#ifdef HAVE_UIDGID_HEADER
# include <linux/uidgid.h>
#endif
-#include <lustre/ll_fiemap.h>
-#include <uapi/linux/lustre_ioctl.h>
+#include <uapi/linux/lustre/lustre_ioctl.h>
#include <lustre_swab.h>
#include "cl_object.h"
static int ll_lease_close(struct obd_client_handle *och, struct inode *inode,
bool *lease_broken);
-static enum llioc_iter
-ll_iocontrol_call(struct inode *inode, struct file *file,
- unsigned int cmd, unsigned long arg, int *rcp);
-
static struct ll_file_data *ll_file_data_get(void)
{
struct ll_file_data *fd;
cl_object_attr_unlock(obj);
if (rc != 0)
- GOTO(out_size_unlock, rc);
+ GOTO(out_size_unlock, rc = (rc == -ENODATA ? 0 : rc));
if (atime < attr->cat_atime)
atime = attr->cat_atime;
static void ll_io_init(struct cl_io *io, struct file *file, enum cl_io_type iot)
{
struct inode *inode = file_inode(file);
+ struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
memset(&io->u.ci_rw.rw_iter, 0, sizeof(io->u.ci_rw.rw_iter));
init_sync_kiocb(&io->u.ci_rw.rw_iocb, file);
io->u.ci_rw.rw_file = file;
io->u.ci_rw.rw_ptask = ll_file_io_ptask;
io->u.ci_rw.rw_nonblock = !!(file->f_flags & O_NONBLOCK);
+ io->ci_lock_no_expand = fd->ll_lock_no_expand;
+
if (iot == CIT_WRITE) {
io->u.ci_rw.rw_append = !!(file->f_flags & O_APPEND);
io->u.ci_rw.rw_sync = !!(file->f_flags & O_SYNC ||
(struct lov_user_md_v3 *)lmm);
if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
- ((struct lov_user_md_v3 *)lmm)->lmm_objects,
- stripe_count);
+ ((struct lov_user_md_v3 *)lmm)->lmm_objects,
+ stripe_count);
} else if (lmm->lmm_magic ==
cpu_to_le32(LOV_MAGIC_COMP_V1)) {
lustre_swab_lov_comp_md_v1(
(struct lov_comp_md_v1 *)lmm);
}
- }
+ }
out:
- *lmmp = lmm;
- *lmm_size = lmmsize;
- *request = req;
- return rc;
+ *lmmp = lmm;
+ *lmm_size = lmmsize;
+ *request = req;
+ return rc;
}
static int ll_lov_setea(struct inode *inode, struct file *file,
RETURN(rc);
}
+static enum cl_lock_mode cl_mode_user_to_kernel(enum lock_mode_user mode)
+{
+ switch (mode) {
+ case MODE_READ_USER:
+ return CLM_READ;
+ case MODE_WRITE_USER:
+ return CLM_WRITE;
+ default:
+ return -EINVAL;
+ }
+}
+
+static const char *const user_lockname[] = LOCK_MODE_NAMES;
+
+/* Used to allow the upper layers of the client to request an LDLM lock
+ * without doing an actual read or write.
+ *
+ * Used for ladvise lockahead to manually request specific locks.
+ *
+ * \param[in] file file this ladvise lock request is on
+ * \param[in] ladvise ladvise struct describing this lock request
+ *
+ * \retval 0 success, no detailed result available (sync requests
+ * and requests sent to the server [not handled locally]
+ * cannot return detailed results)
+ * \retval LLA_RESULT_{SAME,DIFFERENT} - detailed result of the lock request,
+ * see definitions for details.
