#include <linux/pagemap.h>
#include <linux/user_namespace.h>
#include <linux/utsname.h>
-#ifdef HAVE_UIDGID_HEADER
-# include <linux/uidgid.h>
-#endif
+#include <linux/delay.h>
+#include <linux/uidgid.h>
+#include <linux/device.h>
+#include <linux/xarray.h>
#include <lustre_errno.h>
#include <llog_swab.h>
#include <lprocfs_status.h>
#include <lustre_acl.h>
+#include <lustre_compat.h>
#include <lustre_fid.h>
#include <uapi/linux/lustre/lustre_ioctl.h>
#include <lustre_kernelcomm.h>
#include <lustre_lmv.h>
#include <lustre_log.h>
-#include <uapi/linux/lustre/lustre_param.h>
#include <lustre_swab.h>
#include <obd_class.h>
#include <lustre_osc.h>
rc = mdc_getattr_common(exp, req);
if (rc) {
- if (rc == -ERANGE &&
- acl_bufsize != imp->imp_connect_data.ocd_max_easize) {
- acl_bufsize = imp->imp_connect_data.ocd_max_easize;
+ if (rc == -ERANGE) {
+ acl_bufsize = min_t(__u32,
+ imp->imp_connect_data.ocd_max_easize,
+ XATTR_SIZE_MAX);
mdc_reset_acl_req(req);
goto again;
}
rc = mdc_getattr_common(exp, req);
if (rc) {
- if (rc == -ERANGE &&
- acl_bufsize != imp->imp_connect_data.ocd_max_easize) {
- acl_bufsize = imp->imp_connect_data.ocd_max_easize;
+ if (rc == -ERANGE) {
+ acl_bufsize = min_t(__u32,
+ imp->imp_connect_data.ocd_max_easize,
+ XATTR_SIZE_MAX);
mdc_reset_acl_req(req);
goto again;
}
if (req == NULL)
RETURN(-ENOMEM);
- if (xattr_name) {
- xattr_namelen = strlen(xattr_name) + 1;
- req_capsule_set_size(&req->rq_pill, &RMF_NAME, RCL_CLIENT,
- xattr_namelen);
- }
- if (input_size) {
- LASSERT(input);
- req_capsule_set_size(&req->rq_pill, &RMF_EADATA, RCL_CLIENT,
- input_size);
- }
+ if (xattr_name) {
+ xattr_namelen = strlen(xattr_name) + 1;
+ req_capsule_set_size(&req->rq_pill, &RMF_NAME, RCL_CLIENT,
+ xattr_namelen);
+ }
+ if (input_size)
+ LASSERT(input);
+ req_capsule_set_size(&req->rq_pill, &RMF_EADATA, RCL_CLIENT,
+ input_size);
+
+ /* get SELinux policy info if any */
+ rc = sptlrpc_get_sepol(req);
+ if (rc < 0) {
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+ req_capsule_set_size(&req->rq_pill, &RMF_SELINUX_POL, RCL_CLIENT,
+ strlen(req->rq_sepol) ?
+ strlen(req->rq_sepol) + 1 : 0);
/* Flush local XATTR locks to get rid of a possible cancel RPC */
if (opcode == MDS_REINT && fid_is_sane(fid) &&
exp->exp_connect_data.ocd_ibits_known & MDS_INODELOCK_XATTR) {
- struct list_head cancels = LIST_HEAD_INIT(cancels);
+ LIST_HEAD(cancels);
int count;
/* Without that packing would fail */
if (opcode == MDS_REINT) {
struct mdt_rec_setxattr *rec;
- CLASSERT(sizeof(struct mdt_rec_setxattr) ==
- sizeof(struct mdt_rec_reint));
+ BUILD_BUG_ON(sizeof(struct mdt_rec_setxattr) !=
+ sizeof(struct mdt_rec_reint));
rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
rec->sx_opcode = REINT_SETXATTR;
rec->sx_fsuid = from_kuid(&init_user_ns, current_fsuid());
memcpy(tmp, input, input_size);
}
+ mdc_file_sepol_pack(req);
+
if (req_capsule_has_field(&req->rq_pill, &RMF_EADATA, RCL_SERVER))
req_capsule_set_size(&req->rq_pill, &RMF_EADATA,
RCL_SERVER, output_size);
/* make rpc */
if (opcode == MDS_REINT)
- mdc_get_mod_rpc_slot(req, NULL);
+ ptlrpc_get_mod_rpc_slot(req);
rc = ptlrpc_queue_wait(req);
if (opcode == MDS_REINT)
- mdc_put_mod_rpc_slot(req, NULL);
+ ptlrpc_put_mod_rpc_slot(req);
if (rc)
ptlrpc_req_finished(req);
u64 obd_md_valid, const char *name, size_t buf_size,
struct ptlrpc_request **req)
{
+ struct mdt_body *body;
+ int rc;
+
LASSERT(obd_md_valid == OBD_MD_FLXATTR ||
obd_md_valid == OBD_MD_FLXATTRLS);
- return mdc_xattr_common(exp, &RQF_MDS_GETXATTR, fid, MDS_GETXATTR,
- obd_md_valid, name, NULL, 0, buf_size, 0, -1,
- req);
+ /* The below message is checked in sanity-selinux.sh test_20d */
+ CDEBUG(D_INFO, "%s: get xattr '%s' for "DFID"\n",
+ exp->exp_obd->obd_name, name, PFID(fid));
+ rc = mdc_xattr_common(exp, &RQF_MDS_GETXATTR, fid, MDS_GETXATTR,
+ obd_md_valid, name, NULL, 0, buf_size, 0, -1,
+ req);
+ if (rc < 0)
+ GOTO(out, rc);
+
+ body = req_capsule_server_get(&(*req)->rq_pill, &RMF_MDT_BODY);
+ if (body == NULL)
+ GOTO(out, rc = -EPROTO);
+
+ /* only detect the xattr size */
+ if (buf_size == 0) {
+ /* LU-11109: Older MDTs do not distinguish
+ * between nonexistent xattrs and zero length
+ * values in this case. Newer MDTs will return
+ * -ENODATA or set OBD_MD_FLXATTR. */
+ GOTO(out, rc = body->mbo_eadatasize);
+ }
+
+ if (body->mbo_eadatasize == 0) {
+ /* LU-11109: Newer MDTs set OBD_MD_FLXATTR on
+ * success so that we can distinguish between
+ * zero length value and nonexistent xattr.
