linux/fs/nfs_common/grace.c

144 lines
3.4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Common code for control of lockd and nfsv4 grace periods.
*
* Transplanted from lockd code
*/
#include <linux/module.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <linux/fs.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 04:58:21 +03:00
static unsigned int grace_net_id;
static DEFINE_SPINLOCK(grace_lock);
/**
* locks_start_grace
* @net: net namespace that this lock manager belongs to
* @lm: who this grace period is for
*
* A grace period is a period during which locks should not be given
* out. Currently grace periods are only enforced by the two lock
* managers (lockd and nfsd), using the locks_in_grace() function to
* check when they are in a grace period.
*
* This function is called to start a grace period.
*/
void
locks_start_grace(struct net *net, struct lock_manager *lm)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
spin_lock(&grace_lock);
if (list_empty(&lm->list))
list_add(&lm->list, grace_list);
else
WARN(1, "double list_add attempt detected in net %x %s\n",
net->ns.inum, (net == &init_net) ? "(init_net)" : "");
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_start_grace);
/**
* locks_end_grace
* @lm: who this grace period is for
*
* Call this function to state that the given lock manager is ready to
* resume regular locking. The grace period will not end until all lock
* managers that called locks_start_grace() also call locks_end_grace().
* Note that callers count on it being safe to call this more than once,
* and the second call should be a no-op.
*/
void
locks_end_grace(struct lock_manager *lm)
{
spin_lock(&grace_lock);
list_del_init(&lm->list);
spin_unlock(&grace_lock);
}
EXPORT_SYMBOL_GPL(locks_end_grace);
static bool
__state_in_grace(struct net *net, bool open)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
struct lock_manager *lm;
if (!open)
return !list_empty(grace_list);
nfs_common: need lock during iterate through the list If the elem is deleted during be iterated on it, the iteration process will fall into an endless loop. kernel: NMI watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [nfsd:17137] PID: 17137  TASK: ffff8818d93c0000  CPU: 4   COMMAND: "nfsd"     [exception RIP: __state_in_grace+76]     RIP: ffffffffc00e817c  RSP: ffff8818d3aefc98  RFLAGS: 00000246     RAX: ffff881dc0c38298  RBX: ffffffff81b03580  RCX: ffff881dc02c9f50     RDX: ffff881e3fce8500  RSI: 0000000000000001  RDI: ffffffff81b03580     RBP: ffff8818d3aefca0   R8: 0000000000000020   R9: ffff8818d3aefd40     R10: ffff88017fc03800  R11: ffff8818e83933c0  R12: ffff8818d3aefd40     R13: 0000000000000000  R14: ffff8818e8391068  R15: ffff8818fa6e4000     CS: 0010  SS: 0018  #0 [ffff8818d3aefc98] opens_in_grace at ffffffffc00e81e3 [grace]  #1 [ffff8818d3aefca8] nfs4_preprocess_stateid_op at ffffffffc02a3e6c [nfsd]  #2 [ffff8818d3aefd18] nfsd4_write at ffffffffc028ed5b [nfsd]  #3 [ffff8818d3aefd80] nfsd4_proc_compound at ffffffffc0290a0d [nfsd]  #4 [ffff8818d3aefdd0] nfsd_dispatch at ffffffffc027b800 [nfsd]  #5 [ffff8818d3aefe08] svc_process_common at ffffffffc02017f3 [sunrpc]  #6 [ffff8818d3aefe70] svc_process at ffffffffc0201ce3 [sunrpc]  #7 [ffff8818d3aefe98] nfsd at ffffffffc027b117 [nfsd]  #8 [ffff8818d3aefec8] kthread at ffffffff810b88c1  #9 [ffff8818d3aeff50] ret_from_fork at ffffffff816d1607 The troublemake elem: crash> lock_manager ffff881dc0c38298 struct lock_manager {   list = {     next = 0xffff881dc0c38298,     prev = 0xffff881dc0c38298   },   block_opens = false } Fixes: c87fb4a378f9 ("lockd: NLM grace period shouldn't block NFSv4 opens") Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn> Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 15:06:35 +03:00
