Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...
This commit is contained in:
Linus Torvalds
2019-07-18 14:32:33 -07:00
56 changed files with 1838 additions and 877 deletions

View File

@@ -181,18 +181,6 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event,
), \
TP_ARGS(task, mr, nsegs))
TRACE_DEFINE_ENUM(FRWR_IS_INVALID);
TRACE_DEFINE_ENUM(FRWR_IS_VALID);
TRACE_DEFINE_ENUM(FRWR_FLUSHED_FR);
TRACE_DEFINE_ENUM(FRWR_FLUSHED_LI);
#define xprtrdma_show_frwr_state(x) \
__print_symbolic(x, \
{ FRWR_IS_INVALID, "INVALID" }, \
{ FRWR_IS_VALID, "VALID" }, \
{ FRWR_FLUSHED_FR, "FLUSHED_FR" }, \
{ FRWR_FLUSHED_LI, "FLUSHED_LI" })
DECLARE_EVENT_CLASS(xprtrdma_frwr_done,
TP_PROTO(
const struct ib_wc *wc,
@@ -203,22 +191,19 @@ DECLARE_EVENT_CLASS(xprtrdma_frwr_done,
TP_STRUCT__entry(
__field(const void *, mr)
__field(unsigned int, state)
__field(unsigned int, status)
__field(unsigned int, vendor_err)
),
TP_fast_assign(
__entry->mr = container_of(frwr, struct rpcrdma_mr, frwr);
__entry->state = frwr->fr_state;
__entry->status = wc->status;
__entry->vendor_err = __entry->status ? wc->vendor_err : 0;
),
TP_printk(
"mr=%p state=%s: %s (%u/0x%x)",
__entry->mr, xprtrdma_show_frwr_state(__entry->state),
rdma_show_wc_status(__entry->status),
"mr=%p: %s (%u/0x%x)",
__entry->mr, rdma_show_wc_status(__entry->status),
__entry->status, __entry->vendor_err
)
);
@@ -390,6 +375,37 @@ DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc);
DEFINE_RXPRT_EVENT(xprtrdma_op_close);
DEFINE_RXPRT_EVENT(xprtrdma_op_connect);
TRACE_EVENT(xprtrdma_op_set_cto,
TP_PROTO(
const struct rpcrdma_xprt *r_xprt,
unsigned long connect,
unsigned long reconnect
),
TP_ARGS(r_xprt, connect, reconnect),
TP_STRUCT__entry(
__field(const void *, r_xprt)
__field(unsigned long, connect)
__field(unsigned long, reconnect)
__string(addr, rpcrdma_addrstr(r_xprt))
__string(port, rpcrdma_portstr(r_xprt))
),
TP_fast_assign(
__entry->r_xprt = r_xprt;
__entry->connect = connect;
__entry->reconnect = reconnect;
__assign_str(addr, rpcrdma_addrstr(r_xprt));
__assign_str(port, rpcrdma_portstr(r_xprt));
),
TP_printk("peer=[%s]:%s r_xprt=%p: connect=%lu reconnect=%lu",
__get_str(addr), __get_str(port), __entry->r_xprt,
__entry->connect / HZ, __entry->reconnect / HZ
)
);
TRACE_EVENT(xprtrdma_qp_event,
TP_PROTO(
const struct rpcrdma_xprt *r_xprt,
@@ -470,13 +486,12 @@ TRACE_DEFINE_ENUM(rpcrdma_replych);
TRACE_EVENT(xprtrdma_marshal,
TP_PROTO(
const struct rpc_rqst *rqst,
unsigned int hdrlen,
const struct rpcrdma_req *req,
unsigned int rtype,
unsigned int wtype
),
TP_ARGS(rqst, hdrlen, rtype, wtype),
TP_ARGS(req, rtype, wtype),
TP_STRUCT__entry(
__field(unsigned int, task_id)
@@ -491,10 +506,12 @@ TRACE_EVENT(xprtrdma_marshal,
),
TP_fast_assign(
const struct rpc_rqst *rqst = &req->rl_slot;
__entry->task_id = rqst->rq_task->tk_pid;
__entry->client_id = rqst->rq_task->tk_client->cl_clid;
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->hdrlen = hdrlen;
__entry->hdrlen = req->rl_hdrbuf.len;
__entry->headlen = rqst->rq_snd_buf.head[0].iov_len;
__entry->pagelen = rqst->rq_snd_buf.page_len;
__entry->taillen = rqst->rq_snd_buf.tail[0].iov_len;
@@ -538,6 +555,33 @@ TRACE_EVENT(xprtrdma_marshal_failed,
)
);
TRACE_EVENT(xprtrdma_prepsend_failed,
TP_PROTO(const struct rpc_rqst *rqst,
int ret
),
TP_ARGS(rqst, ret),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(u32, xid)
__field(int, ret)
),
TP_fast_assign(
__entry->task_id = rqst->rq_task->tk_pid;
__entry->client_id = rqst->rq_task->tk_client->cl_clid;
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->ret = ret;
),
TP_printk("task:%u@%u xid=0x%08x: ret=%d",
__entry->task_id, __entry->client_id, __entry->xid,
__entry->ret
)
);
TRACE_EVENT(xprtrdma_post_send,
TP_PROTO(
const struct rpcrdma_req *req,
@@ -559,7 +603,8 @@ TRACE_EVENT(xprtrdma_post_send,
const struct rpc_rqst *rqst = &req->rl_slot;
__entry->task_id = rqst->rq_task->tk_pid;
__entry->client_id = rqst->rq_task->tk_client->cl_clid;
__entry->client_id = rqst->rq_task->tk_client ?
rqst->rq_task->tk_client->cl_clid : -1;
__entry->req = req;
__entry->num_sge = req->rl_sendctx->sc_wr.num_sge;
__entry->signaled = req->rl_sendctx->sc_wr.send_flags &
@@ -698,6 +743,7 @@ TRACE_EVENT(xprtrdma_wc_receive,
DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_fastreg);
DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li);
DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_wake);
DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_done);
TRACE_EVENT(xprtrdma_frwr_alloc,
TP_PROTO(