is a pointer to a "struct inode_operations" which describes the methods that
can be performed on individual inodes.
+ struct xattr_handlers
+ ---------------------
+
+ On filesystems that support extended attributes (xattrs), the s_xattr
+ superblock field points to a NULL-terminated array of xattr handlers. Extended
+ attributes are name:value pairs.
+
+ name: Indicates that the handler matches attributes with the specified name
+ (such as "system.posix_acl_access"); the prefix field must be NULL.
+
+ prefix: Indicates that the handler matches all attributes with the specified
+ name prefix (such as "user."); the name field must be NULL.
+
+ list: Determine if attributes matching this xattr handler should be listed
+ for a particular dentry. Used by some listxattr implementations like
+ generic_listxattr.
+
+ get: Called by the VFS to get the value of a particular extended attribute.
+ This method is called by the getxattr(2) system call.
+
+ set: Called by the VFS to set the value of a particular extended attribute.
+ When the new value is NULL, called to remove a particular extended
+ attribute. This method is called by the the setxattr(2) and
+ removexattr(2) system calls.
+
+ When none of the xattr handlers of a filesystem match the specified attribute
+ name or when a filesystem doesn't support extended attributes, the various
+ *xattr(2) system calls return -EOPNOTSUPP.
+
The Inode Object
================
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
- int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
- ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
- int (*removexattr) (struct dentry *, const char *);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
unsigned open_flag, umode_t create_mode, int *opened);
getattr: called by the VFS to get attributes of a file. This method
is called by stat(2) and related system calls.
- setxattr: called by the VFS to set an extended attribute for a file.
- Extended attribute is a name:value pair associated with an
- inode. This method is called by setxattr(2) system call.
-
- getxattr: called by the VFS to retrieve the value of an extended
- attribute name. This method is called by getxattr(2) function
- call.
-
listxattr: called by the VFS to list all extended attributes for a
- given file. This method is called by listxattr(2) system call.
-
- removexattr: called by the VFS to remove an extended attribute from
- a file. This method is called by removexattr(2) system call.
+ given file. This method is called by the listxattr(2) system call.
update_time: called by the VFS to update a specific time or the i_version of
an inode. If this is not defined the VFS will update the inode itself
The second case is when a request has been made to invalidate
some or all pages in an address_space. This can happen
- through the fadvice(POSIX_FADV_DONTNEED) system call or by the
+ through the fadvise(POSIX_FADV_DONTNEED) system call or by the
filesystem explicitly requesting it as nfs and 9fs do (when
they believe the cache may be out of date with storage) by
calling invalidate_inode_pages2().
#define DEBUG_SUBSYSTEM S_LLITE
#include "../include/lustre_dlm.h"
-#include "../include/lustre_lite.h"
#include <linux/pagemap.h>
#include <linux/file.h>
+#include <linux/sched.h>
#include <linux/mount.h>
-#include "llite_internal.h"
#include "../include/lustre/ll_fiemap.h"
+#include "../include/lustre/lustre_ioctl.h"
#include "../include/cl_object.h"
+#include "llite_internal.h"
static int
ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg);
spin_unlock(&lli->lli_lock);
}
- if (rc == 0) {
- rc = ll_objects_destroy(req, inode);
- if (rc)
- CERROR("inode %lu ll_objects destroy: rc = %d\n",
- inode->i_ino, rc);
- }
if (rc == 0 && op_data->op_bias & MDS_HSM_RELEASE) {
struct mdt_body *body;
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (!(body->valid & OBD_MD_FLRELEASED))
+ if (!(body->mbo_valid & OBD_MD_FLRELEASED))
rc = -EBUSY;
}
fd = LUSTRE_FPRIVATE(file);
LASSERT(fd);
- /* The last ref on @file, maybe not be the owner pid of statahead.
- * Different processes can open the same dir, "ll_opendir_key" means:
- * it is me that should stop the statahead thread.
+ /* The last ref on @file, maybe not be the owner pid of statahead,
+ * because parent and child process can share the same file handle.
*/
- if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd &&
- lli->lli_opendir_pid != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
+ if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = NULL;
}
if (!S_ISDIR(inode->i_mode)) {
- lov_read_and_clear_async_rc(lli->lli_clob);
+ if (lli->lli_clob)
+ lov_read_and_clear_async_rc(lli->lli_clob);
lli->lli_async_rc = 0;
}
return rc;
}
-static int ll_intent_file_open(struct dentry *dentry, void *lmm,
- int lmmsize, struct lookup_intent *itp)
+static int ll_intent_file_open(struct dentry *de, void *lmm, int lmmsize,
+ struct lookup_intent *itp)
{
- struct inode *inode = d_inode(dentry);
+ struct inode *inode = d_inode(de);
struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct dentry *parent = dentry->d_parent;
- const char *name = dentry->d_name.name;
- const int len = dentry->d_name.len;
+ struct dentry *parent = de->d_parent;
+ const char *name = NULL;
struct md_op_data *op_data;
- struct ptlrpc_request *req;
- __u32 opc = LUSTRE_OPC_ANY;
- int rc;
+ struct ptlrpc_request *req = NULL;
+ int len = 0, rc;
- /* Usually we come here only for NFSD, and we want open lock. */
- /* We can also get here if there was cached open handle in revalidate_it
- * but it disappeared while we were getting from there to ll_file_open.
- * But this means this file was closed and immediately opened which
- * makes a good candidate for using OPEN lock
- */
- /* If lmmsize & lmm are not 0, we are just setting stripe info
- * parameters. No need for the open lock
+ LASSERT(parent);
+ LASSERT(itp->it_flags & MDS_OPEN_BY_FID);
+
+ /*
+ * if server supports open-by-fid, or file name is invalid, don't pack
+ * name in open request
*/
- if (!lmm && lmmsize == 0) {
- struct ll_dentry_data *ldd = ll_d2d(dentry);
- /*
- * If we came via ll_iget_for_nfs, then we need to request
- * struct ll_dentry_data *ldd = ll_d2d(file->f_dentry);
- *
- * NB: when ldd is NULL, it must have come via normal
- * lookup path only, since ll_iget_for_nfs always calls
- * ll_d_init().
- */
- if (ldd && ldd->lld_nfs_dentry) {
- ldd->lld_nfs_dentry = 0;
- itp->it_flags |= MDS_OPEN_LOCK;
- }
- if (itp->it_flags & FMODE_WRITE)
- opc = LUSTRE_OPC_CREATE;
+ if (!(exp_connect_flags(sbi->ll_md_exp) & OBD_CONNECT_OPEN_BY_FID) &&
+ lu_name_is_valid_2(de->d_name.name, de->d_name.len)) {
+ name = de->d_name.name;
+ len = de->d_name.len;
}
- op_data = ll_prep_md_op_data(NULL, d_inode(parent),
- inode, name, len,
- O_RDWR, opc, NULL);
+ op_data = ll_prep_md_op_data(NULL, d_inode(parent), inode, name, len,
+ O_RDWR, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
+ op_data->op_data = lmm;
+ op_data->op_data_size = lmmsize;
- itp->it_flags |= MDS_OPEN_BY_FID;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, lmm, lmmsize, itp,
- 0 /*unused */, &req, ll_md_blocking_ast, 0);
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, itp, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
if (rc == -ESTALE) {
/* reason for keep own exit path - don`t flood log
struct mdt_body *body;
body = req_capsule_server_get(&it->it_request->rq_pill, &RMF_MDT_BODY);
- och->och_fh = body->handle;
- och->och_fid = body->fid1;
+ och->och_fh = body->mbo_handle;
+ och->och_fid = body->mbo_fid1;
och->och_lease_handle.cookie = it->it_lock_handle;
och->och_magic = OBD_CLIENT_HANDLE_MAGIC;
och->och_flags = it->it_flags;
body = req_capsule_server_get(&it->it_request->rq_pill,
&RMF_MDT_BODY);
- ll_ioepoch_open(lli, body->ioepoch);
+ ll_ioepoch_open(lli, body->mbo_ioepoch);
}
LUSTRE_FPRIVATE(file) = fd;
struct obd_client_handle **och_p = NULL;
__u64 *och_usecount = NULL;
struct ll_file_data *fd;
- int rc = 0, opendir_set = 0;
+ int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), flags %o\n",
PFID(ll_inode2fid(inode)), inode, file->f_flags);
}
fd->fd_file = file;
- if (S_ISDIR(inode->i_mode)) {
- spin_lock(&lli->lli_sa_lock);
- if (!lli->lli_opendir_key && !lli->lli_sai &&
- lli->lli_opendir_pid == 0) {
- lli->lli_opendir_key = fd;
- lli->lli_opendir_pid = current_pid();
- opendir_set = 1;
- }
- spin_unlock(&lli->lli_sa_lock);
- }
+ if (S_ISDIR(inode->i_mode))
+ ll_authorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = fd;
} else if (it->it_flags & FMODE_EXEC) {
och_p = &lli->lli_mds_exec_och;
och_usecount = &lli->lli_open_fd_exec_count;
- } else {
+ } else {
och_p = &lli->lli_mds_read_och;
och_usecount = &lli->lli_open_fd_read_count;
}
* result in a deadlock
*/
mutex_unlock(&lli->lli_och_mutex);
- it->it_create_mode |= M_CHECK_STALE;
+ /*
+ * Normally called under two situations:
+ * 1. NFS export.
+ * 2. revalidate with IT_OPEN (revalidate doesn't
+ * execute this intent any more).
+ *
+ * Always fetch MDS_OPEN_LOCK if this is not setstripe.
+ *
+ * Always specify MDS_OPEN_BY_FID because we don't want
+ * to get file with different fid.
+ */
+ it->it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID;
rc = ll_intent_file_open(file->f_path.dentry, NULL, 0, it);
- it->it_create_mode &= ~M_CHECK_STALE;
if (rc)
goto out_openerr;
mutex_unlock(&lli->lli_och_mutex);
out_openerr:
- if (opendir_set != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
- ll_file_data_put(fd);
+ if (lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
+ if (fd)
+ ll_file_data_put(fd);
} else {
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_OPEN, 1);
}
struct lookup_intent it = { .it_op = IT_OPEN };
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct md_op_data *op_data;
- struct ptlrpc_request *req;
+ struct ptlrpc_request *req = NULL;
struct lustre_handle old_handle = { 0 };
struct obd_client_handle *och = NULL;
int rc;
it.it_flags = fmode | open_flags;
it.it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID | MDS_OPEN_LEASE;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, NULL, 0, &it, 0, &req,
- ll_md_blocking_lease_ast,
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, &it, &req,
+ &ll_md_blocking_lease_ast,
/* LDLM_FL_NO_LRU: To not put the lease lock into LRU list, otherwise
* it can be cancelled which may mislead applications that the lease is
* broken;
* open in ll_md_blocking_ast(). Otherwise as ll_md_blocking_lease_ast
* doesn't deal with openhandle, so normal openhandle will be leaked.
*/
- LDLM_FL_NO_LRU | LDLM_FL_EXCL);
+ LDLM_FL_NO_LRU | LDLM_FL_EXCL);
ll_finish_md_op_data(op_data);
ptlrpc_req_finished(req);
if (rc < 0)
{
struct ldlm_lock *lock;
bool cancelled = true;
- int rc;
lock = ldlm_handle2lock(&och->och_lease_handle);
if (lock) {
if (lease_broken)
*lease_broken = cancelled;
- rc = ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp, inode, och,
- NULL);
- return rc;
+ return ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp,
+ inode, och, NULL);
}
/* Fills the obdo with the attributes for the lsm */
{
struct ll_inode_info *lli = ll_i2info(file_inode(file));
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct range_lock range;
struct cl_io *io;
ssize_t result;
- CDEBUG(D_VFSTRACE, "file: %s, type: %d ppos: %llu, count: %zd\n",
- file->f_path.dentry->d_name.name, iot, *ppos, count);
+ CDEBUG(D_VFSTRACE, "file: %pD, type: %d ppos: %llu, count: %zu\n",
+ file, iot, *ppos, count);
restart:
io = vvp_env_thread_io(env);
if (cl_io_rw_init(env, io, iot, *ppos, count) == 0) {
struct vvp_io *vio = vvp_env_io(env);
- int write_mutex_locked = 0;
+ bool range_locked = false;
+
+ if (file->f_flags & O_APPEND)
+ range_lock_init(&range, 0, LUSTRE_EOF);
+ else
+ range_lock_init(&range, *ppos, *ppos + count - 1);
vio->vui_fd = LUSTRE_FPRIVATE(file);
- vio->vui_io_subtype = args->via_io_subtype;
-
- switch (vio->vui_io_subtype) {
- case IO_NORMAL:
- vio->vui_iter = args->u.normal.via_iter;
- vio->vui_iocb = args->u.normal.via_iocb;
- if ((iot == CIT_WRITE) &&
- !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
- if (mutex_lock_interruptible(&lli->
- lli_write_mutex)) {
- result = -ERESTARTSYS;
- goto out;
- }
- write_mutex_locked = 1;
- }
- down_read(&lli->lli_trunc_sem);
- break;
- case IO_SPLICE:
- vio->u.splice.vui_pipe = args->u.splice.via_pipe;
- vio->u.splice.vui_flags = args->u.splice.via_flags;
- break;
- default:
- CERROR("Unknown IO type - %u\n", vio->vui_io_subtype);
- LBUG();
+ vio->vui_iter = args->u.normal.via_iter;
+ vio->vui_iocb = args->u.normal.via_iocb;
+ /*
+ * Direct IO reads must also take range lock,
+ * or multiple reads will try to work on the same pages
+ * See LU-6227 for details.
+ */
+ if (((iot == CIT_WRITE) ||
+ (iot == CIT_READ && (file->f_flags & O_DIRECT))) &&
+ !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
+ CDEBUG(D_VFSTRACE, "Range lock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ result = range_lock(&lli->lli_write_tree,
+ &range);
+ if (result < 0)
+ goto out;
+
+ range_locked = true;
}
+ down_read(&lli->lli_trunc_sem);
ll_cl_add(file, env, io);
result = cl_io_loop(env, io);
ll_cl_remove(file, env);
- if (args->via_io_subtype == IO_NORMAL)
- up_read(&lli->lli_trunc_sem);
- if (write_mutex_locked)
- mutex_unlock(&lli->lli_write_mutex);
+ up_read(&lli->lli_trunc_sem);
+ if (range_locked) {
+ CDEBUG(D_VFSTRACE, "Range unlock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ range_unlock(&lli->lli_write_tree, &range);
+ }
} else {
/* cl_io_rw_init() handled IO */
result = io->ci_result;
* short read/write instead of restart io.
