/*
* find the victim alloc group, where #blkno fits.
*/
static int ocfs2_find_victim_alloc_group(struct inode *inode,
u64 vict_blkno,
int type, int slot,
int *vict_bit,
struct buffer_head **ret_bh)
{
int ret, i, bits_per_unit = 0;
u64 blkno;
char namebuf[40];
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
struct ocfs2_chain_list *cl;
struct ocfs2_chain_rec *rec;
struct ocfs2_dinode *ac_dinode;
struct ocfs2_group_desc *bg;
ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
strlen(namebuf), &blkno);
if (ret) {
ret = -ENOENT;
goto out;
}
ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
if (ret) {
mlog_errno(ret);
goto out;
}
ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
cl = &(ac_dinode->id2.i_chain);
rec = &(cl->cl_recs[0]);
if (type == GLOBAL_BITMAP_SYSTEM_INODE)
bits_per_unit = osb->s_clustersize_bits -
inode->i_sb->s_blocksize_bits;
/*
* 'vict_blkno' was out of the valid range.
*/
if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
(vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) <<
bits_per_unit))) {
ret = -EINVAL;
goto out;
}
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {
rec = &(cl->cl_recs[i]);
if (!rec)
continue;
bg = NULL;
do {
if (!bg)
blkno = le64_to_cpu(rec->c_blkno);
else
blkno = le64_to_cpu(bg->bg_next_group);
if (gd_bh) {
brelse(gd_bh);
gd_bh = NULL;
}
ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
if (ret) {
mlog_errno(ret);
goto out;
}
bg = (struct ocfs2_group_desc *)gd_bh->b_data;
if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
le16_to_cpu(bg->bg_bits))) {
*ret_bh = gd_bh;
*vict_bit = (vict_blkno - blkno) >>
bits_per_unit;
mlog(0, "find the victim group: #%llu, "
"total_bits: %u, vict_bit: %u\n",
blkno, le16_to_cpu(bg->bg_bits),
*vict_bit);
goto out;
}
} while (le64_to_cpu(bg->bg_next_group));
}
ret = -EINVAL;
out:
brelse(ac_bh);
/*
* caller has to release the gd_bh properly.
*/
return ret;
}
int
cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb,int xid)
{
int rc = 0;
FILE_UNIX_BASIC_INFO findData;
struct cifsTconInfo *pTcon;
struct inode *inode;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
char *tmp_path;
pTcon = cifs_sb->tcon;
cFYI(1, (" Getting info on %s ", search_path));
/* we could have done a find first instead but this returns more info */
rc = CIFSSMBUnixQPathInfo(xid, pTcon, search_path, &findData,
cifs_sb->local_nls);
/* dump_mem("\nUnixQPathInfo return data", &findData, sizeof(findData)); */
if (rc) {
if (rc == -EREMOTE) {
tmp_path =
kmalloc(strnlen
(pTcon->treeName,
MAX_TREE_SIZE + 1) +
strnlen(search_path, MAX_PATHCONF) + 1,
GFP_KERNEL);
if (tmp_path == NULL) {
return -ENOMEM;
}
/* have to skip first of the double backslash of UNC name */
strncpy(tmp_path, pTcon->treeName, MAX_TREE_SIZE);
strncat(tmp_path, search_path, MAX_PATHCONF);
rc = connect_to_dfs_path(xid, pTcon->ses,
/* treename + */ tmp_path,
cifs_sb->local_nls);
kfree(tmp_path);
/* BB fix up inode etc. */
} else if (rc) {
return rc;
}
} else {
struct cifsInodeInfo *cifsInfo;
/* get new inode */
if (*pinode == NULL) {
*pinode = new_inode(sb);
if(*pinode == NULL)
return -ENOMEM;
insert_inode_hash(*pinode);
}
inode = *pinode;
cifsInfo = CIFS_I(inode);
cFYI(1, (" Old time %ld ", cifsInfo->time));
cifsInfo->time = jiffies;
cFYI(1, (" New time %ld ", cifsInfo->time));
atomic_set(&cifsInfo->inUse,1); /* ok to set on every refresh of inode */
inode->i_atime =
cifs_NTtimeToUnix(le64_to_cpu(findData.LastAccessTime));
inode->i_mtime =
cifs_NTtimeToUnix(le64_to_cpu
(findData.LastModificationTime));
inode->i_ctime =
cifs_NTtimeToUnix(le64_to_cpu(findData.LastStatusChange));
inode->i_mode = le64_to_cpu(findData.Permissions);
findData.Type = le32_to_cpu(findData.Type);
if (findData.Type == UNIX_FILE) {
inode->i_mode |= S_IFREG;
} else if (findData.Type == UNIX_SYMLINK) {
inode->i_mode |= S_IFLNK;
} else if (findData.Type == UNIX_DIR) {
inode->i_mode |= S_IFDIR;
} else if (findData.Type == UNIX_CHARDEV) {
inode->i_mode |= S_IFCHR;
inode->i_rdev = MKDEV(le64_to_cpu(findData.DevMajor),
le64_to_cpu(findData.DevMinor) & MINORMASK);
} else if (findData.Type == UNIX_BLOCKDEV) {
inode->i_mode |= S_IFBLK;
inode->i_rdev = MKDEV(le64_to_cpu(findData.DevMajor),
le64_to_cpu(findData.DevMinor) & MINORMASK);
} else if (findData.Type == UNIX_FIFO) {
inode->i_mode |= S_IFIFO;
} else if (findData.Type == UNIX_SOCKET) {
inode->i_mode |= S_IFSOCK;
}
inode->i_uid = le64_to_cpu(findData.Uid);
inode->i_gid = le64_to_cpu(findData.Gid);
inode->i_nlink = le64_to_cpu(findData.Nlinks);
findData.NumOfBytes = le64_to_cpu(findData.NumOfBytes);
findData.EndOfFile = le64_to_cpu(findData.EndOfFile);
if(is_size_safe_to_change(cifsInfo)) {
/* can not safely change the file size here if the
client is writing to it due to potential races */
i_size_write(inode,findData.EndOfFile);
/* blksize needs to be multiple of two. So safer to default to blksize
and blkbits set in superblock so 2**blkbits and blksize will match */
/* inode->i_blksize =
(pTcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE) & 0xFFFFFE00;*/
/* This seems incredibly stupid but it turns out that
i_blocks is not related to (i_size / i_blksize), instead a
size of 512 is required to be used for calculating num blocks */
/* inode->i_blocks =
(inode->i_blksize - 1 + findData.NumOfBytes) >> inode->i_blkbits;*/
/* 512 bytes (2**9) is the fake blocksize that must be used */
/* for this calculation */
inode->i_blocks = (512 - 1 + findData.NumOfBytes) >> 9;
}
if (findData.NumOfBytes < findData.EndOfFile)
cFYI(1, ("Server inconsistency Error: it says allocation size less than end of file "));
cFYI(1,
("Size %ld and blocks %ld ",
(unsigned long) inode->i_size, inode->i_blocks));
if (S_ISREG(inode->i_mode)) {
cFYI(1, (" File inode "));
inode->i_op = &cifs_file_inode_ops;
inode->i_fop = &cifs_file_ops;
inode->i_data.a_ops = &cifs_addr_ops;
} else if (S_ISDIR(inode->i_mode)) {
cFYI(1, (" Directory inode"));
inode->i_op = &cifs_dir_inode_ops;
inode->i_fop = &cifs_dir_ops;
} else if (S_ISLNK(inode->i_mode)) {
cFYI(1, (" Symbolic Link inode "));
inode->i_op = &cifs_symlink_inode_ops;
/* tmp_inode->i_fop = *//* do not need to set to anything */
} else {
cFYI(1, (" Init special inode "));
init_special_inode(inode, inode->i_mode,
inode->i_rdev);
}
}
return rc;
}
void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
int create_ino)
{
struct super_block *sb;
struct ocfs2_super *osb;
int use_plocks = 1;
mlog_entry("(0x%p, size:%llu)\n", inode,
(unsigned long long)le64_to_cpu(fe->i_size));
sb = inode->i_sb;
osb = OCFS2_SB(sb);
if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) ||
ocfs2_mount_local(osb) || !ocfs2_stack_supports_plocks())
use_plocks = 0;
/*
* These have all been checked by ocfs2_read_inode_block() or set
* by ocfs2_mknod_locked(), so a failure is a code bug.
*/
BUG_ON(!OCFS2_IS_VALID_DINODE(fe)); /* This means that read_inode
cannot create a superblock
inode today. change if
that is needed. */
BUG_ON(!(fe->i_flags & cpu_to_le32(OCFS2_VALID_FL)));
BUG_ON(le32_to_cpu(fe->i_fs_generation) != osb->fs_generation);
OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
OCFS2_I(inode)->ip_attr = le32_to_cpu(fe->i_attr);
OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
inode->i_version = 1;
inode->i_generation = le32_to_cpu(fe->i_generation);
inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
inode->i_mode = le16_to_cpu(fe->i_mode);
inode->i_uid = le32_to_cpu(fe->i_uid);
inode->i_gid = le32_to_cpu(fe->i_gid);
/* Fast symlinks will have i_size but no allocated clusters. */
if (S_ISLNK(inode->i_mode) && !fe->i_clusters)
inode->i_blocks = 0;
else
inode->i_blocks = ocfs2_inode_sector_count(inode);
inode->i_mapping->a_ops = &ocfs2_aops;
inode->i_atime.tv_sec = le64_to_cpu(fe->i_atime);
inode->i_atime.tv_nsec = le32_to_cpu(fe->i_atime_nsec);
inode->i_mtime.tv_sec = le64_to_cpu(fe->i_mtime);
inode->i_mtime.tv_nsec = le32_to_cpu(fe->i_mtime_nsec);
inode->i_ctime.tv_sec = le64_to_cpu(fe->i_ctime);
inode->i_ctime.tv_nsec = le32_to_cpu(fe->i_ctime_nsec);
if (OCFS2_I(inode)->ip_blkno != le64_to_cpu(fe->i_blkno))
mlog(ML_ERROR,
"ip_blkno %llu != i_blkno %llu!\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)le64_to_cpu(fe->i_blkno));
inode->i_nlink = ocfs2_read_links_count(fe);
if (fe->i_flags & cpu_to_le32(OCFS2_SYSTEM_FL)) {
OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SYSTEM_FILE;
inode->i_flags |= S_NOQUOTA;
}
if (fe->i_flags & cpu_to_le32(OCFS2_LOCAL_ALLOC_FL)) {
OCFS2_I(inode)->ip_flags |= OCFS2_INODE_BITMAP;
mlog(0, "local alloc inode: i_ino=%lu\n", inode->i_ino);
} else if (fe->i_flags & cpu_to_le32(OCFS2_BITMAP_FL)) {
OCFS2_I(inode)->ip_flags |= OCFS2_INODE_BITMAP;
} else if (fe->i_flags & cpu_to_le32(OCFS2_QUOTA_FL)) {
inode->i_flags |= S_NOQUOTA;
} else if (fe->i_flags & cpu_to_le32(OCFS2_SUPER_BLOCK_FL)) {
mlog(0, "superblock inode: i_ino=%lu\n", inode->i_ino);
/* we can't actually hit this as read_inode can't
* handle superblocks today ;-) */
BUG();
}
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
if (use_plocks)
inode->i_fop = &ocfs2_fops;
else
inode->i_fop = &ocfs2_fops_no_plocks;
inode->i_op = &ocfs2_file_iops;
i_size_write(inode, le64_to_cpu(fe->i_size));
break;
case S_IFDIR:
inode->i_op = &ocfs2_dir_iops;
if (use_plocks)
inode->i_fop = &ocfs2_dops;
else
inode->i_fop = &ocfs2_dops_no_plocks;
i_size_write(inode, le64_to_cpu(fe->i_size));
break;
case S_IFLNK:
if (ocfs2_inode_is_fast_symlink(inode))
inode->i_op = &ocfs2_fast_symlink_inode_operations;
else
inode->i_op = &ocfs2_symlink_inode_operations;
i_size_write(inode, le64_to_cpu(fe->i_size));
break;
default:
inode->i_op = &ocfs2_special_file_iops;
init_special_inode(inode, inode->i_mode,
inode->i_rdev);
break;
}
if (create_ino) {
inode->i_ino = ino_from_blkno(inode->i_sb,
le64_to_cpu(fe->i_blkno));
/*
* If we ever want to create system files from kernel,
* the generation argument to
* ocfs2_inode_lock_res_init() will have to change.
*/
BUG_ON(le32_to_cpu(fe->i_flags) & OCFS2_SYSTEM_FL);
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_inode_lockres,
OCFS2_LOCK_TYPE_META, 0, inode);
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_open_lockres,
OCFS2_LOCK_TYPE_OPEN, 0, inode);
}
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_rw_lockres,
OCFS2_LOCK_TYPE_RW, inode->i_generation,
inode);
ocfs2_set_inode_flags(inode);
OCFS2_I(inode)->ip_last_used_slot = 0;
OCFS2_I(inode)->ip_last_used_group = 0;
mlog_exit_void();
}
int
cifs_create(struct inode *inode, struct dentry *direntry, int mode,
struct nameidata *nd)
{
int rc = -ENOENT;
int xid;
int create_options = CREATE_NOT_DIR;
__u32 oplock = 0;
int oflags;
bool posix_create = false;
/*
* BB below access is probably too much for mknod to request
* but we have to do query and setpathinfo so requesting
* less could fail (unless we want to request getatr and setatr
* permissions (only). At least for POSIX we do not have to
* request so much.
