dout("%s osd_req %p for obj_req %p objno %llu %llu~%llu\n",
__func__, osd_req, obj_req, obj_req->ex.oe_objno,
obj_req->ex.oe_off, obj_req->ex.oe_len);
- ceph_osdc_start_request(osd_req->r_osdc, osd_req, false);
+ ceph_osdc_start_request(osd_req->r_osdc, osd_req);
}
/*
if (ret)
return ret;
- ceph_osdc_start_request(osdc, req, false);
+ ceph_osdc_start_request(osdc, req);
return 0;
}
static void rbd_free_disk(struct rbd_device *rbd_dev)
{
- blk_cleanup_disk(rbd_dev->disk);
+ put_disk(rbd_dev->disk);
blk_mq_free_tag_set(&rbd_dev->tag_set);
rbd_dev->disk = NULL;
}
if (ret)
goto out_req;
- ceph_osdc_start_request(osdc, req, false);
+ ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0)
ceph_copy_from_page_vector(pages, buf, 0, ret);
* Reference snap context in folio->private. Also set
* PagePrivate so that we get invalidate_folio callback.
*/
- VM_BUG_ON_FOLIO(folio_test_private(folio), folio);
+ VM_WARN_ON_FOLIO(folio->private, folio);
folio_attach_private(folio, snapc);
return ceph_fscache_dirty_folio(mapping, folio);
if (err >= 0 && err < subreq->len)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
- netfs_subreq_terminated(subreq, err, true);
+ netfs_subreq_terminated(subreq, err, false);
num_pages = calc_pages_for(osd_data->alignment, osd_data->length);
ceph_put_page_vector(osd_data->pages, num_pages, false);
int err = 0;
u64 len = subreq->len;
- if (ci->i_inline_version != CEPH_INLINE_NONE &&
- ceph_netfs_issue_op_inline(subreq))
+ if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
return;
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
dout("%s: pos=%llu orig_len=%zu len=%llu\n", __func__, subreq->start, subreq->len, len);
iov_iter_xarray(&iter, READ, &rreq->mapping->i_pages, subreq->start, len);
- err = iov_iter_get_pages_alloc(&iter, &pages, len, &page_off);
+ err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
if (err < 0) {
dout("%s: iov_ter_get_pages_alloc returned %d\n", __func__, err);
goto out;
/* should always give us a page-aligned read */
WARN_ON_ONCE(page_off);
len = err;
+ err = 0;
osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
req->r_callback = finish_netfs_read;
req->r_inode = inode;
ihold(inode);
- err = ceph_osdc_start_request(req->r_osdc, req, false);
- if (err)
- iput(inode);
+ ceph_osdc_start_request(req->r_osdc, req);
out:
ceph_osdc_put_request(req);
if (err)
dout("writepage %llu~%llu (%llu bytes)\n", page_off, len, len);
req->r_mtime = inode->i_mtime;
- err = ceph_osdc_start_request(osdc, req, true);
- if (!err)
- err = ceph_osdc_wait_request(osdc, req);
+ ceph_osdc_start_request(osdc, req);
+ err = ceph_osdc_wait_request(osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, err);
}
req->r_mtime = inode->i_mtime;
- rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
- BUG_ON(rc);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
req = NULL;
wbc->nr_to_write -= i;
int r;
r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
- if (r == 0)
- folio_wait_fscache(folio);
- if (r < 0) {
- if (folio)
- folio_put(folio);
- } else {
- WARN_ON_ONCE(!folio_test_locked(folio));
- *pagep = &folio->page;
- }
- return r;
+ if (r < 0)
+ return r;
+
+ folio_wait_fscache(folio);
+ WARN_ON_ONCE(!folio_test_locked(folio));
+ *pagep = &folio->page;
+ return 0;
}
/*
inode, off, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
- ci->i_inline_version == CEPH_INLINE_NONE) {
+ !ceph_has_inline_data(ci)) {
CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
ceph_add_rw_context(fi, &rw_ctx);
ret = filemap_fault(vmf);
}
req->r_mtime = inode->i_mtime;
- err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!err)
- err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ err = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_osdc_put_request(req);
if (err < 0)
goto out_unlock;
}
req->r_mtime = inode->i_mtime;
- err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!err)