+ *
+ * If OBD_MD_FLXATTR is not set then we keep
+ * the old behavior and return -ENODATA for
+ * getxattr() when mbo_eadatasize is 0. But
+ * -ENODATA only makes sense for getxattr()
+ * and not for listxattr(). */
+ if (body->mbo_valid & OBD_MD_FLXATTR)
+ GOTO(out, rc = 0);
+ else if (obd_md_valid == OBD_MD_FLXATTR)
+ GOTO(out, rc = -ENODATA);
+ else
+ GOTO(out, rc = 0);
+ }
+
+ GOTO(out, rc = body->mbo_eadatasize);
+out:
+ if (rc < 0) {
+ ptlrpc_req_finished(*req);
+ *req = NULL;
+ }
+
+ return rc;
}
-#ifdef CONFIG_FS_POSIX_ACL
+#ifdef CONFIG_LUSTRE_FS_POSIX_ACL
static int mdc_unpack_acl(struct ptlrpc_request *req, struct lustre_md *md)
{
struct req_capsule *pill = &req->rq_pill;
GOTO(out, rc = -EPROTO);
}
- lmv_size = md->body->mbo_eadatasize;
- if (lmv_size == 0) {
- CDEBUG(D_INFO, "OBD_MD_FLDIREA is set, "
- "but eadatasize 0\n");
- RETURN(-EPROTO);
- }
-
if (md->body->mbo_valid & OBD_MD_MEA) {
+ lmv_size = md->body->mbo_eadatasize;
+ if (lmv_size == 0) {
+ CDEBUG(D_INFO, "OBD_MD_FLDIREA is set, "
+ "but eadatasize 0\n");
+ RETURN(-EPROTO);
+ }
+
lmv = req_capsule_server_sized_get(pill, &RMF_MDT_MD,
lmv_size);
if (lmv == NULL)
if (rc < 0)
GOTO(out, rc);
- if (rc < (typeof(rc))sizeof(*md->lmv)) {
- CDEBUG(D_INFO, "size too small: "
- "rc < sizeof(*md->lmv) (%d < %d)\n",
- rc, (int)sizeof(*md->lmv));
+ if (rc < (int)sizeof(*md->lmv)) {
+ struct lmv_foreign_md *lfm = md->lfm;
+
+ /* short (< sizeof(struct lmv_stripe_md))
+ * foreign LMV case
+ */
+ if (lfm->lfm_magic != LMV_MAGIC_FOREIGN) {
+ CDEBUG(D_INFO,
+ "lmv size too small: %d < %d\n",
+ rc, (int)sizeof(*md->lmv));
+ GOTO(out, rc = -EPROTO);
+ }
+ }
+ }
+
+ /* since 2.12.58 intent_getattr fetches default LMV */
+ if (md->body->mbo_valid & OBD_MD_DEFAULT_MEA) {
+ lmv_size = sizeof(struct lmv_user_md);
+ lmv = req_capsule_server_sized_get(pill,
+ &RMF_DEFAULT_MDT_MD,
+ lmv_size);
+ if (!lmv)
+ GOTO(out, rc = -EPROTO);
+
+ rc = md_unpackmd(md_exp, &md->default_lmv, lmv,
+ lmv_size);
+ if (rc < 0)
+ GOTO(out, rc);
+
+ if (rc < (int)sizeof(*md->default_lmv)) {
+ CDEBUG(D_INFO,
+ "default lmv size too small: %d < %d\n",
+ rc, (int)sizeof(*md->default_lmv));
GOTO(out, rc = -EPROTO);
}
}
- }
+ }
rc = 0;
if (md->body->mbo_valid & OBD_MD_FLACL) {
rc = mdc_unpack_acl(req, md);
if (rc)
GOTO(out, rc);
-#ifdef CONFIG_FS_POSIX_ACL
+#ifdef CONFIG_LUSTRE_FS_POSIX_ACL
} else {
md->posix_acl = NULL;
#endif
EXIT;
out:
if (rc) {
-#ifdef CONFIG_FS_POSIX_ACL
+#ifdef CONFIG_LUSTRE_FS_POSIX_ACL
posix_acl_release(md->posix_acl);
#endif
}
void mdc_replay_open(struct ptlrpc_request *req)
{
- struct md_open_data *mod = req->rq_cb_data;
- struct ptlrpc_request *close_req;
- struct obd_client_handle *och;
- struct lustre_handle old;
- struct mdt_body *body;
- ENTRY;
+ struct md_open_data *mod = req->rq_cb_data;
+ struct ptlrpc_request *close_req;
+ struct obd_client_handle *och;
+ struct lustre_handle old_open_handle = { };
+ struct mdt_body *body;
+ ENTRY;
- if (mod == NULL) {
- DEBUG_REQ(D_ERROR, req,
- "Can't properly replay without open data.");
- EXIT;
- return;
- }
+ if (mod == NULL) {
+ DEBUG_REQ(D_ERROR, req,
+ "cannot properly replay without open data");
+ EXIT;
+ return;
+ }
- 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);
spin_lock(&req->rq_lock);
och = mod->mod_och;
- if (och && och->och_fh.cookie)
+ if (och && och->och_open_handle.cookie)
req->rq_early_free_repbuf = 1;
else
req->rq_early_free_repbuf = 0;
spin_unlock(&req->rq_lock);
if (req->rq_early_free_repbuf) {
- struct lustre_handle *file_fh;
+ struct lustre_handle *file_open_handle;
LASSERT(och->och_magic == OBD_CLIENT_HANDLE_MAGIC);
- file_fh = &och->och_fh;
+ file_open_handle = &och->och_open_handle;
CDEBUG(D_HA, "updating handle from %#llx to %#llx\n",
- file_fh->cookie, body->mbo_handle.cookie);
- old = *file_fh;
- *file_fh = body->mbo_handle;
+ file_open_handle->cookie, body->mbo_open_handle.cookie);
+ old_open_handle = *file_open_handle;
+ *file_open_handle = body->mbo_open_handle;
}
close_req = mod->mod_close_req;
LASSERT(epoch);
if (req->rq_early_free_repbuf)
- LASSERT(!memcmp(&old, &epoch->mio_handle, sizeof(old)));
+ LASSERT(old_open_handle.cookie ==
+ epoch->mio_open_handle.cookie);
DEBUG_REQ(D_HA, close_req, "updating close body with new fh");
- epoch->mio_handle = body->mbo_handle;
+ epoch->mio_open_handle = body->mbo_open_handle;
}
EXIT;
}
/* Outgoing messages always in my byte order. */
LASSERT(body != NULL);
- /* Only if the import is replayable, we set replay_open data */
- if (och && imp->imp_replayable) {
- mod = obd_mod_alloc();
- if (mod == NULL) {
- DEBUG_REQ(D_ERROR, open_req,
- "Can't allocate md_open_data");
- RETURN(0);
- }
+ /* Only if the import is replayable, we set replay_open data */
+ if (och && imp->imp_replayable) {
+ mod = obd_mod_alloc();
+ if (mod == NULL) {
+ DEBUG_REQ(D_ERROR, open_req,
+ "cannot allocate md_open_data");
+ RETURN(0);
+ }
/**
* Take a reference on \var mod, to be freed on mdc_close().