*/
int desiredAccess = GENERIC_READ | GENERIC_WRITE;
__u16 fileHandle;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *tcon;
char *full_path = NULL;
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
int disposition = FILE_OVERWRITE_IF;
xid = GetXid();
cifs_sb = CIFS_SB(inode->i_sb);
tcon = cifs_sb->tcon;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
rc = -ENOMEM;
FreeXid(xid);
return rc;
}
if (oplockEnabled)
oplock = REQ_OPLOCK;
if (nd && (nd->flags & LOOKUP_OPEN))
oflags = nd->intent.open.flags;
else
oflags = FMODE_READ | SMB_O_CREAT;
if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_open(full_path, &newinode,
nd ? nd->path.mnt : NULL,
inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
/* EIO could indicate that (posix open) operation is not
supported, despite what server claimed in capability
negotation. EREMOTE indicates DFS junction, which is not
handled in posix open */
if (rc == 0) {
posix_create = true;
if (newinode == NULL) /* query inode info */
goto cifs_create_get_file_info;
else /* success, no need to query */
goto cifs_create_set_dentry;
} else if ((rc != -EIO) && (rc != -EREMOTE) &&
(rc != -EOPNOTSUPP) && (rc != -EINVAL))
goto cifs_create_out;
/* else fallthrough to retry, using older open call, this is
case where server does not support this SMB level, and
falsely claims capability (also get here for DFS case
which should be rare for path not covered on files) */
}
if (nd && (nd->flags & LOOKUP_OPEN)) {
/* if the file is going to stay open, then we
need to set the desired access properly */
desiredAccess = 0;
if (oflags & FMODE_READ)
desiredAccess |= GENERIC_READ; /* is this too little? */
if (oflags & FMODE_WRITE)
desiredAccess |= GENERIC_WRITE;
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
disposition = FILE_CREATE;
else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
disposition = FILE_OVERWRITE_IF;
else if ((oflags & O_CREAT) == O_CREAT)
disposition = FILE_OPEN_IF;
else
cFYI(1, ("Create flag not set in create function"));
}
/* BB add processing to set equivalent of mode - e.g. via CreateX with
ACLs */
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
kfree(full_path);
FreeXid(xid);
return -ENOMEM;
}
/*
* if we're not using unix extensions, see if we need to set
* ATTR_READONLY on the create call
*/
if (!tcon->unix_ext && (mode & S_IWUGO) == 0)
create_options |= CREATE_OPTION_READONLY;
if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS)
rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
&fileHandle, &oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
else
rc = -EIO; /* no NT SMB support fall into legacy open below */
if (rc == -EIO) {
/* old server, retry the open legacy style */
rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
&fileHandle, &oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
}
if (rc) {
cFYI(1, ("cifs_create returned 0x%x", rc));
goto cifs_create_out;
}
/* If Open reported that we actually created a file
then we now have to set the mode if possible */
if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) {
struct cifs_unix_set_info_args args = {
.mode = mode,
.ctime = NO_CHANGE_64,
.atime = NO_CHANGE_64,
.mtime = NO_CHANGE_64,
.device = 0,
};
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = (__u64) current_fsuid();
if (inode->i_mode & S_ISGID)
args.gid = (__u64) inode->i_gid;
else
args.gid = (__u64) current_fsgid();
} else {
args.uid = NO_CHANGE_64;
args.gid = NO_CHANGE_64;
}
CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
} else {
/* BB implement mode setting via Windows security
descriptors e.g. */
/* CIFSSMBWinSetPerms(xid,tcon,path,mode,-1,-1,nls);*/
/* Could set r/o dos attribute if mode & 0222 == 0 */
}
cifs_create_get_file_info:
/* server might mask mode so we have to query for it */
if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&newinode, full_path,
inode->i_sb, xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf,
inode->i_sb, xid, &fileHandle);
if (newinode) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
newinode->i_mode = mode;
if ((oplock & CIFS_CREATE_ACTION) &&
(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
newinode->i_uid = current_fsuid();
if (inode->i_mode & S_ISGID)
newinode->i_gid = inode->i_gid;
else
newinode->i_gid = current_fsgid();
}
}
}
cifs_create_set_dentry:
if (rc == 0)
setup_cifs_dentry(tcon, direntry, newinode);
else
cFYI(1, ("Create worked, get_inode_info failed rc = %d", rc));
/* nfsd case - nfs srv does not set nd */
if ((nd == NULL) || (!(nd->flags & LOOKUP_OPEN))) {
/* mknod case - do not leave file open */
CIFSSMBClose(xid, tcon, fileHandle);
} else if (!(posix_create) && (newinode)) {
cifs_new_fileinfo(newinode, fileHandle, NULL,
nd->path.mnt, oflags);
}
cifs_create_out:
kfree(buf);
kfree(full_path);
FreeXid(xid);
return rc;
}
HPT_U64 LE64_TO_CPU(HPT_U64 x) {
return le64_to_cpu(x);
}
int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
{
struct buffer_head *header_bh, *su_bh;
struct nilfs_sufile_header *header;
struct nilfs_segment_usage *su;
size_t susz = NILFS_MDT(sufile)->mi_entry_size;
__u64 segnum, maxsegnum, last_alloc;
void *kaddr;
unsigned long nsegments, ncleansegs, nsus;
int ret, i, j;
down_write(&NILFS_MDT(sufile)->mi_sem);
ret = nilfs_sufile_get_header_block(sufile, &header_bh);
if (ret < 0)
goto out_sem;
kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
header = kaddr + bh_offset(header_bh);
ncleansegs = le64_to_cpu(header->sh_ncleansegs);
last_alloc = le64_to_cpu(header->sh_last_alloc);
kunmap_atomic(kaddr, KM_USER0);
nsegments = nilfs_sufile_get_nsegments(sufile);
segnum = last_alloc + 1;
maxsegnum = nsegments - 1;
for (i = 0; i < nsegments; i += nsus) {
if (segnum >= nsegments) {
/* wrap around */
segnum = 0;
maxsegnum = last_alloc;
}
ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 1,
&su_bh);
if (ret < 0)
goto out_header;
kaddr = kmap_atomic(su_bh->b_page, KM_USER0);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
nsus = nilfs_sufile_segment_usages_in_block(
sufile, segnum, maxsegnum);
for (j = 0; j < nsus; j++, su = (void *)su + susz, segnum++) {
if (!nilfs_segment_usage_clean(su))
continue;
/* found a clean segment */
nilfs_segment_usage_set_dirty(su);
kunmap_atomic(kaddr, KM_USER0);
kaddr = kmap_atomic(header_bh->b_page, KM_USER0);
header = kaddr + bh_offset(header_bh);
le64_add_cpu(&header->sh_ncleansegs, -1);
le64_add_cpu(&header->sh_ndirtysegs, 1);
header->sh_last_alloc = cpu_to_le64(segnum);
kunmap_atomic(kaddr, KM_USER0);
NILFS_SUI(sufile)->ncleansegs--;
nilfs_mdt_mark_buffer_dirty(header_bh);
nilfs_mdt_mark_buffer_dirty(su_bh);
nilfs_mdt_mark_dirty(sufile);
brelse(su_bh);
*segnump = segnum;
goto out_header;
}
kunmap_atomic(kaddr, KM_USER0);
brelse(su_bh);
}
/* no segments left */
ret = -ENOSPC;
out_header:
brelse(header_bh);
out_sem:
up_write(&NILFS_MDT(sufile)->mi_sem);
return ret;
}
/*
* Splits a node by creating two new children beneath the given node.
*
* Before:
* +----------+
* | A ++++++ |
* +----------+
*
*
* After:
* +------------+
* | A (shadow) |
* +------------+
* | |
* +------+ +----+
* | |
* v v
* +-------+ +-------+
* | B +++ | | C +++ |
* +-------+ +-------+
*/
static int btree_split_beneath(struct shadow_spine *s, uint64_t key)
{
int r;
size_t size;
unsigned nr_left, nr_right;
struct dm_block *left, *right, *new_parent;
struct btree_node *pn, *ln, *rn;
__le64 val;
new_parent = shadow_current(s);
r = new_block(s->info, &left);
if (r < 0)
return r;
r = new_block(s->info, &right);
if (r < 0) {
/* FIXME: put left */
return r;
}
pn = dm_block_data(new_parent);
ln = dm_block_data(left);
rn = dm_block_data(right);
nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;
ln->header.flags = pn->header.flags;
ln->header.nr_entries = cpu_to_le32(nr_left);
ln->header.max_entries = pn->header.max_entries;
ln->header.value_size = pn->header.value_size;
rn->header.flags = pn->header.flags;
rn->header.nr_entries = cpu_to_le32(nr_right);
rn->header.max_entries = pn->header.max_entries;
rn->header.value_size = pn->header.value_size;
memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0]));
size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
sizeof(__le64) : s->info->value_type.size;
memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left),
nr_right * size);
/* new_parent should just point to l and r now */
pn->header.flags = cpu_to_le32(INTERNAL_NODE);
pn->header.nr_entries = cpu_to_le32(2);
pn->header.max_entries = cpu_to_le32(
calc_max_entries(sizeof(__le64),
dm_bm_block_size(
dm_tm_get_bm(s->info->tm))));
pn->header.value_size = cpu_to_le32(sizeof(__le64));
val = cpu_to_le64(dm_block_location(left));
__dm_bless_for_disk(&val);
pn->keys[0] = ln->keys[0];
memcpy_disk(value_ptr(pn, 0), &val, sizeof(__le64));
val = cpu_to_le64(dm_block_location(right));
__dm_bless_for_disk(&val);
pn->keys[1] = rn->keys[0];
memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64));
/*
* rejig the spine. This is ugly, since it knows too
* much about the spine
*/
if (s->nodes[0] != new_parent) {
unlock_block(s->info, s->nodes[0]);
s->nodes[0] = new_parent;
}
if (key < le64_to_cpu(rn->keys[0])) {
unlock_block(s->info, right);
s->nodes[1] = left;
} else {
unlock_block(s->info, left);
s->nodes[1] = right;
}
s->count = 2;
return 0;
}
static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int err = -EIO;
int status;
struct ocfs2_dinode *fe = NULL;
struct buffer_head *bh = NULL;
struct buffer_head *buffer_cache_bh = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
void *kaddr;
mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
(unsigned long long)iblock, bh_result, create);
BUG_ON(ocfs2_inode_is_fast_symlink(inode));
if ((iblock << inode->i_sb->s_blocksize_bits) > PATH_MAX + 1) {
mlog(ML_ERROR, "block offset > PATH_MAX: %llu",
(unsigned long long)iblock);
goto bail;
}
status = ocfs2_read_inode_block(inode, &bh);
if (status < 0) {
mlog_errno(status);
goto bail;
}
fe = (struct ocfs2_dinode *) bh->b_data;
if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb,
le32_to_cpu(fe->i_clusters))) {
mlog(ML_ERROR, "block offset is outside the allocated size: "
"%llu\n", (unsigned long long)iblock);
goto bail;
}
/* We don't use the page cache to create symlink data, so if
* need be, copy it over from the buffer cache. */
if (!buffer_uptodate(bh_result) && ocfs2_inode_is_new(inode)) {
u64 blkno = le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) +
iblock;
buffer_cache_bh = sb_getblk(osb->sb, blkno);
if (!buffer_cache_bh) {
mlog(ML_ERROR, "couldn't getblock for symlink!\n");
goto bail;
}
/* we haven't locked out transactions, so a commit
* could've happened. Since we've got a reference on
* the bh, even if it commits while we're doing the
* copy, the data is still good. */
if (buffer_jbd(buffer_cache_bh)
&& ocfs2_inode_is_new(inode)) {
kaddr = kmap_atomic(bh_result->b_page, KM_USER0);
if (!kaddr) {
mlog(ML_ERROR, "couldn't kmap!\n");
goto bail;
}
memcpy(kaddr + (bh_result->b_size * iblock),
