-/* -*- mode: c; c-basic-offset: 8; indent-tabs-mode: nil; -*-
- * vim:expandtab:shiftwidth=8:tabstop=8:
- *
+/*
* GPL HEADER START
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
- * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
- *
- * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
- * CA 95054 USA or visit www.sun.com if you need additional information or
- * have any questions.
+ * http://www.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
/*
* Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
+ *
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
*/
#define DEBUG_SUBSYSTEM S_MDC
-#ifndef __KERNEL__
-# include <fcntl.h>
-# include <liblustre.h>
+#include <linux/user_namespace.h>
+#ifdef HAVE_UIDGID_HEADER
+# include <linux/uidgid.h>
#endif
#include <lustre_net.h>
-#include <lustre/lustre_idl.h>
+#include <obd_class.h>
+#include <obd.h>
+#include <cl_object.h>
#include "mdc_internal.h"
-#ifndef __KERNEL__
-/* some liblustre hackings here */
-#ifndef O_DIRECTORY
-#define O_DIRECTORY 0
-#endif
-#endif
+static void set_mrc_cr_flags(struct mdt_rec_create *mrc, __u64 flags)
+{
+ mrc->cr_flags_l = (__u32)(flags & 0xFFFFFFFFUll);
+ mrc->cr_flags_h = (__u32)(flags >> 32);
+}
static void __mdc_pack_body(struct mdt_body *b, __u32 suppgid)
{
- LASSERT (b != NULL);
-
- b->suppgid = suppgid;
- b->uid = cfs_curproc_uid();
- b->gid = cfs_curproc_gid();
- b->fsuid = cfs_curproc_fsuid();
- b->fsgid = cfs_curproc_fsgid();
- b->capability = cfs_curproc_cap_pack();
+ LASSERT (b != NULL);
+
+ b->mbo_suppgid = suppgid;
+ b->mbo_uid = from_kuid(&init_user_ns, current_uid());
+ b->mbo_gid = from_kgid(&init_user_ns, current_gid());
+ b->mbo_fsuid = from_kuid(&init_user_ns, current_fsuid());
+ b->mbo_fsgid = from_kgid(&init_user_ns, current_fsgid());
+ b->mbo_capability = cfs_curproc_cap_pack();
+}
+
+void mdc_swap_layouts_pack(struct ptlrpc_request *req,
+ struct md_op_data *op_data)
+{
+ struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
+ &RMF_MDT_BODY);
+
+ __mdc_pack_body(b, op_data->op_suppgids[0]);
+ b->mbo_fid1 = op_data->op_fid1;
+ b->mbo_fid2 = op_data->op_fid2;
+ b->mbo_valid |= OBD_MD_FLID;
}
-void mdc_pack_capa(struct ptlrpc_request *req, const struct req_msg_field *field,
- struct obd_capa *oc)
+void mdc_pack_body(struct ptlrpc_request *req, const struct lu_fid *fid,
+ u64 valid, size_t ea_size, u32 suppgid, u32 flags)
{
- struct req_capsule *pill = &req->rq_pill;
- struct lustre_capa *c;
-
- if (oc == NULL) {
- LASSERT(req_capsule_get_size(pill, field, RCL_CLIENT) == 0);
- return;
- }
-
- c = req_capsule_client_get(pill, field);
- LASSERT(c != NULL);
- capa_cpy(c, oc);
- DEBUG_CAPA(D_SEC, c, "pack");
+ struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
+ &RMF_MDT_BODY);
+ LASSERT(b != NULL);
+ b->mbo_valid = valid;
+ b->mbo_eadatasize = ea_size;
+ b->mbo_flags = flags;
+ __mdc_pack_body(b, suppgid);
+ if (fid) {
+ b->mbo_fid1 = *fid;
+ b->mbo_valid |= OBD_MD_FLID;
+ }
}
-void mdc_is_subdir_pack(struct ptlrpc_request *req, const struct lu_fid *pfid,
- const struct lu_fid *cfid, int flags)
+/**
+ * Pack a name (path component) into a request
+ *
+ * \param[in] req request
+ * \param[in] field request field (usually RMF_NAME)
+ * \param[in] name path component
+ * \param[in] name_len length of path component
+ *
+ * \a field must be present in \a req and of size \a name_len + 1.
+ *
+ * \a name must be '\0' terminated of length \a name_len and represent
+ * a single path component (not contain '/').