+ * \retval negative negative errno on error
+ */
+int ll_file_lock_ahead(struct file *file, struct llapi_lu_ladvise *ladvise)
+{
+ struct lu_env *env = NULL;
+ struct cl_io *io = NULL;
+ struct cl_lock *lock = NULL;
+ struct cl_lock_descr *descr = NULL;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+ enum cl_lock_mode cl_mode;
+ off_t start = ladvise->lla_start;
+ off_t end = ladvise->lla_end;
+ int result;
+ __u16 refcheck;
+
+ ENTRY;
+
+ CDEBUG(D_VFSTRACE, "Lock request: file=%.*s, inode=%p, mode=%s "
+ "start=%llu, end=%llu\n", dentry->d_name.len,
+ dentry->d_name.name, dentry->d_inode,
+ user_lockname[ladvise->lla_lockahead_mode], (__u64) start,
+ (__u64) end);
+
+ cl_mode = cl_mode_user_to_kernel(ladvise->lla_lockahead_mode);
+ if (cl_mode < 0)
+ GOTO(out, result = cl_mode);
+
+ /* Get IO environment */
+ result = cl_io_get(inode, &env, &io, &refcheck);
+ if (result <= 0)
+ GOTO(out, result);
+
+ result = cl_io_init(env, io, CIT_MISC, io->ci_obj);
+ if (result > 0) {
+ /*
+ * nothing to do for this io. This currently happens when
+ * stripe sub-object's are not yet created.
+ */
+ result = io->ci_result;
+ } else if (result == 0) {
+ lock = vvp_env_lock(env);
+ descr = &lock->cll_descr;
+
+ descr->cld_obj = io->ci_obj;
+ /* Convert byte offsets to pages */
+ descr->cld_start = cl_index(io->ci_obj, start);
+ descr->cld_end = cl_index(io->ci_obj, end);
+ descr->cld_mode = cl_mode;
+ /* CEF_MUST is used because we do not want to convert a
+ * lockahead request to a lockless lock */
+ descr->cld_enq_flags = CEF_MUST | CEF_LOCK_NO_EXPAND |
+ CEF_NONBLOCK;
+
+ if (ladvise->lla_peradvice_flags & LF_ASYNC)
+ descr->cld_enq_flags |= CEF_SPECULATIVE;
+
+ result = cl_lock_request(env, io, lock);
+
+ /* On success, we need to release the lock */
+ if (result >= 0)
+ cl_lock_release(env, lock);
+ }
+ cl_io_fini(env, io);
+ cl_env_put(env, &refcheck);
+
+ /* -ECANCELED indicates a matching lock with a different extent
+ * was already present, and -EEXIST indicates a matching lock
+ * on exactly the same extent was already present.
+ * We convert them to positive values for userspace to make
+ * recognizing true errors easier.
+ * Note we can only return these detailed results on async requests,
+ * as sync requests look the same as i/o requests for locking. */
+ if (result == -ECANCELED)
+ result = LLA_RESULT_DIFFERENT;
+ else if (result == -EEXIST)
+ result = LLA_RESULT_SAME;
+
+out:
+ RETURN(result);
+}
+static const char *const ladvise_names[] = LU_LADVISE_NAMES;
+
+static int ll_ladvise_sanity(struct inode *inode,
+ struct llapi_lu_ladvise *ladvise)
+{
+ enum lu_ladvise_type advice = ladvise->lla_advice;
+ /* Note the peradvice flags is a 32 bit field, so per advice flags must
+ * be in the first 32 bits of enum ladvise_flags */
+ __u32 flags = ladvise->lla_peradvice_flags;
+ /* 3 lines at 80 characters per line, should be plenty */