buffer_cache_bh->b_data,
bh_result->b_size);
kunmap_atomic(kaddr, KM_USER0);
set_buffer_uptodate(bh_result);
}
brelse(buffer_cache_bh);
}
map_bh(bh_result, inode->i_sb,
le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock);
err = 0;
bail:
brelse(bh);
mlog_exit(err);
return err;
}
int fio_send_data(int sk, const void *p, unsigned int len)
{
struct iovec iov = { .iov_base = (void *) p, .iov_len = len };
assert(len <= sizeof(struct fio_net_cmd) + FIO_SERVER_MAX_FRAGMENT_PDU);
return fio_sendv_data(sk, &iov, 1);
}
int fio_recv_data(int sk, void *p, unsigned int len)
{
do {
int ret = recv(sk, p, len, MSG_WAITALL);
if (ret > 0) {
len -= ret;
if (!len)
break;
p += ret;
continue;
} else if (!ret)
break;
else if (errno == EAGAIN || errno == EINTR)
continue;
else
break;
} while (!exit_backend);
if (!len)
return 0;
return -1;
}
static int verify_convert_cmd(struct fio_net_cmd *cmd)
{
uint16_t crc;
cmd->cmd_crc16 = le16_to_cpu(cmd->cmd_crc16);
cmd->pdu_crc16 = le16_to_cpu(cmd->pdu_crc16);
crc = fio_crc16(cmd, FIO_NET_CMD_CRC_SZ);
if (crc != cmd->cmd_crc16) {
log_err("fio: server bad crc on command (got %x, wanted %x)\n",
cmd->cmd_crc16, crc);
return 1;
}
cmd->version = le16_to_cpu(cmd->version);
cmd->opcode = le16_to_cpu(cmd->opcode);
cmd->flags = le32_to_cpu(cmd->flags);
cmd->tag = le64_to_cpu(cmd->tag);
cmd->pdu_len = le32_to_cpu(cmd->pdu_len);
switch (cmd->version) {
case FIO_SERVER_VER:
break;
default:
log_err("fio: bad server cmd version %d\n", cmd->version);
return 1;
}
if (cmd->pdu_len > FIO_SERVER_MAX_FRAGMENT_PDU) {
log_err("fio: command payload too large: %u\n", cmd->pdu_len);
return 1;
}
return 0;
}
static int
receive_packet (struct net_device *dev)
{
struct netdev_private *np = netdev_priv(dev);
int entry = np->cur_rx % RX_RING_SIZE;
int cnt = 30;
/* If RFDDone, FrameStart and FrameEnd set, there is a new packet in. */
while (1) {
struct netdev_desc *desc = &np->rx_ring[entry];
int pkt_len;
u64 frame_status;
if (!(desc->status & cpu_to_le64(RFDDone)) ||
!(desc->status & cpu_to_le64(FrameStart)) ||
!(desc->status & cpu_to_le64(FrameEnd)))
break;
/* Chip omits the CRC. */
frame_status = le64_to_cpu(desc->status);
pkt_len = frame_status & 0xffff;
if (--cnt < 0)
break;
/* Update rx error statistics, drop packet. */
if (frame_status & RFS_Errors) {
np->stats.rx_errors++;
if (frame_status & (RxRuntFrame | RxLengthError))
np->stats.rx_length_errors++;
if (frame_status & RxFCSError)
np->stats.rx_crc_errors++;
if (frame_status & RxAlignmentError && np->speed != 1000)
np->stats.rx_frame_errors++;
if (frame_status & RxFIFOOverrun)
np->stats.rx_fifo_errors++;
} else {
struct sk_buff *skb;
/* Small skbuffs for short packets */
if (pkt_len > copy_thresh) {
pci_unmap_single (np->pdev,
desc_to_dma(desc),
np->rx_buf_sz,
PCI_DMA_FROMDEVICE);
skb_put (skb = np->rx_skbuff[entry], pkt_len);
np->rx_skbuff[entry] = NULL;
} else if ((skb = netdev_alloc_skb_ip_align(dev, pkt_len))) {
pci_dma_sync_single_for_cpu(np->pdev,
desc_to_dma(desc),
np->rx_buf_sz,
PCI_DMA_FROMDEVICE);
skb_copy_to_linear_data (skb,
np->rx_skbuff[entry]->data,
pkt_len);
skb_put (skb, pkt_len);
pci_dma_sync_single_for_device(np->pdev,
desc_to_dma(desc),
np->rx_buf_sz,
PCI_DMA_FROMDEVICE);
}
skb->protocol = eth_type_trans (skb, dev);
#if 0
/* Checksum done by hw, but csum value unavailable. */
if (np->pdev->pci_rev_id >= 0x0c &&
!(frame_status & (TCPError | UDPError | IPError))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
#endif
netif_rx (skb);
}
entry = (entry + 1) % RX_RING_SIZE;
}
spin_lock(&np->rx_lock);
np->cur_rx = entry;
/* Re-allocate skbuffs to fill the descriptor ring */
entry = np->old_rx;
while (entry != np->cur_rx) {
struct sk_buff *skb;
/* Dropped packets don't need to re-allocate */
if (np->rx_skbuff[entry] == NULL) {
skb = netdev_alloc_skb_ip_align(dev, np->rx_buf_sz);
if (skb == NULL) {
np->rx_ring[entry].fraginfo = 0;
printk (KERN_INFO
"%s: receive_packet: "
"Unable to re-allocate Rx skbuff.#%d\n",
dev->name, entry);
break;
}
np->rx_skbuff[entry] = skb;
np->rx_ring[entry].fraginfo =
cpu_to_le64 (pci_map_single
(np->pdev, skb->data, np->rx_buf_sz,
PCI_DMA_FROMDEVICE));
}
np->rx_ring[entry].fraginfo |=
cpu_to_le64((u64)np->rx_buf_sz << 48);
np->rx_ring[entry].status = 0;
entry = (entry + 1) % RX_RING_SIZE;
}
np->old_rx = entry;
spin_unlock(&np->rx_lock);
return 0;
}
static void header_from_disk(struct log_header *core, struct log_header *disk)
{
core->magic = le32_to_cpu(disk->magic);
core->version = le32_to_cpu(disk->version);
core->nr_regions = le64_to_cpu(disk->nr_regions);
}
static inline dma_addr_t desc_to_dma(struct netdev_desc *desc)
{
return le64_to_cpu(desc->fraginfo) & DMA_BIT_MASK(48);
}
static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi,
unsigned table_count)
{
struct exofs_sb_info *sbi = *psbi;
struct osd_dev *fscb_od;
struct osd_obj_id obj = {.partition = sbi->layout.s_pid,
.id = EXOFS_DEVTABLE_ID};
struct exofs_device_table *dt;
unsigned table_bytes = table_count * sizeof(dt->dt_dev_table[0]) +
sizeof(*dt);
unsigned numdevs, i;
int ret;
dt = kmalloc(table_bytes, GFP_KERNEL);
if (unlikely(!dt)) {
EXOFS_ERR("ERROR: allocating %x bytes for device table\n",
table_bytes);
return -ENOMEM;
}
fscb_od = sbi->layout.s_ods[0];
sbi->layout.s_ods[0] = NULL;
sbi->layout.s_numdevs = 0;
ret = exofs_read_kern(fscb_od, sbi->s_cred, &obj, 0, dt, table_bytes);
if (unlikely(ret)) {
EXOFS_ERR("ERROR: reading device table\n");
goto out;
}
numdevs = le64_to_cpu(dt->dt_num_devices);
if (unlikely(!numdevs)) {
ret = -EINVAL;
goto out;
}
WARN_ON(table_count != numdevs);
ret = _read_and_match_data_map(sbi, numdevs, dt);
if (unlikely(ret))
goto out;
if (likely(numdevs > 1)) {
unsigned size = numdevs * sizeof(sbi->layout.s_ods[0]);
sbi = krealloc(sbi, sizeof(*sbi) + size, GFP_KERNEL);
if (unlikely(!sbi)) {
ret = -ENOMEM;
goto out;
}
memset(&sbi->layout.s_ods[1], 0,
size - sizeof(sbi->layout.s_ods[0]));
*psbi = sbi;
}
for (i = 0; i < numdevs; i++) {
struct exofs_fscb fscb;
struct osd_dev_info odi;
struct osd_dev *od;
if (exofs_devs_2_odi(&dt->dt_dev_table[i], &odi)) {
EXOFS_ERR("ERROR: Read all-zeros device entry\n");
ret = -EINVAL;
goto out;
}
printk(KERN_NOTICE "Add device[%d]: osd_name-%s\n",
i, odi.osdname);
/* On all devices the device table is identical. The user can
* specify any one of the participating devices on the command
* line. We always keep them in device-table order.
*/
if (fscb_od && osduld_device_same(fscb_od, &odi)) {
sbi->layout.s_ods[i] = fscb_od;
++sbi->layout.s_numdevs;
fscb_od = NULL;
continue;
}
od = osduld_info_lookup(&odi);
if (unlikely(IS_ERR(od))) {
ret = PTR_ERR(od);
EXOFS_ERR("ERROR: device requested is not found "
"osd_name-%s =>%d\n", odi.osdname, ret);
goto out;
}
sbi->layout.s_ods[i] = od;
++sbi->layout.s_numdevs;
/* Read the fscb of the other devices to make sure the FS
* partition is there.
*/
ret = exofs_read_kern(od, sbi->s_cred, &obj, 0, &fscb,
sizeof(fscb));
if (unlikely(ret)) {
EXOFS_ERR("ERROR: Malformed participating device "
"error reading fscb osd_name-%s\n",
odi.osdname);
goto out;
}
/* TODO: verify other information is correct and FS-uuid
* matches. Benny what did you say about device table
* generation and old devices?
*/
}
out:
kfree(dt);
if (unlikely(!ret && fscb_od)) {
EXOFS_ERR(
"ERROR: Bad device-table container device not present\n");
osduld_put_device(fscb_od);
ret = -EINVAL;
}
return ret;
}
/*
* Read the superblock from the OSD and fill in the fields
*/
static int exofs_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *root;
struct exofs_mountopt *opts = data;
struct exofs_sb_info *sbi; /*extended info */
struct osd_dev *od; /* Master device */
struct exofs_fscb fscb; /*on-disk superblock info */
struct osd_obj_id obj;
unsigned table_count;
int ret;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY);
if (ret)
goto free_bdi;
/* use mount options to fill superblock */
od = osduld_path_lookup(opts->dev_name);
if (IS_ERR(od)) {
ret = PTR_ERR(od);
goto free_sbi;
}
/* Default layout in case we do not have a device-table */
sbi->layout.stripe_unit = PAGE_SIZE;
sbi->layout.mirrors_p1 = 1;
sbi->layout.group_width = 1;
sbi->layout.group_depth = -1;
sbi->layout.group_count = 1;
sbi->layout.s_ods[0] = od;
sbi->layout.s_numdevs = 1;
sbi->layout.s_pid = opts->pid;
sbi->s_timeout = opts->timeout;
/* fill in some other data by hand */
memset(sb->s_id, 0, sizeof(sb->s_id));
strcpy(sb->s_id, "exofs");
sb->s_blocksize = EXOFS_BLKSIZE;
sb->s_blocksize_bits = EXOFS_BLKSHIFT;
sb->s_maxbytes = MAX_LFS_FILESIZE;
atomic_set(&sbi->s_curr_pending, 0);
sb->s_bdev = NULL;
sb->s_dev = 0;
obj.partition = sbi->layout.s_pid;
obj.id = EXOFS_SUPER_ID;
exofs_make_credential(sbi->s_cred, &obj);
ret = exofs_read_kern(od, sbi->s_cred, &obj, 0, &fscb, sizeof(fscb));
if (unlikely(ret))
goto free_sbi;
sb->s_magic = le16_to_cpu(fscb.s_magic);
sbi->s_nextid = le64_to_cpu(fscb.s_nextid);
sbi->s_numfiles = le32_to_cpu(fscb.s_numfiles);
/* make sure what we read from the object store is correct */
if (sb->s_magic != EXOFS_SUPER_MAGIC) {
if (!silent)
EXOFS_ERR("ERROR: Bad magic value\n");
ret = -EINVAL;
goto free_sbi;
}
if (le32_to_cpu(fscb.s_version) != EXOFS_FSCB_VER) {
EXOFS_ERR("ERROR: Bad FSCB version expected-%d got-%d\n",
EXOFS_FSCB_VER, le32_to_cpu(fscb.s_version));
ret = -EINVAL;
goto free_sbi;
}
/* start generation numbers from a random point */
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
table_count = le64_to_cpu(fscb.s_dev_table_count);
if (table_count) {
ret = exofs_read_lookup_dev_table(&sbi, table_count);
if (unlikely(ret))
goto free_sbi;
}
/* set up operation vectors */
sb->s_bdi = &sbi->bdi;
sb->s_fs_info = sbi;
sb->s_op = &exofs_sops;
sb->s_export_op = &exofs_export_ops;
root = exofs_iget(sb, EXOFS_ROOT_ID - EXOFS_OBJ_OFF);
if (IS_ERR(root)) {
EXOFS_ERR("ERROR: exofs_iget failed\n");
ret = PTR_ERR(root);
goto free_sbi;
}
sb->s_root = d_alloc_root(root);
if (!sb->s_root) {
iput(root);
EXOFS_ERR("ERROR: get root inode failed\n");
ret = -ENOMEM;
goto free_sbi;
}
if (!S_ISDIR(root->i_mode)) {
dput(sb->s_root);
sb->s_root = NULL;
EXOFS_ERR("ERROR: corrupt root inode (mode = %hd)\n",
root->i_mode);
ret = -EINVAL;
goto free_sbi;
}
_exofs_print_device("Mounting", opts->dev_name, sbi->layout.s_ods[0],
sbi->layout.s_pid);
return 0;
free_sbi:
bdi_destroy(&sbi->bdi);
free_bdi:
EXOFS_ERR("Unable to mount exofs on %s pid=0x%llx err=%d\n",
opts->dev_name, sbi->layout.s_pid, ret);
exofs_free_sbi(sbi);
return ret;
}
/*
* Set up the superblock (calls exofs_fill_super eventually)
*/
static struct dentry *exofs_mount(struct file_system_type *type,
int flags, const char *dev_name,
void *data)
{
struct exofs_mountopt opts;
int ret;
ret = parse_options(data, &opts);
if (ret)
return ERR_PTR(ret);
opts.dev_name = dev_name;
return mount_nodev(type, flags, &opts, exofs_fill_super);
}
/*
* Return information about the file system state in the buffer. This is used
* by the 'df' command, for example.
