#include <lustre/lustre_idl.h>
#include <obd_support.h>
#include <obd_class.h>
+#include <lustre_ioctl.h>
#include <lustre_lib.h>
-#include <lustre/lustre_idl.h>
#include <lustre_lite.h>
#include <lustre_dlm.h>
#include <lustre_fid.h>
* After client receives reply, several pages will be integrated into dir page
* in PAGE_CACHE_SIZE (if PAGE_CACHE_SIZE greater than LU_PAGE_SIZE), and the
* lu_dirpage for this integrated page will be adjusted. See
- * lmv_adjust_dirpages().
+ * mdc_adjust_dirpages().
*
*/
-/**
- * The following three APIs will be used by llite to iterate directory
- * entries from MDC dir page caches.
- *
- * ll_dir_entry_start(next) will lookup(return) entry by op_hash_offset.
- * To avoid extra memory allocation, the @entry will be pointed to
- * the dir entries in MDC page directly, so these pages can not be released
- * until the entry has been accessed in ll_readdir(or statahead).
- *
- * The iterate process will be
- *
- * ll_dir_entry_start: locate the page in MDC, and return the first entry.
- * hold the page.
- *
- * ll_dir_entry_next: return the next entry in the current page, if it reaches
- * to the end, release current page.
- *
- * ll_dir_entry_end: release the last page.
- **/
-struct lu_dirent *ll_dir_entry_start(struct inode *dir,
- struct md_op_data *op_data,
- struct page **ppage)
+struct page *ll_get_dir_page(struct inode *dir, struct md_op_data *op_data,
+ __u64 offset, struct ll_dir_chain *chain)
{
- struct lu_dirent *entry;
- struct md_callback cb_op;
- int rc;
+ struct md_callback cb_op;
+ struct page *page;
+ int rc;
- LASSERT(*ppage == NULL);
cb_op.md_blocking_ast = ll_md_blocking_ast;
- rc = md_read_entry(ll_i2mdexp(dir), op_data, &cb_op, &entry, ppage);
+ rc = md_read_page(ll_i2mdexp(dir), op_data, &cb_op, offset, &page);
if (rc != 0)
- entry = ERR_PTR(rc);
- return entry;
+ return ERR_PTR(rc);
+
+ return page;
}
-struct lu_dirent *ll_dir_entry_next(struct inode *dir,
- struct md_op_data *op_data,
- struct lu_dirent *ent,
- struct page **ppage)
+void ll_release_page(struct inode *inode, struct page *page,
+ bool remove)
{
- struct lu_dirent *entry;
- struct md_callback cb_op;
- int rc;
+ kunmap(page);
+
+ /* Always remove the page for striped dir, because the page is
+ * built from temporarily in LMV layer */
+ if (inode != NULL && S_ISDIR(inode->i_mode) &&
+ ll_i2info(inode)->lli_lsm_md != NULL) {
+ __free_page(page);
+ return;
+ }
- LASSERT(*ppage != NULL);
- cb_op.md_blocking_ast = ll_md_blocking_ast;
- op_data->op_hash_offset = le64_to_cpu(ent->lde_hash);
- kunmap(*ppage);
- page_cache_release(*ppage);
- *ppage = NULL;
- rc = md_read_entry(ll_i2mdexp(dir), op_data, &cb_op, &entry, ppage);
- if (rc != 0)
- entry = ERR_PTR(rc);
- return entry;
+ if (remove) {
+ lock_page(page);
+ if (likely(page->mapping != NULL))
+ truncate_complete_page(page->mapping, page);
+ unlock_page(page);
+ }
+ page_cache_release(page);
}
-int ll_dir_read(struct inode *inode, struct md_op_data *op_data,
+#ifdef HAVE_DIR_CONTEXT
+int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
+ struct dir_context *ctx)
+{
+#else
+int ll_dir_read(struct inode *inode, __u64 *ppos, struct md_op_data *op_data,
void *cookie, filldir_t filldir)
{
- struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct ll_dir_chain chain;
- struct lu_dirent *ent;
- int api32 = ll_need_32bit_api(sbi);
- int hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH;
- int done = 0;
- int rc = 0;
- __u64 hash = MDS_DIR_END_OFF;
- __u64 last_hash = MDS_DIR_END_OFF;
- struct page *page = NULL;
+#endif
+ struct ll_sb_info *sbi = ll_i2sbi(inode);
+ __u64 pos = *ppos;
+ bool is_api32 = ll_need_32bit_api(sbi);
+ bool is_hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH;
+ struct page *page;
+ struct ll_dir_chain chain;
+ bool done = false;
+ int rc = 0;
ENTRY;
- ll_dir_chain_init(&chain);
- for (ent = ll_dir_entry_start(inode, op_data, &page);
- ent != NULL && !IS_ERR(ent) && !done;
- ent = ll_dir_entry_next(inode, op_data, ent, &page)) {
- __u16 type;
- int namelen;
- struct lu_fid fid;
- __u64 lhash;
- __u64 ino;
-
- hash = le64_to_cpu(ent->lde_hash);
- if (hash < op_data->op_hash_offset)
- /*
- * Skip until we find target hash
- * value.
