* [PATCH v4 4/5] ceph: record subvolume quarantine from MDS cap updates
2026-10-20 12:52 [PATCH v4 0/5] ceph: support subvolume quarantine Alex Markuze
` (2 preceding siblings ...)
2026-10-20 12:52 ` [PATCH v4 3/5] ceph: add subvolume quarantine wire definitions Alex Markuze
@ 2026-10-20 12:52 ` Alex Markuze
2026-10-20 12:52 ` [PATCH v4 5/5] ceph: fail quarantined subvolume access with EACCES Alex Markuze
2026-10-20 16:05 ` [PATCH v4 0/5] ceph: support subvolume quarantine Eric Biggers
5 siblings, 0 replies; 8+ messages in thread
From: Alex Markuze @ 2026-10-20 12:52 UTC (permalink / raw)
To: ceph-devel
Cc: Alex Markuze, idryomov, xiubo.li, slava, viro, brauner, jack,
linux-fsdevel, linux-fscrypt, ebiggers, tytso, jaegeuk,
linux-kernel
MClientCaps v14 appends a signed quarantine errno after the v13
subvolume ID. Decode it and keep a sticky, counted mark on the inode.
A PIN-only update can reset the errno without clearing that mark.
An accepted grant above PIN or a disable from the reporting rank
clears it. A fresh metadata request can also confirm recovery across
ranks. Ignore older cap sequences when changing quarantine state.
Retain a pending mark when the reporting cap or session is lost, so
that later access must ask the MDS rather than reuse cached caps.
Wake cap waiters when quarantine state changes.
Skip ancestry checks when no inode is marked. Otherwise cache
complete RCU parent walks by generation; incomplete walks remain
unknown and require an MDS answer. Bound retries and take no inode
or dentry references during the walk. Invalidate generations across
renames and alias attachments. Sleeping splices disable cached
answers without leaving the generation odd across an LSM callback.
This patch records state without advertising quarantine support.
The following patch adds the access checks before enabling it.
Signed-off-by: Alex Markuze <amarkuze@redhat.com>
---
fs/ceph/caps.c | 122 ++++++++++-
fs/ceph/dir.c | 9 +
fs/ceph/file.c | 2 +
fs/ceph/inode.c | 476 ++++++++++++++++++++++++++++++++++++++++++-
fs/ceph/mds_client.c | 23 ++-
fs/ceph/mds_client.h | 16 ++
fs/ceph/super.c | 2 +
fs/ceph/super.h | 71 ++++++-
8 files changed, 713 insertions(+), 8 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index b27bcdc24d29..94f015112942 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -692,8 +692,9 @@ void change_auth_cap_ses(struct ceph_inode_info *ci,
* @fmode is the open file mode, if we are opening a file, otherwise
* it is < 0. (This is so we can atomically add the cap and add an
* open file reference to it.)
+ * Returns false when the raw grant predates the recorded cap sequence.
*/
-void ceph_add_cap(struct inode *inode,
+bool ceph_add_cap(struct inode *inode,
struct ceph_mds_session *session, u64 cap_id,
unsigned issued, unsigned wanted,
unsigned seq, unsigned mseq, u64 realmino, int flags,
@@ -706,6 +707,7 @@ void ceph_add_cap(struct inode *inode,
int mds = session->s_mds;
int actual_wanted;
u32 gen;
+ bool cap_current = true;
lockdep_assert_held(&ci->i_ceph_lock);
@@ -737,6 +739,7 @@ void ceph_add_cap(struct inode *inode,
atomic64_inc(&mdsc->metric.total_caps);
spin_unlock(&session->s_cap_lock);
} else {
+ cap_current = ceph_seq_cmp(seq, cap->seq) >= 0;
spin_lock(&session->s_cap_lock);
list_move_tail(&cap->session_caps, &session->s_caps);
spin_unlock(&session->s_cap_lock);
@@ -823,6 +826,7 @@ void ceph_add_cap(struct inode *inode,
cap->mseq = mseq;
cap->cap_gen = gen;
wake_up_all(&ci->i_cap_wq);
+ return cap_current;
}
/*
@@ -1264,6 +1268,11 @@ static void __ceph_remove_cap(struct ceph_inode_info *ci, struct ceph_cap *cap,
mdsc = ceph_inode_to_fs_client(&ci->netfs.inode)->mdsc;
+ /* Losing the reporting cap requires fresh MDS revalidation. */
+ if (READ_ONCE(ci->i_qtine_mds) == cap->mds &&
+ ceph_quarantine_reset(ci))
+ wake_up_all(&ci->i_cap_wq);
+
/* remove from inode's cap rbtree, and clear auth cap */
rb_erase(&cap->ci_node, &ci->i_caps);
if (ci->i_auth_cap == cap)
@@ -3729,6 +3738,9 @@ struct cap_extra_info {
u8 *fscrypt_auth;
u32 fscrypt_auth_len;
u64 fscrypt_file_size;
+ /* MClientCaps v14 oserrno; valid only when oserrno_valid is set */
+ s32 oserrno;
+ bool oserrno_valid;
};
/*
@@ -3757,6 +3769,45 @@ static int parse_inline_data(void **p, void *end,
return -EIO;
}
+/*
+ * Record quarantine state carried by an MClientCaps oserrno.
+ * Caller holds i_ceph_lock. Returns true when waiters should be woken
+ * because quarantine changed or a pending reset was resolved.
+ *
+ * -EQUARANTINED refreshes the sticky flag and its reporting MDS rank.
+ * A current grant above PIN with errno 0 clears only that rank's mark.
+ * Another rank needs a successful metadata request for the current epoch.
+ * A PIN-only update may zero qtine_errno while leaving the flag set.
+ */
+static bool ceph_apply_quarantine(struct ceph_inode_info *ci, int mds,
+ int newcaps, int oserrno)
+{
+ bool was, now, pending;
+
+ was = READ_ONCE(ci->i_qtine_errno) == -CEPH_EQUARANTINED ||
+ test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags);
+ pending = test_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags);
+
+ if ((newcaps & ~CEPH_CAP_PIN) && was && oserrno == 0 &&
+ READ_ONCE(ci->i_qtine_mds) == mds)
+ ceph_quarantine_clear(ci);
+
+ if (oserrno == -CEPH_EQUARANTINED) {
+ ceph_quarantine_set(ci);
+ WRITE_ONCE(ci->i_qtine_mds, mds);
+ }
+
+ if (newcaps || was ||
+ test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags))
+ WRITE_ONCE(ci->i_qtine_errno, oserrno);
+
+ now = READ_ONCE(ci->i_qtine_errno) == -CEPH_EQUARANTINED ||
+ test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags);
+ return was != now ||
+ pending != test_bit(CEPH_I_QUARANTINE_PENDING_BIT,
+ &ci->i_ceph_flags);
+}
+
/*
* Handle a cap GRANT message from the MDS. (Note that a GRANT may
* actually be a revocation if it specifies a smaller cap set.)
@@ -3781,6 +3832,7 @@ static void handle_cap_grant(struct inode *inode,
u64 max_size = le64_to_cpu(grant->max_size);
unsigned char check_caps = 0;
bool was_stale = cap->cap_gen < atomic_read(&session->s_cap_gen);
+ bool quarantine_current = ceph_seq_cmp(seq, cap->seq) >= 0;
bool wake = false;
bool writeback = false;
bool queue_trunc = false;
@@ -4128,6 +4180,15 @@ static void handle_cap_grant(struct inode *inode,
fill_inline = true;
}
+ if (quarantine_current && extra_info->oserrno_valid &&
+ ceph_apply_quarantine(ci, session->s_mds, newcaps,
+ extra_info->oserrno)) {
+ boutc(cl, "quarantine oserrno %d caps %s %llx.%llx\n",
+ extra_info->oserrno, ceph_cap_string(newcaps),
+ ceph_vinop(inode));
+ wake = true;
+ }
+
if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
if (ci->i_auth_cap == cap) {
if (newcaps & ~extra_info->issued)
@@ -4826,6 +4887,20 @@ void ceph_handle_caps(struct ceph_mds_session *session,
goto bad;
}
+ if (msg_version >= 13) {
+ /* v13: subvolume_id. The inode id is learned from replies. */
+ ceph_decode_skip_64(&p, end, bad);
+ }
+
+ if (msg_version >= 14) {
+ u32 raw_errno;
+
+ /* v14: signed oserrno, -CEPH_EQUARANTINED when quarantined */
+ ceph_decode_32_safe(&p, end, raw_errno, bad);
+ extra_info.oserrno = (s32)raw_errno;
+ extra_info.oserrno_valid = true;
+ }
+
/* lookup ino */
inode = ceph_find_inode(mdsc->fsc->sb, vino);
boutc(cl, " caps mds%d op %s ino %llx.%llx inode %p seq %u iseq %u mseq %u\n",
@@ -4981,6 +5056,51 @@ void ceph_handle_caps(struct ceph_mds_session *session,
goto out;
}
+void ceph_handle_quarantine_disable(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ struct ceph_msg *msg)
+{
+ struct super_block *sb = mdsc->fsc->sb;
+ struct ceph_client *cl = mdsc->fsc->client;
+ struct ceph_mds_quarantine_disable *h = msg->front.iov_base;
+ struct ceph_vino vino;
+ struct inode *inode;
+ struct ceph_inode_info *ci;
+
+ if (!ceph_inc_mds_stopping_blocker(mdsc, session))
+ return;
+
+ if (msg->front.iov_len < sizeof(*h)) {
+ pr_err_client(cl, "corrupt quarantine_disable mds%d len %d\n",
+ session->s_mds, (int)msg->front.iov_len);
+ ceph_msg_dump(msg);
+ goto out;
+ }
+
+ vino.ino = le64_to_cpu(h->ino);
+ vino.snap = CEPH_NOSNAP;
+ inode = ceph_find_inode(sb, vino);
+ if (!inode) {
+ doutc(cl, "quarantine disable ino %llx not cached\n", vino.ino);
+ goto out;
+ }
+
+ ci = ceph_inode(inode);
+ spin_lock(&ci->i_ceph_lock);
+ /* Another rank's disable must not erase a newer negative. */
+ if (!test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags) ||
+ READ_ONCE(ci->i_qtine_mds) == session->s_mds) {
+ ceph_quarantine_clear(ci);
+ WRITE_ONCE(ci->i_qtine_errno, 0);
+ }
+ spin_unlock(&ci->i_ceph_lock);
+ wake_up_all(&ci->i_cap_wq);
+ doutc(cl, "quarantine disable ino %llx\n", vino.ino);
+ iput(inode);
+out:
+ ceph_dec_mds_stopping_blocker(mdsc);
+}
+
/*
* Process the expired end of one delayed cap list, whose entries were
* queued @hold jiffies before they expire.
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 384e9edabe2a..d8c8b7ad8930 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -795,7 +795,9 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *res;
struct inode *inode = ceph_get_snapdir(parent);
+ ceph_quarantine_splice_start(parent->i_sb);
res = d_splice_alias(inode, dentry);
+ ceph_quarantine_splice_finish(parent->i_sb);
boutc_formats(cl,
"ENOENT on snapdir %p '%s', linking to snapdir %p %llx.%llx. Spliced dentry %p\n",
"ENOENT on snapdir %p '%pd', linking to snapdir %p %llx.%llx. Spliced dentry %p\n",
@@ -1373,7 +1375,9 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
d_drop(dentry);
} else if (!req->r_reply_info.head->is_dentry) {
ihold(d_inode(old_dentry));
+ ceph_quarantine_splice_start(dir->i_sb);
d_instantiate(dentry, d_inode(old_dentry));
+ ceph_quarantine_splice_finish(dir->i_sb);
}
ceph_mdsc_put_request(req);
ceph_blog_exit(&__ji);
@@ -1701,12 +1705,17 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
}
err = ceph_mdsc_do_request(mdsc, old_dir, req);
if (!err && !req->r_reply_info.head->is_dentry) {
+ struct inode *moved;
+
/*
* Normally d_move() is done by fill_trace (called by
* do_request, above). If there is no trace, we need
* to do it here.
*/
+ moved = d_inode(old_dentry);
+ ceph_quarantine_move_start(moved, old_dir, new_dir);
d_move(old_dentry, new_dentry);
+ ceph_quarantine_move_finish(moved, old_dir, new_dir);
}
ceph_mdsc_put_request(req);
ceph_blog_exit(&__ji);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 856710c63765..9a6eadb94ab4 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -785,7 +785,9 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
if (d_in_lookup(dentry) || d_really_is_negative(dentry)) {
if (!d_unhashed(dentry))
d_drop(dentry);
+ ceph_quarantine_splice_start(dir->i_sb);
dn = d_splice_alias(inode, dentry);
+ ceph_quarantine_splice_finish(dir->i_sb);
WARN_ON_ONCE(dn && dn != dentry);
}
file->f_mode |= FMODE_CREATED;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 94f5215f8eed..78e97cf2f9a4 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -15,6 +15,7 @@
#include <linux/sort.h>
#include <linux/iversion.h>
#include <linux/fscrypt.h>
+#include <linux/cred.h>
#include "super.h"
#include "mds_client.h"
@@ -648,6 +649,11 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ci->i_max_bytes = 0;
ci->i_max_files = 0;
ci->i_subvolume_id = CEPH_SUBVOLUME_ID_NONE;
+ ci->i_qtine_errno = 0;
+ ci->i_qtine_mds = -1;
+ atomic64_set(&ci->i_qtag, 0);
+ atomic64_set(&ci->i_qmds, 0);
+ ci->i_qmds_cred = NULL;
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout));
memset(&ci->i_cached_layout, 0, sizeof(ci->i_cached_layout));
@@ -730,10 +736,461 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
return &ci->netfs.inode;
}
+/*
+ * quarantine_epoch is a seqcount shared by every mark change and every
+ * cross-directory rename. The first writer flips it odd, the last
+ * writer flips it even. Readers must not trust or publish a cache
+ * while it is odd, so a cached false cannot outlive the mutation.
+ *
+ * quarantine_lock makes the writers update and the epoch bump one
+ * step. The epoch is already odd before this returns, and it does not
+ * go even until the last writer has finished the bit change or d_move.
+ * Callers that hold i_ceph_lock take this lock after it. The lock is
+ * not held across the mutation.