+ int rc = 0;
+
+ if (advice > LU_LADVISE_MAX || advice == LU_LADVISE_INVALID) {
+ rc = -EINVAL;
+ CDEBUG(D_VFSTRACE, "%s: advice with value '%d' not recognized,"
+ "last supported advice is %s (value '%d'): rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), advice,
+ ladvise_names[LU_LADVISE_MAX-1], LU_LADVISE_MAX-1, rc);
+ GOTO(out, rc);
+ }
+
+ /* Per-advice checks */
+ switch (advice) {
+ case LU_LADVISE_LOCKNOEXPAND:
+ if (flags & ~LF_LOCKNOEXPAND_MASK) {
+ rc = -EINVAL;
+ CDEBUG(D_VFSTRACE, "%s: Invalid flags (%x) for %s: "
+ "rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), flags,
+ ladvise_names[advice], rc);
+ GOTO(out, rc);
+ }
+ break;
+ case LU_LADVISE_LOCKAHEAD:
+ /* Currently only READ and WRITE modes can be requested */
+ if (ladvise->lla_lockahead_mode >= MODE_MAX_USER ||
+ ladvise->lla_lockahead_mode == 0) {
+ rc = -EINVAL;
+ CDEBUG(D_VFSTRACE, "%s: Invalid mode (%d) for %s: "
+ "rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0),
+ ladvise->lla_lockahead_mode,
+ ladvise_names[advice], rc);
+ GOTO(out, rc);
+ }
+ case LU_LADVISE_WILLREAD:
+ case LU_LADVISE_DONTNEED:
+ default:
+ /* Note fall through above - These checks apply to all advices
+ * except LOCKNOEXPAND */
+ if (flags & ~LF_DEFAULT_MASK) {
+ rc = -EINVAL;
+ CDEBUG(D_VFSTRACE, "%s: Invalid flags (%x) for %s: "
+ "rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), flags,
+ ladvise_names[advice], rc);
+ GOTO(out, rc);
+ }
+ if (ladvise->lla_start >= ladvise->lla_end) {
+ rc = -EINVAL;
+ CDEBUG(D_VFSTRACE, "%s: Invalid range (%llu to %llu) "
+ "for %s: rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0),
+ ladvise->lla_start, ladvise->lla_end,
+ ladvise_names[advice], rc);
+ GOTO(out, rc);
+ }
+ break;
+ }
+
+out:
+ return rc;
+}
+#undef ERRSIZE
+
/*
* Give file access advices
*
RETURN(rc);
}
+static int ll_lock_noexpand(struct file *file, int flags)
+{
+ struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+
+ fd->ll_lock_no_expand = !(flags & LF_UNSET);
+
+ return 0;
+}
+
int ll_ioctl_fsgetxattr(struct inode *inode, unsigned int cmd,
unsigned long arg)
{
sizeof(fsxattr)))
RETURN(-EFAULT);
+ fsxattr.fsx_xflags = ll_inode_to_ext_flags(inode->i_flags);
fsxattr.fsx_projid = ll_i2info(inode)->lli_projid;
if (copy_to_user((struct fsxattr __user *)arg,
&fsxattr, sizeof(fsxattr)))
struct ptlrpc_request *req = NULL;
int rc = 0;
struct fsxattr fsxattr;
+ struct cl_object *obj;
/* only root could change project ID */
if (!cfs_capable(CFS_CAP_SYS_ADMIN))
sizeof(fsxattr)))
GOTO(out_fsxattr1, rc = -EFAULT);
+ op_data->op_attr_flags = fsxattr.fsx_xflags;
op_data->op_projid = fsxattr.fsx_projid;
- op_data->op_attr.ia_valid |= MDS_ATTR_PROJID;
+ op_data->op_attr.ia_valid |= (MDS_ATTR_PROJID | ATTR_ATTR_FLAG);
rc = md_setattr(ll_i2sbi(inode)->ll_md_exp, op_data, NULL,
0, &req);
ptlrpc_req_finished(req);
+ obj = ll_i2info(inode)->lli_clob;
+ if (obj) {
