#include <linux/sched.h>
#include <linux/user_namespace.h>
#include <linux/uidgid.h>
+#include <linux/falloc.h>
#include <uapi/linux/lustre/lustre_ioctl.h>
+#include <uapi/linux/llcrypt.h>
#include <lustre_swab.h>
#include "cl_object.h"
{
struct niobuf_local *lnb = data;
void *kaddr;
+ int rc = 0;
+
+ struct inode *inode = page2inode(page);
kaddr = kmap_atomic(page);
memcpy(kaddr, lnb->lnb_data, lnb->lnb_len);
flush_dcache_page(page);
SetPageUptodate(page);
kunmap_atomic(kaddr);
+
+ if (inode && IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) {
+ if (!llcrypt_has_encryption_key(inode))
+ CDEBUG(D_SEC, "no enc key for "DFID"\n",
+ PFID(ll_inode2fid(inode)));
+ else {
+ unsigned int offs = 0;
+
+ while (offs < PAGE_SIZE) {
+ /* decrypt only if page is not empty */
+ if (memcmp(page_address(page) + offs,
+ page_address(ZERO_PAGE(0)),
+ LUSTRE_ENCRYPTION_UNIT_SIZE) == 0)
+ break;
+
+ rc = llcrypt_decrypt_pagecache_blocks(page,
+ LUSTRE_ENCRYPTION_UNIT_SIZE,
+ offs);
+ if (rc)
+ break;
+
+ offs += LUSTRE_ENCRYPTION_UNIT_SIZE;
+ }
+ }
+ }
unlock_page(page);
- return 0;
+ return rc;
}
-void ll_dom_finish_open(struct inode *inode, struct ptlrpc_request *req,
- struct lookup_intent *it)
+void ll_dom_finish_open(struct inode *inode, struct ptlrpc_request *req)
{
+ struct lu_env *env;
+ struct cl_io *io;
struct ll_inode_info *lli = ll_i2info(inode);
struct cl_object *obj = lli->lli_clob;
struct address_space *mapping = inode->i_mapping;
char *data;
unsigned long index, start;
struct niobuf_local lnb;
+ __u16 refcheck;
+ int rc;
ENTRY;
* buffer, in both cases total size should be equal to the file size.
*/
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (rnb->rnb_offset + rnb->rnb_len != body->mbo_dom_size) {
+ if (rnb->rnb_offset + rnb->rnb_len != body->mbo_dom_size &&
+ !(inode && IS_ENCRYPTED(inode))) {
CERROR("%s: server returns off/len %llu/%u but size %llu\n",
ll_i2sbi(inode)->ll_fsname, rnb->rnb_offset,
rnb->rnb_len, body->mbo_dom_size);
RETURN_EXIT;
}
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ RETURN_EXIT;
+ io = vvp_env_thread_io(env);
+ io->ci_obj = obj;
+ io->ci_ignore_layout = 1;
+ rc = cl_io_init(env, io, CIT_MISC, obj);
+ if (rc)
+ GOTO(out_io, rc);
+
CDEBUG(D_INFO, "Get data along with open at %llu len %i, size %llu\n",
rnb->rnb_offset, rnb->rnb_len, body->mbo_dom_size);
LASSERT((lnb.lnb_file_offset & ~PAGE_MASK) == 0);
lnb.lnb_page_offset = 0;
do {
+ struct cl_page *page;
+
lnb.lnb_data = data + (index << PAGE_SHIFT);
lnb.lnb_len = rnb->rnb_len - (index << PAGE_SHIFT);
if (lnb.lnb_len > PAGE_SIZE)
PTR_ERR(vmpage));
break;
}
+ lock_page(vmpage);
+ if (vmpage->mapping == NULL) {
+ unlock_page(vmpage);
+ put_page(vmpage);
+ /* page was truncated */
+ break;
+ }
+ /* attach VM page to CL page cache */
+ page = cl_page_find(env, obj, vmpage->index, vmpage,
+ CPT_CACHEABLE);
+ if (IS_ERR(page)) {
+ ClearPageUptodate(vmpage);
+ unlock_page(vmpage);
+ put_page(vmpage);
+ break;
+ }
+ cl_page_export(env, page, 1);
+ cl_page_put(env, page);
+ unlock_page(vmpage);
put_page(vmpage);
index++;
} while (rnb->rnb_len > (index << PAGE_SHIFT));
+
+out_io:
+ cl_io_fini(env, io);
+ cl_env_put(env, &refcheck);
+
EXIT;
}
rc = ll_prep_inode(&de->d_inode, req, NULL, itp);
if (!rc && itp->it_lock_mode) {
- struct lustre_handle handle = {.cookie = itp->it_lock_handle};
- struct ldlm_lock *lock;
- bool has_dom_bit = false;
+ __u64 bits = 0;
/* If we got a lock back and it has a LOOKUP bit set,
* make sure the dentry is marked as valid so we can find it.