- */
- continue;
- namelen = le16_to_cpu(ent->lde_namelen);
- if (namelen == 0)
- /*
- * Skip dummy record.
- */
- continue;
+ ll_dir_chain_init(&chain);
- if (api32 && hash64)
- lhash = hash >> 32;
- else
- lhash = hash;
- fid_le_to_cpu(&fid, &ent->lde_fid);
- ino = cl_fid_build_ino(&fid, api32);
- type = ll_dirent_type_get(ent);
- /* For 'll_nfs_get_name_filldir()', it will try
- * to access the 'ent' through its 'lde_name',
- * so the parameter 'name' for 'filldir()' must
- * be part of the 'ent'. */
- done = filldir(cookie, ent->lde_name, namelen, lhash,
- ino, type);
- if (done) {
- if (op_data->op_hash_offset != MDS_DIR_END_OFF)
- op_data->op_hash_offset = last_hash;
+ page = ll_get_dir_page(inode, op_data, pos, &chain);
+
+ while (rc == 0 && !done) {
+ struct lu_dirpage *dp;
+ struct lu_dirent *ent;
+ __u64 hash;
+ __u64 next;
+
+ if (IS_ERR(page)) {
+ rc = PTR_ERR(page);
break;
- } else {
- last_hash = hash;
}
- }
- if (IS_ERR(ent))
- rc = PTR_ERR(ent);
+ hash = MDS_DIR_END_OFF;
+ dp = page_address(page);
+ for (ent = lu_dirent_start(dp); ent != NULL && !done;
+ ent = lu_dirent_next(ent)) {
+ __u16 type;
+ int namelen;
+ struct lu_fid fid;
+ __u64 lhash;
+ __u64 ino;
+
+ hash = le64_to_cpu(ent->lde_hash);
+ if (hash < pos)
+ /*
+ * Skip until we find target hash
+ * value.
+ */
+ continue;
+
+ namelen = le16_to_cpu(ent->lde_namelen);
+ if (namelen == 0)
+ /*
+ * Skip dummy record.
+ */
+ continue;
+
+ if (is_api32 && is_hash64)
+ lhash = hash >> 32;
+ else
+ lhash = hash;
+ fid_le_to_cpu(&fid, &ent->lde_fid);
+ ino = cl_fid_build_ino(&fid, is_api32);
+ type = ll_dirent_type_get(ent);
+ /* For 'll_nfs_get_name_filldir()', it will try
+ * to access the 'ent' through its 'lde_name',
+ * so the parameter 'name' for 'filldir()' must
+ * be part of the 'ent'. */
+#ifdef HAVE_DIR_CONTEXT
+ ctx->pos = lhash;
+ done = !dir_emit(ctx, ent->lde_name, namelen, ino,
+ type);
+#else
+ done = filldir(cookie, ent->lde_name, namelen, lhash,
+ ino, type);
+#endif
+ }
- if (page != NULL) {
- kunmap(page);
- page_cache_release(page);
- }
+ if (done) {
+ pos = hash;
+ ll_release_page(inode, page, false);
+ break;
+ }
+ next = le64_to_cpu(dp->ldp_hash_end);
+ pos = next;
+ if (pos == MDS_DIR_END_OFF) {
+ /*
+ * End of directory reached.
+ */
+ done = 1;
+ ll_release_page(inode, page, false);
+ } else {
+ /*
+ * Normal case: continue to the next
+ * page.
+ */
+ ll_release_page(inode, page,
+ le32_to_cpu(dp->ldp_flags) &
+ LDF_COLLIDE);
+ next = pos;
+ page = ll_get_dir_page(inode, op_data, pos,
+ &chain);
+ }
+ }
+#ifdef HAVE_DIR_CONTEXT
+ ctx->pos = pos;
+#else
+ *ppos = pos;
+#endif
ll_dir_chain_fini(&chain);
RETURN(rc);
}
+#ifdef HAVE_DIR_CONTEXT
+static int ll_iterate(struct file *filp, struct dir_context *ctx)
+#else
static int ll_readdir(struct file *filp, void *cookie, filldir_t filldir)
+#endif
{
struct inode *inode = filp->f_dentry->d_inode;
struct ll_file_data *lfd = LUSTRE_FPRIVATE(filp);
struct ll_sb_info *sbi = ll_i2sbi(inode);
- __u64 pos = lfd->lfd_pos;
int hash64 = sbi->ll_flags & LL_SBI_64BIT_HASH;
