return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
req->r_args.setlayout.layout.fl_stripe_unit =
cpu_to_le32(l.stripe_unit);
req->r_args.setlayout.layout.fl_stripe_count =
cpu_to_le32(l.stripe_count);
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool =
cpu_to_le32(l.data_pool);
err = ceph_mdsc_do_request(mdsc, inode, req);
ceph_mdsc_put_request(req);
return err;
}
/*
* Return object name, size/offset information, and location (OSD
* number, network address) for a given file offset.
*/
static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
{
struct ceph_ioctl_dataloc dl;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
struct ceph_object_locator oloc;
CEPH_DEFINE_OID_ONSTACK(oid);
u32 xlen;
u64 tmp;
struct ceph_pg pgid;
int r;
/* copy and validate */
if (copy_from_user(&dl, arg, sizeof(dl)))
return -EFAULT;
down_read(&osdc->lock);
ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, 1,
&dl.object_no, &dl.object_offset, &xlen);
dl.file_offset -= dl.object_offset;
dl.object_size = ci->i_layout.object_size;
dl.block_size = ci->i_layout.stripe_unit;
/* block_offset = object_offset % block_size */
tmp = dl.object_offset;
dl.block_offset = do_div(tmp, dl.block_size);
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
oloc.pool = ci->i_layout.pool_id;
oloc.pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
ceph_oid_printf(&oid, "%s", dl.object_name);
r = ceph_object_locator_to_pg(osdc->osdmap, &oid, &oloc, &pgid);
ceph_oloc_destroy(&oloc);
if (r < 0) {
up_read(&osdc->lock);
return r;
}
dl.osd = ceph_pg_to_acting_primary(osdc->osdmap, &pgid);
if (dl.osd >= 0) {
struct ceph_entity_addr *a =
ceph_osd_addr(osdc->osdmap, dl.osd);
if (a)
memcpy(&dl.osd_addr, &a->in_addr, sizeof(dl.osd_addr));
} else {
memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
}
up_read(&osdc->lock);
/* send result back to user */
if (copy_to_user(arg, &dl, sizeof(dl)))
return -EFAULT;
return 0;
}
static long ceph_ioctl_lazyio(struct file *file)
{
struct ceph_file_info *fi = file->private_data;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
spin_lock(&ci->i_ceph_lock);
fi->fmode |= CEPH_FILE_MODE_LAZY;
ci->i_nr_by_mode[ffs(CEPH_FILE_MODE_LAZY)]++;
spin_unlock(&ci->i_ceph_lock);
dout("ioctl_layzio: file %p marked lazy\n", file);
ceph_check_caps(ci, 0, NULL);
} else {
dout("ioctl_layzio: file %p already lazy\n", file);
}
return 0;
}
static long ceph_ioctl_syncio(struct file *file)
{
struct ceph_file_info *fi = file->private_data;
fi->flags |= CEPH_F_SYNC;
return 0;
}
long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
switch (cmd) {
case CEPH_IOC_GET_LAYOUT:
return ceph_ioctl_get_layout(file, (void __user *)arg);
case CEPH_IOC_SET_LAYOUT:
return ceph_ioctl_set_layout(file, (void __user *)arg);
case CEPH_IOC_SET_LAYOUT_POLICY:
return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
case CEPH_IOC_GET_DATALOC:
return ceph_ioctl_get_dataloc(file, (void __user *)arg);
case CEPH_IOC_LAZYIO:
return ceph_ioctl_lazyio(file);
case CEPH_IOC_SYNCIO:
return ceph_ioctl_syncio(file);
}
return -ENOTTY;
}
+101
View File
@@ -0,0 +1,101 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef FS_CEPH_IOCTL_H
#define FS_CEPH_IOCTL_H
#include <linux/ioctl.h>
#include <linux/types.h>
#define CEPH_IOCTL_MAGIC 0x97
/*
* CEPH_IOC_GET_LAYOUT - get file layout or dir layout policy
* CEPH_IOC_SET_LAYOUT - set file layout
* CEPH_IOC_SET_LAYOUT_POLICY - set dir layout policy
*
* The file layout specifies how file data is striped over objects in
* the distributed object store, which object pool they belong to (if
* it differs from the default), and an optional 'preferred osd' to
* store them on.
*
* Files get a new layout based on the policy set on the containing
* directory or one of its ancestors. The GET_LAYOUT ioctl will let
* you examine the layout for a file or the policy on a directory.
*
* SET_LAYOUT will let you set a layout on a newly created file. This
* only works immediately after the file is created and before any
* data is written to it.
*
* SET_LAYOUT_POLICY will let you set a layout policy (default layout)
* on a directory that will apply to any new files created in that
* directory (or any child directory that doesn't specify a layout of
* its own).
*/
/* use u64 to align sanely on all archs */
struct ceph_ioctl_layout {
__u64 stripe_unit, stripe_count, object_size;
__u64 data_pool;
/* obsolete. new values ignored, always return -1 */
__s64 preferred_osd;
};
#define CEPH_IOC_GET_LAYOUT _IOR(CEPH_IOCTL_MAGIC, 1, \
struct ceph_ioctl_layout)
#define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2, \
struct ceph_ioctl_layout)
#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5, \
struct ceph_ioctl_layout)
/*
* CEPH_IOC_GET_DATALOC - get location of file data in the cluster
*
* Extract identity, address of the OSD and object storing a given
* file offset.
*/
struct ceph_ioctl_dataloc {
__u64 file_offset; /* in+out: file offset */
__u64 object_offset; /* out: offset in object */
__u64 object_no; /* out: object # */
__u64 object_size; /* out: object size */
char object_name[64]; /* out: object name */
__u64 block_offset; /* out: offset in block */
__u64 block_size; /* out: block length */
__s64 osd; /* out: osd # */
struct sockaddr_storage osd_addr; /* out: osd address */
};
#define CEPH_IOC_GET_DATALOC _IOWR(CEPH_IOCTL_MAGIC, 3, \
struct ceph_ioctl_dataloc)
/*
* CEPH_IOC_LAZYIO - relax consistency
*
* Normally Ceph switches to synchronous IO when multiple clients have
* the file open (and or more for write). Reads and writes bypass the
* page cache and go directly to the OSD. Setting this flag on a file
* descriptor will allow buffered IO for this file in cases where the
* application knows it won't interfere with other nodes (or doesn't
* care).
*/
#define CEPH_IOC_LAZYIO _IO(CEPH_IOCTL_MAGIC, 4)
/*
* CEPH_IOC_SYNCIO - force synchronous IO
*
* This ioctl sets a file flag that forces the synchronous IO that
* bypasses the page cache, even if it is not necessary. This is
* essentially the opposite behavior of IOC_LAZYIO. This forces the
* same read/write path as a file opened by multiple clients when one
* or more of those clients is opened for write.
*
* Note that this type of sync IO takes a different path than a file
* opened with O_SYNC/D_SYNC (writes hit the page cache and are
* immediately flushed on page boundaries). It is very similar to
* O_DIRECT (writes bypass the page cache) excep that O_DIRECT writes
* are not copied (user page must remain stable) and O_DIRECT writes
* have alignment restrictions (on the buffer and file offset).
*/
#define CEPH_IOC_SYNCIO _IO(CEPH_IOCTL_MAGIC, 5)
#endif
+479
View File
@@ -0,0 +1,479 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/file.h>
#include <linux/namei.h>
#include <linux/random.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/pagelist.h>
static u64 lock_secret;
static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req);
static inline u64 secure_addr(void *addr)
{
u64 v = lock_secret ^ (u64)(unsigned long)addr;
/*
* Set the most significant bit, so that MDS knows the 'owner'
* is sufficient to identify the owner of lock. (old code uses
* both 'owner' and 'pid')
*/
v |= (1ULL << 63);
return v;
}
void __init ceph_flock_init(void)
{
get_random_bytes(&lock_secret, sizeof(lock_secret));
}
static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
struct inode *inode = file_inode(src->fl_file);
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
}
static void ceph_fl_release_lock(struct file_lock *fl)
{
struct inode *inode = file_inode(fl->fl_file);
struct ceph_inode_info *ci = ceph_inode(inode);
if (atomic_dec_and_test(&ci->i_filelock_ref)) {
/* clear error when all locks are released */
spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
spin_unlock(&ci->i_ceph_lock);
}
}
static const struct file_lock_operations ceph_fl_lock_ops = {
.fl_copy_lock = ceph_fl_copy_lock,
.fl_release_private = ceph_fl_release_lock,
};
/**
* Implement fcntl and flock locking functions.
*/
static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
int cmd, u8 wait, struct file_lock *fl)
{
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
int err;
u64 length = 0;
u64 owner;
if (operation == CEPH_MDS_OP_SETFILELOCK) {
/*
* increasing i_filelock_ref closes race window between
* handling request reply and adding file_lock struct to
* inode. Otherwise, auth caps may get trimmed in the
* window. Caller function will decrease the counter.
*/
fl->fl_ops = &ceph_fl_lock_ops;
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
}
if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK)
wait = 0;
req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
if (IS_ERR(req))
return PTR_ERR(req);
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
/* mds requires start and length rather than start and end */
if (LLONG_MAX == fl->fl_end)
length = 0;
else
length = fl->fl_end - fl->fl_start + 1;
owner = secure_addr(fl->fl_owner);
dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
"start: %llu, length: %llu, wait: %d, type: %d\n", (int)lock_type,
(int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
wait, fl->fl_type);
req->r_args.filelock_change.rule = lock_type;
req->r_args.filelock_change.type = cmd;
req->r_args.filelock_change.owner = cpu_to_le64(owner);
req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
req->r_args.filelock_change.length = cpu_to_le64(length);
req->r_args.filelock_change.wait = wait;
if (wait)
req->r_wait_for_completion = ceph_lock_wait_for_completion;
err = ceph_mdsc_do_request(mdsc, inode, req);
if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_WRLCK;
else
fl->fl_type = F_UNLCK;
fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
le64_to_cpu(req->r_reply_info.filelock_reply->length);
if (length >= 1)
fl->fl_end = length -1;
else
fl->fl_end = 0;
}
ceph_mdsc_put_request(req);
dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
"length: %llu, wait: %d, type: %d, err code %d\n", (int)lock_type,
(int)operation, (u64)fl->fl_pid, fl->fl_start,
length, wait, fl->fl_type, err);
return err;
}
static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req)
{
struct ceph_mds_request *intr_req;
struct inode *inode = req->r_inode;
int err, lock_type;
BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK);
if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL)
lock_type = CEPH_LOCK_FCNTL_INTR;
else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK)
lock_type = CEPH_LOCK_FLOCK_INTR;
else
BUG_ON(1);
BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK);
err = wait_for_completion_interruptible(&req->r_completion);
if (!err)
return 0;
dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
req->r_tid);
mutex_lock(&mdsc->mutex);
if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
err = 0;
} else {
/*
* ensure we aren't running concurrently with
* ceph_fill_trace or ceph_readdir_prepopulate, which
* rely on locks (dir mutex) held by our caller.