+ */
+static void mdc_pack_name(struct ptlrpc_request *req,
+ const struct req_msg_field *field,
+ const char *name, size_t name_len)
{
- struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
- &RMF_MDT_BODY);
+ char *buf;
+ size_t buf_size;
+ size_t cpy_len;
- if (pfid) {
- b->fid1 = *pfid;
- b->valid = OBD_MD_FLID;
- }
- if (cfid)
- b->fid2 = *cfid;
- b->flags = flags;
+ buf = req_capsule_client_get(&req->rq_pill, field);
+ buf_size = req_capsule_get_size(&req->rq_pill, field, RCL_CLIENT);
+
+ LASSERT(name != NULL && name_len != 0 &&
+ buf != NULL && buf_size == name_len + 1);
+
+ cpy_len = strlcpy(buf, name, buf_size);
+
+ LASSERT(lu_name_is_valid_2(buf, cpy_len));
+ if (cpy_len != name_len)
+ CDEBUG(D_DENTRY, "%s: %s len %zd != %zd, concurrent rename?\n",
+ req->rq_export->exp_obd->obd_name, buf, name_len,
+ cpy_len);
}
-void mdc_pack_body(struct ptlrpc_request *req,
- const struct lu_fid *fid, struct obd_capa *oc,
- __u64 valid, int ea_size, __u32 suppgid, int flags)
+void mdc_file_secctx_pack(struct ptlrpc_request *req, const char *secctx_name,
+ const void *secctx, size_t secctx_size)
{
- struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
- &RMF_MDT_BODY);
- LASSERT(b != NULL);
- b->valid = valid;
- b->eadatasize = ea_size;
- b->flags = flags;
- __mdc_pack_body(b, suppgid);
- if (fid) {
- b->fid1 = *fid;
- b->valid |= OBD_MD_FLID;
- mdc_pack_capa(req, &RMF_CAPA1, oc);
- }
+ void *buf;
+ size_t buf_size;
+
+ if (secctx_name == NULL)
+ return;
+
+ buf = req_capsule_client_get(&req->rq_pill, &RMF_FILE_SECCTX_NAME);
+ buf_size = req_capsule_get_size(&req->rq_pill, &RMF_FILE_SECCTX_NAME,
+ RCL_CLIENT);
+
+ LASSERT(buf_size == strlen(secctx_name) + 1);
+ memcpy(buf, secctx_name, buf_size);
+
+ buf = req_capsule_client_get(&req->rq_pill, &RMF_FILE_SECCTX);
+ buf_size = req_capsule_get_size(&req->rq_pill, &RMF_FILE_SECCTX,
+ RCL_CLIENT);
+
+ LASSERT(buf_size == secctx_size);
+ memcpy(buf, secctx, buf_size);
}
-void mdc_readdir_pack(struct ptlrpc_request *req, __u64 pgoff,
- __u32 size, const struct lu_fid *fid, struct obd_capa *oc)
+void mdc_file_sepol_pack(struct ptlrpc_request *req)
+{
+ void *buf;
+ size_t buf_size;
+
+ if (strlen(req->rq_sepol) == 0)
+ return;
+
+ buf = req_capsule_client_get(&req->rq_pill, &RMF_SELINUX_POL);
+ buf_size = req_capsule_get_size(&req->rq_pill, &RMF_SELINUX_POL,
+ RCL_CLIENT);
+
+ LASSERT(buf_size == strlen(req->rq_sepol) + 1);
+ snprintf(buf, strlen(req->rq_sepol) + 1, "%s", req->rq_sepol);
+}
+
+void mdc_readdir_pack(struct ptlrpc_request *req, __u64 pgoff, size_t size,
+ const struct lu_fid *fid)
{
struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
&RMF_MDT_BODY);
- b->fid1 = *fid;
- b->valid |= OBD_MD_FLID;
- b->size = pgoff; /* !! */
- b->nlink = size; /* !! */
- __mdc_pack_body(b, -1);
- b->mode = LUDA_FID | LUDA_TYPE;
-
- mdc_pack_capa(req, &RMF_CAPA1, oc);
+ b->mbo_fid1 = *fid;
+ b->mbo_valid |= OBD_MD_FLID;
+ b->mbo_size = pgoff; /* !! */
+ b->mbo_nlink = size; /* !! */
+ __mdc_pack_body(b, -1);
+ b->mbo_mode = LUDA_FID | LUDA_TYPE;
}
/* packing of MDS records */
void mdc_create_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
- const void *data, int datalen, __u32 mode,
- __u32 uid, __u32 gid, cfs_cap_t cap_effective, __u64 rdev)
+ const void *data, size_t datalen, umode_t mode,
+ uid_t uid, gid_t gid, cfs_cap_t cap_effective, __u64 rdev)
{
- struct mdt_rec_create *rec;
- char *tmp;
-
- CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_create));
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
-
-
- rec->cr_opcode = REINT_CREATE;
- rec->cr_fsuid = uid;
- rec->cr_fsgid = gid;
- rec->cr_cap = cap_effective;
- rec->cr_fid1 = op_data->op_fid1;
- rec->cr_fid2 = op_data->op_fid2;
