#define DEBUG_SUBSYSTEM S_LLITE
#include "../include/lustre_dlm.h"
-#include "../include/lustre_lite.h"
#include <linux/pagemap.h>
#include <linux/file.h>
+#include <linux/sched.h>
#include <linux/mount.h>
-#include "llite_internal.h"
#include "../include/lustre/ll_fiemap.h"
+#include "../include/lustre/lustre_ioctl.h"
#include "../include/cl_object.h"
+#include "llite_internal.h"
static int
ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg);
spin_unlock(&lli->lli_lock);
}
- if (rc == 0) {
- rc = ll_objects_destroy(req, inode);
- if (rc)
- CERROR("inode %lu ll_objects destroy: rc = %d\n",
- inode->i_ino, rc);
- }
if (rc == 0 && op_data->op_bias & MDS_HSM_RELEASE) {
struct mdt_body *body;
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (!(body->valid & OBD_MD_FLRELEASED))
+ if (!(body->mbo_valid & OBD_MD_FLRELEASED))
rc = -EBUSY;
}
fd = LUSTRE_FPRIVATE(file);
LASSERT(fd);
- /* The last ref on @file, maybe not be the owner pid of statahead.
- * Different processes can open the same dir, "ll_opendir_key" means:
- * it is me that should stop the statahead thread.
+ /* The last ref on @file, maybe not be the owner pid of statahead,
+ * because parent and child process can share the same file handle.
*/
- if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd &&
- lli->lli_opendir_pid != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
+ if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = NULL;
}
if (!S_ISDIR(inode->i_mode)) {
- lov_read_and_clear_async_rc(lli->lli_clob);
+ if (lli->lli_clob)
+ lov_read_and_clear_async_rc(lli->lli_clob);
lli->lli_async_rc = 0;
}
return rc;
}
-static int ll_intent_file_open(struct dentry *dentry, void *lmm,
- int lmmsize, struct lookup_intent *itp)
+static int ll_intent_file_open(struct dentry *de, void *lmm, int lmmsize,
+ struct lookup_intent *itp)
{
- struct inode *inode = d_inode(dentry);
+ struct inode *inode = d_inode(de);
struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct dentry *parent = dentry->d_parent;
- const char *name = dentry->d_name.name;
- const int len = dentry->d_name.len;
+ struct dentry *parent = de->d_parent;
+ const char *name = NULL;
struct md_op_data *op_data;
- struct ptlrpc_request *req;
- __u32 opc = LUSTRE_OPC_ANY;
- int rc;
+ struct ptlrpc_request *req = NULL;
+ int len = 0, rc;
- /* Usually we come here only for NFSD, and we want open lock. */
- /* We can also get here if there was cached open handle in revalidate_it
- * but it disappeared while we were getting from there to ll_file_open.
- * But this means this file was closed and immediately opened which
- * makes a good candidate for using OPEN lock
- */
- /* If lmmsize & lmm are not 0, we are just setting stripe info
- * parameters. No need for the open lock
+ LASSERT(parent);
+ LASSERT(itp->it_flags & MDS_OPEN_BY_FID);
+
+ /*
+ * if server supports open-by-fid, or file name is invalid, don't pack
+ * name in open request
*/
- if (!lmm && lmmsize == 0) {
- struct ll_dentry_data *ldd = ll_d2d(dentry);
- /*
- * If we came via ll_iget_for_nfs, then we need to request
- * struct ll_dentry_data *ldd = ll_d2d(file->f_dentry);
- *
- * NB: when ldd is NULL, it must have come via normal
- * lookup path only, since ll_iget_for_nfs always calls
- * ll_d_init().