+ */
+static void ceph_quarantine_write_begin(struct ceph_mds_client *mdsc)
+{
+ if (!mdsc)
+ return;
+
+ spin_lock(&mdsc->quarantine_lock);
+ if (atomic_inc_return(&mdsc->quarantine_writers) == 1)
+ atomic64_inc_return(&mdsc->quarantine_epoch);
+ spin_unlock(&mdsc->quarantine_lock);
+}
+
+static void ceph_quarantine_write_end(struct ceph_mds_client *mdsc)
+{
+ if (!mdsc)
+ return;
+
+ spin_lock(&mdsc->quarantine_lock);
+ if (atomic_dec_return(&mdsc->quarantine_writers) == 0)
+ atomic64_inc_return(&mdsc->quarantine_epoch);
+ spin_unlock(&mdsc->quarantine_lock);
+}
+
+void ceph_quarantine_set(struct ceph_inode_info *ci)
+{
+ struct ceph_mds_client *mdsc;
+
+ mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
+ /* Every accepted negative invalidates earlier requests and receipts. */
+ ceph_quarantine_write_begin(mdsc);
+ if (mdsc)
+ atomic_inc(&mdsc->quarantine_count);
+ if (test_and_set_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags)) {
+ if (mdsc)
+ atomic_dec(&mdsc->quarantine_count);
+ }
+ clear_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags);
+ ceph_quarantine_write_end(mdsc);
+}
+
+bool ceph_quarantine_clear(struct ceph_inode_info *ci)
+{
+ struct ceph_mds_client *mdsc;
+ bool cleared;
+
+ if (!test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags))
+ return false;
+
+ mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
+ ceph_quarantine_write_begin(mdsc);
+ cleared = test_and_clear_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags);
+ if (cleared) {
+ clear_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags);
+ WRITE_ONCE(ci->i_qtine_errno, 0);
+ WRITE_ONCE(ci->i_qtine_mds, -1);
+ if (mdsc)
+ atomic_dec(&mdsc->quarantine_count);
+ }
+ ceph_quarantine_write_end(mdsc);
+ return cleared;
+}
+
+/* Session loss requires an MDS answer without reopening cached snap caps. */
+bool ceph_quarantine_reset(struct ceph_inode_info *ci)
+{
+ struct ceph_mds_client *mdsc;
+
+ if (!test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags) ||
+ test_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags))
+ return false;
+
+ mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
+ ceph_quarantine_write_begin(mdsc);
+ set_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags);
+ WRITE_ONCE(ci->i_qtine_errno, 0);
+ ceph_quarantine_write_end(mdsc);
+ return true;
+}
+
+bool ceph_inode_quarantine_direct(struct inode *inode)
+{
+ struct ceph_inode_info *ci;
+
+ if (!inode)
+ return false;
+ ci = ceph_inode(inode);
+ return !test_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags) &&
+ (READ_ONCE(ci->i_qtine_errno) == -CEPH_EQUARANTINED ||
+ test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags));
+}
+
+/* Low bit is the answer. The rest is quarantine_epoch, odd values excluded. */
+static u64 ceph_qtag_pack(u64 epoch, bool under)
+{
+ return epoch | (under ? 1ULL : 0);
+}
+
+static void ceph_quarantine_publish(struct ceph_inode_info *ci, bool under,
+ u64 epoch)
+{
+ if (epoch & 1)
+ return;
+
+ /* Pairs with atomic64_read_acquire() of i_qtag. */
+ atomic64_set_release(&ci->i_qtag, ceph_qtag_pack(epoch, under));
+}
+
+static bool ceph_qtag_read(struct ceph_inode_info *ci, u64 epoch, bool *under)
+{
+ u64 packed;
+
+ if (epoch & 1)
+ return false;
+
+ /* Pairs with atomic64_set_release() in ceph_quarantine_publish(). */
+ packed = atomic64_read_acquire(&ci->i_qtag);
+ if ((packed & ~1ULL) != epoch)
+ return false;
+ *under = packed & 1ULL;
+ return true;
+}
+
+/* (epoch | 1) marks an MDS confirmation for this even epoch. */
+static bool ceph_qmds_confirmed(struct ceph_inode_info *ci, u64 epoch)
+{
+ u64 cookie;
+ bool confirmed;
+
+ if (epoch & 1)
+ return false;
+
+ /* Pairs with atomic64_set_release() in remember_clear(). */
+ if ((u64)atomic64_read_acquire(&ci->i_qmds) != (epoch | 1ULL))
+ return false;
+ /* The cookie and its immutable credentials are one locked receipt. */
+ spin_lock(&ci->i_ceph_lock);
+ cookie = atomic64_read(&ci->i_qmds);
+ confirmed = cookie == (epoch | 1ULL) &&
+ ci->i_qmds_cred == current_cred();
+ spin_unlock(&ci->i_ceph_lock);
+ return confirmed;
+}
+
+static void ceph_quarantine_forget_receipt(struct ceph_inode_info *ci)
+{
+ const struct cred *cred;
+
+ spin_lock(&ci->i_ceph_lock);
+ cred = ci->i_qmds_cred;
+ ci->i_qmds_cred = NULL;
+ atomic64_set_release(&ci->i_qmds, 0);
+ spin_unlock(&ci->i_ceph_lock);
+ put_cred(cred);
+}
+
+/* A finished walk reached a mark, an ancestor tag, or the mount root. */
+enum {
+ CEPH_QWALK_CLEAR,
+ CEPH_QWALK_UNDER,
+ CEPH_QWALK_INCOMPLETE,
+};
+
+/*
+ * Parent walk with no inode references. Caller holds rcu_read_lock().
+ * Stops at the mount root, at an MDS mark, or at an ancestor whose
+ * cached answer is for this epoch. No hashed alias, or the depth
+ * limit, is not an answer: the caller must not cache it.
+ */
+static int ceph_quarantine_walk_once(struct inode *inode, u64 epoch,
+ bool use_cache)
+{
+ struct inode *cur = inode;
+ unsigned int depth = 0;
+ bool under = false;
+ bool done = false;
+
+ while (cur && depth++ < 256) {
+ struct ceph_inode_info *ci = ceph_inode(cur);
+ struct dentry *alias;
+ struct dentry *parent;
+ struct inode *next;
+
+ if (test_bit(CEPH_I_QUARANTINE_PENDING_BIT, &ci->i_ceph_flags))
+ break;
+ if (READ_ONCE(ci->i_qtine_errno) == -CEPH_EQUARANTINED ||
+ test_bit(CEPH_I_QUARANTINE_BIT, &ci->i_ceph_flags)) {
+ under = true;
+ done = true;
+ break;
+ }
+
+ if (use_cache && cur != inode &&
+ ceph_qtag_read(ci, epoch, &under)) {
+ done = true;
+ break;
+ }
+
+ alias = d_find_alias_rcu(cur);
+ if (!alias)
+ break;
+
+ parent = READ_ONCE(alias->d_parent);
+ /*
+ * The mount root is its own parent. A disconnected
+ * alias from d_obtain_alias(), or a secondary root from
+ * d_obtain_root(), has the same shape and is not a
+ * finished walk.
+ */
+ if (!parent || parent == alias) {
+ if (parent == alias && S_ISDIR(cur->i_mode) &&
+ alias == READ_ONCE(inode->i_sb->s_root))
+ done = true;
+ break;
+ }
+
+ next = d_inode_rcu(parent);
+ if (!next || next == cur || next->i_sb != inode->i_sb)
+ break;
+ cur = next;
+ }
+ if (!done)
+ return CEPH_QWALK_INCOMPLETE;
+ return under ? CEPH_QWALK_UNDER : CEPH_QWALK_CLEAR;
+}
+
+/*
+ * rename_lock covers d_move(). A chain observed across that move is
+ * not an answer. A few retries, then the caller asks the MDS.
+ */
+static int ceph_quarantine_walk(struct inode *inode, u64 epoch, bool use_cache)
+{
+ unsigned int seq;
+ unsigned int tries = 0;
+ int ret = CEPH_QWALK_INCOMPLETE;
+
+ rcu_read_lock();
+ do {
+ seq = read_seqbegin(&rename_lock);
+ ret = ceph_quarantine_walk_once(inode, epoch, use_cache);
+ if (!read_seqretry(&rename_lock, seq))
+ break;
+ ret = CEPH_QWALK_INCOMPLETE;
+ cpu_relax();
+ } while (++tries < 4);
+ rcu_read_unlock();
+ return ret;
+}
+
+/*
+ * CEPH_Q_UNDER when this inode or an ancestor was marked by an MDS cap
+ * update. Ancestors cover children that have not yet received their
+ * own cap message.
+ *
+ * quarantine_count is zero unless some inode is marked, so the common
+ * path does not walk. While a mark is set, a finished walk is one word
+ * on the inode. A walk stops at an ancestor that already holds that
+ * answer. A short walk is not stored in i_qtag. Callers ask the MDS.
+ * An MDS read receipt in i_qmds overrides inherited marks for the
+ * queried inode until the next epoch bump. It does not override a
+ * definite mark on that inode or authorize cached writes.
+ *
+ * An odd quarantine_epoch is a mark or a d_move() in progress. The
+ * observation is dropped and the check is repeated. Bounded retries
+ * return UNKNOWN, so a preempted writer cannot pin the CPU.
+ */
+static enum ceph_qstate __ceph_inode_quarantine_state(struct inode *inode,
+ bool read_confirmed)
+{
+ struct ceph_mds_client *mdsc;
+ struct ceph_inode_info *ci;
+ unsigned int retries = 0;
+ u64 epoch;
+ bool under, splicing, cached;
+
+ if (!inode)
+ return CEPH_Q_CLEAR;
+
+ mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ if (!mdsc || atomic_read(&mdsc->quarantine_count) == 0)
+ return CEPH_Q_CLEAR;
+
+ ci = ceph_inode(inode);
+ for (;;) {
+ /* Bound retries across both odd writers and changing even epochs. */
+ if (++retries > 32) {
+ cond_resched();
+ return CEPH_Q_UNKNOWN;
+ }
+ /* Pairs with atomic64_inc_return() in write_begin(). */
+ epoch = (u64)atomic64_read_acquire(&mdsc->quarantine_epoch);
+ if (epoch & 1) {
+ cpu_relax();
+ cond_resched();
+ continue;
+ }
+ splicing = atomic_read_acquire(&mdsc->quarantine_splices) != 0;
+
+ if (ceph_inode_quarantine_direct(inode)) {
+ under = true;
+ cached = true;
+ } else if (read_confirmed && !splicing &&
+ ceph_qmds_confirmed(ci, epoch)) {
+ under = false;
+ cached = true;
+ } else {
+ cached = !splicing && ceph_qtag_read(ci, epoch, &under);
+ }
+ if (cached) {
+ /* Orders the marker, receipt, and tag loads before the retry. */
+ smp_rmb();
+ if ((u64)atomic64_read(&mdsc->quarantine_epoch) == epoch &&
+ (splicing || !atomic_read(&mdsc->quarantine_splices)))
+ return under ? CEPH_Q_UNDER : CEPH_Q_CLEAR;
+ cpu_relax();
+ cond_resched();
+ continue;
+ }
+
+ switch (ceph_quarantine_walk(inode, epoch, !splicing)) {
+ case CEPH_QWALK_UNDER:
+ under = true;
+ break;
+ case CEPH_QWALK_CLEAR:
+ under = false;
+ break;
+ default:
+ /* Orders the walk before the retry. */
+ smp_rmb();
+ if ((u64)atomic64_read(&mdsc->quarantine_epoch) == epoch &&
+ (splicing || !atomic_read(&mdsc->quarantine_splices))) {
+ return CEPH_Q_UNKNOWN;
+ }
+ cpu_relax();
+ cond_resched();
+ continue;
+ }
+ /* Orders the walk before the retry, as in read_seqcount_retry(). */
+ smp_rmb();
+ if ((u64)atomic64_read(&mdsc->quarantine_epoch) == epoch &&
+ (splicing || !atomic_read(&mdsc->quarantine_splices))) {
+ if (!splicing)
+ ceph_quarantine_publish(ci, under, epoch);
+ return under ? CEPH_Q_UNDER : CEPH_Q_CLEAR;
+ }
+ cpu_relax();
+ cond_resched();
+ }
+}
+
+enum ceph_qstate ceph_inode_quarantine_state(struct inode *inode)
+{
+ return __ceph_inode_quarantine_state(inode, true);
+}
+
+enum ceph_qstate ceph_inode_quarantine_write_state(struct inode *inode)
+{
+ /* GETATTR can prove read recovery access under a read-only q grant. */
+ return __ceph_inode_quarantine_state(inode, false);
+}
+
+static struct ceph_mds_client *ceph_quarantine_move_mdsc(struct inode *inode,
+ struct inode *old_dir,
+ struct inode *new_dir)
+{
+ if (!inode || old_dir == new_dir)
+ return NULL;
+ return ceph_sb_to_mdsc(inode->i_sb);
+}
+
+/*
+ * Bracket d_move(). The epoch is odd across the parent change, so a
+ * cached false cannot be reused against the new parent. d_move() does
+ * not sleep. Same-directory renames do not take a writer slot.
+ *
+ * Sleeping alias splices use a separate counter below.
+ */
+void ceph_quarantine_move_start(struct inode *inode, struct inode *old_dir,
+ struct inode *new_dir)
+{
+ ceph_quarantine_write_begin(ceph_quarantine_move_mdsc(inode, old_dir,
+ new_dir));
+}
+
+void ceph_quarantine_move_finish(struct inode *inode, struct inode *old_dir,
+ struct inode *new_dir)
+{
+ ceph_quarantine_write_end(ceph_quarantine_move_mdsc(inode, old_dir,
+ new_dir));
+}
+
+/*
+ * d_splice_alias() and d_instantiate() can sleep in the LSM hook before
+ * changing ancestry. Keep the epoch even for that hook, but disallow
+ * all cached answers throughout the splice. A fresh walk also samples
+ * rename_lock, so it cannot accept a chain torn by a move. Bracket
+ * first attachments too: descendants may hold MDS confirmations from
+ * when the directory had no connected alias.
+ *
+ * Fully ordered atomics and quarantine_lock make the counter and epoch
+ * transitions one writer operation. Entry disables cache use before
+ * invalidating tags; exit invalidates tags before enabling cache use.
+ * Adding two preserves the parity of any concurrent mark writer.
+ */
+void ceph_quarantine_splice_start(struct super_block *sb)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+
+ spin_lock(&mdsc->quarantine_lock);
+ atomic_inc_return(&mdsc->quarantine_splices);
+ atomic64_add_return(2, &mdsc->quarantine_epoch);
+ spin_unlock(&mdsc->quarantine_lock);
+}
+
+void ceph_quarantine_splice_finish(struct super_block *sb)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+
+ spin_lock(&mdsc->quarantine_lock);
+ atomic64_add_return(2, &mdsc->quarantine_epoch);
+ atomic_dec_return(&mdsc->quarantine_splices);
+ spin_unlock(&mdsc->quarantine_lock);
+}
+
+static bool ceph_quarantine_reply_can_clear(struct ceph_inode_info *ci,
+ struct ceph_mds_session *session)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->netfs.inode.i_sb);
+ struct ceph_mds_request *req;
+ u64 epoch;
+
+ if (READ_ONCE(ci->i_qtine_mds) == session->s_mds)
+ return true;
+ /* Different ranks have independent cap sequences. */
+ req = ceph_current_mds_request(mdsc->fsc);
+ epoch = (u64)atomic64_read_acquire(&mdsc->quarantine_epoch);
+ return req && !(epoch & 1) && req->r_quarantine_epoch == epoch &&
+ !atomic_read(&mdsc->quarantine_splices);
+}
+
void ceph_free_inode(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ put_cred(ci->i_qmds_cred);
kfree(ci->i_symlink);
#ifdef CONFIG_FS_ENCRYPTION
kfree(ci->fscrypt_auth);
@@ -759,6 +1216,8 @@ void ceph_evict_inode(struct inode *inode)
percpu_counter_dec(&mdsc->metric.total_inodes);
ci->i_subvolume_id = CEPH_SUBVOLUME_ID_NONE;
+ ceph_quarantine_forget_receipt(ci);
+ ceph_quarantine_clear(ci);
netfs_wait_for_outstanding_io(inode);
truncate_inode_pages_final(&inode->i_data);
@@ -1407,7 +1866,7 @@ int ceph_fill_inode(struct inode *inode, struct folio *locked_folio,
/* were we issued a capability? */
if (info_caps) {
if (!ceph_in_snap(inode)) {
- ceph_add_cap(inode, session,
+ bool cap_current = ceph_add_cap(inode, session,
le64_to_cpu(info->cap.cap_id),
info_caps,
le32_to_cpu(info->cap.wanted),
@@ -1416,6 +1875,14 @@ int ceph_fill_inode(struct inode *inode, struct folio *locked_folio,
le64_to_cpu(info->cap.realm),
info->cap.flags, &new_cap);
+ /*
+ * Caps above PIN mean quarantine has been lifted,
+ * including when the disable message was lost.
