hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

rcu: Make rcu_barrier() understand about missing rcuo kthreads 

Commit 35ce7f29a4 (rcu: Create rcuo kthreads only for onlined CPUs)
avoids creating rcuo kthreads for CPUs that never come online.  This
fixes a bug in many instances of firmware: Instead of lying about their
age, these systems instead lie about the number of CPUs that they have.
Before commit 35ce7f29a4, this could result in huge numbers of useless
rcuo kthreads being created.

It appears that experience indicates that I should have told the
people suffering from this problem to fix their broken firmware, but
I instead produced what turned out to be a partial fix.   The missing
piece supplied by this commit makes sure that rcu_barrier() knows not to
post callbacks for no-CBs CPUs that have not yet come online, because
otherwise rcu_barrier() will hang on systems having firmware that lies
about the number of CPUs.

It is tempting to simply have rcu_barrier() refuse to post a callback on
any no-CBs CPU that does not have an rcuo kthread.  This unfortunately
does not work because rcu_barrier() is required to wait for all pending
callbacks.  It is therefore required to wait even for those callbacks
that cannot possibly be invoked.  Even if doing so hangs the system.

Given that posting a callback to a no-CBs CPU that does not yet have an
rcuo kthread can hang rcu_barrier(), It is tempting to report an error
in this case.  Unfortunately, this will result in false positives at
boot time, when it is perfectly legal to post callbacks to the boot CPU
before the scheduler has started, in other words, before it is legal
to invoke rcu_barrier().

So this commit instead has rcu_barrier() avoid posting callbacks to
CPUs having neither rcuo kthread nor pending callbacks, and has it
complain bitterly if it finds CPUs having no rcuo kthread but some
pending callbacks.  And when rcu_barrier() does find CPUs having no rcuo
kthread but pending callbacks, as noted earlier, it has no choice but
to hang indefinitely.

Reported-by: Yanko Kaneti <yaneti@declera.com>
Reported-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Reported-by: Meelis Roos <mroos@linux.ee>
Reported-by: Eric B Munson <emunson@akamai.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Eric B Munson <emunson@akamai.com>
Tested-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Tested-by: Yanko Kaneti <yaneti@declera.com>
Tested-by: Kevin Fenzi <kevin@scrye.com>
Tested-by: Meelis Roos <mroos@linux.ee>
This commit is contained in:
Paul E. McKenney 2014-10-27 09:15:54 -07:00
parent b2c4623dcd
commit d7e2993396
4 changed files with 53 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
include/trace/events/rcu.h
View File

@ -660,18 +660,18 @@ TRACE_EVENT(rcu_torture_read,
/* /*
* Tracepoint for _rcu_barrier() execution. The string "s" describes * Tracepoint for _rcu_barrier() execution. The string "s" describes
* the _rcu_barrier phase: * the _rcu_barrier phase:
* "Begin": rcu_barrier_callback() started. * "Begin": _rcu_barrier() started.
* "Check": rcu_barrier_callback() checking for piggybacking. * "Check": _rcu_barrier() checking for piggybacking.
* "EarlyExit": rcu_barrier_callback() piggybacked, thus early exit. * "EarlyExit": _rcu_barrier() piggybacked, thus early exit.
* "Inc1": rcu_barrier_callback() piggyback check counter incremented. * "Inc1": _rcu_barrier() piggyback check counter incremented.
* "Offline": rcu_barrier_callback() found offline CPU * "OfflineNoCB": _rcu_barrier() found callback on never-online CPU
* "OnlineNoCB": rcu_barrier_callback() found online no-CBs CPU. * "OnlineNoCB": _rcu_barrier() found online no-CBs CPU.
* "OnlineQ": rcu_barrier_callback() found online CPU with callbacks. * "OnlineQ": _rcu_barrier() found online CPU with callbacks.
* "OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks. * "OnlineNQ": _rcu_barrier() found online CPU, no callbacks.
* "IRQ": An rcu_barrier_callback() callback posted on remote CPU. * "IRQ": An rcu_barrier_callback() callback posted on remote CPU.
* "CB": An rcu_barrier_callback() invoked a callback, not the last. * "CB": An rcu_barrier_callback() invoked a callback, not the last.
* "LastCB": An rcu_barrier_callback() invoked the last callback. * "LastCB": An rcu_barrier_callback() invoked the last callback.
* "Inc2": rcu_barrier_callback() piggyback check counter incremented. * "Inc2": _rcu_barrier() piggyback check counter incremented.
* The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
* is the count of remaining callbacks, and "done" is the piggybacking count. * is the count of remaining callbacks, and "done" is the piggybacking count.
*/ */

15
kernel/rcu/tree.c
View File

@ -3299,11 +3299,16 @@ static void _rcu_barrier(struct rcu_state *rsp)
continue; continue;
rdp = per_cpu_ptr(rsp->rda, cpu); rdp = per_cpu_ptr(rsp->rda, cpu);
if (rcu_is_nocb_cpu(cpu)) { if (rcu_is_nocb_cpu(cpu)) {
_rcu_barrier_trace(rsp, "OnlineNoCB", cpu, if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
rsp->n_barrier_done); _rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
atomic_inc(&rsp->barrier_cpu_count); rsp->n_barrier_done);
__call_rcu(&rdp->barrier_head, rcu_barrier_callback, } else {
rsp, cpu, 0); _rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
rsp->n_barrier_done);
atomic_inc(&rsp->barrier_cpu_count);
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
} else if (ACCESS_ONCE(rdp->qlen)) { } else if (ACCESS_ONCE(rdp->qlen)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu, _rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->n_barrier_done); rsp->n_barrier_done);

1
kernel/rcu/tree.h
View File

@ -587,6 +587,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu);
static void print_cpu_stall_info_end(void); static void print_cpu_stall_info_end(void);
static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static void increment_cpu_stall_ticks(void); static void increment_cpu_stall_ticks(void);
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu);
static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
static void rcu_init_one_nocb(struct rcu_node *rnp); static void rcu_init_one_nocb(struct rcu_node *rnp);

33
kernel/rcu/tree_plugin.h
View File

@ -2049,6 +2049,33 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
} }
} }
/*
* Does the specified CPU need an RCU callback for the specified flavor
* of rcu_barrier()?
*/
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
{
struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
struct rcu_head *rhp;
/* No-CBs CPUs might have callbacks on any of three lists. */
rhp = ACCESS_ONCE(rdp->nocb_head);
if (!rhp)
rhp = ACCESS_ONCE(rdp->nocb_gp_head);
if (!rhp)
rhp = ACCESS_ONCE(rdp->nocb_follower_head);
/* Having no rcuo kthread but CBs after scheduler starts is bad! */
if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp) {
/* RCU callback enqueued before CPU first came online??? */
pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
cpu, rhp->func);
WARN_ON_ONCE(1);
}
return !!rhp;
}
/* /*
* Enqueue the specified string of rcu_head structures onto the specified * Enqueue the specified string of rcu_head structures onto the specified
* CPU's no-CBs lists. The CPU is specified by rdp, the head of the * CPU's no-CBs lists. The CPU is specified by rdp, the head of the
@ -2642,6 +2669,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
#else /* #ifdef CONFIG_RCU_NOCB_CPU */ #else /* #ifdef CONFIG_RCU_NOCB_CPU */
static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
{
WARN_ON_ONCE(1); /* Should be dead code. */
return false;
}
static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{ {
} }