summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfs4callback.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-11-26 23:59:30 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2024-11-26 23:59:30 +0300
commit445d9f05fa149556422f7fdd52dacf487cc8e7be (patch)
treec43d557635654a4a629e759c6301dc9868b2efbf /fs/nfsd/nfs4callback.c
parent44b4d13b70f682a86fee356786cc3e17987fae4d (diff)
parent583772eec7b0096516a8ee8b1cc31401894f1e3a (diff)
downloadlinux-445d9f05fa149556422f7fdd52dacf487cc8e7be.tar.xz
Merge tag 'nfsd-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull nfsd updates from Chuck Lever: "Jeff Layton contributed a scalability improvement to NFSD's NFSv4 backchannel session implementation. This improvement is intended to increase the rate at which NFSD can safely recall NFSv4 delegations from clients, to avoid the need to revoke them. Revoking requires a slow state recovery process. A wide variety of bug fixes and other incremental improvements make up the bulk of commits in this series. As always I am grateful to the NFSD contributors, reviewers, testers, and bug reporters who participated during this cycle" * tag 'nfsd-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux: (72 commits) nfsd: allow for up to 32 callback session slots nfs_common: must not hold RCU while calling nfsd_file_put_local nfsd: get rid of include ../internal.h nfsd: fix nfs4_openowner leak when concurrent nfsd4_open occur NFSD: Add nfsd4_copy time-to-live NFSD: Add a laundromat reaper for async copy state NFSD: Block DESTROY_CLIENTID only when there are ongoing async COPY operations NFSD: Handle an NFS4ERR_DELAY response to CB_OFFLOAD NFSD: Free async copy information in nfsd4_cb_offload_release() NFSD: Fix nfsd4_shutdown_copy() NFSD: Add a tracepoint to record canceled async COPY operations nfsd: make nfsd4_session->se_flags a bool nfsd: remove nfsd4_session->se_bchannel nfsd: make use of warning provided by refcount_t nfsd: Don't fail OP_SETCLIENTID when there are too many clients. svcrdma: fix miss destroy percpu_counter in svc_rdma_proc_init() xdrgen: Remove program_stat_to_errno() call sites xdrgen: Update the files included in client-side source code xdrgen: Remove check for "nfs_ok" in C templates xdrgen: Remove tracepoint call site ...
Diffstat (limited to 'fs/nfsd/nfs4callback.c')
-rw-r--r--fs/nfsd/nfs4callback.c139
1 files changed, 101 insertions, 38 deletions
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index b5b3ab9d719a..3877b53e429f 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -287,17 +287,17 @@ static int decode_cb_compound4res(struct xdr_stream *xdr,
u32 length;
__be32 *p;
- p = xdr_inline_decode(xdr, 4 + 4);
+ p = xdr_inline_decode(xdr, XDR_UNIT);
if (unlikely(p == NULL))
goto out_overflow;
- hdr->status = be32_to_cpup(p++);
+ hdr->status = be32_to_cpup(p);
/* Ignore the tag */
- length = be32_to_cpup(p++);
- p = xdr_inline_decode(xdr, length + 4);
- if (unlikely(p == NULL))
+ if (xdr_stream_decode_u32(xdr, &length) < 0)
+ goto out_overflow;
+ if (xdr_inline_decode(xdr, length) == NULL)
+ goto out_overflow;
+ if (xdr_stream_decode_u32(xdr, &hdr->nops) < 0)
goto out_overflow;
- p += XDR_QUADLEN(length);
- hdr->nops = be32_to_cpup(p);
return 0;
out_overflow:
return -EIO;
@@ -364,13 +364,29 @@ encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
struct nfs4_delegation *dp =