- */
- if (ldd && ldd->lld_nfs_dentry) {
- ldd->lld_nfs_dentry = 0;
- itp->it_flags |= MDS_OPEN_LOCK;
- }
- if (itp->it_flags & FMODE_WRITE)
- opc = LUSTRE_OPC_CREATE;
+ if (!(exp_connect_flags(sbi->ll_md_exp) & OBD_CONNECT_OPEN_BY_FID) &&
+ lu_name_is_valid_2(de->d_name.name, de->d_name.len)) {
+ name = de->d_name.name;
+ len = de->d_name.len;
}
- op_data = ll_prep_md_op_data(NULL, d_inode(parent),
- inode, name, len,
- O_RDWR, opc, NULL);
+ op_data = ll_prep_md_op_data(NULL, d_inode(parent), inode, name, len,
+ O_RDWR, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
+ op_data->op_data = lmm;
+ op_data->op_data_size = lmmsize;
- itp->it_flags |= MDS_OPEN_BY_FID;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, lmm, lmmsize, itp,
- 0 /*unused */, &req, ll_md_blocking_ast, 0);
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, itp, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
if (rc == -ESTALE) {
/* reason for keep own exit path - don`t flood log
struct mdt_body *body;
body = req_capsule_server_get(&it->it_request->rq_pill, &RMF_MDT_BODY);
- och->och_fh = body->handle;
- och->och_fid = body->fid1;
+ och->och_fh = body->mbo_handle;
+ och->och_fid = body->mbo_fid1;
och->och_lease_handle.cookie = it->it_lock_handle;
och->och_magic = OBD_CLIENT_HANDLE_MAGIC;
och->och_flags = it->it_flags;
body = req_capsule_server_get(&it->it_request->rq_pill,
&RMF_MDT_BODY);
- ll_ioepoch_open(lli, body->ioepoch);
+ ll_ioepoch_open(lli, body->mbo_ioepoch);
}
LUSTRE_FPRIVATE(file) = fd;
struct obd_client_handle **och_p = NULL;
__u64 *och_usecount = NULL;
struct ll_file_data *fd;
- int rc = 0, opendir_set = 0;
+ int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), flags %o\n",
PFID(ll_inode2fid(inode)), inode, file->f_flags);
}
fd->fd_file = file;
- if (S_ISDIR(inode->i_mode)) {
- spin_lock(&lli->lli_sa_lock);
- if (!lli->lli_opendir_key && !lli->lli_sai &&
- lli->lli_opendir_pid == 0) {
- lli->lli_opendir_key = fd;
- lli->lli_opendir_pid = current_pid();
- opendir_set = 1;
- }
- spin_unlock(&lli->lli_sa_lock);
- }
+ if (S_ISDIR(inode->i_mode))
+ ll_authorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = fd;
} else if (it->it_flags & FMODE_EXEC) {
och_p = &lli->lli_mds_exec_och;
och_usecount = &lli->lli_open_fd_exec_count;
- } else {
+ } else {
och_p = &lli->lli_mds_read_och;
och_usecount = &lli->lli_open_fd_read_count;
}
* result in a deadlock
*/
mutex_unlock(&lli->lli_och_mutex);
- it->it_create_mode |= M_CHECK_STALE;
+ /*
+ * Normally called under two situations:
+ * 1. NFS export.
+ * 2. revalidate with IT_OPEN (revalidate doesn't
+ * execute this intent any more).
+ *
+ * Always fetch MDS_OPEN_LOCK if this is not setstripe.
+ *
+ * Always specify MDS_OPEN_BY_FID because we don't want
+ * to get file with different fid.
+ */
+ it->it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID;
rc = ll_intent_file_open(file->f_path.dentry, NULL, 0, it);
- it->it_create_mode &= ~M_CHECK_STALE;
if (rc)
goto out_openerr;
mutex_unlock(&lli->lli_och_mutex);
out_openerr:
- if (opendir_set != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
- ll_file_data_put(fd);
+ if (lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
+ if (fd)
+ ll_file_data_put(fd);
} else {
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_OPEN, 1);
}
struct lookup_intent it = { .it_op = IT_OPEN };
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct md_op_data *op_data;
- struct ptlrpc_request *req;
+ struct ptlrpc_request *req = NULL;
struct lustre_handle old_handle = { 0 };
struct obd_client_handle *och = NULL;
int rc;
it.it_flags = fmode | open_flags;
it.it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID | MDS_OPEN_LEASE;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, NULL, 0, &it, 0, &req,
- ll_md_blocking_lease_ast,
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, &it, &req,
+ &ll_md_blocking_lease_ast,
/* LDLM_FL_NO_LRU: To not put the lease lock into LRU list, otherwise
* it can be cancelled which may mislead applications that the lease is
* broken;
* open in ll_md_blocking_ast(). Otherwise as ll_md_blocking_lease_ast
* doesn't deal with openhandle, so normal openhandle will be leaked.