- err = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ err = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, err);
osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
0, false, true);
- err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
+ ceph_osdc_start_request(&fsc->client->osdc, rd_req);
wr_req->r_mtime = ci->netfs.inode.i_mtime;
- err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
+ ceph_osdc_start_request(&fsc->client->osdc, wr_req);
- if (!err)
- err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
- if (!err2)
- err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
+ err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
+ err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);
if (err >= 0 || err == -ENOENT)
have |= POOL_READ;
size_t start;
int idx = 0;
- bytes = iov_iter_get_pages(iter, pages, maxsize - size,
+ bytes = iov_iter_get_pages2(iter, pages, maxsize - size,
ITER_GET_BVECS_PAGES, &start);
if (bytes < 0)
return size ?: bytes;
- iov_iter_advance(iter, bytes);
size += bytes;
for ( ; bytes; idx++, bvec_idx++) {
INIT_LIST_HEAD(&fi->rw_contexts);
fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
- if ((file->f_mode & FMODE_WRITE) &&
- ci->i_inline_version != CEPH_INLINE_NONE) {
+ if ((file->f_mode & FMODE_WRITE) && ceph_has_inline_data(ci)) {
ret = ceph_uninline_data(file);
if (ret < 0)
goto error;
char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
&base, 0);
- pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n",
+ pr_warn("async create failure path=(%llx)%s result=%d!\n",
base, IS_ERR(path) ? "<<bad>>" : path, result);
ceph_mdsc_free_path(path, pathlen);
struct ceph_mds_reply_inode in = { };
struct ceph_mds_reply_info_in iinfo = { .in = &in };
struct ceph_inode_info *ci = ceph_inode(dir);
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
struct inode *inode;
struct timespec64 now;
struct ceph_string *pool_ns;
/* Directories always inherit the setgid bit. */
if (S_ISDIR(mode))
mode |= S_ISGID;
- else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
- !in_group_p(dir->i_gid) &&
- !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID))
- mode &= ~S_ISGID;
} else {
in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid()));
}
file->f_mode |= FMODE_CREATED;
ret = finish_open(file, dentry, ceph_open);
}
+
+ spin_lock(&dentry->d_lock);
+ di->flags &= ~CEPH_DENTRY_ASYNC_CREATE;
+ wake_up_bit(&di->flags, CEPH_DENTRY_ASYNC_CREATE_BIT);
+ spin_unlock(&dentry->d_lock);
+
return ret;
}
if (dentry->d_name.len > NAME_MAX)
return -ENAMETOOLONG;
+ err = ceph_wait_on_conflict_unlink(dentry);
+ if (err)
+ return err;
+ /*
+ * Do not truncate the file, since atomic_open is called before the
+ * permission check. The caller will do the truncation afterward.
+ */
+ flags &= ~O_TRUNC;
+
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
(req->r_dir_caps =
try_prep_async_create(dir, dentry, &lo,
&req->r_deleg_ino))) {
+ struct ceph_dentry_info *di = ceph_dentry(dentry);
+
set_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags);
req->r_args.open.flags |= cpu_to_le32(CEPH_O_EXCL);
req->r_callback = ceph_async_create_cb;
+
+ spin_lock(&dentry->d_lock);
+ di->flags |= CEPH_DENTRY_ASYNC_CREATE;
+ spin_unlock(&dentry->d_lock);
+
err = ceph_mdsc_submit_request(mdsc, dir, req);
if (!err) {
err = ceph_finish_async_create(dir, dentry,
}
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
- err = ceph_mdsc_do_request(mdsc,
- (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
- req);
+ err = ceph_mdsc_do_request(mdsc, (flags & O_CREAT) ? dir : NULL, req);
if (err == -ENOENT) {
dentry = ceph_handle_snapdir(req, dentry);
if (IS_ERR(dentry)) {
osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
false, false);
- ret = ceph_osdc_start_request(osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(osdc, req);
+ ceph_osdc_start_request(osdc, req);
+ ret = ceph_osdc_wait_request(osdc, req);