*/
mutex_lock(&req->r_fill_mutex);
req->r_err = err;
set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
mutex_unlock(&req->r_fill_mutex);
if (!req->r_session) {
// haven't sent the request
err = 0;
}
}
mutex_unlock(&mdsc->mutex);
if (!err)
return 0;
intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
USE_AUTH_MDS);
if (IS_ERR(intr_req))
return PTR_ERR(intr_req);
intr_req->r_inode = inode;
ihold(inode);
intr_req->r_num_caps = 1;
intr_req->r_args.filelock_change = req->r_args.filelock_change;
intr_req->r_args.filelock_change.rule = lock_type;
intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK;
err = ceph_mdsc_do_request(mdsc, inode, intr_req);
ceph_mdsc_put_request(intr_req);
if (err && err != -ERESTARTSYS)
return err;
wait_for_completion_killable(&req->r_safe_completion);
return 0;
}
/**
* Attempt to set an fcntl lock.
* For now, this just goes away to the server. Later it may be more awesome.
*/
int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
int err = 0;
u16 op = CEPH_MDS_OP_SETFILELOCK;
u8 wait = 0;
u8 lock_cmd;
if (!(fl->fl_flags & FL_POSIX))
return -ENOLCK;
/* No mandatory locks */
if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
return -ENOLCK;
dout("ceph_lock, fl_owner: %p\n", fl->fl_owner);
/* set wait bit as appropriate, then make command as Ceph expects it*/
if (IS_GETLK(cmd))
op = CEPH_MDS_OP_GETFILELOCK;
else if (IS_SETLKW(cmd))
wait = 1;
spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) {
err = -EIO;
} else if (op == CEPH_MDS_OP_SETFILELOCK) {
/*
* increasing i_filelock_ref closes race window between
* handling request reply and adding file_lock struct to
* inode. Otherwise, i_auth_cap may get trimmed in the
* window. Caller function will decrease the counter.
*/
fl->fl_ops = &ceph_fl_lock_ops;
atomic_inc(&ci->i_filelock_ref);
}
spin_unlock(&ci->i_ceph_lock);
if (err < 0) {
if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type)
posix_lock_file(file, fl, NULL);
return err;
}
if (F_RDLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_SHARED;
else if (F_WRLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_EXCL;
else
lock_cmd = CEPH_LOCK_UNLOCK;
err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl);
if (!err) {
if (op == CEPH_MDS_OP_SETFILELOCK) {
dout("mds locked, locking locally\n");
err = posix_lock_file(file, fl, NULL);
if (err) {
/* undo! This should only happen if
* the kernel detects local
* deadlock. */
ceph_lock_message(CEPH_LOCK_FCNTL, op, inode,
CEPH_LOCK_UNLOCK, 0, fl);
dout("got %d on posix_lock_file, undid lock\n",
err);
}
}
}
return err;
}
int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
int err = 0;
u8 wait = 0;
u8 lock_cmd;
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
/* No mandatory locks */
if (fl->fl_type & LOCK_MAND)
return -EOPNOTSUPP;
dout("ceph_flock, fl_file: %p\n", fl->fl_file);
spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) {
err = -EIO;
} else {
/* see comment in ceph_lock */
fl->fl_ops = &ceph_fl_lock_ops;
atomic_inc(&ci->i_filelock_ref);
}
spin_unlock(&ci->i_ceph_lock);
if (err < 0) {
if (F_UNLCK == fl->fl_type)
locks_lock_file_wait(file, fl);
return err;
}
if (IS_SETLKW(cmd))
wait = 1;
if (F_RDLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_SHARED;
else if (F_WRLCK == fl->fl_type)
lock_cmd = CEPH_LOCK_EXCL;
else
lock_cmd = CEPH_LOCK_UNLOCK;
err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
inode, lock_cmd, wait, fl);
if (!err) {
err = locks_lock_file_wait(file, fl);
if (err) {
ceph_lock_message(CEPH_LOCK_FLOCK,
CEPH_MDS_OP_SETFILELOCK,
inode, CEPH_LOCK_UNLOCK, 0, fl);
dout("got %d on locks_lock_file_wait, undid lock\n", err);
}
}
return err;
}
/*
* Fills in the passed counter variables, so you can prepare pagelist metadata
* before calling ceph_encode_locks.
*/
void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
{
struct file_lock *lock;
struct file_lock_context *ctx;
*fcntl_count = 0;
*flock_count = 0;
ctx = inode->i_flctx;
if (ctx) {
spin_lock(&ctx->flc_lock);
list_for_each_entry(lock, &ctx->flc_posix, fl_list)
++(*fcntl_count);
list_for_each_entry(lock, &ctx->flc_flock, fl_list)
++(*flock_count);
spin_unlock(&ctx->flc_lock);
}
dout("counted %d flock locks and %d fcntl locks\n",
*flock_count, *fcntl_count);
}
/*
* Given a pointer to a lock, convert it to a ceph filelock
*/
static int lock_to_ceph_filelock(struct file_lock *lock,
struct ceph_filelock *cephlock)
{
int err = 0;
cephlock->start = cpu_to_le64(lock->fl_start);
cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
cephlock->client = cpu_to_le64(0);
cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
switch (lock->fl_type) {
case F_RDLCK:
cephlock->type = CEPH_LOCK_SHARED;
break;
case F_WRLCK:
cephlock->type = CEPH_LOCK_EXCL;
break;
case F_UNLCK:
cephlock->type = CEPH_LOCK_UNLOCK;
break;
default:
dout("Have unknown lock type %d\n", lock->fl_type);
err = -EINVAL;
}
return err;
}
/**
* Encode the flock and fcntl locks for the given inode into the ceph_filelock
* array. Must be called with inode->i_lock already held.
* If we encounter more of a specific lock type than expected, return -ENOSPC.
*/
int ceph_encode_locks_to_buffer(struct inode *inode,
struct ceph_filelock *flocks,
int num_fcntl_locks, int num_flock_locks)
{
struct file_lock *lock;
struct file_lock_context *ctx = inode->i_flctx;
int err = 0;
int seen_fcntl = 0;
int seen_flock = 0;
int l = 0;
dout("encoding %d flock and %d fcntl locks\n", num_flock_locks,
num_fcntl_locks);
if (!ctx)
return 0;
spin_lock(&ctx->flc_lock);
list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
++seen_fcntl;
if (seen_fcntl > num_fcntl_locks) {
err = -ENOSPC;
goto fail;
}
err = lock_to_ceph_filelock(lock, &flocks[l]);
if (err)
goto fail;
++l;
}
list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
++seen_flock;
if (seen_flock > num_flock_locks) {
err = -ENOSPC;
goto fail;
}
err = lock_to_ceph_filelock(lock, &flocks[l]);
if (err)
goto fail;
++l;
}
fail:
spin_unlock(&ctx->flc_lock);
return err;
}
/**
* Copy the encoded flock and fcntl locks into the pagelist.
* Format is: #fcntl locks, sequential fcntl locks, #flock locks,
* sequential flock locks.
* Returns zero on success.
*/
int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
struct ceph_pagelist *pagelist,
int num_fcntl_locks, int num_flock_locks)
{
int err = 0;
__le32 nlocks;
nlocks = cpu_to_le32(num_fcntl_locks);
err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
if (err)
goto out_fail;
if (num_fcntl_locks > 0) {
err = ceph_pagelist_append(pagelist, flocks,
num_fcntl_locks * sizeof(*flocks));
if (err)
goto out_fail;
}
nlocks = cpu_to_le32(num_flock_locks);
err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
if (err)
goto out_fail;
if (num_flock_locks > 0) {
err = ceph_pagelist_append(pagelist, &flocks[num_fcntl_locks],
num_flock_locks * sizeof(*flocks));
}
out_fail:
return err;
}
+4331
View File
File diff suppressed because it is too large. Load diff
+466
View File
@@ -0,0 +1,466 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _FS_CEPH_MDS_CLIENT_H
#define _FS_CEPH_MDS_CLIENT_H
#include <linux/completion.h>
#include <linux/kref.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/refcount.h>
#include <linux/utsname.h>
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/mdsmap.h>
#include <linux/ceph/auth.h>
/* The first 8 bits are reserved for old ceph releases */
#define CEPHFS_FEATURE_MIMIC 8
#define CEPHFS_FEATURES_ALL { \
0, 1, 2, 3, 4, 5, 6, 7, \
CEPHFS_FEATURE_MIMIC, \
}
#define CEPHFS_FEATURES_CLIENT_SUPPORTED CEPHFS_FEATURES_ALL
#define CEPHFS_FEATURES_CLIENT_REQUIRED {}
/*
* Some lock dependencies:
*
* session->s_mutex
* mdsc->mutex
*
* mdsc->snap_rwsem
*
* ci->i_ceph_lock
* mdsc->snap_flush_lock
* mdsc->cap_delay_lock
*
*/
struct ceph_fs_client;
struct ceph_cap;
/*
* parsed info about a single inode. pointers are into the encoded
* on-wire structures within the mds reply message payload.
*/
struct ceph_mds_reply_info_in {
struct ceph_mds_reply_inode *in;
struct ceph_dir_layout dir_layout;
u32 symlink_len;
char *symlink;
u32 xattr_len;
char *xattr_data;
u64 inline_version;
u32 inline_len;
char *inline_data;
u32 pool_ns_len;
char *pool_ns_data;
u64 max_bytes;
u64 max_files;
};
struct ceph_mds_reply_dir_entry {
char *name;
u32 name_len;
struct ceph_mds_reply_lease *lease;
struct ceph_mds_reply_info_in inode;
loff_t offset;
};
/*
* parsed info about an mds reply, including information about
* either: 1) the target inode and/or its parent directory and dentry,
* and directory contents (for readdir results), or
* 2) the file range lock info (for fcntl F_GETLK results).
*/
struct ceph_mds_reply_info_parsed {
struct ceph_mds_reply_head *head;
/* trace */
struct ceph_mds_reply_info_in diri, targeti;
struct ceph_mds_reply_dirfrag *dirfrag;
char *dname;
u32 dname_len;
struct ceph_mds_reply_lease *dlease;
/* extra */
union {
/* for fcntl F_GETLK results */
struct ceph_filelock *filelock_reply;
/* for readdir results */
struct {
struct ceph_mds_reply_dirfrag *dir_dir;
size_t dir_buf_size;
int dir_nr;
bool dir_end;
bool dir_complete;
bool hash_order;
bool offset_hash;
struct ceph_mds_reply_dir_entry *dir_entries;
};
/* for create results */
struct {
bool has_create_ino;
u64 ino;
};
};
/* encoded blob describing snapshot contexts for certain
operations (e.g., open) */
void *snapblob;
int snapblob_len;
};
/*
* cap releases are batched and sent to the MDS en masse.
*
* Account for per-message overhead of mds_cap_release header
* and __le32 for osd epoch barrier trailing field.