open_req->rq_commit_cb = mdc_commit_open;
open_req->rq_early_free_repbuf = 1;
spin_unlock(&open_req->rq_lock);
- }
+ }
rec->cr_fid2 = body->mbo_fid1;
- rec->cr_old_handle.cookie = body->mbo_handle.cookie;
+ rec->cr_open_handle_old = body->mbo_open_handle;
open_req->rq_replay_cb = mdc_replay_open;
if (!fid_is_sane(&body->mbo_fid1)) {
- DEBUG_REQ(D_ERROR, open_req, "Saving replay request with "
- "insane fid");
- LBUG();
- }
+ DEBUG_REQ(D_ERROR, open_req,
+ "saving replay request with insane FID " DFID,
+ PFID(&body->mbo_fid1));
+ LBUG();
+ }
- DEBUG_REQ(D_RPCTRACE, open_req, "Set up open replay data");
- RETURN(0);
+ DEBUG_REQ(D_RPCTRACE, open_req, "Set up open replay data");
+ RETURN(0);
}
static void mdc_free_open(struct md_open_data *mod)
* The worst thing is eviction if the client gets open lock
**/
- DEBUG_REQ(D_RPCTRACE, mod->mod_open_req, "free open request rq_replay"
- "= %d\n", mod->mod_open_req->rq_replay);
+ DEBUG_REQ(D_RPCTRACE, mod->mod_open_req,
+ "free open request, rq_replay=%d",
+ mod->mod_open_req->rq_replay);
ptlrpc_request_committed(mod->mod_open_req, committed);
if (mod->mod_close_req)
spin_lock(&mod->mod_open_req->rq_lock);
if (mod->mod_och)
- mod->mod_och->och_fh.cookie = 0;
+ mod->mod_och->och_open_handle.cookie = 0;
mod->mod_open_req->rq_early_free_repbuf = 0;
spin_unlock(&mod->mod_open_req->rq_lock);
mdc_free_open(mod);
mod->mod_close_req = req;
- DEBUG_REQ(D_HA, mod->mod_open_req, "matched open");
+ DEBUG_REQ(D_RPCTRACE, mod->mod_open_req, "matched open");
/* We no longer want to preserve this open for replay even
* though the open was committed. b=3632, b=3633 */
spin_lock(&mod->mod_open_req->rq_lock);
req->rq_request_portal = MDS_READPAGE_PORTAL;
ptlrpc_at_set_req_timeout(req);
+ if (!(exp_connect_flags2(exp) & OBD_CONNECT2_LSOM))
+ op_data->op_xvalid &= ~(OP_XVALID_LAZYSIZE |
+ OP_XVALID_LAZYBLOCKS);
mdc_close_pack(req, op_data);
ptlrpc_request_set_replen(req);
- mdc_get_mod_rpc_slot(req, NULL);
+ ptlrpc_get_mod_rpc_slot(req);
rc = ptlrpc_queue_wait(req);
- mdc_put_mod_rpc_slot(req, NULL);
-
- if (req->rq_repmsg == NULL) {
- CDEBUG(D_RPCTRACE, "request failed to send: %p, %d\n", req,
- req->rq_status);
- if (rc == 0)
- rc = req->rq_status ?: -EIO;
- } else if (rc == 0 || rc == -EAGAIN) {
- struct mdt_body *body;
-
- rc = lustre_msg_get_status(req->rq_repmsg);
- if (lustre_msg_get_type(req->rq_repmsg) == PTL_RPC_MSG_ERR) {
- DEBUG_REQ(D_ERROR, req, "type == PTL_RPC_MSG_ERR, err "
- "= %d", rc);
- if (rc > 0)
- rc = -rc;
- }
- body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (body == NULL)
- rc = -EPROTO;
- } else if (rc == -ESTALE) {
- /**
- * it can be allowed error after 3633 if open was committed and
- * server failed before close was sent. Let's check if mod
- * exists and return no error in that case
- */
- if (mod) {
- DEBUG_REQ(D_HA, req, "Reset ESTALE = %d", rc);
- LASSERT(mod->mod_open_req != NULL);
- if (mod->mod_open_req->rq_committed)
- rc = 0;
- }
- }
+ ptlrpc_put_mod_rpc_slot(req);
+
+ if (req->rq_repmsg == NULL) {
+ CDEBUG(D_RPCTRACE, "request %p failed to send: rc = %d\n", req,
+ req->rq_status);
+ if (rc == 0)
+ rc = req->rq_status ?: -EIO;
+ } else if (rc == 0 || rc == -EAGAIN) {
+ struct mdt_body *body;
+
+ rc = lustre_msg_get_status(req->rq_repmsg);
+ if (lustre_msg_get_type(req->rq_repmsg) == PTL_RPC_MSG_ERR) {
+ DEBUG_REQ(D_ERROR, req,