- rec->cr_mode = mode;
- rec->cr_rdev = rdev;
- rec->cr_time = op_data->op_mod_time;
- rec->cr_suppgid1 = op_data->op_suppgids[0];
- rec->cr_suppgid2 = op_data->op_suppgids[1];
- set_mrc_cr_flags(rec, op_data->op_flags & MF_SOM_LOCAL_FLAGS);
- rec->cr_bias = op_data->op_bias;
-
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
-
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LOGL0(op_data->op_name, op_data->op_namelen, tmp);
-
- if (data) {
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
- memcpy(tmp, data, datalen);
- }
+ struct mdt_rec_create *rec;
+ char *tmp;
+ __u64 flags;
+
+ CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_create));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+
+
+ rec->cr_opcode = REINT_CREATE;
+ rec->cr_fsuid = uid;
+ rec->cr_fsgid = gid;
+ rec->cr_cap = cap_effective;
+ rec->cr_fid1 = op_data->op_fid1;
+ rec->cr_fid2 = op_data->op_fid2;
+ rec->cr_mode = mode;
+ rec->cr_rdev = rdev;
+ rec->cr_time = op_data->op_mod_time;
+ rec->cr_suppgid1 = op_data->op_suppgids[0];
+ rec->cr_suppgid2 = op_data->op_suppgids[1];
+ flags = 0;
+ if (op_data->op_bias & MDS_CREATE_VOLATILE)
+ flags |= MDS_OPEN_VOLATILE;
+ set_mrc_cr_flags(rec, flags);
+ rec->cr_bias = op_data->op_bias;
+ rec->cr_umask = current_umask();
+
+ mdc_pack_name(req, &RMF_NAME, op_data->op_name, op_data->op_namelen);
+ if (data) {
+ tmp = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
+ memcpy(tmp, data, datalen);
+ }
+
+ mdc_file_secctx_pack(req, op_data->op_file_secctx_name,
+ op_data->op_file_secctx,
+ op_data->op_file_secctx_size);
+
+ /* pack SELinux policy info if any */
+ mdc_file_sepol_pack(req);
}
-static __u64 mds_pack_open_flags(__u32 flags, __u32 mode)
+static inline __u64 mds_pack_open_flags(__u64 flags)
{
- __u64 cr_flags = (flags & (FMODE_READ | FMODE_WRITE |
- MDS_OPEN_HAS_EA | MDS_OPEN_HAS_OBJS |
- MDS_OPEN_OWNEROVERRIDE | MDS_OPEN_LOCK));
- if (flags & O_CREAT)
- cr_flags |= MDS_OPEN_CREAT;
- if (flags & O_EXCL)
- cr_flags |= MDS_OPEN_EXCL;
- if (flags & O_TRUNC)
- cr_flags |= MDS_OPEN_TRUNC;
- if (flags & O_APPEND)
- cr_flags |= MDS_OPEN_APPEND;
- if (flags & O_SYNC)
- cr_flags |= MDS_OPEN_SYNC;
- if (flags & O_DIRECTORY)
- cr_flags |= MDS_OPEN_DIRECTORY;
+ __u64 cr_flags = (flags & MDS_OPEN_FL_INTERNAL);
+
+ if (flags & FMODE_READ)
+ cr_flags |= MDS_FMODE_READ;
+ if (flags & FMODE_WRITE)
+ cr_flags |= MDS_FMODE_WRITE;
+ if (flags & O_CREAT)
+ cr_flags |= MDS_OPEN_CREAT;
+ if (flags & O_EXCL)
+ cr_flags |= MDS_OPEN_EXCL;
+ if (flags & O_TRUNC)
+ cr_flags |= MDS_OPEN_TRUNC;
+ if (flags & O_APPEND)
+ cr_flags |= MDS_OPEN_APPEND;
+ if (flags & O_SYNC)
+ cr_flags |= MDS_OPEN_SYNC;
+ if (flags & O_DIRECTORY)
+ cr_flags |= MDS_OPEN_DIRECTORY;
#ifdef FMODE_EXEC
- if (flags & FMODE_EXEC)
- cr_flags |= MDS_FMODE_EXEC;
+ if (flags & FMODE_EXEC)
+ cr_flags |= MDS_FMODE_EXEC;
#endif
- if (flags & O_LOV_DELAY_CREATE)
- cr_flags |= MDS_OPEN_DELAY_CREATE;
+ if (cl_is_lov_delay_create(flags))
+ cr_flags |= MDS_OPEN_DELAY_CREATE;
- if ((flags & O_NOACCESS) || (flags & O_NONBLOCK))
- cr_flags |= MDS_OPEN_NORESTORE;
+ if (flags & O_NONBLOCK)
+ cr_flags |= MDS_OPEN_NORESTORE;
- return cr_flags;
+ return cr_flags;
}
/* packing of MDS records */
void mdc_open_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
- __u32 mode, __u64 rdev, __u32 flags, const void *lmm,
- int lmmlen)
+ umode_t mode, __u64 rdev, __u64 flags, const void *lmm,
+ size_t lmmlen)
{
- struct mdt_rec_create *rec;
- char *tmp;
- __u64 cr_flags;
-
- CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_create));
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
-
- /* XXX do something about time, uid, gid */
- rec->cr_opcode = REINT_OPEN;
- rec->cr_fsuid = cfs_curproc_fsuid();