spin_lock(&grace_lock);
list_for_each_entry(lm, grace_list, list) {
nfs_common: need lock during iterate through the list If the elem is deleted during be iterated on it, the iteration process will fall into an endless loop. kernel: NMI watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [nfsd:17137] PID: 17137  TASK: ffff8818d93c0000  CPU: 4   COMMAND: "nfsd"     [exception RIP: __state_in_grace+76]     RIP: ffffffffc00e817c  RSP: ffff8818d3aefc98  RFLAGS: 00000246     RAX: ffff881dc0c38298  RBX: ffffffff81b03580  RCX: ffff881dc02c9f50     RDX: ffff881e3fce8500  RSI: 0000000000000001  RDI: ffffffff81b03580     RBP: ffff8818d3aefca0   R8: 0000000000000020   R9: ffff8818d3aefd40     R10: ffff88017fc03800  R11: ffff8818e83933c0  R12: ffff8818d3aefd40     R13: 0000000000000000  R14: ffff8818e8391068  R15: ffff8818fa6e4000     CS: 0010  SS: 0018  #0 [ffff8818d3aefc98] opens_in_grace at ffffffffc00e81e3 [grace]  #1 [ffff8818d3aefca8] nfs4_preprocess_stateid_op at ffffffffc02a3e6c [nfsd]  #2 [ffff8818d3aefd18] nfsd4_write at ffffffffc028ed5b [nfsd]  #3 [ffff8818d3aefd80] nfsd4_proc_compound at ffffffffc0290a0d [nfsd]  #4 [ffff8818d3aefdd0] nfsd_dispatch at ffffffffc027b800 [nfsd]  #5 [ffff8818d3aefe08] svc_process_common at ffffffffc02017f3 [sunrpc]  #6 [ffff8818d3aefe70] svc_process at ffffffffc0201ce3 [sunrpc]  #7 [ffff8818d3aefe98] nfsd at ffffffffc027b117 [nfsd]  #8 [ffff8818d3aefec8] kthread at ffffffff810b88c1  #9 [ffff8818d3aeff50] ret_from_fork at ffffffff816d1607 The troublemake elem: crash> lock_manager ffff881dc0c38298 struct lock_manager {   list = {     next = 0xffff881dc0c38298,     prev = 0xffff881dc0c38298   },   block_opens = false } Fixes: c87fb4a378f9 ("lockd: NLM grace period shouldn't block NFSv4 opens") Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn> Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 15:06:35 +03:00
if (lm->block_opens) {
spin_unlock(&grace_lock);
return true;
nfs_common: need lock during iterate through the list If the elem is deleted during be iterated on it, the iteration process will fall into an endless loop. kernel: NMI watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [nfsd:17137] PID: 17137  TASK: ffff8818d93c0000  CPU: 4   COMMAND: "nfsd"     [exception RIP: __state_in_grace+76]     RIP: ffffffffc00e817c  RSP: ffff8818d3aefc98  RFLAGS: 00000246     RAX: ffff881dc0c38298  RBX: ffffffff81b03580  RCX: ffff881dc02c9f50     RDX: ffff881e3fce8500  RSI: 0000000000000001  RDI: ffffffff81b03580     RBP: ffff8818d3aefca0   R8: 0000000000000020   R9: ffff8818d3aefd40     R10: ffff88017fc03800  R11: ffff8818e83933c0  R12: ffff8818d3aefd40     R13: 0000000000000000  R14: ffff8818e8391068  R15: ffff8818fa6e4000     CS: 0010  SS: 0018  #0 [ffff8818d3aefc98] opens_in_grace at ffffffffc00e81e3 [grace]  #1 [ffff8818d3aefca8] nfs4_preprocess_stateid_op at ffffffffc02a3e6c [nfsd]  #2 [ffff8818d3aefd18] nfsd4_write at ffffffffc028ed5b [nfsd]  #3 [ffff8818d3aefd80] nfsd4_proc_compound at ffffffffc0290a0d [nfsd]  #4 [ffff8818d3aefdd0] nfsd_dispatch at ffffffffc027b800 [nfsd]  #5 [ffff8818d3aefe08] svc_process_common at ffffffffc02017f3 [sunrpc]  #6 [ffff8818d3aefe70] svc_process at ffffffffc0201ce3 [sunrpc]  #7 [ffff8818d3aefe98] nfsd at ffffffffc027b117 [nfsd]  #8 [ffff8818d3aefec8] kthread at ffffffff810b88c1  #9 [ffff8818d3aeff50] ret_from_fork at ffffffff816d1607 The troublemake elem: crash> lock_manager ffff881dc0c38298 struct lock_manager {   list = {     next = 0xffff881dc0c38298,     prev = 0xffff881dc0c38298   },   block_opens = false } Fixes: c87fb4a378f9 ("lockd: NLM grace period shouldn't block NFSv4 opens") Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn> Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 15:06:35 +03:00
