Merge tag 'nfs-for-4.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Highlights include:

  Stable bugfixes:
   - NFSv4: Fix memory and state leak in _nfs4_open_and_get_state
   - xprtrdma: Fix Read chunk padding
   - xprtrdma: Per-connection pad optimization
   - xprtrdma: Disable pad optimization by default
   - xprtrdma: Reduce required number of send SGEs
   - nlm: Ensure callback code also checks that the files match
   - pNFS/flexfiles: If the layout is invalid, it must be updated before
     retrying
   - NFSv4: Fix reboot recovery in copy offload
   - Revert "NFSv4.1: Handle NFS4ERR_BADSESSION/NFS4ERR_DEADSESSION
     replies to OP_SEQUENCE"
   - NFSv4: fix getacl head length estimation
   - NFSv4: fix getacl ERANGE for sum ACL buffer sizes

  Features:
   - Add and use dprintk_cont macros
   - Various cleanups to NFS v4.x to reduce code duplication and
     complexity
   - Remove unused cr_magic related code
   - Improvements to sunrpc "read from buffer" code
   - Clean up sunrpc timeout code and allow changing TCP timeout
     parameters
   - Remove duplicate mw_list management code in xprtrdma
   - Add generic functions for encoding and decoding xdr streams

  Bugfixes:
   - Clean up nfs_show_mountd_netid
   - Make layoutreturn_ops static and use NULL instead of 0 to fix
     sparse warnings
   - Properly handle -ERESTARTSYS in nfs_rename()
   - Check if register_shrinker() failed during rpcauth_init()
   - Properly clean up procfs/pipefs entries
   - Various NFS over RDMA related fixes
   - Silence unititialized variable warning in sunrpc"

* tag 'nfs-for-4.11-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (64 commits)
  NFSv4: fix getacl ERANGE for some ACL buffer sizes
  NFSv4: fix getacl head length estimation
  Revert "NFSv4.1: Handle NFS4ERR_BADSESSION/NFS4ERR_DEADSESSION replies to OP_SEQUENCE"
  NFSv4: Fix reboot recovery in copy offload
  pNFS/flexfiles: If the layout is invalid, it must be updated before retrying
  NFSv4: Clean up owner/group attribute decode
  SUNRPC: Add a helper function xdr_stream_decode_string_dup()
  NFSv4: Remove bogus "struct nfs_client" argument from decode_ace()
  NFSv4: Fix the underestimation of delegation XDR space reservation
  NFSv4: Replace callback string decode function with a generic
  NFSv4: Replace the open coded decode_opaque_inline() with the new generic
  NFSv4: Replace ad-hoc xdr encode/decode helpers with xdr_stream_* generics
  SUNRPC: Add generic helpers for xdr_stream encode/decode
  sunrpc: silence uninitialized variable warning
  nlm: Ensure callback code also checks that the files match
  sunrpc: Allow xprt->ops->timer method to sleep
  xprtrdma: Refactor management of mw_list field
  xprtrdma: Handle stale connection rejection
  xprtrdma: Properly recover FRWRs with in-flight FASTREG WRs
  xprtrdma: Shrink send SGEs array
  ...
This commit is contained in:
Linus Torvalds
2017-03-01 16:10:30 -08:00
39 changed files with 901 additions and 831 deletions