int api32 = ll_need_32bit_api(sbi);
struct md_op_data *op_data;
+ __u64 pos;
int rc;
-#ifdef HAVE_TOUCH_ATIME_1ARG
- struct path path;
-#endif
ENTRY;
if (lfd != NULL)
if (IS_ERR(op_data))
GOTO(out, rc = PTR_ERR(op_data));
- op_data->op_hash_offset = pos;
- op_data->op_max_pages = sbi->ll_md_brw_size >> PAGE_CACHE_SHIFT;
- rc = ll_dir_read(inode, op_data, cookie, filldir);
+ if (unlikely(op_data->op_mea1 != NULL)) {
+ /* This is only needed for striped dir to fill ..,
+ * see lmv_read_entry */
+ if (filp->f_dentry->d_parent != NULL &&
+ filp->f_dentry->d_parent->d_inode != NULL) {
+ __u64 ibits = MDS_INODELOCK_UPDATE;
+ struct inode *parent =
+ filp->f_dentry->d_parent->d_inode;
+
+ if (ll_have_md_lock(parent, &ibits, LCK_MINMODE))
+ op_data->op_fid3 = *ll_inode2fid(parent);
+ }
+
+ /* If it can not find in cache, do lookup .. on the master
+ * object */
+ if (fid_is_zero(&op_data->op_fid3)) {
+ rc = ll_dir_get_parent_fid(inode, &op_data->op_fid3);
+ if (rc != 0) {
+ ll_finish_md_op_data(op_data);
+ RETURN(rc);
+ }
+ }
+ }
+ op_data->op_max_pages = sbi->ll_md_brw_pages;
+#ifdef HAVE_DIR_CONTEXT
+ ctx->pos = pos;
+ rc = ll_dir_read(inode, &pos, op_data, ctx);
+ pos = ctx->pos;
+#else
+ rc = ll_dir_read(inode, &pos, op_data, cookie, filldir);
+#endif
if (lfd != NULL)
- lfd->lfd_pos = op_data->op_hash_offset;
+ lfd->lfd_pos = pos;
if (pos == MDS_DIR_END_OFF) {
if (api32)
- filp->f_pos = LL_DIR_END_OFF_32BIT;
+ pos = LL_DIR_END_OFF_32BIT;
else
- filp->f_pos = LL_DIR_END_OFF;
+ pos = LL_DIR_END_OFF;
} else {
if (api32 && hash64)
- filp->f_pos = op_data->op_hash_offset >> 32;
- else
- filp->f_pos = op_data->op_hash_offset;
+ pos = pos >> 32;
}
-
- ll_finish_md_op_data(op_data);
- filp->f_version = inode->i_version;
-#ifdef HAVE_TOUCH_ATIME_1ARG
-#ifdef HAVE_F_PATH_MNT
- path.mnt = filp->f_path.mnt;
+#ifdef HAVE_DIR_CONTEXT
+ ctx->pos = pos;
#else
- path.mnt = filp->f_vfsmnt;
-#endif
- path.dentry = filp->f_dentry;
- touch_atime(&path);
-#else
- touch_atime(filp->f_vfsmnt, filp->f_dentry);
+ filp->f_pos = pos;
#endif
+ ll_finish_md_op_data(op_data);
+ filp->f_version = inode->i_version;
out:
if (!rc)
RETURN(rc);
}
-int ll_send_mgc_param(struct obd_export *mgc, char *string)
+static int ll_send_mgc_param(struct obd_export *mgc, char *string)
{
struct mgs_send_param *msp;
int rc = 0;
if (!msp)
return -ENOMEM;
- strncpy(msp->mgs_param, string, MGS_PARAM_MAXLEN);
+ strlcpy(msp->mgs_param, string, sizeof(msp->mgs_param));
rc = obd_set_info_async(NULL, mgc, sizeof(KEY_SET_INFO), KEY_SET_INFO,
sizeof(struct mgs_send_param), msp, NULL);
if (rc)
return rc;
}
-int ll_dir_setdirstripe(struct inode *dir, struct lmv_user_md *lump,
- char *filename)
+/**
+ * Create striped directory with specified stripe(@lump)
+ *
+ * param[in]parent the parent of the directory.
+ * param[in]lump the specified stripes.
+ * param[in]dirname the name of the directory.
+ * param[in]mode the specified mode of the directory.
+ *
+ * retval =0 if striped directory is being created successfully.
+ * <0 if the creation is failed.
