aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ceph
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/addr.c21
-rw-r--r--fs/ceph/export.c32
-rw-r--r--fs/ceph/file.c1
-rw-r--r--fs/ceph/ioctl.c102
-rw-r--r--fs/ceph/ioctl.h2
-rw-r--r--fs/ceph/mds_client.c54
-rw-r--r--fs/ceph/mds_client.h5
-rw-r--r--fs/ceph/snap.c2
-rw-r--r--fs/ceph/xattr.c9
9 files changed, 109 insertions, 119 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 173b1d22e59b..8b67304e4b80 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -54,7 +54,12 @@
(CONGESTION_ON_THRESH(congestion_kb) - \
(CONGESTION_ON_THRESH(congestion_kb) >> 2))
-
+static inline struct ceph_snap_context *page_snap_context(struct page *page)
+{
+ if (PagePrivate(page))
+ return (void *)page->private;
+ return NULL;
+}
/*
* Dirty a page. Optimistically adjust accounting, on the assumption
@@ -142,10 +147,9 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
{
struct inode *inode;
struct ceph_inode_info *ci;
- struct ceph_snap_context *snapc = (void *)page->private;
+ struct ceph_snap_context *snapc = page_snap_context(page);
BUG_ON(!PageLocked(page));
- BUG_ON(!page->private);
BUG_ON(!PagePrivate(page));
BUG_ON(!page->mapping);
@@ -182,7 +186,6 @@ static int ceph_releasepage(struct page *page, gfp_t g)
struct inode *inode = page->mapping ? page->mapping->host : NULL;
dout("%p releasepage %p idx %lu\n", inode, page, page->index);
WARN_ON(PageDirty(page));
- WARN_ON(page->private);
WARN_ON(PagePrivate(page));
return 0;
}
@@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
osdc = &fsc->client->osdc;
/* verify this is a writeable snap context */
- snapc = (void *)page->private;
+ snapc = page_snap_context(page);
if (snapc == NULL) {
dout("writepage %p page %p not dirty?\n", inode, page);
goto out;
@@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
oldest = get_oldest_context(inode, &snap_size);
if (snapc->seq > oldest->seq) {
dout("writepage %p page %p snapc %p not writeable - noop\n",
- inode, page, (void *)page->private);
+ inode, page, snapc);
/* we should only noop if called by kswapd */
WARN_ON((current->flags & PF_MEMALLOC) == 0);
ceph_put_snap_context(oldest);
@@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req,
clear_bdi_congested(&fsc->backing_dev_info,
BLK_RW_ASYNC);
- ceph_put_snap_context((void *)page->private);
+ ceph_put_snap_context(page_snap_context(page));
page->private = 0;
ClearPagePrivate(page);
dout("unlocking %d %p\n", i, page);
@@ -795,7 +798,7 @@ get_more_pages:
}
/* only if matching snap context */
- pgsnapc = (void *)page->private;
+ pgsnapc = page_snap_context(page);
if (pgsnapc->seq > snapc->seq) {
dout("page snapc %p %lld > oldest %p %lld\n",
pgsnapc, pgsnapc->seq, snapc, snapc->seq);
@@ -984,7 +987,7 @@ retry_locked:
BUG_ON(!ci->i_snap_realm);
down_read(&mdsc->snap_rwsem);
BUG_ON(!ci->i_snap_realm->cached_context);
- snapc = (void *)page->private;
+ snapc = page_snap_context(page);
if (snapc && snapc != ci->i_head_snapc) {
/*
* this page is already dirty in another (older) snap
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index fbb2a643ef10..8e1b60e557b6 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -40,38 +40,49 @@ struct ceph_nfs_confh {
u32 parent_name_hash;
} __attribute__ ((packed));
-static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
- int connectable)
+/*
+ * The presence of @parent_inode here tells us whether NFS wants a
+ * connectable file handle. However, we want to make a connectionable
+ * file handle unconditionally so that the MDS gets as much of a hint
+ * as possible. That means we only use @parent_dentry to indicate
+ * whether nfsd wants a connectable fh, and whether we should indicate
+ * failure from a too-small @max_len.