*/
- LDLM_FL_NO_LRU | LDLM_FL_EXCL);
+ LDLM_FL_NO_LRU | LDLM_FL_EXCL);
ll_finish_md_op_data(op_data);
ptlrpc_req_finished(req);
if (rc < 0)
{
struct ldlm_lock *lock;
bool cancelled = true;
- int rc;
lock = ldlm_handle2lock(&och->och_lease_handle);
if (lock) {
if (lease_broken)
*lease_broken = cancelled;
- rc = ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp, inode, och,
- NULL);
- return rc;
+ return ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp,
+ inode, och, NULL);
}
/* Fills the obdo with the attributes for the lsm */
{
struct ll_inode_info *lli = ll_i2info(file_inode(file));
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct range_lock range;
struct cl_io *io;
ssize_t result;
- CDEBUG(D_VFSTRACE, "file: %pD, type: %d ppos: %llu, count: %zd\n",
+ CDEBUG(D_VFSTRACE, "file: %pD, type: %d ppos: %llu, count: %zu\n",
file, iot, *ppos, count);
restart:
if (cl_io_rw_init(env, io, iot, *ppos, count) == 0) {
struct vvp_io *vio = vvp_env_io(env);
- int write_mutex_locked = 0;
+ bool range_locked = false;
+
+ if (file->f_flags & O_APPEND)
+ range_lock_init(&range, 0, LUSTRE_EOF);
+ else
+ range_lock_init(&range, *ppos, *ppos + count - 1);
vio->vui_fd = LUSTRE_FPRIVATE(file);
- vio->vui_io_subtype = args->via_io_subtype;
-
- switch (vio->vui_io_subtype) {
- case IO_NORMAL:
- vio->vui_iter = args->u.normal.via_iter;
- vio->vui_iocb = args->u.normal.via_iocb;
- if ((iot == CIT_WRITE) &&
- !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
- if (mutex_lock_interruptible(&lli->
- lli_write_mutex)) {
- result = -ERESTARTSYS;
- goto out;
- }
- write_mutex_locked = 1;
- }
- down_read(&lli->lli_trunc_sem);
- break;
- case IO_SPLICE:
- vio->u.splice.vui_pipe = args->u.splice.via_pipe;
- vio->u.splice.vui_flags = args->u.splice.via_flags;
- break;
- default:
- CERROR("Unknown IO type - %u\n", vio->vui_io_subtype);
- LBUG();
+ vio->vui_iter = args->u.normal.via_iter;
+ vio->vui_iocb = args->u.normal.via_iocb;
+ /*
+ * Direct IO reads must also take range lock,
+ * or multiple reads will try to work on the same pages
+ * See LU-6227 for details.
+ */
+ if (((iot == CIT_WRITE) ||
+ (iot == CIT_READ && (file->f_flags & O_DIRECT))) &&
+ !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
+ CDEBUG(D_VFSTRACE, "Range lock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ result = range_lock(&lli->lli_write_tree,
+ &range);
+ if (result < 0)
+ goto out;
+
+ range_locked = true;
}
+ down_read(&lli->lli_trunc_sem);
ll_cl_add(file, env, io);
result = cl_io_loop(env, io);
ll_cl_remove(file, env);
- if (args->via_io_subtype == IO_NORMAL)
- up_read(&lli->lli_trunc_sem);
- if (write_mutex_locked)
- mutex_unlock(&lli->lli_write_mutex);
+ up_read(&lli->lli_trunc_sem);
+ if (range_locked) {
+ CDEBUG(D_VFSTRACE, "Range unlock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ range_unlock(&lli->lli_write_tree, &range);
+ }
} else {
/* cl_io_rw_init() handled IO */
result = io->ci_result;
* short read/write instead of restart io.
*/
if ((result == 0 || result == -ENODATA) && io->ci_need_restart) {
- CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zd\n",
+ CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zu\n",
iot == CIT_READ ? "read" : "write",
file, *ppos, count);
LASSERTF(io->ci_nob == 0, "%zd\n", io->ci_nob);
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = to;
args->u.normal.via_iocb = iocb;
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = from;
args->u.normal.via_iocb = iocb;
return result;
}
-/*
- * Send file content (through pagecache) somewhere with helper
- */
-static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t count,
- unsigned int flags)
-{
- struct lu_env *env;
- struct vvp_io_args *args;
- ssize_t result;
- int refcheck;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- return PTR_ERR(env);
-
- args = ll_env_args(env, IO_SPLICE);
- args->u.splice.via_pipe = pipe;
- args->u.splice.via_flags = flags;
-
- result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
- cl_env_put(env, &refcheck);
- return result;
-}
-
-static int ll_lov_recreate(struct inode *inode, struct ost_id *oi, u32 ost_idx)
-{
- struct obd_export *exp = ll_i2dtexp(inode);
- struct obd_trans_info oti = { 0 };
- struct obdo *oa = NULL;
- int lsm_size;
- int rc = 0;