*/
if ((result == 0 || result == -ENODATA) && io->ci_need_restart) {
- CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zd\n",
+ CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zu\n",
iot == CIT_READ ? "read" : "write",
file, *ppos, count);
LASSERTF(io->ci_nob == 0, "%zd\n", io->ci_nob);
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = to;
args->u.normal.via_iocb = iocb;
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = from;
args->u.normal.via_iocb = iocb;
return result;
}
-/*
- * Send file content (through pagecache) somewhere with helper
- */
-static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t count,
- unsigned int flags)
-{
- struct lu_env *env;
- struct vvp_io_args *args;
- ssize_t result;
- int refcheck;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- return PTR_ERR(env);
-
- args = ll_env_args(env, IO_SPLICE);
- args->u.splice.via_pipe = pipe;
- args->u.splice.via_flags = flags;
-
- result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
- cl_env_put(env, &refcheck);
- return result;
-}
-
-static int ll_lov_recreate(struct inode *inode, struct ost_id *oi, u32 ost_idx)
-{
- struct obd_export *exp = ll_i2dtexp(inode);
- struct obd_trans_info oti = { 0 };
- struct obdo *oa = NULL;
- int lsm_size;
- int rc = 0;
- struct lov_stripe_md *lsm = NULL, *lsm2;
-
- oa = kmem_cache_zalloc(obdo_cachep, GFP_NOFS);
- if (!oa)
- return -ENOMEM;
-
- lsm = ccc_inode_lsm_get(inode);
- if (!lsm_has_objects(lsm)) {
- rc = -ENOENT;
- goto out;
- }
-
- lsm_size = sizeof(*lsm) + (sizeof(struct lov_oinfo) *
- (lsm->lsm_stripe_count));
-
- lsm2 = libcfs_kvzalloc(lsm_size, GFP_NOFS);
- if (!lsm2) {
- rc = -ENOMEM;
- goto out;
- }
-
- oa->o_oi = *oi;
- oa->o_nlink = ost_idx;
- oa->o_flags |= OBD_FL_RECREATE_OBJS;
- oa->o_valid = OBD_MD_FLID | OBD_MD_FLFLAGS | OBD_MD_FLGROUP;
- obdo_from_inode(oa, inode, OBD_MD_FLTYPE | OBD_MD_FLATIME |
- OBD_MD_FLMTIME | OBD_MD_FLCTIME);
- obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid);
- memcpy(lsm2, lsm, lsm_size);
- ll_inode_size_lock(inode);
- rc = obd_create(NULL, exp, oa, &lsm2, &oti);
- ll_inode_size_unlock(inode);
-
- kvfree(lsm2);
- goto out;
-out:
- ccc_inode_lsm_put(inode, lsm);
- kmem_cache_free(obdo_cachep, oa);
- return rc;
-}
-
-static int ll_lov_recreate_obj(struct inode *inode, unsigned long arg)
-{
- struct ll_recreate_obj ucreat;
- struct ost_id oi;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&ucreat, (struct ll_recreate_obj __user *)arg,
- sizeof(ucreat)))
- return -EFAULT;
-
- ostid_set_seq_mdt0(&oi);
- ostid_set_id(&oi, ucreat.lrc_id);
- return ll_lov_recreate(inode, &oi, ucreat.lrc_ost_idx);
-}
-
-static int ll_lov_recreate_fid(struct inode *inode, unsigned long arg)
-{
- struct lu_fid fid;
- struct ost_id oi;
- u32 ost_idx;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&fid, (struct lu_fid __user *)arg, sizeof(fid)))
- return -EFAULT;
-
- fid_to_ostid(&fid, &oi);
- ost_idx = (fid_seq(&fid) >> 16) & 0xffff;
- return ll_lov_recreate(inode, &oi, ost_idx);
-}
-
int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
__u64 flags, struct lov_user_md *lum,
int lum_size)
{
struct lov_stripe_md *lsm = NULL;
- struct lookup_intent oit = {.it_op = IT_OPEN, .it_flags = flags};
+ struct lookup_intent oit = {
+ .it_op = IT_OPEN,
+ .it_flags = flags | MDS_OPEN_BY_FID,
+ };
int rc = 0;
lsm = ccc_inode_lsm_get(inode);
ll_inode_size_lock(inode);
rc = ll_intent_file_open(dentry, lum, lum_size, &oit);
- if (rc)
+ if (rc < 0)
goto out_unlock;
rc = oit.it_status;
if (rc < 0)
- goto out_req_free;
+ goto out_unlock;
ll_release_openhandle(inode, &oit);
ccc_inode_lsm_put(inode, lsm);
out:
return rc;
-out_req_free:
- ptlrpc_req_finished((struct ptlrpc_request *)oit.it_request);
- goto out;
}
int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename,
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
- if (!(body->valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
+ if (!(body->mbo_valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
lmmsize == 0) {
rc = -ENODATA;
goto out;
*/
if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V1)) {
lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v1 *)lmm)->lmm_objects,
stripe_count);
} else if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V3)) {
lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v3 *)lmm)->lmm_objects,
stripe_count);
return rc;
}
+static int ll_file_getstripe(struct inode *inode,
+ struct lov_user_md __user *lum)
+{
+ struct lu_env *env;
+ int refcheck;
+ int rc;
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ return PTR_ERR(env);
+
+ rc = cl_object_getstripe(env, ll_i2info(inode)->lli_clob, lum);
+ cl_env_put(env, &refcheck);
+ return rc;
+}
+
static int ll_lov_setstripe(struct inode *inode, struct file *file,
unsigned long arg)
{
- struct lov_user_md_v3 lumv3;
- struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;
- struct lov_user_md_v1 __user *lumv1p = (void __user *)arg;
- struct lov_user_md_v3 __user *lumv3p = (void __user *)arg;
+ struct lov_user_md __user *lum = (struct lov_user_md __user *)arg;
+ struct lov_user_md *klum;
int lum_size, rc;
__u64 flags = FMODE_WRITE;
- /* first try with v1 which is smaller than v3 */
- lum_size = sizeof(struct lov_user_md_v1);
- if (copy_from_user(lumv1, lumv1p, lum_size))
- return -EFAULT;
-
- if (lumv1->lmm_magic == LOV_USER_MAGIC_V3) {
- lum_size = sizeof(struct lov_user_md_v3);
- if (copy_from_user(&lumv3, lumv3p, lum_size))
- return -EFAULT;
- }
+ rc = ll_copy_user_md(lum, &klum);
+ if (rc < 0)
+ return rc;
- rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lumv1,
+ lum_size = rc;
+ rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, klum,
lum_size);
cl_lov_delay_create_clear(&file->f_flags);
if (rc == 0) {
- struct lov_stripe_md *lsm;
__u32 gen;
- put_user(0, &lumv1p->lmm_stripe_count);
+ put_user(0, &lum->lmm_stripe_count);
ll_layout_refresh(inode, &gen);
- lsm = ccc_inode_lsm_get(inode);
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode),
- 0, lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ rc = ll_file_getstripe(inode, (struct lov_user_md __user *)arg);
}
- return rc;
-}
-static int ll_lov_getstripe(struct inode *inode, unsigned long arg)
-{
- struct lov_stripe_md *lsm;
- int rc = -ENODATA;
-
- lsm = ccc_inode_lsm_get(inode);
- if (lsm)
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode), 0,
- lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ kfree(klum);
return rc;
}
return rc;
}
+static inline long ll_lease_type_from_fmode(fmode_t fmode)
+{
+ return ((fmode & FMODE_READ) ? LL_LEASE_RDLCK : 0) |
+ ((fmode & FMODE_WRITE) ? LL_LEASE_WRLCK : 0);
+}
+
static long
ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
return rc;
}
case LL_IOC_LOV_GETSTRIPE:
- return ll_lov_getstripe(inode, arg);
- case LL_IOC_RECREATE_OBJ:
- return ll_lov_recreate_obj(inode, arg);
- case LL_IOC_RECREATE_FID:
- return ll_lov_recreate_fid(inode, arg);
+ return ll_file_getstripe(inode,
+ (struct lov_user_md __user *)arg);
case FSFILT_IOC_FIEMAP:
return ll_ioctl_fiemap(inode, arg);
case FSFILT_IOC_GETFLAGS:
return 0;
}
+ case LL_IOC_GETPARENT:
+ return ll_getparent(file, (struct getparent __user *)arg);
case OBD_IOC_FID2PATH:
return ll_fid2path(inode, (void __user *)arg);
case LL_IOC_DATA_VERSION: {
struct ll_inode_info *lli = ll_i2info(inode);
struct obd_client_handle *och = NULL;
bool lease_broken;
- fmode_t mode = 0;
+ fmode_t fmode;
switch (arg) {
- case F_WRLCK:
+ case LL_LEASE_WRLCK:
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
- mode = FMODE_WRITE;
+ fmode = FMODE_WRITE;
break;
- case F_RDLCK:
+ case LL_LEASE_RDLCK:
if (!(file->f_mode & FMODE_READ))
return -EPERM;
- mode = FMODE_READ;
+ fmode = FMODE_READ;
break;
- case F_UNLCK:
+ case LL_LEASE_UNLCK:
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
och = fd->fd_lease_och;
}
mutex_unlock(&lli->lli_och_mutex);
- if (och) {
- mode = och->och_flags &
- (FMODE_READ|FMODE_WRITE);
- rc = ll_lease_close(och, inode, &lease_broken);
- if (rc == 0 && lease_broken)
- mode = 0;
- } else {
- rc = -ENOLCK;
- }
+ if (!och)
+ return -ENOLCK;
+
+ fmode = och->och_flags;
+ rc = ll_lease_close(och, inode, &lease_broken);
+ if (rc < 0)
+ return rc;
+
+ if (lease_broken)
+ fmode = 0;
- /* return the type of lease or error */
- return rc < 0 ? rc : (int)mode;
+ return ll_lease_type_from_fmode(fmode);
default:
return -EINVAL;
}
- CDEBUG(D_INODE, "Set lease with mode %d\n", mode);
+ CDEBUG(D_INODE, "Set lease with mode %u\n", fmode);
/* apply for lease */
- och = ll_lease_open(inode, file, mode, 0);
+ och = ll_lease_open(inode, file, fmode, 0);
if (IS_ERR(och))
return PTR_ERR(och);
case LL_IOC_GET_LEASE: {
struct ll_inode_info *lli = ll_i2info(inode);
struct ldlm_lock *lock = NULL;
+ fmode_t fmode = 0;
- rc = 0;
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
struct obd_client_handle *och = fd->fd_lease_och;
if (lock) {
lock_res_and_lock(lock);
if (!ldlm_is_cancel(lock))
- rc = och->och_flags &
- (FMODE_READ | FMODE_WRITE);
+ fmode = och->och_flags;
unlock_res_and_lock(lock);
LDLM_LOCK_PUT(lock);
}
}
mutex_unlock(&lli->lli_och_mutex);
- return rc;
+ return ll_lease_type_from_fmode(fmode);
}
case LL_IOC_HSM_IMPORT: {
struct hsm_user_import *hui;
eof = i_size_read(inode);
}
- retval = generic_file_llseek_size(file, offset, origin,
- ll_file_maxbytes(inode), eof);
- return retval;
+ return generic_file_llseek_size(file, offset, origin,
+ ll_file_maxbytes(inode), eof);
}
static int ll_flush(struct file *file, fl_owner_t id)
*/
rc = lli->lli_async_rc;
lli->lli_async_rc = 0;
- err = lov_read_and_clear_async_rc(lli->lli_clob);
- if (rc == 0)
- rc = err;
+ if (lli->lli_clob) {
+ err = lov_read_and_clear_async_rc(lli->lli_clob);
+ if (!rc)
+ rc = err;
+ }
/* The application has been told about write failure already.
* Do not report failure again.
struct md_op_data *op_data;
struct lustre_handle lockh = {0};
ldlm_policy_data_t flock = { {0} };
+ int fl_type = file_lock->fl_type;
__u64 flags = 0;
int rc;
int rc2 = 0;
if (file_lock->fl_lmops && file_lock->fl_lmops->lm_compare_owner)
flock.l_flock.owner = (unsigned long)file_lock->fl_pid;
- switch (file_lock->fl_type) {
+ switch (fl_type) {
case F_RDLCK:
einfo.ei_mode = LCK_PR;
break;
einfo.ei_mode = LCK_PW;
break;
default:
- CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n",
- file_lock->fl_type);
+ CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n", fl_type);
return -ENOTSUPP;
}
case F_GETLK64:
#endif
flags = LDLM_FL_TEST_LOCK;
- /* Save the old mode so that if the mode in the lock changes we
- * can decrement the appropriate reader or writer refcount.
- */
- file_lock->fl_type = einfo.ei_mode;
break;
default:
CERROR("unknown fcntl lock command: %d\n", cmd);
return -EINVAL;
}
+ /*
+ * Save the old mode so that if the mode in the lock changes we
+ * can decrement the appropriate reader or writer refcount.
+ */
+ file_lock->fl_type = einfo.ei_mode;
+
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
PFID(ll_inode2fid(inode)), flock.l_flock.pid, flags,
einfo.ei_mode, flock.l_flock.start, flock.l_flock.end);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data, &lockh,
+ flags);
+
+ /* Restore the file lock type if not TEST lock. */
+ if (!(flags & LDLM_FL_TEST_LOCK))
+ file_lock->fl_type = fl_type;
if ((rc == 0 || file_lock->fl_type == F_UNLCK) &&
!(flags & LDLM_FL_TEST_LOCK))
if (rc2 && file_lock->fl_type != F_UNLCK) {
einfo.ei_mode = LCK_NL;
- md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data,
+ &lockh, flags);
rc = rc2;
}
return rc;
}
+int ll_get_fid_by_name(struct inode *parent, const char *name,
+ int namelen, struct lu_fid *fid)
+{
+ struct md_op_data *op_data = NULL;
+ struct ptlrpc_request *req;
+ struct mdt_body *body;
+ int rc;
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen, 0,
+ LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ op_data->op_valid = OBD_MD_FLID;
+ rc = md_getattr_name(ll_i2sbi(parent)->ll_md_exp, op_data, &req);
+ ll_finish_md_op_data(op_data);
+ if (rc < 0)
+ return rc;
+
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (!body) {
+ rc = -EFAULT;
+ goto out_req;
+ }
+ if (fid)
+ *fid = body->mbo_fid1;
+out_req:
+ ptlrpc_req_finished(req);
+ return rc;
+}
+
+int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
+ const char *name, int namelen)
+{
+ struct ptlrpc_request *request = NULL;
+ struct inode *child_inode = NULL;
+ struct dentry *dchild = NULL;
+ struct md_op_data *op_data;
+ struct qstr qstr;
+ int rc;
+
+ CDEBUG(D_VFSTRACE, "migrate %s under "DFID" to MDT%d\n",
+ name, PFID(ll_inode2fid(parent)), mdtidx);
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen,
+ 0, LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ /* Get child FID first */
+ qstr.hash = full_name_hash(parent, name, namelen);
+ qstr.name = name;
+ qstr.len = namelen;
+ dchild = d_lookup(file_dentry(file), &qstr);
+ if (dchild) {
+ op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
+ if (dchild->d_inode) {
+ child_inode = igrab(dchild->d_inode);
+ if (child_inode) {
+ inode_lock(child_inode);
+ op_data->op_fid3 = *ll_inode2fid(child_inode);
+ ll_invalidate_aliases(child_inode);
+ }
+ }
+ dput(dchild);
+ } else {
+ rc = ll_get_fid_by_name(parent, name, namelen,
+ &op_data->op_fid3);
+ if (rc)
+ goto out_free;
+ }
+
+ if (!fid_is_sane(&op_data->op_fid3)) {
+ CERROR("%s: migrate %s, but fid "DFID" is insane\n",
+ ll_get_fsname(parent->i_sb, NULL, 0), name,
+ PFID(&op_data->op_fid3));
+ rc = -EINVAL;
+ goto out_free;
+ }
+
+ rc = ll_get_mdt_idx_by_fid(ll_i2sbi(parent), &op_data->op_fid3);
+ if (rc < 0)
+ goto out_free;
+
+ if (rc == mdtidx) {
+ CDEBUG(D_INFO, "%s:"DFID" is already on MDT%d.\n", name,
+ PFID(&op_data->op_fid3), mdtidx);
+ rc = 0;
+ goto out_free;
+ }
+
+ op_data->op_mds = mdtidx;
+ op_data->op_cli_flags = CLI_MIGRATE;
+ rc = md_rename(ll_i2sbi(parent)->ll_md_exp, op_data, name,
+ namelen, name, namelen, &request);
+ if (!rc)
+ ll_update_times(request, parent);
+
+ ptlrpc_req_finished(request);
+
+out_free:
+ if (child_inode) {
+ clear_nlink(child_inode);
+ inode_unlock(child_inode);
+ iput(child_inode);
+ }
+
+ ll_finish_md_op_data(op_data);
+ return rc;
+}
+
static int
ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
{
struct lustre_handle lockh;
ldlm_policy_data_t policy;
enum ldlm_mode mode = (l_req_mode == LCK_MINMODE) ?
