summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/smb/client/cifsfs.c2
-rw-r--r--fs/smb/client/cifsproto.h2
-rw-r--r--fs/smb/client/connect.c46
-rw-r--r--fs/smb/client/dfs_cache.c55
-rw-r--r--fs/smb/client/smb2ops.c3
-rw-r--r--fs/smb/server/transport_ipc.c8
-rw-r--r--fs/smb/server/transport_rdma.c47
-rw-r--r--fs/xfs/libxfs/xfs_rtgroup.h6
-rw-r--r--fs/xfs/xfs_zone_alloc.c8
-rw-r--r--fs/xfs/xfs_zone_gc.c27
10 files changed, 155 insertions, 49 deletions
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 4f959f1e08d2..185ac41bd7e9 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -173,7 +173,7 @@ module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
module_param(enable_gcm_256, bool, 0644);
-MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0");
+MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/1");
module_param(require_gcm_256, bool, 0644);
MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0");
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index fb1813cbe0eb..3528c365a452 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -616,6 +616,8 @@ extern int E_md4hash(const unsigned char *passwd, unsigned char *p16,
extern struct TCP_Server_Info *
cifs_find_tcp_session(struct smb3_fs_context *ctx);
+struct cifs_tcon *cifs_setup_ipc(struct cifs_ses *ses, bool seal);
+
void __cifs_put_smb_ses(struct cifs_ses *ses);
extern struct cifs_ses *
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index dd12f3eb61dc..55cb4b0cbd48 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -310,6 +310,8 @@ cifs_abort_connection(struct TCP_Server_Info *server)
server->ssocket->flags);
sock_release(server->ssocket);
server->ssocket = NULL;
+ } else if (cifs_rdma_enabled(server)) {
+ smbd_destroy(server);
}
server->sequence_number = 0;
server->session_estab = false;
@@ -338,12 +340,6 @@ cifs_abort_connection(struct TCP_Server_Info *server)
mid_execute_callback(mid);
release_mid(mid);
}
-
- if (cifs_rdma_enabled(server)) {
- cifs_server_lock(server);
- smbd_destroy(server);
- cifs_server_unlock(server);
- }
}
static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets)
@@ -2015,39 +2011,31 @@ static int match_session(struct cifs_ses *ses,
/**
* cifs_setup_ipc - helper to setup the IPC tcon for the session
* @ses: smb session to issue the request on
- * @ctx: the superblock configuration context to use for building the
- * new tree connection for the IPC (interprocess communication RPC)
+ * @seal: if encryption is requested
*
* A new IPC connection is made and stored in the session
* tcon_ipc. The IPC tcon has the same lifetime as the session.
*/
-static int
-cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
+struct cifs_tcon *cifs_setup_ipc(struct cifs_ses *ses, bool seal)
{
int rc = 0, xid;
struct cifs_tcon *tcon;
char unc[SERVER_NAME_LENGTH + sizeof("//x/IPC$")] = {0};
- bool seal = false;
struct TCP_Server_Info *server = ses->server;
/*
* If the mount request that resulted in the creation of the
* session requires encryption, force IPC to be encrypted too.
*/
- if (ctx->seal) {
- if (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)
- seal = true;
- else {
- cifs_server_dbg(VFS,
- "IPC: server doesn't support encryption\n");
- return -EOPNOTSUPP;
- }
+ if (seal && !(server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)) {
+ cifs_server_dbg(VFS, "IPC: server doesn't support encryption\n");
+ return ERR_PTR(-EOPNOTSUPP);
}
/* no need to setup directory caching on IPC share, so pass in false */
tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_ipc);
if (tcon == NULL)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
spin_lock(&server->srv_lock);
scnprintf(unc, sizeof(unc), "\\\\%s\\IPC$", server->hostname);
@@ -2057,13 +2045,13 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
tcon->ses = ses;
tcon->ipc = true;
tcon->seal = seal;
- rc = server->ops->tree_connect(xid, ses, unc, tcon, ctx->local_nls);
+ rc = server->ops->tree_connect(xid, ses, unc, tcon, ses->local_nls);