*/
static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct exofs_sb_info *sbi = sb->s_fs_info;
struct exofs_io_state *ios;
struct osd_attr attrs[] = {
ATTR_DEF(OSD_APAGE_PARTITION_QUOTAS,
OSD_ATTR_PQ_CAPACITY_QUOTA, sizeof(__be64)),
ATTR_DEF(OSD_APAGE_PARTITION_INFORMATION,
OSD_ATTR_PI_USED_CAPACITY, sizeof(__be64)),
};
uint64_t capacity = ULLONG_MAX;
uint64_t used = ULLONG_MAX;
uint8_t cred_a[OSD_CAP_LEN];
int ret;
ret = exofs_get_io_state(&sbi->layout, &ios);
if (ret) {
EXOFS_DBGMSG("exofs_get_io_state failed.\n");
return ret;
}
exofs_make_credential(cred_a, &ios->obj);
ios->cred = sbi->s_cred;
ios->in_attr = attrs;
ios->in_attr_len = ARRAY_SIZE(attrs);
ret = exofs_sbi_read(ios);
if (unlikely(ret))
goto out;
ret = extract_attr_from_ios(ios, &attrs[0]);
if (likely(!ret)) {
capacity = get_unaligned_be64(attrs[0].val_ptr);
if (unlikely(!capacity))
capacity = ULLONG_MAX;
} else
EXOFS_DBGMSG("exofs_statfs: get capacity failed.\n");
ret = extract_attr_from_ios(ios, &attrs[1]);
if (likely(!ret))
used = get_unaligned_be64(attrs[1].val_ptr);
else
EXOFS_DBGMSG("exofs_statfs: get used-space failed.\n");
/* fill in the stats buffer */
buf->f_type = EXOFS_SUPER_MAGIC;
buf->f_bsize = EXOFS_BLKSIZE;
buf->f_blocks = capacity >> 9;
buf->f_bfree = (capacity - used) >> 9;
buf->f_bavail = buf->f_bfree;
buf->f_files = sbi->s_numfiles;
buf->f_ffree = EXOFS_MAX_ID - sbi->s_numfiles;
buf->f_namelen = EXOFS_NAME_LEN;
out:
exofs_put_io_state(ios);
return ret;
}
static const struct super_operations exofs_sops = {
.alloc_inode = exofs_alloc_inode,
.destroy_inode = exofs_destroy_inode,
.write_inode = exofs_write_inode,
.evict_inode = exofs_evict_inode,
.put_super = exofs_put_super,
.write_super = exofs_write_super,
.sync_fs = exofs_sync_fs,
.statfs = exofs_statfs,
};
/******************************************************************************
* EXPORT OPERATIONS
*****************************************************************************/
struct dentry *exofs_get_parent(struct dentry *child)
{
unsigned long ino = exofs_parent_ino(child);
if (!ino)
return NULL;
return d_obtain_alias(exofs_iget(child->d_inode->i_sb, ino));
}
static int _read_and_match_data_map(struct exofs_sb_info *sbi, unsigned numdevs,
struct exofs_device_table *dt)
{
u64 stripe_length;
sbi->data_map.odm_num_comps =
le32_to_cpu(dt->dt_data_map.cb_num_comps);
sbi->data_map.odm_stripe_unit =
le64_to_cpu(dt->dt_data_map.cb_stripe_unit);
sbi->data_map.odm_group_width =
le32_to_cpu(dt->dt_data_map.cb_group_width);
sbi->data_map.odm_group_depth =
le32_to_cpu(dt->dt_data_map.cb_group_depth);
sbi->data_map.odm_mirror_cnt =
le32_to_cpu(dt->dt_data_map.cb_mirror_cnt);
sbi->data_map.odm_raid_algorithm =
le32_to_cpu(dt->dt_data_map.cb_raid_algorithm);
/* FIXME: Only raid0 for now. if not so, do not mount */
if (sbi->data_map.odm_num_comps != numdevs) {
EXOFS_ERR("odm_num_comps(%u) != numdevs(%u)\n",
sbi->data_map.odm_num_comps, numdevs);
return -EINVAL;
}
if (sbi->data_map.odm_raid_algorithm != PNFS_OSD_RAID_0) {
EXOFS_ERR("Only RAID_0 for now\n");
return -EINVAL;
}
if (0 != (numdevs % (sbi->data_map.odm_mirror_cnt + 1))) {
EXOFS_ERR("Data Map wrong, numdevs=%d mirrors=%d\n",
numdevs, sbi->data_map.odm_mirror_cnt);
return -EINVAL;
}
if (0 != (sbi->data_map.odm_stripe_unit & ~PAGE_MASK)) {
EXOFS_ERR("Stripe Unit(0x%llx)"
" must be Multples of PAGE_SIZE(0x%lx)\n",
_LLU(sbi->data_map.odm_stripe_unit), PAGE_SIZE);
return -EINVAL;
}
sbi->layout.stripe_unit = sbi->data_map.odm_stripe_unit;
sbi->layout.mirrors_p1 = sbi->data_map.odm_mirror_cnt + 1;
if (sbi->data_map.odm_group_width) {
sbi->layout.group_width = sbi->data_map.odm_group_width;
sbi->layout.group_depth = sbi->data_map.odm_group_depth;
if (!sbi->layout.group_depth) {
EXOFS_ERR("group_depth == 0 && group_width != 0\n");
return -EINVAL;
}
sbi->layout.group_count = sbi->data_map.odm_num_comps /
sbi->layout.mirrors_p1 /
sbi->data_map.odm_group_width;
} else {
if (sbi->data_map.odm_group_depth) {
printk(KERN_NOTICE "Warning: group_depth ignored "
"group_width == 0 && group_depth == %d\n",
sbi->data_map.odm_group_depth);
sbi->data_map.odm_group_depth = 0;
}
sbi->layout.group_width = sbi->data_map.odm_num_comps /
sbi->layout.mirrors_p1;
sbi->layout.group_depth = -1;
sbi->layout.group_count = 1;
}
stripe_length = (u64)sbi->layout.group_width * sbi->layout.stripe_unit;
if (stripe_length >= (1ULL << 32)) {
EXOFS_ERR("Total Stripe length(0x%llx)"
" >= 32bit is not supported\n", _LLU(stripe_length));
return -EINVAL;
}
return 0;
}
static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
struct the_nilfs *nilfs = sb->s_fs_info;
unsigned long old_sb_flags;
unsigned long old_mount_opt;
int err;
old_sb_flags = sb->s_flags;
old_mount_opt = nilfs->ns_mount_opt;
if (!parse_options(data, sb, 1)) {
err = -EINVAL;
goto restore_opts;
}
sb->s_flags = (sb->s_flags & ~MS_POSIXACL);
err = -EINVAL;
if (!nilfs_valid_fs(nilfs)) {
printk(KERN_WARNING "NILFS (device %s): couldn't "
"remount because the filesystem is in an "
"incomplete recovery state.\n", sb->s_id);
goto restore_opts;
}
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
goto out;
if (*flags & MS_RDONLY) {
/* Shutting down log writer */
nilfs_detach_log_writer(sb);
sb->s_flags |= MS_RDONLY;
/*
* Remounting a valid RW partition RDONLY, so set
* the RDONLY flag and then mark the partition as valid again.
*/
down_write(&nilfs->ns_sem);
nilfs_cleanup_super(sb);
up_write(&nilfs->ns_sem);
} else {
__u64 features;
struct nilfs_root *root;
/*
* Mounting a RDONLY partition read-write, so reread and
* store the current valid flag. (It may have been changed
* by fsck since we originally mounted the partition.)
*/
down_read(&nilfs->ns_sem);
features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
~NILFS_FEATURE_COMPAT_RO_SUPP;
up_read(&nilfs->ns_sem);
if (features) {
printk(KERN_WARNING "NILFS (device %s): couldn't "
"remount RDWR because of unsupported optional "
"features (%llx)\n",
sb->s_id, (unsigned long long)features);
err = -EROFS;
goto restore_opts;
}
sb->s_flags &= ~MS_RDONLY;
root = NILFS_I(sb->s_root->d_inode)->i_root;
err = nilfs_attach_log_writer(sb, root);
if (err)
goto restore_opts;
down_write(&nilfs->ns_sem);
nilfs_setup_super(sb, true);
up_write(&nilfs->ns_sem);
}
out:
return 0;
restore_opts:
sb->s_flags = old_sb_flags;
nilfs->ns_mount_opt = old_mount_opt;
return err;
}
static u64 ntfs_fix_file_name(ntfs_inode *dir_ni, ntfschar *uname,
int uname_len)
{
ntfs_volume *vol = dir_ni->vol;
ntfs_index_context *icx;
u64 mref;
le64 lemref;
int lkup;
int olderrno;
int i;
u32 cpuchar;
INDEX_ENTRY *entry;
FILE_NAME_ATTR *found;
struct {
FILE_NAME_ATTR attr;
ntfschar file_name[NTFS_MAX_NAME_LEN + 1];
} find;
mref = (u64)-1; /* default return (not found) */
icx = ntfs_index_ctx_get(dir_ni, NTFS_INDEX_I30, 4);
if (icx) {
if (uname_len > NTFS_MAX_NAME_LEN)
uname_len = NTFS_MAX_NAME_LEN;
find.attr.file_name_length = uname_len;
for (i=0; i<uname_len; i++) {
cpuchar = le16_to_cpu(uname[i]);
/*
* We need upper or lower value, whichever is smaller,
* but we can only convert to upper case, so we
* will fail when searching for an upper case char
* whose lower case is smaller (such as umlauted Y)
*/
if ((cpuchar < vol->upcase_len)
&& (le16_to_cpu(vol->upcase[cpuchar]) < cpuchar))
find.attr.file_name[i] = vol->upcase[cpuchar];
else
find.attr.file_name[i] = uname[i];
}
olderrno = errno;
lkup = ntfs_index_lookup((char*)&find, uname_len, icx);
if (errno == ENOENT)
errno = olderrno;
/*
* We generally only get the first matching candidate,
* so we still have to check whether this is a real match
*/
if (icx->entry && (icx->entry->ie_flags & INDEX_ENTRY_END))
/* get next entry if reaching end of block */
entry = ntfs_index_next(icx->entry, icx);
else
entry = icx->entry;
if (entry) {
found = &entry->key.file_name;
if (lkup
&& ntfs_names_are_equal(find.attr.file_name,
find.attr.file_name_length,
found->file_name, found->file_name_length,
IGNORE_CASE,
vol->upcase, vol->upcase_len))
lkup = 0;
if (!lkup) {
/*
* name found :
* fix original name and return inode
*/
lemref = entry->indexed_file;
mref = le64_to_cpu(lemref);
if (NVolCaseSensitive(vol) || !vol->locase) {
for (i=0; i<found->file_name_length; i++)
uname[i] = found->file_name[i];
} else {
for (i=0; i<found->file_name_length; i++)
uname[i] = vol->locase[found->file_name[i]];
}
}
}
ntfs_index_ctx_put(icx);
}
return (mref);
}
/* read the superblock from the bitmap file and initialize some bitmap fields */
static int bitmap_read_sb(struct bitmap *bitmap)
{
char *reason = NULL;
bitmap_super_t *sb;
unsigned long chunksize, daemon_sleep, write_behind;
unsigned long long events;
int err = -EINVAL;
/* page 0 is the superblock, read it... */
if (bitmap->file) {
loff_t isize = i_size_read(bitmap->file->f_mapping->host);
int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
} else {
bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0);
}
if (IS_ERR(bitmap->sb_page)) {
err = PTR_ERR(bitmap->sb_page);
bitmap->sb_page = NULL;
return err;
}
sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
chunksize = le32_to_cpu(sb->chunksize);
daemon_sleep = le32_to_cpu(sb->daemon_sleep);
write_behind = le32_to_cpu(sb->write_behind);
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
reason = "bad magic";
else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
reason = "unrecognized superblock version";
else if (chunksize < PAGE_SIZE)
reason = "bitmap chunksize too small";
else if ((1 << ffz(~chunksize)) != chunksize)
reason = "bitmap chunksize not a power of 2";
else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ)
reason = "daemon sleep period out of range";
else if (write_behind > COUNTER_MAX)
reason = "write-behind limit out of range (0 - 16383)";
if (reason) {
printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
bmname(bitmap), reason);
goto out;
}
/* keep the array size field of the bitmap superblock up to date */
sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
if (!bitmap->mddev->persistent)
goto success;
/*
* if we have a persistent array superblock, compare the
* bitmap's UUID and event counter to the mddev's
*/
if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
printk(KERN_INFO "%s: bitmap superblock UUID mismatch\n",
bmname(bitmap));
goto out;
}
events = le64_to_cpu(sb->events);
if (events < bitmap->mddev->events) {
printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) "
"-- forcing full recovery\n", bmname(bitmap), events,
(unsigned long long) bitmap->mddev->events);
sb->state |= cpu_to_le32(BITMAP_STALE);
}
success:
/* assign fields using values from superblock */
bitmap->chunksize = chunksize;
bitmap->daemon_sleep = daemon_sleep;
bitmap->daemon_lastrun = jiffies;
bitmap->max_write_behind = write_behind;
bitmap->flags |= le32_to_cpu(sb->state);
if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
bitmap->flags |= BITMAP_HOSTENDIAN;
bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
if (sb->state & cpu_to_le32(BITMAP_STALE))
bitmap->events_cleared = bitmap->mddev->events;
err = 0;
out:
kunmap_atomic(sb, KM_USER0);
if (err)
bitmap_print_sb(bitmap);
return err;
}
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super = NULL;
struct buffer_head *raw_super_buf;
struct inode *root;
long err = -EINVAL;
bool retry = true, need_fsck = false;
char *options = NULL;
int i;
try_onemore:
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
/* set a block size */
if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
goto free_sbi;
}
err = read_raw_super_block(sb, &raw_super, &raw_super_buf);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
/* init some FS parameters */
sbi->active_logs = NR_CURSEG_TYPE;
set_opt(sbi, BG_GC);
set_opt(sbi, INLINE_DATA);
#ifdef CONFIG_F2FS_FS_XATTR
set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
set_opt(sbi, POSIX_ACL);
#endif
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
if (data && !options) {
err = -ENOMEM;
goto free_sb_buf;
}
err = parse_options(sb, options);
if (err)
goto free_options;
sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
sb->s_max_links = F2FS_LINK_MAX;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
sb->s_op = &f2fs_sops;
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
sbi->sb = sb;
sbi->raw_super = raw_super;
sbi->raw_super_buf = raw_super_buf;
mutex_init(&sbi->gc_mutex);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
clear_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
sbi->read_io.sbi = sbi;
sbi->read_io.bio = NULL;
for (i = 0; i < NR_PAGE_TYPE; i++) {
init_rwsem(&sbi->write_io[i].io_rwsem);
sbi->write_io[i].sbi = sbi;
sbi->write_io[i].bio = NULL;
}
init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
goto free_options;
}
err = get_valid_checkpoint(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
}
/* sanity checking of checkpoint */
err = -EINVAL;
if (sanity_check_ckpt(sbi)) {
f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
goto free_cp;
}
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
sbi->total_valid_inode_count =
le32_to_cpu(sbi->ckpt->valid_inode_count);
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
sbi->alloc_valid_block_count = 0;
INIT_LIST_HEAD(&sbi->dir_inode_list);
spin_lock_init(&sbi->dir_inode_lock);
init_extent_cache_info(sbi);
init_ino_entry_info(sbi);
/* setup f2fs internal modules */
err = build_segment_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS segment manager");
goto free_sm;
}
err = build_node_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS node manager");
goto free_nm;
}
build_gc_manager(sbi);
/* get an inode for node space */
sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
if (IS_ERR(sbi->node_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
err = PTR_ERR(sbi->node_inode);
goto free_nm;
}
/* if there are nt orphan nodes free them */
recover_orphan_inodes(sbi);
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
err = PTR_ERR(root);
goto free_node_inode;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
err = -EINVAL;
goto free_node_inode;
}
sb->s_root = d_make_root(root); /* allocate root dentry */
if (!sb->s_root) {
err = -ENOMEM;
goto free_root_inode;
}
err = f2fs_build_stats(sbi);
if (err)
goto free_root_inode;
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
if (sbi->s_proc)
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
if (test_opt(sbi, DISCARD)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q))
f2fs_msg(sb, KERN_WARNING,
"mounting with \"discard\" option, but "
"the device does not support discard");
}
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
"%s", sb->s_id);
if (err)
goto free_proc;
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
* mount should be failed, when device has readonly mode, and
* previous checkpoint was not done by clean system shutdown.