- struct lov_stripe_md *lsm = NULL, *lsm2;
-
- oa = kmem_cache_zalloc(obdo_cachep, GFP_NOFS);
- if (!oa)
- return -ENOMEM;
-
- lsm = ccc_inode_lsm_get(inode);
- if (!lsm_has_objects(lsm)) {
- rc = -ENOENT;
- goto out;
- }
-
- lsm_size = sizeof(*lsm) + (sizeof(struct lov_oinfo) *
- (lsm->lsm_stripe_count));
-
- lsm2 = libcfs_kvzalloc(lsm_size, GFP_NOFS);
- if (!lsm2) {
- rc = -ENOMEM;
- goto out;
- }
-
- oa->o_oi = *oi;
- oa->o_nlink = ost_idx;
- oa->o_flags |= OBD_FL_RECREATE_OBJS;
- oa->o_valid = OBD_MD_FLID | OBD_MD_FLFLAGS | OBD_MD_FLGROUP;
- obdo_from_inode(oa, inode, OBD_MD_FLTYPE | OBD_MD_FLATIME |
- OBD_MD_FLMTIME | OBD_MD_FLCTIME);
- obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid);
- memcpy(lsm2, lsm, lsm_size);
- ll_inode_size_lock(inode);
- rc = obd_create(NULL, exp, oa, &lsm2, &oti);
- ll_inode_size_unlock(inode);
-
- kvfree(lsm2);
- goto out;
-out:
- ccc_inode_lsm_put(inode, lsm);
- kmem_cache_free(obdo_cachep, oa);
- return rc;
-}
-
-static int ll_lov_recreate_obj(struct inode *inode, unsigned long arg)
-{
- struct ll_recreate_obj ucreat;
- struct ost_id oi;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&ucreat, (struct ll_recreate_obj __user *)arg,
- sizeof(ucreat)))
- return -EFAULT;
-
- ostid_set_seq_mdt0(&oi);
- ostid_set_id(&oi, ucreat.lrc_id);
- return ll_lov_recreate(inode, &oi, ucreat.lrc_ost_idx);
-}
-
-static int ll_lov_recreate_fid(struct inode *inode, unsigned long arg)
-{
- struct lu_fid fid;
- struct ost_id oi;
- u32 ost_idx;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&fid, (struct lu_fid __user *)arg, sizeof(fid)))
- return -EFAULT;
-
- fid_to_ostid(&fid, &oi);
- ost_idx = (fid_seq(&fid) >> 16) & 0xffff;
- return ll_lov_recreate(inode, &oi, ost_idx);
-}
-
int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
__u64 flags, struct lov_user_md *lum,
int lum_size)
{
struct lov_stripe_md *lsm = NULL;
- struct lookup_intent oit = {.it_op = IT_OPEN, .it_flags = flags};
+ struct lookup_intent oit = {
+ .it_op = IT_OPEN,
+ .it_flags = flags | MDS_OPEN_BY_FID,
+ };
int rc = 0;
lsm = ccc_inode_lsm_get(inode);
ll_inode_size_lock(inode);
rc = ll_intent_file_open(dentry, lum, lum_size, &oit);
- if (rc)
+ if (rc < 0)
goto out_unlock;
rc = oit.it_status;
if (rc < 0)
- goto out_req_free;
+ goto out_unlock;
ll_release_openhandle(inode, &oit);
ccc_inode_lsm_put(inode, lsm);
out:
return rc;
-out_req_free:
- ptlrpc_req_finished((struct ptlrpc_request *)oit.it_request);
- goto out;
}
int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename,
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
- if (!(body->valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
+ if (!(body->mbo_valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
lmmsize == 0) {
rc = -ENODATA;
goto out;
*/
if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V1)) {
lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v1 *)lmm)->lmm_objects,
stripe_count);
} else if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V3)) {
lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v3 *)lmm)->lmm_objects,
stripe_count);
return rc;
}
+static int ll_file_getstripe(struct inode *inode,
+ struct lov_user_md __user *lum)
+{
+ struct lu_env *env;
+ int refcheck;
+ int rc;
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ return PTR_ERR(env);
+
+ rc = cl_object_getstripe(env, ll_i2info(inode)->lli_clob, lum);
+ cl_env_put(env, &refcheck);
+ return rc;
+}
+
static int ll_lov_setstripe(struct inode *inode, struct file *file,
unsigned long arg)
{
- struct lov_user_md_v3 lumv3;
- struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;
- struct lov_user_md_v1 __user *lumv1p = (void __user *)arg;
- struct lov_user_md_v3 __user *lumv3p = (void __user *)arg;
+ struct lov_user_md __user *lum = (struct lov_user_md __user *)arg;
+ struct lov_user_md *klum;
int lum_size, rc;
__u64 flags = FMODE_WRITE;
- /* first try with v1 which is smaller than v3 */
- lum_size = sizeof(struct lov_user_md_v1);
- if (copy_from_user(lumv1, lumv1p, lum_size))
- return -EFAULT;
-
- if (lumv1->lmm_magic == LOV_USER_MAGIC_V3) {
- lum_size = sizeof(struct lov_user_md_v3);
- if (copy_from_user(&lumv3, lumv3p, lum_size))
- return -EFAULT;
- }
+ rc = ll_copy_user_md(lum, &klum);
+ if (rc < 0)
+ return rc;
- rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lumv1,
+ lum_size = rc;
+ rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, klum,
lum_size);
cl_lov_delay_create_clear(&file->f_flags);
if (rc == 0) {
- struct lov_stripe_md *lsm;
__u32 gen;
- put_user(0, &lumv1p->lmm_stripe_count);
+ put_user(0, &lum->lmm_stripe_count);
ll_layout_refresh(inode, &gen);
- lsm = ccc_inode_lsm_get(inode);
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode),
- 0, lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ rc = ll_file_getstripe(inode, (struct lov_user_md __user *)arg);
}
- return rc;
-}
-static int ll_lov_getstripe(struct inode *inode, unsigned long arg)
-{
- struct lov_stripe_md *lsm;
- int rc = -ENODATA;
-
- lsm = ccc_inode_lsm_get(inode);
- if (lsm)
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode), 0,
- lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ kfree(klum);
return rc;
}
return rc;
}
+static inline long ll_lease_type_from_fmode(fmode_t fmode)
+{
+ return ((fmode & FMODE_READ) ? LL_LEASE_RDLCK : 0) |
+ ((fmode & FMODE_WRITE) ? LL_LEASE_WRLCK : 0);
+}
+
static long
ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
return rc;
}
case LL_IOC_LOV_GETSTRIPE:
- return ll_lov_getstripe(inode, arg);
- case LL_IOC_RECREATE_OBJ:
- return ll_lov_recreate_obj(inode, arg);
- case LL_IOC_RECREATE_FID:
- return ll_lov_recreate_fid(inode, arg);
+ return ll_file_getstripe(inode,
+ (struct lov_user_md __user *)arg);
case FSFILT_IOC_FIEMAP:
return ll_ioctl_fiemap(inode, arg);
case FSFILT_IOC_GETFLAGS:
return 0;
}
+ case LL_IOC_GETPARENT:
+ return ll_getparent(file, (struct getparent __user *)arg);
case OBD_IOC_FID2PATH:
return ll_fid2path(inode, (void __user *)arg);
case LL_IOC_DATA_VERSION: {
struct ll_inode_info *lli = ll_i2info(inode);
struct obd_client_handle *och = NULL;
bool lease_broken;
- fmode_t mode = 0;
+ fmode_t fmode;
switch (arg) {
- case F_WRLCK:
+ case LL_LEASE_WRLCK:
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
- mode = FMODE_WRITE;
+ fmode = FMODE_WRITE;
break;
- case F_RDLCK:
+ case LL_LEASE_RDLCK:
if (!(file->f_mode & FMODE_READ))
return -EPERM;
- mode = FMODE_READ;
+ fmode = FMODE_READ;
break;
- case F_UNLCK:
+ case LL_LEASE_UNLCK:
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
och = fd->fd_lease_och;
}
mutex_unlock(&lli->lli_och_mutex);
- if (och) {
- mode = och->och_flags &
- (FMODE_READ|FMODE_WRITE);
- rc = ll_lease_close(och, inode, &lease_broken);
- if (rc == 0 && lease_broken)
- mode = 0;
- } else {
- rc = -ENOLCK;
- }
+ if (!och)
+ return -ENOLCK;
+
+ fmode = och->och_flags;
+ rc = ll_lease_close(och, inode, &lease_broken);
+ if (rc < 0)
+ return rc;
+
+ if (lease_broken)
+ fmode = 0;
- /* return the type of lease or error */
- return rc < 0 ? rc : (int)mode;
+ return ll_lease_type_from_fmode(fmode);
default:
return -EINVAL;
}
- CDEBUG(D_INODE, "Set lease with mode %d\n", mode);
+ CDEBUG(D_INODE, "Set lease with mode %u\n", fmode);
/* apply for lease */
- och = ll_lease_open(inode, file, mode, 0);
+ och = ll_lease_open(inode, file, fmode, 0);
if (IS_ERR(och))
return PTR_ERR(och);
case LL_IOC_GET_LEASE: {
struct ll_inode_info *lli = ll_i2info(inode);
struct ldlm_lock *lock = NULL;
+ fmode_t fmode = 0;
- rc = 0;
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
struct obd_client_handle *och = fd->fd_lease_och;
if (lock) {
lock_res_and_lock(lock);
if (!ldlm_is_cancel(lock))
- rc = och->och_flags &
- (FMODE_READ | FMODE_WRITE);
+ fmode = och->och_flags;
unlock_res_and_lock(lock);
LDLM_LOCK_PUT(lock);
}
}
mutex_unlock(&lli->lli_och_mutex);
- return rc;
+ return ll_lease_type_from_fmode(fmode);
}
case LL_IOC_HSM_IMPORT: {
struct hsm_user_import *hui;
eof = i_size_read(inode);
}
- retval = generic_file_llseek_size(file, offset, origin,
- ll_file_maxbytes(inode), eof);
- return retval;
+ return generic_file_llseek_size(file, offset, origin,
+ ll_file_maxbytes(inode), eof);
}
static int ll_flush(struct file *file, fl_owner_t id)
*/
rc = lli->lli_async_rc;
lli->lli_async_rc = 0;
- err = lov_read_and_clear_async_rc(lli->lli_clob);
- if (rc == 0)
- rc = err;
+ if (lli->lli_clob) {
+ err = lov_read_and_clear_async_rc(lli->lli_clob);
+ if (!rc)
+ rc = err;
+ }
/* The application has been told about write failure already.