- rec->cr_fsgid = cfs_curproc_fsgid();
- rec->cr_cap = cfs_curproc_cap_pack();
- if (op_data != NULL) {
- rec->cr_fid1 = op_data->op_fid1;
- rec->cr_fid2 = op_data->op_fid2;
- }
- rec->cr_mode = mode;
- cr_flags = mds_pack_open_flags(flags, mode);
- rec->cr_rdev = rdev;
- rec->cr_time = op_data->op_mod_time;
- rec->cr_suppgid1 = op_data->op_suppgids[0];
- rec->cr_suppgid2 = op_data->op_suppgids[1];
- rec->cr_bias = op_data->op_bias;
-
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
- /* the next buffer is child capa, which is used for replay,
- * will be packed from the data in reply message. */
-
- if (op_data->op_name) {
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LOGL0(op_data->op_name, op_data->op_namelen, tmp);
- }
-
- if (lmm) {
- cr_flags |= MDS_OPEN_HAS_EA;
-#ifndef __KERNEL__
- /*XXX a hack for liblustre to set EA (LL_IOC_LOV_SETSTRIPE) */
- rec->cr_fid2 = op_data->op_fid2;
-#endif
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
- memcpy (tmp, lmm, lmmlen);
- }
- set_mrc_cr_flags(rec, cr_flags);
+ struct mdt_rec_create *rec;
+ char *tmp;
+ __u64 cr_flags;
+
+ CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_create));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+
+ /* XXX do something about time, uid, gid */
+ rec->cr_opcode = REINT_OPEN;
+ rec->cr_fsuid = from_kuid(&init_user_ns, current_fsuid());
+ rec->cr_fsgid = from_kgid(&init_user_ns, current_fsgid());
+ rec->cr_cap = cfs_curproc_cap_pack();
+ rec->cr_mode = mode;
+ cr_flags = mds_pack_open_flags(flags);
+ rec->cr_rdev = rdev;
+ rec->cr_umask = current_umask();
+ if (op_data != NULL) {
+ rec->cr_fid1 = op_data->op_fid1;
+ rec->cr_fid2 = op_data->op_fid2;
+ rec->cr_time = op_data->op_mod_time;
+ rec->cr_suppgid1 = op_data->op_suppgids[0];
+ rec->cr_suppgid2 = op_data->op_suppgids[1];
+ rec->cr_bias = op_data->op_bias;
+ rec->cr_open_handle_old = op_data->op_open_handle;
+
+ if (op_data->op_name) {
+ mdc_pack_name(req, &RMF_NAME, op_data->op_name,
+ op_data->op_namelen);
+
+ if (op_data->op_bias & MDS_CREATE_VOLATILE)
+ cr_flags |= MDS_OPEN_VOLATILE;
+ }
+
+ mdc_file_secctx_pack(req, op_data->op_file_secctx_name,
+ op_data->op_file_secctx,
+ op_data->op_file_secctx_size);
+
+ /* pack SELinux policy info if any */
+ mdc_file_sepol_pack(req);
+ }
+
+ if (lmm) {
+ cr_flags |= MDS_OPEN_HAS_EA;
+ tmp = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
+ memcpy(tmp, lmm, lmmlen);
+ if (cr_flags & MDS_OPEN_PCC) {
+ LASSERT(op_data != NULL);
+ rec->cr_archive_id = op_data->op_archive_id;
+ }
+ }
+ set_mrc_cr_flags(rec, cr_flags);
}
-static inline __u64 attr_pack(unsigned int ia_valid) {
- __u64 sa_valid = 0;
+static inline u64 attr_pack(unsigned int ia_valid, enum op_xvalid ia_xvalid)
+{
+ u64 sa_valid = 0;
if (ia_valid & ATTR_MODE)
sa_valid |= MDS_ATTR_MODE;
sa_valid |= MDS_ATTR_MTIME_SET;
if (ia_valid & ATTR_FORCE)
sa_valid |= MDS_ATTR_FORCE;
- if (ia_valid & ATTR_ATTR_FLAG)
- sa_valid |= MDS_ATTR_ATTR_FLAG;
- if (ia_valid & ATTR_KILL_SUID)
- sa_valid |= MDS_ATTR_KILL_SUID;
- if (ia_valid & ATTR_KILL_SGID)
- sa_valid |= MDS_ATTR_KILL_SGID;
- if (ia_valid & ATTR_CTIME_SET)
- sa_valid |= MDS_ATTR_CTIME_SET;
- if (ia_valid & ATTR_FROM_OPEN)
- sa_valid |= MDS_ATTR_FROM_OPEN;
- if (ia_valid & ATTR_BLOCKS)
- sa_valid |= MDS_ATTR_BLOCKS;
- if (ia_valid & MDS_OPEN_OWNEROVERRIDE)
- /* NFSD hack (see bug 5781) */
- sa_valid |= MDS_OPEN_OWNEROVERRIDE;
+ if (ia_xvalid & OP_XVALID_FLAGS)
+ sa_valid |= MDS_ATTR_ATTR_FLAG;
+ if (ia_valid & ATTR_KILL_SUID)
+ sa_valid |= MDS_ATTR_KILL_SUID;
+ if (ia_valid & ATTR_KILL_SGID)
+ sa_valid |= MDS_ATTR_KILL_SGID;
+ if (ia_xvalid & OP_XVALID_CTIME_SET)
+ sa_valid |= MDS_ATTR_CTIME_SET;
+ if (ia_valid & ATTR_OPEN)
+ sa_valid |= MDS_ATTR_FROM_OPEN;