*/
#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) - \
sizeof(struct ceph_mds_cap_release)) / \
sizeof(struct ceph_mds_cap_item))
/*
* state associated with each MDS<->client session
*/
enum {
CEPH_MDS_SESSION_NEW = 1,
CEPH_MDS_SESSION_OPENING = 2,
CEPH_MDS_SESSION_OPEN = 3,
CEPH_MDS_SESSION_HUNG = 4,
CEPH_MDS_SESSION_CLOSING = 5,
CEPH_MDS_SESSION_RESTARTING = 6,
CEPH_MDS_SESSION_RECONNECTING = 7,
CEPH_MDS_SESSION_REJECTED = 8,
};
struct ceph_mds_session {
struct ceph_mds_client *s_mdsc;
int s_mds;
int s_state;
unsigned long s_ttl; /* time until mds kills us */
u64 s_seq; /* incoming msg seq # */
struct mutex s_mutex; /* serialize session messages */
struct ceph_connection s_con;
struct ceph_auth_handshake s_auth;
/* protected by s_gen_ttl_lock */
spinlock_t s_gen_ttl_lock;
u32 s_cap_gen; /* inc each time we get mds stale msg */
unsigned long s_cap_ttl; /* when session caps expire */
/* protected by s_cap_lock */
spinlock_t s_cap_lock;
struct list_head s_caps; /* all caps issued by this session */
int s_nr_caps, s_trim_caps;
int s_num_cap_releases;
int s_cap_reconnect;
int s_readonly;
struct list_head s_cap_releases; /* waiting cap_release messages */
struct ceph_cap *s_cap_iterator;
/* protected by mutex */
struct list_head s_cap_flushing; /* inodes w/ flushing caps */
unsigned long s_renew_requested; /* last time we sent a renew req */
u64 s_renew_seq;
refcount_t s_ref;
struct list_head s_waiting; /* waiting requests */
struct list_head s_unsafe; /* unsafe requests */
};
/*
* modes of choosing which MDS to send a request to
*/
enum {
USE_ANY_MDS,
USE_RANDOM_MDS,
USE_AUTH_MDS, /* prefer authoritative mds for this metadata item */
};
struct ceph_mds_request;
struct ceph_mds_client;
/*
* request completion callback
*/
typedef void (*ceph_mds_request_callback_t) (struct ceph_mds_client *mdsc,
struct ceph_mds_request *req);
/*
* wait for request completion callback
*/
typedef int (*ceph_mds_request_wait_callback_t) (struct ceph_mds_client *mdsc,
struct ceph_mds_request *req);
/*
* an in-flight mds request
*/
struct ceph_mds_request {
u64 r_tid; /* transaction id */
struct rb_node r_node;
struct ceph_mds_client *r_mdsc;
int r_op; /* mds op code */
/* operation on what? */
struct inode *r_inode; /* arg1 */
struct dentry *r_dentry; /* arg1 */
struct dentry *r_old_dentry; /* arg2: rename from or link from */
struct inode *r_old_dentry_dir; /* arg2: old dentry's parent dir */
char *r_path1, *r_path2;
struct ceph_vino r_ino1, r_ino2;
struct inode *r_parent; /* parent dir inode */
struct inode *r_target_inode; /* resulting inode */
#define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */
#define CEPH_MDS_R_ABORTED (2) /* call was aborted */
#define CEPH_MDS_R_GOT_UNSAFE (3) /* got an unsafe reply */
#define CEPH_MDS_R_GOT_SAFE (4) /* got a safe reply */
#define CEPH_MDS_R_GOT_RESULT (5) /* got a result */
#define CEPH_MDS_R_DID_PREPOPULATE (6) /* prepopulated readdir */
#define CEPH_MDS_R_PARENT_LOCKED (7) /* is r_parent->i_rwsem wlocked? */
unsigned long r_req_flags;
struct mutex r_fill_mutex;
union ceph_mds_request_args r_args;
int r_fmode; /* file mode, if expecting cap */
kuid_t r_uid;
kgid_t r_gid;
struct timespec64 r_stamp;
/* for choosing which mds to send this request to */
int r_direct_mode;
u32 r_direct_hash; /* choose dir frag based on this dentry hash */
/* data payload is used for xattr ops */
struct ceph_pagelist *r_pagelist;
/* what caps shall we drop? */
int r_inode_drop, r_inode_unless;
int r_dentry_drop, r_dentry_unless;
int r_old_dentry_drop, r_old_dentry_unless;
struct inode *r_old_inode;
int r_old_inode_drop, r_old_inode_unless;
struct ceph_msg *r_request; /* original request */
int r_request_release_offset;
struct ceph_msg *r_reply;
struct ceph_mds_reply_info_parsed r_reply_info;
struct page *r_locked_page;
int r_err;
unsigned long r_timeout; /* optional. jiffies, 0 is "wait forever" */
unsigned long r_started; /* start time to measure timeout against */
unsigned long r_request_started; /* start time for mds request only,
used to measure lease durations */
/* link unsafe requests to parent directory, for fsync */
struct inode *r_unsafe_dir;
struct list_head r_unsafe_dir_item;
/* unsafe requests that modify the target inode */
struct list_head r_unsafe_target_item;
struct ceph_mds_session *r_session;
int r_attempts; /* resend attempts */
int r_num_fwd; /* number of forward attempts */
int r_resend_mds; /* mds to resend to next, if any*/
u32 r_sent_on_mseq; /* cap mseq request was sent at*/
struct kref r_kref;
struct list_head r_wait;
struct completion r_completion;
struct completion r_safe_completion;
ceph_mds_request_callback_t r_callback;
ceph_mds_request_wait_callback_t r_wait_for_completion;
struct list_head r_unsafe_item; /* per-session unsafe list item */
long long r_dir_release_cnt;
long long r_dir_ordered_cnt;
int r_readdir_cache_idx;
u32 r_readdir_offset;
struct ceph_cap_reservation r_caps_reservation;
int r_num_caps;
};
struct ceph_pool_perm {
struct rb_node node;
int perm;
s64 pool;
size_t pool_ns_len;
char pool_ns[];
};
/*
* mds client state
*/
struct ceph_mds_client {
struct ceph_fs_client *fsc;
struct mutex mutex; /* all nested structures */
struct ceph_mdsmap *mdsmap;
struct completion safe_umount_waiters;
wait_queue_head_t session_close_wq;
struct list_head waiting_for_map;
int mdsmap_err;
struct ceph_mds_session **sessions; /* NULL for mds if no session */
atomic_t num_sessions;
int max_sessions; /* len of s_mds_sessions */
int stopping; /* true if shutting down */
atomic64_t quotarealms_count; /* # realms with quota */
/*
* snap_rwsem will cover cap linkage into snaprealms, and
* realm snap contexts. (later, we can do per-realm snap
* contexts locks..) the empty list contains realms with no
* references (implying they contain no inodes with caps) that
* should be destroyed.
*/
u64 last_snap_seq;
struct rw_semaphore snap_rwsem;
struct rb_root snap_realms;
struct list_head snap_empty;
spinlock_t snap_empty_lock; /* protect snap_empty */
u64 last_tid; /* most recent mds request */
u64 oldest_tid; /* oldest incomplete mds request,
excluding setfilelock requests */
struct rb_root request_tree; /* pending mds requests */
struct delayed_work delayed_work; /* delayed work */
unsigned long last_renew_caps; /* last time we renewed our caps */
struct list_head cap_delay_list; /* caps with delayed release */
spinlock_t cap_delay_lock; /* protects cap_delay_list */
struct list_head snap_flush_list; /* cap_snaps ready to flush */
spinlock_t snap_flush_lock;
u64 last_cap_flush_tid;
struct list_head cap_flush_list;
struct list_head cap_dirty; /* inodes with dirty caps */
struct list_head cap_dirty_migrating; /* ...that are migration... */
int num_cap_flushing; /* # caps we are flushing */
spinlock_t cap_dirty_lock; /* protects above items */
wait_queue_head_t cap_flushing_wq;
/*
* Cap reservations
*
* Maintain a global pool of preallocated struct ceph_caps, referenced
* by struct ceph_caps_reservations. This ensures that we preallocate
* memory needed to successfully process an MDS response. (If an MDS
* sends us cap information and we fail to process it, we will have
* problems due to the client and MDS being out of sync.)
*
* Reservations are 'owned' by a ceph_cap_reservation context.
*/
spinlock_t caps_list_lock;
struct list_head caps_list; /* unused (reserved or
unreserved) */
int caps_total_count; /* total caps allocated */
int caps_use_count; /* in use */
int caps_reserve_count; /* unused, reserved */
int caps_avail_count; /* unused, unreserved */
int caps_min_count; /* keep at least this many
(unreserved) */
spinlock_t dentry_lru_lock;
struct list_head dentry_lru;
int num_dentry;
struct rw_semaphore pool_perm_rwsem;
struct rb_root pool_perm_tree;
char nodename[__NEW_UTS_LEN + 1];
};
extern const char *ceph_mds_op_name(int op);
extern struct ceph_mds_session *
__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
static inline struct ceph_mds_session *
ceph_get_mds_session(struct ceph_mds_session *s)
{
refcount_inc(&s->s_ref);
return s;
}
extern const char *ceph_session_state_name(int s);
extern void ceph_put_mds_session(struct ceph_mds_session *s);
extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
struct ceph_msg *msg, int mds);
extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc);
extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
extern void ceph_invalidate_dir_request(struct ceph_mds_request *req);
extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req,
struct inode *dir);
extern struct ceph_mds_request *
ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode);
extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc,
struct ceph_mds_request *req);
extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
struct inode *dir,
struct ceph_mds_request *req);
static inline void ceph_mdsc_get_request(struct ceph_mds_request *req)
{
kref_get(&req->r_kref);
}
extern void ceph_mdsc_release_request(struct kref *kref);
static inline void ceph_mdsc_put_request(struct ceph_mds_request *req)
{
kref_put(&req->r_kref, ceph_mdsc_release_request);
}
extern void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
int stop_on_nosnap);
extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
struct inode *inode,
struct dentry *dentry, char action,
u32 seq);
extern void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc,
struct ceph_msg *msg);
extern void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc,
struct ceph_msg *msg);
extern struct ceph_mds_session *
ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target);
extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session,
int max_caps);
#endif
+396
View File
@@ -0,0 +1,396 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/bug.h>
#include <linux/err.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/ceph/mdsmap.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/decode.h>
#include "super.h"
/*
* choose a random mds that is "up" (i.e. has a state > 0), or -1.
*/
int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
{
int n = 0;
int i;
/* special case for one mds */
if (1 == m->m_num_mds && m->m_info[0].state > 0)
return 0;
/* count */
for (i = 0; i < m->m_num_mds; i++)
if (m->m_info[i].state > 0)
n++;
if (n == 0)
return -1;
/* pick */
n = prandom_u32() % n;
i = 0;
for (i = 0; n > 0; i++, n--)
while (m->m_info[i].state <= 0)
i++;
return i;
}
#define __decode_and_drop_type(p, end, type, bad) \
do { \
if (*p + sizeof(type) > end) \
goto bad; \
*p += sizeof(type); \
} while (0)
#define __decode_and_drop_set(p, end, type, bad) \
do { \
u32 n; \
size_t need; \
ceph_decode_32_safe(p, end, n, bad); \
need = sizeof(type) * n; \
ceph_decode_need(p, end, need, bad); \
*p += need; \
} while (0)
#define __decode_and_drop_map(p, end, ktype, vtype, bad) \
do { \
u32 n; \
size_t need; \
ceph_decode_32_safe(p, end, n, bad); \
need = (sizeof(ktype) + sizeof(vtype)) * n; \
ceph_decode_need(p, end, need, bad); \
*p += need; \
} while (0)
static int __decode_and_drop_compat_set(void **p, void* end)
{
int i;
/* compat, ro_compat, incompat*/
for (i = 0; i < 3; i++) {
u32 n;
ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
/* mask */
*p += sizeof(u64);
/* names (map<u64, string>) */
n = ceph_decode_32(p);
while (n-- > 0) {
u32 len;
ceph_decode_need(p, end, sizeof(u64) + sizeof(u32),
bad);
*p += sizeof(u64);
len = ceph_decode_32(p);
ceph_decode_need(p, end, len, bad);
*p += len;
}
}
return 0;
bad:
return -1;
}
/*
* Decode an MDS map
*
* Ignore any fields we don't care about (there are quite a few of
* them).