* Do not report failure again.
struct md_op_data *op_data;
struct lustre_handle lockh = {0};
ldlm_policy_data_t flock = { {0} };
+ int fl_type = file_lock->fl_type;
__u64 flags = 0;
int rc;
int rc2 = 0;
if (file_lock->fl_lmops && file_lock->fl_lmops->lm_compare_owner)
flock.l_flock.owner = (unsigned long)file_lock->fl_pid;
- switch (file_lock->fl_type) {
+ switch (fl_type) {
case F_RDLCK:
einfo.ei_mode = LCK_PR;
break;
einfo.ei_mode = LCK_PW;
break;
default:
- CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n",
- file_lock->fl_type);
+ CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n", fl_type);
return -ENOTSUPP;
}
case F_GETLK64:
#endif
flags = LDLM_FL_TEST_LOCK;
- /* Save the old mode so that if the mode in the lock changes we
- * can decrement the appropriate reader or writer refcount.
- */
- file_lock->fl_type = einfo.ei_mode;
break;
default:
CERROR("unknown fcntl lock command: %d\n", cmd);
return -EINVAL;
}
+ /*
+ * Save the old mode so that if the mode in the lock changes we
+ * can decrement the appropriate reader or writer refcount.
+ */
+ file_lock->fl_type = einfo.ei_mode;
+
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
PFID(ll_inode2fid(inode)), flock.l_flock.pid, flags,
einfo.ei_mode, flock.l_flock.start, flock.l_flock.end);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data, &lockh,
+ flags);
+
+ /* Restore the file lock type if not TEST lock. */
+ if (!(flags & LDLM_FL_TEST_LOCK))
+ file_lock->fl_type = fl_type;
if ((rc == 0 || file_lock->fl_type == F_UNLCK) &&
!(flags & LDLM_FL_TEST_LOCK))
if (rc2 && file_lock->fl_type != F_UNLCK) {
einfo.ei_mode = LCK_NL;
- md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data,
+ &lockh, flags);
rc = rc2;
}
return rc;
}
+int ll_get_fid_by_name(struct inode *parent, const char *name,
+ int namelen, struct lu_fid *fid)
+{
+ struct md_op_data *op_data = NULL;
+ struct ptlrpc_request *req;
+ struct mdt_body *body;
+ int rc;
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen, 0,
+ LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ op_data->op_valid = OBD_MD_FLID;
+ rc = md_getattr_name(ll_i2sbi(parent)->ll_md_exp, op_data, &req);
+ ll_finish_md_op_data(op_data);
+ if (rc < 0)
+ return rc;
+
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (!body) {
+ rc = -EFAULT;
+ goto out_req;
+ }
+ if (fid)
+ *fid = body->mbo_fid1;
+out_req:
+ ptlrpc_req_finished(req);
+ return rc;
+}
+
+int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
+ const char *name, int namelen)
+{
+ struct ptlrpc_request *request = NULL;
+ struct inode *child_inode = NULL;
+ struct dentry *dchild = NULL;
+ struct md_op_data *op_data;
+ struct qstr qstr;
+ int rc;
+
+ CDEBUG(D_VFSTRACE, "migrate %s under "DFID" to MDT%d\n",
+ name, PFID(ll_inode2fid(parent)), mdtidx);
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen,
+ 0, LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ /* Get child FID first */
+ qstr.hash = full_name_hash(parent, name, namelen);
+ qstr.name = name;
+ qstr.len = namelen;
+ dchild = d_lookup(file_dentry(file), &qstr);
+ if (dchild) {
+ op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
+ if (dchild->d_inode) {
+ child_inode = igrab(dchild->d_inode);
+ if (child_inode) {
+ inode_lock(child_inode);
+ op_data->op_fid3 = *ll_inode2fid(child_inode);
+ ll_invalidate_aliases(child_inode);
+ }
+ }
+ dput(dchild);
+ } else {
+ rc = ll_get_fid_by_name(parent, name, namelen,
+ &op_data->op_fid3);