+ */
+ if (cap_current && (info_caps & ~CEPH_CAP_PIN) &&
+ ceph_quarantine_reply_can_clear(ci, session))
+ ceph_quarantine_clear(ci);
+
/* set dir completion flag? */
if (S_ISDIR(inode->i_mode) &&
ci->i_files == 0 && ci->i_subdirs == 0 &&
@@ -1618,6 +2085,7 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
realdn = d_find_any_alias(in);
if (realdn) {
struct ceph_dentry_info *di = ceph_dentry(realdn);
+
spin_lock(&realdn->d_lock);
realdn->d_op->d_prune(realdn);
@@ -1634,7 +2102,9 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
/* dn must be unhashed */
if (!d_unhashed(dn))
d_drop(dn);
+ ceph_quarantine_splice_start(dn->d_sb);
realdn = d_splice_alias(in, dn);
+ ceph_quarantine_splice_finish(dn->d_sb);
if (IS_ERR(realdn)) {
pr_err_client(cl, "error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
@@ -1859,6 +2329,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
/* rename? */
if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) {
struct inode *olddir = req->r_old_dentry_dir;
+ struct inode *moved;
BUG_ON(!olddir);
boutc(cl, " src %p '%s' dst %p '%s'\n",
@@ -1869,7 +2340,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
ceph_dir_clear_ordered(dir);
ceph_dir_clear_ordered(olddir);
+ moved = d_inode(req->r_old_dentry);
+ ceph_quarantine_move_start(moved, olddir, dir);
d_move(req->r_old_dentry, dn);
+ ceph_quarantine_move_finish(moved, olddir, dir);
boutc(cl, " src %p '%s' dst %p '%s'\n",
req->r_old_dentry, req->r_old_dentry->d_name.name, dn, dn->d_name.name);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d4ef8a355a48..bb7cf9384fd6 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2041,10 +2041,12 @@ static int remove_session_caps_cb(struct inode *inode, int mds, void *arg)
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_client *cl = ceph_inode_to_client(inode);
bool invalidate = false;
+ bool reset;
struct ceph_cap *cap;
int iputs = 0;
spin_lock(&ci->i_ceph_lock);
+ reset = ceph_quarantine_reset(ci);
cap = __get_cap_for_mds(ci, mds);
if (cap) {
boutc(cl, " removing cap %p, ci is %p, inode is %p\n",
@@ -2054,7 +2056,7 @@ static int remove_session_caps_cb(struct inode *inode, int mds, void *arg)
}
spin_unlock(&ci->i_ceph_lock);
- if (cap)
+ if (cap || reset)
wake_up_all(&ci->i_cap_wq);
if (invalidate)
ceph_queue_invalidate(inode);
@@ -2860,6 +2862,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
mutex_init(&req->r_fill_mutex);
req->r_mdsc = mdsc;
+ req->r_quarantine_epoch = atomic64_read_acquire(&mdsc->quarantine_epoch);
req->r_started = jiffies;
req->r_start_latency = ktime_get();
req->r_resend_mds = -1;
@@ -5009,6 +5012,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
struct ceph_path_info path_info = {0};
int err;
u64 snap_follows;
+ bool reset = false;
dentry = d_find_primary(inode);
if (dentry) {
@@ -5023,9 +5027,16 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
}
spin_lock(&ci->i_ceph_lock);
+ /*
+ * Require a fresh MDS answer after reconnect. A PIN import may
+ * carry no quarantine errno, so it must not reopen cached snap caps.
+ */
+ reset = ceph_quarantine_reset(ci);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
spin_unlock(&ci->i_ceph_lock);
+ if (reset)
+ wake_up_all(&ci->i_cap_wq);
err = 0;
goto out_err;
}
@@ -5088,6 +5099,8 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
snap_follows = capsnap->follows;
}
spin_unlock(&ci->i_ceph_lock);
+ if (reset)
+ wake_up_all(&ci->i_cap_wq);
if (recon_state->msg_version >= 2) {
int num_fcntl_locks, num_flock_locks;
@@ -6468,6 +6481,11 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
init_completion(&mdsc->safe_umount_waiters);
spin_lock_init(&mdsc->stopping_lock);
atomic_set(&mdsc->stopping_blockers, 0);
+ atomic_set(&mdsc->quarantine_count, 0);
+ atomic_set(&mdsc->quarantine_writers, 0);
+ atomic_set(&mdsc->quarantine_splices, 0);
+ atomic64_set(&mdsc->quarantine_epoch, 0);
+ spin_lock_init(&mdsc->quarantine_lock);
init_completion(&mdsc->stopping_waiter);
atomic64_set(&mdsc->dirty_folios, 0);
init_waitqueue_head(&mdsc->flush_end_wq);
@@ -7368,6 +7386,9 @@ static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
case CEPH_MSG_CLIENT_QUOTA:
ceph_handle_quota(mdsc, s, msg);
break;
+ case CEPH_MSG_CLIENT_QUARANTINE_DISABLE:
+ ceph_handle_quarantine_disable(mdsc, s, msg);
+ break;
default:
pr_err_client(cl, "received unknown message type %d %s\n",
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 863cdb8d588a..816f5f2d32cc 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -375,6 +375,7 @@ struct ceph_mds_request {
int r_fmode; /* file mode, if expecting cap */
int r_request_release_offset;
const struct cred *r_cred;
+ u64 r_quarantine_epoch; /* generation when the request was created */
struct mnt_idmap *r_mnt_idmap;
struct timespec64 r_stamp;
@@ -506,6 +507,21 @@ struct ceph_mds_client {
spinlock_t stopping_lock; /* protect snap_empty */
int stopping; /* the stage of shutting down */
atomic_t stopping_blockers;
+ /*
+ * Inodes with CEPH_I_QUARANTINE set. Hot paths skip the
+ * ancestor walk while this is zero.
+ * quarantine_epoch is a seqcount: even while idle, odd while
+ * quarantine_writers is non-zero. Writers are mark changes and
+ * cross-directory renames. quarantine_lock covers the writers
+ * update and the epoch bump together. Sleeping alias splices use
+ * quarantine_splices instead: readers walk without cached answers
+ * while it is non-zero. Each splice edge also bumps the epoch.
+ */
+ atomic_t quarantine_count;
+ atomic_t quarantine_writers;
+ atomic_t quarantine_splices;
+ atomic64_t quarantine_epoch;
+ spinlock_t quarantine_lock; /* writers update + epoch bump */
struct completion stopping_waiter;
atomic64_t dirty_folios;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 40be4b16e486..ad9460d9673c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1139,7 +1139,9 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
struct inode *inode = req->r_target_inode;
req->r_target_inode = NULL;
doutc(cl, "success\n");
+ ceph_quarantine_splice_start(fsc->sb);
root = d_make_root(inode);
+ ceph_quarantine_splice_finish(fsc->sb);
if (!root) {
root = ERR_PTR(-ENOMEM);
goto out;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 458fd63dd79f..0264bd9d705f 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -444,6 +444,33 @@ struct ceph_inode_info {
#define CEPH_SUBVOLUME_ID_NONE 0
u64 i_subvolume_id;
+ /*
+ * Cap oserrno from the MDS. -CEPH_EQUARANTINED means this inode
+ * was revoked because its subvolume is quarantined. Paired with
+ * CEPH_I_QUARANTINE, which stays set when a later PIN-only update
+ * clears the errno.
+ */
+ int i_qtine_errno;
+ int i_qtine_mds; /* negative cap origin, retained across pending reset */
+ /*
+ * Cached ancestry answer: epoch | under, where epoch is even.
+ * Atomic64 accesses also prevent tearing on 32-bit clients. An odd
+ * quarantine_epoch means a mark or a rename is in progress.
+ * Do not trust this word while the epoch is odd or an alias
+ * splice is in progress.
+ * Zero means "not under" at epoch 0.
+ *
+ * i_qmds stores (epoch | 1) after the MDS confirms an inode
+ * can be read despite uncertain or marked ancestry. This read
+ * permission is scoped to this inode, never its descendants or
+ * cached writes. The next epoch bump drops the confirmation.
+ * Zero means there is no confirmation.
+ */
+ atomic64_t i_qtag;
+ atomic64_t i_qmds;
+ /* Immutable request credentials scope the MDS read receipt. */
+ const struct cred *i_qmds_cred; /* protected with i_qmds by i_ceph_lock */
+
s32 i_dir_pin;
int i_fragtree_nsplits;
@@ -773,6 +800,8 @@ static inline u64 ceph_get_truncate_pagecache_size(const struct ceph_inode_info
* the deferred work completes
*/
#define CEPH_I_EVICT_ON_FINAL_IPUT_BIT (16) /* evict at the final iput() */
+#define CEPH_I_QUARANTINE_BIT (17) /* subvolume quarantine opt set */
+#define CEPH_I_QUARANTINE_PENDING_BIT (18) /* quarantine needs MDS confirmation */
#define CEPH_I_DIR_ORDERED (1 << CEPH_I_DIR_ORDERED_BIT)
#define CEPH_I_FLUSH (1 << CEPH_I_FLUSH_BIT)
@@ -1259,6 +1288,38 @@ extern int ceph_getattr(struct mnt_idmap *idmap,
u32 request_mask, unsigned int flags);
void ceph_inode_shutdown(struct inode *inode);
+/*
+ * CEPH_Q_CLEAR: cached ancestry is clear, or the MDS confirmed read
+ * access to this exact inode for the current epoch. Writers must use
+ * ceph_inode_quarantine_write_state(), which ignores read receipts.
+ * CEPH_Q_UNDER: this inode or a cached ancestor is marked.
+ * CEPH_Q_UNKNOWN: the parent chain is not fully cached. Ask the MDS.
+ * Do not treat that as quarantined and do not use cached caps.
+ */
+enum ceph_qstate {
+ CEPH_Q_CLEAR = 0,
+ CEPH_Q_UNDER,
+ CEPH_Q_UNKNOWN,
+};
+
+enum ceph_qstate ceph_inode_quarantine_state(struct inode *inode);
+enum ceph_qstate ceph_inode_quarantine_write_state(struct inode *inode);
+bool ceph_inode_quarantine_direct(struct inode *inode);
+int ceph_quarantine_revalidate(struct inode *inode);
+int ceph_snapshot_read_auth(struct inode *inode);
+void ceph_quarantine_set(struct ceph_inode_info *ci);
+bool ceph_quarantine_clear(struct ceph_inode_info *ci);
+bool ceph_quarantine_reset(struct ceph_inode_info *ci);
+void ceph_quarantine_move_start(struct inode *inode, struct inode *old_dir,
+ struct inode *new_dir);
+void ceph_quarantine_move_finish(struct inode *inode, struct inode *old_dir,
+ struct inode *new_dir);
+void ceph_quarantine_splice_start(struct super_block *sb);
+void ceph_quarantine_splice_finish(struct super_block *sb);
+void ceph_handle_quarantine_disable(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ struct ceph_msg *msg);
+
static inline bool ceph_inode_is_shutdown(const struct inode *inode)
{
unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags);
@@ -1368,11 +1429,11 @@ extern void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_msg *msg);
extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
-extern void ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- unsigned issued, unsigned wanted,
- unsigned cap, unsigned seq, u64 realmino, int flags,
- struct ceph_cap **new_cap);
+bool ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ unsigned int issued, unsigned int wanted,
+ unsigned int seq, unsigned int mseq, u64 realmino, int flags,
+ struct ceph_cap **new_cap);
/**
* Determine whether __ceph_remove_cap() has been called on this #cap
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH v4 5/5] ceph: fail quarantined subvolume access with EACCES
2026-10-20 12:52 [PATCH v4 0/5] ceph: support subvolume quarantine Alex Markuze
` (3 preceding siblings ...)
2026-10-20 12:52 ` [PATCH v4 4/5] ceph: record subvolume quarantine from MDS cap updates Alex Markuze
@ 2026-10-20 12:52 ` Alex Markuze
2026-10-20 16:05 ` [PATCH v4 0/5] ceph: support subvolume quarantine Eric Biggers
5 siblings, 0 replies; 8+ messages in thread
From: Alex Markuze @ 2026-10-20 12:52 UTC (permalink / raw)
To: ceph-devel
Cc: Alex Markuze, idryomov, xiubo.li, slava, viro, brauner, jack,
linux-fsdevel, linux-fscrypt, ebiggers, tytso, jaegeuk,
linux-kernel
Advertise CEPHFS_FEATURE_QUARANTINE after gating cached data and
metadata access. The MDS can then return EACCES for quarantined
requests instead of parking them until quarantine is lifted.
Reject cached access to a directly marked inode. Ask the MDS when
ancestry is incomplete or an inherited mark may permit recovery
with q/Q auth caps. Scope read confirmations to the exact inode,
credentials and epoch; authorize writes separately with a mode-
specific OPEN. Keep nonblocking acquisition free of RPCs and drop
locked folios before blocking revalidation.
Wait interruptibly for namespace writers and retry invalidated MDS
answers instead of leaking EAGAIN from blocking reads and readdir.
Track the tasks performing sleeping splices and reject their recursive
LSM hooks with EBUSY rather than waiting on their own operation. Keep
the fill-trace recursion guard, including cross-mount calls. Wake
waiters when mark writers and splices finish.
Keep snapshot access cached only when the connected head inode is the
subvolume root identified by the target's nonzero MDS subvolume ID,
holds a valid AUTH_SHARED cap from a quarantine-aware authoritative
MDS, and there are no local quarantine marks. An ancestor snapshot
P/.snap/S/V/file must not use P's cap to authorize access inside V:
quarantining V leaves P's cap valid and may supply no local marks.
Copy the parent's subvolume ID into synthetic snapdir inodes too.
Unknown IDs, other head ancestors, expired root caps and active
quarantine still require an MDS answer. Keep 32-bit clients on that
path because membership IDs use plain 64-bit READ/WRITE_ONCE accesses.
Preserve connected paths and exact inode/snapshot LOOKUPINO fallback,
including reply-identity and required-payload checks.