* We don't need to care about actual hashing since other bits
* of kernel will deal with that later.
*/
- lock = ldlm_handle2lock(&handle);
- if (lock) {
- has_dom_bit = ldlm_has_dom(lock);
- if (lock->l_policy_data.l_inodebits.bits &
- MDS_INODELOCK_LOOKUP)
- d_lustre_revalidate(de);
-
- LDLM_LOCK_PUT(lock);
- }
- ll_set_lock_data(sbi->ll_md_exp, de->d_inode, itp, NULL);
- if (has_dom_bit)
- ll_dom_finish_open(de->d_inode, req, itp);
+ ll_set_lock_data(sbi->ll_md_exp, de->d_inode, itp, &bits);
+ if (bits & MDS_INODELOCK_LOOKUP)
+ d_lustre_revalidate(de);
+ /* if DoM bit returned along with LAYOUT bit then there
+ * can be read-on-open data returned.
+ */
+ if (bits & MDS_INODELOCK_DOM && bits & MDS_INODELOCK_LAYOUT)
+ ll_dom_finish_open(de->d_inode, req);
}
out:
it = file->private_data; /* XXX: compat macro */
file->private_data = NULL; /* prevent ll_local_open assertion */
+ if (S_ISREG(inode->i_mode)) {
+ rc = llcrypt_file_open(inode, file);
+ if (rc)
+ GOTO(out_nofiledata, rc);
+ }
+
fd = ll_file_data_get();
if (fd == NULL)
GOTO(out_nofiledata, rc = -ENOMEM);
/* already get lease, handle lease lock */
ll_set_lock_data(sbi->ll_md_exp, inode, &it, NULL);
- if (it.it_lock_mode == 0 ||
- it.it_lock_bits != MDS_INODELOCK_OPEN) {
+ if (!it.it_lock_mode ||
+ !(it.it_lock_bits & MDS_INODELOCK_OPEN)) {
/* open lock must return for lease */
CERROR(DFID "lease granted but no open lock, %d/%llu.\n",
PFID(ll_inode2fid(inode)), it.it_lock_mode,
IS_SYNC(inode));
#ifdef HAVE_GENERIC_WRITE_SYNC_2ARGS
io->u.ci_wr.wr_sync |= !!(args &&
- args->via_io_subtype == IO_NORMAL &&
- args->u.normal.via_iocb->ki_flags & IOCB_DSYNC);
+ (args->u.normal.via_iocb->ki_flags &
+ IOCB_DSYNC));
#endif
}
struct file *file, enum cl_io_type iot,
loff_t *ppos, size_t count)
{
- struct vvp_io *vio = vvp_env_io(env);
- struct inode *inode = file_inode(file);
- struct ll_inode_info *lli = ll_i2info(inode);
- struct ll_file_data *fd = file->private_data;
- struct range_lock range;
- struct cl_io *io;
- ssize_t result = 0;
- int rc = 0;
- unsigned retried = 0;
- unsigned ignore_lockless = 0;
+ struct vvp_io *vio = vvp_env_io(env);
+ struct inode *inode = file_inode(file);
+ struct ll_inode_info *lli = ll_i2info(inode);
+ struct ll_file_data *fd = file->private_data;
+ struct range_lock range;
+ struct cl_io *io;
+ ssize_t result = 0;
+ int rc = 0;
+ unsigned int retried = 0, ignore_lockless = 0;
+ bool is_aio = false;
+ struct cl_dio_aio *ci_aio = NULL;
ENTRY;
file_dentry(file)->d_name.name,
iot == CIT_READ ? "read" : "write", *ppos, count);
+ io = vvp_env_thread_io(env);
+ if (file->f_flags & O_DIRECT) {
+ if (!is_sync_kiocb(args->u.normal.via_iocb))
+ is_aio = true;
+ ci_aio = cl_aio_alloc(args->u.normal.via_iocb);
+ if (!ci_aio)
+ GOTO(out, rc = -ENOMEM);
+ }
+
restart:
io = vvp_env_thread_io(env);
ll_io_init(io, file, iot, args);
+ io->ci_aio = ci_aio;
io->ci_ignore_lockless = ignore_lockless;
io->ci_ndelay_tried = retried;
range_lock_init(&range, *ppos, *ppos + count - 1);
vio->vui_fd = file->private_data;
- 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;
- /* 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 "RL_FMT"\n",
- RL_PARA(&range));