- (LCK_CR|LCK_CW|LCK_PR|LCK_PW) : l_req_mode;
+ (LCK_CR | LCK_CW | LCK_PR | LCK_PW) : l_req_mode;
struct lu_fid *fid;
__u64 flags;
int i;
{
ldlm_policy_data_t policy = { .l_inodebits = {bits} };
struct lu_fid *fid;
- enum ldlm_mode rc;
fid = &ll_i2info(inode)->lli_fid;
CDEBUG(D_INFO, "trying to match res "DFID"\n", PFID(fid));
- rc = md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
- fid, LDLM_IBITS, &policy, mode, lockh);
-
- return rc;
+ return md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
+ fid, LDLM_IBITS, &policy, mode, lockh);
}
static int ll_inode_revalidate_fini(struct inode *inode, int rc)
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- oit.it_create_mode |= M_CHECK_STALE;
- rc = md_intent_lock(exp, op_data, NULL, 0,
- /* we are not interested in name
- * based lookup
- */
- &oit, 0, &req,
- ll_md_blocking_ast, 0);
+ rc = md_intent_lock(exp, op_data, &oit, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
- oit.it_create_mode &= ~M_CHECK_STALE;
if (rc < 0) {
rc = ll_inode_revalidate_fini(inode, rc);
goto out;
op_data->op_valid = valid;
rc = md_getattr(sbi->ll_md_exp, op_data, &req);
ll_finish_md_op_data(op_data);
- if (rc) {
- rc = ll_inode_revalidate_fini(inode, rc);
- return rc;
- }
+ if (rc)
+ return ll_inode_revalidate_fini(inode, rc);
rc = ll_prep_inode(&inode, req, NULL, NULL);
}
return rc;
}
+static int ll_merge_md_attr(struct inode *inode)
+{
+ struct cl_attr attr = { 0 };
+ int rc;
+
+ LASSERT(ll_i2info(inode)->lli_lsm_md);
+ rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+ &attr, ll_md_blocking_ast);
+ if (rc)
+ return rc;
+
+ set_nlink(inode, attr.cat_nlink);
+ inode->i_blocks = attr.cat_blocks;
+ i_size_write(inode, attr.cat_size);
+
+ ll_i2info(inode)->lli_atime = attr.cat_atime;
+ ll_i2info(inode)->lli_mtime = attr.cat_mtime;
+ ll_i2info(inode)->lli_ctime = attr.cat_ctime;
+
+ return 0;
+}
+
static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
{
struct inode *inode = d_inode(dentry);
/* if object isn't regular file, don't validate size */
if (!S_ISREG(inode->i_mode)) {
+ if (S_ISDIR(inode->i_mode) &&
+ ll_i2info(inode)->lli_lsm_md) {
+ rc = ll_merge_md_attr(inode);
+ if (rc)
+ return rc;
+ }
+
LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime;
LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime;
LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime;
if (res)
return res;
+ OBD_FAIL_TIMEOUT(OBD_FAIL_GETATTR_DELAY, 30);
+
stat->dev = inode->i_sb->s_dev;
if (ll_need_32bit_api(sbi))
stat->ino = cl_fid_build_ino(&lli->lli_fid, 1);
else
stat->ino = inode->i_ino;
stat->mode = inode->i_mode;
- stat->nlink = inode->i_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->rdev = inode->i_rdev;
stat->ctime = inode->i_ctime;
stat->blksize = 1 << inode->i_blkbits;
+ stat->nlink = inode->i_nlink;
stat->size = i_size_read(inode);
stat->blocks = inode->i_blocks;
int ll_inode_permission(struct inode *inode, int mask)
{
+ struct ll_sb_info *sbi;
+ struct root_squash_info *squash;
+ const struct cred *old_cred = NULL;
+ struct cred *cred = NULL;
+ bool squash_id = false;
+ cfs_cap_t cap;
int rc = 0;
if (mask & MAY_NOT_BLOCK)
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), inode mode %x mask %o\n",
PFID(ll_inode2fid(inode)), inode, inode->i_mode, mask);
+ /* squash fsuid/fsgid if needed */
+ sbi = ll_i2sbi(inode);
+ squash = &sbi->ll_squash;
+ if (unlikely(squash->rsi_uid &&
+ uid_eq(current_fsuid(), GLOBAL_ROOT_UID) &&
+ !(sbi->ll_flags & LL_SBI_NOROOTSQUASH))) {
+ squash_id = true;
+ }
+
+ if (squash_id) {
+ CDEBUG(D_OTHER, "squash creds (%d:%d)=>(%d:%d)\n",
+ __kuid_val(current_fsuid()), __kgid_val(current_fsgid()),
+ squash->rsi_uid, squash->rsi_gid);
+
+ /*
+ * update current process's credentials
+ * and FS capability
+ */
+ cred = prepare_creds();
+ if (!cred)
+ return -ENOMEM;
+
+ cred->fsuid = make_kuid(&init_user_ns, squash->rsi_uid);
+ cred->fsgid = make_kgid(&init_user_ns, squash->rsi_gid);
+ for (cap = 0; cap < sizeof(cfs_cap_t) * 8; cap++) {
+ if ((1 << cap) & CFS_CAP_FS_MASK)
+ cap_lower(cred->cap_effective, cap);
+ }
+ old_cred = override_creds(cred);
+ }
+
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_INODE_PERM, 1);
rc = generic_permission(inode, mask);
+ /* restore current process's credentials and FS capability */
+ if (squash_id) {
+ revert_creds(old_cred);
+ put_cred(cred);
+ }
+
return rc;
}
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush
};
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = generic_removexattr,
.fiemap = ll_fiemap,
.get_acl = ll_get_acl,
};
if (!in_data)
return NULL;
- memset(in_data, 0, sizeof(*in_data));
in_data->iocd_size = size;
in_data->iocd_cb = cb;
in_data->iocd_count = count;
goto out;
}
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
if (lmmsize == 0) /* empty layout */ {
rc = 0;
goto out;
PFID(&lli->lli_fid), inode, reconf);
/* in case this is a caching lock and reinstate with new inode */
- md_set_lock_data(sbi->ll_md_exp, &lockh->cookie, inode, NULL);
+ md_set_lock_data(sbi->ll_md_exp, lockh, inode, NULL);
lock_res_and_lock(lock);
lvb_ready = ldlm_is_lvb_ready(lock);
struct ldlm_enqueue_info einfo = {
.ei_type = LDLM_IBITS,
.ei_mode = LCK_CR,
- .ei_cb_bl = ll_md_blocking_ast,
- .ei_cb_cp = ldlm_completion_ast,
+ .ei_cb_bl = &ll_md_blocking_ast,
+ .ei_cb_cp = &ldlm_completion_ast,
};
int rc;
ll_get_fsname(inode->i_sb, NULL, 0),
PFID(&lli->lli_fid), inode);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, &it, op_data, &lockh,
- NULL, 0, NULL, 0);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL, &it, op_data, &lockh, 0);
ptlrpc_req_finished(it.it_request);
it.it_request = NULL;
#include "../include/obd_support.h"
#include "../include/lustre_fid.h"
-#include "../include/lustre_lite.h"
#include "../include/lustre_dlm.h"
#include "../include/lustre_ver.h"
#include "llite_internal.h"
-static int ll_create_it(struct inode *, struct dentry *,
- int, struct lookup_intent *);
+static int ll_create_it(struct inode *dir, struct dentry *dentry,
+ struct lookup_intent *it);
/* called from iget5_locked->find_inode() under inode_hash_lock spinlock */
static int ll_test_inode(struct inode *inode, void *opaque)
struct ll_inode_info *lli = ll_i2info(inode);
struct lustre_md *md = opaque;
- if (unlikely(!(md->body->valid & OBD_MD_FLID))) {
+ if (unlikely(!(md->body->mbo_valid & OBD_MD_FLID))) {
CERROR("MDS body missing FID\n");
return 0;
}
- if (!lu_fid_eq(&lli->lli_fid, &md->body->fid1))
+ if (!lu_fid_eq(&lli->lli_fid, &md->body->mbo_fid1))
return 0;
return 1;
struct ll_inode_info *lli = ll_i2info(inode);
struct mdt_body *body = ((struct lustre_md *)opaque)->body;
- if (unlikely(!(body->valid & OBD_MD_FLID))) {
+ if (unlikely(!(body->mbo_valid & OBD_MD_FLID))) {
CERROR("MDS body missing FID\n");
return -EINVAL;
}
- lli->lli_fid = body->fid1;
- if (unlikely(!(body->valid & OBD_MD_FLTYPE))) {
+ lli->lli_fid = body->mbo_fid1;
+ if (unlikely(!(body->mbo_valid & OBD_MD_FLTYPE))) {
CERROR("Can not initialize inode " DFID
" without object type: valid = %#llx\n",
- PFID(&lli->lli_fid), body->valid);
+ PFID(&lli->lli_fid), body->mbo_valid);
return -EINVAL;
}
- inode->i_mode = (inode->i_mode & ~S_IFMT) | (body->mode & S_IFMT);
+ inode->i_mode = (inode->i_mode & ~S_IFMT) | (body->mbo_mode & S_IFMT);
if (unlikely(inode->i_mode == 0)) {
CERROR("Invalid inode "DFID" type\n", PFID(&lli->lli_fid));
return -EINVAL;
return 0;
}
-/*
- * Get an inode by inode number (already instantiated by the intent lookup).
- * Returns inode or NULL
+/**
+ * Get an inode by inode number(@hash), which is already instantiated by
+ * the intent lookup).
*/
struct inode *ll_iget(struct super_block *sb, ino_t hash,
struct lustre_md *md)
{
struct inode *inode;
+ int rc = 0;
LASSERT(hash != 0);
inode = iget5_locked(sb, hash, ll_test_inode, ll_set_inode, md);
-
- if (inode) {
- if (inode->i_state & I_NEW) {
- int rc = 0;
-
- ll_read_inode2(inode, md);
- if (S_ISREG(inode->i_mode) &&
- !ll_i2info(inode)->lli_clob) {
- CDEBUG(D_INODE,
- "%s: apply lsm %p to inode " DFID ".\n",
- ll_get_fsname(sb, NULL, 0), md->lsm,
- PFID(ll_inode2fid(inode)));
- rc = cl_file_inode_init(inode, md);
- }
- if (rc != 0) {
- iget_failed(inode);
- inode = NULL;
- } else {
- unlock_new_inode(inode);
- }
- } else if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
- ll_update_inode(inode, md);
- CDEBUG(D_VFSTRACE, "got inode: "DFID"(%p)\n",
- PFID(&md->body->fid1), inode);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+
+ if (inode->i_state & I_NEW) {
+ rc = ll_read_inode2(inode, md);
+ if (!rc && S_ISREG(inode->i_mode) &&
+ !ll_i2info(inode)->lli_clob) {
+ CDEBUG(D_INODE, "%s: apply lsm %p to inode "DFID"\n",
+ ll_get_fsname(sb, NULL, 0), md->lsm,
+ PFID(ll_inode2fid(inode)));
+ rc = cl_file_inode_init(inode, md);
+ }
+ if (rc) {
+ make_bad_inode(inode);
+ unlock_new_inode(inode);
+ iput(inode);
+ inode = ERR_PTR(rc);
+ } else {
+ unlock_new_inode(inode);
+ }
+ } else if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
+ rc = ll_update_inode(inode, md);
+ CDEBUG(D_VFSTRACE, "got inode: "DFID"(%p): rc = %d\n",
+ PFID(&md->body->mbo_fid1), inode, rc);
+ if (rc) {
+ iput(inode);
+ inode = ERR_PTR(rc);
}
}
return inode;
spin_unlock(&dir->i_lock);
}
+int ll_test_inode_by_fid(struct inode *inode, void *opaque)
+{
+ return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
+}
+
int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
void *data, int flag)
{
}
if (bits & MDS_INODELOCK_XATTR) {
+ if (S_ISDIR(inode->i_mode))
+ ll_i2info(inode)->lli_def_stripe_offset = -1;
ll_xattr_cache_destroy(inode);
bits &= ~MDS_INODELOCK_XATTR;
}
}
if ((bits & MDS_INODELOCK_UPDATE) && S_ISDIR(inode->i_mode)) {
- CDEBUG(D_INODE, "invalidating inode "DFID"\n",
- PFID(ll_inode2fid(inode)));
+ struct ll_inode_info *lli = ll_i2info(inode);
+
+ CDEBUG(D_INODE, "invalidating inode "DFID" lli = %p, pfid = "DFID"\n",
+ PFID(ll_inode2fid(inode)), lli,
+ PFID(&lli->lli_pfid));
+
truncate_inode_pages(inode->i_mapping, 0);
- ll_invalidate_negative_children(inode);
+
+ if (unlikely(!fid_is_zero(&lli->lli_pfid))) {
+ struct inode *master_inode = NULL;
+ unsigned long hash;
+
+ /*
+ * This is slave inode, since all of the child
+ * dentry is connected on the master inode, so
+ * we have to invalidate the negative children
+ * on master inode
+ */
+ CDEBUG(D_INODE, "Invalidate s"DFID" m"DFID"\n",
+ PFID(ll_inode2fid(inode)),
+ PFID(&lli->lli_pfid));
+
+ hash = cl_fid_build_ino(&lli->lli_pfid,
+ ll_need_32bit_api(ll_i2sbi(inode)));
+
+ master_inode = ilookup5(inode->i_sb, hash,
+ ll_test_inode_by_fid,
+ (void *)&lli->lli_pfid);
+ if (master_inode && !IS_ERR(master_inode)) {
+ ll_invalidate_negative_children(master_inode);
+ iput(master_inode);
+ }
+ } else {
+ ll_invalidate_negative_children(inode);
+ }
}
if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) &&
LASSERT(alias != dentry);
spin_lock(&alias->d_lock);
- if (alias->d_flags & DCACHE_DISCONNECTED)
+ if ((alias->d_flags & DCACHE_DISCONNECTED) &&
+ S_ISDIR(inode->i_mode))
/* LASSERT(last_discon == NULL); LU-405, bz 20055 */
discon_alias = alias;
else if (alias->d_parent == dentry->d_parent &&
struct lookup_intent parent_it = {
.it_op = IT_GETATTR,
.it_lock_handle = 0 };
+ struct lu_fid fid = ll_i2info(parent)->lli_fid;
+
+ /* If it is striped directory, get the real stripe parent */
+ if (unlikely(ll_i2info(parent)->lli_lsm_md)) {
+ rc = md_get_fid_from_lsm(ll_i2mdexp(parent),
+ ll_i2info(parent)->lli_lsm_md,
+ (*de)->d_name.name,
+ (*de)->d_name.len, &fid);
+ if (rc)
+ return rc;
+ }
- if (md_revalidate_lock(ll_i2mdexp(parent), &parent_it,
- &ll_i2info(parent)->lli_fid, NULL)) {
+ if (md_revalidate_lock(ll_i2mdexp(parent), &parent_it, &fid,
+ NULL)) {
d_lustre_revalidate(*de);
ll_intent_release(&parent_it);
}
}
static struct dentry *ll_lookup_it(struct inode *parent, struct dentry *dentry,
- struct lookup_intent *it, int lookup_flags)
+ struct lookup_intent *it)
{
struct lookup_intent lookup_it = { .it_op = IT_LOOKUP };
struct dentry *save = dentry, *retval;
struct ptlrpc_request *req = NULL;
+ struct md_op_data *op_data = NULL;
struct inode *inode;
- struct md_op_data *op_data;
__u32 opc;
int rc;
if (!it || it->it_op == IT_GETXATTR)
it = &lookup_it;
- if (it->it_op == IT_GETATTR) {
- rc = ll_statahead_enter(parent, &dentry, 0);
+ if (it->it_op == IT_GETATTR && dentry_may_statahead(parent, dentry)) {
+ rc = ll_statahead(parent, &dentry, 0);
if (rc == 1) {
if (dentry == save)
retval = NULL;
opc = LUSTRE_OPC_ANY;
op_data = ll_prep_md_op_data(NULL, parent, NULL, dentry->d_name.name,
- dentry->d_name.len, lookup_flags, opc,
- NULL);
+ dentry->d_name.len, 0, opc, NULL);
if (IS_ERR(op_data))
return (void *)op_data;
if (!IS_POSIXACL(parent) || !exp_connect_umask(ll_i2mdexp(parent)))
it->it_create_mode &= ~current_umask();
- rc = md_intent_lock(ll_i2mdexp(parent), op_data, NULL, 0, it,
- lookup_flags, &req, ll_md_blocking_ast, 0);
- ll_finish_md_op_data(op_data);
+ rc = md_intent_lock(ll_i2mdexp(parent), op_data, it, &req,
+ &ll_md_blocking_ast, 0);
+ /*
+ * If the MDS allows the client to chgrp (CFS_SETGRP_PERM), but the
+ * client does not know which suppgid should be sent to the MDS, or
+ * some other(s) changed the target file's GID after this RPC sent
+ * to the MDS with the suppgid as the original GID, then we should
+ * try again with right suppgid.