*/
if (bdev_read_only(sb->s_bdev) &&
!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
err = -EROFS;
goto free_kobj;
}
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
err = recover_fsync_data(sbi);
if (err) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
}
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
goto free_kobj;
}
kfree(options);
return 0;
free_kobj:
kobject_del(&sbi->s_kobj);
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
f2fs_destroy_stats(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
iput(sbi->node_inode);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
free_cp:
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
kfree(options);
free_sb_buf:
brelse(raw_super_buf);
free_sbi:
kfree(sbi);
/* give only one another chance */
if (retry) {
retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
return err;
}
/*
* Splits a node by creating a sibling node and shifting half the nodes
* contents across. Assumes there is a parent node, and it has room for
* another child.
*
* Before:
* +--------+
* | Parent |
* +--------+
* |
* v
* +----------+
* | A ++++++ |
* +----------+
*
*
* After:
* +--------+
* | Parent |
* +--------+
* | |
* v +------+
* +---------+ |
* | A* +++ | v
* +---------+ +-------+
* | B +++ |
* +-------+
*
* Where A* is a shadow of A.
*/
static int btree_split_sibling(struct shadow_spine *s, dm_block_t root,
unsigned parent_index, uint64_t key)
{
int r;
size_t size;
unsigned nr_left, nr_right;
struct dm_block *left, *right, *parent;
struct btree_node *ln, *rn, *pn;
__le64 location;
left = shadow_current(s);
r = new_block(s->info, &right);
if (r < 0)
return r;
ln = dm_block_data(left);
rn = dm_block_data(right);
nr_left = le32_to_cpu(ln->header.nr_entries) / 2;
nr_right = le32_to_cpu(ln->header.nr_entries) - nr_left;
ln->header.nr_entries = cpu_to_le32(nr_left);
rn->header.flags = ln->header.flags;
rn->header.nr_entries = cpu_to_le32(nr_right);
rn->header.max_entries = ln->header.max_entries;
rn->header.value_size = ln->header.value_size;
memcpy(rn->keys, ln->keys + nr_left, nr_right * sizeof(rn->keys[0]));
size = le32_to_cpu(ln->header.flags) & INTERNAL_NODE ?
sizeof(uint64_t) : s->info->value_type.size;
memcpy(value_ptr(rn, 0), value_ptr(ln, nr_left),
size * nr_right);
/*
* Patch up the parent
*/
parent = shadow_parent(s);
pn = dm_block_data(parent);
location = cpu_to_le64(dm_block_location(left));
__dm_bless_for_disk(&location);
memcpy_disk(value_ptr(pn, parent_index),
&location, sizeof(__le64));
location = cpu_to_le64(dm_block_location(right));
__dm_bless_for_disk(&location);
r = insert_at(sizeof(__le64), pn, parent_index + 1,
le64_to_cpu(rn->keys[0]), &location);
if (r)
return r;
if (key < le64_to_cpu(rn->keys[0])) {
unlock_block(s->info, right);
s->nodes[1] = left;
} else {
unlock_block(s->info, left);
s->nodes[1] = right;
}
return 0;
}
static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv,
struct resource *io_res, u64 start, u32 size)
{
struct resource new_res = {
.start = start,
.end = start + size - 1,
.flags = IORESOURCE_MEM,
};
/* Detect a 64 bit address on a 32 bit system */
if (start != new_res.start)
return (void __iomem *) ERR_PTR(-EINVAL);
if (!resource_contains(io_res, &new_res))
return devm_ioremap_resource(dev, &new_res);
return priv->iobase + (new_res.start - io_res->start);
}
static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
struct acpi_table_tpm2 *buf)
{
struct list_head resources;
struct resource io_res;
struct device *dev = &device->dev;
u64 cmd_pa;
u32 cmd_size;
u64 rsp_pa;
u32 rsp_size;
int ret;
INIT_LIST_HEAD(&resources);
ret = acpi_dev_get_resources(device, &resources, crb_check_resource,
&io_res);
if (ret < 0)
return ret;
acpi_dev_free_resource_list(&resources);
if (resource_type(&io_res) != IORESOURCE_MEM) {
dev_err(dev,
FW_BUG "TPM2 ACPI table does not define a memory resource\n");
return -EINVAL;
}
priv->iobase = devm_ioremap_resource(dev, &io_res);
if (IS_ERR(priv->iobase))
return PTR_ERR(priv->iobase);
priv->cca = crb_map_res(dev, priv, &io_res, buf->control_address,
sizeof(struct crb_control_area));
if (IS_ERR(priv->cca))
return PTR_ERR(priv->cca);
cmd_pa = ((u64) ioread32(&priv->cca->cmd_pa_high) << 32) |
(u64) ioread32(&priv->cca->cmd_pa_low);
cmd_size = ioread32(&priv->cca->cmd_size);
priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size);
if (IS_ERR(priv->cmd))
return PTR_ERR(priv->cmd);
memcpy_fromio(&rsp_pa, &priv->cca->rsp_pa, 8);
rsp_pa = le64_to_cpu(rsp_pa);
rsp_size = ioread32(&priv->cca->rsp_size);
if (cmd_pa != rsp_pa) {
priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size);
return PTR_ERR_OR_ZERO(priv->rsp);
}
/* According to the PTP specification, overlapping command and response
* buffer sizes must be identical.
*/
if (cmd_size != rsp_size) {
dev_err(dev, FW_BUG "overlapping command and response buffer sizes are not identical");
return -EINVAL;
}
priv->rsp = priv->cmd;
return 0;
}
static int crb_acpi_add(struct acpi_device *device)
{
struct acpi_table_tpm2 *buf;
struct crb_priv *priv;
struct device *dev = &device->dev;
acpi_status status;
u32 sm;
int rc;
status = acpi_get_table(ACPI_SIG_TPM2, 1,
(struct acpi_table_header **) &buf);
if (ACPI_FAILURE(status) || buf->header.length < sizeof(*buf)) {
dev_err(dev, FW_BUG "failed to get TPM2 ACPI table\n");
return -EINVAL;
}
/* Should the FIFO driver handle this? */
sm = buf->start_method;
if (sm == ACPI_TPM2_MEMORY_MAPPED)
return -ENODEV;
priv = devm_kzalloc(dev, sizeof(struct crb_priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
/* The reason for the extra quirk is that the PTT in 4th Gen Core CPUs
* report only ACPI start but in practice seems to require both
* ACPI start and CRB start.
*/
if (sm == ACPI_TPM2_COMMAND_BUFFER || sm == ACPI_TPM2_MEMORY_MAPPED ||
!strcmp(acpi_device_hid(device), "MSFT0101"))
priv->flags |= CRB_FL_CRB_START;
if (sm == ACPI_TPM2_START_METHOD ||
sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD)
priv->flags |= CRB_FL_ACPI_START;
rc = crb_map_io(device, priv, buf);
if (rc)
return rc;
return crb_init(device, priv);
}
static int crb_acpi_remove(struct acpi_device *device)
{
struct device *dev = &device->dev;
struct tpm_chip *chip = dev_get_drvdata(dev);
tpm_chip_unregister(chip);
return 0;
}
static struct acpi_device_id crb_device_ids[] = {
{"MSFT0101", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, crb_device_ids);
static struct acpi_driver crb_acpi_driver = {
.name = "tpm_crb",
.ids = crb_device_ids,
.ops = {
.add = crb_acpi_add,
.remove = crb_acpi_remove,
},
.drv = {
.pm = &crb_pm,
},
};
static int btree_insert_raw(struct shadow_spine *s, dm_block_t root,
struct dm_btree_value_type *vt,
uint64_t key, unsigned *index)
{
int r, i = *index, top = 1;
struct btree_node *node;
for (;;) {
r = shadow_step(s, root, vt);
if (r < 0)
return r;
node = dm_block_data(shadow_current(s));
/*
* We have to patch up the parent node, ugly, but I don't
* see a way to do this automatically as part of the spine
* op.
*/
if (shadow_has_parent(s) && i >= 0) { /* FIXME: second clause unness. */
__le64 location = cpu_to_le64(dm_block_location(shadow_current(s)));
__dm_bless_for_disk(&location);
memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i),
&location, sizeof(__le64));
}
node = dm_block_data(shadow_current(s));
if (node->header.nr_entries == node->header.max_entries) {
if (top)
r = btree_split_beneath(s, key);
else
r = btree_split_sibling(s, root, i, key);
if (r < 0)
return r;
}
node = dm_block_data(shadow_current(s));
i = lower_bound(node, key);
if (le32_to_cpu(node->header.flags) & LEAF_NODE)
break;
if (i < 0) {
/* change the bounds on the lowest key */
node->keys[0] = cpu_to_le64(key);
i = 0;
}
root = value64(node, i);
top = 0;
}
if (i < 0 || le64_to_cpu(node->keys[i]) != key)
i++;
*index = i;
return 0;
}
/**
* is_gpt_valid() - tests one GPT header and PTEs for validity
* @bdev
* @lba is the logical block address of the GPT header to test
* @gpt is a GPT header ptr, filled on return.
* @ptes is a PTEs ptr, filled on return.
*
* Description: returns 1 if valid, 0 on error.
* If valid, returns pointers to newly allocated GPT header and PTEs.
*/
static int
is_gpt_valid(struct block_device *bdev, u64 lba,
gpt_header **gpt, gpt_entry **ptes)
{
u32 crc, origcrc;
u64 lastlba;
if (!bdev || !gpt || !ptes)
return 0;
if (!(*gpt = alloc_read_gpt_header(bdev, lba)))
return 0;
/* Check the GUID Partition Table signature */
if (le64_to_cpu((*gpt)->signature) != GPT_HEADER_SIGNATURE) {
pr_debug("GUID Partition Table Header signature is wrong:"
"%lld != %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->signature),
(unsigned long long)GPT_HEADER_SIGNATURE);
goto fail;
}
/* Check the GUID Partition Table CRC */
origcrc = le32_to_cpu((*gpt)->header_crc32);
(*gpt)->header_crc32 = 0;
crc = efi_crc32((const unsigned char *) (*gpt), le32_to_cpu((*gpt)->header_size));
if (crc != origcrc) {
pr_debug("GUID Partition Table Header CRC is wrong: %x != %x\n",
crc, origcrc);
goto fail;
}
(*gpt)->header_crc32 = cpu_to_le32(origcrc);
/* Check that the my_lba entry points to the LBA that contains
* the GUID Partition Table */
if (le64_to_cpu((*gpt)->my_lba) != lba) {
pr_debug("GPT my_lba incorrect: %lld != %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->my_lba),
(unsigned long long)lba);
goto fail;
}
/* Check the first_usable_lba and last_usable_lba are
* within the disk.