- rc = range_lock(&lli->lli_write_tree, &range);
- if (rc < 0)
- GOTO(out, rc);
+ 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 "RL_FMT"\n",
+ RL_PARA(&range));
+ rc = range_lock(&lli->lli_write_tree, &range);
+ if (rc < 0)
+ GOTO(out, rc);
- range_locked = true;
- }
- 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 subtype %u\n", vio->vui_io_subtype);
- LBUG();
+ range_locked = true;
}
ll_cl_add(file, env, io, LCC_RW);
rc = io->ci_result;
}
+ /*
+ * In order to move forward AIO, ci_nob was increased,
+ * but that doesn't mean io have been finished, it just
+ * means io have been submited, we will always return
+ * EIOCBQUEUED to the caller, So we could only return
+ * number of bytes in non-AIO case.
+ */
if (io->ci_nob > 0) {
- result += io->ci_nob;
- count -= io->ci_nob;
- *ppos = io->u.ci_wr.wr.crw_pos; /* for splice */
+ if (!is_aio) {
+ result += io->ci_nob;
+ *ppos = io->u.ci_wr.wr.crw_pos; /* for splice */
+ }
+ count -= io->ci_nob;
/* prepare IO restart */
- if (count > 0 && args->via_io_subtype == IO_NORMAL)
+ if (count > 0)
args->u.normal.via_iter = vio->vui_iter;
}
out:
goto restart;
}
+ if (io->ci_aio) {
+ /*
+ * VFS will call aio_complete() if no -EIOCBQUEUED
+ * is returned for AIO, so we can not call aio_complete()
+ * in our end_io().
+ */
+ if (rc != -EIOCBQUEUED)
+ io->ci_aio->cda_no_aio_complete = 1;
+ /**
+ * Drop one extra reference so that end_io() could be
+ * called for this IO context, we could call it after
+ * we make sure all AIO requests have been proceed.
+ */
+ cl_sync_io_note(env, &io->ci_aio->cda_sync,
+ rc == -EIOCBQUEUED ? 0 : rc);
+ if (!is_aio) {
+ cl_aio_free(io->ci_aio);
+ io->ci_aio = NULL;
+ }
+ }
+
if (iot == CIT_READ) {
if (result > 0)
ll_stats_ops_tally(ll_i2sbi(inode),
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;
* XXX: exact copy from kernel code (__generic_file_aio_write_nolock)
*/
static int ll_file_get_iov_count(const struct iovec *iov,
- unsigned long *nr_segs, size_t *count)
+ unsigned long *nr_segs, size_t *count,
+ int access_flags)
{
size_t cnt = 0;
unsigned long seg;
cnt += iv->iov_len;
if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
return -EINVAL;
- if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
+ if (access_ok(access_flags, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
ssize_t result;
ENTRY;
- result = ll_file_get_iov_count(iov, &nr_segs, &iov_count);
+ result = ll_file_get_iov_count(iov, &nr_segs, &iov_count, VERIFY_READ);
if (result)
RETURN(result);
ssize_t result;
ENTRY;
- result = ll_file_get_iov_count(iov, &nr_segs, &iov_count);
+ result = ll_file_get_iov_count(iov, &nr_segs, &iov_count, VERIFY_WRITE);
if (result)
RETURN(result);
}
#endif /* !HAVE_FILE_OPERATIONS_READ_WRITE_ITER */
-/*
- * 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;
- __u16 refcheck;
- bool cached;
-
- ENTRY;
-
- result = pcc_file_splice_read(in_file, ppos, pipe,
- count, flags, &cached);
- if (cached)
- RETURN(result);
-
- ll_ras_enter(in_file, *ppos, count);
-
- 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);
-
- if (result > 0)
- ll_rw_stats_tally(ll_i2sbi(file_inode(in_file)), current->pid,
- in_file->private_data, *ppos, result,