ceph_update_read_metrics(&fsc->mdsc->metric,
req->r_start_latency,
req->r_inode = inode;
req->r_priv = aio_req;
- ret = ceph_osdc_start_request(req->r_osdc, req, false);
+ ceph_osdc_start_request(req->r_osdc, req);
out:
if (ret < 0) {
req->r_result = ret;
size_t count = iov_iter_count(iter);
loff_t pos = iocb->ki_pos;
bool write = iov_iter_rw(iter) == WRITE;
- bool should_dirty = !write && iter_is_iovec(iter);
+ bool should_dirty = !write && user_backed_iter(iter);
if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
continue;
}
- ret = ceph_osdc_start_request(req->r_osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(req->r_osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
if (write)
ceph_update_write_metrics(metric, req->r_start_latency,
r_private_item);
list_del_init(&req->r_private_item);
if (ret >= 0)
- ret = ceph_osdc_start_request(req->r_osdc,
- req, false);
+ ceph_osdc_start_request(req->r_osdc, req);
if (ret < 0) {
req->r_result = ret;
ceph_aio_complete_req(req);
false, true);
req->r_mtime = mtime;
- ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!ret)
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
ceph_update_write_metrics(&fsc->mdsc->metric, req->r_start_latency,
req->r_end_latency, len, ret);
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- if (ci->i_inline_version == CEPH_INLINE_NONE) {
+ if (!ceph_has_inline_data(ci)) {
if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
ret = ceph_direct_read_write(iocb, to,
NULL, NULL);
if (dirty)
__mark_inode_dirty(inode, dirty);
if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
- ceph_check_caps(ci, 0, NULL);
+ ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
}
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
*/
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *inode = file->f_mapping->host;
- struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- loff_t i_size;
- loff_t ret;
-
- inode_lock(inode);
-
if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
+ struct inode *inode = file_inode(file);
+ int ret;
+
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
if (ret < 0)
- goto out;
- }
-
- i_size = i_size_read(inode);
- switch (whence) {
- case SEEK_END:
- offset += i_size;
- break;
- case SEEK_CUR:
- /*
- * Here we special-case the lseek(fd, 0, SEEK_CUR)
- * position-querying operation. Avoid rewriting the "same"
- * f_pos value back to the file because a concurrent read(),
- * write() or lseek() might have altered it
- */
- if (offset == 0) {
- ret = file->f_pos;
- goto out;
- }
- offset += file->f_pos;
- break;
- case SEEK_DATA:
- if (offset < 0 || offset >= i_size) {
- ret = -ENXIO;
- goto out;
- }
- break;
- case SEEK_HOLE:
- if (offset < 0 || offset >= i_size) {
- ret = -ENXIO;
- goto out;
- }
- offset = i_size;
- break;
+ return ret;
}
-
- ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size));
-
- out:
- inode_unlock(inode);
- return ret;
+ return generic_file_llseek(file, offset, whence);
}
static inline void ceph_zero_partial_page(
}
req->r_mtime = inode->i_mtime;
- ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
- if (!ret) {
- ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
- if (ret == -ENOENT)
- ret = 0;
- }
+ ceph_osdc_start_request(&fsc->client->osdc, req);
+ ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+ if (ret == -ENOENT)
+ ret = 0;
ceph_osdc_put_request(req);
out:
if (IS_ERR(req))
ret = PTR_ERR(req);
else {
- ceph_osdc_start_request(osdc, req, false);
+ ceph_osdc_start_request(osdc, req);
ret = ceph_osdc_wait_request(osdc, req);
ceph_update_copyfrom_metrics(&fsc->mdsc->metric,
req->r_start_latency,
/* Let the MDS know about dst file size change */
if (ceph_inode_set_size(dst_inode, dst_off) ||
ceph_quota_is_max_bytes_approaching(dst_inode, dst_off))
- ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY, NULL);
+ ceph_check_caps(dst_ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_FLUSH,