*/
struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
{
struct ceph_mdsmap *m;
const void *start = *p;
int i, j, n;
int err = -EINVAL;
u8 mdsmap_v, mdsmap_cv;
u16 mdsmap_ev;
m = kzalloc(sizeof(*m), GFP_NOFS);
if (!m)
return ERR_PTR(-ENOMEM);
ceph_decode_need(p, end, 1 + 1, bad);
mdsmap_v = ceph_decode_8(p);
mdsmap_cv = ceph_decode_8(p);
if (mdsmap_v >= 4) {
u32 mdsmap_len;
ceph_decode_32_safe(p, end, mdsmap_len, bad);
if (end < *p + mdsmap_len)
goto bad;
end = *p + mdsmap_len;
}
ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
m->m_epoch = ceph_decode_32(p);
m->m_client_epoch = ceph_decode_32(p);
m->m_last_failure = ceph_decode_32(p);
m->m_root = ceph_decode_32(p);
m->m_session_timeout = ceph_decode_32(p);
m->m_session_autoclose = ceph_decode_32(p);
m->m_max_file_size = ceph_decode_64(p);
m->m_max_mds = ceph_decode_32(p);
m->m_num_mds = m->m_max_mds;
m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS);
if (!m->m_info)
goto nomem;
/* pick out active nodes from mds_info (state > 0) */
n = ceph_decode_32(p);
for (i = 0; i < n; i++) {
u64 global_id;
u32 namelen;
s32 mds, inc, state;
u64 state_seq;
u8 info_v;
void *info_end = NULL;
struct ceph_entity_addr addr;
u32 num_export_targets;
void *pexport_targets = NULL;
struct ceph_timespec laggy_since;
struct ceph_mds_info *info;
ceph_decode_need(p, end, sizeof(u64) + 1, bad);
global_id = ceph_decode_64(p);
info_v= ceph_decode_8(p);
if (info_v >= 4) {
u32 info_len;
u8 info_cv;
ceph_decode_need(p, end, 1 + sizeof(u32), bad);
info_cv = ceph_decode_8(p);
info_len = ceph_decode_32(p);
info_end = *p + info_len;
if (info_end > end)
goto bad;
}
ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad);
*p += sizeof(u64);
namelen = ceph_decode_32(p); /* skip mds name */
*p += namelen;
ceph_decode_need(p, end,
4*sizeof(u32) + sizeof(u64) +
sizeof(addr) + sizeof(struct ceph_timespec),
bad);
mds = ceph_decode_32(p);
inc = ceph_decode_32(p);
state = ceph_decode_32(p);
state_seq = ceph_decode_64(p);
ceph_decode_copy(p, &addr, sizeof(addr));
ceph_decode_addr(&addr);
ceph_decode_copy(p, &laggy_since, sizeof(laggy_since));
*p += sizeof(u32);
ceph_decode_32_safe(p, end, namelen, bad);
*p += namelen;
if (info_v >= 2) {
ceph_decode_32_safe(p, end, num_export_targets, bad);
pexport_targets = *p;
*p += num_export_targets * sizeof(u32);
} else {
num_export_targets = 0;
}
if (info_end && *p != info_end) {
if (*p > info_end)
goto bad;
*p = info_end;
}
dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
i+1, n, global_id, mds, inc,
ceph_pr_addr(&addr.in_addr),
ceph_mds_state_name(state));
if (mds < 0 || state <= 0)
continue;
if (mds >= m->m_num_mds) {
int new_num = max(mds + 1, m->m_num_mds * 2);
void *new_m_info = krealloc(m->m_info,
new_num * sizeof(*m->m_info),
GFP_NOFS | __GFP_ZERO);
if (!new_m_info)
goto nomem;
m->m_info = new_m_info;
m->m_num_mds = new_num;
}
info = &m->m_info[mds];
info->global_id = global_id;
info->state = state;
info->addr = addr;
info->laggy = (laggy_since.tv_sec != 0 ||
laggy_since.tv_nsec != 0);
info->num_export_targets = num_export_targets;
if (num_export_targets) {
info->export_targets = kcalloc(num_export_targets,
sizeof(u32), GFP_NOFS);
if (!info->export_targets)
goto nomem;
for (j = 0; j < num_export_targets; j++)
info->export_targets[j] =
ceph_decode_32(&pexport_targets);
} else {
info->export_targets = NULL;
}
}
if (m->m_num_mds > m->m_max_mds) {
/* find max up mds */
for (i = m->m_num_mds; i >= m->m_max_mds; i--) {
if (i == 0 || m->m_info[i-1].state > 0)
break;
}
m->m_num_mds = i;
}
/* pg_pools */
ceph_decode_32_safe(p, end, n, bad);
m->m_num_data_pg_pools = n;
m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS);
if (!m->m_data_pg_pools)
goto nomem;
ceph_decode_need(p, end, sizeof(u64)*(n+1), bad);
for (i = 0; i < n; i++)
m->m_data_pg_pools[i] = ceph_decode_64(p);
m->m_cas_pg_pool = ceph_decode_64(p);
m->m_enabled = m->m_epoch > 1;
mdsmap_ev = 1;
if (mdsmap_v >= 2) {
ceph_decode_16_safe(p, end, mdsmap_ev, bad_ext);
}
if (mdsmap_ev >= 3) {
if (__decode_and_drop_compat_set(p, end) < 0)
goto bad_ext;
}
/* metadata_pool */
if (mdsmap_ev < 5) {
__decode_and_drop_type(p, end, u32, bad_ext);
} else {
__decode_and_drop_type(p, end, u64, bad_ext);
}
/* created + modified + tableserver */
__decode_and_drop_type(p, end, struct ceph_timespec, bad_ext);
__decode_and_drop_type(p, end, struct ceph_timespec, bad_ext);
__decode_and_drop_type(p, end, u32, bad_ext);
/* in */
{
int num_laggy = 0;
ceph_decode_32_safe(p, end, n, bad_ext);
ceph_decode_need(p, end, sizeof(u32) * n, bad_ext);
for (i = 0; i < n; i++) {
s32 mds = ceph_decode_32(p);
if (mds >= 0 && mds < m->m_num_mds) {
if (m->m_info[mds].laggy)
num_laggy++;
}
}
m->m_num_laggy = num_laggy;
if (n > m->m_num_mds) {
void *new_m_info = krealloc(m->m_info,
n * sizeof(*m->m_info),
GFP_NOFS | __GFP_ZERO);
if (!new_m_info)
goto nomem;
m->m_info = new_m_info;
}
m->m_num_mds = n;
}
/* inc */
__decode_and_drop_map(p, end, u32, u32, bad_ext);
/* up */
__decode_and_drop_map(p, end, u32, u64, bad_ext);
/* failed */
__decode_and_drop_set(p, end, u32, bad_ext);
/* stopped */
__decode_and_drop_set(p, end, u32, bad_ext);
if (mdsmap_ev >= 4) {
/* last_failure_osd_epoch */
__decode_and_drop_type(p, end, u32, bad_ext);
}
if (mdsmap_ev >= 6) {
/* ever_allowed_snaps */
__decode_and_drop_type(p, end, u8, bad_ext);
/* explicitly_allowed_snaps */
__decode_and_drop_type(p, end, u8, bad_ext);
}
if (mdsmap_ev >= 7) {
/* inline_data_enabled */
__decode_and_drop_type(p, end, u8, bad_ext);
}
if (mdsmap_ev >= 8) {
u32 name_len;
/* enabled */
ceph_decode_8_safe(p, end, m->m_enabled, bad_ext);
ceph_decode_32_safe(p, end, name_len, bad_ext);
ceph_decode_need(p, end, name_len, bad_ext);
*p += name_len;
}
/* damaged */
if (mdsmap_ev >= 9) {
size_t need;
ceph_decode_32_safe(p, end, n, bad_ext);
need = sizeof(u32) * n;
ceph_decode_need(p, end, need, bad_ext);
*p += need;
m->m_damaged = n > 0;
} else {
m->m_damaged = false;
}
bad_ext:
*p = end;
dout("mdsmap_decode success epoch %u\n", m->m_epoch);
return m;
nomem:
err = -ENOMEM;
goto out_err;
bad:
pr_err("corrupt mdsmap\n");
print_hex_dump(KERN_DEBUG, "mdsmap: ",
DUMP_PREFIX_OFFSET, 16, 1,
start, end - start, true);
out_err:
ceph_mdsmap_destroy(m);
return ERR_PTR(err);
}
void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
{
int i;
for (i = 0; i < m->m_num_mds; i++)
kfree(m->m_info[i].export_targets);
kfree(m->m_info);
kfree(m->m_data_pg_pools);
kfree(m);
}
bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m)
{
int i, nr_active = 0;
if (!m->m_enabled)
return false;
if (m->m_damaged)
return false;
if (m->m_num_laggy > 0)
return false;
for (i = 0; i < m->m_num_mds; i++) {
if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
nr_active++;
}
return nr_active > 0;
}
+362
View File
@@ -0,0 +1,362 @@
// SPDX-License-Identifier: GPL-2.0
/*
* quota.c - CephFS quota
*
* Copyright (C) 2017-2018 SUSE
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/statfs.h>
#include "super.h"
#include "mds_client.h"
void ceph_adjust_quota_realms_count(struct inode *inode, bool inc)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
if (inc)
atomic64_inc(&mdsc->quotarealms_count);
else
atomic64_dec(&mdsc->quotarealms_count);
}
static inline bool ceph_has_realms_with_quotas(struct inode *inode)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
return atomic64_read(&mdsc->quotarealms_count) > 0;
}
void ceph_handle_quota(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session,
struct ceph_msg *msg)
{
struct super_block *sb = mdsc->fsc->sb;
struct ceph_mds_quota *h = msg->front.iov_base;
struct ceph_vino vino;
struct inode *inode;
struct ceph_inode_info *ci;
if (msg->front.iov_len < sizeof(*h)) {
pr_err("%s corrupt message mds%d len %d\n", __func__,
session->s_mds, (int)msg->front.iov_len);
ceph_msg_dump(msg);
return;
}
/* increment msg sequence number */
mutex_lock(&session->s_mutex);
session->s_seq++;
mutex_unlock(&session->s_mutex);
/* lookup inode */
vino.ino = le64_to_cpu(h->ino);
vino.snap = CEPH_NOSNAP;
inode = ceph_find_inode(sb, vino);
if (!inode) {
pr_warn("Failed to find inode %llu\n", vino.ino);
return;
}
ci = ceph_inode(inode);
spin_lock(&ci->i_ceph_lock);
ci->i_rbytes = le64_to_cpu(h->rbytes);
ci->i_rfiles = le64_to_cpu(h->rfiles);
ci->i_rsubdirs = le64_to_cpu(h->rsubdirs);
__ceph_update_quota(ci, le64_to_cpu(h->max_bytes),
le64_to_cpu(h->max_files));
spin_unlock(&ci->i_ceph_lock);
iput(inode);
}
/*
* This function walks through the snaprealm for an inode and returns the
* ceph_snap_realm for the first snaprealm that has quotas set (either max_files
* or max_bytes). If the root is reached, return the root ceph_snap_realm
* instead.