- READ);
- RETURN(result);
-}
-
int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
__u64 flags, struct lov_user_md *lum, int lum_size)
{
GOTO(out, rc);
rc = ll_file_getstripe(inode, arg, lum_size);
+ if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode) &&
+ ll_i2info(inode)->lli_clob) {
+ struct iattr attr = { 0 };
+
+ rc = cl_setattr_ost(ll_i2info(inode)->lli_clob, &attr,
+ OP_XVALID_FLAGS, LUSTRE_ENCRYPT_FL);
+ }
}
cl_lov_delay_create_clear(&file->f_flags);
ENTRY;
- CDEBUG(D_VFSTRACE, "Lock request: file=%.*s, inode=%p, mode=%s "
- "start=%llu, end=%llu\n", dentry->d_name.len,
- dentry->d_name.name, dentry->d_inode,
+ CDEBUG(D_VFSTRACE,
+ "Lock request: file=%pd, inode=%p, mode=%s start=%llu, end=%llu\n",
+ dentry, dentry->d_inode,
user_lockname[ladvise->lla_lockahead_mode], (__u64) start,
(__u64) end);
fd->fd_designated_mirror = (__u32)arg;
RETURN(0);
}
- case LL_IOC_FSGETXATTR:
+ case FS_IOC_FSGETXATTR:
RETURN(ll_ioctl_fsgetxattr(inode, cmd, arg));
- case LL_IOC_FSSETXATTR:
+ case FS_IOC_FSSETXATTR:
RETURN(ll_ioctl_fssetxattr(inode, cmd, arg));
case BLKSSZGET:
RETURN(put_user(PAGE_SIZE, (int __user *)arg));
OBD_FREE_PTR(state);
RETURN(rc);
}
+#ifdef HAVE_LUSTRE_CRYPTO
+ case LL_IOC_SET_ENCRYPTION_POLICY:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_set_policy(file, (const void __user *)arg);
+ case LL_IOC_GET_ENCRYPTION_POLICY_EX:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_get_policy_ex(file, (void __user *)arg);
+ case LL_IOC_ADD_ENCRYPTION_KEY:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_add_key(file, (void __user *)arg);
+ case LL_IOC_REMOVE_ENCRYPTION_KEY:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_remove_key(file, (void __user *)arg);
+ case LL_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_remove_key_all_users(file,
+ (void __user *)arg);
+ case LL_IOC_GET_ENCRYPTION_KEY_STATUS:
+ if (!ll_sbi_has_encrypt(ll_i2sbi(inode)))
+ return -EOPNOTSUPP;
+ return llcrypt_ioctl_get_key_status(file, (void __user *)arg);
+#endif
default:
RETURN(obd_iocontrol(cmd, ll_i2dtexp(inode), 0, NULL,
(void __user *)arg));
}
}
+loff_t ll_lseek(struct inode *inode, loff_t offset, int whence)
+{
+ struct lu_env *env;
+ struct cl_io *io;
+ struct cl_lseek_io *lsio;
+ __u16 refcheck;
+ int rc;
+ loff_t retval;
+
+ ENTRY;
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ RETURN(PTR_ERR(env));
+
+ io = vvp_env_thread_io(env);
+ io->ci_obj = ll_i2info(inode)->lli_clob;
+
+ lsio = &io->u.ci_lseek;
+ lsio->ls_start = offset;
+ lsio->ls_whence = whence;
+ lsio->ls_result = -ENXIO;
+
+ do {
+ rc = cl_io_init(env, io, CIT_LSEEK, io->ci_obj);
+ if (!rc)
+ rc = cl_io_loop(env, io);
+ else
+ rc = io->ci_result;
+ retval = rc ? : lsio->ls_result;
+ cl_io_fini(env, io);
+ } while (unlikely(io->ci_need_restart));
+
+ cl_env_put(env, &refcheck);
+
+ RETURN(retval);
+}
+
static loff_t ll_file_seek(struct file *file, loff_t offset, int origin)
{
struct inode *inode = file_inode(file);
- loff_t retval, eof = 0;
+ loff_t retval = offset, eof = 0;
ktime_t kstart = ktime_get();
ENTRY;
- retval = offset + ((origin == SEEK_END) ? i_size_read(inode) :
- (origin == SEEK_CUR) ? file->f_pos : 0);
+