container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
+ u32 bmap[1];
+
+ bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
encode_nfs_fh4(xdr, fh);
- encode_bitmap4(xdr, fattr->ncf_cb_bmap, ARRAY_SIZE(fattr->ncf_cb_bmap));
+ encode_bitmap4(xdr, bmap, ARRAY_SIZE(bmap));
hdr->nops++;
}
+static u32 highest_slotid(struct nfsd4_session *ses)
+{
+ u32 idx;
+
+ spin_lock(&ses->se_lock);
+ idx = fls(~ses->se_cb_slot_avail);
+ if (idx > 0)
+ --idx;
+ idx = max(idx, ses->se_cb_highest_slot);
+ spin_unlock(&ses->se_lock);
+ return idx;
+}
+
/*
* CB_SEQUENCE4args
*
@@ -397,15 +413,40 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr,
encode_sessionid4(xdr, session);
p = xdr_reserve_space(xdr, 4 + 4 + 4 + 4 + 4);
- *p++ = cpu_to_be32(session->se_cb_seq_nr); /* csa_sequenceid */
- *p++ = xdr_zero; /* csa_slotid */
- *p++ = xdr_zero; /* csa_highest_slotid */
+ *p++ = cpu_to_be32(session->se_cb_seq_nr[cb->cb_held_slot]); /* csa_sequenceid */
+ *p++ = cpu_to_be32(cb->cb_held_slot); /* csa_slotid */
+ *p++ = cpu_to_be32(highest_slotid(session)); /* csa_highest_slotid */
*p++ = xdr_zero; /* csa_cachethis */
xdr_encode_empty_array(p); /* csa_referring_call_lists */
hdr->nops++;
}
+static void update_cb_slot_table(struct nfsd4_session *ses, u32 target)
+{
+ /* No need to do anything if nothing changed */
+ if (likely(target == READ_ONCE(ses->se_cb_highest_slot)))
+ return;
+
+ spin_lock(&ses->se_lock);
+ if (target > ses->se_cb_highest_slot) {
+ int i;
+
+ target = min(target, NFSD_BC_SLOT_TABLE_SIZE - 1);
+
+ /*
+ * Growing the slot table. Reset any new sequences to 1.
+ *
+ * NB: There is some debate about whether the RFC requires this,
+ * but the Linux client expects it.
+ */
+ for (i = ses->se_cb_highest_slot + 1; i <= target; ++i)
+ ses->se_cb_seq_nr[i] = 1;
+ }
+ ses->se_cb_highest_slot = target;
+ spin_unlock(&ses->se_lock);
+}
+
/*
* CB_SEQUENCE4resok
*
@@ -433,7 +474,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
int status = -ESERVERFAULT;
__be32 *p;
- u32 dummy;
+ u32 seqid, slotid, target;
/*
* If the server returns different values for sessionID, slotID or
@@ -449,21 +490,22 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
}
p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN);
- dummy = be32_to_cpup(p++);
- if (dummy != session->se_cb_seq_nr) {
+ seqid = be32_to_cpup(p++);
+ if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) {
dprintk("NFS: %s Invalid sequence number\n", __func__);
goto out;
}
- dummy = be32_to_cpup(p++);
- if (dummy != 0) {
+ slotid = be32_to_cpup(p++);
+ if (slotid != cb->cb_held_slot) {
dprintk("NFS: %s Invalid slotid\n", __func__);
goto out;
}
- /*
- * FIXME: process highest slotid and target highest slotid
- */
+ p++; // ignore current highest slot value
+
+ target = be32_to_cpup(p++);
+ update_cb_slot_table(session, target);
status = 0;
out:
cb->cb_seq_status = status;
@@ -1164,6 +1206,22 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
spin_unlock(&clp->cl_lock);
}
+static int grab_slot(struct nfsd4_session *ses)
+{
+ int idx;
+
+ spin_lock(&ses->se_lock);
+ idx = ffs(ses->se_cb_slot_avail) - 1;
+ if (idx < 0 || idx > ses->se_cb_highest_slot) {
+ spin_unlock(&ses->se_lock);
+ return -1;
+ }
+ /* clear the bit for the slot */
+ ses->se_cb_slot_avail &= ~BIT(idx);
+ spin_unlock(&ses->se_lock);
+ return idx;
+}
+
/*
* There's currently a single callback channel slot.