*
* Note that the caller is responsible for calling ceph_put_snap_realm() on the
* returned realm.
*/
static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
struct inode *inode)
{
struct ceph_inode_info *ci = NULL;
struct ceph_snap_realm *realm, *next;
struct inode *in;
bool has_quota;
if (ceph_snap(inode) != CEPH_NOSNAP)
return NULL;
realm = ceph_inode(inode)->i_snap_realm;
if (realm)
ceph_get_snap_realm(mdsc, realm);
else
pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) "
"null i_snap_realm\n", ceph_vinop(inode));
while (realm) {
spin_lock(&realm->inodes_with_caps_lock);
in = realm->inode ? igrab(realm->inode) : NULL;
spin_unlock(&realm->inodes_with_caps_lock);
if (!in)
break;
ci = ceph_inode(in);
has_quota = __ceph_has_any_quota(ci);
iput(in);
next = realm->parent;
if (has_quota || !next)
return realm;
ceph_get_snap_realm(mdsc, next);
ceph_put_snap_realm(mdsc, realm);
realm = next;
}
if (realm)
ceph_put_snap_realm(mdsc, realm);
return NULL;
}
bool ceph_quota_is_same_realm(struct inode *old, struct inode *new)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(old)->mdsc;
struct ceph_snap_realm *old_realm, *new_realm;
bool is_same;
down_read(&mdsc->snap_rwsem);
old_realm = get_quota_realm(mdsc, old);
new_realm = get_quota_realm(mdsc, new);
is_same = (old_realm == new_realm);
up_read(&mdsc->snap_rwsem);
if (old_realm)
ceph_put_snap_realm(mdsc, old_realm);
if (new_realm)
ceph_put_snap_realm(mdsc, new_realm);
return is_same;
}
enum quota_check_op {
QUOTA_CHECK_MAX_FILES_OP, /* check quota max_files limit */
QUOTA_CHECK_MAX_BYTES_OP, /* check quota max_files limit */
QUOTA_CHECK_MAX_BYTES_APPROACHING_OP /* check if quota max_files
limit is approaching */
};
/*
* check_quota_exceeded() will walk up the snaprealm hierarchy and, for each
* realm, it will execute quota check operation defined by the 'op' parameter.
* The snaprealm walk is interrupted if the quota check detects that the quota
* is exceeded or if the root inode is reached.
*/
static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op,
loff_t delta)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci;
struct ceph_snap_realm *realm, *next;
struct inode *in;
u64 max, rvalue;
bool exceeded = false;
if (ceph_snap(inode) != CEPH_NOSNAP)
return false;
down_read(&mdsc->snap_rwsem);
realm = ceph_inode(inode)->i_snap_realm;
if (realm)
ceph_get_snap_realm(mdsc, realm);
else
pr_err_ratelimited("check_quota_exceeded: ino (%llx.%llx) "
"null i_snap_realm\n", ceph_vinop(inode));
while (realm) {
spin_lock(&realm->inodes_with_caps_lock);
in = realm->inode ? igrab(realm->inode) : NULL;
spin_unlock(&realm->inodes_with_caps_lock);
if (!in)
break;
ci = ceph_inode(in);
spin_lock(&ci->i_ceph_lock);
if (op == QUOTA_CHECK_MAX_FILES_OP) {
max = ci->i_max_files;
rvalue = ci->i_rfiles + ci->i_rsubdirs;
} else {
max = ci->i_max_bytes;
rvalue = ci->i_rbytes;
}
spin_unlock(&ci->i_ceph_lock);
switch (op) {
case QUOTA_CHECK_MAX_FILES_OP:
exceeded = (max && (rvalue >= max));
break;
case QUOTA_CHECK_MAX_BYTES_OP:
exceeded = (max && (rvalue + delta > max));
break;
case QUOTA_CHECK_MAX_BYTES_APPROACHING_OP:
if (max) {
if (rvalue >= max)
exceeded = true;
else {
/*
* when we're writing more that 1/16th
* of the available space
*/
exceeded =
(((max - rvalue) >> 4) < delta);
}
}
break;
default:
/* Shouldn't happen */
pr_warn("Invalid quota check op (%d)\n", op);
exceeded = true; /* Just break the loop */
}
iput(in);
next = realm->parent;
if (exceeded || !next)
break;
ceph_get_snap_realm(mdsc, next);
ceph_put_snap_realm(mdsc, realm);
realm = next;
}
if (realm)
ceph_put_snap_realm(mdsc, realm);
up_read(&mdsc->snap_rwsem);
return exceeded;
}
/*
* ceph_quota_is_max_files_exceeded - check if we can create a new file
* @inode: directory where a new file is being created
*
* This functions returns true is max_files quota allows a new file to be
* created. It is necessary to walk through the snaprealm hierarchy (until the
* FS root) to check all realms with quotas set.
*/
bool ceph_quota_is_max_files_exceeded(struct inode *inode)
{
if (!ceph_has_realms_with_quotas(inode))
return false;
WARN_ON(!S_ISDIR(inode->i_mode));
return check_quota_exceeded(inode, QUOTA_CHECK_MAX_FILES_OP, 0);
}
/*
* ceph_quota_is_max_bytes_exceeded - check if we can write to a file
* @inode: inode being written
* @newsize: new size if write succeeds
*
* This functions returns true is max_bytes quota allows a file size to reach
* @newsize; it returns false otherwise.
*/
bool ceph_quota_is_max_bytes_exceeded(struct inode *inode, loff_t newsize)
{
loff_t size = i_size_read(inode);
if (!ceph_has_realms_with_quotas(inode))
return false;
/* return immediately if we're decreasing file size */
if (newsize <= size)
return false;
return check_quota_exceeded(inode, QUOTA_CHECK_MAX_BYTES_OP, (newsize - size));
}
/*
* ceph_quota_is_max_bytes_approaching - check if we're reaching max_bytes
* @inode: inode being written
* @newsize: new size if write succeeds
*
* This function returns true if the new file size @newsize will be consuming
* more than 1/16th of the available quota space; it returns false otherwise.
*/
bool ceph_quota_is_max_bytes_approaching(struct inode *inode, loff_t newsize)
{
loff_t size = ceph_inode(inode)->i_reported_size;
if (!ceph_has_realms_with_quotas(inode))
return false;
/* return immediately if we're decreasing file size */
if (newsize <= size)
return false;
return check_quota_exceeded(inode, QUOTA_CHECK_MAX_BYTES_APPROACHING_OP,
(newsize - size));
}
/*
* ceph_quota_update_statfs - if root has quota update statfs with quota status
* @fsc: filesystem client instance
* @buf: statfs to update
*
* If the mounted filesystem root has max_bytes quota set, update the filesystem
* statistics with the quota status.
*
* This function returns true if the stats have been updated, false otherwise.
*/
bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf)
{
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_inode_info *ci;
struct ceph_snap_realm *realm;
struct inode *in;
u64 total = 0, used, free;
bool is_updated = false;
down_read(&mdsc->snap_rwsem);
realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root));
up_read(&mdsc->snap_rwsem);
if (!realm)
return false;
spin_lock(&realm->inodes_with_caps_lock);
in = realm->inode ? igrab(realm->inode) : NULL;
spin_unlock(&realm->inodes_with_caps_lock);
if (in) {
ci = ceph_inode(in);
spin_lock(&ci->i_ceph_lock);
if (ci->i_max_bytes) {
total = ci->i_max_bytes >> CEPH_BLOCK_SHIFT;
used = ci->i_rbytes >> CEPH_BLOCK_SHIFT;
/* It is possible for a quota to be exceeded.
* Report 'zero' in that case
*/
free = total > used ? total - used : 0;
}
spin_unlock(&ci->i_ceph_lock);
if (total) {
buf->f_blocks = total;
buf->f_bfree = free;
buf->f_bavail = free;
is_updated = true;
}
iput(in);
}
ceph_put_snap_realm(mdsc, realm);
return is_updated;
}
+995
View File
@@ -0,0 +1,995 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/sort.h>
#include <linux/slab.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/decode.h>
/*
* Snapshots in ceph are driven in large part by cooperation from the
* client. In contrast to local file systems or file servers that
* implement snapshots at a single point in the system, ceph's
* distributed access to storage requires clients to help decide
* whether a write logically occurs before or after a recently created
* snapshot.
*
* This provides a perfect instantanous client-wide snapshot. Between
* clients, however, snapshots may appear to be applied at slightly
* different points in time, depending on delays in delivering the
* snapshot notification.
*
* Snapshots are _not_ file system-wide. Instead, each snapshot
* applies to the subdirectory nested beneath some directory. This
* effectively divides the hierarchy into multiple "realms," where all
* of the files contained by each realm share the same set of
* snapshots. An individual realm's snap set contains snapshots
* explicitly created on that realm, as well as any snaps in its
* parent's snap set _after_ the point at which the parent became it's
* parent (due to, say, a rename). Similarly, snaps from prior parents
* during the time intervals during which they were the parent are included.
*
* The client is spared most of this detail, fortunately... it must only
* maintains a hierarchy of realms reflecting the current parent/child
* realm relationship, and for each realm has an explicit list of snaps
* inherited from prior parents.
*
* A snap_realm struct is maintained for realms containing every inode
* with an open cap in the system. (The needed snap realm information is
* provided by the MDS whenever a cap is issued, i.e., on open.) A 'seq'
* version number is used to ensure that as realm parameters change (new
* snapshot, new parent, etc.) the client's realm hierarchy is updated.
*
* The realm hierarchy drives the generation of a 'snap context' for each
* realm, which simply lists the resulting set of snaps for the realm. This
* is attached to any writes sent to OSDs.
*/
/*
* Unfortunately error handling is a bit mixed here. If we get a snap
* update, but don't have enough memory to update our realm hierarchy,
* it's not clear what we can do about it (besides complaining to the
* console).
*/
/*
* increase ref count for the realm
*
* caller must hold snap_rwsem for write.
*/
void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm)
{
dout("get_realm %p %d -> %d\n", realm,
atomic_read(&realm->nref), atomic_read(&realm->nref)+1);
/*
* since we _only_ increment realm refs or empty the empty
* list with snap_rwsem held, adjusting the empty list here is
* safe. we do need to protect against concurrent empty list
* additions, however.