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), to=%llu=%#llx(%d)\n",
PFID(ll_inode2fid(inode)), inode, retval, retval,
origin);
- if (origin == SEEK_END || origin == SEEK_HOLE || origin == SEEK_DATA) {
+ if (origin == SEEK_END) {
retval = ll_glimpse_size(inode);
if (retval != 0)
RETURN(retval);
eof = i_size_read(inode);
}
- retval = generic_file_llseek_size(file, offset, origin,
- ll_file_maxbytes(inode), eof);
+ if (origin == SEEK_HOLE || origin == SEEK_DATA) {
+ if (offset < 0)
+ return -ENXIO;
+
+ /* flush local cache first if any */
+ cl_sync_file_range(inode, offset, OBD_OBJECT_EOF,
+ CL_FSYNC_LOCAL, 0);
+
+ retval = ll_lseek(inode, offset, origin);
+ if (retval < 0)
+ return retval;
+ retval = vfs_setpos(file, retval, ll_file_maxbytes(inode));
+ } else {
+ retval = generic_file_llseek_size(file, offset, origin,
+ ll_file_maxbytes(inode), eof);
+ }
if (retval >= 0)
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_LLSEEK,
ktime_us_delta(ktime_get(), kstart));
flags = LDLM_FL_BLOCK_GRANTED | LDLM_FL_CBPENDING | LDLM_FL_TEST_LOCK;
for (i = 0; i < MDS_INODELOCK_NUMBITS && *bits != 0; i++) {
- policy.l_inodebits.bits = *bits & (1 << i);
+ policy.l_inodebits.bits = *bits & BIT(i);
if (policy.l_inodebits.bits == 0)
continue;
- if (md_lock_match(ll_i2mdexp(inode), flags, fid, LDLM_IBITS,
- &policy, mode, &lockh)) {
- struct ldlm_lock *lock;
-
- lock = ldlm_handle2lock(&lockh);
- if (lock) {
- *bits &=
- ~(lock->l_policy_data.l_inodebits.bits);
- LDLM_LOCK_PUT(lock);
- } else {
- *bits &= ~policy.l_inodebits.bits;
- }
- }
- }
+ if (md_lock_match(ll_i2mdexp(inode), flags, fid, LDLM_IBITS,
+ &policy, mode, &lockh)) {
+ struct ldlm_lock *lock;
+
+ lock = ldlm_handle2lock(&lockh);
+ if (lock) {
+ *bits &=
+ ~(lock->l_policy_data.l_inodebits.bits);
+ LDLM_LOCK_PUT(lock);
+ } else {
+ *bits &= ~policy.l_inodebits.bits;
+ }
+ }
+ }
RETURN(*bits == 0);
}
static int ll_inode_revalidate(struct dentry *dentry, enum ldlm_intent_flags op)
{
+ struct inode *parent;
struct inode *inode = dentry->d_inode;
struct obd_export *exp = ll_i2mdexp(inode);
struct lookup_intent oit = {
};
struct ptlrpc_request *req = NULL;
struct md_op_data *op_data;
+ const char *name = NULL;
+ size_t namelen = 0;
int rc = 0;
ENTRY;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p),name=%s\n",
PFID(ll_inode2fid(inode)), inode, dentry->d_name.name);
- /* Call getattr by fid, so do not provide name at all. */
- op_data = ll_prep_md_op_data(NULL, inode, inode, NULL, 0, 0,
+ if (exp_connect_flags2(exp) & OBD_CONNECT2_GETATTR_PFID) {
+ parent = dentry->d_parent->d_inode;
+ name = dentry->d_name.name;
+ namelen = dentry->d_name.len;
+ } else {
+ parent = inode;
+ }
+
+ op_data = ll_prep_md_op_data(NULL, parent, inode, name, namelen, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
RETURN(PTR_ERR(op_data));
+ /* Call getattr by fid */
+ if (exp_connect_flags2(exp) & OBD_CONNECT2_GETATTR_PFID)
+ op_data->op_flags = MF_GETATTR_BY_FID;
rc = md_intent_lock(exp, op_data, &oit, &req, &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
if (rc < 0) {
* do_lookup() -> ll_revalidate_it(). We cannot use d_drop
* here to preserve get_cwd functionality on 2.6.