+ struct iattr *attr;
+
+ inode->i_flags = ll_ext_to_inode_flags(fsxattr.fsx_xflags);
+ OBD_ALLOC_PTR(attr);
+ if (attr == NULL)
+ GOTO(out_fsxattr1, rc = -ENOMEM);
+ attr->ia_valid = ATTR_ATTR_FLAG;
+ rc = cl_setattr_ost(obj, attr, fsxattr.fsx_xflags);
+
+ OBD_FREE_PTR(attr);
+ }
out_fsxattr1:
ll_finish_md_op_data(op_data);
RETURN(rc);
RETURN(ll_file_futimes_3(file, &lfu));
}
case LL_IOC_LADVISE: {
- struct llapi_ladvise_hdr *ladvise_hdr;
+ struct llapi_ladvise_hdr *k_ladvise_hdr;
+ struct llapi_ladvise_hdr __user *u_ladvise_hdr;
int i;
int num_advise;
- int alloc_size = sizeof(*ladvise_hdr);
+ int alloc_size = sizeof(*k_ladvise_hdr);
rc = 0;
- OBD_ALLOC_PTR(ladvise_hdr);
- if (ladvise_hdr == NULL)
+ u_ladvise_hdr = (void __user *)arg;
+ OBD_ALLOC_PTR(k_ladvise_hdr);
+ if (k_ladvise_hdr == NULL)
RETURN(-ENOMEM);
- if (copy_from_user(ladvise_hdr,
- (const struct llapi_ladvise_hdr __user *)arg,
- alloc_size))
+ if (copy_from_user(k_ladvise_hdr, u_ladvise_hdr, alloc_size))
GOTO(out_ladvise, rc = -EFAULT);
- if (ladvise_hdr->lah_magic != LADVISE_MAGIC ||
- ladvise_hdr->lah_count < 1)
+ if (k_ladvise_hdr->lah_magic != LADVISE_MAGIC ||
+ k_ladvise_hdr->lah_count < 1)
GOTO(out_ladvise, rc = -EINVAL);
- num_advise = ladvise_hdr->lah_count;
+ num_advise = k_ladvise_hdr->lah_count;
if (num_advise >= LAH_COUNT_MAX)
GOTO(out_ladvise, rc = -EFBIG);
- OBD_FREE_PTR(ladvise_hdr);
- alloc_size = offsetof(typeof(*ladvise_hdr),
+ OBD_FREE_PTR(k_ladvise_hdr);
+ alloc_size = offsetof(typeof(*k_ladvise_hdr),
lah_advise[num_advise]);
- OBD_ALLOC(ladvise_hdr, alloc_size);
- if (ladvise_hdr == NULL)
+ OBD_ALLOC(k_ladvise_hdr, alloc_size);
+ if (k_ladvise_hdr == NULL)
RETURN(-ENOMEM);
/*
* TODO: submit multiple advices to one server in a single RPC
*/
- if (copy_from_user(ladvise_hdr,
- (const struct llapi_ladvise_hdr __user *)arg,
- alloc_size))
+ if (copy_from_user(k_ladvise_hdr, u_ladvise_hdr, alloc_size))
GOTO(out_ladvise, rc = -EFAULT);
for (i = 0; i < num_advise; i++) {
- rc = ll_ladvise(inode, file, ladvise_hdr->lah_flags,
- &ladvise_hdr->lah_advise[i]);
+ struct llapi_lu_ladvise *k_ladvise =
+ &k_ladvise_hdr->lah_advise[i];
+ struct llapi_lu_ladvise __user *u_ladvise =
+ &u_ladvise_hdr->lah_advise[i];
+
+ rc = ll_ladvise_sanity(inode, k_ladvise);
if (rc)
+ GOTO(out_ladvise, rc);
+
+ switch (k_ladvise->lla_advice) {
+ case LU_LADVISE_LOCKNOEXPAND:
+ rc = ll_lock_noexpand(file,
+ k_ladvise->lla_peradvice_flags);
+ GOTO(out_ladvise, rc);
+ case LU_LADVISE_LOCKAHEAD:
+
+ rc = ll_file_lock_ahead(file, k_ladvise);
+
+ if (rc < 0)
+ GOTO(out_ladvise, rc);
+
+ if (put_user(rc,
+ &u_ladvise->lla_lockahead_result))
+ GOTO(out_ladvise, rc = -EFAULT);
break;
+ default:
+ rc = ll_ladvise(inode, file,
+ k_ladvise_hdr->lah_flags,
+ k_ladvise);
+ if (rc)
+ GOTO(out_ladvise, rc);
+ break;
+ }
+
}
out_ladvise:
- OBD_FREE(ladvise_hdr, alloc_size);
+ OBD_FREE(k_ladvise_hdr, alloc_size);