*/
if (atomic_inc_return(&realm->nref) == 1) {
spin_lock(&mdsc->snap_empty_lock);
list_del_init(&realm->empty_item);
spin_unlock(&mdsc->snap_empty_lock);
}
}
static void __insert_snap_realm(struct rb_root *root,
struct ceph_snap_realm *new)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct ceph_snap_realm *r = NULL;
while (*p) {
parent = *p;
r = rb_entry(parent, struct ceph_snap_realm, node);
if (new->ino < r->ino)
p = &(*p)->rb_left;
else if (new->ino > r->ino)
p = &(*p)->rb_right;
else
BUG();
}
rb_link_node(&new->node, parent, p);
rb_insert_color(&new->node, root);
}
/*
* create and get the realm rooted at @ino and bump its ref count.
*
* caller must hold snap_rwsem for write.
*/
static struct ceph_snap_realm *ceph_create_snap_realm(
struct ceph_mds_client *mdsc,
u64 ino)
{
struct ceph_snap_realm *realm;
realm = kzalloc(sizeof(*realm), GFP_NOFS);
if (!realm)
return ERR_PTR(-ENOMEM);
atomic_set(&realm->nref, 1); /* for caller */
realm->ino = ino;
INIT_LIST_HEAD(&realm->children);
INIT_LIST_HEAD(&realm->child_item);
INIT_LIST_HEAD(&realm->empty_item);
INIT_LIST_HEAD(&realm->dirty_item);
INIT_LIST_HEAD(&realm->inodes_with_caps);
spin_lock_init(&realm->inodes_with_caps_lock);
__insert_snap_realm(&mdsc->snap_realms, realm);
dout("create_snap_realm %llx %p\n", realm->ino, realm);
return realm;
}
/*
* lookup the realm rooted at @ino.
*
* caller must hold snap_rwsem for write.
*/
static struct ceph_snap_realm *__lookup_snap_realm(struct ceph_mds_client *mdsc,
u64 ino)
{
struct rb_node *n = mdsc->snap_realms.rb_node;
struct ceph_snap_realm *r;
while (n) {
r = rb_entry(n, struct ceph_snap_realm, node);
if (ino < r->ino)
n = n->rb_left;
else if (ino > r->ino)
n = n->rb_right;
else {
dout("lookup_snap_realm %llx %p\n", r->ino, r);
return r;
}
}
return NULL;
}
struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
u64 ino)
{
struct ceph_snap_realm *r;
r = __lookup_snap_realm(mdsc, ino);
if (r)
ceph_get_snap_realm(mdsc, r);
return r;
}
static void __put_snap_realm(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm);
/*
* called with snap_rwsem (write)
*/
static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm)
{
dout("__destroy_snap_realm %p %llx\n", realm, realm->ino);
rb_erase(&realm->node, &mdsc->snap_realms);
if (realm->parent) {
list_del_init(&realm->child_item);
__put_snap_realm(mdsc, realm->parent);
}
kfree(realm->prior_parent_snaps);
kfree(realm->snaps);
ceph_put_snap_context(realm->cached_context);
kfree(realm);
}
/*
* caller holds snap_rwsem (write)
*/
static void __put_snap_realm(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm)
{
dout("__put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
if (atomic_dec_and_test(&realm->nref))
__destroy_snap_realm(mdsc, realm);
}
/*
* caller needn't hold any locks
*/
void ceph_put_snap_realm(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm)
{
dout("put_snap_realm %llx %p %d -> %d\n", realm->ino, realm,
atomic_read(&realm->nref), atomic_read(&realm->nref)-1);
if (!atomic_dec_and_test(&realm->nref))
return;
if (down_write_trylock(&mdsc->snap_rwsem)) {
__destroy_snap_realm(mdsc, realm);
up_write(&mdsc->snap_rwsem);
} else {
spin_lock(&mdsc->snap_empty_lock);
list_add(&realm->empty_item, &mdsc->snap_empty);
spin_unlock(&mdsc->snap_empty_lock);
}
}
/*
* Clean up any realms whose ref counts have dropped to zero. Note
* that this does not include realms who were created but not yet
* used.
*
* Called under snap_rwsem (write)
*/
static void __cleanup_empty_realms(struct ceph_mds_client *mdsc)
{
struct ceph_snap_realm *realm;
spin_lock(&mdsc->snap_empty_lock);
while (!list_empty(&mdsc->snap_empty)) {
realm = list_first_entry(&mdsc->snap_empty,
struct ceph_snap_realm, empty_item);
list_del(&realm->empty_item);
spin_unlock(&mdsc->snap_empty_lock);
__destroy_snap_realm(mdsc, realm);
spin_lock(&mdsc->snap_empty_lock);
}
spin_unlock(&mdsc->snap_empty_lock);
}
void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc)
{
down_write(&mdsc->snap_rwsem);
__cleanup_empty_realms(mdsc);
up_write(&mdsc->snap_rwsem);
}
/*
* adjust the parent realm of a given @realm. adjust child list, and parent
* pointers, and ref counts appropriately.
*
* return true if parent was changed, 0 if unchanged, <0 on error.
*
* caller must hold snap_rwsem for write.
*/
static int adjust_snap_realm_parent(struct ceph_mds_client *mdsc,
struct ceph_snap_realm *realm,
u64 parentino)
{
struct ceph_snap_realm *parent;
if (realm->parent_ino == parentino)
return 0;
parent = ceph_lookup_snap_realm(mdsc, parentino);
if (!parent) {
parent = ceph_create_snap_realm(mdsc, parentino);
if (IS_ERR(parent))
return PTR_ERR(parent);
}
dout("adjust_snap_realm_parent %llx %p: %llx %p -> %llx %p\n",
realm->ino, realm, realm->parent_ino, realm->parent,
parentino, parent);
if (realm->parent) {
list_del_init(&realm->child_item);
ceph_put_snap_realm(mdsc, realm->parent);
}
realm->parent_ino = parentino;
realm->parent = parent;
list_add(&realm->child_item, &parent->children);
return 1;
}
static int cmpu64_rev(const void *a, const void *b)
{
if (*(u64 *)a < *(u64 *)b)
return 1;
if (*(u64 *)a > *(u64 *)b)
return -1;
return 0;
}
/*
* build the snap context for a given realm.
*/
static int build_snap_context(struct ceph_snap_realm *realm,
struct list_head* dirty_realms)
{
struct ceph_snap_realm *parent = realm->parent;
struct ceph_snap_context *snapc;
int err = 0;
u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
/*
* build parent context, if it hasn't been built.
* conservatively estimate that all parent snaps might be
* included by us.
*/
if (parent) {
if (!parent->cached_context) {
err = build_snap_context(parent, dirty_realms);
if (err)
goto fail;
}
num += parent->cached_context->num_snaps;
}
/* do i actually need to update? not if my context seq
matches realm seq, and my parents' does to. (this works
because we rebuild_snap_realms() works _downward_ in
hierarchy after each update.) */
if (realm->cached_context &&
realm->cached_context->seq == realm->seq &&
(!parent ||
realm->cached_context->seq >= parent->cached_context->seq)) {
dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
" (unchanged)\n",
realm->ino, realm, realm->cached_context,
realm->cached_context->seq,
(unsigned int)realm->cached_context->num_snaps);
return 0;
}
/* alloc new snap context */
err = -ENOMEM;
if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
goto fail;
snapc = ceph_create_snap_context(num, GFP_NOFS);
if (!snapc)
goto fail;
/* build (reverse sorted) snap vector */
num = 0;
snapc->seq = realm->seq;
if (parent) {
u32 i;
/* include any of parent's snaps occurring _after_ my
parent became my parent */
for (i = 0; i < parent->cached_context->num_snaps; i++)
if (parent->cached_context->snaps[i] >=
realm->parent_since)
snapc->snaps[num++] =
parent->cached_context->snaps[i];
if (parent->cached_context->seq > snapc->seq)
snapc->seq = parent->cached_context->seq;
}
memcpy(snapc->snaps + num, realm->snaps,
sizeof(u64)*realm->num_snaps);
num += realm->num_snaps;
memcpy(snapc->snaps + num, realm->prior_parent_snaps,
sizeof(u64)*realm->num_prior_parent_snaps);
num += realm->num_prior_parent_snaps;
sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
snapc->num_snaps = num;
dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
realm->ino, realm, snapc, snapc->seq,
(unsigned int) snapc->num_snaps);
ceph_put_snap_context(realm->cached_context);
realm->cached_context = snapc;
/* queue realm for cap_snap creation */
list_add_tail(&realm->dirty_item, dirty_realms);
return 0;
fail:
/*
* if we fail, clear old (incorrect) cached_context... hopefully
* we'll have better luck building it later
*/
if (realm->cached_context) {
ceph_put_snap_context(realm->cached_context);
realm->cached_context = NULL;
}
pr_err("build_snap_context %llx %p fail %d\n", realm->ino,
realm, err);
return err;
}
/*
* rebuild snap context for the given realm and all of its children.
*/
static void rebuild_snap_realms(struct ceph_snap_realm *realm,
struct list_head *dirty_realms)
{
struct ceph_snap_realm *child;
dout("rebuild_snap_realms %llx %p\n", realm->ino, realm);
build_snap_context(realm, dirty_realms);
list_for_each_entry(child, &realm->children, child_item)
rebuild_snap_realms(child, dirty_realms);
}
/*
* helper to allocate and decode an array of snapids. free prior
* instance, if any.
*/
static int dup_array(u64 **dst, __le64 *src, u32 num)
{
u32 i;
kfree(*dst);
if (num) {
*dst = kcalloc(num, sizeof(u64), GFP_NOFS);
if (!*dst)
return -ENOMEM;
for (i = 0; i < num; i++)
(*dst)[i] = get_unaligned_le64(src + i);
} else {
*dst = NULL;
}
return 0;
}
static bool has_new_snaps(struct ceph_snap_context *o,
struct ceph_snap_context *n)
{
if (n->num_snaps == 0)
return false;
/* snaps are in descending order */
return n->snaps[0] > o->seq;
}
/*
* When a snapshot is applied, the size/mtime inode metadata is queued
* in a ceph_cap_snap (one for each snapshot) until writeback
* completes and the metadata can be flushed back to the MDS.
*
* However, if a (sync) write is currently in-progress when we apply
* the snapshot, we have to wait until the write succeeds or fails
* (and a final size/mtime is known). In this case the
* cap_snap->writing = 1, and is said to be "pending." When the write
* finishes, we __ceph_finish_cap_snap().
*
* Caller must hold snap_rwsem for read (i.e., the realm topology won't
* change).
*/
void ceph_queue_cap_snap(struct ceph_inode_info *ci)
{
struct inode *inode = &ci->vfs_inode;
struct ceph_cap_snap *capsnap;
struct ceph_snap_context *old_snapc, *new_snapc;
struct ceph_buffer *old_blob = NULL;
int used, dirty;
capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
if (!capsnap) {
pr_err("ENOMEM allocating ceph_cap_snap on %p\n", inode);
return;
}
spin_lock(&ci->i_ceph_lock);
used = __ceph_caps_used(ci);
dirty = __ceph_caps_dirty(ci);
old_snapc = ci->i_head_snapc;
new_snapc = ci->i_snap_realm->cached_context;
/*
* If there is a write in progress, treat that as a dirty Fw,
* even though it hasn't completed yet; by the time we finish
* up this capsnap it will be.