+ */
+ if (rc == -EACCES && it->it_op & IT_OPEN &&
+ it_disposition(it, DISP_OPEN_DENY)) {
+ struct mdt_body *body;
+
+ LASSERT(req);
+
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (op_data->op_suppgids[0] == body->mbo_gid ||
+ op_data->op_suppgids[1] == body->mbo_gid ||
+ !in_group_p(make_kgid(&init_user_ns, body->mbo_gid))) {
+ retval = ERR_PTR(-EACCES);
+ goto out;
+ }
+
+ fid_zero(&op_data->op_fid2);
+ op_data->op_suppgids[1] = body->mbo_gid;
+ ptlrpc_req_finished(req);
+ req = NULL;
+ ll_intent_release(it);
+ rc = md_intent_lock(ll_i2mdexp(parent), op_data, it, &req,
+ ll_md_blocking_ast, 0);
+ }
+
if (rc < 0) {
retval = ERR_PTR(rc);
goto out;
retval = NULL;
else
retval = dentry;
- out:
- if (req)
- ptlrpc_req_finished(req);
- if (it->it_op == IT_GETATTR && (!retval || retval == dentry))
- ll_statahead_mark(parent, dentry);
+out:
+ if (op_data && !IS_ERR(op_data))
+ ll_finish_md_op_data(op_data);
+
+ ptlrpc_req_finished(req);
return retval;
}
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir="DFID"(%p),flags=%u\n",
dentry, PFID(ll_inode2fid(parent)), parent, flags);
- /* Optimize away (CREATE && !OPEN). Let .create handle the race. */
- if ((flags & LOOKUP_CREATE) && !(flags & LOOKUP_OPEN))
+ /* Optimize away (CREATE && !OPEN). Let .create handle the race.
+ * but only if we have write permissions there, otherwise we need
+ * to proceed with lookup. LU-4185
+ */
+ if ((flags & LOOKUP_CREATE) && !(flags & LOOKUP_OPEN) &&
+ (inode_permission(parent, MAY_WRITE | MAY_EXEC) == 0))
return NULL;
- if (flags & (LOOKUP_PARENT|LOOKUP_OPEN|LOOKUP_CREATE))
+ if (flags & (LOOKUP_PARENT | LOOKUP_OPEN | LOOKUP_CREATE))
itp = NULL;
else
itp = ⁢
- de = ll_lookup_it(parent, dentry, itp, 0);
+ de = ll_lookup_it(parent, dentry, itp);
if (itp)
ll_intent_release(itp);
{
struct lookup_intent *it;
struct dentry *de;
- long long lookup_flags = LOOKUP_OPEN;
int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir="DFID"(%p),file %p,open_flags %x,mode %x opened %d\n",
return -ENOMEM;
it->it_op = IT_OPEN;
- if (open_flags & O_CREAT) {
+ if (open_flags & O_CREAT)
it->it_op |= IT_CREAT;
- lookup_flags |= LOOKUP_CREATE;
- }
it->it_create_mode = (mode & S_IALLUGO) | S_IFREG;
it->it_flags = (open_flags & ~O_ACCMODE) | OPEN_FMODE(open_flags);
+ it->it_flags &= ~MDS_OPEN_FL_INTERNAL;
/* Dentry added to dcache tree in ll_lookup_it */
- de = ll_lookup_it(dir, dentry, it, lookup_flags);
+ de = ll_lookup_it(dir, dentry, it);
if (IS_ERR(de))
rc = PTR_ERR(de);
else if (de)
if (!rc) {
if (it_disposition(it, DISP_OPEN_CREATE)) {
/* Dentry instantiated in ll_create_it. */
- rc = ll_create_it(dir, dentry, mode, it);
+ rc = ll_create_it(dir, dentry, it);
if (rc) {
/* We dget in ll_splice_alias. */
if (de)
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ll_create_it(struct inode *dir, struct dentry *dentry, int mode,
+static int ll_create_it(struct inode *dir, struct dentry *dentry,
struct lookup_intent *it)
{
struct inode *inode;
return 0;
}
-static void ll_update_times(struct ptlrpc_request *request,
- struct inode *inode)
+void ll_update_times(struct ptlrpc_request *request, struct inode *inode)
{
struct mdt_body *body = req_capsule_server_get(&request->rq_pill,
&RMF_MDT_BODY);
LASSERT(body);
- if (body->valid & OBD_MD_FLMTIME &&
- body->mtime > LTIME_S(inode->i_mtime)) {
+ if (body->mbo_valid & OBD_MD_FLMTIME &&
+ body->mbo_mtime > LTIME_S(inode->i_mtime)) {
CDEBUG(D_INODE, "setting fid "DFID" mtime from %lu to %llu\n",
PFID(ll_inode2fid(inode)), LTIME_S(inode->i_mtime),
- body->mtime);
- LTIME_S(inode->i_mtime) = body->mtime;
+ body->mbo_mtime);
+ LTIME_S(inode->i_mtime) = body->mbo_mtime;
}
- if (body->valid & OBD_MD_FLCTIME &&
- body->ctime > LTIME_S(inode->i_ctime))
- LTIME_S(inode->i_ctime) = body->ctime;
+ if (body->mbo_valid & OBD_MD_FLCTIME &&
+ body->mbo_ctime > LTIME_S(inode->i_ctime))
+ LTIME_S(inode->i_ctime) = body->mbo_ctime;
}
static int ll_new_node(struct inode *dir, struct dentry *dentry,
- const char *tgt, int mode, int rdev,
+ const char *tgt, umode_t mode, int rdev,
__u32 opc)
{
struct ptlrpc_request *request = NULL;
if (unlikely(tgt))
tgt_len = strlen(tgt) + 1;
-
+again:
op_data = ll_prep_md_op_data(NULL, dir, NULL,
dentry->d_name.name,
dentry->d_name.len,
from_kgid(&init_user_ns, current_fsgid()),
cfs_curproc_cap_pack(), rdev, &request);
ll_finish_md_op_data(op_data);
- if (err)
+ if (err < 0 && err != -EREMOTE)
goto err_exit;
+ /*
+ * If the client doesn't know where to create a subdirectory (or
+ * in case of a race that sends the RPC to the wrong MDS), the
+ * MDS will return -EREMOTE and the client will fetch the layout
+ * of the directory, then create the directory on the right MDT.
+ */
+ if (unlikely(err == -EREMOTE)) {
+ struct ll_inode_info *lli = ll_i2info(dir);
+ struct lmv_user_md *lum;
+ int lumsize, err2;
+
+ ptlrpc_req_finished(request);
+ request = NULL;
+
+ err2 = ll_dir_getstripe(dir, (void **)&lum, &lumsize, &request,
+ OBD_MD_DEFAULT_MEA);
+ if (!err2) {
+ /* Update stripe_offset and retry */
+ lli->lli_def_stripe_offset = lum->lum_stripe_offset;
+ } else if (err2 == -ENODATA &&
+ lli->lli_def_stripe_offset != -1) {
+ /*
+ * If there are no default stripe EA on the MDT, but the
+ * client has default stripe, then it probably means
+ * default stripe EA has just been deleted.
+ */
+ lli->lli_def_stripe_offset = -1;
+ } else {
+ goto err_exit;
+ }
+
+ ptlrpc_req_finished(request);
+ request = NULL;
+ goto again;
+ }
+
ll_update_times(request, dir);
err = ll_prep_inode(&inode, request, dir->i_sb, NULL);
d_instantiate(dentry, inode);
err_exit:
- ptlrpc_req_finished(request);
+ if (request)
+ ptlrpc_req_finished(request);
return err;
}
return rc;
}
-int ll_objects_destroy(struct ptlrpc_request *request, struct inode *dir)
-{
- struct mdt_body *body;
- struct lov_mds_md *eadata;
- struct lov_stripe_md *lsm = NULL;
- struct obd_trans_info oti = { 0 };
- struct obdo *oa;
- int rc;
-
- /* req is swabbed so this is safe */
- body = req_capsule_server_get(&request->rq_pill, &RMF_MDT_BODY);
- if (!(body->valid & OBD_MD_FLEASIZE))
- return 0;
-
- if (body->eadatasize == 0) {
- CERROR("OBD_MD_FLEASIZE set but eadatasize zero\n");
- rc = -EPROTO;
- goto out;
- }
-
- /* The MDS sent back the EA because we unlinked the last reference
- * to this file. Use this EA to unlink the objects on the OST.
- * It's opaque so we don't swab here; we leave it to obd_unpackmd() to
- * check it is complete and sensible.
- */
- eadata = req_capsule_server_sized_get(&request->rq_pill, &RMF_MDT_MD,
- body->eadatasize);
- LASSERT(eadata);
-
- rc = obd_unpackmd(ll_i2dtexp(dir), &lsm, eadata, body->eadatasize);
- if (rc < 0) {
- CERROR("obd_unpackmd: %d\n", rc);
- goto out;
- }
- LASSERT(rc >= sizeof(*lsm));
-
- oa = kmem_cache_zalloc(obdo_cachep, GFP_NOFS);
- if (!oa) {
- rc = -ENOMEM;
- goto out_free_memmd;
- }
-
- oa->o_oi = lsm->lsm_oi;
- oa->o_mode = body->mode & S_IFMT;
- oa->o_valid = OBD_MD_FLID | OBD_MD_FLTYPE | OBD_MD_FLGROUP;
-
- if (body->valid & OBD_MD_FLCOOKIE) {
- oa->o_valid |= OBD_MD_FLCOOKIE;
- oti.oti_logcookies =
- req_capsule_server_sized_get(&request->rq_pill,
- &RMF_LOGCOOKIES,
- sizeof(struct llog_cookie) *
- lsm->lsm_stripe_count);
- if (!oti.oti_logcookies) {
- oa->o_valid &= ~OBD_MD_FLCOOKIE;
- body->valid &= ~OBD_MD_FLCOOKIE;
- }
- }
-
- rc = obd_destroy(NULL, ll_i2dtexp(dir), oa, lsm, &oti,
- ll_i2mdexp(dir));
- if (rc)
- CERROR("obd destroy objid "DOSTID" error %d\n",
- POSTID(&lsm->lsm_oi), rc);
-out_free_memmd:
- obd_free_memmd(ll_i2dtexp(dir), &lsm);
- kmem_cache_free(obdo_cachep, oa);
-out:
- return rc;
-}
-
/* ll_unlink() doesn't update the inode with the new link count.
* Instead, ll_ddelete() and ll_d_iput() will update it based upon if there
* is any lock existing. They will recycle dentries and inodes based upon locks
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- if (dchild && dchild->d_inode)
+ if (dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
op_data->op_fid2 = op_data->op_fid3;
ll_update_times(request, dir);
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_UNLINK, 1);
- rc = ll_objects_destroy(request, dir);
out:
ptlrpc_req_finished(request);
return rc;
if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir)))
mode &= ~current_umask();
- mode = (mode & (S_IRWXUGO|S_ISVTX)) | S_IFDIR;
- err = ll_new_node(dir, dentry, NULL, mode, 0, LUSTRE_OPC_MKDIR);
+ mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
+ err = ll_new_node(dir, dentry, NULL, mode, 0, LUSTRE_OPC_MKDIR);
if (!err)
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_MKDIR, 1);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- if (dchild && dchild->d_inode)
+ if (dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
op_data->op_fid2 = op_data->op_fid3;
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- if (src_dchild && src_dchild->d_inode)
+ if (src_dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(src_dchild->d_inode);
- if (tgt_dchild && tgt_dchild->d_inode)
+ if (tgt_dchild->d_inode)
op_data->op_fid4 = *ll_inode2fid(tgt_dchild->d_inode);
err = md_rename(sbi->ll_md_exp, op_data,
ll_update_times(request, src);
ll_update_times(request, tgt);
ll_stats_ops_tally(sbi, LPROC_LL_RENAME, 1);
- err = ll_objects_destroy(request, src);
}
ptlrpc_req_finished(request);
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ll_get_acl,
};
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ll_get_acl,
};
#include <linux/stat.h>
#define DEBUG_SUBSYSTEM S_LLITE
-#include "../include/lustre_lite.h"
#include "llite_internal.h"
static int ll_readlink_internal(struct inode *inode,
}
body = req_capsule_server_get(&(*request)->rq_pill, &RMF_MDT_BODY);
- if ((body->valid & OBD_MD_LINKNAME) == 0) {
+ if ((body->mbo_valid & OBD_MD_LINKNAME) == 0) {
CERROR("OBD_MD_LINKNAME not set on reply\n");
rc = -EPROTO;
goto failed;
}
LASSERT(symlen != 0);
- if (body->eadatasize != symlen) {
+ if (body->mbo_eadatasize != symlen) {
CERROR("%s: inode "DFID": symlink length %d not expected %d\n",
ll_get_fsname(inode->i_sb, NULL, 0),
- PFID(ll_inode2fid(inode)), body->eadatasize - 1,
+ PFID(ll_inode2fid(inode)), body->mbo_eadatasize - 1,
symlen - 1);
rc = -EPROTO;
goto failed;
.get_link = ll_get_link,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = generic_removexattr,
};
p9_debug(P9_DEBUG_VFS, "\n");
- retval = inode_change_ok(inode, iattr);
+ retval = setattr_prepare(dentry, iattr);
if (retval)
return retval;
.rename = v9fs_vfs_rename,
.getattr = v9fs_vfs_getattr_dotl,
.setattr = v9fs_vfs_setattr_dotl,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = v9fs_listxattr,
.get_acl = v9fs_iop_get_acl,
};
const struct inode_operations v9fs_file_inode_operations_dotl = {
.getattr = v9fs_vfs_getattr_dotl,
.setattr = v9fs_vfs_setattr_dotl,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = v9fs_listxattr,
.get_acl = v9fs_iop_get_acl,
};
.get_link = v9fs_vfs_get_link_dotl,
.getattr = v9fs_vfs_getattr_dotl,
.setattr = v9fs_vfs_setattr_dotl,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = v9fs_listxattr,
};
if (btrfs_root_readonly(root))
return -EROFS;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
if (!bio)
return -ENOMEM;
- bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf);
+ bio_set_op_attrs(bio, bio_op(orig_bio), bio_flags(orig_bio));
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
start_sector, GFP_NOFS);
if (!bio)
goto out_err;
- bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf);
+ bio_set_op_attrs(bio, bio_op(orig_bio),
+ bio_flags(orig_bio));
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
goto out;
/* If this is a write we don't need to check anymore */
- if (iov_iter_rw(iter) == WRITE)
+ if (iov_iter_rw(iter) != READ || !iter_is_iovec(iter))
return 0;
/*
* Check to make sure we don't have duplicate iov_base's in this
}
-/* Inspired by filemap_check_errors() */
-int btrfs_inode_check_errors(struct inode *inode)
-{
- int ret = 0;
-
- if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags))
- ret = -ENOSPC;
- if (test_bit(AS_EIO, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_EIO, &inode->i_mapping->flags))
- ret = -EIO;
-
- return ret;
-}
-
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
.symlink = btrfs_symlink,
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = generic_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
static const struct inode_operations btrfs_file_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = generic_removexattr,
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = generic_removexattr,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = generic_removexattr,
.update_time = btrfs_update_time,
};
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/slab.h>
+ #include <linux/xattr.h>
#include "internal.h"
#define CACHEFILES_KEYBUF_SIZE 512
* Mark an object as being inactive.