Gate VFS ACL cache suppression and namespace mutation bookkeeping on
negotiated quarantine support. Invalidate older cached ACLs when the
first supporting session opens and pair mutation tokens across that
transition. Keep support enabled across subsequent reconnects.
Select fscrypt's symlink cache opt-out alongside the get_link checks.
This closes readlinkat() with an empty path on a held O_PATH symlink
fd. Pathname lookup already rejects quarantined paths; an existing
O_PATH fd bypasses that lookup and needs the get_link check itself.
Encrypted symlink readlink, traversal and lstat now allocate and
decrypt a temporary target on each access.
Gate cached stat, xattr, directory, ioctl and mmap access. Keep ACL
inheritance in the encoded xattr blob and fail ENOMEM if it cannot
be installed. Leave metadata submission and lock release on their
normal paths, and route uncertain async mutations to the MDS. Fresh
metadata replies recover after a lost disable notification. Existing
snapshot PTEs still require server notifications for revocation.
Signed-off-by: Alex Markuze <amarkuze@redhat.com>
---
fs/ceph/acl.c | 33 ++-
fs/ceph/addr.c | 72 ++++--
fs/ceph/caps.c | 195 +++++++++++++++-
fs/ceph/crypto.c | 1 +
fs/ceph/debugfs.c | 1 +
fs/ceph/dir.c | 57 +++--
fs/ceph/file.c | 114 +++++++---
fs/ceph/inode.c | 521 ++++++++++++++++++++++++++++++++++++++-----
fs/ceph/ioctl.c | 13 ++
fs/ceph/mds_client.c | 5 +
fs/ceph/mds_client.h | 14 +-
fs/ceph/super.c | 6 +-
fs/ceph/super.h | 40 +++-
fs/ceph/xattr.c | 54 ++++-
14 files changed, 980 insertions(+), 146 deletions(-)
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index dbc64ab60308..14feb719a1cf 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -18,18 +18,45 @@
#include "mds_client.h"
static inline void ceph_set_cached_acl(struct inode *inode,
- int type, struct posix_acl *acl)
+ int type, struct posix_acl *acl)
{
struct ceph_inode_info *ci = ceph_inode(inode);
spin_lock(&ci->i_ceph_lock);
- if (__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
+ if (!READ_ONCE(ceph_sb_to_mdsc(inode->i_sb)->quarantine_supported) &&
+ __ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 0))
set_cached_acl(inode, type, acl);
else
forget_cached_acl(inode, type);
spin_unlock(&ci->i_ceph_lock);
}
+void ceph_quarantine_uncache_inode_acls(struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct posix_acl *acl, *default_acl;
+
+ spin_lock(&ci->i_ceph_lock);
+ acl = xchg(&inode->i_acl, ACL_DONT_CACHE);
+ default_acl = xchg(&inode->i_default_acl, ACL_DONT_CACHE);
+ spin_unlock(&ci->i_ceph_lock);
+ if (!is_uncached_acl(acl))
+ posix_acl_release(acl);
+ if (!is_uncached_acl(default_acl))
+ posix_acl_release(default_acl);
+}
+
+void ceph_quarantine_disable_acl_cache(struct super_block *sb)
+{
+ struct inode *inode;
+
+ /* Cover inodes cached before the first supporting session opened. */
+ spin_lock(&sb->s_inode_list_lock);
+ list_for_each_entry(inode, &sb->s_inodes, i_sb_list)
+ ceph_quarantine_uncache_inode_acls(inode);
+ spin_unlock(&sb->s_inode_list_lock);
+}
+
struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
{
struct ceph_client *cl = ceph_inode_to_client(inode);
@@ -73,6 +100,8 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type, bool rcu)
acl = posix_acl_from_xattr(&init_user_ns, value, size);
} else if (size == -ENODATA || size == 0) {
acl = NULL;
+ } else if (size == -EACCES) {
+ acl = ERR_PTR(-EACCES);
} else {
pr_err_ratelimited_client(cl, "%llx.%llx failed, err=%d\n",
ceph_vinop(inode), size);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index dd2bd8ed2424..79e396752601 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -540,6 +540,10 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
want |= CEPH_CAP_FILE_LAZYIO;
}
+ /*
+ * NETFS_READPAGE is synchronous. ceph_read_folio() holds caps for
+ * its duration, including the authorization for a snapshot read.
+ */
if (rreq->origin == NETFS_READAHEAD) {
/*
* readahead callers do not necessarily hold Fcb caps
@@ -563,21 +567,6 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
ret = -EACCES;
goto out;
}
- } else {
- /*
- * Make sure we have caps, just in case read_folio was
- * called directly (e.g. by erofs) which may have
- * bypassed the usual Ceph cap checks. This branch
- * uses __ceph_get_caps() which blocks until the
- * required cap has been granted.
- */
- ret = __ceph_get_caps(inode, fi, CEPH_CAP_FILE_RD, want, -1,
- &got);
- if (ret < 0) {
- boutc(cl, "%llx.%llx, error getting cap\n",
- ceph_vinop(inode));
- goto out;
- }
}
priv->caps = got;
@@ -2069,8 +2058,44 @@ static int ceph_write_end(const struct kiocb *iocb,
return copied;
}
+/* Direct read_folio callers may not have entered through read_iter or fault. */
+static int ceph_read_folio(struct file *file, struct folio *folio)
+{
+ struct address_space *mapping = folio->mapping;
+ struct inode *inode = mapping->host;
+ struct ceph_file_info *fi = file ? file->private_data : NULL;
+ int want = CEPH_CAP_FILE_CACHE;
+ int got, ret;
+
+ if (fi && ceph_find_rw_context(fi))
+ return netfs_read_folio(file, folio);
+
+ if (fi && (fi->fmode & CEPH_FILE_MODE_LAZY))
+ want |= CEPH_CAP_FILE_LAZYIO;
+
+ /* A blocking getattr can fill inline data into this folio. */
+ folio_unlock(folio);
+ got = 0;
+ ret = __ceph_get_caps(inode, fi, CEPH_CAP_FILE_RD, want, -1, &got);
+ if (ret < 0)
+ return ret;
+
+ folio_lock(folio);
+ if (folio->mapping != mapping) {
+ folio_unlock(folio);
+ ret = AOP_TRUNCATED_PAGE;
+ } else if (folio_test_uptodate(folio)) {
+ folio_unlock(folio);
+ ret = 0;
+ } else {
+ ret = netfs_read_folio(file, folio);
+ }
+ ceph_put_cap_refs(ceph_inode(inode), got);
+ return ret;
+}
+
const struct address_space_operations ceph_aops = {
- .read_folio = netfs_read_folio,
+ .read_folio = ceph_read_folio,
.readahead = netfs_readahead,
.writepages = ceph_writepages_start,
.write_begin = ceph_write_begin,
@@ -2649,9 +2674,24 @@ static const struct vm_operations_struct ceph_vmops = {
int ceph_mmap_prepare(struct vm_area_desc *desc)
{
struct address_space *mapping = desc->file->f_mapping;
+ struct inode *inode = file_inode(desc->file);
+ int err, got = 0;
if (!mapping->a_ops->read_folio)
return -ENOEXEC;
+ err = ceph_quarantine_revalidate(inode);
+ if (err)
+ return err;
+ if (vma_desc_test_all(desc, VMA_SHARED_BIT, VMA_WRITE_BIT) &&
+ ceph_inode_quarantine_write_state(inode) != CEPH_Q_CLEAR) {
+ /* A read receipt cannot admit a writable shared mapping. */
+ err = ceph_get_caps(desc->file, CEPH_CAP_FILE_WR, 0, -1, &got);
+ if (err)
+ return err;
+ ceph_put_cap_refs(ceph_inode(inode), got);
+ }
+ if (ceph_inode_quarantine_direct(inode))
+ return -EACCES;
desc->vm_ops = &ceph_vmops;
return 0;
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 94f015112942..5af1c0a58774 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3010,10 +3010,39 @@ enum {
/* first 8 bits are reserved for CEPH_FILE_MODE_FOO */
NON_BLOCKING = (1 << 8),
CHECK_FILELOCK = (1 << 9),
+ MDS_AUTHORIZED = (1 << 10),
};
+/* Immutable snapshot caps need a live, quarantine-aware head cap to watch. */
+bool ceph_quarantine_head_cap_valid(struct inode *inode)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_cap *cap;
+ bool valid;
+
+ spin_lock(&ci->i_ceph_lock);
+ cap = ci->i_auth_cap;
+ valid = cap && __cap_is_valid(ci, cap) &&
+ test_bit(CEPHFS_FEATURE_QUARANTINE, &cap->session->s_features) &&
+ (cap->issued & CEPH_CAP_AUTH_SHARED);
+ spin_unlock(&ci->i_ceph_lock);
+ return valid;
+}
+
+static bool ceph_cap_auth_valid(struct ceph_mds_client *mdsc, u64 epoch)
+{
+ if (!atomic_read(&mdsc->quarantine_count))
+ return true;
+
+ /* Order authorization and cap observations before the generation check. */
+ smp_rmb();
+ return !(epoch & 1) &&
+ (u64)atomic64_read_acquire(&mdsc->quarantine_epoch) == epoch &&
+ !atomic_read(&mdsc->quarantine_splices);
+}
+
static int try_get_cap_refs(struct inode *inode, int need, int want,
- loff_t endoff, int flags, int *got)
+ loff_t endoff, int flags, u64 qepoch, int *got)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc;
@@ -3029,6 +3058,15 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
again:
spin_lock(&ci->i_ceph_lock);
+ if (ceph_inode_quarantine_direct(inode)) {
+ ret = -EACCES;
+ goto out_unlock;
+ }
+ if ((flags & MDS_AUTHORIZED) && !ceph_cap_auth_valid(mdsc, qepoch)) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+
if ((flags & CHECK_FILELOCK) &&
test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) {
doutc(cl, "%p %llx.%llx error filelock\n", inode,
@@ -3050,6 +3088,15 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
}
__ceph_do_pending_vmtruncate(inode);
spin_lock(&ci->i_ceph_lock);
+ if (ceph_inode_quarantine_direct(inode)) {
+ ret = -EACCES;
+ goto out_unlock;
+ }
+ if ((flags & MDS_AUTHORIZED) &&
+ !ceph_cap_auth_valid(mdsc, qepoch)) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
}
have = __ceph_caps_issued(ci, &implemented);
@@ -3198,6 +3245,31 @@ static int try_get_cap_refs(struct inode *inode, int need, int want,
if (snap_rwsem_locked)
up_read(&mdsc->snap_rwsem);
+ /* A truncate or cap wait may have outlived the quarantine check. */
+ if (ret == 1) {
+ enum ceph_qstate qstate = CEPH_Q_CLEAR;
+
+ if (!(flags & MDS_AUTHORIZED) &&
+ ceph_snapshot_needs_revalidate(inode))
+ qstate = CEPH_Q_UNKNOWN;
+ else if (!(flags & MDS_AUTHORIZED))
+ qstate = need & CEPH_CAP_FILE_WR ?
+ ceph_inode_quarantine_write_state(inode) :
+ ceph_inode_quarantine_state(inode);
+ else if (!ceph_cap_auth_valid(mdsc, qepoch))
+ qstate = CEPH_Q_UNKNOWN;
+ /* An MDS answer cannot outlive a new negative on this inode. */
+ if (ceph_inode_quarantine_direct(inode))
+ qstate = CEPH_Q_UNDER;
+
+ if (qstate != CEPH_Q_CLEAR) {
+ ceph_put_cap_refs(ci, *got);
+ *got = 0;
+ ret = qstate == CEPH_Q_UNDER &&
+ ceph_inode_quarantine_direct(inode) ? -EACCES : -EAGAIN;
+ }
+ }
+
if (!ret)
ceph_update_cap_mis(&mdsc->metric);
else if (ret == 1)
@@ -3266,17 +3338,34 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
BUG_ON(want & ~(CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO |
CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
CEPH_CAP_ANY_DIR_OPS));
+ /* Immutable snapshot caps have no MDS revoke notifications. */
+ if (ceph_snapshot_needs_revalidate(inode))
+ return 0;
+
if (need) {
ret = ceph_pool_perm_check(inode, need);
if (ret < 0)
return ret;
}
+ switch (ceph_inode_quarantine_state(inode)) {
+ case CEPH_Q_UNDER:
+ return ceph_inode_quarantine_direct(inode) ? -EACCES : 0;
+ case CEPH_Q_UNKNOWN:
+ /*
+ * Callers may hold locked folios or another inode's caps.
+ * Leave blocking revalidation to ceph_get_caps().
+ */
+ return 0;
+ default:
+ break;
+ }
+
flags = get_used_fmode(need | want);
if (nonblock)
flags |= NON_BLOCKING;
- ret = try_get_cap_refs(inode, need, want, 0, flags, got);
+ ret = try_get_cap_refs(inode, need, want, 0, flags, 0, got);
/* three special error codes */
if (ret == -EAGAIN || ret == -EFBIG || ret == -EUCLEAN)
ret = 0;
@@ -3293,6 +3382,9 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+ struct ceph_mds_client *mdsc = fsc->mdsc;
+ bool snapshot = ceph_in_snap(inode) && ceph_snap(inode) != CEPH_SNAPDIR;
+ u64 qepoch = 0;
int ret, _got, flags;
ret = ceph_pool_perm_check(inode, need);
@@ -3307,15 +3399,71 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
while (true) {
flags &= CEPH_FILE_MODE_MASK;
+ if (snapshot && ceph_snapshot_needs_revalidate(inode)) {
+ /*
+ * i_snap_caps cannot be revoked, and an idle snapshot
+ * inode may receive no quarantine notification at all.
+ * An MDS answer authorizes only this acquisition.
+ */
+ qepoch = atomic64_read_acquire(&mdsc->quarantine_epoch);
+ if (!ceph_cap_auth_valid(mdsc, qepoch)) {
+ ret = ceph_quarantine_wait(inode);
+ if (ret)
+ return ret;
+ continue;
+ }
+ ret = ceph_snapshot_read_auth(inode);
+ if (ret)
+ return ret;
+ flags |= MDS_AUTHORIZED;
+ } else {
+ enum ceph_qstate qstate = need & CEPH_CAP_FILE_WR ?
+ ceph_inode_quarantine_write_state(inode) :
+ ceph_inode_quarantine_state(inode);
+
+ switch (qstate) {
+ case CEPH_Q_UNDER:
+ if (ceph_inode_quarantine_direct(inode))
+ return -EACCES;
+ fallthrough;
+ case CEPH_Q_UNKNOWN:
+ if (!(need & CEPH_CAP_FILE_WR)) {
+ ret = ceph_quarantine_revalidate(inode);
+ if (ret)
+ return ret;
+ continue;
+ }
+ /* A GETATTR receipt cannot authorize writes. */
+ qepoch = atomic64_read_acquire(&mdsc->quarantine_epoch);
+ if (!ceph_cap_auth_valid(mdsc, qepoch)) {
+ ret = ceph_quarantine_wait(inode);
+ if (ret)
+ return ret;
+ continue;
+ }
+ ret = ceph_renew_caps(inode, flags, true);
+ if (ret)
+ return ret;
+ flags |= MDS_AUTHORIZED;
+ break;
+ default:
+ break;
+ }
+ }
+
if (vfs_inode_has_locks(inode))
flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
- flags, &_got);
- WARN_ON_ONCE(ret == -EAGAIN);
+ flags, qepoch, &_got);
+ if (ret == -EAGAIN) {
+ ret = ceph_quarantine_wait(inode);
+ if (ret)
+ return ret;
+ continue;
+ }
if (!ret) {
#ifdef CONFIG_DEBUG_FS
- struct ceph_mds_client *mdsc = fsc->mdsc;
struct cap_wait cw;
#endif
DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -3336,8 +3484,33 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
add_wait_queue(&ci->i_cap_wq, &wait);
flags |= NON_BLOCKING;
- while (!(ret = try_get_cap_refs(inode, need, want,
- endoff, flags, &_got))) {
+ while (true) {
+ enum ceph_qstate qstate = CEPH_Q_CLEAR;
+
+ if (!(flags & MDS_AUTHORIZED))
+ qstate = need & CEPH_CAP_FILE_WR ?