*/
lastlba = last_lba(bdev);
if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) {
pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->first_usable_lba),
(unsigned long long)lastlba);
goto fail;
}
if (le64_to_cpu((*gpt)->last_usable_lba) > lastlba) {
pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n",
(unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
(unsigned long long)lastlba);
goto fail;
}
if (!(*ptes = alloc_read_gpt_entries(bdev, *gpt)))
goto fail;
/* Check the GUID Partition Entry Array CRC */
crc = efi_crc32((const unsigned char *) (*ptes),
le32_to_cpu((*gpt)->num_partition_entries) *
le32_to_cpu((*gpt)->sizeof_partition_entry));
if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
pr_debug("GUID Partitition Entry Array CRC check failed.\n");
goto fail_ptes;
}
/* We're done, all's well */
return 1;
fail_ptes:
kfree(*ptes);
*ptes = NULL;
fail:
kfree(*gpt);
*gpt = NULL;
return 0;
}
static int
cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
struct tcon_link *tlink, unsigned oflags, umode_t mode,
__u32 *oplock, struct cifs_fid *fid)
{
int rc = -ENOENT;
int create_options = CREATE_NOT_DIR;
int desired_access;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = tlink_tcon(tlink);
char *full_path = NULL;
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
int disposition;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
*oplock = 0;
if (tcon->ses->server->oplocks)
*oplock = REQ_OPLOCK;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
rc = -ENOMEM;
goto out;
}
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_open(full_path, &newinode, inode->i_sb, mode,
oflags, oplock, &fid->netfid, xid);
switch (rc) {
case 0:
if (newinode == NULL) {
/* query inode info */
goto cifs_create_get_file_info;
}
if (!S_ISREG(newinode->i_mode)) {
/*
* The server may allow us to open things like
* FIFOs, but the client isn't set up to deal
* with that. If it's not a regular file, just
* close it and proceed as if it were a normal
* lookup.
*/
CIFSSMBClose(xid, tcon, fid->netfid);
goto cifs_create_get_file_info;
}
/* success, no need to query */
goto cifs_create_set_dentry;
case -ENOENT:
goto cifs_create_get_file_info;
case -EIO:
case -EINVAL:
/*
* EIO could indicate that (posix open) operation is not
* supported, despite what server claimed in capability
* negotiation.
*
* POSIX open in samba versions 3.3.1 and earlier could
* incorrectly fail with invalid parameter.
*/
tcon->broken_posix_open = true;
break;
case -EREMOTE:
case -EOPNOTSUPP:
/*
* EREMOTE indicates DFS junction, which is not handled
* in posix open. If either that or op not supported
* returned, follow the normal lookup.
*/
break;
default:
goto out;
}
/*
* fallthrough to retry, using older open call, this is case
* where server does not support this SMB level, and falsely
* claims capability (also get here for DFS case which should be
* rare for path not covered on files)
*/
}
desired_access = 0;
if (OPEN_FMODE(oflags) & FMODE_READ)
desired_access |= GENERIC_READ; /* is this too little? */
if (OPEN_FMODE(oflags) & FMODE_WRITE)
desired_access |= GENERIC_WRITE;
disposition = FILE_OVERWRITE_IF;
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
disposition = FILE_CREATE;
else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
disposition = FILE_OVERWRITE_IF;
else if ((oflags & O_CREAT) == O_CREAT)
disposition = FILE_OPEN_IF;
else
cifs_dbg(FYI, "Create flag not set in create function\n");
/*
* BB add processing to set equivalent of mode - e.g. via CreateX with
* ACLs
*/
if (!server->ops->open) {
rc = -ENOSYS;
goto out;
}
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
rc = -ENOMEM;
goto out;
}
/*
* if we're not using unix extensions, see if we need to set
* ATTR_READONLY on the create call
*/
if (!tcon->unix_ext && (mode & S_IWUGO) == 0)
create_options |= CREATE_OPTION_READONLY;
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = desired_access;
oparms.create_options = create_options;
oparms.disposition = disposition;
oparms.path = full_path;
oparms.fid = fid;
oparms.reconnect = false;
rc = server->ops->open(xid, &oparms, oplock, buf);
if (rc) {
cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc);
goto out;
}
/*
* If Open reported that we actually created a file then we now have to
* set the mode if possible.
*/
if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
struct cifs_unix_set_info_args args = {
.mode = mode,
.ctime = NO_CHANGE_64,
.atime = NO_CHANGE_64,
.mtime = NO_CHANGE_64,
.device = 0,
};
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = current_fsuid();
if (inode->i_mode & S_ISGID)
args.gid = inode->i_gid;
else
args.gid = current_fsgid();
} else {
args.uid = INVALID_UID; /* no change */
args.gid = INVALID_GID; /* no change */
}
CIFSSMBUnixSetFileInfo(xid, tcon, &args, fid->netfid,
current->tgid);
} else {
/*
* BB implement mode setting via Windows security
* descriptors e.g.
*/
/* CIFSSMBWinSetPerms(xid,tcon,path,mode,-1,-1,nls);*/
/* Could set r/o dos attribute if mode & 0222 == 0 */
}
cifs_create_get_file_info:
/* server might mask mode so we have to query for it */
if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb,
xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb,
xid, fid);
if (newinode) {
if (server->ops->set_lease_key)
server->ops->set_lease_key(newinode, fid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
newinode->i_mode = mode;
if ((*oplock & CIFS_CREATE_ACTION) &&
(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
newinode->i_uid = current_fsuid();
if (inode->i_mode & S_ISGID)
newinode->i_gid = inode->i_gid;
else
newinode->i_gid = current_fsgid();
}
}
}
cifs_create_set_dentry:
if (rc != 0) {
cifs_dbg(FYI, "Create worked, get_inode_info failed rc = %d\n",
rc);
if (server->ops->close)
server->ops->close(xid, tcon, fid);
goto out;
}
d_drop(direntry);
d_add(direntry, newinode);
out:
kfree(buf);
kfree(full_path);
return rc;
}
/**
* compare_gpts() - Search disk for valid GPT headers and PTEs
* @pgpt is the primary GPT header
* @agpt is the alternate GPT header
* @lastlba is the last LBA number
* Description: Returns nothing. Sanity checks pgpt and agpt fields
* and prints warnings on discrepancies.
*
*/
static void
compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba)
{
int error_found = 0;
if (!pgpt || !agpt)
return;
if (le64_to_cpu(pgpt->my_lba) != le64_to_cpu(agpt->alternate_lba)) {
printk(KERN_WARNING
"GPT:Primary header LBA != Alt. header alternate_lba\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->my_lba),
(unsigned long long)le64_to_cpu(agpt->alternate_lba));
error_found++;
}
if (le64_to_cpu(pgpt->alternate_lba) != le64_to_cpu(agpt->my_lba)) {
printk(KERN_WARNING
"GPT:Primary header alternate_lba != Alt. header my_lba\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->alternate_lba),
(unsigned long long)le64_to_cpu(agpt->my_lba));
error_found++;
}
if (le64_to_cpu(pgpt->first_usable_lba) !=
le64_to_cpu(agpt->first_usable_lba)) {
printk(KERN_WARNING "GPT:first_usable_lbas don't match.\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->first_usable_lba),
(unsigned long long)le64_to_cpu(agpt->first_usable_lba));
error_found++;
}
if (le64_to_cpu(pgpt->last_usable_lba) !=
le64_to_cpu(agpt->last_usable_lba)) {
printk(KERN_WARNING "GPT:last_usable_lbas don't match.\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->last_usable_lba),
(unsigned long long)le64_to_cpu(agpt->last_usable_lba));
error_found++;
}
if (efi_guidcmp(pgpt->disk_guid, agpt->disk_guid)) {
printk(KERN_WARNING "GPT:disk_guids don't match.\n");
error_found++;
}
if (le32_to_cpu(pgpt->num_partition_entries) !=
le32_to_cpu(agpt->num_partition_entries)) {
printk(KERN_WARNING "GPT:num_partition_entries don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->num_partition_entries),
le32_to_cpu(agpt->num_partition_entries));
error_found++;
}
if (le32_to_cpu(pgpt->sizeof_partition_entry) !=
le32_to_cpu(agpt->sizeof_partition_entry)) {
printk(KERN_WARNING
"GPT:sizeof_partition_entry values don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->sizeof_partition_entry),
le32_to_cpu(agpt->sizeof_partition_entry));
error_found++;
}
if (le32_to_cpu(pgpt->partition_entry_array_crc32) !=
le32_to_cpu(agpt->partition_entry_array_crc32)) {
printk(KERN_WARNING
"GPT:partition_entry_array_crc32 values don't match: "
"0x%x != 0x%x\n",
le32_to_cpu(pgpt->partition_entry_array_crc32),
le32_to_cpu(agpt->partition_entry_array_crc32));
error_found++;
}
if (le64_to_cpu(pgpt->alternate_lba) != lastlba) {
printk(KERN_WARNING
"GPT:Primary header thinks Alt. header is not at the end of the disk.\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(pgpt->alternate_lba),
(unsigned long long)lastlba);
error_found++;
}
if (le64_to_cpu(agpt->my_lba) != lastlba) {
printk(KERN_WARNING
"GPT:Alternate GPT header not at the end of the disk.\n");
printk(KERN_WARNING "GPT:%lld != %lld\n",
(unsigned long long)le64_to_cpu(agpt->my_lba),
(unsigned long long)lastlba);
error_found++;
}
if (error_found)
printk(KERN_WARNING
"GPT: Use GNU Parted to correct GPT errors.\n");
return;
}
int
cifs_get_inode_info(struct inode **pinode, const unsigned char *search_path,
FILE_ALL_INFO * pfindData, struct super_block *sb, int xid)
{
int rc = 0;
struct cifsTconInfo *pTcon;
struct inode *inode;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
char *tmp_path;
char *buf = NULL;
pTcon = cifs_sb->tcon;
cFYI(1,("Getting info on %s ", search_path));
if((pfindData == NULL) && (*pinode != NULL)) {
if(CIFS_I(*pinode)->clientCanCacheRead) {
cFYI(1,("No need to revalidate inode sizes on cached file "));
return rc;
}
}
/* if file info not passed in then get it from server */
if(pfindData == NULL) {
buf = kmalloc(sizeof(FILE_ALL_INFO),GFP_KERNEL);
pfindData = (FILE_ALL_INFO *)buf;
/* could do find first instead but this returns more info */
rc = CIFSSMBQPathInfo(xid, pTcon, search_path, pfindData,
cifs_sb->local_nls);
}
/* dump_mem("\nQPathInfo return data",&findData, sizeof(findData)); */
if (rc) {
if (rc == -EREMOTE) {
tmp_path =
kmalloc(strnlen
(pTcon->treeName,
MAX_TREE_SIZE + 1) +
strnlen(search_path, MAX_PATHCONF) + 1,
GFP_KERNEL);
if (tmp_path == NULL) {
if(buf)
kfree(buf);
return -ENOMEM;
}
strncpy(tmp_path, pTcon->treeName, MAX_TREE_SIZE);
strncat(tmp_path, search_path, MAX_PATHCONF);
rc = connect_to_dfs_path(xid, pTcon->ses,
/* treename + */ tmp_path,
cifs_sb->local_nls);
kfree(tmp_path);
/* BB fix up inode etc. */
} else if (rc) {
if(buf)
kfree(buf);
return rc;
}
} else {
struct cifsInodeInfo *cifsInfo;
/* get new inode */
if (*pinode == NULL) {
*pinode = new_inode(sb);
if(*pinode == NULL)
return -ENOMEM;
insert_inode_hash(*pinode);
}
inode = *pinode;
cifsInfo = CIFS_I(inode);
pfindData->Attributes = le32_to_cpu(pfindData->Attributes);
cifsInfo->cifsAttrs = pfindData->Attributes;
cFYI(1, (" Old time %ld ", cifsInfo->time));
cifsInfo->time = jiffies;
cFYI(1, (" New time %ld ", cifsInfo->time));
/* blksize needs to be multiple of two. So safer to default to blksize
and blkbits set in superblock so 2**blkbits and blksize will match */
/* inode->i_blksize =
(pTcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE) & 0xFFFFFE00;*/
/* Linux can not store file creation time unfortunately so we ignore it */
inode->i_atime =
cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
inode->i_mtime =
cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
inode->i_ctime =
cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
cFYI(0,
(" Attributes came in as 0x%x ", pfindData->Attributes));
/* set default mode. will override for dirs below */
if(atomic_read(&cifsInfo->inUse) == 0)
/* new inode, can safely set these fields */
inode->i_mode = cifs_sb->mnt_file_mode;
if (pfindData->Attributes & ATTR_REPARSE) {
/* Can IFLNK be set as it basically is on windows with IFREG or IFDIR? */
inode->i_mode |= S_IFLNK;
} else if (pfindData->Attributes & ATTR_DIRECTORY) {
/* override default perms since we do not do byte range locking on dirs */
inode->i_mode = cifs_sb->mnt_dir_mode;
inode->i_mode |= S_IFDIR;
} else {
inode->i_mode |= S_IFREG;
/* treat the dos attribute of read-only as read-only mode e.g. 555 */
if(cifsInfo->cifsAttrs & ATTR_READONLY)
inode->i_mode &= ~(S_IWUGO);
/* BB add code here - validate if device or weird share or device type? */
}
if(is_size_safe_to_change(cifsInfo)) {
/* can not safely change the file size here if the
client is writing to it due to potential races */
i_size_write(inode,le64_to_cpu(pfindData->EndOfFile));
/* 512 bytes (2**9) is the fake blocksize that must be used */
/* for this calculation */
inode->i_blocks = (512 - 1 + pfindData->AllocationSize)
>> 9;
}
pfindData->AllocationSize = le64_to_cpu(pfindData->AllocationSize);
inode->i_nlink = le32_to_cpu(pfindData->NumberOfLinks);
/* BB fill in uid and gid here? with help from winbind?