+ */
+static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
+ struct inode *parent_inode)
{
int type;
struct ceph_nfs_fh *fh = (void *)rawfh;
struct ceph_nfs_confh *cfh = (void *)rawfh;
- struct dentry *parent;
- struct inode *inode = dentry->d_inode;
int connected_handle_length = sizeof(*cfh)/4;
int handle_length = sizeof(*fh)/4;
+ struct dentry *dentry = d_find_alias(inode);
+ struct dentry *parent;
/* don't re-export snaps */
if (ceph_snap(inode) != CEPH_NOSNAP)
return -EINVAL;
- spin_lock(&dentry->d_lock);
- parent = dentry->d_parent;
- if (*max_len >= connected_handle_length) {
+ /* if we found an alias, generate a connectable fh */
+ if (*max_len >= connected_handle_length && dentry) {
dout("encode_fh %p connectable\n", dentry);
- cfh->ino = ceph_ino(dentry->d_inode);
+ spin_lock(&dentry->d_lock);
+ parent = dentry->d_parent;
+ cfh->ino = ceph_ino(inode);
cfh->parent_ino = ceph_ino(parent->d_inode);
cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode,
dentry);
*max_len = connected_handle_length;
type = 2;
+ spin_unlock(&dentry->d_lock);
} else if (*max_len >= handle_length) {
- if (connectable) {
+ if (parent_inode) {
+ /* nfsd wants connectable */
*max_len = connected_handle_length;
type = 255;
} else {
dout("encode_fh %p\n", dentry);
- fh->ino = ceph_ino(dentry->d_inode);
+ fh->ino = ceph_ino(inode);
*max_len = handle_length;
type = 1;
}
@@ -79,7 +90,6 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
*max_len = handle_length;
type = 255;
}
- spin_unlock(&dentry->d_lock);
return type;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ed72428d9c75..988d4f302e48 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -54,7 +54,6 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
req->r_fmode = ceph_flags_to_mode(flags);
req->r_args.open.flags = cpu_to_le32(flags);
req->r_args.open.mode = cpu_to_le32(create_mode);
- req->r_args.open.preferred = cpu_to_le32(-1);
out:
return req;
}
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 790914a598dd..8e3fb69fbe62 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -26,8 +26,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
l.object_size = ceph_file_layout_object_size(ci->i_layout);
l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
- l.preferred_osd =
- (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred);
+ l.preferred_osd = (s32)-1;
if (copy_to_user(arg, &l, sizeof(l)))
return -EFAULT;
}
@@ -35,6 +34,32 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
return err;
}
+static long __validate_layout(struct ceph_mds_client *mdsc,
+ struct ceph_ioctl_layout *l)
+{
+ int i, err;
+
+ /* validate striping parameters */
+ if ((l->object_size & ~PAGE_MASK) ||
+ (l->stripe_unit & ~PAGE_MASK) ||
+ ((unsigned)l->object_size % (unsigned)l->stripe_unit))
+ return -EINVAL;
+
+ /* make sure it's a valid data pool */
+ mutex_lock(&mdsc->mutex);
+ err = -EINVAL;
+ for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+ if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) {
+ err = 0;
+ break;
+ }
+ mutex_unlock(&mdsc->mutex);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
struct inode *inode = file->f_dentry->d_inode;
@@ -44,52 +69,40 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
struct ceph_ioctl_layout l;
struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
struct ceph_ioctl_layout nl;
- int err, i;
+ int err;
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
/* validate changed params against current layout */
err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
- if (!err) {
- nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
- nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
- nl.object_size = ceph_file_layout_object_size(ci->i_layout);
- nl.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
- nl.preferred_osd =
- (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred);
- } else
+ if (err)
return err;
+ memset(&nl, 0, sizeof(nl));
if (l.stripe_count)
nl.stripe_count = l.stripe_count;
+ else
+ nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
if (l.stripe_unit)
nl.stripe_unit = l.stripe_unit;
+ else
+ nl.stripe_unit = ceph_file_layout_su(ci->i_layout);
if (l.object_size)
nl.object_size = l.object_size;
+ else
+ nl.object_size = ceph_file_layout_object_size(ci->i_layout);
if (l.data_pool)
nl.data_pool = l.data_pool;
- if (l.preferred_osd)
- nl.preferred_osd = l.preferred_osd;
+ else
+ nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout);
- if ((nl.object_size & ~PAGE_MASK) ||
- (nl.stripe_unit & ~PAGE_MASK) ||
- ((unsigned)nl.object_size % (unsigned)nl.stripe_unit))
- return -EINVAL;
+ /* this is obsolete, and always -1 */
+ nl.preferred_osd = le64_to_cpu(-1);
- /* make sure it's a valid data pool */
- if (l.data_pool > 0) {
- mutex_lock(&mdsc->mutex);
- err = -EINVAL;
- for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
- if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
- err = 0;
- break;
- }
- mutex_unlock(&mdsc->mutex);
- if (err)
- return err;
- }
+ err = __validate_layout(mdsc, &nl);
+ if (err)
+ return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
USE_AUTH_MDS);
@@ -106,8 +119,6 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
req->r_args.setlayout.layout.fl_object_size =
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
- req->r_args.setlayout.layout.fl_pg_preferred =
- cpu_to_le32(l.preferred_osd);
parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
@@ -127,33 +138,16 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