+ if (rc)
+ goto out_free;
+ }
+
+ if (!fid_is_sane(&op_data->op_fid3)) {
+ CERROR("%s: migrate %s, but fid "DFID" is insane\n",
+ ll_get_fsname(parent->i_sb, NULL, 0), name,
+ PFID(&op_data->op_fid3));
+ rc = -EINVAL;
+ goto out_free;
+ }
+
+ rc = ll_get_mdt_idx_by_fid(ll_i2sbi(parent), &op_data->op_fid3);
+ if (rc < 0)
+ goto out_free;
+
+ if (rc == mdtidx) {
+ CDEBUG(D_INFO, "%s:"DFID" is already on MDT%d.\n", name,
+ PFID(&op_data->op_fid3), mdtidx);
+ rc = 0;
+ goto out_free;
+ }
+
+ op_data->op_mds = mdtidx;
+ op_data->op_cli_flags = CLI_MIGRATE;
+ rc = md_rename(ll_i2sbi(parent)->ll_md_exp, op_data, name,
+ namelen, name, namelen, &request);
+ if (!rc)
+ ll_update_times(request, parent);
+
+ ptlrpc_req_finished(request);
+
+out_free:
+ if (child_inode) {
+ clear_nlink(child_inode);
+ inode_unlock(child_inode);
+ iput(child_inode);
+ }
+
+ ll_finish_md_op_data(op_data);
+ return rc;
+}
+
static int
ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
{
struct lustre_handle lockh;
ldlm_policy_data_t policy;
enum ldlm_mode mode = (l_req_mode == LCK_MINMODE) ?
- (LCK_CR|LCK_CW|LCK_PR|LCK_PW) : l_req_mode;
+ (LCK_CR | LCK_CW | LCK_PR | LCK_PW) : l_req_mode;
struct lu_fid *fid;
__u64 flags;
int i;
{
ldlm_policy_data_t policy = { .l_inodebits = {bits} };
struct lu_fid *fid;
- enum ldlm_mode rc;
fid = &ll_i2info(inode)->lli_fid;
CDEBUG(D_INFO, "trying to match res "DFID"\n", PFID(fid));
- rc = md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
- fid, LDLM_IBITS, &policy, mode, lockh);
-
- return rc;
+ return md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
+ fid, LDLM_IBITS, &policy, mode, lockh);
}
static int ll_inode_revalidate_fini(struct inode *inode, int rc)
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- oit.it_create_mode |= M_CHECK_STALE;
- rc = md_intent_lock(exp, op_data, NULL, 0,
- /* we are not interested in name
- * based lookup
- */
- &oit, 0, &req,
- ll_md_blocking_ast, 0);
+ rc = md_intent_lock(exp, op_data, &oit, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
- oit.it_create_mode &= ~M_CHECK_STALE;
if (rc < 0) {
rc = ll_inode_revalidate_fini(inode, rc);
goto out;
op_data->op_valid = valid;
rc = md_getattr(sbi->ll_md_exp, op_data, &req);
ll_finish_md_op_data(op_data);
- if (rc) {
- rc = ll_inode_revalidate_fini(inode, rc);
- return rc;
- }
+ if (rc)
+ return ll_inode_revalidate_fini(inode, rc);
rc = ll_prep_inode(&inode, req, NULL, NULL);
}
return rc;
}
+static int ll_merge_md_attr(struct inode *inode)
+{
+ struct cl_attr attr = { 0 };
+ int rc;
+
+ LASSERT(ll_i2info(inode)->lli_lsm_md);
+ rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+ &attr, ll_md_blocking_ast);
+ if (rc)
+ return rc;
+
+ set_nlink(inode, attr.cat_nlink);
+ inode->i_blocks = attr.cat_blocks;
+ i_size_write(inode, attr.cat_size);
+
+ ll_i2info(inode)->lli_atime = attr.cat_atime;
+ ll_i2info(inode)->lli_mtime = attr.cat_mtime;
+ ll_i2info(inode)->lli_ctime = attr.cat_ctime;
+
+ return 0;
+}
+
static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
{
struct inode *inode = d_inode(dentry);
/* if object isn't regular file, don't validate size */
if (!S_ISREG(inode->i_mode)) {
+ if (S_ISDIR(inode->i_mode) &&
+ ll_i2info(inode)->lli_lsm_md) {
+ rc = ll_merge_md_attr(inode);
+ if (rc)
+ return rc;
+ }
+
LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime;
LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime;
LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime;