or retrieve from NTFS stream extended attribute */
if(atomic_read(&cifsInfo->inUse) == 0) {
inode->i_uid = cifs_sb->mnt_uid;
inode->i_gid = cifs_sb->mnt_gid;
/* set so we do not keep refreshing these fields with
bad data after user has changed them in memory */
atomic_set(&cifsInfo->inUse,1);
}
if (S_ISREG(inode->i_mode)) {
cFYI(1, (" File inode "));
inode->i_op = &cifs_file_inode_ops;
inode->i_fop = &cifs_file_ops;
inode->i_data.a_ops = &cifs_addr_ops;
} else if (S_ISDIR(inode->i_mode)) {
cFYI(1, (" Directory inode "));
inode->i_op = &cifs_dir_inode_ops;
inode->i_fop = &cifs_dir_ops;
} else if (S_ISLNK(inode->i_mode)) {
cFYI(1, (" Symbolic Link inode "));
inode->i_op = &cifs_symlink_inode_ops;
} else {
init_special_inode(inode, inode->i_mode,
inode->i_rdev);
}
}
if(buf)
kfree(buf);
return rc;
}
/**
* find_valid_gpt() - Search disk for valid GPT headers and PTEs
* @bdev
* @gpt is a GPT header ptr, filled on return.
* @ptes is a PTEs ptr, filled on return.
* Description: Returns 1 if valid, 0 on error.
* If valid, returns pointers to newly allocated GPT header and PTEs.
* Validity depends on PMBR being valid (or being overridden by the
* 'gpt' kernel command line option) and finding either the Primary
* GPT header and PTEs valid, or the Alternate GPT header and PTEs
* valid. If the Primary GPT header is not valid, the Alternate GPT header
* is not checked unless the 'gpt' kernel command line option is passed.
* This protects against devices which misreport their size, and forces
* the user to decide to use the Alternate GPT.
*/
static int
find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
{
int good_pgpt = 0, good_agpt = 0, good_pmbr = 0;
gpt_header *pgpt = NULL, *agpt = NULL;
gpt_entry *pptes = NULL, *aptes = NULL;
legacy_mbr *legacymbr;
u64 lastlba;
if (!bdev || !gpt || !ptes)
return 0;
lastlba = last_lba(bdev);
if (!force_gpt) {
/* This will be added to the EFI Spec. per Intel after v1.02. */
legacymbr = kzalloc(sizeof (*legacymbr), GFP_KERNEL);
if (legacymbr) {
read_lba(bdev, 0, (u8 *) legacymbr,
sizeof (*legacymbr));
good_pmbr = is_pmbr_valid(legacymbr);
kfree(legacymbr);
}
if (!good_pmbr)
goto fail;
}
good_pgpt = is_gpt_valid(bdev, GPT_PRIMARY_PARTITION_TABLE_LBA,
&pgpt, &pptes);
if (good_pgpt)
good_agpt = is_gpt_valid(bdev,
le64_to_cpu(pgpt->alternate_lba),
&agpt, &aptes);
if (!good_agpt && force_gpt)
good_agpt = is_gpt_valid(bdev, lastlba,
&agpt, &aptes);
/* The obviously unsuccessful case */
if (!good_pgpt && !good_agpt)
goto fail;
compare_gpts(pgpt, agpt, lastlba);
/* The good cases */
if (good_pgpt) {
*gpt = pgpt;
*ptes = pptes;
kfree(agpt);
kfree(aptes);
if (!good_agpt) {
printk(KERN_WARNING
"Alternate GPT is invalid, "
"using primary GPT.\n");
}
return 1;
}
else if (good_agpt) {
*gpt = agpt;
*ptes = aptes;
kfree(pgpt);
kfree(pptes);
printk(KERN_WARNING
"Primary GPT is invalid, using alternate GPT.\n");
return 1;
}
fail:
kfree(pgpt);
kfree(agpt);
kfree(pptes);
kfree(aptes);
*gpt = NULL;
*ptes = NULL;
return 0;
}
int ocfs2_validate_inode_block(struct super_block *sb,
struct buffer_head *bh)
{
int rc;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
mlog(0, "Validating dinode %llu\n",
(unsigned long long)bh->b_blocknr);
BUG_ON(!buffer_uptodate(bh));
/*
* If the ecc fails, we return the error but otherwise
* leave the filesystem running. We know any error is
* local to this block.
*/
rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
if (rc) {
mlog(ML_ERROR, "Checksum failed for dinode %llu\n",
(unsigned long long)bh->b_blocknr);
goto bail;
}
/*
* Errors after here are fatal.
*/
rc = -EINVAL;
if (!OCFS2_IS_VALID_DINODE(di)) {
ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
(unsigned long long)bh->b_blocknr, 7,
di->i_signature);
goto bail;
}
if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
(unsigned long long)bh->b_blocknr,
(unsigned long long)le64_to_cpu(di->i_blkno));
goto bail;
}
if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
ocfs2_error(sb,
"Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
(unsigned long long)bh->b_blocknr);
goto bail;
}
if (le32_to_cpu(di->i_fs_generation) !=
OCFS2_SB(sb)->fs_generation) {
ocfs2_error(sb,
"Invalid dinode #%llu: fs_generation is %u\n",
(unsigned long long)bh->b_blocknr,
le32_to_cpu(di->i_fs_generation));
goto bail;
}
rc = 0;
bail:
return rc;
}
/* Query the cluster to determine whether we should wipe an inode from
* disk or not.
*
* Requires the inode to have the cluster lock. */
static int ocfs2_query_inode_wipe(struct inode *inode,
struct buffer_head *di_bh,
int *wipe)
{
int status = 0;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
struct ocfs2_dinode *di;
*wipe = 0;
/* While we were waiting for the cluster lock in
* ocfs2_delete_inode, another node might have asked to delete
* the inode. Recheck our flags to catch this. */
if (!ocfs2_inode_is_valid_to_delete(inode)) {
mlog(0, "Skipping delete of %llu because flags changed\n",
(unsigned long long)oi->ip_blkno);
goto bail;
}
/* Now that we have an up to date inode, we can double check
* the link count. */
if (inode->i_nlink) {
mlog(0, "Skipping delete of %llu because nlink = %u\n",
(unsigned long long)oi->ip_blkno, inode->i_nlink);
goto bail;
}
/* Do some basic inode verification... */
di = (struct ocfs2_dinode *) di_bh->b_data;
if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL))) {
/* for lack of a better error? */
status = -EEXIST;
mlog(ML_ERROR,
"Inode %llu (on-disk %llu) not orphaned! "
"Disk flags 0x%x, inode flags 0x%x\n",
(unsigned long long)oi->ip_blkno,
(unsigned long long)le64_to_cpu(di->i_blkno),
le32_to_cpu(di->i_flags), oi->ip_flags);
goto bail;
}
/* has someone already deleted us?! baaad... */
if (di->i_dtime) {
status = -EEXIST;
mlog_errno(status);
goto bail;
}
/*
* This is how ocfs2 determines whether an inode is still live
* within the cluster. Every node takes a shared read lock on
* the inode open lock in ocfs2_read_locked_inode(). When we
* get to ->delete_inode(), each node tries to convert it's
* lock to an exclusive. Trylocks are serialized by the inode
* meta data lock. If the upconvert suceeds, we know the inode
* is no longer live and can be deleted.
*
* Though we call this with the meta data lock held, the
* trylock keeps us from ABBA deadlock.
*/
status = ocfs2_try_open_lock(inode, 1);
if (status == -EAGAIN) {
status = 0;
mlog(0, "Skipping delete of %llu because it is in use on "
"other nodes\n", (unsigned long long)oi->ip_blkno);
goto bail;
}
if (status < 0) {
mlog_errno(status);
goto bail;
}
*wipe = 1;
mlog(0, "Inode %llu is ok to wipe from orphan dir %u\n",
(unsigned long long)oi->ip_blkno,
le16_to_cpu(di->i_orphaned_slot));
bail:
return status;
}
static int ocfs2_read_locked_inode(struct inode *inode,
struct ocfs2_find_inode_args *args)
{
struct super_block *sb;
struct ocfs2_super *osb;
struct ocfs2_dinode *fe;
struct buffer_head *bh = NULL;
int status, can_lock;
u32 generation = 0;
mlog_entry("(0x%p, 0x%p)\n", inode, args);
status = -EINVAL;
if (inode == NULL || inode->i_sb == NULL) {
mlog(ML_ERROR, "bad inode\n");
return status;
}
sb = inode->i_sb;
osb = OCFS2_SB(sb);
if (!args) {
mlog(ML_ERROR, "bad inode args\n");
make_bad_inode(inode);
return status;
}
/*
* To improve performance of cold-cache inode stats, we take
* the cluster lock here if possible.
*
* Generally, OCFS2 never trusts the contents of an inode
* unless it's holding a cluster lock, so taking it here isn't
* a correctness issue as much as it is a performance
* improvement.
*
* There are three times when taking the lock is not a good idea:
*
* 1) During startup, before we have initialized the DLM.
*
* 2) If we are reading certain system files which never get
* cluster locks (local alloc, truncate log).
*
* 3) If the process doing the iget() is responsible for
* orphan dir recovery. We're holding the orphan dir lock and
* can get into a deadlock with another process on another
* node in ->delete_inode().
*
* #1 and #2 can be simply solved by never taking the lock
* here for system files (which are the only type we read
* during mount). It's a heavier approach, but our main
* concern is user-accesible files anyway.
*
* #3 works itself out because we'll eventually take the
* cluster lock before trusting anything anyway.
*/
can_lock = !(args->fi_flags & OCFS2_FI_FLAG_SYSFILE)
&& !(args->fi_flags & OCFS2_FI_FLAG_ORPHAN_RECOVERY)
&& !ocfs2_mount_local(osb);
/*
* To maintain backwards compatibility with older versions of
* ocfs2-tools, we still store the generation value for system
* files. The only ones that actually matter to userspace are
* the journals, but it's easier and inexpensive to just flag
* all system files similarly.
*/
if (args->fi_flags & OCFS2_FI_FLAG_SYSFILE)
generation = osb->fs_generation;
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_inode_lockres,
OCFS2_LOCK_TYPE_META,
generation, inode);
ocfs2_inode_lock_res_init(&OCFS2_I(inode)->ip_open_lockres,
OCFS2_LOCK_TYPE_OPEN,
0, inode);
if (can_lock) {
status = ocfs2_open_lock(inode);
if (status) {
make_bad_inode(inode);
mlog_errno(status);
return status;
}
status = ocfs2_inode_lock(inode, NULL, 0);
if (status) {
make_bad_inode(inode);
mlog_errno(status);
return status;
}
}
if (args->fi_flags & OCFS2_FI_FLAG_ORPHAN_RECOVERY) {
status = ocfs2_try_open_lock(inode, 0);
if (status) {
make_bad_inode(inode);
return status;
}
}
if (can_lock) {
status = ocfs2_read_inode_block_full(inode, &bh,
OCFS2_BH_IGNORE_CACHE);
} else {
status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
if (!status)
status = ocfs2_validate_inode_block(osb->sb, bh);
}
if (status < 0) {
mlog_errno(status);
goto bail;
}
status = -EINVAL;
fe = (struct ocfs2_dinode *) bh->b_data;
/*
* This is a code bug. Right now the caller needs to
* understand whether it is asking for a system file inode or
* not so the proper lock names can be built.