+ if (ia_xvalid & OP_XVALID_BLOCKS)
+ sa_valid |= MDS_ATTR_BLOCKS;
+ if (ia_xvalid & OP_XVALID_OWNEROVERRIDE)
+ /* NFSD hack (see bug 5781) */
+ sa_valid |= MDS_OPEN_OWNEROVERRIDE;
+ if (ia_xvalid & OP_XVALID_PROJID)
+ sa_valid |= MDS_ATTR_PROJID;
+ if (ia_xvalid & OP_XVALID_LAZYSIZE)
+ sa_valid |= MDS_ATTR_LSIZE;
+ if (ia_xvalid & OP_XVALID_LAZYBLOCKS)
+ sa_valid |= MDS_ATTR_LBLOCKS;
return sa_valid;
}
static void mdc_setattr_pack_rec(struct mdt_rec_setattr *rec,
- struct md_op_data *op_data)
+ struct md_op_data *op_data)
{
- rec->sa_opcode = REINT_SETATTR;
- rec->sa_fsuid = cfs_curproc_fsuid();
- rec->sa_fsgid = cfs_curproc_fsgid();
- rec->sa_cap = cfs_curproc_cap_pack();
- rec->sa_suppgid = -1;
-
- rec->sa_fid = op_data->op_fid1;
- rec->sa_valid = attr_pack(op_data->op_attr.ia_valid);
- rec->sa_mode = op_data->op_attr.ia_mode;
- rec->sa_uid = op_data->op_attr.ia_uid;
- rec->sa_gid = op_data->op_attr.ia_gid;
- rec->sa_size = op_data->op_attr.ia_size;
- rec->sa_blocks = op_data->op_attr_blocks;
- rec->sa_atime = LTIME_S(op_data->op_attr.ia_atime);
- rec->sa_mtime = LTIME_S(op_data->op_attr.ia_mtime);
- rec->sa_ctime = LTIME_S(op_data->op_attr.ia_ctime);
- rec->sa_attr_flags = ((struct ll_iattr *)&op_data->op_attr)->ia_attr_flags;
- if ((op_data->op_attr.ia_valid & ATTR_GID) &&
- cfs_curproc_is_in_groups(op_data->op_attr.ia_gid))
- rec->sa_suppgid = op_data->op_attr.ia_gid;
- else
- rec->sa_suppgid = op_data->op_suppgids[0];
+ rec->sa_opcode = REINT_SETATTR;
+ rec->sa_fsuid = from_kuid(&init_user_ns, current_fsuid());
+ rec->sa_fsgid = from_kgid(&init_user_ns, current_fsgid());
+ rec->sa_cap = cfs_curproc_cap_pack();
+ rec->sa_suppgid = -1;
+
+ rec->sa_fid = op_data->op_fid1;
+ rec->sa_valid = attr_pack(op_data->op_attr.ia_valid,
+ op_data->op_xvalid);
+ rec->sa_mode = op_data->op_attr.ia_mode;
+ rec->sa_uid = from_kuid(&init_user_ns, op_data->op_attr.ia_uid);
+ rec->sa_gid = from_kgid(&init_user_ns, op_data->op_attr.ia_gid);
+ rec->sa_projid = op_data->op_projid;
+ rec->sa_size = op_data->op_attr.ia_size;
+ rec->sa_blocks = op_data->op_attr_blocks;
+ rec->sa_atime = op_data->op_attr.ia_atime.tv_sec;
+ rec->sa_mtime = op_data->op_attr.ia_mtime.tv_sec;
+ rec->sa_ctime = op_data->op_attr.ia_ctime.tv_sec;
+ rec->sa_attr_flags = op_data->op_attr_flags;
+ if ((op_data->op_attr.ia_valid & ATTR_GID) &&
+ in_group_p(op_data->op_attr.ia_gid))
+ rec->sa_suppgid =
+ from_kgid(&init_user_ns, op_data->op_attr.ia_gid);
+ else
+ rec->sa_suppgid = op_data->op_suppgids[0];
+
+ rec->sa_bias = op_data->op_bias;
}
static void mdc_ioepoch_pack(struct mdt_ioepoch *epoch,
- struct md_op_data *op_data)
+ struct md_op_data *op_data)
{
- memcpy(&epoch->handle, &op_data->op_handle, sizeof(epoch->handle));
- epoch->ioepoch = op_data->op_ioepoch;
- epoch->flags = op_data->op_flags & MF_SOM_LOCAL_FLAGS;
+ epoch->mio_open_handle = op_data->op_open_handle;
+ epoch->mio_unused1 = 0;
+ epoch->mio_unused2 = 0;
+ epoch->mio_padding = 0;
}
void mdc_setattr_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
- void *ea, int ealen, void *ea2, int ea2len)
+ void *ea, size_t ealen)
{
- struct mdt_rec_setattr *rec;
- struct mdt_ioepoch *epoch;
- struct lov_user_md *lum = NULL;
-
- CLASSERT(sizeof(struct mdt_rec_reint) ==sizeof(struct mdt_rec_setattr));
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
- mdc_setattr_pack_rec(rec, op_data);
-
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
-
- if (op_data->op_flags & (MF_SOM_CHANGE | MF_EPOCH_OPEN)) {
- epoch = req_capsule_client_get(&req->rq_pill, &RMF_MDT_EPOCH);
- mdc_ioepoch_pack(epoch, op_data);
- }
-
- if (ealen == 0)
- return;
-
- lum = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
- if (ea == NULL) { /* Remove LOV EA */