+ ceph_inode_quarantine_write_state(inode) :
+ ceph_inode_quarantine_state(inode);
+ else if (!ceph_cap_auth_valid(mdsc, qepoch))
+ qstate = CEPH_Q_UNKNOWN;
+ if (ceph_inode_quarantine_direct(inode))
+ qstate = CEPH_Q_UNDER;
+ switch (qstate) {
+ case CEPH_Q_UNDER:
+ ret = ceph_inode_quarantine_direct(inode) ?
+ -EACCES : -EAGAIN;
+ break;
+ case CEPH_Q_UNKNOWN:
+ /* Revalidate outside the cap wait. */
+ ret = -EAGAIN;
+ break;
+ default:
+ ret = try_get_cap_refs(inode, need, want,
+ endoff, flags, qepoch, &_got);
+ break;
+ }
+ if (ret)
+ break;
if (signal_pending(current)) {
ret = -ERESTARTSYS;
break;
@@ -3366,8 +3539,12 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
spin_unlock(&mdsc->caps_list_lock);
#endif
- if (ret == -EAGAIN)
+ if (ret == -EAGAIN) {
+ ret = ceph_quarantine_wait(inode);
+ if (ret)
+ return ret;
continue;
+ }
}
if (fi && (fi->fmode & CEPH_FILE_MODE_WR) &&
@@ -3390,7 +3567,7 @@ int __ceph_get_caps(struct inode *inode, struct ceph_file_info *fi, int need,
if (ret == -EUCLEAN) {
/* session was killed or a waited cap
* request needs a retry */
- ret = ceph_renew_caps(inode, flags);
+ ret = ceph_renew_caps(inode, flags, false);
if (ret == 0)
continue;
}
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 9e0ebb071840..de786a0e626c 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -92,6 +92,7 @@ static struct fscrypt_operations ceph_fscrypt_ops = {
.inode_info_offs = (int)offsetof(struct ceph_inode_info, i_crypt_info) -
(int)offsetof(struct ceph_inode_info, netfs.inode),
.needs_bounce_pages = 1,
+ .no_symlink_cache = 1,
.get_context = ceph_crypt_get_context,
.set_context = ceph_crypt_set_context,
.get_dummy_policy = ceph_get_dummy_policy,
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6a9a5551d9d7..ef10e948a2d3 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -53,6 +53,7 @@ static const struct ceph_session_feature_desc ceph_session_feature_table[] = {
{ CEPHFS_FEATURE_HAS_OWNER_UIDGID, "HAS_OWNER_UIDGID" },
{ CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, "MDS_AUTH_CAPS_CHECK" },
{ CEPHFS_FEATURE_SUBVOLUME_METRICS, "SUBVOLUME_METRICS" },
+ { CEPHFS_FEATURE_QUARANTINE, "QUARANTINE" },
};
static int mdsmap_show(struct seq_file *s, void *p)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d8c8b7ad8930..d0687e731dea 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -349,6 +349,13 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
ceph_blog_enter(fsc, &__ji);
+ /* Validate before returning cached entries, dots, or end-of-directory. */
+ err = ceph_quarantine_revalidate(inode);
+ if (err) {
+ ceph_blog_exit(&__ji);
+ return err;
+ }
+
boutc(cl, "%p %llx.%llx file %p pos %llx\n", inode,
ceph_vinop(inode), file, ctx->pos);
if (dfi->file_info.flags & CEPH_F_ATEND) {
@@ -785,6 +792,7 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *dentry)
{
+ struct ceph_quarantine_splice qsplice;
struct ceph_fs_client *fsc = ceph_sb_to_fs_client(dentry->d_sb);
struct inode *parent = d_inode(dentry->d_parent); /* we hold i_rwsem */
struct ceph_client *cl = ceph_inode_to_client(parent);
@@ -795,9 +803,9 @@ struct dentry *ceph_handle_snapdir(struct ceph_mds_request *req,
struct dentry *res;
struct inode *inode = ceph_get_snapdir(parent);
- ceph_quarantine_splice_start(parent->i_sb);
+ ceph_quarantine_splice_start(parent->i_sb, &qsplice);
res = d_splice_alias(inode, dentry);
- ceph_quarantine_splice_finish(parent->i_sb);
+ ceph_quarantine_splice_finish(&qsplice);
boutc_formats(cl,
"ENOENT on snapdir %p '%s', linking to snapdir %p %llx.%llx. Spliced dentry %p\n",
"ENOENT on snapdir %p '%pd', linking to snapdir %p %llx.%llx. Spliced dentry %p\n",
@@ -904,8 +912,13 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
ceph_dir_clear_complete(dir);
}
- /* can we conclude ENOENT locally? */
- if (d_really_is_negative(dentry)) {
+ /*
+ * A marked directory, or one whose parents are not cached,
+ * must not answer from the complete-dir cache. The MDS reply
+ * is what clears a lost disable.
+ */
+ if (d_really_is_negative(dentry) &&
+ ceph_inode_quarantine_state(dir) == CEPH_Q_CLEAR) {
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
@@ -1068,9 +1081,7 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir,
out_req:
ceph_mdsc_put_request(req);
out:
- if (!err)
- ceph_init_inode_acls(d_inode(dentry), &as_ctx);
- else
+ if (err)
d_drop(dentry);
ceph_release_acl_sec_ctx(&as_ctx);
ceph_blog_exit(&__ji);
@@ -1297,13 +1308,8 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
ret = dget(req->r_dentry);
ceph_mdsc_put_request(req);
out:
- if (!IS_ERR(ret)) {
- if (ret)
- dentry = ret;
- ceph_init_inode_acls(d_inode(dentry), &as_ctx);
- } else {
+ if (IS_ERR(ret))
d_drop(dentry);
- }
ceph_release_acl_sec_ctx(&as_ctx);
ceph_blog_exit(&__ji);
return ret;
@@ -1312,6 +1318,7 @@ static struct dentry *ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir,
static int ceph_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
+ struct ceph_quarantine_splice qsplice;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_fs_client *fsc = mdsc->fsc;
struct ceph_client *cl = mdsc->fsc->client;
@@ -1375,9 +1382,9 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
d_drop(dentry);
} else if (!req->r_reply_info.head->is_dentry) {
ihold(d_inode(old_dentry));
- ceph_quarantine_splice_start(dir->i_sb);
+ ceph_quarantine_splice_start(dir->i_sb, &qsplice);
d_instantiate(dentry, d_inode(old_dentry));
- ceph_quarantine_splice_finish(dir->i_sb);
+ ceph_quarantine_splice_finish(&qsplice);
}
ceph_mdsc_put_request(req);
ceph_blog_exit(&__ji);
@@ -1441,8 +1448,17 @@ static int get_caps_for_async_unlink(struct inode *dir, struct dentry *dentry)
{
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di;
+ struct inode *inode = d_inode(dentry);
int got = 0, want = CEPH_CAP_FILE_EXCL | CEPH_CAP_DIR_UNLINK;
+ /*
+ * Async unlink completes in the cache. A marked inode, or one
+ * whose parents are not cached, has to go to the MDS.
+ */
+ if (ceph_inode_quarantine_write_state(dir) != CEPH_Q_CLEAR ||
+ (inode && ceph_inode_quarantine_write_state(inode) != CEPH_Q_CLEAR))
+ return 0;
+
spin_lock(&ci->i_ceph_lock);
if ((__ceph_caps_issued(ci, NULL) & want) == want) {
ceph_take_cap_refs(ci, want, false);
@@ -1627,6 +1643,7 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
struct dentry *old_dentry, struct inode *new_dir,
struct dentry *new_dentry, unsigned int flags)
{
+ struct ceph_mds_client *qmdsc;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old_dir->i_sb);
struct ceph_fs_client *fsc = mdsc->fsc;
struct ceph_client *cl = mdsc->fsc->client;
@@ -1713,9 +1730,9 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir,
* to do it here.
*/
moved = d_inode(old_dentry);
- ceph_quarantine_move_start(moved, old_dir, new_dir);
+ qmdsc = ceph_quarantine_move_start(moved, old_dir, new_dir);
d_move(old_dentry, new_dentry);
- ceph_quarantine_move_finish(moved, old_dir, new_dir);
+ ceph_quarantine_move_finish(qmdsc);
}
ceph_mdsc_put_request(req);
ceph_blog_exit(&__ji);
@@ -2349,12 +2366,16 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
struct ceph_dir_file_info *dfi = file->private_data;
struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
- int left;
+ int left, err;
const int bufsize = 1024;
if (!ceph_test_mount_opt(ceph_sb_to_fs_client(inode->i_sb), DIRSTAT))
return -EISDIR;
+ err = ceph_quarantine_revalidate(inode);
+ if (err)
+ return err;
+
if (!dfi->dir_info) {
dfi->dir_info = kmalloc(bufsize, GFP_KERNEL);
if (!dfi->dir_info)
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 9a6eadb94ab4..5b3a64c8571c 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -297,8 +297,10 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
/*
* Retry cap acquisition after a stale session or a lost cap update.
+ * A forced request checks this operation's access on the MDS even when
+ * another opener already holds the requested caps.
*/
-int ceph_renew_caps(struct inode *inode, int fmode)
+int ceph_renew_caps(struct inode *inode, int fmode, bool force)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
struct ceph_client *cl = mdsc->fsc->client;
@@ -308,9 +310,9 @@ int ceph_renew_caps(struct inode *inode, int fmode)
spin_lock(&ci->i_ceph_lock);
__ceph_touch_fmode(ci, mdsc, fmode);
- wanted = __ceph_caps_file_wanted(ci);
+ wanted = force ? ceph_caps_for_mode(fmode) : __ceph_caps_file_wanted(ci);
issued = __ceph_caps_issued(ci, NULL);
- if (__ceph_is_any_real_caps(ci) &&
+ if (!force && __ceph_is_any_real_caps(ci) &&
(!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap) &&
(issued & wanted) == wanted) {
spin_unlock(&ci->i_ceph_lock);
@@ -371,7 +373,9 @@ int ceph_open(struct inode *inode, struct file *file)
struct dentry *dentry;
char *path;
bool do_sync = false;
+ bool snapshot = ceph_in_snap(inode) && ceph_snap(inode) != CEPH_SNAPDIR;
int mask = MAY_READ;
+ enum ceph_qstate qstate;
struct ceph_journal_info __ji;
ceph_blog_enter(fsc, &__ji);
@@ -382,6 +386,23 @@ int ceph_open(struct inode *inode, struct file *file)
return 0;
}
+ /*
+ * Existing caps can satisfy open without an MDS round-trip.
+ * A short walk cannot. Snapshot access needs a fresh MDS request below.
+ */
+ if (!snapshot) {
+ qstate = file->f_mode & FMODE_WRITE ?
+ ceph_inode_quarantine_write_state(inode) :
+ ceph_inode_quarantine_state(inode);
+ if (qstate == CEPH_Q_UNDER &&
+ ceph_inode_quarantine_direct(inode)) {
+ ceph_blog_exit(&__ji);
+ return -EACCES;
+ }
+ if (qstate != CEPH_Q_CLEAR)
+ do_sync = true;
+ }
+
/* filter out O_CREAT|O_EXCL; vfs did that already. yuck. */
flags = file->f_flags & ~(O_CREAT|O_EXCL);
if (S_ISDIR(inode->i_mode)) {
@@ -414,28 +435,31 @@ int ceph_open(struct inode *inode, struct file *file)
if (fmode & CEPH_FILE_MODE_WR)
mask |= MAY_WRITE;
- dentry = d_find_alias(inode);
- if (!dentry) {
- do_sync = true;
- } else {
- struct ceph_path_info path_info = {0};
- path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
- if (IS_ERR(path)) {
+ if (!snapshot) {
+ dentry = d_find_alias(inode);
+ if (!dentry) {
do_sync = true;
- err = 0;
} else {
- err = ceph_mds_check_access(mdsc, path, mask);
- }
- ceph_mdsc_free_path_info(&path_info);
- dput(dentry);
+ struct ceph_path_info path_info = {0};
- /* For none EACCES cases will let the MDS do the mds auth check */
- if (err == -EACCES) {
- ceph_blog_exit(&__ji);
- return err;
- } else if (err < 0) {
- do_sync = true;
- err = 0;
+ path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
+ if (IS_ERR(path)) {
+ do_sync = true;
+ err = 0;
+ } else {
+ err = ceph_mds_check_access(mdsc, path, mask);
+ }
+ ceph_mdsc_free_path_info(&path_info);
+ dput(dentry);
+
+ /* Let the MDS handle errors other than EACCES. */
+ if (err == -EACCES) {
+ ceph_blog_exit(&__ji);
+ return err;
+ } else if (err < 0) {
+ do_sync = true;
+ err = 0;
+ }
}
}
@@ -445,12 +469,23 @@ int ceph_open(struct inode *inode, struct file *file)
return -EROFS;
}
- /* trivially open snapdir */
+ /* A synthetic snapdir must be validated through its real parent. */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
+ err = ceph_quarantine_revalidate(inode);
ceph_blog_exit(&__ji);
+ if (err)
+ return err;
return ceph_init_file(inode, file, fmode);
}
+ if (snapshot) {
+ err = ceph_snapshot_read_auth(inode);
+ if (!err)
+ err = ceph_init_file(inode, file, fmode);
+ ceph_blog_exit(&__ji);
+ return err;
+ }
+
/*
* No need to block if we have caps on the auth MDS (for
* write) or any MDS (for read). Update wanted set
@@ -541,6 +576,13 @@ static int try_prep_async_create(struct inode *dir, struct dentry *dentry,
int got = 0, want = CEPH_CAP_FILE_EXCL | CEPH_CAP_DIR_CREATE;
u64 ino;
+ /*
+ * Async create completes in the cache. A marked directory, or
+ * one whose parents are not cached, has to go to the MDS.