+ NULL);
}
/* Mark Fw dirty */
spin_lock(&dst_ci->i_ceph_lock);
#define FSCRYPT_CONTEXT_V2 2
/* Keep this in sync with include/uapi/linux/fscrypt.h */
-#define FSCRYPT_MODE_MAX FSCRYPT_MODE_ADIANTUM
+#define FSCRYPT_MODE_MAX FSCRYPT_MODE_AES_256_HCTR2
struct fscrypt_context_v1 {
u8 version; /* FSCRYPT_CONTEXT_V1 */
const struct fscrypt_info *ci);
/* fname.c */
- int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
- u8 *out, unsigned int olen);
- bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
- u32 orig_len, u32 max_len,
- u32 *encrypted_len_ret);
+ bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+ u32 orig_len, u32 max_len,
+ u32 *encrypted_len_ret);
/* hkdf.c */
-
struct fscrypt_hkdf {
struct crypto_shash *hmac_tfm;
};
return sb->s_cop->get_dummy_policy(sb);
}
-static bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode)
+static bool fscrypt_valid_enc_modes_v1(u32 contents_mode, u32 filenames_mode)
{
if (contents_mode == FSCRYPT_MODE_AES_256_XTS &&
filenames_mode == FSCRYPT_MODE_AES_256_CTS)
return false;
}
+static bool fscrypt_valid_enc_modes_v2(u32 contents_mode, u32 filenames_mode)
+{
+ if (contents_mode == FSCRYPT_MODE_AES_256_XTS &&
+ filenames_mode == FSCRYPT_MODE_AES_256_HCTR2)
+ return true;
+ return fscrypt_valid_enc_modes_v1(contents_mode, filenames_mode);
+}
+
static bool supported_direct_key_modes(const struct inode *inode,
u32 contents_mode, u32 filenames_mode)
{
static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy,
const struct inode *inode)
{
- if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+ if (!fscrypt_valid_enc_modes_v1(policy->contents_encryption_mode,
policy->filenames_encryption_mode)) {
fscrypt_warn(inode,
"Unsupported encryption modes (contents %d, filenames %d)",
{
int count = 0;
- if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+ if (!fscrypt_valid_enc_modes_v2(policy->contents_encryption_mode,
policy->filenames_encryption_mode)) {
fscrypt_warn(inode,
"Unsupported encryption modes (contents %d, filenames %d)",
return fscrypt_get_dummy_policy(dir->i_sb);
}
+ /**
+ * fscrypt_context_for_new_inode() - create an encryption context for a new inode
+ * @ctx: where context should be written
+ * @inode: inode from which to fetch policy and nonce
+ *
+ * Given an in-core "prepared" (via fscrypt_prepare_new_inode) inode,
+ * generate a new context and write it to ctx. ctx _must_ be at least
+ * FSCRYPT_SET_CONTEXT_MAX_SIZE bytes.
+ *
+ * Return: size of the resulting context or a negative error code.
+ */
+ int fscrypt_context_for_new_inode(void *ctx, struct inode *inode)
+ {
+ struct fscrypt_info *ci = inode->i_crypt_info;
+
+ BUILD_BUG_ON(sizeof(union fscrypt_context) !=
+ FSCRYPT_SET_CONTEXT_MAX_SIZE);
+
+ /* fscrypt_prepare_new_inode() should have set up the key already. */
+ if (WARN_ON_ONCE(!ci))
+ return -ENOKEY;
+
+ return fscrypt_new_context(ctx, &ci->ci_policy, ci->ci_nonce);
+ }
+ EXPORT_SYMBOL_GPL(fscrypt_context_for_new_inode);
+
/**
* fscrypt_set_context() - Set the fscrypt context of a new inode
* @inode: a new inode
union fscrypt_context ctx;
int ctxsize;
- /* fscrypt_prepare_new_inode() should have set up the key already. */
- if (WARN_ON_ONCE(!ci))
- return -ENOKEY;
-
- BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
- ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, ci->ci_nonce);
+ ctxsize = fscrypt_context_for_new_inode(&ctx, inode);
+ if (ctxsize < 0)
+ return ctxsize;
/*
* This may be the first time the inode number is available, so do any
}
res = d_splice_alias(inode, found);
if (res) {
+ d_lookup_done(found);
dput(found);
return res;
}
}
EXPORT_SYMBOL(d_add_ci);
-
- static inline bool d_same_name(const struct dentry *dentry,
- const struct dentry *parent,
- const struct qstr *name)
+ /**
+ * d_same_name - compare dentry name with case-exact name
+ * @parent: parent dentry
+ * @dentry: the negative dentry that was passed to the parent's lookup func