- lum->lmm_magic = LOV_USER_MAGIC_V1;
- lum->lmm_stripe_size = 0;
- lum->lmm_stripe_count = 0;
- lum->lmm_stripe_offset = (typeof(lum->lmm_stripe_offset))(-1);
- } else {
- memcpy(lum, ea, ealen);
- }
-
- if (ea2len == 0)
- return;
-
- memcpy(req_capsule_client_get(&req->rq_pill, &RMF_LOGCOOKIES), ea2,
- ea2len);
+ struct mdt_rec_setattr *rec;
+ struct lov_user_md *lum = NULL;
+
+ CLASSERT(sizeof(struct mdt_rec_reint) ==
+ sizeof(struct mdt_rec_setattr));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+ mdc_setattr_pack_rec(rec, op_data);
+
+ if (ealen == 0)
+ return;
+
+ lum = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
+ if (ea == NULL) { /* Remove LOV EA */
+ lum->lmm_magic = cpu_to_le32(LOV_USER_MAGIC_V1);
+ lum->lmm_stripe_size = 0;
+ lum->lmm_stripe_count = 0;
+ lum->lmm_stripe_offset =
+ (typeof(lum->lmm_stripe_offset))LOV_OFFSET_DEFAULT;
+ } else {
+ memcpy(lum, ea, ealen);
+ }
}
void mdc_unlink_pack(struct ptlrpc_request *req, struct md_op_data *op_data)
{
- struct mdt_rec_unlink *rec;
- char *tmp;
-
- CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_unlink));
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
- LASSERT (rec != NULL);
+ struct mdt_rec_unlink *rec;
- rec->ul_opcode = REINT_UNLINK;
+ CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_unlink));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+ LASSERT(rec != NULL);
+
+ rec->ul_opcode = op_data->op_cli_flags & CLI_RM_ENTRY ?
+ REINT_RMENTRY : REINT_UNLINK;
rec->ul_fsuid = op_data->op_fsuid;
rec->ul_fsgid = op_data->op_fsgid;
rec->ul_cap = op_data->op_cap;
rec->ul_time = op_data->op_mod_time;
rec->ul_bias = op_data->op_bias;
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
+ mdc_pack_name(req, &RMF_NAME, op_data->op_name, op_data->op_namelen);
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LASSERT(tmp != NULL);
- LOGL0(op_data->op_name, op_data->op_namelen, tmp);
+ /* pack SELinux policy info if any */
+ mdc_file_sepol_pack(req);
}
void mdc_link_pack(struct ptlrpc_request *req, struct md_op_data *op_data)
{
struct mdt_rec_link *rec;
- char *tmp;
CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_link));
rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
rec->lk_time = op_data->op_mod_time;
rec->lk_bias = op_data->op_bias;
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
- mdc_pack_capa(req, &RMF_CAPA2, op_data->op_capa2);
+ mdc_pack_name(req, &RMF_NAME, op_data->op_name, op_data->op_namelen);
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LOGL0(op_data->op_name, op_data->op_namelen, tmp);
+ /* pack SELinux policy info if any */
+ mdc_file_sepol_pack(req);
}
-void mdc_rename_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
- const char *old, int oldlen, const char *new, int newlen)
+static void mdc_close_intent_pack(struct ptlrpc_request *req,
+ struct md_op_data *op_data)
{
- struct mdt_rec_rename *rec;
- char *tmp;
+ struct close_data *data;
+ struct ldlm_lock *lock;
+ enum mds_op_bias bias = op_data->op_bias;
+
+ if (!(bias & (MDS_CLOSE_INTENT | MDS_CLOSE_MIGRATE)))
+ return;
+
+ data = req_capsule_client_get(&req->rq_pill, &RMF_CLOSE_DATA);
+ LASSERT(data != NULL);
+
+ lock = ldlm_handle2lock(&op_data->op_lease_handle);
+ if (lock != NULL) {
+ data->cd_handle = lock->l_remote_handle;
+ LDLM_LOCK_PUT(lock);
+ }
+ ldlm_cli_cancel(&op_data->op_lease_handle, LCF_LOCAL);
+
+ data->cd_data_version = op_data->op_data_version;
+ data->cd_fid = op_data->op_fid2;
+
+ if (bias & MDS_CLOSE_LAYOUT_SPLIT) {
+ data->cd_mirror_id = op_data->op_mirror_id;
+ } else if (bias & MDS_CLOSE_RESYNC_DONE) {
+ struct close_data_resync_done *sync = &data->cd_resync;
+
+ CLASSERT(sizeof(data->cd_resync) <= sizeof(data->cd_reserved));