* Bug 10503 */
- if (!dentry->d_inode->i_nlink) {
- spin_lock(&inode->i_lock);
- d_lustre_invalidate(dentry, 0);
- spin_unlock(&inode->i_lock);
- }
+ if (!dentry->d_inode->i_nlink)
+ d_lustre_invalidate(dentry);
ll_lookup_finish_locks(&oit, dentry);
out:
RETURN(0);
down_read(&lli->lli_lsm_sem);
- rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+ rc = md_merge_attr(ll_i2mdexp(inode), &lli->lli_fid, lli->lli_lsm_md,
&attr, ll_md_blocking_ast);
up_read(&lli->lli_lsm_sem);
if (rc != 0)
RETURN(0);
}
-int ll_getattr_dentry(struct dentry *de, struct kstat *stat)
+int ll_getattr_dentry(struct dentry *de, struct kstat *stat, u32 request_mask,
+ unsigned int flags)
{
struct inode *inode = de->d_inode;
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct ll_inode_info *lli = ll_i2info(inode);
+ struct inode *dir = de->d_parent->d_inode;
+ bool need_glimpse = true;
ktime_t kstart = ktime_get();
int rc;
+ /* The OST object(s) determine the file size, blocks and mtime. */
+ if (!(request_mask & STATX_SIZE || request_mask & STATX_BLOCKS ||
+ request_mask & STATX_MTIME))
+ need_glimpse = false;
+
+ if (dentry_may_statahead(dir, de))
+ ll_start_statahead(dir, de, need_glimpse &&
+ !(flags & AT_STATX_DONT_SYNC));
+
+ if (flags & AT_STATX_DONT_SYNC)
+ GOTO(fill_attr, rc = 0);
+
rc = ll_inode_revalidate(de, IT_GETATTR);
if (rc < 0)
RETURN(rc);
if (S_ISREG(inode->i_mode)) {
bool cached;
- rc = pcc_inode_getattr(inode, &cached);
+ if (!need_glimpse)
+ GOTO(fill_attr, rc);
+
+ rc = pcc_inode_getattr(inode, request_mask, flags, &cached);
if (cached && rc < 0)
RETURN(rc);
+ if (cached)
+ GOTO(fill_attr, rc);
+
+ /*
+ * If the returned attr is masked with OBD_MD_FLSIZE &
+ * OBD_MD_FLBLOCKS & OBD_MD_FLMTIME, it means that the file size
+ * or blocks obtained from MDT is strictly correct, and the file
+ * is usually not being modified by clients, and the [a|m|c]time
+ * got from MDT is also strictly correct.
+ * Under this circumstance, it does not need to send glimpse
+ * RPCs to OSTs for file attributes such as the size and blocks.
+ */
+ if (lli->lli_attr_valid & OBD_MD_FLSIZE &&
+ lli->lli_attr_valid & OBD_MD_FLBLOCKS &&
+ lli->lli_attr_valid & OBD_MD_FLMTIME) {
+ inode->i_mtime.tv_sec = lli->lli_mtime;
+ if (lli->lli_attr_valid & OBD_MD_FLATIME)
+ inode->i_atime.tv_sec = lli->lli_atime;
+ if (lli->lli_attr_valid & OBD_MD_FLCTIME)
+ inode->i_ctime.tv_sec = lli->lli_ctime;
+ GOTO(fill_attr, rc);
+ }
+
/* In case of restore, the MDT has the right size and has
* already send it back without granting the layout lock,
* inode is up-to-date so glimpse is useless.