* If the slot is available, then mark it busy. Otherwise, set the
@@ -1172,28 +1230,32 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn)
static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task)
{
struct nfs4_client *clp = cb->cb_clp;
+ struct nfsd4_session *ses = clp->cl_cb_session;
- if (!cb->cb_holds_slot &&
- test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+ if (cb->cb_held_slot >= 0)
+ return true;
+ cb->cb_held_slot = grab_slot(ses);
+ if (cb->cb_held_slot < 0) {
rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
/* Race breaker */
- if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
- dprintk("%s slot is busy\n", __func__);
+ cb->cb_held_slot = grab_slot(ses);
+ if (cb->cb_held_slot < 0)
return false;
- }
rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
}
- cb->cb_holds_slot = true;
return true;
}
static void nfsd41_cb_release_slot(struct nfsd4_callback *cb)
{
struct nfs4_client *clp = cb->cb_clp;
+ struct nfsd4_session *ses = clp->cl_cb_session;
- if (cb->cb_holds_slot) {
- cb->cb_holds_slot = false;
- clear_bit(0, &clp->cl_cb_slot_busy);
+ if (cb->cb_held_slot >= 0) {
+ spin_lock(&ses->se_lock);
+ ses->se_cb_slot_avail |= BIT(cb->cb_held_slot);
+ spin_unlock(&ses->se_lock);
+ cb->cb_held_slot = -1;
rpc_wake_up_next(&clp->cl_cb_waitq);
}
}
@@ -1210,8 +1272,8 @@ static void nfsd41_destroy_cb(struct nfsd4_callback *cb)
}
/*
- * TODO: cb_sequence should support referring call lists, cachethis, multiple
- * slots, and mark callback channel down on communication errors.
+ * TODO: cb_sequence should support referring call lists, cachethis,
+ * and mark callback channel down on communication errors.
*/
static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
{
@@ -1253,7 +1315,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
return true;
}
- if (!cb->cb_holds_slot)
+ if (cb->cb_held_slot < 0)
goto need_restart;
/* This is the operation status code for CB_SEQUENCE */
@@ -1267,10 +1329,10 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
* If CB_SEQUENCE returns an error, then the state of the slot
* (sequence ID, cached reply) MUST NOT change.
*/
- ++session->se_cb_seq_nr;
+ ++session->se_cb_seq_nr[cb->cb_held_slot];
break;
case -ESERVERFAULT:
- ++session->se_cb_seq_nr;
+ ++session->se_cb_seq_nr[cb->cb_held_slot];
nfsd4_mark_cb_fault(cb->cb_clp);
ret = false;
break;
@@ -1296,17 +1358,16 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
case -NFS4ERR_BADSLOT:
goto retry_nowait;
case -NFS4ERR_SEQ_MISORDERED:
- if (session->se_cb_seq_nr != 1) {
- session->se_cb_seq_nr = 1;
+ if (session->se_cb_seq_nr[cb->cb_held_slot] != 1) {
+ session->se_cb_seq_nr[cb->cb_held_slot] = 1;
goto retry_nowait;
}
break;
default:
nfsd4_mark_cb_fault(cb->cb_clp);
}
- nfsd41_cb_release_slot(cb);
-
trace_nfsd_cb_free_slot(task, cb);
+ nfsd41_cb_release_slot(cb);
if (RPC_SIGNALLED(task))
goto need_restart;
@@ -1461,6 +1522,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
ses = c->cn_session;
}
spin_unlock(&clp->cl_lock);
+ if (!c)
+ return;
err = setup_callback_client(clp, &conn, ses);
if (err) {
@@ -1524,7 +1587,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
cb->cb_status = 0;
cb->cb_need_restart = false;
- cb->cb_holds_slot = false;
+ cb->cb_held_slot = -1;
}
/**