free_xid(xid);
if (rc) {
- cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc);
+ cifs_server_dbg(VFS | ONCE, "failed to connect to IPC (rc=%d)\n", rc);
tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail);
- goto out;
+ return ERR_PTR(rc);
}
cifs_dbg(FYI, "IPC tcon rc=%d ipc tid=0x%x\n", rc, tcon->tid);
@@ -2071,9 +2059,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx)
spin_lock(&tcon->tc_lock);
tcon->status = TID_GOOD;
spin_unlock(&tcon->tc_lock);
- ses->tcon_ipc = tcon;
-out:
- return rc;
+ return tcon;
}
static struct cifs_ses *
@@ -2347,6 +2333,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
{
struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr;
struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr;
+ struct cifs_tcon *ipc;
struct cifs_ses *ses;
unsigned int xid;
int retries = 0;
@@ -2525,7 +2512,12 @@ retry_new_session:
list_add(&ses->smb_ses_list, &server->smb_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
- cifs_setup_ipc(ses, ctx);
+ ipc = cifs_setup_ipc(ses, ctx->seal);
+ spin_lock(&cifs_tcp_ses_lock);
+ spin_lock(&ses->ses_lock);
+ ses->tcon_ipc = !IS_ERR(ipc) ? ipc : NULL;
+ spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
free_xid(xid);
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 4dada26d56b5..f2ad0ccd08a7 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1120,24 +1120,63 @@ static bool target_share_equal(struct cifs_tcon *tcon, const char *s1)
return match;
}
-static bool is_ses_good(struct cifs_ses *ses)
+static bool is_ses_good(struct cifs_tcon *tcon, struct cifs_ses *ses)
{
struct TCP_Server_Info *server = ses->server;
- struct cifs_tcon *tcon = ses->tcon_ipc;
+ struct cifs_tcon *ipc = NULL;
bool ret;
+ spin_lock(&cifs_tcp_ses_lock);
spin_lock(&ses->ses_lock);
spin_lock(&ses->chan_lock);
+
ret = !cifs_chan_needs_reconnect(ses, server) &&
- ses->ses_status == SES_GOOD &&
- !tcon->need_reconnect;
+ ses->ses_status == SES_GOOD;
+
spin_unlock(&ses->chan_lock);
+
+ if (!ret)
+ goto out;
+
+ if (likely(ses->tcon_ipc)) {
+ if (ses->tcon_ipc->need_reconnect) {
+ ret = false;
+ goto out;
+ }
+ } else {
+ spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ ipc = cifs_setup_ipc(ses, tcon->seal);
+
+ spin_lock(&cifs_tcp_ses_lock);
+ spin_lock(&ses->ses_lock);
+ if (!IS_ERR(ipc)) {
+ if (!ses->tcon_ipc) {
+ ses->tcon_ipc = ipc;
+ ipc = NULL;
+ }
+ } else {
+ ret = false;
+ ipc = NULL;
+ }
+ }
+
+out:
spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ if (ipc && server->ops->tree_disconnect) {
+ unsigned int xid = get_xid();
+
+ (void)server->ops->tree_disconnect(xid, ipc);
+ _free_xid(xid);
+ }
+ tconInfoFree(ipc, netfs_trace_tcon_ref_free_ipc);
return ret;
}
/* Refresh dfs referral of @ses */
-static void refresh_ses_referral(struct cifs_ses *ses)
+static void refresh_ses_referral(struct cifs_tcon *tcon, struct cifs_ses *ses)
{
struct cache_entry *ce;
unsigned int xid;
@@ -1153,7 +1192,7 @@ static void refresh_ses_referral(struct cifs_ses *ses)
}
ses = CIFS_DFS_ROOT_SES(ses);
- if (!is_ses_good(ses)) {
+ if (!is_ses_good(tcon, ses)) {
cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n",
__func__);
goto out;
@@ -1241,7 +1280,7 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh)
up_read(&htable_rw_lock);
ses = CIFS_DFS_ROOT_SES(ses);
- if (!is_ses_good(ses)) {
+ if (!is_ses_good(tcon, ses)) {
cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n",
__func__);
goto out;
@@ -1309,7 +1348,7 @@ void dfs_cache_refresh(struct work_struct *work)
tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work);
list_for_each_entry(ses, &tcon->dfs_ses_list, dlist)
- refresh_ses_referral(ses);
+ refresh_ses_referral(tcon, ses);
refresh_tcon_referral(tcon, false);
queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 0f9130ef2e7d..1e39f2165e42 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2799,11 +2799,12 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid fid;