+ sync->resync_count = op_data->op_data_size / sizeof(__u32);
+ if (sync->resync_count <= INLINE_RESYNC_ARRAY_SIZE) {
+ memcpy(sync->resync_ids_inline, op_data->op_data,
+ op_data->op_data_size);
+ } else {
+ size_t count = sync->resync_count;
+
+ memcpy(req_capsule_client_get(&req->rq_pill, &RMF_U32),
+ op_data->op_data, count * sizeof(__u32));
+ }
+ } else if (bias & MDS_PCC_ATTACH) {
+ data->cd_archive_id = op_data->op_archive_id;
+ }
+}
- CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_rename));
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+void mdc_rename_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
+ const char *old, size_t oldlen,
+ const char *new, size_t newlen)
+{
+ struct mdt_rec_rename *rec;
+
+ CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_rename));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+
+ /* XXX do something about time, uid, gid */
+ rec->rn_opcode = REINT_RENAME;
+ rec->rn_fsuid = op_data->op_fsuid;
+ rec->rn_fsgid = op_data->op_fsgid;
+ rec->rn_cap = op_data->op_cap;
+ rec->rn_suppgid1 = op_data->op_suppgids[0];
+ rec->rn_suppgid2 = op_data->op_suppgids[1];
+ rec->rn_fid1 = op_data->op_fid1;
+ rec->rn_fid2 = op_data->op_fid2;
+ rec->rn_time = op_data->op_mod_time;
+ rec->rn_mode = op_data->op_mode;
+ rec->rn_bias = op_data->op_bias;
+
+ mdc_pack_name(req, &RMF_NAME, old, oldlen);
+
+ if (new != NULL)
+ mdc_pack_name(req, &RMF_SYMTGT, new, newlen);
+
+ /* pack SELinux policy info if any */
+ mdc_file_sepol_pack(req);
+}
- /* XXX do something about time, uid, gid */
- rec->rn_opcode = REINT_RENAME;
- rec->rn_fsuid = op_data->op_fsuid;
- rec->rn_fsgid = op_data->op_fsgid;
- rec->rn_cap = op_data->op_cap;
- rec->rn_suppgid1 = op_data->op_suppgids[0];
- rec->rn_suppgid2 = op_data->op_suppgids[1];
- rec->rn_fid1 = op_data->op_fid1;
- rec->rn_fid2 = op_data->op_fid2;
- rec->rn_time = op_data->op_mod_time;
- rec->rn_mode = op_data->op_mode;
- rec->rn_bias = op_data->op_bias;
-
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
- mdc_pack_capa(req, &RMF_CAPA2, op_data->op_capa2);
-
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LOGL0(old, oldlen, tmp);
-
- if (new) {
- tmp = req_capsule_client_get(&req->rq_pill, &RMF_SYMTGT);
- LOGL0(new, newlen, tmp);
- }
+void mdc_migrate_pack(struct ptlrpc_request *req, struct md_op_data *op_data,
+ const char *name, size_t namelen)
+{
+ struct mdt_rec_rename *rec;
+ char *ea;
+
+ CLASSERT(sizeof(struct mdt_rec_reint) == sizeof(struct mdt_rec_rename));
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+
+ rec->rn_opcode = REINT_MIGRATE;
+ rec->rn_fsuid = op_data->op_fsuid;
+ rec->rn_fsgid = op_data->op_fsgid;
+ rec->rn_cap = op_data->op_cap;
+ rec->rn_suppgid1 = op_data->op_suppgids[0];
+ rec->rn_suppgid2 = op_data->op_suppgids[1];
+ rec->rn_fid1 = op_data->op_fid1;
+ rec->rn_fid2 = op_data->op_fid4;
+ rec->rn_time = op_data->op_mod_time;
+ rec->rn_mode = op_data->op_mode;
+ rec->rn_bias = op_data->op_bias;
+
+ mdc_pack_name(req, &RMF_NAME, name, namelen);
+
+ if (op_data->op_bias & MDS_CLOSE_MIGRATE) {
+ struct mdt_ioepoch *epoch;
+
+ mdc_close_intent_pack(req, op_data);
+ epoch = req_capsule_client_get(&req->rq_pill, &RMF_MDT_EPOCH);
+ mdc_ioepoch_pack(epoch, op_data);
+ }
+
+ ea = req_capsule_client_get(&req->rq_pill, &RMF_EADATA);
+ memcpy(ea, op_data->op_data, op_data->op_data_size);
}
-void mdc_getattr_pack(struct ptlrpc_request *req, __u64 valid, int flags,
- struct md_op_data *op_data, int ea_size)
+void mdc_getattr_pack(struct ptlrpc_request *req, __u64 valid, __u32 flags,
+ struct md_op_data *op_data, size_t ea_size)
{
struct mdt_body *b = req_capsule_client_get(&req->rq_pill,
&RMF_MDT_BODY);
- b->valid = valid;
- if (op_data->op_bias & MDS_CHECK_SPLIT)