+ "type = PTL_RPC_MSG_ERR: rc = %d", rc);
+ if (rc > 0)
+ rc = -rc;
+ }
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (body == NULL)
+ rc = -EPROTO;
+ } else if (rc == -ESTALE) {
+ /**
+ * it can be allowed error after 3633 if open was committed and
+ * server failed before close was sent. Let's check if mod
+ * exists and return no error in that case
+ */
+ if (mod) {
+ DEBUG_REQ(D_HA, req, "Reset ESTALE = %d", rc);
+ LASSERT(mod->mod_open_req != NULL);
+ if (mod->mod_open_req->rq_committed)
+ rc = 0;
+ }
+ }
out:
if (mod) {
struct ptlrpc_request *req;
struct ptlrpc_bulk_desc *desc;
int i;
- wait_queue_head_t waitq;
int resends = 0;
- struct l_wait_info lwi;
int rc;
ENTRY;
*request = NULL;
- init_waitqueue_head(&waitq);
restart_bulk:
req = ptlrpc_request_alloc(class_exp2cliimp(exp), &RQF_MDS_READPAGE);
ptlrpc_at_set_req_timeout(req);
desc = ptlrpc_prep_bulk_imp(req, npages, 1,
- PTLRPC_BULK_PUT_SINK | PTLRPC_BULK_BUF_KIOV,
+ PTLRPC_BULK_PUT_SINK,
MDS_BULK_PORTAL,
&ptlrpc_bulk_kiov_pin_ops);
if (desc == NULL) {
exp->exp_obd->obd_name, -EIO);
RETURN(-EIO);
}
- lwi = LWI_TIMEOUT_INTR(cfs_time_seconds(resends), NULL, NULL,
- NULL);
- l_wait_event(waitq, 0, &lwi);
+
+ /* If a signal interrupts then the timeout returned will
+ * not be zero. In that case return -EINTR
+ */
+ if (msleep_interruptible(resends * 1000))
+ RETURN(-EINTR);
goto restart_bulk;
}
if (remove) {
lock_page(page);
if (likely(page->mapping != NULL))
- truncate_complete_page(page->mapping, page);
+ delete_from_page_cache(page);
unlock_page(page);
}
put_page(page);
*/
unsigned long offset = hash_x_index(*hash, hash64);
struct page *page;
+ unsigned long flags;
int found;
- spin_lock_irq(&mapping->tree_lock);
+ ll_xa_lock_irqsave(&mapping->i_pages, flags);
found = radix_tree_gang_lookup(&mapping->page_tree,
(void **)&page, offset, 1);
- if (found > 0 && !radix_tree_exceptional_entry(page)) {
+ if (found > 0 && !ll_xa_is_value(page)) {
struct lu_dirpage *dp;
get_page(page);
- spin_unlock_irq(&mapping->tree_lock);
+ ll_xa_unlock_irqrestore(&mapping->i_pages, flags);
/*
* In contrast to find_lock_page() we are sure that directory
* page cannot be truncated (while DLM lock is held) and,
page = ERR_PTR(-EIO);
}
} else {
- spin_unlock_irq(&mapping->tree_lock);
+ ll_xa_unlock_irqrestore(&mapping->i_pages, flags);
page = NULL;
}
return page;
int i;
for (i = 0; i < cfs_pgs; i++) {
- struct lu_dirpage *dp = kmap(pages[i]);
- struct lu_dirpage *first = dp;
- struct lu_dirent *end_dirent = NULL;
- struct lu_dirent *ent;
- __u64 hash_end = le64_to_cpu(dp->ldp_hash_end);
- __u32 flags = le32_to_cpu(dp->ldp_flags);
+ struct lu_dirpage *dp = kmap(pages[i]);
+ struct lu_dirpage *first = dp;
+ struct lu_dirent *end_dirent = NULL;
+ struct lu_dirent *ent;
+ __u64 hash_end = dp->ldp_hash_end;
+ __u32 flags = dp->ldp_flags;
while (--lu_pgs > 0) {
ent = lu_dirent_start(dp);
break;
/* Save the hash and flags of this lu_dirpage. */
- hash_end = le64_to_cpu(dp->ldp_hash_end);
- flags = le32_to_cpu(dp->ldp_flags);
+ hash_end = dp->ldp_hash_end;
+ flags = dp->ldp_flags;
/* Check if lu_dirpage contains no entries. */
if (end_dirent == NULL)
struct md_callback *rp_cb;
};
-#ifndef HAVE_DELETE_FROM_PAGE_CACHE
-static inline void delete_from_page_cache(struct page *page)
-{
- remove_from_page_cache(page);
- put_page(page);
-}
-#endif
-
/**
* Read pages from server.