+ */
+static int ll_dir_setdirstripe(struct inode *parent, struct lmv_user_md *lump,
+ const char *dirname, umode_t mode)
{
struct ptlrpc_request *request = NULL;
struct md_op_data *op_data;
- struct ll_sb_info *sbi = ll_i2sbi(dir);
- int mode;
+ struct ll_sb_info *sbi = ll_i2sbi(parent);
int err;
-
ENTRY;
- mode = (0755 & (S_IRWXUGO|S_ISVTX) & ~current->fs->umask) | S_IFDIR;
- op_data = ll_prep_md_op_data(NULL, dir, NULL, filename,
- strlen(filename), mode, LUSTRE_OPC_MKDIR,
+ if (unlikely(lump->lum_magic != LMV_USER_MAGIC))
+ RETURN(-EINVAL);
+
+ CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p) name %s"
+ "stripe_offset %d, stripe_count: %u\n",
+ PFID(ll_inode2fid(parent)), parent, dirname,
+ (int)lump->lum_stripe_offset, lump->lum_stripe_count);
+
+ if (lump->lum_magic != cpu_to_le32(LMV_USER_MAGIC))
+ lustre_swab_lmv_user_md(lump);
+
+ if (!IS_POSIXACL(parent) || !exp_connect_umask(ll_i2mdexp(parent)))
+ mode &= ~current_umask();
+ mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, dirname,
+ strlen(dirname), mode, LUSTRE_OPC_MKDIR,
lump);
if (IS_ERR(op_data))
GOTO(err_exit, err = PTR_ERR(op_data));
op_data->op_cli_flags |= CLI_SET_MEA;
err = md_create(sbi->ll_md_exp, op_data, lump, sizeof(*lump), mode,
- current_fsuid(), current_fsgid(),
+ from_kuid(&init_user_ns, current_fsuid()),
+ from_kgid(&init_user_ns, current_fsgid()),
cfs_curproc_cap_pack(), 0, &request);
ll_finish_md_op_data(op_data);
if (err)
lum_size = sizeof(struct lov_user_md_v3);
break;
}
+ case LMV_USER_MAGIC: {
+ if (lump->lmm_magic != cpu_to_le32(LMV_USER_MAGIC))
+ lustre_swab_lmv_user_md(
+ (struct lmv_user_md *)lump);
+ lum_size = sizeof(struct lmv_user_md);
+ break;
+ }
default: {
CDEBUG(D_IOCTL, "bad userland LOV MAGIC:"
" %#08x != %#08x nor %#08x\n",
if (IS_ERR(op_data))
RETURN(PTR_ERR(op_data));
- if (lump != NULL && lump->lmm_magic == cpu_to_le32(LMV_USER_MAGIC))
- op_data->op_cli_flags |= CLI_SET_MEA;
-
/* swabbing is done in lov_setstripe() on server side */
rc = md_setattr(sbi->ll_md_exp, op_data, lump, lum_size,
NULL, 0, &req, NULL);
RETURN(rc);
}
-int ll_dir_getstripe(struct inode *inode, struct lov_mds_md **lmmp,
- int *lmm_size, struct ptlrpc_request **request)
+/**
+ * This function will be used to get default LOV/LMV/Default LMV
+ * @valid will be used to indicate which stripe it will retrieve
+ * OBD_MD_MEA LMV stripe EA
+ * OBD_MD_DEFAULT_MEA Default LMV stripe EA
+ * otherwise Default LOV EA.
+ * Each time, it can only retrieve 1 stripe EA
+ **/
+int ll_dir_getstripe(struct inode *inode, void **plmm, int *plmm_size,
+ struct ptlrpc_request **request, obd_valid valid)
{
- struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct mdt_body *body;
- struct lov_mds_md *lmm = NULL;
- struct ptlrpc_request *req = NULL;
- int rc, lmmsize;
- struct md_op_data *op_data;
+ struct ll_sb_info *sbi = ll_i2sbi(inode);
+ struct mdt_body *body;
+ struct lov_mds_md *lmm = NULL;
+ struct ptlrpc_request *req = NULL;
+ int rc, lmm_size;
+ struct md_op_data *op_data;
+ ENTRY;
- rc = ll_get_max_mdsize(sbi, &lmmsize);
- if (rc)
- RETURN(rc);
+ rc = ll_get_default_mdsize(sbi, &lmm_size);
+ if (rc)
+ RETURN(rc);
- op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL,
- 0, lmmsize, LUSTRE_OPC_ANY,
- NULL);
- if (IS_ERR(op_data))
- RETURN(PTR_ERR(op_data));
+ op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL,
+ 0, lmm_size, LUSTRE_OPC_ANY,
+ NULL);
+ if (IS_ERR(op_data))
+ RETURN(PTR_ERR(op_data));
- op_data->op_valid = OBD_MD_FLEASIZE | OBD_MD_FLDIREA;
- rc = md_getattr(sbi->ll_md_exp, op_data, &req);
- ll_finish_md_op_data(op_data);
- if (rc < 0) {
+ op_data->op_valid = valid | OBD_MD_FLEASIZE | OBD_MD_FLDIREA;
+ rc = md_getattr(sbi->ll_md_exp, op_data, &req);
+ ll_finish_md_op_data(op_data);
+ if (rc < 0) {
CDEBUG(D_INFO, "md_getattr failed on inode "
DFID": rc %d\n", PFID(ll_inode2fid(inode)), rc);
- GOTO(out, rc);
- }
+ GOTO(out, rc);
+ }
- body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- LASSERT(body != NULL);
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ LASSERT(body != NULL);
- lmmsize = body->eadatasize;
+ lmm_size = body->mbo_eadatasize;
- if (!(body->valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
- lmmsize == 0) {
- GOTO(out, rc = -ENODATA);
- }
+ if (!(body->mbo_valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
+ lmm_size == 0) {
+ GOTO(out, rc = -ENODATA);
+ }
- lmm = req_capsule_server_sized_get(&req->rq_pill,
- &RMF_MDT_MD, lmmsize);
- LASSERT(lmm != NULL);
-
- /*
- * This is coming from the MDS, so is probably in
- * little endian. We convert it to host endian before
- * passing it to userspace.