- b->valid |= OBD_MD_FLCKSPLIT;
- if (op_data->op_bias & MDS_CROSS_REF)
- b->valid |= OBD_MD_FLCROSSREF;
- b->eadatasize = ea_size;
- b->flags = flags;
- __mdc_pack_body(b, op_data->op_suppgids[0]);
-
- b->fid1 = op_data->op_fid1;
- b->fid2 = op_data->op_fid2;
- b->valid |= OBD_MD_FLID;
+ b->mbo_valid = valid;
+ if (op_data->op_bias & MDS_CROSS_REF)
+ b->mbo_valid |= OBD_MD_FLCROSSREF;
+ b->mbo_eadatasize = ea_size;
+ b->mbo_flags = flags;
+ __mdc_pack_body(b, op_data->op_suppgids[0]);
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
+ b->mbo_fid1 = op_data->op_fid1;
+ b->mbo_fid2 = op_data->op_fid2;
+ b->mbo_valid |= OBD_MD_FLID;
- if (op_data->op_name) {
- char *tmp = req_capsule_client_get(&req->rq_pill, &RMF_NAME);
- LOGL0(op_data->op_name, op_data->op_namelen, tmp);
-
- }
+ if (op_data->op_name != NULL)
+ mdc_pack_name(req, &RMF_NAME, op_data->op_name,
+ op_data->op_namelen);
}
void mdc_close_pack(struct ptlrpc_request *req, struct md_op_data *op_data)
{
- struct mdt_ioepoch *epoch;
- struct mdt_rec_setattr *rec;
-
- epoch = req_capsule_client_get(&req->rq_pill, &RMF_MDT_EPOCH);
- rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
-
- mdc_setattr_pack_rec(rec, op_data);
- mdc_pack_capa(req, &RMF_CAPA1, op_data->op_capa1);
- mdc_ioepoch_pack(epoch, op_data);
-}
-
-static int mdc_req_avail(struct client_obd *cli, struct mdc_cache_waiter *mcw)
-{
- int rc;
- ENTRY;
- client_obd_list_lock(&cli->cl_loi_list_lock);
- rc = cfs_list_empty(&mcw->mcw_entry);
- client_obd_list_unlock(&cli->cl_loi_list_lock);
- RETURN(rc);
-};
-
-/* We record requests in flight in cli->cl_r_in_flight here.
- * There is only one write rpc possible in mdc anyway. If this to change
- * in the future - the code may need to be revisited. */
-void mdc_enter_request(struct client_obd *cli)
-{
- struct mdc_cache_waiter mcw;
- struct l_wait_info lwi = { 0 };
-
- client_obd_list_lock(&cli->cl_loi_list_lock);
- if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
- cfs_list_add_tail(&mcw.mcw_entry, &cli->cl_cache_waiters);
- cfs_waitq_init(&mcw.mcw_waitq);
- client_obd_list_unlock(&cli->cl_loi_list_lock);
- l_wait_event(mcw.mcw_waitq, mdc_req_avail(cli, &mcw), &lwi);
- } else {
- cli->cl_r_in_flight++;
- client_obd_list_unlock(&cli->cl_loi_list_lock);
- }
-}
-
-void mdc_exit_request(struct client_obd *cli)
-{
- cfs_list_t *l, *tmp;
- struct mdc_cache_waiter *mcw;
-
- client_obd_list_lock(&cli->cl_loi_list_lock);
- cli->cl_r_in_flight--;
- cfs_list_for_each_safe(l, tmp, &cli->cl_cache_waiters) {
- if (cli->cl_r_in_flight >= cli->cl_max_rpcs_in_flight) {
- /* No free request slots anymore */
- break;
- }
-
- mcw = cfs_list_entry(l, struct mdc_cache_waiter, mcw_entry);
- cfs_list_del_init(&mcw->mcw_entry);
- cli->cl_r_in_flight++;
- cfs_waitq_signal(&mcw->mcw_waitq);
- }
- /* Empty waiting list? Decrease reqs in-flight number */
-
- client_obd_list_unlock(&cli->cl_loi_list_lock);
+ struct mdt_ioepoch *epoch;
+ struct mdt_rec_setattr *rec;
+
+ epoch = req_capsule_client_get(&req->rq_pill, &RMF_MDT_EPOCH);
+ rec = req_capsule_client_get(&req->rq_pill, &RMF_REC_REINT);
+
+ mdc_setattr_pack_rec(rec, op_data);
+ /*
+ * The client will zero out local timestamps when losing the IBITS lock
+ * so any new RPC timestamps will update the client inode's timestamps.
+ * There was a defect on the server side which allowed the atime to be
+ * overwritten by a zeroed-out atime packed into the close RPC.
+ *
+ * Proactively clear the MDS_ATTR_ATIME flag in the RPC in this case
+ * to avoid zeroing the atime on old unpatched servers. See LU-8041.
+ */
+ if (rec->sa_atime == 0)
+ rec->sa_valid &= ~MDS_ATTR_ATIME;
+
+ mdc_ioepoch_pack(epoch, op_data);
+ mdc_close_intent_pack(req, op_data);
}