View File

@@ -52,6 +52,8 @@
#include "sunrpc.h"
static void xs_close(struct rpc_xprt *xprt);
static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
struct socket *sock);
/*
* xprtsock tunables
@@ -666,6 +668,9 @@ static int xs_tcp_send_request(struct rpc_task *task)
if (task->tk_flags & RPC_TASK_SENT)
zerocopy = false;
if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state))
xs_tcp_set_socket_timeouts(xprt, transport->sock);
/* Continue transmitting the packet/record. We must be careful
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
@@ -1734,7 +1739,9 @@ static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t
*/
static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
{
spin_lock_bh(&xprt->transport_lock);
xprt_adjust_cwnd(xprt, task, -ETIMEDOUT);
spin_unlock_bh(&xprt->transport_lock);
}
static unsigned short xs_get_random_port(void)
@@ -2235,6 +2242,66 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
xs_reset_transport(transport);
}
static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
unsigned int keepidle;
unsigned int keepcnt;
unsigned int opt_on = 1;
unsigned int timeo;
spin_lock_bh(&xprt->transport_lock);
keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ);
keepcnt = xprt->timeout->to_retries + 1;
timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
(xprt->timeout->to_retries + 1);
clear_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
spin_unlock_bh(&xprt->transport_lock);
/* TCP Keepalive options */
kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
(char *)&opt_on, sizeof(opt_on));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
(char *)&keepidle, sizeof(keepidle));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
(char *)&keepidle, sizeof(keepidle));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
(char *)&keepcnt, sizeof(keepcnt));
/* TCP user timeout (see RFC5482) */
kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
(char *)&timeo, sizeof(timeo));
}
static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt,
unsigned long connect_timeout,
unsigned long reconnect_timeout)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct rpc_timeout to;
unsigned long initval;
spin_lock_bh(&xprt->transport_lock);
if (reconnect_timeout < xprt->max_reconnect_timeout)
xprt->max_reconnect_timeout = reconnect_timeout;
if (connect_timeout < xprt->connect_timeout) {
memcpy(&to, xprt->timeout, sizeof(to));
initval = DIV_ROUND_UP(connect_timeout, to.to_retries + 1);
/* Arbitrary lower limit */
if (initval < XS_TCP_INIT_REEST_TO << 1)
initval = XS_TCP_INIT_REEST_TO << 1;
to.to_initval = initval;
to.to_maxval = initval;
memcpy(&transport->tcp_timeout, &to,
sizeof(transport->tcp_timeout));
xprt->timeout = &transport->tcp_timeout;
xprt->connect_timeout = connect_timeout;
}
set_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state);
spin_unlock_bh(&xprt->transport_lock);
}
static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -2242,22 +2309,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
if (!transport->inet) {
struct sock *sk = sock->sk;
unsigned int keepidle = xprt->timeout->to_initval / HZ;
unsigned int keepcnt = xprt->timeout->to_retries + 1;
unsigned int opt_on = 1;
unsigned int timeo;
unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC;
/* TCP Keepalive options */
kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
(char *)&opt_on, sizeof(opt_on));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
(char *)&keepidle, sizeof(keepidle));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
(char *)&keepidle, sizeof(keepidle));
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
(char *)&keepcnt, sizeof(keepcnt));
/* Avoid temporary address, they are bad for long-lived
* connections such as NFS mounts.
* RFC4941, section 3.6 suggests that:
@@ -2268,11 +2321,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES,
(char *)&addr_pref, sizeof(addr_pref));
/* TCP user timeout (see RFC5482) */
timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
(xprt->timeout->to_retries + 1);
kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
(char *)&timeo, sizeof(timeo));
xs_tcp_set_socket_timeouts(xprt, sock);
write_lock_bh(&sk->sk_callback_lock);
@@ -2721,6 +2770,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
.set_retrans_timeout = xprt_set_retrans_timeout_def,
.close = xs_tcp_shutdown,
.destroy = xs_destroy,
.set_connect_timeout = xs_tcp_set_connect_timeout,
.print_stats = xs_tcp_print_stats,
.enable_swap = xs_enable_swap,
.disable_swap = xs_disable_swap,
@@ -3007,6 +3057,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
xprt->timeout = &xs_tcp_default_timeout;
xprt->max_reconnect_timeout = xprt->timeout->to_maxval;
xprt->connect_timeout = xprt->timeout->to_initval *
(xprt->timeout->to_retries + 1);
INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn);
INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket);
@@ -3209,7 +3261,9 @@ static int param_set_uint_minmax(const char *val,
if (!val)
return -EINVAL;
ret = kstrtouint(val, 0, &num);
if (ret == -EINVAL || num < min || num > max)
if (ret)
return ret;
if (num < min || num > max)
return -EINVAL;
*((unsigned int *)kp->arg) = num;
return 0;