int rc;
__le16 *utf16_path;
- struct cached_fid *cfid = NULL;
+ struct cached_fid *cfid;
int retries = 0, cur_sleep = 1;
replay_again:
/* reinitialize for possible replay */
+ cfid = NULL;
flags = CIFS_CP_CREATE_CLOSE_OP;
oplock = SMB2_OPLOCK_LEVEL_NONE;
server = cifs_pick_channel(ses);
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 46f87fd1ce1c..2c08cccfa680 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -263,10 +263,16 @@ static void ipc_msg_handle_free(int handle)
static int handle_response(int type, void *payload, size_t sz)
{
- unsigned int handle = *(unsigned int *)payload;
+ unsigned int handle;
struct ipc_msg_table_entry *entry;
int ret = 0;
+ /* Prevent 4-byte read beyond declared payload size */
+ if (sz < sizeof(unsigned int))
+ return -EINVAL;
+
+ handle = *(unsigned int *)payload;
+
ipc_update_last_active();
down_read(&ipc_msg_table_lock);
hash_for_each_possible(ipc_msg_table, entry, ipc_table_hlist, handle) {
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 89b02efdba0c..7d86553fcc7c 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -418,9 +418,6 @@ static struct smb_direct_transport *alloc_transport(struct rdma_cm_id *cm_id)
sc->ib.dev = sc->rdma.cm_id->device;
- INIT_WORK(&sc->recv_io.posted.refill_work,
- smb_direct_post_recv_credits);
- INIT_WORK(&sc->idle.immediate_work, smb_direct_send_immediate_work);
INIT_DELAYED_WORK(&sc->idle.timer_work, smb_direct_idle_connection_timer);
conn = ksmbd_conn_alloc();
@@ -469,6 +466,9 @@ static void free_transport(struct smb_direct_transport *t)
disable_delayed_work_sync(&sc->idle.timer_work);
disable_work_sync(&sc->idle.immediate_work);
+ if (sc->rdma.cm_id)
+ rdma_lock_handler(sc->rdma.cm_id);
+
if (sc->ib.qp) {
ib_drain_qp(sc->ib.qp);
sc->ib.qp = NULL;
@@ -497,8 +497,10 @@ static void free_transport(struct smb_direct_transport *t)
ib_free_cq(sc->ib.recv_cq);
if (sc->ib.pd)
ib_dealloc_pd(sc->ib.pd);
- if (sc->rdma.cm_id)
+ if (sc->rdma.cm_id) {
+ rdma_unlock_handler(sc->rdma.cm_id);
rdma_destroy_id(sc->rdma.cm_id);
+ }
smb_direct_destroy_pools(sc);
ksmbd_conn_free(KSMBD_TRANS(t)->conn);
@@ -1727,10 +1729,10 @@ static int smb_direct_cm_handler(struct rdma_cm_id *cm_id,
}
case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_DISCONNECTED: {
- ib_drain_qp(sc->ib.qp);
-
sc->status = SMBDIRECT_SOCKET_DISCONNECTED;
smb_direct_disconnect_rdma_work(&sc->disconnect_work);
+ if (sc->ib.qp)
+ ib_drain_qp(sc->ib.qp);
break;
}
case RDMA_CM_EVENT_CONNECT_ERROR: {
@@ -1904,7 +1906,6 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc)
goto out_err;
}
- smb_direct_post_recv_credits(&sc->recv_io.posted.refill_work);
return 0;
out_err:
put_recvmsg(sc, recvmsg);
@@ -2249,8 +2250,8 @@ static int smb_direct_prepare(struct ksmbd_transport *t)
return -ECONNABORTED;
ret = smb_direct_check_recvmsg(recvmsg);
- if (ret == -ECONNABORTED)
- goto out;
+ if (ret)
+ goto put;
req = (struct smbdirect_negotiate_req *)recvmsg->packet;
sp->max_recv_size = min_t(int, sp->max_recv_size,
@@ -2265,14 +2266,38 @@ static int smb_direct_prepare(struct ksmbd_transport *t)
sc->recv_io.credits.target = min_t(u16, sc->recv_io.credits.target, sp->recv_credit_max);
sc->recv_io.credits.target = max_t(u16, sc->recv_io.credits.target, 1);
- ret = smb_direct_send_negotiate_response(sc, ret);
-out:
+put:
spin_lock_irqsave(&sc->recv_io.reassembly.lock, flags);
sc->recv_io.reassembly.queue_length--;
list_del(&recvmsg->list);
spin_unlock_irqrestore(&sc->recv_io.reassembly.lock, flags);
put_recvmsg(sc, recvmsg);
+ if (ret == -ECONNABORTED)
+ return ret;
+
+ if (ret)
+ goto respond;
+
+ /*
+ * We negotiated with success, so we need to refill the recv queue.
+ * We do that with sc->idle.immediate_work still being disabled
+ * via smbdirect_socket_init(), so that queue_work(sc->workqueue,
+ * &sc->idle.immediate_work) in smb_direct_post_recv_credits()
+ * is a no-op.
+ *
+ * The message that grants the credits to the client is
+ * the negotiate response.
