*/
static int readpage_nounlock(struct file *filp, struct page *page)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_inode_to_client(inode)->client->osdc;
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- int rc, bytes;
+ int rc = req->r_result;
+ int bytes = le32_to_cpu(msg->hdr.data_len);
int i;
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- rc = le32_to_cpu(replyhead->result);
- bytes = le32_to_cpu(msg->hdr.data_len);
-
dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
/* unlock all pages, zeroing any data we didn't read */
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0,
ci->i_truncate_seq, ci->i_truncate_size,
- NULL, false, 1, 0);
+ NULL, false, 0);
if (IS_ERR(req))
return PTR_ERR(req);
static int ceph_readpages(struct file *file, struct address_space *mapping,
struct list_head *page_list, unsigned nr_pages)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
int rc = 0;
int max = 0;
&ci->i_layout, snapc,
page_off, len,
ci->i_truncate_seq, ci->i_truncate_size,
- &inode->i_mtime,
- &page, 1, 0, 0, true);
+ &inode->i_mtime, &page, 1);
if (err < 0) {
dout("writepage setting page/mapping error %d %p\n", err, page);
SetPageError(page);
struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- struct ceph_osd_op *op;
struct ceph_inode_info *ci = ceph_inode(inode);
unsigned wrote;
struct page *page;
int i;
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
- __s32 rc = -EIO;
- u64 bytes = 0;
+ int rc = req->r_result;
+ u64 bytes = le64_to_cpu(req->r_request_ops[0].extent.length);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
long writeback_stat;
unsigned issued = ceph_caps_issued(ci);
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- op = (void *)(replyhead + 1);
- rc = le32_to_cpu(replyhead->result);
- bytes = le64_to_cpu(op->extent.length);
-
if (rc >= 0) {
/*
* Assume we wrote the pages we originally sent. The
struct page *page;
int want;
u64 offset, len;
- struct ceph_osd_request_head *reqhead;
- struct ceph_osd_op *op;
long writeback_stat;
next = 0;
snapc, do_sync,
ci->i_truncate_seq,
ci->i_truncate_size,
- &inode->i_mtime, true, 1, 0);
+ &inode->i_mtime, true, 0);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
/* revise final length, page count */
req->r_num_pages = locked_pages;
- reqhead = req->r_request->front.iov_base;
- op = (void *)(reqhead + 1);
- op->extent.length = cpu_to_le64(len);
- op->payload_len = cpu_to_le32(len);
+ req->r_request_ops[0].extent.length = cpu_to_le64(len);
+ req->r_request_ops[0].payload_len = cpu_to_le32(len);
req->r_request->hdr.data_len = cpu_to_le32(len);
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
loff_t pos, unsigned len,
struct page *page)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
loff_t page_off = pos & PAGE_CACHE_MASK;
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = file->private_data;
struct page *page;
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
*/
static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct page *page = vmf->page;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
loff_t off = page_offset(page);
if (flags & CEPH_CAP_FLAG_AUTH)
ci->i_auth_cap = cap;
- else if (ci->i_auth_cap == cap)
+ else if (ci->i_auth_cap == cap) {
ci->i_auth_cap = NULL;
+ spin_lock(&mdsc->cap_dirty_lock);
+ if (!list_empty(&ci->i_dirty_item)) {
+ dout(" moving %p to cap_dirty_migrating\n", inode);
+ list_move(&ci->i_dirty_item,
+ &mdsc->cap_dirty_migrating);
+ }
+ spin_unlock(&mdsc->cap_dirty_lock);
+ }
dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
u64 size, u64 max_size,
struct timespec *mtime, struct timespec *atime,
u64 time_warp_seq,
- uid_t uid, gid_t gid, umode_t mode,
+ kuid_t uid, kgid_t gid, umode_t mode,
u64 xattr_version,
struct ceph_buffer *xattrs_buf,
u64 follows)
ceph_encode_timespec(&fc->atime, atime);
fc->time_warp_seq = cpu_to_le32(time_warp_seq);
- fc->uid = cpu_to_le32(uid);
- fc->gid = cpu_to_le32(gid);
+ fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
+ fc->gid = cpu_to_le32(from_kgid(&init_user_ns, gid));
fc->mode = cpu_to_le32(mode);
fc->xattr_version = cpu_to_le64(xattr_version);
struct timespec mtime, atime;
int wake = 0;
umode_t mode;
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
struct ceph_mds_session *session;
u64 xattr_version = 0;
struct ceph_buffer *xattr_blob = NULL;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
- int file_wanted, used;
+ int file_wanted, used, cap_used;
int took_snap_rwsem = 0; /* true if mdsc->snap_rwsem held */
int issued, implemented, want, retain, revoking, flushing = 0;