+ */
+ if (ceph_inode_quarantine_write_state(dir) != CEPH_Q_CLEAR)
+ return 0;
+
spin_lock(&ci->i_ceph_lock);
/* No auth cap means no chance for Dc caps */
if (!ci->i_auth_cap)
@@ -687,6 +729,7 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
struct ceph_acl_sec_ctx *as_ctx,
struct ceph_file_layout *lo)
{
+ struct ceph_quarantine_splice qsplice;
int ret;
char xattr_buf[4];
struct ceph_mds_reply_inode in = { };
@@ -785,9 +828,9 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode,
if (d_in_lookup(dentry) || d_really_is_negative(dentry)) {
if (!d_unhashed(dentry))
d_drop(dentry);
- ceph_quarantine_splice_start(dir->i_sb);
+ ceph_quarantine_splice_start(dir->i_sb, &qsplice);
dn = d_splice_alias(inode, dentry);
- ceph_quarantine_splice_finish(dir->i_sb);
+ ceph_quarantine_splice_finish(&qsplice);
WARN_ON_ONCE(dn && dn != dentry);
}
file->f_mode |= FMODE_CREATED;
@@ -2972,6 +3015,27 @@ static int get_rd_wr_caps(struct file *src_filp, int *src_got,
int ret = 0;
bool retrying = false;
+ if (ceph_in_snap(file_inode(src_filp)) &&
+ ceph_snap(file_inode(src_filp)) != CEPH_SNAPDIR) {
+ /*
+ * Snapshot caps have no MDS revocation state, so holding
+ * them cannot prevent a destination cap grant. Validate
+ * the snapshot before taking any destination references.
+ */
+ ret = ceph_get_caps(src_filp, CEPH_CAP_FILE_RD,
+ CEPH_CAP_FILE_SHARED, -1, src_got);
+ if (ret < 0)
+ return ret;
+ ret = ceph_get_caps(dst_filp, CEPH_CAP_FILE_WR,
+ CEPH_CAP_FILE_BUFFER, dst_endoff, dst_got);
+ if (ret < 0) {
+ ceph_put_cap_refs(ceph_inode(file_inode(src_filp)),
+ *src_got);
+ *src_got = 0;
+ }
+ return ret;
+ }
+
retry_caps:
ret = ceph_get_caps(dst_filp, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
dst_endoff, dst_got);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 78e97cf2f9a4..511bb1750c38 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -60,6 +60,13 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
#endif
inode_set_iversion_raw(inode, 0);
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ /* The VFS ACL cache would bypass Ceph's quarantine checks. */
+ if (READ_ONCE(mdsc->quarantine_supported)) {
+ inode->i_acl = ACL_DONT_CACHE;
+ inode->i_default_acl = ACL_DONT_CACHE;
+ }
+#endif
percpu_counter_inc(&mdsc->metric.total_inodes);
return 0;
@@ -252,6 +259,8 @@ struct inode *ceph_get_snapdir(struct inode *parent)
inode_set_atime_to_ts(inode, inode_get_atime(parent));
ci->i_rbytes = 0;
ci->i_btime = ceph_inode(parent)->i_btime;
+ ceph_inode_set_subvolume(inode,
+ READ_ONCE(ceph_inode(parent)->i_subvolume_id));
#ifdef CONFIG_FS_ENCRYPTION
/* if encrypted, just borrow fscrypt_auth from parent */
@@ -768,6 +777,17 @@ static void ceph_quarantine_write_end(struct ceph_mds_client *mdsc)
if (atomic_dec_return(&mdsc->quarantine_writers) == 0)
atomic64_inc_return(&mdsc->quarantine_epoch);
spin_unlock(&mdsc->quarantine_lock);
+ wake_up_all(&mdsc->quarantine_waitq);
+}
+
+/* Called under mdsc->mutex before a supporting session starts its requests. */
+void ceph_quarantine_enable(struct ceph_mds_client *mdsc)
+{
+ if (READ_ONCE(mdsc->quarantine_supported))
+ return;
+
+ WRITE_ONCE(mdsc->quarantine_supported, true);
+ ceph_quarantine_disable_acl_cache(mdsc->fsc->sb);
}
void ceph_quarantine_set(struct ceph_inode_info *ci)
@@ -890,6 +910,46 @@ static bool ceph_qmds_confirmed(struct ceph_inode_info *ci, u64 epoch)
return confirmed;
}
+static void ceph_quarantine_remember_clear(struct inode *inode, u64 epoch,
+ const struct cred *cred)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ const struct cred *old = NULL;
+
+ if (!mdsc || atomic_read(&mdsc->quarantine_count) == 0)
+ return;
+
+ /* Serialize the credential and epoch pair against other receipts. */
+ spin_lock(&ci->i_ceph_lock);
+ if (atomic_read(&mdsc->quarantine_count) == 0 ||
+ ceph_inode_quarantine_direct(inode) || (epoch & 1) ||
+ atomic_read(&mdsc->quarantine_splices) ||
+ (u64)atomic64_read_acquire(&mdsc->quarantine_epoch) != epoch)
+ goto out;
+
+ old = ci->i_qmds_cred;
+ /* Invalidate the old receipt before publishing its new credentials. */
+ atomic64_set_release(&ci->i_qmds, 0);
+ if (old != cred)
+ ci->i_qmds_cred = get_cred(cred);
+ else
+ old = NULL;
+
+ /* Pairs with atomic64_read_acquire() in ceph_qmds_confirmed(). */
+ atomic64_set_release(&ci->i_qmds, epoch | 1ULL);
+ /* Order the confirmation store before re-reading its generation. */
+ smp_mb();
+ if ((u64)atomic64_read(&mdsc->quarantine_epoch) != epoch ||
+ atomic_read(&mdsc->quarantine_splices)) {
+ /* The epoch moved. Drop the confirmation. */
+ atomic64_set_release(&ci->i_qmds, 0);
+ }
+out:
+ spin_unlock(&ci->i_ceph_lock);
+ put_cred(old);
+}
+
static void ceph_quarantine_forget_receipt(struct ceph_inode_info *ci)
{
const struct cred *cred;
@@ -955,8 +1015,8 @@ static int ceph_quarantine_walk_once(struct inode *inode, u64 epoch,
* d_obtain_root(), has the same shape and is not a
* finished walk.
*/
- if (!parent || parent == alias) {
- if (parent == alias && S_ISDIR(cur->i_mode) &&
+ if (parent == alias) {
+ if (S_ISDIR(cur->i_mode) &&
alias == READ_ONCE(inode->i_sb->s_root))
done = true;
break;
@@ -1107,67 +1167,146 @@ enum ceph_qstate ceph_inode_quarantine_write_state(struct inode *inode)
return __ceph_inode_quarantine_state(inode, false);
}
-static struct ceph_mds_client *ceph_quarantine_move_mdsc(struct inode *inode,
- struct inode *old_dir,
- struct inode *new_dir)
+/* Wait for namespace writers without blocking a fill-trace's own LSM hook. */
+int ceph_quarantine_wait(struct inode *inode)
{
- if (!inode || old_dir == new_dir)
- return NULL;
- return ceph_sb_to_mdsc(inode->i_sb);
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ struct ceph_quarantine_splice *splice;
+ bool own_splice = false;
+ int err;
+
+ /* A fill-trace LSM hook may own the splice that would wake us. */
+ if (ceph_current_fill_trace_request())
+ return -EBUSY;
+ /* Async create and mount-root instantiation can run hooks too. */
+ spin_lock(&mdsc->quarantine_lock);
+ list_for_each_entry(splice, &mdsc->quarantine_splice_owners, item) {
+ if (splice->task == current) {
+ own_splice = true;
+ break;
+ }
+ }
+ spin_unlock(&mdsc->quarantine_lock);
+ if (own_splice)
+ return -EBUSY;
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+ err = wait_event_interruptible(mdsc->quarantine_waitq,
+ !(atomic64_read_acquire(&mdsc->quarantine_epoch) & 1) &&
+ !atomic_read_acquire(&mdsc->quarantine_splices));
+ if (err)
+ return err;
+ if (ceph_inode_is_shutdown(inode))
+ return -ESTALE;
+ cond_resched();
+ return 0;
}
/*
- * Bracket d_move(). The epoch is odd across the parent change, so a
- * cached false cannot be reused against the new parent. d_move() does
- * not sleep. Same-directory renames do not take a writer slot.
- *
- * Sleeping alias splices use a separate counter below.
+ * Snapshots need a fresh MDS answer unless a connected head cap can receive
+ * quarantine revocations. For head inodes, a direct mark fails the caller.
+ * Inherited marks may permit recovery through a path-scoped q/Q grant.
+ * A GETATTR read receipt covers only this inode, credentials and epoch;
+ * writes need a mode-specific OPEN. A new epoch invalidates the receipt.
*/
-void ceph_quarantine_move_start(struct inode *inode, struct inode *old_dir,
- struct inode *new_dir)
+int ceph_quarantine_revalidate(struct inode *inode)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ enum ceph_qstate q;
+ u64 epoch;
+ int err;
+
+ /* Immutable snapshot caps cannot receive quarantine notifications. */
+ if (ceph_in_snap(inode)) {
+ if (!ceph_snapshot_needs_revalidate(inode))
+ return 0;
+ if (ceph_snap(inode) == CEPH_SNAPDIR)
+ return ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, true);
+ return ceph_snapshot_read_auth(inode);
+ }
+
+ for (;;) {
+ q = ceph_inode_quarantine_state(inode);
+ if (q == CEPH_Q_CLEAR)
+ return 0;
+ if (q == CEPH_Q_UNDER && ceph_inode_quarantine_direct(inode))
+ return -EACCES;
+ /*
+ * A splice may be sleeping in an LSM hook which calls back
+ * here. The wait helper rejects that recursion; ordinary
+ * blocking operations wait for a stable namespace instead
+ * of exposing an internal retry to userspace.
+ */
+ err = ceph_quarantine_wait(inode);
+ if (err)
+ return err;
+ epoch = (u64)atomic64_read_acquire(&mdsc->quarantine_epoch);
+ if ((epoch & 1) || atomic_read(&mdsc->quarantine_splices))
+ continue;
+
+ err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL, true);
+ if (err)
+ return err;
+
+ /* Recheck the walk and the confirmation before using caps. */
+ }
+}
+
+/* The returned token pairs the gate decision across feature activation. */
+struct ceph_mds_client *ceph_quarantine_move_start(struct inode *inode,
+ struct inode *old_dir,
+ struct inode *new_dir)
{
- ceph_quarantine_write_begin(ceph_quarantine_move_mdsc(inode, old_dir,
- new_dir));
+ struct ceph_mds_client *mdsc;
+
+ if (!inode || old_dir == new_dir)
+ return NULL;
+ mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ if (!READ_ONCE(mdsc->quarantine_supported))
+ return NULL;
+ ceph_quarantine_write_begin(mdsc);
+ return mdsc;
}
-void ceph_quarantine_move_finish(struct inode *inode, struct inode *old_dir,
- struct inode *new_dir)
+void ceph_quarantine_move_finish(struct ceph_mds_client *mdsc)
{
- ceph_quarantine_write_end(ceph_quarantine_move_mdsc(inode, old_dir,
- new_dir));
+ ceph_quarantine_write_end(mdsc);
}
/*
- * d_splice_alias() and d_instantiate() can sleep in the LSM hook before
- * changing ancestry. Keep the epoch even for that hook, but disallow
- * all cached answers throughout the splice. A fresh walk also samples
- * rename_lock, so it cannot accept a chain torn by a move. Bracket
- * first attachments too: descendants may hold MDS confirmations from
- * when the directory had no connected alias.
- *
- * Fully ordered atomics and quarantine_lock make the counter and epoch
- * transitions one writer operation. Entry disables cache use before
- * invalidating tags; exit invalidates tags before enabling cache use.
- * Adding two preserves the parity of any concurrent mark writer.
+ * LSM hooks can sleep and reenter Ceph during a splice. Keep the epoch
+ * even but disable cached receipts while the ancestry can change.
+ * Namespace operations on unsupported mounts do not take writer slots.
*/
-void ceph_quarantine_splice_start(struct super_block *sb)
+void ceph_quarantine_splice_start(struct super_block *sb,
+ struct ceph_quarantine_splice *splice)
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+ splice->mdsc = NULL;
+ if (!READ_ONCE(mdsc->quarantine_supported))
+ return;
+ splice->mdsc = mdsc;
+ splice->task = current;
spin_lock(&mdsc->quarantine_lock);
+ list_add(&splice->item, &mdsc->quarantine_splice_owners);
atomic_inc_return(&mdsc->quarantine_splices);
atomic64_add_return(2, &mdsc->quarantine_epoch);
spin_unlock(&mdsc->quarantine_lock);
}
-void ceph_quarantine_splice_finish(struct super_block *sb)
+void ceph_quarantine_splice_finish(struct ceph_quarantine_splice *splice)
{
- struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(sb);
+ struct ceph_mds_client *mdsc = splice->mdsc;
+ if (!mdsc)
+ return;
spin_lock(&mdsc->quarantine_lock);
+ list_del(&splice->item);
atomic64_add_return(2, &mdsc->quarantine_epoch);
atomic_dec_return(&mdsc->quarantine_splices);
spin_unlock(&mdsc->quarantine_lock);
+ wake_up_all(&mdsc->quarantine_waitq);
}
static bool ceph_quarantine_reply_can_clear(struct ceph_inode_info *ci,
@@ -1611,9 +1750,12 @@ int ceph_fill_inode(struct inode *inode, struct folio *locked_folio,
*/
if (iinfo->xattr_len > 4) {
xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS);
- if (!xattr_blob)
+ if (!xattr_blob) {
pr_err_client(cl, "ENOMEM xattr blob %d bytes\n",
iinfo->xattr_len);
+ err = -ENOMEM;
+ goto out;
+ }
}
if (iinfo->pool_ns_len > 0)
@@ -1623,6 +1765,9 @@ int ceph_fill_inode(struct inode *inode, struct folio *locked_folio,
if (ceph_in_snap(inode) && !ci->i_snapid_map)
ci->i_snapid_map = ceph_get_snapid_map(mdsc, ceph_snap(inode));
+ if (READ_ONCE(session->s_mdsc->quarantine_supported))
+ ceph_quarantine_uncache_inode_acls(inode);
+
spin_lock(&ci->i_ceph_lock);
/*
@@ -1850,7 +1995,7 @@ int ceph_fill_inode(struct inode *inode, struct folio *locked_folio,
*/
inode->i_op = &ceph_encrypted_symlink_iops;
} else {
- inode->i_link = ci->i_symlink;
+ /* VFS i_link would bypass the quarantine get_link check. */
inode->i_op = &ceph_symlink_iops;
}
break;
@@ -2071,6 +2216,7 @@ static void update_dentry_lease_careful(struct dentry *dentry,
*/
static int splice_dentry(struct dentry **pdn, struct inode *in)
{
+ struct ceph_quarantine_splice qsplice;
struct ceph_client *cl = ceph_inode_to_client(in);
struct dentry *dn = *pdn;
struct dentry *realdn;
@@ -2102,9 +2248,9 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
/* dn must be unhashed */
if (!d_unhashed(dn))
d_drop(dn);
- ceph_quarantine_splice_start(dn->d_sb);
+ ceph_quarantine_splice_start(dn->d_sb, &qsplice);
realdn = d_splice_alias(in, dn);
- ceph_quarantine_splice_finish(dn->d_sb);
+ ceph_quarantine_splice_finish(&qsplice);
if (IS_ERR(realdn)) {
pr_err_client(cl, "error %ld %p inode %p ino %llx.%llx\n",
PTR_ERR(realdn), dn, in, ceph_vinop(in));
@@ -2138,6 +2284,7 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
*/
int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
{
+ struct ceph_mds_client *qmdsc;
struct ceph_mds_session *session = req->r_session;
struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
struct inode *in = NULL;
@@ -2261,17 +2408,24 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
}
if (rinfo->head->is_target) {
+ struct ceph_vino expected;
+
/* Should be filled in by handle_reply */
BUG_ON(!req->r_target_inode);
in = req->r_target_inode;
ceph_inode_set_subvolume(in, rinfo->targeti.subvolume_id);
- err = ceph_fill_inode(in, req->r_locked_folio, &rinfo->targeti,
- NULL, session,
- (!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
- !test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) &&
- rinfo->head->result == 0) ? req->r_fmode : -1,
- &req->r_caps_reservation);
+ expected = req->r_inode ? ceph_vino(req->r_inode) : req->r_ino1;
+ if (req->r_locked_folio &&
+ (ceph_ino(in) != expected.ino || ceph_snap(in) != expected.snap))
+ err = -ESTALE;
+ else
+ err = ceph_fill_inode(in, req->r_locked_folio, &rinfo->targeti,
+ NULL, session,
+ (!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
+ !test_bit(CEPH_MDS_R_ASYNC, &req->r_req_flags) &&
+ rinfo->head->result == 0) ? req->r_fmode : -1,
+ &req->r_caps_reservation);
if (err < 0) {
pr_err_client(cl, "badness %p %llx.%llx\n", in,
ceph_vinop(in));
@@ -2341,9 +2495,9 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
ceph_dir_clear_ordered(olddir);
moved = d_inode(req->r_old_dentry);
- ceph_quarantine_move_start(moved, olddir, dir);
+ qmdsc = ceph_quarantine_move_start(moved, olddir, dir);
d_move(req->r_old_dentry, dn);
- ceph_quarantine_move_finish(moved, olddir, dir);
+ ceph_quarantine_move_finish(qmdsc);
boutc(cl, " src %p '%s' dst %p '%s'\n",
req->r_old_dentry, req->r_old_dentry->d_name.name, dn, dn->d_name.name);
@@ -2952,14 +3106,47 @@ static void ceph_inode_work(struct work_struct *work)
iput(inode);
}
+static int ceph_symlink_revalidate(struct inode *inode)
+{
+ /*
+ * A saved target without live caps receives no quarantine revocation.