+ */
+ INIT_WORK(&sc->recv_io.posted.refill_work, smb_direct_post_recv_credits);
+ smb_direct_post_recv_credits(&sc->recv_io.posted.refill_work);
+ if (unlikely(sc->first_error))
+ return sc->first_error;
+ INIT_WORK(&sc->idle.immediate_work, smb_direct_send_immediate_work);
+
+respond:
+ ret = smb_direct_send_negotiate_response(sc, ret);
+
return ret;
}
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index d36a6ae0abe5..d4fcf591e63d 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -50,6 +50,12 @@ struct xfs_rtgroup {
uint8_t *rtg_rsum_cache;
struct xfs_open_zone *rtg_open_zone;
};
+
+ /*
+ * Count of outstanding GC operations for zoned XFS. Any RTG with a
+ * non-zero rtg_gccount will not be picked as new GC victim.
+ */
+ atomic_t rtg_gccount;
};
/*
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 23cdab4515bb..040402240807 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -246,6 +246,14 @@ xfs_zoned_map_extent(
* If a data write raced with this GC write, keep the existing data in
* the data fork, mark our newly written GC extent as reclaimable, then
* move on to the next extent.
+ *
+ * Note that this can also happen when racing with operations that do
+ * not actually invalidate the data, but just move it to a different
+ * inode (XFS_IOC_EXCHANGE_RANGE), or to a different offset inside the
+ * inode (FALLOC_FL_COLLAPSE_RANGE / FALLOC_FL_INSERT_RANGE). If the
+ * data was just moved around, GC fails to free the zone, but the zone
+ * becomes a GC candidate again as soon as all previous GC I/O has
+ * finished and these blocks will be moved out eventually.
*/
if (old_startblock != NULLFSBLOCK &&
old_startblock != data.br_startblock)
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 109877d9a6bf..4ade54445532 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -114,6 +114,8 @@ struct xfs_gc_bio {
/* Open Zone being written to */
struct xfs_open_zone *oz;
+ struct xfs_rtgroup *victim_rtg;
+
/* Bio used for reads and writes, including the bvec used by it */
struct bio_vec bv;
struct bio bio; /* must be last */
@@ -264,6 +266,7 @@ xfs_zone_gc_iter_init(
iter->rec_count = 0;
iter->rec_idx = 0;
iter->victim_rtg = victim_rtg;
+ atomic_inc(&victim_rtg->rtg_gccount);
}
/*
@@ -362,6 +365,7 @@ xfs_zone_gc_query(
return 0;
done:
+ atomic_dec(&iter->victim_rtg->rtg_gccount);
xfs_rtgroup_rele(iter->victim_rtg);
iter->victim_rtg = NULL;
return 0;
@@ -451,6 +455,20 @@ xfs_zone_gc_pick_victim_from(
if (!rtg)
continue;
+ /*
+ * If the zone is already undergoing GC, don't pick it again.
+ *
+ * This prevents us from picking one of the zones for which we
+ * already submitted GC I/O, but for which the remapping hasn't
+ * concluded yet. This won't cause data corruption, but
+ * increases write amplification and slows down GC, so this is
+ * a bad thing.
+ */
+ if (atomic_read(&rtg->rtg_gccount)) {
+ xfs_rtgroup_rele(rtg);
+ continue;
+ }
+
/* skip zones that are just waiting for a reset */
if (rtg_rmap(rtg)->i_used_blocks == 0 ||
rtg_rmap(rtg)->i_used_blocks >= victim_used) {
@@ -688,6 +706,9 @@ xfs_zone_gc_start_chunk(
chunk->scratch = &data->scratch[data->scratch_idx];
chunk->data = data;
chunk->oz = oz;
+ chunk->victim_rtg = iter->victim_rtg;
+ atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+ atomic_inc(&chunk->victim_rtg->rtg_gccount);
bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock);
bio->bi_end_io = xfs_zone_gc_end_io;
@@ -710,6 +731,8 @@ static void
xfs_zone_gc_free_chunk(
struct xfs_gc_bio *chunk)
{
+ atomic_dec(&chunk->victim_rtg->rtg_gccount);
+ xfs_rtgroup_rele(chunk->victim_rtg);
list_del(&chunk->entry);
xfs_open_zone_put(chunk->oz);
xfs_irele(chunk->ip);
@@ -770,6 +793,10 @@ xfs_zone_gc_split_write(
split_chunk->oz = chunk->oz;
atomic_inc(&chunk->oz->oz_ref);
+ split_chunk->victim_rtg = chunk->victim_rtg;
+ atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref);
+ atomic_inc(&chunk->victim_rtg->rtg_gccount);
+
chunk->offset += split_len;
chunk->len -= split_len;
chunk->old_startblock += XFS_B_TO_FSB(data->mp, split_len);
generated by cgit (git 2.34.1) at 2025-11-02 09:40:34 +0000