*
fid = &op_data->op_fid1;
LASSERT(inode != NULL);
- OBD_ALLOC(page_pool, sizeof(page_pool[0]) * max_pages);
+ OBD_ALLOC_PTR_ARRAY(page_pool, max_pages);
if (page_pool != NULL) {
page_pool[0] = page0;
} else {
}
for (npages = 1; npages < max_pages; npages++) {
- page = __page_cache_alloc(mapping_gfp_mask(inode->i_mapping)
- | __GFP_COLD);
+ page = page_cache_alloc(inode->i_mapping);
if (page == NULL)
break;
page_pool[npages] = page;
}
if (page_pool != &page0)
- OBD_FREE(page_pool, sizeof(page_pool[0]) * max_pages);
+ OBD_FREE_PTR_ARRAY(page_pool, max_pages);
RETURN(rc);
}
goto out_unlock;
}
+static int mdc_statfs_interpret(const struct lu_env *env,
+ struct ptlrpc_request *req, void *args, int rc)
+{
+ struct obd_info *oinfo = args;
+ struct obd_statfs *osfs;
+
+ if (!rc) {
+ osfs = req_capsule_server_get(&req->rq_pill, &RMF_OBD_STATFS);
+ if (!osfs)
+ return -EPROTO;
+
+ oinfo->oi_osfs = osfs;
+
+ CDEBUG(D_CACHE, "blocks=%llu free=%llu avail=%llu "
+ "objects=%llu free=%llu state=%x\n",
+ osfs->os_blocks, osfs->os_bfree, osfs->os_bavail,
+ osfs->os_files, osfs->os_ffree, osfs->os_state);
+ }
+
+ oinfo->oi_cb_up(oinfo, rc);
+
+ return rc;
+}
+
+static int mdc_statfs_async(struct obd_export *exp,
+ struct obd_info *oinfo, time64_t max_age,
+ struct ptlrpc_request_set *unused)
+{
+ struct ptlrpc_request *req;
+ struct obd_info *aa;
+
+ req = ptlrpc_request_alloc_pack(class_exp2cliimp(exp), &RQF_MDS_STATFS,
+ LUSTRE_MDS_VERSION, MDS_STATFS);
+ if (req == NULL)
+ return -ENOMEM;
+
+ ptlrpc_request_set_replen(req);
+ req->rq_interpret_reply = mdc_statfs_interpret;
+
+ aa = ptlrpc_req_async_args(aa, req);
+ *aa = *oinfo;
+
+ ptlrpcd_add_req(req);
+
+ return 0;
+}
+
static int mdc_statfs(const struct lu_env *env,
struct obd_export *exp, struct obd_statfs *osfs,
time64_t max_age, __u32 flags)
{
- struct obd_device *obd = class_exp2obd(exp);
- struct ptlrpc_request *req;
- struct obd_statfs *msfs;
- struct obd_import *imp = NULL;
- int rc;
- ENTRY;
+ struct obd_device *obd = class_exp2obd(exp);
+ struct req_format *fmt;
+ struct ptlrpc_request *req;
+ struct obd_statfs *msfs;
+ struct obd_import *imp = NULL;
+ int rc;
+ ENTRY;
/*
* Since the request might also come from lprocfs, so we need
* sync this with client_disconnect_export Bug15684
*/
down_read(&obd->u.cli.cl_sem);
- if (obd->u.cli.cl_import)
- imp = class_import_get(obd->u.cli.cl_import);
+ if (obd->u.cli.cl_import)
+ imp = class_import_get(obd->u.cli.cl_import);
up_read(&obd->u.cli.cl_sem);
- if (!imp)
- RETURN(-ENODEV);
+ if (!imp)
+ RETURN(-ENODEV);
+
+ fmt = &RQF_MDS_STATFS;
+ if ((exp_connect_flags2(exp) & OBD_CONNECT2_SUM_STATFS) &&
+ (flags & OBD_STATFS_SUM))
+ fmt = &RQF_MDS_STATFS_NEW;
+ req = ptlrpc_request_alloc_pack(imp, fmt, LUSTRE_MDS_VERSION,
+ MDS_STATFS);
+ if (req == NULL)
+ GOTO(output, rc = -ENOMEM);
- req = ptlrpc_request_alloc_pack(imp, &RQF_MDS_STATFS,
- LUSTRE_MDS_VERSION, MDS_STATFS);
- if (req == NULL)
- GOTO(output, rc = -ENOMEM);
+ if ((flags & OBD_STATFS_SUM) &&
+ (exp_connect_flags2(exp) & OBD_CONNECT2_SUM_STATFS)) {
+ /* request aggregated states */
+ struct mdt_body *body;
+
+ body = req_capsule_client_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (body == NULL)
+ GOTO(out, rc = -EPROTO);
+ body->mbo_valid = OBD_MD_FLAGSTATFS;
+ }
ptlrpc_request_set_replen(req);
ptlrpc_request_set_replen(req);
- mdc_get_mod_rpc_slot(req, NULL);
+ ptlrpc_get_mod_rpc_slot(req);
rc = ptlrpc_queue_wait(req);
- mdc_put_mod_rpc_slot(req, NULL);
+ ptlrpc_put_mod_rpc_slot(req);
GOTO(out, rc);
out:
ptlrpc_req_finished(req);
return rc;
}
-
-static int mdc_ioc_hsm_ct_register(struct obd_import *imp, __u32 archives)
+/**
+ * Send hsm_ct_register to MDS
+ *
+ * \param[in] imp import
+ * \param[in] archive_count if in bitmap format, it is the bitmap,
+ * else it is the count of archive_ids
+ * \param[in] archives if in bitmap format, it is NULL,
+ * else it is archive_id lists
+ */
+static int mdc_ioc_hsm_ct_register(struct obd_import *imp, __u32 archive_count,
+ __u32 *archives)
{
- __u32 *archive_mask;
- struct ptlrpc_request *req;
- int rc;
+ struct ptlrpc_request *req;
+ __u32 *archive_array;
+ size_t archives_size;
+ int rc;