*/
void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
- struct cachefiles_object *object)
+ struct cachefiles_object *object,
+ blkcnt_t i_blocks)
{
- blkcnt_t i_blocks = d_backing_inode(object->dentry)->i_blocks;
-
write_lock(&cache->active_lock);
rb_erase(&object->active_node, &cache->active_nodes);
clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
check_error:
_debug("check error %d", ret);
- cachefiles_mark_object_inactive(cache, object);
+ cachefiles_mark_object_inactive(
+ cache, object, d_backing_inode(object->dentry)->i_blocks);
release_dentry:
dput(object->dentry);
object->dentry = NULL;
}
ret = -EPERM;
- if (!d_backing_inode(subdir)->i_op->setxattr ||
- !d_backing_inode(subdir)->i_op->getxattr ||
+ if (!(d_backing_inode(subdir)->i_opflags & IOP_XATTR) ||
!d_backing_inode(subdir)->i_op->lookup ||
!d_backing_inode(subdir)->i_op->mkdir ||
!d_backing_inode(subdir)->i_op->create ||
.permission = ceph_permission,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ceph_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ceph_get_acl,
.set_acl = ceph_set_acl,
};
.get_link = simple_get_link,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ceph_listxattr,
- .removexattr = generic_removexattr,
};
int __ceph_setattr(struct inode *inode, struct iattr *attr)
int inode_dirty_flags = 0;
bool lock_snap_rwsem = false;
- if (ceph_snap(inode) != CEPH_NOSNAP)
- return -EROFS;
-
- err = inode_change_ok(inode, attr);
- if (err != 0)
- return err;
-
prealloc_cf = ceph_alloc_cap_flush();
if (!prealloc_cf)
return -ENOMEM;
*/
int ceph_setattr(struct dentry *dentry, struct iattr *attr)
{
- return __ceph_setattr(d_inode(dentry), attr);
+ struct inode *inode = d_inode(dentry);
+ int err;
+
+ if (ceph_snap(inode) != CEPH_NOSNAP)
+ return -EROFS;
+
+ err = setattr_prepare(dentry, attr);
+ if (err != 0)
+ return err;
+
+ return __ceph_setattr(inode, attr);
}
/*
}
mutex_unlock(&crypt_stat->cs_mutex);
- rc = inode_change_ok(inode, ia);
+ rc = setattr_prepare(dentry, ia);
if (rc)
goto out;
if (ia->ia_valid & ATTR_SIZE) {
const char *name, const void *value,
size_t size, int flags)
{
- int rc = 0;
+ int rc;
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!d_inode(lower_dentry)->i_op->setxattr) {
+ if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
-
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
if (!rc && inode)
fsstack_copy_attr_all(inode, d_inode(lower_dentry));
ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
const char *name, void *value, size_t size)
{
- int rc = 0;
+ int rc;
- if (!lower_inode->i_op->getxattr) {
+ if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
inode_lock(lower_inode);
- rc = lower_inode->i_op->getxattr(lower_dentry, lower_inode,
- name, value, size);
+ rc = __vfs_getxattr(lower_dentry, lower_inode, name, value, size);
inode_unlock(lower_inode);
out:
return rc;
return rc;
}
- static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
+ static int ecryptfs_removexattr(struct dentry *dentry, struct inode *inode,
+ const char *name)
{
- int rc = 0;
+ int rc;
struct dentry *lower_dentry;
+ struct inode *lower_inode;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!d_inode(lower_dentry)->i_op->removexattr) {
+ lower_inode = ecryptfs_inode_to_lower(inode);
+ if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
- inode_lock(d_inode(lower_dentry));
- rc = d_inode(lower_dentry)->i_op->removexattr(lower_dentry, name);
- inode_unlock(d_inode(lower_dentry));
+ inode_lock(lower_inode);
+ rc = __vfs_removexattr(lower_dentry, name);
+ inode_unlock(lower_inode);
out:
return rc;
}
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.getattr = ecryptfs_getattr_link,
- .setxattr = ecryptfs_setxattr,
- .getxattr = ecryptfs_getxattr,
.listxattr = ecryptfs_listxattr,
- .removexattr = ecryptfs_removexattr
};
const struct inode_operations ecryptfs_dir_iops = {
.rename = ecryptfs_rename,
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
- .setxattr = ecryptfs_setxattr,
- .getxattr = ecryptfs_getxattr,
.listxattr = ecryptfs_listxattr,
- .removexattr = ecryptfs_removexattr
};
const struct inode_operations ecryptfs_main_iops = {
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.getattr = ecryptfs_getattr,
- .setxattr = ecryptfs_setxattr,
- .getxattr = ecryptfs_getxattr,
.listxattr = ecryptfs_listxattr,
- .removexattr = ecryptfs_removexattr
+ };
+
+ static int ecryptfs_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+ {
+ return ecryptfs_getxattr(dentry, inode, name, buffer, size);
+ }
+
+ static int ecryptfs_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size,
+ int flags)
+ {
+ if (value)
+ return ecryptfs_setxattr(dentry, inode, name, value, size, flags);
+ else {
+ BUG_ON(flags != XATTR_REPLACE);
+ return ecryptfs_removexattr(dentry, inode, name);
+ }
+ }
+
+ const struct xattr_handler ecryptfs_xattr_handler = {
+ .prefix = "", /* match anything */
+ .get = ecryptfs_xattr_get,
+ .set = ecryptfs_xattr_set,
+ };
+
+ const struct xattr_handler *ecryptfs_xattr_handlers[] = {
+ &ecryptfs_xattr_handler,
+ NULL
};
#include <linux/pagemap.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
+#include <linux/iomap.h>
+#include <linux/uio.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
#ifdef CONFIG_FS_DAX
+static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ ssize_t ret;
+
+ if (!iov_iter_count(to))
+ return 0; /* skip atime */
+
+ inode_lock_shared(inode);
+ ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops);
+ inode_unlock_shared(inode);
+
+ file_accessed(iocb->ki_filp);
+ return ret;
+}
+
+static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
+
+ inode_lock(inode);
+ ret = generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out_unlock;
+ ret = file_remove_privs(file);
+ if (ret)
+ goto out_unlock;
+ ret = file_update_time(file);
+ if (ret)
+ goto out_unlock;
+
+ ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops);
+ if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
+ i_size_write(inode, iocb->ki_pos);
+ mark_inode_dirty(inode);
+ }
+
+out_unlock:
+ inode_unlock(inode);
+ if (ret > 0)
+ ret = generic_write_sync(iocb, ret);
+ return ret;
+}
+
/*
* The lock ordering for ext2 DAX fault paths is:
*
}
down_read(&ei->dax_sem);
- ret = dax_fault(vma, vmf, ext2_get_block);
+ ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
return ret;
}
-/*
- * We have mostly NULL's here: the current defaults are ok for
- * the ext2 filesystem.
- */
+static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+#ifdef CONFIG_FS_DAX
+ if (IS_DAX(iocb->ki_filp->f_mapping->host))
+ return ext2_dax_read_iter(iocb, to);
+#endif
+ return generic_file_read_iter(iocb, to);
+}
+
+static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+#ifdef CONFIG_FS_DAX
+ if (IS_DAX(iocb->ki_filp->f_mapping->host))
+ return ext2_dax_write_iter(iocb, from);
+#endif
+ return generic_file_write_iter(iocb, from);
+}
+
const struct file_operations ext2_file_operations = {
.llseek = generic_file_llseek,
- .read_iter = generic_file_read_iter,
- .write_iter = generic_file_write_iter,
+ .read_iter = ext2_file_read_iter,
+ .write_iter = ext2_file_write_iter,
.unlocked_ioctl = ext2_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
.open = dquot_file_open,
.release = ext2_release_file,
.fsync = ext2_fsync,
+ .get_unmapped_area = thp_get_unmapped_area,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
};
const struct inode_operations ext2_file_inode_operations = {
#ifdef CONFIG_EXT2_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext2_listxattr,
- .removexattr = generic_removexattr,
#endif
.setattr = ext2_setattr,
.get_acl = ext2_get_acl,
static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(iocb->ki_filp);
- struct blk_plug plug;
int o_direct = iocb->ki_flags & IOCB_DIRECT;
int unaligned_aio = 0;
int overwrite = 0;
if (o_direct) {
size_t length = iov_iter_count(from);
loff_t pos = iocb->ki_pos;
- blk_start_plug(&plug);
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
- !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ pos + length <= i_size_read(inode)) {
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
int err, len;
map.m_lblk = pos >> blkbits;
- map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- - map.m_lblk;
+ map.m_len = EXT4_MAX_BLOCKS(length, pos, blkbits);
len = map.m_len;
err = ext4_map_blocks(NULL, inode, &map, 0);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
- if (o_direct)
- blk_finish_plug(&plug);
return ret;
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
+ .get_unmapped_area = thp_get_unmapped_area,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ext4_fallocate,
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
res = fscrypt_fname_alloc_buffer(
dir, len,
&fname_crypto_str);
- if (res < 0)
+ if (res)
printk(KERN_WARNING "Error "
"allocating crypto "
"buffer--skipping "
res = fscrypt_fname_disk_to_usr(dir,
0, 0, &de_name,
&fname_crypto_str);
- if (res < 0) {
+ if (res) {
printk(KERN_WARNING "Error "
"converting filename "
"from disk to usr"
err = fscrypt_fname_disk_to_usr(dir, hinfo->hash,
hinfo->minor_hash, &de_name,
&fname_crypto_str);
- if (err < 0) {
+ if (err) {
count = err;
goto errout;
}
frame->entries = entries;
frame->at = entries;
frame->bh = bh;
- bh = bh2;
retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
if (retval)
goto out_frames;
- retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+ retval = ext4_handle_dirty_dirent_node(handle, dir, bh2);
if (retval)
goto out_frames;
- de = do_split(handle,dir, &bh, frame, &fname->hinfo);
+ de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
if (IS_ERR(de)) {
retval = PTR_ERR(de);
goto out_frames;
}
- dx_release(frames);
- retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
- brelse(bh);
- return retval;
+ retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2);
out_frames:
/*
* Even if the block split failed, we have to properly write
* out all the changes we did so far. Otherwise we can end up
* with corrupted filesystem.
*/
- ext4_mark_inode_dirty(handle, dir);
+ if (retval)
+ ext4_mark_inode_dirty(handle, dir);
dx_release(frames);
+ brelse(bh2);
return retval;
}
istr.name = (const unsigned char *) symname;
istr.len = len;
err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
- if (err < 0)
+ if (err)
goto err_drop_inode;
sd->len = cpu_to_le16(ostr.len);
disk_link.name = (char *) sd;
.tmpfile = ext4_tmpfile,
.rename2 = ext4_rename2,
.setattr = ext4_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
};
char *caddr, *paddr = NULL;
struct fscrypt_str cstr, pstr;
struct fscrypt_symlink_data *sd;
- loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
int res;
u32 max_size = inode->i_sb->s_blocksize;
if (IS_ERR(cpage))
return ERR_CAST(cpage);
caddr = page_address(cpage);
- caddr[size] = 0;
}
/* Symlink is encrypted */
res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
if (res)
goto errout;
+ paddr = pstr.name;
res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
- if (res < 0)
+ if (res)
goto errout;
- paddr = pstr.name;
-
/* Null-terminate the name */
- if (res <= pstr.len)
- paddr[res] = '\0';
+ paddr[pstr.len] = '\0';
if (cpage)
put_page(cpage);
set_delayed_call(done, kfree_link, paddr);
.readlink = generic_readlink,
.get_link = ext4_encrypted_get_link,
.setattr = ext4_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
};
const struct inode_operations ext4_symlink_inode_operations = {
.readlink = generic_readlink,
.get_link = page_get_link,
.setattr = ext4_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
};
const struct inode_operations ext4_fast_symlink_inode_operations = {
.readlink = generic_readlink,
.get_link = simple_get_link,
.setattr = ext4_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ext4_listxattr,
- .removexattr = generic_removexattr,
};
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
- else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino))
+ else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
need_cp = true;
else if (file_wrong_pino(inode))
need_cp = true;
return 0;
if (cache_only) {
- page = f2fs_grab_cache_page(mapping, index, false);
+ page = find_lock_page(mapping, index);
if (page && PageUptodate(page))
goto truncate_out;
f2fs_put_page(page, 1);
struct inode *inode = d_inode(dentry);
int err;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
#ifdef CONFIG_F2FS_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
- .removexattr = generic_removexattr,
#endif
.fiemap = f2fs_fiemap,
};
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int flags;
unsigned int oldflags;
int ret;
* avoid defragment running in SSR mode when free section are allocated
* intensively
*/
- if (has_not_enough_free_secs(sbi, sec_num)) {
+ if (has_not_enough_free_secs(sbi, 0, sec_num)) {
err = -EAGAIN;
goto out;
}
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
+ if (src == dst) {
+ if (pos_in == pos_out)
+ return 0;
+ if (pos_out > pos_in && pos_out < pos_in + len)
+ return -EINVAL;
+ }
+
inode_lock(src);
if (src != dst) {
if (!inode_trylock(dst)) {
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
- ret = __exchange_data_block(src, dst, pos_in,
- pos_out, len >> F2FS_BLKSIZE_BITS, false);
+ ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
+ pos_out >> F2FS_BLKSIZE_BITS,
+ len >> F2FS_BLKSIZE_BITS, false);
if (!ret) {
if (dst_max_i_size)
{
size_t slen = strlen(s);
size_t sublen = strlen(sub);
+ int i;
/*
* filename format of multimedia file should be defined as:
- * "filename + '.' + extension".
+ * "filename + '.' + extension + (optional: '.' + temp extension)".
*/
if (slen < sublen + 2)
return 0;
- if (s[slen - sublen - 1] != '.')
- return 0;
+ for (i = 1; i < slen - sublen; i++) {
+ if (s[i] != '.')
+ continue;
+ if (!strncasecmp(s + i + 1, sub, sublen))
+ return 1;
+ }
- return !strncasecmp(s + slen - sublen, sub, sublen);
+ return 0;
}
/*
ostr.name = sd->encrypted_path;
ostr.len = disk_link.len;
err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
- if (err < 0)
+ if (err)
goto err_out;
sd->len = cpu_to_le16(ostr.len);
struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
struct fscrypt_symlink_data *sd;
- loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
u32 max_size = inode->i_sb->s_blocksize;
int res;
if (IS_ERR(cpage))
return ERR_CAST(cpage);
caddr = page_address(cpage);
- caddr[size] = 0;
/* Symlink is encrypted */
sd = (struct fscrypt_symlink_data *)caddr;
goto errout;
res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
- if (res < 0)
+ if (res)
goto errout;
/* this is broken symlink case */
paddr = pstr.name;
/* Null-terminate the name */
- paddr[res] = '\0';
+ paddr[pstr.len] = '\0';
put_page(cpage);
set_delayed_call(done, kfree_link, paddr);
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
- .removexattr = generic_removexattr,
#endif
};
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
#ifdef CONFIG_F2FS_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
- .removexattr = generic_removexattr,
#endif
};
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
- .removexattr = generic_removexattr,
#endif
};
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
#ifdef CONFIG_F2FS_FS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = f2fs_listxattr,
- .removexattr = generic_removexattr,
#endif
};
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/posix_acl.h>
static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx)
{
set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
}
-#if BITS_PER_LONG >= 64
+union fuse_dentry {
+ u64 time;
+ struct rcu_head rcu;
+};
+
static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
{
- entry->d_time = time;
+ ((union fuse_dentry *) entry->d_fsdata)->time = time;
}
static inline u64 fuse_dentry_time(struct dentry *entry)
{
- return entry->d_time;
-}
-#else
-/*
- * On 32 bit archs store the high 32 bits of time in d_fsdata
- */
-static void fuse_dentry_settime(struct dentry *entry, u64 time)
-{
- entry->d_time = time;
- entry->d_fsdata = (void *) (unsigned long) (time >> 32);
-}
-
-static u64 fuse_dentry_time(struct dentry *entry)
-{
- return (u64) entry->d_time +
- ((u64) (unsigned long) entry->d_fsdata << 32);
+ return ((union fuse_dentry *) entry->d_fsdata)->time;
}
-#endif
/*
* FUSE caches dentries and attributes with separate timeout. The
* time in jiffies until the dentry/attributes are valid is stored in
- * dentry->d_time and fuse_inode->i_time respectively.