}
}
nfs_common: need lock during iterate through the list If the elem is deleted during be iterated on it, the iteration process will fall into an endless loop. kernel: NMI watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [nfsd:17137] PID: 17137  TASK: ffff8818d93c0000  CPU: 4   COMMAND: "nfsd"     [exception RIP: __state_in_grace+76]     RIP: ffffffffc00e817c  RSP: ffff8818d3aefc98  RFLAGS: 00000246     RAX: ffff881dc0c38298  RBX: ffffffff81b03580  RCX: ffff881dc02c9f50     RDX: ffff881e3fce8500  RSI: 0000000000000001  RDI: ffffffff81b03580     RBP: ffff8818d3aefca0   R8: 0000000000000020   R9: ffff8818d3aefd40     R10: ffff88017fc03800  R11: ffff8818e83933c0  R12: ffff8818d3aefd40     R13: 0000000000000000  R14: ffff8818e8391068  R15: ffff8818fa6e4000     CS: 0010  SS: 0018  #0 [ffff8818d3aefc98] opens_in_grace at ffffffffc00e81e3 [grace]  #1 [ffff8818d3aefca8] nfs4_preprocess_stateid_op at ffffffffc02a3e6c [nfsd]  #2 [ffff8818d3aefd18] nfsd4_write at ffffffffc028ed5b [nfsd]  #3 [ffff8818d3aefd80] nfsd4_proc_compound at ffffffffc0290a0d [nfsd]  #4 [ffff8818d3aefdd0] nfsd_dispatch at ffffffffc027b800 [nfsd]  #5 [ffff8818d3aefe08] svc_process_common at ffffffffc02017f3 [sunrpc]  #6 [ffff8818d3aefe70] svc_process at ffffffffc0201ce3 [sunrpc]  #7 [ffff8818d3aefe98] nfsd at ffffffffc027b117 [nfsd]  #8 [ffff8818d3aefec8] kthread at ffffffff810b88c1  #9 [ffff8818d3aeff50] ret_from_fork at ffffffff816d1607 The troublemake elem: crash> lock_manager ffff881dc0c38298 struct lock_manager {   list = {     next = 0xffff881dc0c38298,     prev = 0xffff881dc0c38298   },   block_opens = false } Fixes: c87fb4a378f9 ("lockd: NLM grace period shouldn't block NFSv4 opens") Signed-off-by: Cheng Lin <cheng.lin130@zte.com.cn> Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
2020-12-01 15:06:35 +03:00
spin_unlock(&grace_lock);
return false;
}
/**
* locks_in_grace
* @net: network namespace
*
* Lock managers call this function to determine when it is OK for them
* to answer ordinary lock requests, and when they should accept only
* lock reclaims.
*/
bool locks_in_grace(struct net *net)
{
return __state_in_grace(net, false);
}
EXPORT_SYMBOL_GPL(locks_in_grace);
bool opens_in_grace(struct net *net)
{
return __state_in_grace(net, true);
}
EXPORT_SYMBOL_GPL(opens_in_grace);
static int __net_init
grace_init_net(struct net *net)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
INIT_LIST_HEAD(grace_list);
return 0;
}
static void __net_exit
grace_exit_net(struct net *net)
{
struct list_head *grace_list = net_generic(net, grace_net_id);
WARN_ONCE(!list_empty(grace_list),
"net %x %s: grace_list is not empty\n",
net->ns.inum, __func__);
}
static struct pernet_operations grace_net_ops = {
.init = grace_init_net,
.exit = grace_exit_net,
.id = &grace_net_id,
.size = sizeof(struct list_head),
};
static int __init
init_grace(void)
{
return register_pernet_subsys(&grace_net_ops);
}
static void __exit
exit_grace(void)
{
unregister_pernet_subsys(&grace_net_ops);
}
MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>");
MODULE_LICENSE("GPL");
module_init(init_grace)
module_exit(exit_grace)