ENTRY;
- req = ptlrpc_request_alloc_pack(imp, &RQF_MDS_HSM_CT_REGISTER,
- LUSTRE_MDS_VERSION,
- MDS_HSM_CT_REGISTER);
+ req = ptlrpc_request_alloc(imp, &RQF_MDS_HSM_CT_REGISTER);
if (req == NULL)
- GOTO(out, rc = -ENOMEM);
+ RETURN(-ENOMEM);
+
+ if (archives != NULL)
+ archives_size = sizeof(*archive_array) * archive_count;
+ else
+ archives_size = sizeof(archive_count);
+
+ req_capsule_set_size(&req->rq_pill, &RMF_MDS_HSM_ARCHIVE,
+ RCL_CLIENT, archives_size);
+
+ rc = ptlrpc_request_pack(req, LUSTRE_MDS_VERSION, MDS_HSM_CT_REGISTER);
+ if (rc) {
+ ptlrpc_request_free(req);
+ RETURN(-ENOMEM);
+ }
mdc_pack_body(req, NULL, 0, 0, -1, 0);
- /* Copy hsm_progress struct */
- archive_mask = req_capsule_client_get(&req->rq_pill,
- &RMF_MDS_HSM_ARCHIVE);
- if (archive_mask == NULL)
+ archive_array = req_capsule_client_get(&req->rq_pill,
+ &RMF_MDS_HSM_ARCHIVE);
+ if (archive_array == NULL)
GOTO(out, rc = -EPROTO);
- *archive_mask = archives;
+ if (archives != NULL)
+ memcpy(archive_array, archives, archives_size);
+ else
+ *archive_array = archive_count;
ptlrpc_request_set_replen(req);
+ req->rq_no_resend = 1;
rc = mdc_queue_wait(req);
GOTO(out, rc);
ptlrpc_request_set_replen(req);
- mdc_get_mod_rpc_slot(req, NULL);
+ ptlrpc_get_mod_rpc_slot(req);
rc = ptlrpc_queue_wait(req);
- mdc_put_mod_rpc_slot(req, NULL);
+ ptlrpc_put_mod_rpc_slot(req);
GOTO(out, rc);
out:
ptlrpc_request_set_replen(req);
- mdc_get_mod_rpc_slot(req, NULL);
+ ptlrpc_get_mod_rpc_slot(req);
rc = ptlrpc_queue_wait(req);
- mdc_put_mod_rpc_slot(req, NULL);
+ ptlrpc_put_mod_rpc_slot(req);
GOTO(out, rc);
static int mdc_quotactl(struct obd_device *unused, struct obd_export *exp,
struct obd_quotactl *oqctl)
{
- struct ptlrpc_request *req;
- struct obd_quotactl *oqc;
- int rc;
+ struct ptlrpc_request *req;
+ struct obd_quotactl *oqc;
+ int rc;
ENTRY;
- req = ptlrpc_request_alloc_pack(class_exp2cliimp(exp),
- &RQF_MDS_QUOTACTL, LUSTRE_MDS_VERSION,
- MDS_QUOTACTL);
+ req = ptlrpc_request_alloc(class_exp2cliimp(exp), &RQF_MDS_QUOTACTL);
if (req == NULL)
RETURN(-ENOMEM);
+
+ if (LUSTRE_Q_CMD_IS_POOL(oqctl->qc_cmd))
+ req_capsule_set_size(&req->rq_pill,
+ &RMF_OBD_QUOTACTL,
+ RCL_CLIENT,
+ sizeof(*oqc) + LOV_MAXPOOLNAME + 1);
+
+ rc = ptlrpc_request_pack(req, LUSTRE_MDS_VERSION,
+ MDS_QUOTACTL);
+ if (rc) {
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+
oqc = req_capsule_client_get(&req->rq_pill, &RMF_OBD_QUOTACTL);
- *oqc = *oqctl;
+ QCTL_COPY(oqc, oqctl);
ptlrpc_request_set_replen(req);
ptlrpc_at_set_req_timeout(req);
rc = ptlrpc_queue_wait(req);
- if (rc)
- CERROR("ptlrpc_queue_wait failed, rc: %d\n", rc);
+ if (rc) {
+ CERROR("%s: ptlrpc_queue_wait failed: rc = %d\n",
+ exp->exp_obd->obd_name, rc);
+ GOTO(out, rc);
+ }
if (req->rq_repmsg &&
(oqc = req_capsule_server_get(&req->rq_pill, &RMF_OBD_QUOTACTL))) {
- *oqctl = *oqc;
+ QCTL_COPY(oqctl, oqc);
} else if (!rc) {
- CERROR ("Can't unpack obd_quotactl\n");
rc = -EPROTO;
+ CERROR("%s: cannot unpack obd_quotactl: rc = %d\n",
+ exp->exp_obd->obd_name, rc);
}
+out:
ptlrpc_req_finished(req);
RETURN(rc);
static int mdc_ioc_swap_layouts(struct obd_export *exp,
struct md_op_data *op_data)
{
- struct list_head cancels = LIST_HEAD_INIT(cancels);
+ LIST_HEAD(cancels);
struct ptlrpc_request *req;
int rc, count;
struct mdc_swap_layouts *msl, *payload;
case IOC_OSC_SET_ACTIVE:
rc = ptlrpc_set_import_active(imp, data->ioc_offset);
GOTO(out, rc);
- case OBD_IOC_PING_TARGET:
- rc = ptlrpc_obd_ping(obd);
- GOTO(out, rc);
/*
* Normally IOC_OBD_STATFS, OBD_IOC_QUOTACTL iocontrol are handled by
* LMV instead of MDC. But when the cluster is upgraded from 1.8,
static int mdc_ioc_hsm_ct_start(struct obd_export *exp,
struct lustre_kernelcomm *lk)
{
- struct obd_import *imp = class_exp2cliimp(exp);
- __u32 archive = lk->lk_data;
- int rc = 0;
+ struct obd_import *imp = class_exp2cliimp(exp);
+ int rc = 0;
if (lk->lk_group != KUC_GRP_HSM) {
CERROR("Bad copytool group %d\n", lk->lk_group);
/* Unregister with the coordinator */
rc = mdc_ioc_hsm_ct_unregister(imp);
} else {
- rc = mdc_ioc_hsm_ct_register(imp, archive);
+ __u32 *archives = NULL;
+
+ if ((lk->lk_flags & LK_FLG_DATANR) && lk->lk_data_count > 0)