+ * Snapshot caps are immutable, so always ask the MDS for those.
+ */
+ if (ceph_in_snap(inode) && ceph_snap(inode) != CEPH_SNAPDIR)
+ return ceph_snapshot_read_auth(inode);
+ return ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, ceph_in_snap(inode));
+}
+
+static const char *ceph_get_link(struct dentry *dentry, struct inode *inode,
+ struct delayed_call *done)
+{
+ int err;
+
+ if (!dentry)
+ return ERR_PTR(-ECHILD);
+ err = ceph_symlink_revalidate(inode);
+ if (err)
+ return ERR_PTR(err);
+ return ceph_inode(inode)->i_symlink;
+}
+
+/*
+ * fscrypt can cache the decrypted target in ->i_link, allowing the VFS to
+ * bypass this callback. Checking those cache hits needs separate fscrypt
+ * support; this check covers only accesses that reach ->get_link().
+ */
static const char *ceph_encrypted_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
struct ceph_inode_info *ci = ceph_inode(inode);
+ int err;
if (!dentry)
return ERR_PTR(-ECHILD);
+ err = ceph_symlink_revalidate(inode);
+ if (err)
+ return ERR_PTR(err);
return fscrypt_get_symlink(inode, ci->i_symlink, i_size_read(inode),
done);
@@ -2982,7 +3169,7 @@ static int ceph_encrypted_symlink_getattr(struct mnt_idmap *idmap,
* symlinks
*/
static const struct inode_operations ceph_symlink_iops = {
- .get_link = simple_get_link,
+ .get_link = ceph_get_link,
.setattr = ceph_setattr,
.getattr = ceph_getattr,
.listxattr = ceph_listxattr,
@@ -3193,6 +3380,25 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
return PTR_ERR(req);
}
+ /*
+ * Exclusive caps apply mode, owner, times, and a size increase
+ * with no MDS round trip. The state check may schedule, so it runs
+ * before i_ceph_lock. A short walk sends the setattr.
+ */
+ switch (ceph_inode_quarantine_write_state(inode)) {
+ case CEPH_Q_UNDER:
+ if (ceph_inode_quarantine_direct(inode)) {
+ err = -EACCES;
+ goto out;
+ }
+ fallthrough;
+ case CEPH_Q_UNKNOWN:
+ do_sync = true;
+ break;
+ default:
+ break;
+ }
+
fill_fscrypt = false;
spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
@@ -3231,7 +3437,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
kfree(ci->fscrypt_auth);
ci->fscrypt_auth = (u8 *)cia->fscrypt_auth;
ci->fscrypt_auth_len = len;
- } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_AUTH_SHARED) == 0 ||
ci->fscrypt_auth_len != len ||
memcmp(ci->fscrypt_auth, cia->fscrypt_auth, len)) {
req->r_fscrypt_auth = cia->fscrypt_auth;
@@ -3258,7 +3464,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_uid = fsuid;
dirtied |= CEPH_CAP_AUTH_EXCL;
- } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_AUTH_SHARED) == 0 ||
!uid_eq(fsuid, inode->i_uid)) {
req->r_args.setattr.uid = cpu_to_le32(
from_kuid(&init_user_ns, fsuid));
@@ -3276,7 +3482,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_gid = fsgid;
dirtied |= CEPH_CAP_AUTH_EXCL;
- } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_AUTH_SHARED) == 0 ||
!gid_eq(fsgid, inode->i_gid)) {
req->r_args.setattr.gid = cpu_to_le32(
from_kgid(&init_user_ns, fsgid));
@@ -3290,9 +3496,10 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL)) {
inode->i_mode = attr->ia_mode;
dirtied |= CEPH_CAP_AUTH_EXCL;
- } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_AUTH_SHARED) == 0 ||
attr->ia_mode != inode->i_mode) {
- inode->i_mode = attr->ia_mode;
+ if (!do_sync)
+ inode->i_mode = attr->ia_mode;
req->r_args.setattr.mode = cpu_to_le32(attr->ia_mode);
mask |= CEPH_SETATTR_MODE;
release |= CEPH_CAP_AUTH_SHARED;
@@ -3313,7 +3520,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
&attr->ia_atime) < 0) {
inode_set_atime_to_ts(inode, attr->ia_atime);
dirtied |= CEPH_CAP_FILE_WR;
- } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_FILE_SHARED) == 0 ||
!timespec64_equal(&atime, &attr->ia_atime)) {
ceph_encode_timespec64(&req->r_args.setattr.atime,
&attr->ia_atime);
@@ -3352,7 +3559,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
dirtied |= CEPH_CAP_FILE_EXCL;
ia_valid |= ATTR_MTIME;
}
- } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_FILE_SHARED) == 0 ||
attr->ia_size != isize) {
mask |= CEPH_SETATTR_SIZE;
release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
@@ -3387,7 +3594,7 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
timespec64_compare(&mtime, &attr->ia_mtime) < 0) {
inode_set_mtime_to_ts(inode, attr->ia_mtime);
dirtied |= CEPH_CAP_FILE_WR;
- } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
+ } else if (do_sync || (issued & CEPH_CAP_FILE_SHARED) == 0 ||
!timespec64_equal(&mtime, &attr->ia_mtime)) {
ceph_encode_timespec64(&req->r_args.setattr.mtime,
&attr->ia_mtime);
@@ -3411,11 +3618,11 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
* we need to choose a cap to dirty under, or do
* a almost-no-op setattr
*/
- if (issued & CEPH_CAP_AUTH_EXCL)
+ if (!do_sync && (issued & CEPH_CAP_AUTH_EXCL))
dirtied |= CEPH_CAP_AUTH_EXCL;
- else if (issued & CEPH_CAP_FILE_EXCL)
+ else if (!do_sync && (issued & CEPH_CAP_FILE_EXCL))
dirtied |= CEPH_CAP_FILE_EXCL;
- else if (issued & CEPH_CAP_XATTR_EXCL)
+ else if (!do_sync && (issued & CEPH_CAP_XATTR_EXCL))
dirtied |= CEPH_CAP_XATTR_EXCL;
else
mask |= CEPH_SETATTR_CTIME;
@@ -3471,6 +3678,12 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
ceph_free_cap_flush(prealloc_cf);
goto retry;
}
+ if (!err && do_sync) {
+ /* Existing exclusive caps may keep reply-fill from updating attrs. */
+ spin_lock(&ci->i_ceph_lock);
+ setattr_copy(idmap, inode, attr);
+ spin_unlock(&ci->i_ceph_lock);
+ }
}
out:
boutc(cl, "%p %llx.%llx result=%d (%s locally, %d remote)\n", inode,
@@ -3571,6 +3784,149 @@ int ceph_try_to_choose_auth_mds(struct inode *inode, int mask)
return USE_ANY_MDS;
}
+/* A snapshot path must reach a head inode to encode its snapshot name. */
+static bool ceph_snapshot_has_path(struct inode *inode, bool check_caps)
+{
+ struct dentry *cur;
+ u64 subvolume_id = CEPH_SUBVOLUME_ID_NONE;
+ unsigned int seq, depth = 0;
+ bool connected = false;
+
+ /* A torn membership ID cannot establish revocation coverage. */
+ if (check_caps && IS_ENABLED(CONFIG_64BIT))
+ subvolume_id = READ_ONCE(ceph_inode(inode)->i_subvolume_id);
+
+ rcu_read_lock();
+ seq = read_seqbegin(&rename_lock);
+ cur = d_find_alias_rcu(inode);
+ while (cur && depth++ < 256) {
+ struct inode *in = d_inode_rcu(cur);
+ struct dentry *parent;
+
+ if (!in)
+ break;
+ if (!ceph_in_snap(in)) {
+ connected = !check_caps ||
+ (subvolume_id != CEPH_SUBVOLUME_ID_NONE &&
+ ceph_ino(in) == subvolume_id &&
+ ceph_quarantine_head_cap_valid(in));
+ break;
+ }
+ if (d_unhashed(cur) ||
+ (READ_ONCE(cur->d_flags) & DCACHE_DISCONNECTED))
+ break;
+ parent = READ_ONCE(cur->d_parent);
+ if (parent == cur)
+ break;
+ cur = parent;
+ }
+ if (read_seqretry(&rename_lock, seq))
+ connected = false;
+ rcu_read_unlock();
+ return connected;
+}
+
+/*
+ * Only the target's subvolume root supplies reliable quarantine revocations.
+ * A snapshot taken above that root can reach a head ancestor outside the
+ * subvolume; its cap stays valid when the target is quarantined. Require the
+ * MDS-provided subvolume ID to identify the head root whose AUTH_SHARED cap
+ * we check. Unknown IDs, 32-bit clients and other head ancestors need an MDS
+ * answer, as do detached snapshots, expired root caps and active quarantine.
+ */
+bool ceph_snapshot_needs_revalidate(struct inode *inode)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ u64 epoch;
+
+ if (!ceph_in_snap(inode) || !READ_ONCE(mdsc->quarantine_supported))
+ return false;
+ epoch = atomic64_read_acquire(&mdsc->quarantine_epoch);
+ if ((epoch & 1) || atomic_read(&mdsc->quarantine_count) ||
+ atomic_read(&mdsc->quarantine_splices) ||
+ !ceph_snapshot_has_path(inode, true))
+ return true;
+ /* Do not accept a head cap observed across a revoke or parent change. */
+ smp_rmb();
+ return (u64)atomic64_read_acquire(&mdsc->quarantine_epoch) != epoch ||
+ atomic_read(&mdsc->quarantine_count) ||
+ atomic_read(&mdsc->quarantine_splices);
+}
+
+static int ceph_snapshot_reply_error(struct inode *inode,
+ struct ceph_mds_request *req, int mask)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ bool have_xattrs;
+
+ if (!req->r_target_inode ||
+ ceph_ino(req->r_target_inode) != ceph_ino(inode) ||
+ ceph_snap(req->r_target_inode) != ceph_snap(inode))
+ return -EOPNOTSUPP;
+
+ /* LOOKUPINO can authorize access without returning the requested blob. */
+ if ((mask & CEPH_CAP_XATTR_SHARED) &&
+ req->r_reply_info.targeti.xattr_len < 4) {
+ spin_lock(&ci->i_ceph_lock);
+ have_xattrs = ci->i_xattrs.version != 0;
+ spin_unlock(&ci->i_ceph_lock);
+ if (!have_xattrs)
+ return -EOPNOTSUPP;
+ }
+ if ((mask & CEPH_CAP_FILE_RD) &&
+ req->r_reply_info.targeti.inline_version == 0 &&
+ ceph_has_inline_data(ci) && i_size_read(inode) > 0)
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+static int ceph_snapshot_lookupino(struct inode *inode,
+ struct folio *locked_folio, int mask)
+{
+ struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
+ struct ceph_mds_request *req;
+ int err;
+
+ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO, USE_ANY_MDS);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+ /* No r_inode: an NFS alias may not encode a snapshot pathname. */
+ req->r_ino1 = ceph_vino(inode);
+ req->r_args.lookupino.snapid = cpu_to_le64(ceph_snap(inode));
+ req->r_args.lookupino.mask = cpu_to_le32(mask);
+ req->r_num_caps = 1;
+ req->r_locked_folio = locked_folio;
+ err = ceph_mdsc_do_request(mdsc, NULL, req);
+ if (!err)
+ err = ceph_snapshot_reply_error(inode, req, mask);
+ if (locked_folio && !err) {
+ u64 version = req->r_reply_info.targeti.inline_version;
+
+ if (version == 0)
+ err = -EINVAL;
+ else if (version == CEPH_INLINE_NONE || version == 1)
+ err = -ENODATA;
+ else
+ err = req->r_reply_info.targeti.inline_len;
+ }
+ ceph_mdsc_put_request(req);
+ return err;
+}
+
+int ceph_snapshot_read_auth(struct inode *inode)
+{
+ if (!ceph_snapshot_needs_revalidate(inode))
+ return 0;
+
+ /*
+ * Preserve a connected snapshot path: its head inode may have been
+ * deleted and no longer be cached by the MDS. Disconnected handles
+ * fall back to LOOKUPINO, with the exact inode and snapshot ID.
+ * The authorization is scoped to this operation, never cached.
+ */
+ return ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED, true);
+}
+
/*
* Verify that we have a lease on the given mask. If not,
* do a getattr against an mds.