+ * @name: the case-exact name to be associated with the returned dentry
+ *
+ * Return: true if names are same, or false
+ */
+ bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
+ const struct qstr *name)
{
if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) {
if (dentry->d_name.len != name->len)
dentry->d_name.len, dentry->d_name.name,
name) == 0;
}
+ EXPORT_SYMBOL_GPL(d_same_name);
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
static inline unsigned start_dir_add(struct inode *dir)
{
-
+ /*
+ * The caller holds a spinlock (dentry::d_lock). On !PREEMPT_RT
+ * kernels spin_lock() implicitly disables preemption, but not on
+ * PREEMPT_RT. So for RT it has to be done explicitly to protect
+ * the sequence count write side critical section against a reader
+ * or another writer preempting, which would result in a live lock.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_disable();
for (;;) {
unsigned n = dir->i_dir_seq;
if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
}
}
-static inline void end_dir_add(struct inode *dir, unsigned n)
+static inline void end_dir_add(struct inode *dir, unsigned int n,
+ wait_queue_head_t *d_wait)
{
smp_store_release(&dir->i_dir_seq, n + 2);
+ if (IS_ENABLED(CONFIG_PREEMPT_RT))
+ preempt_enable();
+ wake_up_all(d_wait);
}
static void d_wait_lookup(struct dentry *dentry)
}
EXPORT_SYMBOL(d_alloc_parallel);
-void __d_lookup_done(struct dentry *dentry)
+/*
+ * - Unhash the dentry
+ * - Retrieve and clear the waitqueue head in dentry
+ * - Return the waitqueue head
+ */
+static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry)
{
- struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent,
- dentry->d_name.hash);
+ wait_queue_head_t *d_wait;
+ struct hlist_bl_head *b;
+
+ lockdep_assert_held(&dentry->d_lock);
+
+ b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash);
hlist_bl_lock(b);
dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
- wake_up_all(dentry->d_wait);
+ d_wait = dentry->d_wait;
dentry->d_wait = NULL;
hlist_bl_unlock(b);
INIT_HLIST_NODE(&dentry->d_u.d_alias);
INIT_LIST_HEAD(&dentry->d_lru);
+ return d_wait;
+}
+
+void __d_lookup_unhash_wake(struct dentry *dentry)
+{
+ spin_lock(&dentry->d_lock);
+ wake_up_all(__d_lookup_unhash(dentry));
+ spin_unlock(&dentry->d_lock);
}
-EXPORT_SYMBOL(__d_lookup_done);
+EXPORT_SYMBOL(__d_lookup_unhash_wake);
/* inode->i_lock held if inode is non-NULL */
static inline void __d_add(struct dentry *dentry, struct inode *inode)
{
+ wait_queue_head_t *d_wait;
struct inode *dir = NULL;
unsigned n;
spin_lock(&dentry->d_lock);
if (unlikely(d_in_lookup(dentry))) {
dir = dentry->d_parent->d_inode;
n = start_dir_add(dir);
- __d_lookup_done(dentry);
+ d_wait = __d_lookup_unhash(dentry);
}
if (inode) {
unsigned add_flags = d_flags_for_inode(inode);
}
__d_rehash(dentry);
if (dir)
- end_dir_add(dir, n);
+ end_dir_add(dir, n, d_wait);
spin_unlock(&dentry->d_lock);
if (inode)
spin_unlock(&inode->i_lock);
bool exchange)
{
struct dentry *old_parent, *p;
+ wait_queue_head_t *d_wait;
struct inode *dir = NULL;
unsigned n;
if (unlikely(d_in_lookup(target))) {
dir = target->d_parent->d_inode;
n = start_dir_add(dir);
- __d_lookup_done(target);
+ d_wait = __d_lookup_unhash(target);
}
write_seqcount_begin(&dentry->d_seq);
write_seqcount_end(&dentry->d_seq);
if (dir)
- end_dir_add(dir, n);
+ end_dir_add(dir, n, d_wait);
if (dentry->d_parent != old_parent)
spin_unlock(&dentry->d_parent->d_lock);
INIT_LIST_HEAD(&inode->i_io_list);
INIT_LIST_HEAD(&inode->i_wb_list);
INIT_LIST_HEAD(&inode->i_lru);
+ INIT_LIST_HEAD(&inode->i_sb_list);
__address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
}
{
/*
* We have to cycle the i_pages lock here because reclaim can be in the
- * process of removing the last page (in __delete_from_page_cache())
+ * process of removing the last page (in __filemap_remove_folio())
* and we must not free the mapping under it.