+ archives = lk->lk_data;
+
+ rc = mdc_ioc_hsm_ct_register(imp, lk->lk_data_count, archives);
}
return rc;
*/
static int mdc_hsm_ct_reregister(void *data, void *cb_arg)
{
- struct kkuc_ct_data *kcd = data;
- struct obd_import *imp = (struct obd_import *)cb_arg;
- int rc;
+ struct obd_import *imp = (struct obd_import *)cb_arg;
+ struct kkuc_ct_data *kcd = data;
+ __u32 *archives = NULL;
+ int rc;
- if (kcd == NULL || kcd->kcd_magic != KKUC_CT_DATA_MAGIC)
+ if (kcd == NULL ||
+ (kcd->kcd_magic != KKUC_CT_DATA_ARRAY_MAGIC &&
+ kcd->kcd_magic != KKUC_CT_DATA_BITMAP_MAGIC))
return -EPROTO;
- CDEBUG(D_HA, "%s: recover copytool registration to MDT (archive=%#x)\n",
- imp->imp_obd->obd_name, kcd->kcd_archive);
- rc = mdc_ioc_hsm_ct_register(imp, kcd->kcd_archive);
+ if (kcd->kcd_magic == KKUC_CT_DATA_BITMAP_MAGIC) {
+ CDEBUG(D_HA, "%s: recover copytool registration to MDT "
+ "(archive=%#x)\n", imp->imp_obd->obd_name,
+ kcd->kcd_nr_archives);
+ } else {
+ CDEBUG(D_HA, "%s: recover copytool registration to MDT "
+ "(archive nr = %u)\n",
+ imp->imp_obd->obd_name, kcd->kcd_nr_archives);
+ if (kcd->kcd_nr_archives != 0)
+ archives = kcd->kcd_archives;
+ }
+ rc = mdc_ioc_hsm_ct_register(imp, kcd->kcd_nr_archives, archives);
/* ignore error if the copytool is already registered */
return (rc == -EEXIST) ? 0 : rc;
}
RETURN(rc);
}
+struct mdc_rmfid_args {
+ int *mra_rcs;
+ int mra_nr;
+};
+
+int mdc_rmfid_interpret(const struct lu_env *env, struct ptlrpc_request *req,
+ void *args, int rc)
+{
+ struct mdc_rmfid_args *aa;
+ int *rcs, size;
+ ENTRY;
+
+ if (!rc) {
+ aa = ptlrpc_req_async_args(aa, req);
+
+ size = req_capsule_get_size(&req->rq_pill, &RMF_RCS,
+ RCL_SERVER);
+ LASSERT(size == sizeof(int) * aa->mra_nr);
+ rcs = req_capsule_server_get(&req->rq_pill, &RMF_RCS);
+ LASSERT(rcs);
+ LASSERT(aa->mra_rcs);
+ LASSERT(aa->mra_nr);
+ memcpy(aa->mra_rcs, rcs, size);
+ }
+
+ RETURN(rc);
+}
+
+static int mdc_rmfid(struct obd_export *exp, struct fid_array *fa,
+ int *rcs, struct ptlrpc_request_set *set)
+{
+ struct ptlrpc_request *req;
+ struct mdc_rmfid_args *aa;
+ struct mdt_body *b;
+ struct lu_fid *tmp;
+ int rc, flen;
+ ENTRY;
+
+ req = ptlrpc_request_alloc(class_exp2cliimp(exp), &RQF_MDS_RMFID);
+ if (req == NULL)
+ RETURN(-ENOMEM);
+
+ flen = fa->fa_nr * sizeof(struct lu_fid);
+ req_capsule_set_size(&req->rq_pill, &RMF_FID_ARRAY,
+ RCL_CLIENT, flen);
+ req_capsule_set_size(&req->rq_pill, &RMF_FID_ARRAY,
+ RCL_SERVER, flen);
+ req_capsule_set_size(&req->rq_pill, &RMF_RCS,
+ RCL_SERVER, fa->fa_nr * sizeof(__u32));
+ rc = ptlrpc_request_pack(req, LUSTRE_MDS_VERSION, MDS_RMFID);
+ if (rc) {
+ ptlrpc_request_free(req);
+ RETURN(rc);
+ }
+ tmp = req_capsule_client_get(&req->rq_pill, &RMF_FID_ARRAY);
+ memcpy(tmp, fa->fa_fids, flen);
+
+ mdc_pack_body(req, NULL, 0, 0, -1, 0);
+ b = req_capsule_client_get(&req->rq_pill, &RMF_MDT_BODY);
+ b->mbo_ctime = ktime_get_real_seconds();
+
+ ptlrpc_request_set_replen(req);
+
+ LASSERT(rcs);
+ aa = ptlrpc_req_async_args(aa, req);
+ aa->mra_rcs = rcs;
+ aa->mra_nr = fa->fa_nr;
+ req->rq_interpret_reply = mdc_rmfid_interpret;
+
+ ptlrpc_set_add_req(set, req);
+ ptlrpc_check_set(NULL, set);
+
+ RETURN(rc);
+}
+
static int mdc_import_event(struct obd_device *obd, struct obd_import *imp,
enum obd_import_event event)
{
if (lock->l_policy_data.l_inodebits.bits & MDS_INODELOCK_OPEN)
RETURN(0);
+ /* Special case for DoM locks, cancel only unused and granted locks */
+ if (ldlm_has_dom(lock) &&
+ (lock->l_granted_mode != lock->l_req_mode ||
+ osc_ldlm_weigh_ast(lock) != 0))
+ RETURN(0);
+
RETURN(1);
}
if (rc)
GOTO(err_osc_cleanup, rc);
+ obd->u.cli.cl_dom_min_inline_repsize = MDC_DOM_DEF_INLINE_REPSIZE;
+
ns_register_cancel(obd->obd_namespace, mdc_cancel_weight);
obd->obd_namespace->ns_lvbo = &inode_lvbo;
return osc_cleanup_common(obd);
}
-int mdc_process_config(struct obd_device *obd, size_t len, void *buf)
-{
- struct lustre_cfg *lcfg = buf;
- size_t count = class_modify_config(lcfg, PARAM_MDC,
- &obd->obd_kset.kobj);
-
- return count > 0 ? 0 : count;
-}
-
-static struct obd_ops mdc_obd_ops = {
- .o_owner = THIS_MODULE,
- .o_setup = mdc_setup,
- .o_precleanup = mdc_precleanup,