struct inode *inode = file->f_dentry->d_inode;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
- int err, i;
+ int err;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
/* copy and validate */
if (copy_from_user(&l, arg, sizeof(l)))
return -EFAULT;
- if ((l.object_size & ~PAGE_MASK) ||
- (l.stripe_unit & ~PAGE_MASK) ||
- !l.stripe_unit ||
- (l.object_size &&
- (unsigned)l.object_size % (unsigned)l.stripe_unit))
- return -EINVAL;
-
- /* make sure it's a valid data pool */
- if (l.data_pool > 0) {
- mutex_lock(&mdsc->mutex);
- err = -EINVAL;
- for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
- if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
- err = 0;
- break;
- }
- mutex_unlock(&mdsc->mutex);
- if (err)
- return err;
- }
+ err = __validate_layout(mdsc, &l);
+ if (err)
+ return err;
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
USE_AUTH_MDS);
@@ -171,8 +165,6 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
cpu_to_le32(l.object_size);
req->r_args.setlayout.layout.fl_pg_pool =
cpu_to_le32(l.data_pool);
- req->r_args.setlayout.layout.fl_pg_preferred =
- cpu_to_le32(l.preferred_osd);
err = ceph_mdsc_do_request(mdsc, inode, req);
ceph_mdsc_put_request(req);
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index be4a60487333..c77028afb1e1 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -34,6 +34,8 @@
struct ceph_ioctl_layout {
__u64 stripe_unit, stripe_count, object_size;
__u64 data_pool;
+
+ /* obsolete. new values ignored, always return -1 */
__s64 preferred_osd;
};
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 89971e137aab..200bc87eceb1 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -334,10 +334,10 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
dout("mdsc put_session %p %d -> %d\n", s,
atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
if (atomic_dec_and_test(&s->s_ref)) {
- if (s->s_authorizer)
+ if (s->s_auth.authorizer)
s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
s->s_mdsc->fsc->client->monc.auth,
- s->s_authorizer);
+ s->s_auth.authorizer);
kfree(s);
}
}
@@ -3395,39 +3395,33 @@ out:
/*
* authentication
*/
-static int get_authorizer(struct ceph_connection *con,
- void **buf, int *len, int *proto,
- void **reply_buf, int *reply_len, int force_new)
+
+/*
+ * Note: returned pointer is the address of a structure that's
+ * managed separately. Caller must *not* attempt to free it.
+ */
+static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
+ int *proto, int force_new)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
- int ret = 0;
-
- if (force_new && s->s_authorizer) {
- ac->ops->destroy_authorizer(ac, s->s_authorizer);
- s->s_authorizer = NULL;
- }
- if (s->s_authorizer == NULL) {
- if (ac->ops->create_authorizer) {
- ret = ac->ops->create_authorizer(
- ac, CEPH_ENTITY_TYPE_MDS,
- &s->s_authorizer,
- &s->s_authorizer_buf,
- &s->s_authorizer_buf_len,
- &s->s_authorizer_reply_buf,
- &s->s_authorizer_reply_buf_len);
- if (ret)
- return ret;
- }
- }
+ struct ceph_auth_handshake *auth = &s->s_auth;
+ if (force_new && auth->authorizer) {
+ if (ac->ops && ac->ops->destroy_authorizer)
+ ac->ops->destroy_authorizer(ac, auth->authorizer);
+ auth->authorizer = NULL;
+ }
+ if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
+ int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
+ auth);
+ if (ret)
+ return ERR_PTR(ret);
+ }
*proto = ac->protocol;
- *buf = s->s_authorizer_buf;
- *len = s->s_authorizer_buf_len;
- *reply_buf = s->s_authorizer_reply_buf;
- *reply_len = s->s_authorizer_reply_buf_len;
- return 0;
+
+ return auth;
}
@@ -3437,7 +3431,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
struct ceph_mds_client *mdsc = s->s_mdsc;
struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
- return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
+ return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len);
}
static int invalidate_authorizer(struct ceph_connection *con)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 8c7c04ebb595..dd26846dd71d 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -11,6 +11,7 @@
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/auth.h>
/*
* Some lock dependencies:
@@ -113,9 +114,7 @@ struct ceph_mds_session {
struct ceph_connection s_con;
- struct ceph_authorizer *s_authorizer;
- void *s_authorizer_buf, *s_authorizer_reply_buf;
- size_t s_authorizer_buf_len, s_authorizer_reply_buf_len;
+ struct ceph_auth_handshake s_auth;
/* protected by s_gen_ttl_lock */
spinlock_t s_gen_ttl_lock;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index f04c0961f993..e5206fc76562 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
/* alloc new snap context */
err = -ENOMEM;
- if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
+ if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
goto fail;
snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
if (!snapc)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 35b86331d8a5..785cb3057c95 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -118,15 +118,6 @@ static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
(unsigned long long)ceph_file_layout_su(ci->i_layout),
(unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
(unsigned long long)ceph_file_layout_object_size(ci->i_layout));
-
- if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) {
- val += ret;
- size -= ret;
- ret += snprintf(val, size, "preferred_osd=%lld\n",
- (unsigned long long)ceph_file_layout_pg_preferred(
- ci->i_layout));
- }
-
return ret;
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.