@@ -3582,20 +3938,46 @@ int __ceph_do_getattr(struct inode *inode, struct folio *locked_folio,
struct ceph_client *cl = fsc->client;
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
+ u64 qepoch;
int mode;
int err;
if (ceph_snap(inode) == CEPH_SNAPDIR) {
+ struct inode *parent;
+
boutc(cl, "inode %p %llx.%llx SNAPDIR\n", inode,
ceph_vinop(inode));
- return 0;
+ if (!ceph_snapshot_needs_revalidate(inode))
+ return 0;
+ /* The synthetic snapdir has the real directory's ino. */
+ parent = ceph_lookup_inode(inode->i_sb, ceph_ino(inode));
+ if (IS_ERR(parent))
+ return PTR_ERR(parent);
+ err = ceph_do_getattr(parent, mask, true);
+ iput(parent);
+ return err;
}
+ /*
+ * Cached caps would satisfy getattr after the MDS has revoked
+ * access, and a short walk has no ancestor to consult. Ask the
+ * MDS so a lost quarantine-disable can clear the mark, and so
+ * an uncached parent chain is not treated as clear. Snapshot caps need
+ * an MDS check unless a live head cap provides quarantine notifications.
+ */
+ if (ceph_snapshot_needs_revalidate(inode) ||
+ ceph_inode_quarantine_state(inode) != CEPH_Q_CLEAR)
+ force = true;
+
boutc(cl, "inode %p %llx.%llx mask %s mode 0%o\n", inode,
ceph_vinop(inode), ceph_cap_string(mask), inode->i_mode);
if (!force && ceph_caps_issued_mask_metric(ceph_inode(inode), mask, 1))
return 0;
+ if (ceph_in_snap(inode) && !ceph_snapshot_has_path(inode, false))
+ return ceph_snapshot_lookupino(inode, locked_folio, mask);
+
+ qepoch = (u64)atomic64_read_acquire(&mdsc->quarantine_epoch);
mode = ceph_try_to_choose_auth_mds(inode, mask);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, mode);
if (IS_ERR(req))
@@ -3606,6 +3988,15 @@ int __ceph_do_getattr(struct inode *inode, struct folio *locked_folio,
req->r_args.getattr.mask = cpu_to_le32(mask);
req->r_locked_folio = locked_folio;
err = ceph_mdsc_do_request(mdsc, NULL, req);
+ if (ceph_in_snap(inode)) {
+ if (err == -EINVAL || err == -ESTALE ||
+ (!err && ceph_snapshot_reply_error(inode, req, mask))) {
+ ceph_mdsc_put_request(req);
+ return ceph_snapshot_lookupino(inode, locked_folio, mask);
+ }
+ }
+ if (!err && !ceph_in_snap(inode))
+ ceph_quarantine_remember_clear(inode, qepoch, req->r_cred);
if (locked_folio && err == 0) {
u64 inline_version = req->r_reply_info.targeti.inline_version;
if (inline_version == 0) {
@@ -3751,8 +4142,14 @@ int ceph_getattr(struct mnt_idmap *idmap, const struct path *path,
return -ESTALE;
}
- /* Skip the getattr altogether if we're asked not to sync */
- if ((flags & AT_STATX_SYNC_TYPE) != AT_STATX_DONT_SYNC) {
+ /*
+ * AT_STATX_DONT_SYNC would return the cached attrs. A
+ * quarantined inode, or one whose parents are not cached,
+ * still has to ask the MDS. Snapshot caps need a live head cap for notifications.
+ */
+ if (ceph_snapshot_needs_revalidate(inode) ||
+ ceph_inode_quarantine_state(inode) != CEPH_Q_CLEAR ||
+ (flags & AT_STATX_SYNC_TYPE) != AT_STATX_DONT_SYNC) {
err = ceph_do_getattr(inode,
statx_to_caps(request_mask, inode->i_mode),
flags & AT_STATX_FORCE_SYNC);
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 12cb50e0a166..d152cad10c23 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -201,6 +201,10 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
if (copy_from_user(&dl, arg, sizeof(dl)))
return -EFAULT;
+ r = ceph_do_getattr(inode, CEPH_STAT_CAP_LAYOUT, false);
+ if (r)
+ return r;
+
down_read(&osdc->lock);
ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, 1,
&dl.object_no, &dl.object_offset, &xlen);
@@ -401,12 +405,18 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case FS_IOC_GET_ENCRYPTION_POLICY:
ret = vet_mds_for_fscrypt(file);
+ if (ret)
+ return ret;
+ ret = ceph_quarantine_revalidate(inode);
if (ret)
return ret;
return fscrypt_ioctl_get_policy(file, (void __user *)arg);
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
ret = vet_mds_for_fscrypt(file);
+ if (ret)
+ return ret;
+ ret = ceph_quarantine_revalidate(inode);
if (ret)
return ret;
return fscrypt_ioctl_get_policy_ex(file, (void __user *)arg);
@@ -429,6 +439,9 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case FS_IOC_GET_ENCRYPTION_NONCE:
ret = vet_mds_for_fscrypt(file);
+ if (ret)
+ return ret;
+ ret = ceph_quarantine_revalidate(inode);
if (ret)
return ret;
return fscrypt_ioctl_get_nonce(file, (void __user *)arg);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index bb7cf9384fd6..dcac8a6a8657 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4667,6 +4667,8 @@ static void handle_session(struct ceph_mds_session *session,
mdsc->s_cap_auths = cap_auths;
session->s_features = features;
+ if (test_bit(CEPHFS_FEATURE_QUARANTINE, &session->s_features))
+ ceph_quarantine_enable(mdsc);
if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT,
&session->s_features))
ceph_metric_bind_session(mdsc, session);
@@ -6482,6 +6484,9 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc)
spin_lock_init(&mdsc->stopping_lock);
atomic_set(&mdsc->stopping_blockers, 0);
atomic_set(&mdsc->quarantine_count, 0);
+ mdsc->quarantine_supported = false;
+ init_waitqueue_head(&mdsc->quarantine_waitq);
+ INIT_LIST_HEAD(&mdsc->quarantine_splice_owners);
atomic_set(&mdsc->quarantine_writers, 0);
atomic_set(&mdsc->quarantine_splices, 0);
atomic64_set(&mdsc->quarantine_epoch, 0);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 816f5f2d32cc..422a27e44c38 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -39,7 +39,14 @@ enum ceph_feature_type {
CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK,
CEPHFS_FEATURE_SUBVOLUME_METRICS,
- CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_SUBVOLUME_METRICS,
+ /*
+ * Bit 23 is CEPHFS_FEATURE_BLOCKDIFF on the MDS and is not
+ * advertised here. Bit 24 is subvolume quarantine; it must stay
+ * aligned with the userspace client.
+ */
+ CEPHFS_FEATURE_QUARANTINE = 24,
+
+ CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_QUARANTINE,
};
#define CEPHFS_FEATURES_CLIENT_SUPPORTED { \
@@ -57,6 +64,7 @@ enum ceph_feature_type {
CEPHFS_FEATURE_HAS_OWNER_UIDGID, \
CEPHFS_FEATURE_MDS_AUTH_CAPS_CHECK, \
CEPHFS_FEATURE_SUBVOLUME_METRICS, \
+ CEPHFS_FEATURE_QUARANTINE, \
}
/*
@@ -507,6 +515,10 @@ struct ceph_mds_client {
spinlock_t stopping_lock; /* protect snap_empty */
int stopping; /* the stage of shutting down */
atomic_t stopping_blockers;
+ /* Once negotiated, keep tracking across reconnects and mixed ranks. */
+ bool quarantine_supported;
+ wait_queue_head_t quarantine_waitq;
+ struct list_head quarantine_splice_owners; /* quarantine_lock */
/*
* Inodes with CEPH_I_QUARANTINE set. Hot paths skip the
* ancestor walk while this is zero.
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index ad9460d9673c..ed2eab9d6969 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1137,11 +1137,13 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
err = ceph_mdsc_do_request(mdsc, NULL, req);
if (err == 0) {
struct inode *inode = req->r_target_inode;
+ struct ceph_quarantine_splice qsplice;
+
req->r_target_inode = NULL;
doutc(cl, "success\n");
- ceph_quarantine_splice_start(fsc->sb);
+ ceph_quarantine_splice_start(fsc->sb, &qsplice);
root = d_make_root(inode);
- ceph_quarantine_splice_finish(fsc->sb);
+ ceph_quarantine_splice_finish(&qsplice);
if (!root) {
root = ERR_PTR(-ENOMEM);
goto out;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 0264bd9d705f..7f9c7766531e 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1306,16 +1306,27 @@ enum ceph_qstate ceph_inode_quarantine_state(struct inode *inode);
enum ceph_qstate ceph_inode_quarantine_write_state(struct inode *inode);
bool ceph_inode_quarantine_direct(struct inode *inode);
int ceph_quarantine_revalidate(struct inode *inode);
+int ceph_quarantine_wait(struct inode *inode);
+bool ceph_snapshot_needs_revalidate(struct inode *inode);
+bool ceph_quarantine_head_cap_valid(struct inode *inode);
+void ceph_quarantine_enable(struct ceph_mds_client *mdsc);
int ceph_snapshot_read_auth(struct inode *inode);
void ceph_quarantine_set(struct ceph_inode_info *ci);
bool ceph_quarantine_clear(struct ceph_inode_info *ci);
bool ceph_quarantine_reset(struct ceph_inode_info *ci);
-void ceph_quarantine_move_start(struct inode *inode, struct inode *old_dir,
- struct inode *new_dir);
-void ceph_quarantine_move_finish(struct inode *inode, struct inode *old_dir,
- struct inode *new_dir);
-void ceph_quarantine_splice_start(struct super_block *sb);
-void ceph_quarantine_splice_finish(struct super_block *sb);
+struct ceph_mds_client *ceph_quarantine_move_start(struct inode *inode,
+ struct inode *old_dir,
+ struct inode *new_dir);
+void ceph_quarantine_move_finish(struct ceph_mds_client *mdsc);
+struct ceph_quarantine_splice {
+ struct ceph_mds_client *mdsc;
+ struct task_struct *task;
+ struct list_head item;
+};
+
+void ceph_quarantine_splice_start(struct super_block *sb,
+ struct ceph_quarantine_splice *splice);
+void ceph_quarantine_splice_finish(struct ceph_quarantine_splice *splice);
void ceph_handle_quarantine_disable(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session,
struct ceph_msg *msg);
@@ -1379,6 +1390,7 @@ static inline int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
{
return 0;
}
+
static inline void ceph_security_invalidate_secctx(struct inode *inode)
{
}
@@ -1394,8 +1406,9 @@ int ceph_set_acl(struct mnt_idmap *idmap,
struct dentry *dentry, struct posix_acl *acl, int type);
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acl_sec_ctx *as_ctx);
-void ceph_init_inode_acls(struct inode *inode,
- struct ceph_acl_sec_ctx *as_ctx);
+void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx);
+void ceph_quarantine_uncache_inode_acls(struct inode *inode);
+void ceph_quarantine_disable_acl_cache(struct super_block *sb);
static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
@@ -1412,11 +1425,20 @@ static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
{
return 0;
}
+
static inline void ceph_init_inode_acls(struct inode *inode,
struct ceph_acl_sec_ctx *as_ctx)
{
}
+static inline void ceph_quarantine_uncache_inode_acls(struct inode *inode)
+{
+}
+
+static inline void ceph_quarantine_disable_acl_cache(struct super_block *sb)
+{
+}
+
static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
}
@@ -1578,7 +1600,7 @@ static inline bool ceph_has_inline_data(const struct ceph_inode_info *ci)
/* file.c */
extern const struct file_operations ceph_file_fops;
-extern int ceph_renew_caps(struct inode *inode, int fmode);
+int ceph_renew_caps(struct inode *inode, int fmode, bool force);
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 4cba6e7bffd3..9db250b2e7be 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -997,6 +997,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
struct ceph_vxattr *vxattr;
int req_mask;
ssize_t err;
+ bool ask_mds = false;
if (strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
goto handle_non_vxattrs;
@@ -1034,7 +1035,19 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
ceph_vinop(inode), name, ci->i_xattrs.version,
ci->i_xattrs.index_version);
- if (ci->i_xattrs.version == 0 ||
+ /*
+ * A shared cap would answer from the cache. The state check may
+ * schedule, so drop i_ceph_lock first. A reply reading the blob
+ * it just installed must still use that cache.
+ */
+ if (!ceph_current_fill_trace_request()) {
+ spin_unlock(&ci->i_ceph_lock);
+ ask_mds = ceph_snapshot_needs_revalidate(inode) ||
+ ceph_inode_quarantine_state(inode) != CEPH_Q_CLEAR;
+ spin_lock(&ci->i_ceph_lock);
+ }
+
+ if (ask_mds || ci->i_xattrs.version == 0 ||
!((req_mask & CEPH_CAP_XATTR_SHARED) ||
__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1))) {
spin_unlock(&ci->i_ceph_lock);
@@ -1089,6 +1102,7 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
struct ceph_client *cl = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
bool len_only = (size == 0);
+ bool ask_mds = false;
u32 namelen;
int err;
struct ceph_journal_info __ji;
@@ -1100,7 +1114,15 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
ceph_vinop(inode), ci->i_xattrs.version,
ci->i_xattrs.index_version);
- if (ci->i_xattrs.version == 0 ||
+ /* Same as __ceph_getxattr(): do not serve a shared cap hit. */
+ if (!ceph_current_fill_trace_request()) {
+ spin_unlock(&ci->i_ceph_lock);
+ ask_mds = ceph_snapshot_needs_revalidate(inode) ||
+ ceph_inode_quarantine_state(inode) != CEPH_Q_CLEAR;
+ spin_lock(&ci->i_ceph_lock);
+ }
+
+ if (ask_mds || ci->i_xattrs.version == 0 ||
!__ceph_caps_issued_mask_metric(ci, CEPH_CAP_XATTR_SHARED, 1)) {
spin_unlock(&ci->i_ceph_lock);
err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR, true);
@@ -1222,6 +1244,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,
int required_blob_size;
bool check_realm = false;
bool lock_snap_rwsem = false;
+ bool checked_quarantine = false;
if (ceph_in_snap(inode))
return -EROFS;
@@ -1319,6 +1342,33 @@ int __ceph_setxattr(struct inode *inode, const char *name,
goto retry;
}
+ /*
+ * XATTR_EXCL applies the new blob with no MDS round trip.
+ * The state check may schedule, so drop i_ceph_lock first.
+ */
+ if (!checked_quarantine) {
+ enum ceph_qstate qstate;
+
+ spin_unlock(&ci->i_ceph_lock);
+ qstate = ceph_inode_quarantine_write_state(inode);
+ if (qstate == CEPH_Q_UNDER &&
+ ceph_inode_quarantine_direct(inode)) {
+ ceph_buffer_put(old_blob);
+ if (lock_snap_rwsem)
+ up_read(&mdsc->snap_rwsem);
+ err = -EACCES;
+ goto out;
+ }
+ if (qstate != CEPH_Q_CLEAR) {
+ ceph_buffer_put(old_blob);
+ old_blob = NULL;
+ goto do_sync_unlocked;
+ }
+ checked_quarantine = true;
+ spin_lock(&ci->i_ceph_lock);
+ goto retry;
+ }
+
err = __set_xattr(ci, newname, name_len, newval, val_len,
flags, value ? 1 : -1, &xattr);
^ permalink raw reply related [flat|nested] 8+ messages in thread