*/
if (used & CEPH_CAP_FILE_WR)
dirty |= CEPH_CAP_FILE_WR;
if (__ceph_have_pending_cap_snap(ci)) {
/* there is no point in queuing multiple "pending" cap_snaps,
as no new writes are allowed to start when pending, so any
writes in progress now were started before the previous
cap_snap. lucky us. */
dout("queue_cap_snap %p already pending\n", inode);
goto update_snapc;
}
if (ci->i_wrbuffer_ref_head == 0 &&
!(dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))) {
dout("queue_cap_snap %p nothing dirty|writing\n", inode);
goto update_snapc;
}
BUG_ON(!old_snapc);
/*
* There is no need to send FLUSHSNAP message to MDS if there is
* no new snapshot. But when there is dirty pages or on-going
* writes, we still need to create cap_snap. cap_snap is needed
* by the write path and page writeback path.
*
* also see ceph_try_drop_cap_snap()
*/
if (has_new_snaps(old_snapc, new_snapc)) {
if (dirty & (CEPH_CAP_ANY_EXCL|CEPH_CAP_FILE_WR))
capsnap->need_flush = true;
} else {
if (!(used & CEPH_CAP_FILE_WR) &&
ci->i_wrbuffer_ref_head == 0) {
dout("queue_cap_snap %p "
"no new_snap|dirty_page|writing\n", inode);
goto update_snapc;
}
}
dout("queue_cap_snap %p cap_snap %p queuing under %p %s %s\n",
inode, capsnap, old_snapc, ceph_cap_string(dirty),
capsnap->need_flush ? "" : "no_flush");
ihold(inode);
refcount_set(&capsnap->nref, 1);
INIT_LIST_HEAD(&capsnap->ci_item);
capsnap->follows = old_snapc->seq;
capsnap->issued = __ceph_caps_issued(ci, NULL);
capsnap->dirty = dirty;
capsnap->mode = inode->i_mode;
capsnap->uid = inode->i_uid;
capsnap->gid = inode->i_gid;
if (dirty & CEPH_CAP_XATTR_EXCL) {
old_blob = __ceph_build_xattrs_blob(ci);
capsnap->xattr_blob =
ceph_buffer_get(ci->i_xattrs.blob);
capsnap->xattr_version = ci->i_xattrs.version;
} else {
capsnap->xattr_blob = NULL;
capsnap->xattr_version = 0;
}
capsnap->inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
/* dirty page count moved from _head to this cap_snap;
all subsequent writes page dirties occur _after_ this
snapshot. */
capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
ci->i_wrbuffer_ref_head = 0;
capsnap->context = old_snapc;
list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
if (used & CEPH_CAP_FILE_WR) {
dout("queue_cap_snap %p cap_snap %p snapc %p"
" seq %llu used WR, now pending\n", inode,
capsnap, old_snapc, old_snapc->seq);
capsnap->writing = 1;
} else {
/* note mtime, size NOW. */
__ceph_finish_cap_snap(ci, capsnap);
}
capsnap = NULL;
old_snapc = NULL;
update_snapc:
if (ci->i_wrbuffer_ref_head == 0 &&
ci->i_wr_ref == 0 &&
ci->i_dirty_caps == 0 &&
ci->i_flushing_caps == 0) {
ci->i_head_snapc = NULL;
} else {
ci->i_head_snapc = ceph_get_snap_context(new_snapc);
dout(" new snapc is %p\n", new_snapc);
}
spin_unlock(&ci->i_ceph_lock);
ceph_buffer_put(old_blob);
kfree(capsnap);
ceph_put_snap_context(old_snapc);
}
/*
* Finalize the size, mtime for a cap_snap.. that is, settle on final values
* to be used for the snapshot, to be flushed back to the mds.
*
* If capsnap can now be flushed, add to snap_flush list, and return 1.
*
* Caller must hold i_ceph_lock.
*/
int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap *capsnap)
{
struct inode *inode = &ci->vfs_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
BUG_ON(capsnap->writing);
capsnap->size = inode->i_size;
capsnap->mtime = inode->i_mtime;
capsnap->atime = inode->i_atime;
capsnap->ctime = inode->i_ctime;
capsnap->time_warp_seq = ci->i_time_warp_seq;
capsnap->truncate_size = ci->i_truncate_size;
capsnap->truncate_seq = ci->i_truncate_seq;
if (capsnap->dirty_pages) {
dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu "
"still has %d dirty pages\n", inode, capsnap,
capsnap->context, capsnap->context->seq,
ceph_cap_string(capsnap->dirty), capsnap->size,
capsnap->dirty_pages);
return 0;
}
ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS;
dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
inode, capsnap, capsnap->context,
capsnap->context->seq, ceph_cap_string(capsnap->dirty),
capsnap->size);
spin_lock(&mdsc->snap_flush_lock);
if (list_empty(&ci->i_snap_flush_item))
list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
spin_unlock(&mdsc->snap_flush_lock);
return 1; /* caller may want to ceph_flush_snaps */
}
/*
* Queue cap_snaps for snap writeback for this realm and its children.
* Called under snap_rwsem, so realm topology won't change.
*/
static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
{
struct ceph_inode_info *ci;
struct inode *lastinode = NULL;
dout("queue_realm_cap_snaps %p %llx inodes\n", realm, realm->ino);
spin_lock(&realm->inodes_with_caps_lock);
list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) {
struct inode *inode = igrab(&ci->vfs_inode);
if (!inode)
continue;
spin_unlock(&realm->inodes_with_caps_lock);
iput(lastinode);
lastinode = inode;
ceph_queue_cap_snap(ci);
spin_lock(&realm->inodes_with_caps_lock);
}
spin_unlock(&realm->inodes_with_caps_lock);
iput(lastinode);
dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino);
}
/*
* Parse and apply a snapblob "snap trace" from the MDS. This specifies
* the snap realm parameters from a given realm and all of its ancestors,
* up to the root.
*
* Caller must hold snap_rwsem for write.
*/
int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
void *p, void *e, bool deletion,
struct ceph_snap_realm **realm_ret)
{
struct ceph_mds_snap_realm *ri; /* encoded */
__le64 *snaps; /* encoded */
__le64 *prior_parent_snaps; /* encoded */
struct ceph_snap_realm *realm = NULL;
struct ceph_snap_realm *first_realm = NULL;
int invalidate = 0;
int err = -ENOMEM;
LIST_HEAD(dirty_realms);
dout("update_snap_trace deletion=%d\n", deletion);
more:
ceph_decode_need(&p, e, sizeof(*ri), bad);
ri = p;
p += sizeof(*ri);
ceph_decode_need(&p, e, sizeof(u64)*(le32_to_cpu(ri->num_snaps) +
le32_to_cpu(ri->num_prior_parent_snaps)), bad);
snaps = p;
p += sizeof(u64) * le32_to_cpu(ri->num_snaps);
prior_parent_snaps = p;
p += sizeof(u64) * le32_to_cpu(ri->num_prior_parent_snaps);
realm = ceph_lookup_snap_realm(mdsc, le64_to_cpu(ri->ino));
if (!realm) {
realm = ceph_create_snap_realm(mdsc, le64_to_cpu(ri->ino));
if (IS_ERR(realm)) {
err = PTR_ERR(realm);
goto fail;
}
}
/* ensure the parent is correct */
err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent));
if (err < 0)
goto fail;
invalidate += err;
if (le64_to_cpu(ri->seq) > realm->seq) {
dout("update_snap_trace updating %llx %p %lld -> %lld\n",
realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
/* update realm parameters, snap lists */
realm->seq = le64_to_cpu(ri->seq);
realm->created = le64_to_cpu(ri->created);
realm->parent_since = le64_to_cpu(ri->parent_since);
realm->num_snaps = le32_to_cpu(ri->num_snaps);
err = dup_array(&realm->snaps, snaps, realm->num_snaps);
if (err < 0)
goto fail;
realm->num_prior_parent_snaps =
le32_to_cpu(ri->num_prior_parent_snaps);
err = dup_array(&realm->prior_parent_snaps, prior_parent_snaps,
realm->num_prior_parent_snaps);
if (err < 0)
goto fail;
if (realm->seq > mdsc->last_snap_seq)
mdsc->last_snap_seq = realm->seq;
invalidate = 1;
} else if (!realm->cached_context) {
dout("update_snap_trace %llx %p seq %lld new\n",
realm->ino, realm, realm->seq);
invalidate = 1;
} else {
dout("update_snap_trace %llx %p seq %lld unchanged\n",
realm->ino, realm, realm->seq);
}
dout("done with %llx %p, invalidated=%d, %p %p\n", realm->ino,
realm, invalidate, p, e);
/* invalidate when we reach the _end_ (root) of the trace */
if (invalidate && p >= e)
rebuild_snap_realms(realm, &dirty_realms);
if (!first_realm)
first_realm = realm;
else
ceph_put_snap_realm(mdsc, realm);
if (p < e)
goto more;
/*
* queue cap snaps _after_ we've built the new snap contexts,
* so that i_head_snapc can be set appropriately.
*/
while (!list_empty(&dirty_realms)) {
realm = list_first_entry(&dirty_realms, struct ceph_snap_realm,
dirty_item);
list_del_init(&realm->dirty_item);
queue_realm_cap_snaps(realm);
}
if (realm_ret)
*realm_ret = first_realm;
else
ceph_put_snap_realm(mdsc, first_realm);
__cleanup_empty_realms(mdsc);
return 0;
bad:
err = -EINVAL;
fail:
if (realm && !IS_ERR(realm))
ceph_put_snap_realm(mdsc, realm);
if (first_realm)
ceph_put_snap_realm(mdsc, first_realm);
pr_err("update_snap_trace error %d\n", err);
return err;
}
/*
* Send any cap_snaps that are queued for flush. Try to carry
* s_mutex across multiple snap flushes to avoid locking overhead.
*
* Caller holds no locks.
*/
static void flush_snaps(struct ceph_mds_client *mdsc)
{
struct ceph_inode_info *ci;
struct inode *inode;
struct ceph_mds_session *session = NULL;
dout("flush_snaps\n");
spin_lock(&mdsc->snap_flush_lock);
while (!list_empty(&mdsc->snap_flush_list)) {
ci = list_first_entry(&mdsc->snap_flush_list,
struct ceph_inode_info, i_snap_flush_item);
inode = &ci->vfs_inode;
ihold(inode);
spin_unlock(&mdsc->snap_flush_lock);
ceph_flush_snaps(ci, &session);
iput(inode);
spin_lock(&mdsc->snap_flush_lock);
}
spin_unlock(&mdsc->snap_flush_lock);
if (session) {
mutex_unlock(&session->s_mutex);
ceph_put_mds_session(session);
}
dout("flush_snaps done\n");
}
/*
* Handle a snap notification from the MDS.
*
* This can take two basic forms: the simplest is just a snap creation
* or deletion notification on an existing realm. This should update the
* realm and its children.