if (res)
return res;
+ OBD_FAIL_TIMEOUT(OBD_FAIL_GETATTR_DELAY, 30);
+
stat->dev = inode->i_sb->s_dev;
if (ll_need_32bit_api(sbi))
stat->ino = cl_fid_build_ino(&lli->lli_fid, 1);
else
stat->ino = inode->i_ino;
stat->mode = inode->i_mode;
- stat->nlink = inode->i_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->rdev = inode->i_rdev;
stat->ctime = inode->i_ctime;
stat->blksize = 1 << inode->i_blkbits;
+ stat->nlink = inode->i_nlink;
stat->size = i_size_read(inode);
stat->blocks = inode->i_blocks;
int ll_inode_permission(struct inode *inode, int mask)
{
+ struct ll_sb_info *sbi;
+ struct root_squash_info *squash;
+ const struct cred *old_cred = NULL;
+ struct cred *cred = NULL;
+ bool squash_id = false;
+ cfs_cap_t cap;
int rc = 0;
if (mask & MAY_NOT_BLOCK)
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), inode mode %x mask %o\n",
PFID(ll_inode2fid(inode)), inode, inode->i_mode, mask);
+ /* squash fsuid/fsgid if needed */
+ sbi = ll_i2sbi(inode);
+ squash = &sbi->ll_squash;
+ if (unlikely(squash->rsi_uid &&
+ uid_eq(current_fsuid(), GLOBAL_ROOT_UID) &&
+ !(sbi->ll_flags & LL_SBI_NOROOTSQUASH))) {
+ squash_id = true;
+ }
+
+ if (squash_id) {
+ CDEBUG(D_OTHER, "squash creds (%d:%d)=>(%d:%d)\n",
+ __kuid_val(current_fsuid()), __kgid_val(current_fsgid()),
+ squash->rsi_uid, squash->rsi_gid);
+
+ /*
+ * update current process's credentials
+ * and FS capability
+ */
+ cred = prepare_creds();
+ if (!cred)
+ return -ENOMEM;
+
+ cred->fsuid = make_kuid(&init_user_ns, squash->rsi_uid);
+ cred->fsgid = make_kgid(&init_user_ns, squash->rsi_gid);
+ for (cap = 0; cap < sizeof(cfs_cap_t) * 8; cap++) {
+ if ((1 << cap) & CFS_CAP_FS_MASK)
+ cap_lower(cred->cap_effective, cap);
+ }
+ old_cred = override_creds(cred);
+ }
+
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_INODE_PERM, 1);
rc = generic_permission(inode, mask);
+ /* restore current process's credentials and FS capability */
+ if (squash_id) {
+ revert_creds(old_cred);
+ put_cred(cred);
+ }
+
return rc;
}
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush
};
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = ll_setxattr,
- .getxattr = ll_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = ll_removexattr,
+ .removexattr = generic_removexattr,
.fiemap = ll_fiemap,
.get_acl = ll_get_acl,
};
if (!in_data)
return NULL;
- memset(in_data, 0, sizeof(*in_data));
in_data->iocd_size = size;
in_data->iocd_cb = cb;
in_data->iocd_count = count;
goto out;
}
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
if (lmmsize == 0) /* empty layout */ {
rc = 0;
goto out;
PFID(&lli->lli_fid), inode, reconf);
/* in case this is a caching lock and reinstate with new inode */
- md_set_lock_data(sbi->ll_md_exp, &lockh->cookie, inode, NULL);
+ md_set_lock_data(sbi->ll_md_exp, lockh, inode, NULL);
lock_res_and_lock(lock);
lvb_ready = ldlm_is_lvb_ready(lock);
struct ldlm_enqueue_info einfo = {
.ei_type = LDLM_IBITS,
.ei_mode = LCK_CR,
- .ei_cb_bl = ll_md_blocking_ast,
- .ei_cb_cp = ldlm_completion_ast,
+ .ei_cb_bl = &ll_md_blocking_ast,
+ .ei_cb_cp = &ldlm_completion_ast,
};
int rc;
ll_get_fsname(inode->i_sb, NULL, 0),
PFID(&lli->lli_fid), inode);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, &it, op_data, &lockh,
- NULL, 0, NULL, 0);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL, &it, op_data, &lockh, 0);
ptlrpc_req_finished(it.it_request);
it.it_request = NULL;
projects / cascardo / linux.git / blobdiff