- .o_cleanup = mdc_cleanup,
- .o_add_conn = client_import_add_conn,
- .o_del_conn = client_import_del_conn,
- .o_connect = client_connect_import,
+static const struct obd_ops mdc_obd_ops = {
+ .o_owner = THIS_MODULE,
+ .o_setup = mdc_setup,
+ .o_precleanup = mdc_precleanup,
+ .o_cleanup = mdc_cleanup,
+ .o_add_conn = client_import_add_conn,
+ .o_del_conn = client_import_del_conn,
+ .o_connect = client_connect_import,
.o_reconnect = osc_reconnect,
.o_disconnect = osc_disconnect,
- .o_iocontrol = mdc_iocontrol,
- .o_set_info_async = mdc_set_info_async,
- .o_statfs = mdc_statfs,
+ .o_iocontrol = mdc_iocontrol,
+ .o_set_info_async = mdc_set_info_async,
+ .o_statfs = mdc_statfs,
+ .o_statfs_async = mdc_statfs_async,
.o_fid_init = client_fid_init,
.o_fid_fini = client_fid_fini,
- .o_fid_alloc = mdc_fid_alloc,
- .o_import_event = mdc_import_event,
- .o_get_info = mdc_get_info,
- .o_process_config = mdc_process_config,
- .o_get_uuid = mdc_get_uuid,
- .o_quotactl = mdc_quotactl,
+ .o_fid_alloc = mdc_fid_alloc,
+ .o_import_event = mdc_import_event,
+ .o_get_info = mdc_get_info,
+ .o_get_uuid = mdc_get_uuid,
+ .o_quotactl = mdc_quotactl,
};
-static struct md_ops mdc_md_ops = {
+static const struct md_ops mdc_md_ops = {
.m_get_root = mdc_get_root,
- .m_null_inode = mdc_null_inode,
- .m_close = mdc_close,
- .m_create = mdc_create,
- .m_enqueue = mdc_enqueue,
- .m_getattr = mdc_getattr,
- .m_getattr_name = mdc_getattr_name,
- .m_intent_lock = mdc_intent_lock,
- .m_link = mdc_link,
- .m_rename = mdc_rename,
- .m_setattr = mdc_setattr,
- .m_setxattr = mdc_setxattr,
- .m_getxattr = mdc_getxattr,
+ .m_null_inode = mdc_null_inode,
+ .m_close = mdc_close,
+ .m_create = mdc_create,
+ .m_enqueue = mdc_enqueue,
+ .m_getattr = mdc_getattr,
+ .m_getattr_name = mdc_getattr_name,
+ .m_intent_lock = mdc_intent_lock,
+ .m_link = mdc_link,
+ .m_rename = mdc_rename,
+ .m_setattr = mdc_setattr,
+ .m_setxattr = mdc_setxattr,
+ .m_getxattr = mdc_getxattr,
.m_fsync = mdc_fsync,
.m_file_resync = mdc_file_resync,
.m_read_page = mdc_read_page,
- .m_unlink = mdc_unlink,
- .m_cancel_unused = mdc_cancel_unused,
- .m_init_ea_size = mdc_init_ea_size,
- .m_set_lock_data = mdc_set_lock_data,
- .m_lock_match = mdc_lock_match,
- .m_get_lustre_md = mdc_get_lustre_md,
- .m_free_lustre_md = mdc_free_lustre_md,
- .m_set_open_replay_data = mdc_set_open_replay_data,
- .m_clear_open_replay_data = mdc_clear_open_replay_data,
- .m_intent_getattr_async = mdc_intent_getattr_async,
- .m_revalidate_lock = mdc_revalidate_lock
+ .m_unlink = mdc_unlink,
+ .m_cancel_unused = mdc_cancel_unused,
+ .m_init_ea_size = mdc_init_ea_size,
+ .m_set_lock_data = mdc_set_lock_data,
+ .m_lock_match = mdc_lock_match,
+ .m_get_lustre_md = mdc_get_lustre_md,
+ .m_free_lustre_md = mdc_free_lustre_md,
+ .m_set_open_replay_data = mdc_set_open_replay_data,
+ .m_clear_open_replay_data = mdc_clear_open_replay_data,
+ .m_intent_getattr_async = mdc_intent_getattr_async,
+ .m_revalidate_lock = mdc_revalidate_lock,
+ .m_rmfid = mdc_rmfid,
};
+dev_t mdc_changelog_dev;
+struct class *mdc_changelog_class;
static int __init mdc_init(void)
{
- return class_register_type(&mdc_obd_ops, &mdc_md_ops, true, NULL,
- LUSTRE_MDC_NAME, &mdc_device_type);
+ int rc = 0;
+ rc = alloc_chrdev_region(&mdc_changelog_dev, 0,
+ MDC_CHANGELOG_DEV_COUNT,
+ MDC_CHANGELOG_DEV_NAME);
+ if (rc)
+ return rc;
+
+ mdc_changelog_class = class_create(THIS_MODULE, MDC_CHANGELOG_DEV_NAME);
+ if (IS_ERR(mdc_changelog_class)) {
+ rc = PTR_ERR(mdc_changelog_class);
+ goto out_dev;
+ }
+
+ rc = class_register_type(&mdc_obd_ops, &mdc_md_ops, true, NULL,
+ LUSTRE_MDC_NAME, &mdc_device_type);
+ if (rc)
+ goto out_class;
+
+ return 0;
+
+out_class:
+ class_destroy(mdc_changelog_class);
+out_dev:
+ unregister_chrdev_region(mdc_changelog_dev, MDC_CHANGELOG_DEV_COUNT);
+ return rc;
}
static void __exit mdc_exit(void)
{
- class_unregister_type(LUSTRE_MDC_NAME);
+ class_unregister_type(LUSTRE_MDC_NAME);
+ class_destroy(mdc_changelog_class);
+ unregister_chrdev_region(mdc_changelog_dev, MDC_CHANGELOG_DEV_COUNT);
+ idr_destroy(&mdc_changelog_minor_idr);
}
MODULE_AUTHOR("OpenSFS, Inc. <http://www.lustre.org/>");