- */
- /* We don't swab objects for directories */
- switch (le32_to_cpu(lmm->lmm_magic)) {
- case LOV_MAGIC_V1:
- if (LOV_MAGIC != cpu_to_le32(LOV_MAGIC))
- lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm);
- break;
- case LOV_MAGIC_V3:
- if (LOV_MAGIC != cpu_to_le32(LOV_MAGIC))
- lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
- break;
- default:
- CERROR("unknown magic: %lX\n", (unsigned long)lmm->lmm_magic);
- rc = -EPROTO;
- }
+ lmm = req_capsule_server_sized_get(&req->rq_pill,
+ &RMF_MDT_MD, lmm_size);
+ LASSERT(lmm != NULL);
+
+ /*
+ * This is coming from the MDS, so is probably in
+ * little endian. We convert it to host endian before
+ * passing it to userspace.
+ */
+ /* We don't swab objects for directories */
+ switch (le32_to_cpu(lmm->lmm_magic)) {
+ case LOV_MAGIC_V1:
+ if (LOV_MAGIC != cpu_to_le32(LOV_MAGIC))
+ lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm);
+ break;
+ case LOV_MAGIC_V3:
+ if (LOV_MAGIC != cpu_to_le32(LOV_MAGIC))
+ lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
+ break;
+ case LMV_MAGIC_V1:
+ if (LMV_MAGIC != cpu_to_le32(LMV_MAGIC))
+ lustre_swab_lmv_mds_md((union lmv_mds_md *)lmm);
+ break;
+ case LMV_USER_MAGIC:
+ if (LMV_USER_MAGIC != cpu_to_le32(LMV_USER_MAGIC))
+ lustre_swab_lmv_user_md((struct lmv_user_md *)lmm);
+ break;
+ default:
+ CERROR("unknown magic: %lX\n", (unsigned long)lmm->lmm_magic);
+ rc = -EPROTO;
+ }
out:
- *lmmp = lmm;
- *lmm_size = lmmsize;
- *request = req;
- return rc;
+ *plmm = lmm;
+ *plmm_size = lmm_size;
+ *request = req;
+ return rc;
+}
+
+int ll_get_mdt_idx_by_fid(struct ll_sb_info *sbi, const struct lu_fid *fid)
+{
+ struct md_op_data *op_data;
+ int rc;
+ int mdt_index;
+ ENTRY;
+
+ OBD_ALLOC_PTR(op_data);
+ if (op_data == NULL)
+ RETURN(-ENOMEM);
+
+ op_data->op_flags |= MF_GET_MDT_IDX;
+ op_data->op_fid1 = *fid;
+ rc = md_getattr(sbi->ll_md_exp, op_data, NULL);
+ mdt_index = op_data->op_mds;
+ OBD_FREE_PTR(op_data);
+ if (rc < 0)
+ RETURN(rc);
+
+ RETURN(mdt_index);
}
/*
*/
int ll_get_mdt_idx(struct inode *inode)
{
- struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct md_op_data *op_data;
- int rc, mdtidx;
- ENTRY;
-
- op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0,
- 0, LUSTRE_OPC_ANY, NULL);
- if (IS_ERR(op_data))
- RETURN(PTR_ERR(op_data));
-
- op_data->op_flags |= MF_GET_MDT_IDX;
- rc = md_getattr(sbi->ll_md_exp, op_data, NULL);
- mdtidx = op_data->op_mds;
- ll_finish_md_op_data(op_data);
- if (rc < 0) {
- CDEBUG(D_INFO, "md_getattr_name: %d\n", rc);
- RETURN(rc);
- }
- return mdtidx;
+ return ll_get_mdt_idx_by_fid(ll_i2sbi(inode), ll_inode2fid(inode));
}
/**
RETURN(-EPERM);
break;
case Q_GETQUOTA:
- if (((type == USRQUOTA && current_euid() != id) ||
- (type == GRPQUOTA && !in_egroup_p(id))) &&
+ if (((type == USRQUOTA &&
+ !uid_eq(current_euid(), make_kuid(&init_user_ns, id))) ||
+ (type == GRPQUOTA &&
+ !in_egroup_p(make_kgid(&init_user_ns, id)))) &&
(!cfs_capable(CFS_CAP_SYS_ADMIN) ||
sbi->ll_flags & LL_SBI_RMT_CLIENT))
RETURN(-EPERM);
return 0;
}
case IOC_MDC_LOOKUP: {
- struct ptlrpc_request *request = NULL;
- int namelen, len = 0;
- char *buf = NULL;
- char *filename;
- struct md_op_data *op_data;
-
- rc = obd_ioctl_getdata(&buf, &len, (void *)arg);
- if (rc)
- RETURN(rc);
- data = (void *)buf;
+ int namelen, len = 0;
+ char *buf = NULL;
+ char *filename;
- filename = data->ioc_inlbuf1;