*
* The more difficult case is realm creation, due to snap creation at a
* new point in the file hierarchy, or due to a rename that moves a file or
* directory into another realm.
*/
void ceph_handle_snap(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session,
struct ceph_msg *msg)
{
struct super_block *sb = mdsc->fsc->sb;
int mds = session->s_mds;
u64 split;
int op;
int trace_len;
struct ceph_snap_realm *realm = NULL;
void *p = msg->front.iov_base;
void *e = p + msg->front.iov_len;
struct ceph_mds_snap_head *h;
int num_split_inos, num_split_realms;
__le64 *split_inos = NULL, *split_realms = NULL;
int i;
int locked_rwsem = 0;
/* decode */
if (msg->front.iov_len < sizeof(*h))
goto bad;
h = p;
op = le32_to_cpu(h->op);
split = le64_to_cpu(h->split); /* non-zero if we are splitting an
* existing realm */
num_split_inos = le32_to_cpu(h->num_split_inos);
num_split_realms = le32_to_cpu(h->num_split_realms);
trace_len = le32_to_cpu(h->trace_len);
p += sizeof(*h);
dout("handle_snap from mds%d op %s split %llx tracelen %d\n", mds,
ceph_snap_op_name(op), split, trace_len);
mutex_lock(&session->s_mutex);
session->s_seq++;
mutex_unlock(&session->s_mutex);
down_write(&mdsc->snap_rwsem);
locked_rwsem = 1;
if (op == CEPH_SNAP_OP_SPLIT) {
struct ceph_mds_snap_realm *ri;
/*
* A "split" breaks part of an existing realm off into
* a new realm. The MDS provides a list of inodes
* (with caps) and child realms that belong to the new
* child.
*/
split_inos = p;
p += sizeof(u64) * num_split_inos;
split_realms = p;
p += sizeof(u64) * num_split_realms;
ceph_decode_need(&p, e, sizeof(*ri), bad);
/* we will peek at realm info here, but will _not_
* advance p, as the realm update will occur below in
* ceph_update_snap_trace. */
ri = p;
realm = ceph_lookup_snap_realm(mdsc, split);
if (!realm) {
realm = ceph_create_snap_realm(mdsc, split);
if (IS_ERR(realm))
goto out;
}
dout("splitting snap_realm %llx %p\n", realm->ino, realm);
for (i = 0; i < num_split_inos; i++) {
struct ceph_vino vino = {
.ino = le64_to_cpu(split_inos[i]),
.snap = CEPH_NOSNAP,
};
struct inode *inode = ceph_find_inode(sb, vino);
struct ceph_inode_info *ci;
struct ceph_snap_realm *oldrealm;
if (!inode)
continue;
ci = ceph_inode(inode);
spin_lock(&ci->i_ceph_lock);
if (!ci->i_snap_realm)
goto skip_inode;
/*
* If this inode belongs to a realm that was
* created after our new realm, we experienced
* a race (due to another split notifications
* arriving from a different MDS). So skip
* this inode.
*/
if (ci->i_snap_realm->created >
le64_to_cpu(ri->created)) {
dout(" leaving %p in newer realm %llx %p\n",
inode, ci->i_snap_realm->ino,
ci->i_snap_realm);
goto skip_inode;
}
dout(" will move %p to split realm %llx %p\n",
inode, realm->ino, realm);
/*
* Move the inode to the new realm
*/
oldrealm = ci->i_snap_realm;
spin_lock(&oldrealm->inodes_with_caps_lock);
list_del_init(&ci->i_snap_realm_item);
spin_unlock(&oldrealm->inodes_with_caps_lock);
spin_lock(&realm->inodes_with_caps_lock);
list_add(&ci->i_snap_realm_item,
&realm->inodes_with_caps);
ci->i_snap_realm = realm;
if (realm->ino == ci->i_vino.ino)
realm->inode = inode;
spin_unlock(&realm->inodes_with_caps_lock);
spin_unlock(&ci->i_ceph_lock);
ceph_get_snap_realm(mdsc, realm);
ceph_put_snap_realm(mdsc, oldrealm);
iput(inode);
continue;
skip_inode:
spin_unlock(&ci->i_ceph_lock);
iput(inode);
}
/* we may have taken some of the old realm's children. */
for (i = 0; i < num_split_realms; i++) {
struct ceph_snap_realm *child =
__lookup_snap_realm(mdsc,
le64_to_cpu(split_realms[i]));
if (!child)
continue;
adjust_snap_realm_parent(mdsc, child, realm->ino);
}
}
/*
* update using the provided snap trace. if we are deleting a
* snap, we can avoid queueing cap_snaps.
*/
ceph_update_snap_trace(mdsc, p, e,
op == CEPH_SNAP_OP_DESTROY, NULL);
if (op == CEPH_SNAP_OP_SPLIT)
/* we took a reference when we created the realm, above */
ceph_put_snap_realm(mdsc, realm);
__cleanup_empty_realms(mdsc);
up_write(&mdsc->snap_rwsem);
flush_snaps(mdsc);
return;
bad:
pr_err("corrupt snap message from mds%d\n", mds);
ceph_msg_dump(msg);
out:
if (locked_rwsem)
up_write(&mdsc->snap_rwsem);
return;
}
+128
View File
@@ -0,0 +1,128 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Ceph fs string constants
*/
#include <linux/module.h>
#include <linux/ceph/types.h>
const char *ceph_mds_state_name(int s)
{
switch (s) {
/* down and out */
case CEPH_MDS_STATE_DNE: return "down:dne";
case CEPH_MDS_STATE_STOPPED: return "down:stopped";
/* up and out */
case CEPH_MDS_STATE_BOOT: return "up:boot";
case CEPH_MDS_STATE_STANDBY: return "up:standby";
case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay";
case CEPH_MDS_STATE_REPLAYONCE: return "up:oneshot-replay";
case CEPH_MDS_STATE_CREATING: return "up:creating";
case CEPH_MDS_STATE_STARTING: return "up:starting";
/* up and in */
case CEPH_MDS_STATE_REPLAY: return "up:replay";
case CEPH_MDS_STATE_RESOLVE: return "up:resolve";
case CEPH_MDS_STATE_RECONNECT: return "up:reconnect";
case CEPH_MDS_STATE_REJOIN: return "up:rejoin";
case CEPH_MDS_STATE_CLIENTREPLAY: return "up:clientreplay";
case CEPH_MDS_STATE_ACTIVE: return "up:active";
case CEPH_MDS_STATE_STOPPING: return "up:stopping";
}
return "???";
}
const char *ceph_session_op_name(int op)
{
switch (op) {
case CEPH_SESSION_REQUEST_OPEN: return "request_open";
case CEPH_SESSION_OPEN: return "open";
case CEPH_SESSION_REQUEST_CLOSE: return "request_close";
case CEPH_SESSION_CLOSE: return "close";
case CEPH_SESSION_REQUEST_RENEWCAPS: return "request_renewcaps";
case CEPH_SESSION_RENEWCAPS: return "renewcaps";
case CEPH_SESSION_STALE: return "stale";
case CEPH_SESSION_RECALL_STATE: return "recall_state";
case CEPH_SESSION_FLUSHMSG: return "flushmsg";
case CEPH_SESSION_FLUSHMSG_ACK: return "flushmsg_ack";
case CEPH_SESSION_FORCE_RO: return "force_ro";
case CEPH_SESSION_REJECT: return "reject";
}
return "???";
}
const char *ceph_mds_op_name(int op)
{
switch (op) {
case CEPH_MDS_OP_LOOKUP: return "lookup";
case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash";
case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent";
case CEPH_MDS_OP_LOOKUPINO: return "lookupino";
case CEPH_MDS_OP_LOOKUPNAME: return "lookupname";
case CEPH_MDS_OP_GETATTR: return "getattr";
case CEPH_MDS_OP_SETXATTR: return "setxattr";
case CEPH_MDS_OP_SETATTR: return "setattr";
case CEPH_MDS_OP_RMXATTR: return "rmxattr";
case CEPH_MDS_OP_SETLAYOUT: return "setlayou";
case CEPH_MDS_OP_SETDIRLAYOUT: return "setdirlayout";
case CEPH_MDS_OP_READDIR: return "readdir";
case CEPH_MDS_OP_MKNOD: return "mknod";
case CEPH_MDS_OP_LINK: return "link";
case CEPH_MDS_OP_UNLINK: return "unlink";
case CEPH_MDS_OP_RENAME: return "rename";
case CEPH_MDS_OP_MKDIR: return "mkdir";
case CEPH_MDS_OP_RMDIR: return "rmdir";
case CEPH_MDS_OP_SYMLINK: return "symlink";
case CEPH_MDS_OP_CREATE: return "create";
case CEPH_MDS_OP_OPEN: return "open";
case CEPH_MDS_OP_LOOKUPSNAP: return "lookupsnap";
case CEPH_MDS_OP_LSSNAP: return "lssnap";
case CEPH_MDS_OP_MKSNAP: return "mksnap";
case CEPH_MDS_OP_RMSNAP: return "rmsnap";
case CEPH_MDS_OP_RENAMESNAP: return "renamesnap";
case CEPH_MDS_OP_SETFILELOCK: return "setfilelock";
case CEPH_MDS_OP_GETFILELOCK: return "getfilelock";
}
return "???";
}
const char *ceph_cap_op_name(int op)
{
switch (op) {
case CEPH_CAP_OP_GRANT: return "grant";
case CEPH_CAP_OP_REVOKE: return "revoke";
case CEPH_CAP_OP_TRUNC: return "trunc";
case CEPH_CAP_OP_EXPORT: return "export";
case CEPH_CAP_OP_IMPORT: return "import";
case CEPH_CAP_OP_UPDATE: return "update";
case CEPH_CAP_OP_DROP: return "drop";
case CEPH_CAP_OP_FLUSH: return "flush";
case CEPH_CAP_OP_FLUSH_ACK: return "flush_ack";
case CEPH_CAP_OP_FLUSHSNAP: return "flushsnap";
case CEPH_CAP_OP_FLUSHSNAP_ACK: return "flushsnap_ack";
case CEPH_CAP_OP_RELEASE: return "release";
case CEPH_CAP_OP_RENEW: return "renew";
}
return "???";
}
const char *ceph_lease_op_name(int o)
{
switch (o) {
case CEPH_MDS_LEASE_REVOKE: return "revoke";
case CEPH_MDS_LEASE_RELEASE: return "release";
case CEPH_MDS_LEASE_RENEW: return "renew";
case CEPH_MDS_LEASE_REVOKE_ACK: return "revoke_ack";
}
return "???";
}
const char *ceph_snap_op_name(int o)
{
switch (o) {
case CEPH_SNAP_OP_UPDATE: return "update";
case CEPH_SNAP_OP_CREATE: return "create";
case CEPH_SNAP_OP_DESTROY: return "destroy";
case CEPH_SNAP_OP_SPLIT: return "split";
}
return "???";
}
+1214
View File
File diff suppressed because it is too large. Load diff
+1118
View File
File diff suppressed because it is too large. Load diff
+1201
View File
File diff suppressed because it is too large. Load diff