+ * dentry->d_fsdata and fuse_inode->i_time respectively.
*/
/*
* Calculate the time in jiffies until a dentry/attributes are valid
*/
-static u64 time_to_jiffies(unsigned long sec, unsigned long nsec)
+static u64 time_to_jiffies(u64 sec, u32 nsec)
{
if (sec || nsec) {
- struct timespec ts = {sec, nsec};
- return get_jiffies_64() + timespec_to_jiffies(&ts);
+ struct timespec64 ts = {
+ sec,
+ max_t(u32, nsec, NSEC_PER_SEC - 1)
+ };
+
+ return get_jiffies_64() + timespec64_to_jiffies(&ts);
} else
return 0;
}
if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
return !nodeid || nodeid == FUSE_ROOT_ID;
}
+static int fuse_dentry_init(struct dentry *dentry)
+{
+ dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL);
+
+ return dentry->d_fsdata ? 0 : -ENOMEM;
+}
+static void fuse_dentry_release(struct dentry *dentry)
+{
+ union fuse_dentry *fd = dentry->d_fsdata;
+
+ kfree_rcu(fd, rcu);
+}
+
const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
+ .d_init = fuse_dentry_init,
+ .d_release = fuse_dentry_release,
};
int fuse_valid_type(int m)
if (time_before64(fi->i_time, get_jiffies_64())) {
r = true;
+ forget_all_cached_acls(inode);
err = fuse_do_getattr(inode, stat, file);
} else {
r = false;
{
const struct cred *cred;
- if (fc->flags & FUSE_ALLOW_OTHER)
+ if (fc->allow_other)
return 1;
cred = current_cred();
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
+ forget_all_cached_acls(inode);
return fuse_do_getattr(inode, NULL, NULL);
}
/*
* If attributes are needed, refresh them before proceeding
*/
- if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
+ if (fc->default_permissions ||
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
}
}
- if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
+ if (fc->default_permissions) {
err = generic_permission(inode, mask);
/* If permission is denied, try to refresh file
fi->nlookup++;
spin_unlock(&fc->lock);
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &o->attr,
entry_attr_timeout(o),
attr_version);
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
-int fuse_do_setattr(struct inode *inode, struct iattr *attr,
+int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
struct file *file)
{
+ struct inode *inode = d_inode(dentry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
FUSE_ARGS(args);
int err;
bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode);
- if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
{
struct inode *inode = d_inode(entry);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL;
+ int ret;
if (!fuse_allow_current_process(get_fuse_conn(inode)))
return -EACCES;
- if (attr->ia_valid & ATTR_FILE)
- return fuse_do_setattr(inode, attr, attr->ia_file);
- else
- return fuse_do_setattr(inode, attr, NULL);
+ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) {
+ attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID |
+ ATTR_MODE);
+
+ /*
+ * The only sane way to reliably kill suid/sgid is to do it in
+ * the userspace filesystem
+ *
+ * This should be done on write(), truncate() and chown().
+ */
+ if (!fc->handle_killpriv) {
+ int kill;
+
+ /*
+ * ia_mode calculation may have used stale i_mode.
+ * Refresh and recalculate.
+ */
+ ret = fuse_do_getattr(inode, NULL, file);
+ if (ret)
+ return ret;
+
+ attr->ia_mode = inode->i_mode;
+ kill = should_remove_suid(entry);
+ if (kill & ATTR_KILL_SUID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISUID;
+ }
+ if (kill & ATTR_KILL_SGID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISGID;
+ }
+ }
+ }
+ if (!attr->ia_valid)
+ return 0;
+
+ ret = fuse_do_setattr(entry, attr, file);
+ if (!ret) {
+ /*
+ * If filesystem supports acls it may have updated acl xattrs in
+ * the filesystem, so forget cached acls for the inode.
+ */
+ if (fc->posix_acl)
+ forget_all_cached_acls(inode);
+
+ /* Directory mode changed, may need to revalidate access */
+ if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE))
+ fuse_invalidate_entry_cache(entry);
+ }
+ return ret;
}
static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct file_operations fuse_dir_operations = {
.setattr = fuse_setattr,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct inode_operations fuse_symlink_inode_operations = {
.get_link = fuse_get_link,
.readlink = generic_readlink,
.getattr = fuse_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = generic_removexattr,
};
void fuse_init_common(struct inode *inode)
}
gfs2_set_iop(inode);
+
+ inode->i_atime.tv_sec = 0;
+ inode->i_atime.tv_nsec = 0;
+
unlock_new_inode(inode);
}
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
goto out;
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.getattr = gfs2_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = gfs2_listxattr,
- .removexattr = generic_removexattr,
.fiemap = gfs2_fiemap,
};
#include <linux/mpage.h>
#include <linux/sched.h>
#include <linux/uio.h>
+ #include <linux/xattr.h>
#include "hfs_fs.h"
#include "btree.h"
struct hfs_sb_info *hsb = HFS_SB(inode->i_sb);
int error;
- error = inode_change_ok(inode, attr); /* basic permission checks */
+ error = setattr_prepare(dentry, attr); /* basic permission checks */
if (error)
return error;
static const struct inode_operations hfs_file_inode_operations = {
.lookup = hfs_file_lookup,
.setattr = hfs_inode_setattr,
- .setxattr = hfs_setxattr,
- .getxattr = hfs_getxattr,
- .listxattr = hfs_listxattr,
+ .listxattr = generic_listxattr,
};
struct inode *inode = d_inode(dentry);
int error;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
static const struct inode_operations hfsplus_file_inode_operations = {
.setattr = hfsplus_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
- .removexattr = generic_removexattr,
#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
.get_acl = hfsplus_get_posix_acl,
.set_acl = hfsplus_set_posix_acl,
inode->i_fop = &no_open_fops;
inode->__i_nlink = 1;
inode->i_opflags = 0;
+ if (sb->s_xattr)
+ inode->i_opflags |= IOP_XATTR;
i_uid_write(inode, 0);
i_gid_write(inode, 0);
atomic_set(&inode->i_writecount, 0);
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode;
-
+again:
spin_lock(&inode_hash_lock);
inode = find_inode(sb, head, test, data);
spin_unlock(&inode_hash_lock);
if (inode) {
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
return inode;
}
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
}
return inode;
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
-
+again:
spin_lock(&inode_hash_lock);
inode = find_inode_fast(sb, head, ino);
spin_unlock(&inode_hash_lock);
if (inode) {
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
return inode;
}
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
}
return inode;
}
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
- struct inode *inode = ilookup5_nowait(sb, hashval, test, data);
-
- if (inode)
+ struct inode *inode;
+again:
+ inode = ilookup5_nowait(sb, hashval, test, data);
+ if (inode) {
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
+ }
return inode;
}
EXPORT_SYMBOL(ilookup5);
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
-
+again:
spin_lock(&inode_hash_lock);
inode = find_inode_fast(sb, head, ino);
spin_unlock(&inode_hash_lock);
- if (inode)
+ if (inode) {
wait_on_inode(inode);
+ if (unlikely(inode_unhashed(inode))) {
+ iput(inode);
+ goto again;
+ }
+ }
return inode;
}
EXPORT_SYMBOL(ilookup);
}
EXPORT_SYMBOL(bmap);
+/*
+ * Update times in overlayed inode from underlying real inode
+ */
+static void update_ovl_inode_times(struct dentry *dentry, struct inode *inode,
+ bool rcu)
+{
+ if (!rcu) {
+ struct inode *realinode = d_real_inode(dentry);
+
+ if (unlikely(inode != realinode) &&
+ (!timespec_equal(&inode->i_mtime, &realinode->i_mtime) ||
+ !timespec_equal(&inode->i_ctime, &realinode->i_ctime))) {
+ inode->i_mtime = realinode->i_mtime;
+ inode->i_ctime = realinode->i_ctime;
+ }
+ }
+}
+
/*
* With relative atime, only update atime if the previous atime is
* earlier than either the ctime or mtime or if at least a day has
* passed since the last atime update.
*/
-static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
- struct timespec now)
+static int relatime_need_update(const struct path *path, struct inode *inode,
+ struct timespec now, bool rcu)
{
- if (!(mnt->mnt_flags & MNT_RELATIME))
+ if (!(path->mnt->mnt_flags & MNT_RELATIME))
return 1;
+
+ update_ovl_inode_times(path->dentry, inode, rcu);
/*
* Is mtime younger than atime? If yes, update atime:
*/
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
-bool atime_needs_update(const struct path *path, struct inode *inode)
+bool __atime_needs_update(const struct path *path, struct inode *inode,
+ bool rcu)
{
struct vfsmount *mnt = path->mnt;
struct timespec now;
now = current_fs_time(inode->i_sb);
- if (!relatime_need_update(mnt, inode, now))
+ if (!relatime_need_update(path, inode, now, rcu))
return false;
if (timespec_equal(&inode->i_atime, &now))
struct inode *inode = d_inode(path->dentry);
struct timespec now;
- if (!atime_needs_update(path, inode))
+ if (!__atime_needs_update(path, inode, false))
return;
if (!sb_start_write_trylock(inode->i_sb))
struct inode *inode = d_inode(dentry);
int rc;
- rc = inode_change_ok(inode, iattr);
+ rc = setattr_prepare(dentry, iattr);
if (rc)
return rc;
}
const struct inode_operations jfs_file_inode_operations = {
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = jfs_listxattr,
- .removexattr = generic_removexattr,
.setattr = jfs_setattr,
#ifdef CONFIG_JFS_POSIX_ACL
.get_acl = jfs_get_acl,
.permission = kernfs_iop_permission,
.setattr = kernfs_iop_setattr,
.getattr = kernfs_iop_getattr,
- .setxattr = kernfs_iop_setxattr,
- .removexattr = kernfs_iop_removexattr,
- .getxattr = kernfs_iop_getxattr,
.listxattr = kernfs_iop_listxattr,
};
return -EINVAL;
mutex_lock(&kernfs_mutex);
- error = inode_change_ok(inode, iattr);
+ error = setattr_prepare(dentry, iattr);
if (error)
goto out;
return error;
}
- static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata,
+ static int kernfs_node_setsecdata(struct kernfs_iattrs *attrs, void **secdata,
u32 *secdata_len)
{
- struct kernfs_iattrs *attrs;
void *old_secdata;
size_t old_secdata_len;
- attrs = kernfs_iattrs(kn);
- if (!attrs)
- return -ENOMEM;
-
old_secdata = attrs->ia_secdata;
old_secdata_len = attrs->ia_secdata_len;
return 0;
}
- int kernfs_iop_setxattr(struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
- {
- struct kernfs_node *kn = inode->i_private;
- struct kernfs_iattrs *attrs;
- void *secdata;
- int error;
- u32 secdata_len = 0;
-
- attrs = kernfs_iattrs(kn);
- if (!attrs)
- return -ENOMEM;
-
- if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
- const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
- error = security_inode_setsecurity(inode, suffix,
- value, size, flags);
- if (error)
- return error;
- error = security_inode_getsecctx(inode,
- &secdata, &secdata_len);
- if (error)
- return error;
-
- mutex_lock(&kernfs_mutex);
- error = kernfs_node_setsecdata(kn, &secdata, &secdata_len);
- mutex_unlock(&kernfs_mutex);
-
- if (secdata)
- security_release_secctx(secdata, secdata_len);
- return error;
- } else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
- return simple_xattr_set(&attrs->xattrs, name, value, size,
- flags);
- }
-
- return -EINVAL;
- }
-
- int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
- {
- struct kernfs_node *kn = dentry->d_fsdata;
- struct kernfs_iattrs *attrs;
-
- attrs = kernfs_iattrs(kn);
- if (!attrs)
- return -ENOMEM;
-
- return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE);
- }
-
- ssize_t kernfs_iop_getxattr(struct dentry *unused, struct inode *inode,
- const char *name, void *buf, size_t size)
- {
- struct kernfs_node *kn = inode->i_private;
- struct kernfs_iattrs *attrs;
-
- attrs = kernfs_iattrs(kn);
- if (!attrs)
- return -ENOMEM;
-
- return simple_xattr_get(&attrs->xattrs, name, buf, size);
- }
-
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
{
struct kernfs_node *kn = dentry->d_fsdata;
return generic_permission(inode, mask);
}
+
+ static int kernfs_xattr_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *suffix, void *value, size_t size)
+ {
+ const char *name = xattr_full_name(handler, suffix);
+ struct kernfs_node *kn = inode->i_private;
+ struct kernfs_iattrs *attrs;
+
+ attrs = kernfs_iattrs(kn);
+ if (!attrs)
+ return -ENOMEM;
+
+ return simple_xattr_get(&attrs->xattrs, name, value, size);
+ }
+
+ static int kernfs_xattr_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *suffix, const void *value,
+ size_t size, int flags)
+ {
+ const char *name = xattr_full_name(handler, suffix);
+ struct kernfs_node *kn = inode->i_private;
+ struct kernfs_iattrs *attrs;
+
+ attrs = kernfs_iattrs(kn);
+ if (!attrs)
+ return -ENOMEM;
+
+ return simple_xattr_set(&attrs->xattrs, name, value, size, flags);
+ }
+
+ const struct xattr_handler kernfs_trusted_xattr_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .get = kernfs_xattr_get,
+ .set = kernfs_xattr_set,
+ };
+
+ static int kernfs_security_xattr_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *suffix, const void *value,
+ size_t size, int flags)
+ {
+ struct kernfs_node *kn = inode->i_private;
+ struct kernfs_iattrs *attrs;
+ void *secdata;
+ u32 secdata_len = 0;
+ int error;
+
+ attrs = kernfs_iattrs(kn);
+ if (!attrs)
+ return -ENOMEM;
+
+ error = security_inode_setsecurity(inode, suffix, value, size, flags);
+ if (error)
+ return error;
+ error = security_inode_getsecctx(inode, &secdata, &secdata_len);
+ if (error)
+ return error;
+
+ mutex_lock(&kernfs_mutex);
+ error = kernfs_node_setsecdata(attrs, &secdata, &secdata_len);
+ mutex_unlock(&kernfs_mutex);
+
+ if (secdata)
+ security_release_secctx(secdata, secdata_len);
+ return error;
+ }
+
+ const struct xattr_handler kernfs_security_xattr_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = kernfs_xattr_get,
+ .set = kernfs_security_xattr_set,
+ };
+
+ const struct xattr_handler *kernfs_xattr_handlers[] = {
+ &kernfs_trusted_xattr_handler,
+ &kernfs_security_xattr_handler,
+ NULL
+ };
* Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that
* will never be mountable)
*/
- struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name,
- const struct super_operations *ops,
+ struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name,