*/
xa_lock_irq(&inode->i_data.i_pages);
spin_lock(&inode->i_lock);
inode->i_state = 0;
spin_unlock(&inode->i_lock);
- INIT_LIST_HEAD(&inode->i_sb_list);
}
return inode;
}
{
struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
struct inode *old;
- bool creating = inode->i_state & I_CREATING;
again:
spin_lock(&inode_hash_lock);
inode->i_state |= I_NEW;
hlist_add_head_rcu(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
- if (!creating)
+
+ /*
+ * Add inode to the sb list if it's not already. It has I_NEW at this
+ * point, so it should be safe to test i_sb_list locklessly.
+ */
+ if (list_empty(&inode->i_sb_list))
inode_sb_list_add(inode);
unlock:
spin_unlock(&inode_hash_lock);
return notify_change(mnt_userns, dentry, &newattrs, NULL);
}
-/*
- * Remove special file priviledges (suid, capabilities) when file is written
- * to or truncated.
- */
-int file_remove_privs(struct file *file)
+static int __file_remove_privs(struct file *file, unsigned int flags)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = file_inode(file);
+ int error;
int kill;
- int error = 0;
- /*
- * Fast path for nothing security related.
- * As well for non-regular files, e.g. blkdev inodes.
- * For example, blkdev_write_iter() might get here
- * trying to remove privs which it is not allowed to.
- */
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(dentry);
- if (kill < 0)
+ if (kill <= 0)
return kill;
- if (kill)
- error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
if (!error)
inode_has_no_xattr(inode);
return error;
}
-EXPORT_SYMBOL(file_remove_privs);
/**
- * file_update_time - update mtime and ctime time
- * @file: file accessed
+ * file_remove_privs - remove special file privileges (suid, capabilities)
+ * @file: file to remove privileges from
+ *
+ * When file is modified by a write or truncation ensure that special
+ * file privileges are removed.
*
- * Update the mtime and ctime members of an inode and mark the inode
- * for writeback. Note that this function is meant exclusively for
- * usage in the file write path of filesystems, and filesystems may
- * choose to explicitly ignore update via this function with the
- * S_NOCMTIME inode flag, e.g. for network filesystem where these
- * timestamps are handled by the server. This can return an error for
- * file systems who need to allocate space in order to update an inode.
+ * Return: 0 on success, negative errno on failure.
*/
+int file_remove_privs(struct file *file)
+{
+ return __file_remove_privs(file, 0);
+}
+EXPORT_SYMBOL(file_remove_privs);
-int file_update_time(struct file *file)
+static int inode_needs_update_time(struct inode *inode, struct timespec64 *now)
{
- struct inode *inode = file_inode(file);
- struct timespec64 now;
int sync_it = 0;
- int ret;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return 0;
- now = current_time(inode);
- if (!timespec64_equal(&inode->i_mtime, &now))
+ if (!timespec64_equal(&inode->i_mtime, now))
sync_it = S_MTIME;
- if (!timespec64_equal(&inode->i_ctime, &now))
+ if (!timespec64_equal(&inode->i_ctime, now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
if (!sync_it)
return 0;
- /* Finally allowed to write? Takes lock. */
- if (__mnt_want_write_file(file))
- return 0;
+ return sync_it;
+}
- ret = inode_update_time(inode, &now, sync_it);
- __mnt_drop_write_file(file);
+static int __file_update_time(struct file *file, struct timespec64 *now,
+ int sync_mode)
+{
+ int ret = 0;
+ struct inode *inode = file_inode(file);
+
+ /* try to update time settings */
+ if (!__mnt_want_write_file(file)) {
+ ret = inode_update_time(inode, now, sync_mode);
+ __mnt_drop_write_file(file);
+ }
return ret;
}
+
+/**
+ * file_update_time - update mtime and ctime time
+ * @file: file accessed
+ *
+ * Update the mtime and ctime members of an inode and mark the inode for
+ * writeback. Note that this function is meant exclusively for usage in
+ * the file write path of filesystems, and filesystems may choose to
+ * explicitly ignore updates via this function with the _NOCMTIME inode
+ * flag, e.g. for network filesystem where these imestamps are handled
+ * by the server. This can return an error for file systems who need to
+ * allocate space in order to update an inode.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_update_time(struct file *file)
+{
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
+
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+
+ return __file_update_time(file, &now, ret);
+}
EXPORT_SYMBOL(file_update_time);
-/* Caller must hold the file's inode lock */
-int file_modified(struct file *file)
+/**
+ * file_modified_flags - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ * @flags: kiocb flags
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * If IOCB_NOWAIT is set, special file privileges will not be removed and
+ * time settings will not be updated. It will return -EAGAIN.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int file_modified_flags(struct file *file, int flags)
{
- int err;
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
/*
* Clear the security bits if the process is not being run by root.