- namelen = strlen(filename);
-
- if (namelen < 1) {
- CDEBUG(D_INFO, "IOC_MDC_LOOKUP missing filename\n");
- GOTO(out_free, rc = -EINVAL);
- }
+ rc = obd_ioctl_getdata(&buf, &len, (void *)arg);
+ if (rc != 0)
+ RETURN(rc);
+ data = (void *)buf;
- op_data = ll_prep_md_op_data(NULL, inode, NULL, filename, namelen,
- 0, LUSTRE_OPC_ANY, NULL);
- if (IS_ERR(op_data))
- GOTO(out_free, rc = PTR_ERR(op_data));
+ filename = data->ioc_inlbuf1;
+ namelen = strlen(filename);
+ if (namelen < 1) {
+ CDEBUG(D_INFO, "IOC_MDC_LOOKUP missing filename\n");
+ GOTO(out_free, rc = -EINVAL);
+ }
- op_data->op_valid = OBD_MD_FLID;
- rc = md_getattr_name(sbi->ll_md_exp, op_data, &request);
- ll_finish_md_op_data(op_data);
- if (rc < 0) {
- CDEBUG(D_INFO, "md_getattr_name: %d\n", rc);
- GOTO(out_free, rc);
- }
- ptlrpc_req_finished(request);
- EXIT;
+ rc = ll_get_fid_by_name(inode, filename, namelen, NULL);
+ if (rc < 0) {
+ CERROR("%s: lookup %.*s failed: rc = %d\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), namelen,
+ filename, rc);
+ GOTO(out_free, rc);
+ }
out_free:
obd_ioctl_freedata(buf, len);
return rc;
char *filename;
int namelen = 0;
int lumlen = 0;
+ umode_t mode;
int len;
int rc;
GOTO(lmv_out_free, rc = -EINVAL);
}
- /**
- * ll_dir_setdirstripe will be used to set dir stripe
- * mdc_create--->mdt_reint_create (with dirstripe)
- */
- rc = ll_dir_setdirstripe(inode, lum, filename);
+#if LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 9, 50, 0)
+ mode = data->ioc_type != 0 ? data->ioc_type : S_IRWXUGO;
+#else
+ mode = data->ioc_type;
+#endif
+ rc = ll_dir_setdirstripe(inode, lum, filename, mode);
lmv_out_free:
obd_ioctl_freedata(buf, len);
RETURN(rc);
}
+ case LL_IOC_LMV_SET_DEFAULT_STRIPE: {
+ struct lmv_user_md lum;
+ struct lmv_user_md __user *ulump =
+ (struct lmv_user_md __user *)arg;
+ int rc;
+
+ if (copy_from_user(&lum, ulump, sizeof(lum)))
+ RETURN(-EFAULT);
+
+ if (lum.lum_magic != LMV_USER_MAGIC)
+ RETURN(-EINVAL);
+
+ rc = ll_dir_setstripe(inode, (struct lov_user_md *)&lum, 0);
+
+ RETURN(rc);
+ }
case LL_IOC_LOV_SETSTRIPE: {
struct lov_user_md_v3 lumv3;
struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;
RETURN(rc);
}
case LL_IOC_LMV_GETSTRIPE: {
- struct lmv_user_md *lump = (struct lmv_user_md *)arg;
- struct lmv_user_md lum;
- struct lmv_user_md *tmp;
- int lum_size;
- int rc = 0;
- int mdtindex;
-
- if (copy_from_user(&lum, lump, sizeof(struct lmv_user_md)))
+ struct lmv_user_md __user *ulmv =
+ (struct lmv_user_md __user *)arg;
+ struct lmv_user_md lum;
+ struct ptlrpc_request *request = NULL;
+ union lmv_mds_md *lmm = NULL;
+ int lmmsize;
+ obd_valid valid = 0;
+ struct lmv_user_md *tmp = NULL;
+ int mdt_index;
+ int lum_size;
+ int stripe_count;
+ int i;
+ int rc;
+
+ if (copy_from_user(&lum, ulmv, sizeof(*ulmv)))
RETURN(-EFAULT);
- if (lum.lum_magic != LMV_MAGIC_V1)
+ /* lum_magic will indicate which stripe the ioctl will like
+ * to get, LMV_MAGIC_V1 is for normal LMV stripe, LMV_USER_MAGIC
+ * is for default LMV stripe */
+ if (lum.lum_magic == LMV_MAGIC_V1)
+ valid |= OBD_MD_MEA;
+ else if (lum.lum_magic == LMV_USER_MAGIC)
+ valid |= OBD_MD_DEFAULT_MEA;
+ else
RETURN(-EINVAL);
- lum_size = lmv_user_md_size(1, LMV_MAGIC_V1);
+ rc = ll_dir_getstripe(inode, (void **)&lmm, &lmmsize, &request,
+ valid);
+ if (rc != 0)
+ GOTO(finish_req, rc);
+
+ /* Get default LMV EA */
+ if (lum.lum_magic == LMV_USER_MAGIC) {