* restore the MDT holds the layout lock so the glimpse will
* block up to the end of restore (getattr will block)
*/
- if (!cached && !ll_file_test_flag(lli, LLIF_FILE_RESTORING)) {
+ if (!ll_file_test_flag(lli, LLIF_FILE_RESTORING)) {
rc = ll_glimpse_size(inode);
if (rc < 0)
RETURN(rc);
RETURN(rc);
}
- inode->i_atime.tv_sec = lli->lli_atime;
- inode->i_mtime.tv_sec = lli->lli_mtime;
- inode->i_ctime.tv_sec = lli->lli_ctime;
+ if (lli->lli_attr_valid & OBD_MD_FLATIME)
+ inode->i_atime.tv_sec = lli->lli_atime;
+ if (lli->lli_attr_valid & OBD_MD_FLMTIME)
+ inode->i_mtime.tv_sec = lli->lli_mtime;
+ if (lli->lli_attr_valid & OBD_MD_FLCTIME)
+ inode->i_ctime.tv_sec = lli->lli_ctime;
}
+fill_attr:
OBD_FAIL_TIMEOUT(OBD_FAIL_GETATTR_DELAY, 30);
if (ll_need_32bit_api(sbi)) {
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
- stat->blksize = sbi->ll_stat_blksize ?: 1 << inode->i_blkbits;
+ /* stat->blksize is used to tell about preferred IO size */
+ if (sbi->ll_stat_blksize)
+ stat->blksize = sbi->ll_stat_blksize;
+ else if (S_ISREG(inode->i_mode))
+ stat->blksize = 1 << min(PTLRPC_MAX_BRW_BITS + 1,
+ LL_MAX_BLKSIZE_BITS);
+ else
+ stat->blksize = 1 << inode->i_sb->s_blocksize_bits;
stat->nlink = inode->i_nlink;
stat->size = i_size_read(inode);
stat->blocks = inode->i_blocks;
+#ifdef HAVE_INODEOPS_ENHANCED_GETATTR
+ if (flags & AT_STATX_DONT_SYNC) {
+ if (stat->size == 0 &&
+ lli->lli_attr_valid & OBD_MD_FLLAZYSIZE)
+ stat->size = lli->lli_lazysize;
+ if (stat->blocks == 0 &&
+ lli->lli_attr_valid & OBD_MD_FLLAZYBLOCKS)
+ stat->blocks = lli->lli_lazyblocks;
+ }
+
+ if (lli->lli_attr_valid & OBD_MD_FLBTIME) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = lli->lli_btime;
+ }
+
+ stat->attributes_mask = STATX_ATTR_IMMUTABLE | STATX_ATTR_APPEND;
+ stat->attributes |= ll_inode_to_ext_flags(inode->i_flags);
+ stat->result_mask &= request_mask;
+#endif
+
ll_stats_ops_tally(sbi, LPROC_LL_GETATTR,
ktime_us_delta(ktime_get(), kstart));
int ll_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
- struct dentry *de = path->dentry;
+ return ll_getattr_dentry(path->dentry, stat, request_mask, flags);
+}
#else
int ll_getattr(struct vfsmount *mnt, struct dentry *de, struct kstat *stat)
{
+ return ll_getattr_dentry(de, stat, STATX_BASIC_STATS,
+ AT_STATX_SYNC_AS_STAT);
+}
#endif
- return ll_getattr_dentry(de, stat);
+
+int cl_falloc(struct inode *inode, int mode, loff_t offset, loff_t len)
+{
+ struct lu_env *env;
+ struct cl_io *io;
+ __u16 refcheck;
+ int rc; loff_t sa_falloc_end;
+ loff_t size = i_size_read(inode);
+
+ ENTRY;
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ RETURN(PTR_ERR(env));
+
+ io = vvp_env_thread_io(env);
+ io->ci_obj = ll_i2info(inode)->lli_clob;
+ io->ci_verify_layout = 1;
+ io->u.ci_setattr.sa_parent_fid = lu_object_fid(&io->ci_obj->co_lu);
+ io->u.ci_setattr.sa_falloc_mode = mode;
+ io->u.ci_setattr.sa_falloc_offset = offset;
+ io->u.ci_setattr.sa_falloc_len = len;
+ io->u.ci_setattr.sa_falloc_end = io->u.ci_setattr.sa_falloc_offset +
+ io->u.ci_setattr.sa_falloc_len;
+ io->u.ci_setattr.sa_subtype = CL_SETATTR_FALLOCATE;
+ sa_falloc_end = io->u.ci_setattr.sa_falloc_end;
+ if (sa_falloc_end > size) {
+ /* Check new size against VFS/VM file size limit and rlimit */
+ rc = inode_newsize_ok(inode, sa_falloc_end);
+ if (rc)
+ goto out;
+ if (sa_falloc_end > ll_file_maxbytes(inode)) {
+ CDEBUG(D_INODE, "file size too large %llu > %llu\n",
+ (unsigned long long)(sa_falloc_end),