+ const struct super_operations *ops, const struct xattr_handler **xattr,
const struct dentry_operations *dops, unsigned long magic)
{
struct super_block *s;
s->s_blocksize_bits = PAGE_SHIFT;
s->s_magic = magic;
s->s_op = ops ? ops : &simple_super_operations;
+ s->s_xattr = xattr;
s->s_time_gran = 1;
root = new_inode(s);
if (!root)
deactivate_locked_super(s);
return ERR_PTR(-ENOMEM);
}
- EXPORT_SYMBOL(mount_pseudo);
+ EXPORT_SYMBOL(mount_pseudo_xattr);
int simple_open(struct inode *inode, struct file *file)
{
struct inode *inode = d_inode(dentry);
int error;
- error = inode_change_ok(inode, iattr);
+ error = setattr_prepare(dentry, iattr);
if (error)
return error;
return -EPERM;
}
- static int empty_dir_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
- {
- return -EOPNOTSUPP;
- }
-
- static ssize_t empty_dir_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
- {
- return -EOPNOTSUPP;
- }
-
- static int empty_dir_removexattr(struct dentry *dentry, const char *name)
- {
- return -EOPNOTSUPP;
- }
-
static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size)
{
return -EOPNOTSUPP;
.permission = generic_permission,
.setattr = empty_dir_setattr,
.getattr = empty_dir_getattr,
- .setxattr = empty_dir_setxattr,
- .getxattr = empty_dir_getxattr,
- .removexattr = empty_dir_removexattr,
.listxattr = empty_dir_listxattr,
};
inode->i_blocks = 0;
inode->i_op = &empty_dir_inode_operations;
+ inode->i_opflags &= ~IOP_XATTR;
inode->i_fop = &empty_dir_operations;
}
if (!(attr->ia_valid & OCFS2_VALID_ATTRS))
return 0;
- status = inode_change_ok(inode, attr);
+ status = setattr_prepare(dentry, attr);
if (status)
return status;
return ret;
}
-static ssize_t ocfs2_file_splice_read(struct file *in,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len,
- unsigned int flags)
-{
- int ret = 0, lock_level = 0;
- struct inode *inode = file_inode(in);
-
- trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- in->f_path.dentry->d_name.len,
- in->f_path.dentry->d_name.name, len);
-
- /*
- * See the comment in ocfs2_file_read_iter()
- */
- ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
- if (ret < 0) {
- mlog_errno(ret);
- goto bail;
- }
- ocfs2_inode_unlock(inode, lock_level);
-
- ret = generic_file_splice_read(in, ppos, pipe, len, flags);
-
-bail:
- return ret;
-}
-
static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
struct iov_iter *to)
{
.setattr = ocfs2_setattr,
.getattr = ocfs2_getattr,
.permission = ocfs2_permission,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ocfs2_listxattr,
- .removexattr = generic_removexattr,
.fiemap = ocfs2_fiemap,
.get_acl = ocfs2_iop_get_acl,
.set_acl = ocfs2_iop_set_acl,
#endif
.lock = ocfs2_lock,
.flock = ocfs2_flock,
- .splice_read = ocfs2_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
.compat_ioctl = ocfs2_compat_ioctl,
#endif
.flock = ocfs2_flock,
- .splice_read = ocfs2_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
struct iov_iter *iter)
{
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_direct_IO: %s\n",
- iocb->ki_filp->f_path.dentry->d_name.name);
+ "orangefs_direct_IO: %pD\n",
+ iocb->ki_filp);
return -EINVAL;
}
struct inode *inode = dentry->d_inode;
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_setattr: called on %s\n",
- dentry->d_name.name);
+ "orangefs_setattr: called on %pd\n",
+ dentry);
- ret = inode_change_ok(inode, iattr);
+ ret = setattr_prepare(dentry, iattr);
if (ret)
goto out;
struct orangefs_inode_s *orangefs_inode = NULL;
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_getattr: called on %s\n",
- dentry->d_name.name);
+ "orangefs_getattr: called on %pd\n",
+ dentry);
ret = orangefs_inode_getattr(inode, 0, 0);
if (ret == 0) {
.set_acl = orangefs_set_acl,
.setattr = orangefs_setattr,
.getattr = orangefs_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = orangefs_listxattr,
- .removexattr = generic_removexattr,
.permission = orangefs_permission,
};
struct inode *inode;
int ret;
- gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
+ gossip_debug(GOSSIP_NAME_DEBUG, "%s: %pd\n",
__func__,
- dentry->d_name.name);
+ dentry);
new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
if (!new_op)
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
+ "%s: %pd: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
__func__,
- dentry->d_name.name,
+ dentry,
&new_op->downcall.resp.create.refn.khandle,
new_op->downcall.resp.create.refn.fs_id,
new_op,
inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
&new_op->downcall.resp.create.refn);
if (IS_ERR(inode)) {
- gossip_err("%s: Failed to allocate inode for file :%s:\n",
+ gossip_err("%s: Failed to allocate inode for file :%pd:\n",
__func__,
- dentry->d_name.name);
+ dentry);
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: Assigned inode :%pU: for file :%s:\n",
+ "%s: Assigned inode :%pU: for file :%pd:\n",
__func__,
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: dentry instantiated for %s\n",
+ "%s: dentry instantiated for %pd\n",
__func__,
- dentry->d_name.name);
+ dentry);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
out:
op_release(new_op);
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: %s: returning %d\n",
+ "%s: %pd: returning %d\n",
__func__,
- dentry->d_name.name,
+ dentry,
ret);
return ret;
}
* -EEXIST on O_EXCL opens, which is broken if we skip this lookup
* in the create path)
*/
- gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %s\n",
- __func__, dentry->d_name.name);
+ gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %pd\n",
+ __func__, dentry);
if (dentry->d_name.len > (ORANGEFS_NAME_MAX - 1))
return ERR_PTR(-ENAMETOOLONG);
gossip_debug(GOSSIP_NAME_DEBUG,
"orangefs_lookup: Adding *negative* dentry "
- "%p for %s\n",
+ "%p for %pd\n",
dentry,
- dentry->d_name.name);
+ dentry);
d_add(dentry, NULL);
res = NULL;
goto out;
}
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
if (IS_ERR(inode)) {
int ret;
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: called on %s\n"
+ "%s: called on %pd\n"
" (inode %pU): Parent is %pU | fs_id %d\n",
__func__,
- dentry->d_name.name,
+ dentry,
get_khandle_from_ino(inode),
&parent->refn.khandle,
parent->refn.fs_id);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "Inode (Symlink) %pU -> %s\n",
+ "Inode (Symlink) %pU -> %pd\n",
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "Inode (Directory) %pU -> %s\n",
+ "Inode (Directory) %pU -> %pd\n",
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
/*
* NOTE: we have no good way to keep nlink consistent for directories
.rename = orangefs_rename,
.setattr = orangefs_setattr,
.getattr = orangefs_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = orangefs_listxattr,
.permission = orangefs_permission,
};
char *buf, *name, *value = NULL;
int uninitialized_var(error);
- if (!old->d_inode->i_op->getxattr ||
- !new->d_inode->i_op->getxattr)
+ if (!(old->d_inode->i_opflags & IOP_XATTR) ||
+ !(new->d_inode->i_opflags & IOP_XATTR))
return 0;
list_size = vfs_listxattr(old, NULL, 0);
goto retry;
}
+ error = security_inode_copy_up_xattr(name);
+ if (error < 0 && error != -EOPNOTSUPP)
+ break;
+ if (error == 1) {
+ error = 0;
+ continue; /* Discard */
+ }
error = vfs_setxattr(new, name, value, size, 0);
if (error)
break;
struct dentry *upper = NULL;
umode_t mode = stat->mode;
int err;
+ const struct cred *old_creds = NULL;
+ struct cred *new_creds = NULL;
newdentry = ovl_lookup_temp(workdir, dentry);
err = PTR_ERR(newdentry);
if (IS_ERR(upper))
goto out1;
+ err = security_inode_copy_up(dentry, &new_creds);
+ if (err < 0)
+ goto out2;
+
+ if (new_creds)
+ old_creds = override_creds(new_creds);
+
/* Can't properly set mode on creation because of the umask */
stat->mode &= S_IFMT;
err = ovl_create_real(wdir, newdentry, stat, link, NULL, true);
stat->mode = mode;
+
+ if (new_creds) {
+ revert_creds(old_creds);
+ put_cred(new_creds);
+ }
+
if (err)
goto out2;
if (override_cred) {
override_cred->fsuid = inode->i_uid;
override_cred->fsgid = inode->i_gid;
+ if (!hardlink) {
+ err = security_dentry_create_files_as(dentry,
+ stat->mode, &dentry->d_name, old_cred,
+ override_cred);
+ if (err) {
+ put_cred(override_cred);
+ goto out_revert_creds;
+ }
+ }
put_cred(override_creds(override_cred));
put_cred(override_cred);
err = ovl_create_over_whiteout(dentry, inode, stat,
link, hardlink);
}
+out_revert_creds:
revert_creds(old_cred);
if (!err) {
struct inode *realinode = d_inode(ovl_dentry_upper(dentry));
.mknod = ovl_mknod,
.permission = ovl_permission,
.getattr = ovl_dir_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
* inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
* check for a swapfile (which this won't be anyway).
*/
- err = inode_change_ok(dentry->d_inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
.setattr = ovl_setattr,
.permission = ovl_permission,
.getattr = ovl_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
.get_link = ovl_get_link,
.readlink = ovl_readlink,
.getattr = ovl_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = generic_removexattr,
.update_time = ovl_update_time,
};
char val;
struct inode *inode = dentry->d_inode;
- if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr)
+ if (!S_ISDIR(inode->i_mode) || !(inode->i_opflags & IOP_XATTR))
return false;
- res = inode->i_op->getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1);
+ res = __vfs_getxattr(dentry, inode, OVL_XATTR_OPAQUE, &val, 1);
if (res == 1 && val == 'y')
return true;
sb->s_xattr = ovl_xattr_handlers;
sb->s_root = root_dentry;
sb->s_fs_info = ufs;
- sb->s_flags |= MS_POSIXACL;
+ sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
return 0;
dbg_gen("ino %lu, mode %#x, ia_valid %#x",
inode->i_ino, inode->i_mode, attr->ia_valid);
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
const struct inode_operations ubifs_file_inode_operations = {
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ubifs_listxattr,
- .removexattr = generic_removexattr,
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
.update_time = ubifs_update_time,
#endif
.get_link = simple_get_link,
.setattr = ubifs_setattr,
.getattr = ubifs_getattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = ubifs_listxattr,
- .removexattr = generic_removexattr,
#ifdef CONFIG_UBIFS_ATIME_SUPPORT
.update_time = ubifs_update_time,
#endif
inode->i_mtime = iattr->ia_mtime;
}
+static int
+xfs_vn_change_ok(
+ struct dentry *dentry,
+ struct iattr *iattr)
+{
+ struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount;
+
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ return -EROFS;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ return setattr_prepare(dentry, iattr);
+}
+
+/*
+ * Set non-size attributes of an inode.
+ *
+ * Caution: The caller of this function is responsible for calling
+ * setattr_prepare() or otherwise verifying the change is fine.
+ */
int
xfs_setattr_nonsize(
struct xfs_inode *ip,
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
- trace_xfs_setattr(ip);
-
- /* If acls are being inherited, we already have this checked */
- if (!(flags & XFS_ATTR_NOACL)) {
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- return -EROFS;
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
-
- error = inode_change_ok(inode, iattr);
- if (error)
- return error;
- }
-
ASSERT((mask & ATTR_SIZE) == 0);
/*
return error;
}
+int
+xfs_vn_setattr_nonsize(
+ struct dentry *dentry,
+ struct iattr *iattr)
+{
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ int error;
+
+ trace_xfs_setattr(ip);
+
+ error = xfs_vn_change_ok(dentry, iattr);
+ if (error)
+ return error;
+ return xfs_setattr_nonsize(ip, iattr, 0);
+}
+
/*
* Truncate file. Must have write permission and not be a directory.
+ *
+ * Caution: The caller of this function is responsible for calling
+ * setattr_prepare() or otherwise verifying the change is fine.
*/
int
xfs_setattr_size(
uint lock_flags = 0;
bool did_zeroing = false;
- trace_xfs_setattr(ip);
-
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- return -EROFS;
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
-
- error = inode_change_ok(inode, iattr);
- if (error)
- return error;
-
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
goto out_unlock;
}
+int
+xfs_vn_setattr_size(
+ struct dentry *dentry,
+ struct iattr *iattr)
+{
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ int error;
+
+ trace_xfs_setattr(ip);
+
+ error = xfs_vn_change_ok(dentry, iattr);
+ if (error)
+ return error;
+ return xfs_setattr_size(ip, iattr);
+}
+
STATIC int
xfs_vn_setattr(
struct dentry *dentry,
struct iattr *iattr)
{
- struct xfs_inode *ip = XFS_I(d_inode(dentry));
int error;
if (iattr->ia_valid & ATTR_SIZE) {
- uint iolock = XFS_IOLOCK_EXCL;
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ uint iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(d_inode(dentry), &iolock, true);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
- error = xfs_setattr_size(ip, iattr);
+ error = xfs_vn_setattr_size(dentry, iattr);
}
xfs_iunlock(ip, iolock);
} else {
- error = xfs_setattr_nonsize(ip, iattr, 0);
+ error = xfs_vn_setattr_nonsize(dentry, iattr);
}
return error;
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.fiemap = xfs_vn_fiemap,
.update_time = xfs_vn_update_time,
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
.get_link = xfs_vn_get_link,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
};
.get_link = xfs_vn_get_link_inline,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
};
extern struct files_stat_struct files_stat;
extern unsigned long get_max_files(void);
-extern int sysctl_nr_open;
+extern unsigned int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
extern int sysctl_protected_symlinks;
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
+#define ATTR_TOUCH (1 << 17)
/*
* Whiteout is represented by a char device. The following constants define the
#define IOP_FASTPERM 0x0001
#define IOP_LOOKUP 0x0002
#define IOP_NOFOLLOW 0x0004
+ #define IOP_XATTR 0x0008
/*
* Keep mostly read-only and often accessed (especially for
extern void send_sigio(struct fown_struct *fown, int fd, int band);
+/*
+ * Return the inode to use for locking
+ *
+ * For overlayfs this should be the overlay inode, not the real inode returned
+ * by file_inode(). For any other fs file_inode(filp) and locks_inode(filp) are
+ * equal.