+ if (rc != 0)
+ GOTO(finish_req, rc);
+
+ if (lmmsize > sizeof(*ulmv))
+ GOTO(finish_req, rc = -EINVAL);
+
+ if (copy_to_user(ulmv, lmm, lmmsize))
+ GOTO(finish_req, rc = -EFAULT);
+
+ GOTO(finish_req, rc);
+ }
+
+ stripe_count = lmv_mds_md_stripe_count_get(lmm);
+ lum_size = lmv_user_md_size(stripe_count, LMV_MAGIC_V1);
OBD_ALLOC(tmp, lum_size);
if (tmp == NULL)
- GOTO(free_lmv, rc = -ENOMEM);
-
- memcpy(tmp, &lum, sizeof(lum));
- tmp->lum_type = LMV_STRIPE_TYPE;
- tmp->lum_stripe_count = 1;
- mdtindex = ll_get_mdt_idx(inode);
- if (mdtindex < 0)
- GOTO(free_lmv, rc = -ENOMEM);
-
- tmp->lum_stripe_offset = mdtindex;
- tmp->lum_objects[0].lum_mds = mdtindex;
- memcpy(&tmp->lum_objects[0].lum_fid, ll_inode2fid(inode),
- sizeof(struct lu_fid));
- if (copy_to_user((void *)arg, tmp, lum_size))
- GOTO(free_lmv, rc = -EFAULT);
-free_lmv:
- if (tmp)
- OBD_FREE(tmp, lum_size);
- RETURN(rc);
+ GOTO(finish_req, rc = -ENOMEM);
+
+ mdt_index = ll_get_mdt_idx(inode);
+ if (mdt_index < 0)
+ GOTO(out_tmp, rc = -ENOMEM);
+
+ tmp->lum_magic = LMV_MAGIC_V1;
+ tmp->lum_stripe_count = 0;
+ tmp->lum_stripe_offset = mdt_index;
+ for (i = 0; i < stripe_count; i++) {
+ struct lu_fid fid;
+
+ fid_le_to_cpu(&fid, &lmm->lmv_md_v1.lmv_stripe_fids[i]);
+ mdt_index = ll_get_mdt_idx_by_fid(sbi, &fid);
+ if (mdt_index < 0)
+ GOTO(out_tmp, rc = mdt_index);
+
+ tmp->lum_objects[i].lum_mds = mdt_index;
+ tmp->lum_objects[i].lum_fid = fid;
+ tmp->lum_stripe_count++;
+ }
+
+ if (copy_to_user(ulmv, tmp, lum_size))
+ GOTO(out_tmp, rc = -EFAULT);
+out_tmp:
+ OBD_FREE(tmp, lum_size);
+finish_req:
+ ptlrpc_req_finished(request);
+ return rc;
}
+
case LL_IOC_REMOVE_ENTRY: {
char *filename = NULL;
int namelen = 0;
}
case LL_IOC_LOV_SWAP_LAYOUTS:
RETURN(-EPERM);
- case LL_IOC_OBD_STATFS:
- RETURN(ll_obd_statfs(inode, (void *)arg));
+ case IOC_OBD_STATFS:
+ RETURN(ll_obd_statfs(inode, (void *)arg));
case LL_IOC_LOV_GETSTRIPE:
case LL_IOC_MDC_GETINFO:
case IOC_MDC_GETFILEINFO:
rc = ll_lov_getstripe_ea_info(inode, filename, &lmm,
&lmmsize, &request);
- } else {
- rc = ll_dir_getstripe(inode, &lmm, &lmmsize, &request);
- }
+ } else {
+ rc = ll_dir_getstripe(inode, (void **)&lmm, &lmmsize,
+ &request, 0);
+ }
if (request) {
body = req_capsule_server_get(&request->rq_pill,
struct lov_user_mds_data *lmdp;
lstat_t st = { 0 };
- st.st_dev = inode->i_sb->s_dev;
- st.st_mode = body->mode;
- st.st_nlink = body->nlink;
- st.st_uid = body->uid;
- st.st_gid = body->gid;
- st.st_rdev = body->rdev;
- st.st_size = body->size;
- st.st_blksize = PAGE_CACHE_SIZE;
- st.st_blocks = body->blocks;
- st.st_atime = body->atime;
- st.st_mtime = body->mtime;
- st.st_ctime = body->ctime;
- st.st_ino = inode->i_ino;
-
- lmdp = (struct lov_user_mds_data *)arg;
+ st.st_dev = inode->i_sb->s_dev;
+ st.st_mode = body->mbo_mode;
+ st.st_nlink = body->mbo_nlink;
+ st.st_uid = body->mbo_uid;
+ st.st_gid = body->mbo_gid;
+ st.st_rdev = body->mbo_rdev;
+ st.st_size = body->mbo_size;
+ st.st_blksize = PAGE_CACHE_SIZE;
+ st.st_blocks = body->mbo_blocks;
+ st.st_atime = body->mbo_atime;
+ st.st_mtime = body->mbo_mtime;
+ st.st_ctime = body->mbo_ctime;
+ st.st_ino = inode->i_ino;
+
+ lmdp = (struct lov_user_mds_data *)arg;
if (copy_to_user(&lmdp->lmd_st, &st, sizeof(st)))
GOTO(out_req, rc = -EFAULT);
}
OBD_FREE_LARGE(lmm, lmmsize);
return rc;
}
- case OBD_IOC_LLOG_CATINFO: {
- RETURN(-EOPNOTSUPP);
- }