+ ll_file_maxbytes(inode));
+ rc = -EFBIG;
+ goto out;
+ }
+ io->u.ci_setattr.sa_attr.lvb_size = sa_falloc_end;
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ io->u.ci_setattr.sa_avalid |= ATTR_SIZE;
+ } else {
+ io->u.ci_setattr.sa_attr.lvb_size = size;
+ }
+
+again:
+ if (cl_io_init(env, io, CIT_SETATTR, io->ci_obj) == 0)
+ rc = cl_io_loop(env, io);
+ else
+ rc = io->ci_result;
+
+ cl_io_fini(env, io);
+ if (unlikely(io->ci_need_restart))
+ goto again;
+
+out:
+ cl_env_put(env, &refcheck);
+ RETURN(rc);
+}
+
+long ll_fallocate(struct file *filp, int mode, loff_t offset, loff_t len)
+{
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ int rc;
+
+ /*
+ * Encrypted inodes can't handle collapse range or zero range or insert
+ * range since we would need to re-encrypt blocks with a different IV or
+ * XTS tweak (which are based on the logical block number).
+ * Similar to what ext4 does.
+ */
+ if (IS_ENCRYPTED(inode) &&
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE |
+ FALLOC_FL_ZERO_RANGE)))
+ RETURN(-EOPNOTSUPP);
+
+ /*
+ * Only mode == 0 (which is standard prealloc) is supported now.
+ * Punch is not supported yet.
+ */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ RETURN(-EOPNOTSUPP);
+
+ ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_FALLOCATE, 1);
+
+ rc = cl_falloc(inode, mode, offset, len);
+
+ RETURN(rc);
}
static int ll_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
cfs_cap_t cap;
bool squash_id = false;
ktime_t kstart = ktime_get();
+
ENTRY;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
- /* as root inode are NOT getting validated in lookup operation,
- * need to do it before permission check. */
+ /*
+ * as root inode are NOT getting validated in lookup operation,
+ * need to do it before permission check.
+ */
- if (inode == inode->i_sb->s_root->d_inode) {
+ if (inode == inode->i_sb->s_root->d_inode) {
rc = ll_inode_revalidate(inode->i_sb->s_root, IT_LOOKUP);
- if (rc)
- RETURN(rc);
- }
+ if (rc)
+ RETURN(rc);
+ }
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), inode mode %x mask %o\n",
PFID(ll_inode2fid(inode)), inode, inode->i_mode, mask);
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)
+ if (BIT(cap) & CFS_CAP_FS_MASK)
cap_lower(cred->cap_effective, cap);
}
old_cred = override_creds(cred);
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+#ifndef HAVE_DEFAULT_FILE_SPLICE_READ_EXPORT
+ .splice_read = generic_file_splice_read,
+#else
+ .splice_read = pcc_file_splice_read,
+#endif
.fsync = ll_fsync,
- .flush = ll_flush
+ .flush = ll_flush,
+ .fallocate = ll_fallocate,
};
struct file_operations ll_file_operations_flock = {
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+#ifndef HAVE_DEFAULT_FILE_SPLICE_READ_EXPORT
+ .splice_read = generic_file_splice_read,
+#else
+ .splice_read = pcc_file_splice_read,
+#endif
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
- .lock = ll_file_flock
+ .lock = ll_file_flock,
+ .fallocate = ll_fallocate,
};
/* These are for -o noflock - to return ENOSYS on flock calls */
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+#ifndef HAVE_DEFAULT_FILE_SPLICE_READ_EXPORT
+ .splice_read = generic_file_splice_read,
+#else
+ .splice_read = pcc_file_splice_read,
+#endif
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
- .lock = ll_file_noflock
+ .lock = ll_file_noflock,
+ .fallocate = ll_fallocate,
};
struct inode_operations ll_file_inode_operations = {