+ */
+static inline struct inode *locks_inode(const struct file *f)
+{
+ return f->f_path.dentry->d_inode;
+}
+
#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
- return locks_lock_inode_wait(file_inode(filp), fl);
+ return locks_lock_inode_wait(locks_inode(filp), fl);
}
struct fasync_struct {
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
- int (*setxattr) (struct dentry *, struct inode *,
- const char *, const void *, size_t, int);
- ssize_t (*getxattr) (struct dentry *, struct inode *,
- const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
- int (*removexattr) (struct dentry *, const char *);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, struct timespec *, int);
S_VERSION = 8,
};
-extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
{
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags, void *data);
- extern struct dentry *mount_pseudo(struct file_system_type *, char *,
- const struct super_operations *ops,
- const struct dentry_operations *dops,
- unsigned long);
+ extern struct dentry *mount_pseudo_xattr(struct file_system_type *, char *,
+ const struct super_operations *ops,
+ const struct xattr_handler **xattr,
+ const struct dentry_operations *dops,
+ unsigned long);
+
+ static inline struct dentry *
+ mount_pseudo(struct file_system_type *fs_type, char *name,
+ const struct super_operations *ops,
+ const struct dentry_operations *dops, unsigned long magic)
+ {
+ return mount_pseudo_xattr(fs_type, name, ops, NULL, dops, magic);
+ }
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
static inline int locks_verify_locked(struct file *file)
{
- if (mandatory_lock(file_inode(file)))
+ if (mandatory_lock(locks_inode(file)))
return locks_mandatory_locked(file);
return 0;
}
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
-extern ssize_t default_file_splice_read(struct file *, loff_t *,
- struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
#define buffer_migrate_page NULL
#endif
-extern int inode_change_ok(const struct inode *, struct iattr *);
+extern int setattr_prepare(struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
return retval ? retval : error;
}
-static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
-{
- struct address_space *mapping = in->f_mapping;
- struct inode *inode = mapping->host;
- unsigned int loff, nr_pages, req_pages;
- struct page *pages[PIPE_DEF_BUFFERS];
- struct partial_page partial[PIPE_DEF_BUFFERS];
- struct page *page;
- pgoff_t index, end_index;
- loff_t isize, left;
- int error, page_nr;
- struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
- .nr_pages_max = PIPE_DEF_BUFFERS,
- .flags = flags,
- .ops = &page_cache_pipe_buf_ops,
- .spd_release = spd_release_page,
- };
-
- isize = i_size_read(inode);
- if (unlikely(*ppos >= isize))
- return 0;
-
- left = isize - *ppos;
- if (unlikely(left < len))
- len = left;
-
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
-
- index = *ppos >> PAGE_SHIFT;
- loff = *ppos & ~PAGE_MASK;
- req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT;
- nr_pages = min(req_pages, spd.nr_pages_max);
-
- spd.nr_pages = find_get_pages_contig(mapping, index,
- nr_pages, spd.pages);
- index += spd.nr_pages;
- error = 0;
-
- while (spd.nr_pages < nr_pages) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- spd.pages[spd.nr_pages++] = page;
- index++;
- }
-
- index = *ppos >> PAGE_SHIFT;
- nr_pages = spd.nr_pages;
- spd.nr_pages = 0;
-
- for (page_nr = 0; page_nr < nr_pages; page_nr++) {
- unsigned int this_len;
-
- if (!len)
- break;
-
- this_len = min_t(unsigned long, len, PAGE_SIZE - loff);
- page = spd.pages[page_nr];
-
- if (!PageUptodate(page) || page->mapping != mapping) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- put_page(spd.pages[page_nr]);
- spd.pages[page_nr] = page;
- }
-
- isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (unlikely(!isize || index > end_index))
- break;
-
- if (end_index == index) {
- unsigned int plen;
-
- plen = ((isize - 1) & ~PAGE_MASK) + 1;
- if (plen <= loff)
- break;
-
- this_len = min(this_len, plen - loff);
- len = this_len;
- }
-
- spd.partial[page_nr].offset = loff;
- spd.partial[page_nr].len = this_len;
- len -= this_len;
- loff = 0;
- spd.nr_pages++;
- index++;
- }
-
- while (page_nr < nr_pages)
- put_page(spd.pages[page_nr++]);
-
- if (spd.nr_pages)
- error = splice_to_pipe(pipe, &spd);
-
- splice_shrink_spd(&spd);
-
- if (error > 0) {
- *ppos += error;
- file_accessed(in);
- }
- return error;
-}
-
/*
* llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
*/
.readlink = generic_readlink,
.get_link = simple_get_link,
#ifdef CONFIG_TMPFS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = shmem_listxattr,
- .removexattr = generic_removexattr,
#endif
};
.readlink = generic_readlink,
.get_link = shmem_get_link,
#ifdef CONFIG_TMPFS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = shmem_listxattr,
- .removexattr = generic_removexattr,
#endif
};
.read_iter = shmem_file_read_iter,
.write_iter = generic_file_write_iter,
.fsync = noop_fsync,
- .splice_read = shmem_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
.getattr = shmem_getattr,
.setattr = shmem_setattr,
#ifdef CONFIG_TMPFS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = shmem_listxattr,
- .removexattr = generic_removexattr,
.set_acl = simple_set_acl,
#endif
};
.tmpfile = shmem_tmpfile,
#endif
#ifdef CONFIG_TMPFS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = shmem_listxattr,
- .removexattr = generic_removexattr,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
static const struct inode_operations shmem_special_inode_operations = {
#ifdef CONFIG_TMPFS_XATTR
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
.listxattr = shmem_listxattr,
- .removexattr = generic_removexattr,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
/* common code */
-static struct dentry_operations anon_ops = {
+static const struct dentry_operations anon_ops = {
.d_dname = simple_dname
};
int ima_read_xattr(struct dentry *dentry,
struct evm_ima_xattr_data **xattr_value)
{
- struct inode *inode = d_backing_inode(dentry);
-
- if (!inode->i_op->getxattr)
- return 0;
+ ssize_t ret;
- return vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
- 0, GFP_NOFS);
+ ret = vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
+ 0, GFP_NOFS);
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
+ return ret;
}
/*
{
static const char op[] = "appraise_data";
char *cause = "unknown";
- struct dentry *dentry = file->f_path.dentry;
+ struct dentry *dentry = file_dentry(file);
struct inode *inode = d_backing_inode(dentry);
enum integrity_status status = INTEGRITY_UNKNOWN;
int rc = xattr_len, hash_start = 0;
- if (!inode->i_op->getxattr)
+ if (!(inode->i_opflags & IOP_XATTR))
return INTEGRITY_UNKNOWN;
if (rc <= 0) {
*/
void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
{
- struct dentry *dentry = file->f_path.dentry;
+ struct dentry *dentry = file_dentry(file);
int rc = 0;
/* do not collect and update hash for digital signatures */
{
struct inode *inode = d_backing_inode(dentry);
struct integrity_iint_cache *iint;
- int must_appraise, rc;
+ int must_appraise;
if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)
- || !inode->i_op->removexattr)
+ || !(inode->i_opflags & IOP_XATTR))
return;
must_appraise = ima_must_appraise(inode, MAY_ACCESS, POST_SETATTR);
iint->flags |= IMA_APPRAISE;
}
if (!must_appraise)
- rc = inode->i_op->removexattr(dentry, XATTR_NAME_IMA);
- return;
+ __vfs_removexattr(dentry, XATTR_NAME_IMA);
}
/*
the root directory. -ENODATA is ok, as this may be
the first boot of the SELinux kernel before we have
assigned xattr values to the filesystem. */
- if (!root_inode->i_op->getxattr) {
+ if (!(root_inode->i_opflags & IOP_XATTR)) {
printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
"xattr support\n", sb->s_id, sb->s_type->name);
rc = -EOPNOTSUPP;
goto out;
}
- rc = root_inode->i_op->getxattr(root, root_inode,
- XATTR_NAME_SELINUX, NULL, 0);
+
+ rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0);
if (rc < 0 && rc != -ENODATA) {
if (rc == -EOPNOTSUPP)
printk(KERN_WARNING "SELinux: (dev %s, type "
case SECURITY_FS_USE_NATIVE:
break;
case SECURITY_FS_USE_XATTR:
- if (!inode->i_op->getxattr) {
+ if (!(inode->i_opflags & IOP_XATTR)) {
isec->sid = sbsec->def_sid;
break;
}
-
/* Need a dentry, since the xattr API requires one.
Life would be simpler if we could just pass the inode. */
if (opt_dentry) {
goto out_unlock;
}
context[len] = '\0';
- rc = inode->i_op->getxattr(dentry, inode, XATTR_NAME_SELINUX,
- context, len);
+ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len);
if (rc == -ERANGE) {
kfree(context);
/* Need a larger buffer. Query for the right size. */
- rc = inode->i_op->getxattr(dentry, inode, XATTR_NAME_SELINUX,
- NULL, 0);
+ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0);
if (rc < 0) {
dput(dentry);
goto out_unlock;
goto out_unlock;
}
context[len] = '\0';
- rc = inode->i_op->getxattr(dentry, inode,
- XATTR_NAME_SELINUX,
- context, len);
+ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len);
}
dput(dentry);
if (rc < 0) {
{
struct common_audit_data ad;
- ad.type = LSM_AUDIT_DATA_PATH;
- ad.u.path = file->f_path;
+ ad.type = LSM_AUDIT_DATA_FILE;
+ ad.u.file = file;
return inode_has_perm(cred, file_inode(file), av, &ad);
}
u32 sid = cred_sid(cred);
int rc;
- ad.type = LSM_AUDIT_DATA_PATH;
- ad.u.path = file->f_path;
+ ad.type = LSM_AUDIT_DATA_FILE;
+ ad.u.file = file;
if (sid != fsec->sid) {
rc = avc_has_perm(sid, fsec->sid,
/*
* Determine the label for an inode that might be unioned.
*/
-static int selinux_determine_inode_label(struct inode *dir,
- const struct qstr *name,
- u16 tclass,
- u32 *_new_isid)
+static int
+selinux_determine_inode_label(const struct task_security_struct *tsec,
+ struct inode *dir,
+ const struct qstr *name, u16 tclass,
+ u32 *_new_isid)
{
const struct superblock_security_struct *sbsec = dir->i_sb->s_security;
- const struct task_security_struct *tsec = current_security();
if ((sbsec->flags & SE_SBINITIALIZED) &&
(sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) {
if (rc)
return rc;
- rc = selinux_determine_inode_label(dir, &dentry->d_name, tclass,
- &newsid);
+ rc = selinux_determine_inode_label(current_security(), dir,
+ &dentry->d_name, tclass, &newsid);
if (rc)
return rc;
new_tsec->sid = old_tsec->sid;
}
- ad.type = LSM_AUDIT_DATA_PATH;
- ad.u.path = bprm->file->f_path;
+ ad.type = LSM_AUDIT_DATA_FILE;
+ ad.u.file = bprm->file;
if (new_tsec->sid == old_tsec->sid) {
rc = avc_has_perm(old_tsec->sid, isec->sid,
u32 newsid;
int rc;
- rc = selinux_determine_inode_label(d_inode(dentry->d_parent), name,
+ rc = selinux_determine_inode_label(current_security(),
+ d_inode(dentry->d_parent), name,
inode_mode_to_security_class(mode),
&newsid);
if (rc)
return security_sid_to_context(newsid, (char **)ctx, ctxlen);
}
+static int selinux_dentry_create_files_as(struct dentry *dentry, int mode,
+ struct qstr *name,
+ const struct cred *old,
+ struct cred *new)
+{
+ u32 newsid;
+ int rc;
+ struct task_security_struct *tsec;
+
+ rc = selinux_determine_inode_label(old->security,
+ d_inode(dentry->d_parent), name,
+ inode_mode_to_security_class(mode),
+ &newsid);
+ if (rc)
+ return rc;
+
+ tsec = new->security;
+ tsec->create_sid = newsid;
+ return 0;
+}
+
static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr,
const char **name,
sid = tsec->sid;
newsid = tsec->create_sid;
- rc = selinux_determine_inode_label(
+ rc = selinux_determine_inode_label(current_security(),
dir, qstr,
inode_mode_to_security_class(inode->i_mode),
&newsid);
*secid = isec->sid;
}
+static int selinux_inode_copy_up(struct dentry *src, struct cred **new)
+{
+ u32 sid;
+ struct task_security_struct *tsec;
+ struct cred *new_creds = *new;
+
+ if (new_creds == NULL) {
+ new_creds = prepare_creds();
+ if (!new_creds)
+ return -ENOMEM;
+ }
+
+ tsec = new_creds->security;
+ /* Get label from overlay inode and set it in create_sid */
+ selinux_inode_getsecid(d_inode(src), &sid);
+ tsec->create_sid = sid;
+ *new = new_creds;
+ return 0;
+}
+
+static int selinux_inode_copy_up_xattr(const char *name)
+{
+ /* The copy_up hook above sets the initial context on an inode, but we
+ * don't then want to overwrite it by blindly copying all the lower
+ * xattrs up. Instead, we have to filter out SELinux-related xattrs.
+ */
+ if (strcmp(name, XATTR_NAME_SELINUX) == 0)
+ return 1; /* Discard */
+ /*
+ * Any other attribute apart from SELINUX is not claimed, supported
+ * by selinux.
+ */
+ return -EOPNOTSUPP;
+}
+
/* file security operations */
static int selinux_revalidate_file_permission(struct file *file, int mask)
/* finit_module */
- ad.type = LSM_AUDIT_DATA_PATH;
- ad.u.path = file->f_path;
+ ad.type = LSM_AUDIT_DATA_FILE;
+ ad.u.file = file;
fsec = file->f_security;
if (sid != fsec->sid) {
return ret;
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
/* Returns error only if unable to parse addresses */
static int selinux_parse_skb_ipv6(struct sk_buff *skb,
&ad->u.net->v4info.daddr);
goto okay;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
case PF_INET6:
ret = selinux_parse_skb_ipv6(skb, ad, proto);
if (ret)
return selinux_ip_forward(skb, state->in, PF_INET);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static unsigned int selinux_ipv6_forward(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
return selinux_ip_output(skb, PF_INET);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static unsigned int selinux_ipv6_output(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
return selinux_ip_postroute(skb, state->out, PF_INET);
}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
static unsigned int selinux_ipv6_postroute(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
LSM_HOOK_INIT(sb_parse_opts_str, selinux_parse_opts_str),
LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security),
+ LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as),
LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security),
LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security),
LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity),
LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity),
LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid),
+ LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up),
+ LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr),
LSM_HOOK_INIT(file_permission, selinux_file_permission),
LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_SELINUX_FIRST,
},
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
{
.hook = selinux_ipv6_postroute,
.pf = NFPROTO_IPV6,
char *buffer;
struct smack_known *skp = NULL;
- if (ip->i_op->getxattr == NULL)
+ if (!(ip->i_opflags & IOP_XATTR))
return ERR_PTR(-EOPNOTSUPP);
buffer = kzalloc(SMK_LONGLABEL, GFP_KERNEL);
if (buffer == NULL)
return ERR_PTR(-ENOMEM);
- rc = ip->i_op->getxattr(dp, ip, name, buffer, SMK_LONGLABEL);
+ rc = __vfs_getxattr(dp, ip, name, buffer, SMK_LONGLABEL);
if (rc < 0)
skp = ERR_PTR(rc);
else if (rc == 0)
/* we don't log here as rc can be overriden */
skp = file->f_security;
- rc = smk_access(skp, tkp, MAY_WRITE, NULL);
- rc = smk_bu_note("sigiotask", skp, tkp, MAY_WRITE, rc);
+ rc = smk_access(skp, tkp, MAY_DELIVER, NULL);
+ rc = smk_bu_note("sigiotask", skp, tkp, MAY_DELIVER, rc);
if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
rc = 0;
smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
smk_ad_setfield_u_tsk(&ad, tsk);
- smack_log(skp->smk_known, tkp->smk_known, MAY_WRITE, rc, &ad);
+ smack_log(skp->smk_known, tkp->smk_known, MAY_DELIVER, rc, &ad);
return rc;
}
* can write the receiver.
*/
if (secid == 0) {
- rc = smk_curacc(tkp, MAY_WRITE, &ad);
- rc = smk_bu_task(p, MAY_WRITE, rc);
+ rc = smk_curacc(tkp, MAY_DELIVER, &ad);
+ rc = smk_bu_task(p, MAY_DELIVER, rc);
return rc;
}
/*
* we can't take privilege into account.
*/
skp = smack_from_secid(secid);
- rc = smk_access(skp, tkp, MAY_WRITE, &ad);
- rc = smk_bu_note("USB signal", skp, tkp, MAY_WRITE, rc);
+ rc = smk_access(skp, tkp, MAY_DELIVER, &ad);
+ rc = smk_bu_note("USB signal", skp, tkp, MAY_DELIVER, rc);
return rc;
}
* It would be curious if the label of the task
* does not match that assigned.
*/
- if (inode->i_op->getxattr == NULL)
- break;
+ if (!(inode->i_opflags & IOP_XATTR))
+ break;
/*
* Get the dentry for xattr.
*/
*/
if (isp->smk_flags & SMK_INODE_CHANGED) {
isp->smk_flags &= ~SMK_INODE_CHANGED;
- rc = inode->i_op->setxattr(dp, inode,
+ rc = __vfs_setxattr(dp, inode,
XATTR_NAME_SMACKTRANSMUTE,
TRANS_TRUE, TRANS_TRUE_SIZE,
0);
} else {
- rc = inode->i_op->getxattr(dp, inode,
+ rc = __vfs_getxattr(dp, inode,
XATTR_NAME_SMACKTRANSMUTE, trattr,
TRANS_TRUE_SIZE);
if (rc >= 0 && strncmp(trattr, TRANS_TRUE,