* This keeps people from modifying setuid and setgid binaries.
*/
- err = file_remove_privs(file);
- if (err)
- return err;
+ ret = __file_remove_privs(file, flags);
+ if (ret)
+ return ret;
if (unlikely(file->f_mode & FMODE_NOCMTIME))
return 0;
- return file_update_time(file);
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ return __file_update_time(file, &now, ret);
+}
+
+/**
+ * file_modified - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_modified(struct file *file)
+{
+ return file_modified_flags(file, 0);
}
EXPORT_SYMBOL(file_modified);
+/**
+ * kiocb_modified - handle mandated vfs changes when modifying a file
+ * @iocb: iocb that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int kiocb_modified(struct kiocb *iocb)
+{
+ return file_modified_flags(iocb->ki_filp, iocb->ki_flags);
+}
+EXPORT_SYMBOL_GPL(kiocb_modified);
+
int inode_needs_sync(struct inode *inode)
{
if (IS_SYNC(inode))
/* Directories are special, and always inherit S_ISGID */
if (S_ISDIR(mode))
mode |= S_ISGID;
- else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
- !in_group_p(i_gid_into_mnt(mnt_userns, dir)) &&
- !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
- mode &= ~S_ISGID;
} else
inode_fsgid_set(inode, mnt_userns);
inode->i_mode = mode;
return timestamp_truncate(now, inode);
}
EXPORT_SYMBOL(current_time);
+
+/**
+ * mode_strip_sgid - handle the sgid bit for non-directories
+ * @mnt_userns: User namespace of the mount the inode was created from
+ * @dir: parent directory inode
+ * @mode: mode of the file to be created in @dir
+ *
+ * If the @mode of the new file has both the S_ISGID and S_IXGRP bit
+ * raised and @dir has the S_ISGID bit raised ensure that the caller is
+ * either in the group of the parent directory or they have CAP_FSETID
+ * in their user namespace and are privileged over the parent directory.
+ * In all other cases, strip the S_ISGID bit from @mode.
+ *
+ * Return: the new mode to use for the file
+ */
+umode_t mode_strip_sgid(struct user_namespace *mnt_userns,
+ const struct inode *dir, umode_t mode)
+{
+ if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP))
+ return mode;
+ if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID))
+ return mode;
+ if (in_group_p(i_gid_into_mnt(mnt_userns, dir)))
+ return mode;
+ if (capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
+ return mode;
+
+ return mode & ~S_ISGID;
+}
+EXPORT_SYMBOL(mode_strip_sgid);
wait_queue_head_t *);
extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
+ extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
+ const struct qstr *name);
extern struct dentry * d_exact_alias(struct dentry *, struct inode *);
extern struct dentry *d_find_any_alias(struct inode *inode);
extern struct dentry * d_obtain_alias(struct inode *);
spin_unlock(&dentry->d_lock);
}
-extern void __d_lookup_done(struct dentry *);
+extern void __d_lookup_unhash_wake(struct dentry *dentry);
static inline int d_in_lookup(const struct dentry *dentry)
{
static inline void d_lookup_done(struct dentry *dentry)
{
- if (unlikely(d_in_lookup(dentry))) {
- spin_lock(&dentry->d_lock);
- __d_lookup_done(dentry);
- spin_unlock(&dentry->d_lock);
- }
+ if (unlikely(d_in_lookup(dentry)))
+ __d_lookup_unhash_wake(dentry);
}
extern void dput(struct dentry *);