- case OBD_IOC_QUOTACHECK: {
+ case OBD_IOC_QUOTACHECK: {
struct obd_quotactl *oqctl;
int error = 0;
OBD_FREE_PTR(oqctl);
return error ?: rc;
}
- case OBD_IOC_POLL_QUOTACHECK: {
+ case OBD_IOC_POLL_QUOTACHECK: {
struct if_quotacheck *check;
if (!cfs_capable(CFS_CAP_SYS_ADMIN) ||
#else
#warning "remove old LL_IOC_QUOTACTL_18 compatibility code"
#endif /* LUSTRE_VERSION_CODE < OBD_OCD_VERSION(2, 7, 50, 0) */
- case LL_IOC_QUOTACTL: {
+ case OBD_IOC_QUOTACTL: {
struct if_quotactl *qctl;
OBD_ALLOC_PTR(qctl);
rc = copy_and_ioctl(cmd, sbi->ll_md_exp, (void *)arg,
sizeof(struct ioc_changelog));
RETURN(rc);
- case OBD_IOC_FID2PATH:
+ case OBD_IOC_FID2PATH:
RETURN(ll_fid2path(inode, (void *)arg));
+ case LL_IOC_FID2MDTIDX: {
+ struct obd_export *exp = ll_i2mdexp(inode);
+ struct lu_fid fid;
+ __u32 index;
+
+ if (copy_from_user(&fid, (const struct lu_fid __user *)arg,
+ sizeof(fid)))
+ RETURN(-EFAULT);
+
+ /* Call mdc_iocontrol */
+ rc = obd_iocontrol(LL_IOC_FID2MDTIDX, exp, sizeof(fid), &fid,
+ &index);
+ if (rc != 0)
+ RETURN(rc);
+
+ RETURN(index);
+ }
case LL_IOC_HSM_REQUEST: {
struct hsm_user_request *hur;
- int totalsize;
+ ssize_t totalsize;
OBD_ALLOC_PTR(hur);
if (hur == NULL)
/* Compute the whole struct size */
totalsize = hur_len(hur);
OBD_FREE_PTR(hur);
+ if (totalsize < 0)
+ RETURN(-E2BIG);
- /* Make sure the size is reasonable */
- if (totalsize >= MDS_MAXREQSIZE)
+ /* Final size will be more than double totalsize */
+ if (totalsize >= MDS_MAXREQSIZE / 3)
RETURN(-E2BIG);
OBD_ALLOC_LARGE(hur, totalsize);
OBD_FREE_PTR(copy);
RETURN(rc);
}
+ case LL_IOC_MIGRATE: {
+ char *buf = NULL;
+ const char *filename;
+ int namelen = 0;
+ int len;
+ int rc;
+ int mdtidx;
+
+ rc = obd_ioctl_getdata(&buf, &len, (void __user *)arg);
+ if (rc < 0)
+ RETURN(rc);
+
+ data = (struct obd_ioctl_data *)buf;
+ if (data->ioc_inlbuf1 == NULL || data->ioc_inlbuf2 == NULL ||
+ data->ioc_inllen1 == 0 || data->ioc_inllen2 == 0)
+ GOTO(migrate_free, rc = -EINVAL);
+
+ filename = data->ioc_inlbuf1;
+ namelen = data->ioc_inllen1;
+ /* \0 is packed at the end of filename */
+ if (namelen < 1 || namelen != strlen(filename) + 1)
+ GOTO(migrate_free, rc = -EINVAL);
+
+ if (data->ioc_inllen2 != sizeof(mdtidx))
+ GOTO(migrate_free, rc = -EINVAL);
+ mdtidx = *(int *)data->ioc_inlbuf2;
+
+ rc = ll_migrate(inode, file, mdtidx, filename, namelen - 1);
+migrate_free:
+ obd_ioctl_freedata(buf, len);
+
+ RETURN(rc);
+ }
default:
RETURN(obd_iocontrol(cmd, sbi->ll_dt_exp, 0, NULL,
(void *)arg));
return ret;
}
-int ll_dir_open(struct inode *inode, struct file *file)
+static int ll_dir_open(struct inode *inode, struct file *file)
{
ENTRY;
RETURN(ll_file_open(inode, file));
}
-int ll_dir_release(struct inode *inode, struct file *file)
+static int ll_dir_release(struct inode *inode, struct file *file)
{
ENTRY;
RETURN(ll_file_release(inode, file));
}
-struct file_operations ll_dir_operations = {
- .llseek = ll_dir_seek,
- .open = ll_dir_open,
- .release = ll_dir_release,
- .read = generic_read_dir,
- .readdir = ll_readdir,
- .unlocked_ioctl = ll_dir_ioctl,
- .fsync = ll_fsync,
+const struct file_operations ll_dir_operations = {
+ .llseek = ll_dir_seek,
+ .open = ll_dir_open,
+ .release = ll_dir_release,
+ .read = generic_read_dir,
+#ifdef HAVE_DIR_CONTEXT
+ .iterate = ll_iterate,
+#else
+ .readdir = ll_readdir,
+#endif
+ .unlocked_ioctl = ll_dir_ioctl,
+ .fsync = ll_fsync,
};