*/
mlog_bug_on_msg(!!(fe->i_flags & cpu_to_le32(OCFS2_SYSTEM_FL)) !=
!!(args->fi_flags & OCFS2_FI_FLAG_SYSFILE),
"Inode %llu: system file state is ambigous\n",
(unsigned long long)args->fi_blkno);
if (S_ISCHR(le16_to_cpu(fe->i_mode)) ||
S_ISBLK(le16_to_cpu(fe->i_mode)))
inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
ocfs2_populate_inode(inode, fe, 0);
BUG_ON(args->fi_blkno != le64_to_cpu(fe->i_blkno));
status = 0;
bail:
if (can_lock)
ocfs2_inode_unlock(inode, 0);
if (status < 0)
make_bad_inode(inode);
if (args && bh)
brelse(bh);
mlog_exit(status);
return status;
}
void convert_thread_options_to_cpu(struct thread_options *o,
struct thread_options_pack *top)
{
int i, j;
for (i = 0; i < NR_OPTS_SZ; i++)
o->set_options[i] = le64_to_cpu(top->set_options[i]);
string_to_cpu(&o->description, top->description);
string_to_cpu(&o->name, top->name);
string_to_cpu(&o->directory, top->directory);
string_to_cpu(&o->filename, top->filename);
string_to_cpu(&o->filename_format, top->filename_format);
string_to_cpu(&o->opendir, top->opendir);
string_to_cpu(&o->ioengine, top->ioengine);
string_to_cpu(&o->mmapfile, top->mmapfile);
string_to_cpu(&o->read_iolog_file, top->read_iolog_file);
string_to_cpu(&o->write_iolog_file, top->write_iolog_file);
string_to_cpu(&o->bw_log_file, top->bw_log_file);
string_to_cpu(&o->lat_log_file, top->lat_log_file);
string_to_cpu(&o->iops_log_file, top->iops_log_file);
string_to_cpu(&o->replay_redirect, top->replay_redirect);
string_to_cpu(&o->exec_prerun, top->exec_prerun);
string_to_cpu(&o->exec_postrun, top->exec_postrun);
string_to_cpu(&o->ioscheduler, top->ioscheduler);
string_to_cpu(&o->profile, top->profile);
string_to_cpu(&o->cgroup, top->cgroup);
o->allow_create = le32_to_cpu(top->allow_create);
o->allow_mounted_write = le32_to_cpu(top->allow_mounted_write);
o->td_ddir = le32_to_cpu(top->td_ddir);
o->rw_seq = le32_to_cpu(top->rw_seq);
o->kb_base = le32_to_cpu(top->kb_base);
o->unit_base = le32_to_cpu(top->kb_base);
o->ddir_seq_nr = le32_to_cpu(top->ddir_seq_nr);
o->ddir_seq_add = le64_to_cpu(top->ddir_seq_add);
o->iodepth = le32_to_cpu(top->iodepth);
o->iodepth_low = le32_to_cpu(top->iodepth_low);
o->iodepth_batch = le32_to_cpu(top->iodepth_batch);
o->iodepth_batch_complete_min = le32_to_cpu(top->iodepth_batch_complete_min);
o->iodepth_batch_complete_max = le32_to_cpu(top->iodepth_batch_complete_max);
o->size = le64_to_cpu(top->size);
o->io_limit = le64_to_cpu(top->io_limit);
o->size_percent = le32_to_cpu(top->size_percent);
o->fill_device = le32_to_cpu(top->fill_device);
o->file_append = le32_to_cpu(top->file_append);
o->file_size_low = le64_to_cpu(top->file_size_low);
o->file_size_high = le64_to_cpu(top->file_size_high);
o->start_offset = le64_to_cpu(top->start_offset);
for (i = 0; i < DDIR_RWDIR_CNT; i++) {
o->bs[i] = le32_to_cpu(top->bs[i]);
o->ba[i] = le32_to_cpu(top->ba[i]);
o->min_bs[i] = le32_to_cpu(top->min_bs[i]);
o->max_bs[i] = le32_to_cpu(top->max_bs[i]);
o->bssplit_nr[i] = le32_to_cpu(top->bssplit_nr[i]);
if (o->bssplit_nr[i]) {
o->bssplit[i] = malloc(o->bssplit_nr[i] * sizeof(struct bssplit));
for (j = 0; j < o->bssplit_nr[i]; j++) {
o->bssplit[i][j].bs = le32_to_cpu(top->bssplit[i][j].bs);
o->bssplit[i][j].perc = le32_to_cpu(top->bssplit[i][j].perc);
}
}
o->rwmix[i] = le32_to_cpu(top->rwmix[i]);
o->rate[i] = le32_to_cpu(top->rate[i]);
o->ratemin[i] = le32_to_cpu(top->ratemin[i]);
o->rate_iops[i] = le32_to_cpu(top->rate_iops[i]);
o->rate_iops_min[i] = le32_to_cpu(top->rate_iops_min[i]);
o->perc_rand[i] = le32_to_cpu(top->perc_rand[i]);
}
o->ratecycle = le32_to_cpu(top->ratecycle);
o->io_submit_mode = le32_to_cpu(top->io_submit_mode);
o->nr_files = le32_to_cpu(top->nr_files);
o->open_files = le32_to_cpu(top->open_files);
o->file_lock_mode = le32_to_cpu(top->file_lock_mode);
o->odirect = le32_to_cpu(top->odirect);
o->oatomic = le32_to_cpu(top->oatomic);
o->invalidate_cache = le32_to_cpu(top->invalidate_cache);
o->create_serialize = le32_to_cpu(top->create_serialize);
o->create_fsync = le32_to_cpu(top->create_fsync);
o->create_on_open = le32_to_cpu(top->create_on_open);
o->create_only = le32_to_cpu(top->create_only);
o->end_fsync = le32_to_cpu(top->end_fsync);
o->pre_read = le32_to_cpu(top->pre_read);
o->sync_io = le32_to_cpu(top->sync_io);
o->verify = le32_to_cpu(top->verify);
o->do_verify = le32_to_cpu(top->do_verify);
o->verifysort = le32_to_cpu(top->verifysort);
o->verifysort_nr = le32_to_cpu(top->verifysort_nr);
o->experimental_verify = le32_to_cpu(top->experimental_verify);
o->verify_state = le32_to_cpu(top->verify_state);
o->verify_interval = le32_to_cpu(top->verify_interval);
o->verify_offset = le32_to_cpu(top->verify_offset);
memcpy(o->verify_pattern, top->verify_pattern, MAX_PATTERN_SIZE);
memcpy(o->buffer_pattern, top->buffer_pattern, MAX_PATTERN_SIZE);
o->verify_pattern_bytes = le32_to_cpu(top->verify_pattern_bytes);
o->verify_fatal = le32_to_cpu(top->verify_fatal);
o->verify_dump = le32_to_cpu(top->verify_dump);
o->verify_async = le32_to_cpu(top->verify_async);
o->verify_batch = le32_to_cpu(top->verify_batch);
o->use_thread = le32_to_cpu(top->use_thread);
o->unlink = le32_to_cpu(top->unlink);
o->do_disk_util = le32_to_cpu(top->do_disk_util);
o->override_sync = le32_to_cpu(top->override_sync);
o->rand_repeatable = le32_to_cpu(top->rand_repeatable);
o->allrand_repeatable = le32_to_cpu(top->allrand_repeatable);
o->rand_seed = le64_to_cpu(top->rand_seed);
o->log_avg_msec = le32_to_cpu(top->log_avg_msec);
o->log_offset = le32_to_cpu(top->log_offset);
o->log_gz = le32_to_cpu(top->log_gz);
o->log_gz_store = le32_to_cpu(top->log_gz_store);
o->norandommap = le32_to_cpu(top->norandommap);
o->softrandommap = le32_to_cpu(top->softrandommap);
o->bs_unaligned = le32_to_cpu(top->bs_unaligned);
o->fsync_on_close = le32_to_cpu(top->fsync_on_close);
o->bs_is_seq_rand = le32_to_cpu(top->bs_is_seq_rand);
o->random_distribution = le32_to_cpu(top->random_distribution);
o->zipf_theta.u.f = fio_uint64_to_double(le64_to_cpu(top->zipf_theta.u.i));
o->pareto_h.u.f = fio_uint64_to_double(le64_to_cpu(top->pareto_h.u.i));
o->gauss_dev.u.f = fio_uint64_to_double(le64_to_cpu(top->gauss_dev.u.i));
o->random_generator = le32_to_cpu(top->random_generator);
o->hugepage_size = le32_to_cpu(top->hugepage_size);
o->rw_min_bs = le32_to_cpu(top->rw_min_bs);
o->thinktime = le32_to_cpu(top->thinktime);
o->thinktime_spin = le32_to_cpu(top->thinktime_spin);
o->thinktime_blocks = le32_to_cpu(top->thinktime_blocks);
o->fsync_blocks = le32_to_cpu(top->fsync_blocks);
o->fdatasync_blocks = le32_to_cpu(top->fdatasync_blocks);
o->barrier_blocks = le32_to_cpu(top->barrier_blocks);
o->verify_backlog = le64_to_cpu(top->verify_backlog);
o->start_delay = le64_to_cpu(top->start_delay);
o->start_delay_high = le64_to_cpu(top->start_delay_high);
o->timeout = le64_to_cpu(top->timeout);
o->ramp_time = le64_to_cpu(top->ramp_time);
o->zone_range = le64_to_cpu(top->zone_range);
o->zone_size = le64_to_cpu(top->zone_size);
o->zone_skip = le64_to_cpu(top->zone_skip);
o->lockmem = le64_to_cpu(top->lockmem);
o->offset_increment = le64_to_cpu(top->offset_increment);
o->number_ios = le64_to_cpu(top->number_ios);
o->overwrite = le32_to_cpu(top->overwrite);
o->bw_avg_time = le32_to_cpu(top->bw_avg_time);
o->iops_avg_time = le32_to_cpu(top->iops_avg_time);
o->loops = le32_to_cpu(top->loops);
o->mem_type = le32_to_cpu(top->mem_type);
o->mem_align = le32_to_cpu(top->mem_align);
o->max_latency = le32_to_cpu(top->max_latency);
o->stonewall = le32_to_cpu(top->stonewall);
o->new_group = le32_to_cpu(top->new_group);
o->numjobs = le32_to_cpu(top->numjobs);
o->cpus_allowed_policy = le32_to_cpu(top->cpus_allowed_policy);
o->iolog = le32_to_cpu(top->iolog);
o->rwmixcycle = le32_to_cpu(top->rwmixcycle);
o->nice = le32_to_cpu(top->nice);
o->ioprio = le32_to_cpu(top->ioprio);
o->ioprio_class = le32_to_cpu(top->ioprio_class);
o->file_service_type = le32_to_cpu(top->file_service_type);
o->group_reporting = le32_to_cpu(top->group_reporting);
o->fadvise_hint = le32_to_cpu(top->fadvise_hint);
o->fallocate_mode = le32_to_cpu(top->fallocate_mode);
o->zero_buffers = le32_to_cpu(top->zero_buffers);
o->refill_buffers = le32_to_cpu(top->refill_buffers);
o->scramble_buffers = le32_to_cpu(top->scramble_buffers);
o->buffer_pattern_bytes = le32_to_cpu(top->buffer_pattern_bytes);
o->time_based = le32_to_cpu(top->time_based);
o->disable_lat = le32_to_cpu(top->disable_lat);
o->disable_clat = le32_to_cpu(top->disable_clat);
o->disable_slat = le32_to_cpu(top->disable_slat);
o->disable_bw = le32_to_cpu(top->disable_bw);
o->unified_rw_rep = le32_to_cpu(top->unified_rw_rep);
o->gtod_reduce = le32_to_cpu(top->gtod_reduce);
o->gtod_cpu = le32_to_cpu(top->gtod_cpu);
o->clocksource = le32_to_cpu(top->clocksource);
o->no_stall = le32_to_cpu(top->no_stall);
o->trim_percentage = le32_to_cpu(top->trim_percentage);
o->trim_batch = le32_to_cpu(top->trim_batch);
o->trim_zero = le32_to_cpu(top->trim_zero);
o->clat_percentiles = le32_to_cpu(top->clat_percentiles);
o->percentile_precision = le32_to_cpu(top->percentile_precision);
o->continue_on_error = le32_to_cpu(top->continue_on_error);
o->cgroup_weight = le32_to_cpu(top->cgroup_weight);
o->cgroup_nodelete = le32_to_cpu(top->cgroup_nodelete);
o->uid = le32_to_cpu(top->uid);
o->gid = le32_to_cpu(top->gid);
o->flow_id = __le32_to_cpu(top->flow_id);
o->flow = __le32_to_cpu(top->flow);
o->flow_watermark = __le32_to_cpu(top->flow_watermark);
o->flow_sleep = le32_to_cpu(top->flow_sleep);
o->sync_file_range = le32_to_cpu(top->sync_file_range);
o->latency_target = le64_to_cpu(top->latency_target);
o->latency_window = le64_to_cpu(top->latency_window);
o->latency_percentile.u.f = fio_uint64_to_double(le64_to_cpu(top->latency_percentile.u.i));
o->compress_percentage = le32_to_cpu(top->compress_percentage);
o->compress_chunk = le32_to_cpu(top->compress_chunk);
o->dedupe_percentage = le32_to_cpu(top->dedupe_percentage);
o->skip_bad = le32_to_cpu(top->skip_bad);
o->block_error_hist = le32_to_cpu(top->block_error_hist);
o->replay_align = le32_to_cpu(top->replay_align);
o->replay_scale = le32_to_cpu(top->replay_scale);
o->per_job_logs = le32_to_cpu(top->per_job_logs);
o->trim_backlog = le64_to_cpu(top->trim_backlog);
for (i = 0; i < FIO_IO_U_LIST_MAX_LEN; i++)
o->percentile_list[i].u.f = fio_uint64_to_double(le64_to_cpu(top->percentile_list[i].u.i));
#if 0
uint8_t cpumask[FIO_TOP_STR_MAX];
uint8_t verify_cpumask[FIO_TOP_STR_MAX];
#endif
}