RETURN(rc);
}
case LL_IOC_FSGETXATTR:
RETURN(ll_ioctl_fsgetxattr(inode, cmd, arg));
case LL_IOC_FSSETXATTR:
RETURN(ll_ioctl_fssetxattr(inode, cmd, arg));
- default: {
- int err;
-
- if (LLIOC_STOP ==
- ll_iocontrol_call(inode, file, cmd, arg, &err))
- RETURN(err);
-
+ case BLKSSZGET:
+ RETURN(put_user(PAGE_SIZE, (int __user *)arg));
+ default:
RETURN(obd_iocontrol(cmd, ll_i2dtexp(inode), 0, NULL,
(void __user *)arg));
}
- }
}
#ifndef HAVE_FILE_LLSEEK_SIZE
#endif
};
-/* dynamic ioctl number support routins */
-static struct llioc_ctl_data {
- struct rw_semaphore ioc_sem;
- struct list_head ioc_head;
-} llioc = {
- __RWSEM_INITIALIZER(llioc.ioc_sem),
- LIST_HEAD_INIT(llioc.ioc_head)
-};
-
-
-struct llioc_data {
- struct list_head iocd_list;
- unsigned int iocd_size;
- llioc_callback_t iocd_cb;
- unsigned int iocd_count;
- unsigned int iocd_cmd[0];
-};
-
-void *ll_iocontrol_register(llioc_callback_t cb, int count, unsigned int *cmd)
-{
- unsigned int size;
- struct llioc_data *in_data = NULL;
- ENTRY;
-
- if (cb == NULL || cmd == NULL ||
- count > LLIOC_MAX_CMD || count < 0)
- RETURN(NULL);
-
- size = sizeof(*in_data) + count * sizeof(unsigned int);
- OBD_ALLOC(in_data, size);
- if (in_data == NULL)
- RETURN(NULL);
-
- memset(in_data, 0, sizeof(*in_data));
- in_data->iocd_size = size;
- in_data->iocd_cb = cb;
- in_data->iocd_count = count;
- memcpy(in_data->iocd_cmd, cmd, sizeof(unsigned int) * count);
-
- down_write(&llioc.ioc_sem);
- list_add_tail(&in_data->iocd_list, &llioc.ioc_head);
- up_write(&llioc.ioc_sem);
-
- RETURN(in_data);
-}
-
-void ll_iocontrol_unregister(void *magic)
-{
- struct llioc_data *tmp;
-
- if (magic == NULL)
- return;
-
- down_write(&llioc.ioc_sem);
- list_for_each_entry(tmp, &llioc.ioc_head, iocd_list) {
- if (tmp == magic) {
- unsigned int size = tmp->iocd_size;
-
- list_del(&tmp->iocd_list);
- up_write(&llioc.ioc_sem);
-
- OBD_FREE(tmp, size);
- return;
- }
- }
- up_write(&llioc.ioc_sem);
-
- CWARN("didn't find iocontrol register block with magic: %p\n", magic);
-}
-
-EXPORT_SYMBOL(ll_iocontrol_register);
-EXPORT_SYMBOL(ll_iocontrol_unregister);
-
-static enum llioc_iter
-ll_iocontrol_call(struct inode *inode, struct file *file,
- unsigned int cmd, unsigned long arg, int *rcp)
-{
- enum llioc_iter ret = LLIOC_CONT;
- struct llioc_data *data;
- int rc = -EINVAL, i;
-
- down_read(&llioc.ioc_sem);
- list_for_each_entry(data, &llioc.ioc_head, iocd_list) {
- for (i = 0; i < data->iocd_count; i++) {
- if (cmd != data->iocd_cmd[i])
- continue;
-
- ret = data->iocd_cb(inode, file, cmd, arg, data, &rc);
- break;
- }
-
- if (ret == LLIOC_STOP)
- break;
- }
- up_read(&llioc.ioc_sem);
-
- if (rcp)
- *rcp = rc;
- return ret;
-}
-
int ll_layout_conf(struct inode *inode, const struct cl_object_conf *conf)
{
struct ll_inode_info *lli = ll_i2info(inode);
git://git.whamcloud.com / fs / lustre-release.git / blobdiff