int mds = -1; /* keep track of how far we've gone through i_caps list
/* NOTE: no side-effects allowed, until we take s_mutex */
+ cap_used = used;
+ if (ci->i_auth_cap && cap != ci->i_auth_cap)
+ cap_used &= ~ci->i_auth_cap->issued;
+
revoking = cap->implemented & ~cap->issued;
- dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+ dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
cap->mds, cap, ceph_cap_string(cap->issued),
+ ceph_cap_string(cap_used),
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
}
/* completed revocation? going down and there are no caps? */
- if (revoking && (revoking & used) == 0) {
+ if (revoking && (revoking & cap_used) == 0) {
dout("completed revocation of %s\n",
ceph_cap_string(cap->implemented & ~cap->issued));
goto ack;
sent++;
/* __send_cap drops i_ceph_lock */
- delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
- retain, flushing, NULL);
+ delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
+ want, retain, flushing, NULL);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
- inode->i_uid = le32_to_cpu(grant->uid);
- inode->i_gid = le32_to_cpu(grant->gid);
+ inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
+ inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
- inode->i_uid, inode->i_gid);
+ from_kuid(&init_user_ns, inode->i_uid),
+ from_kgid(&init_user_ns, inode->i_gid));
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
dout("mds wanted %s -> %s\n",
ceph_cap_string(le32_to_cpu(grant->wanted)),
ceph_cap_string(wanted));
- grant->wanted = cpu_to_le32(wanted);
+ /* imported cap may not have correct mds_wanted */
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT)
+ check_caps = 1;
}
cap->seq = seq;
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
+ if (op == CEPH_CAP_OP_IMPORT)
+ ceph_add_cap_releases(mdsc, session);
+
/* lookup ino */
inode = ceph_find_inode(sb, vino);
ci = ceph_inode(inode);
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
+ if (err)
+ goto out_err;
+
err = ceph_handle_snapdir(req, dentry, err);
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
+ if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ *opened |= FILE_CREATED;
+ }
err = finish_open(file, dentry, ceph_open, opened);
}
static ssize_t ceph_sync_read(struct file *file, char __user *data,
unsigned len, loff_t *poff, int *checkeof)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct page **pages;
u64 off = *poff;
int num_pages, ret;
static ssize_t ceph_sync_write(struct file *file, const char __user *data,
size_t left, loff_t *offset)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_osd_request *req;
int ret;
struct timespec mtime = CURRENT_TIME;
- if (ceph_snap(file->f_dentry->d_inode) != CEPH_NOSNAP)
+ if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
dout("sync_write on file %p %lld~%u %s\n", file, *offset,
ci->i_snap_realm->cached_context,
do_sync,
ci->i_truncate_seq, ci->i_truncate_size,
- &mtime, false, 2, page_align);
+ &mtime, false, page_align);
if (IS_ERR(req))
return PTR_ERR(req);
struct ceph_file_info *fi = filp->private_data;
loff_t *ppos = &iocb->ki_pos;
size_t len = iov->iov_len;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
void __user *base = iov->iov_base;
ssize_t ret;
{
struct file *file = iocb->ki_filp;
struct ceph_file_info *fi = file->private_data;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
*/
static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
{
- struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
+ struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout l;
int err;
- err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
+ err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (!err) {
l.stripe_unit = ceph_file_layout_su(ci->i_layout);
l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct inode *parent_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
- struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
+ struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout nl;
int err;
return -EFAULT;
/* validate changed params against current layout */
- err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
+ err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (err)
return err;
*/
static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
int err;
static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
{
struct ceph_ioctl_dataloc dl;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
u64 len = 1, olen;
u64 tmp;
- struct ceph_object_layout ol;
struct ceph_pg pgid;
int r;
return -EFAULT;
down_read(&osdc->map_sem);
- r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
+ r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
if (r < 0)
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
- ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout,
+ ceph_calc_object_layout(&pgid, dl.object_name, &ci->i_layout,
osdc->osdmap);
- pgid = ol.ol_pgid;
dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
if (dl.osd >= 0) {
struct ceph_entity_addr *a =
static long ceph_ioctl_lazyio(struct file *file)
{
struct ceph_file_info *fi = file->private_data;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
return -EIO;
}
+ /*
+ * parse create results
+ */
+ static int parse_reply_info_create(void **p, void *end,
+ struct ceph_mds_reply_info_parsed *info,
+ int features)
+ {
+ if (features & CEPH_FEATURE_REPLY_CREATE_INODE) {
+ if (*p == end) {
+ info->has_create_ino = false;
+ } else {
+ info->has_create_ino = true;
+ info->ino = ceph_decode_64(p);
+ }
+ }
+
+ if (unlikely(*p != end))
+ goto bad;
+ return 0;
+
+ bad:
+ return -EIO;
+ }
+
/*
* parse extra results
*/
{
if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
- else
+ else if (info->head->op == CEPH_MDS_OP_READDIR)
return parse_reply_info_dir(p, end, info, features);
+ else if (info->head->op == CEPH_MDS_OP_CREATE)
+ return parse_reply_info_create(p, end, info, features);
+ else
+ return -EIO;
}
/*
head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
head->op = cpu_to_le32(req->r_op);
- head->caller_uid = cpu_to_le32(req->r_uid);
- head->caller_gid = cpu_to_le32(req->r_gid);
+ head->caller_uid = cpu_to_le32(from_kuid(&init_user_ns, req->r_uid));
+ head->caller_gid = cpu_to_le32(from_kgid(&init_user_ns, req->r_gid));
head->args = req->r_args;
ceph_encode_filepath(&p, end, ino1, path1);
mutex_lock(&req->r_fill_mutex);
err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
if (err == 0) {
- if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
+ if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
+ req->r_op == CEPH_MDS_OP_LSSNAP) &&
rinfo->dir_nr)
ceph_readdir_prepopulate(req, req->r_session);
ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
struct ceph_mds_reply_info_in *dir_in;
u8 dir_complete, dir_end;
};
+
+ /* for create results */
+ struct {
+ bool has_create_ino;
+ u64 ino;
+ };
};
/* encoded blob describing snapshot contexts for certain
union ceph_mds_request_args r_args;
int r_fmode; /* file mode, if expecting cap */
- uid_t r_uid;
- gid_t r_gid;
+ kuid_t r_uid;
+ kgid_t r_gid;
/* for choosing which mds to send this request to */
int r_direct_mode;
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
- #define CEPH_BLOCK_SHIFT 20 /* 1 MB */
+ #define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
struct ceph_snap_context *context;
umode_t mode;
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
struct ceph_buffer *xattr_blob;
u64 xattr_version;
/* file.c */
extern const struct file_operations ceph_file_fops;
extern const struct address_space_operations ceph_aops;
- extern int ceph_copy_to_page_vector(struct page **pages,
- const char *data,
- loff_t off, size_t len);
- extern int ceph_copy_from_page_vector(struct page **pages,
- char *data,
- loff_t off, size_t len);
- extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode,
#include <linux/slab.h>
#include <linux/statfs.h>
#include <linux/string.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
#include <linux/ceph/ceph_features.h>
#include "crypto.h"
+ /*
+ * Module compatibility interface. For now it doesn't do anything,
+ * but its existence signals a certain level of functionality.
+ *
+ * The data buffer is used to pass information both to and from
+ * libceph. The return value indicates whether libceph determines
+ * it is compatible with the caller (from another kernel module),
+ * given the provided data.
+ *
+ * The data pointer can be null.
+ */
+ bool libceph_compatible(void *data)
+ {
+ return true;
+ }
+ EXPORT_SYMBOL(libceph_compatible);
/*
* find filename portion of a path (/foo/bar/baz -> baz)
int err = -ENOMEM;
substring_t argstr[MAX_OPT_ARGS];
+ if (current->nsproxy->net_ns != &init_net)
+ return ERR_PTR(-EINVAL);
+
opt = kzalloc(sizeof(*opt), GFP_KERNEL);
if (!opt)
return ERR_PTR(-ENOMEM);
if (ret < 0)
goto out_crypto;
- pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n",
- CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL,
- CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
- CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+ pr_info("loaded (mon/osd proto %d/%d)\n",
+ CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL);
return 0;
projects / linux.git / commitdiff