486e259340
When CONFIG_RCU_FAST_NO_HZ is enabled, RCU will allow a given CPU to enter dyntick-idle mode even if it still has RCU callbacks queued. RCU avoids system hangs in this case by scheduling a timer for several jiffies in the future. However, if all of the callbacks on that CPU are from kfree_rcu(), there is no reason to wake the CPU up, as it is not a problem to defer freeing of memory. This commit therefore tracks the number of callbacks on a given CPU that are from kfree_rcu(), and avoids scheduling the timer if all of a given CPU's callbacks are from kfree_rcu(). Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
571 lines
16 KiB
C
571 lines
16 KiB
C
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM rcu
|
|
|
|
#if !defined(_TRACE_RCU_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_RCU_H
|
|
|
|
#include <linux/tracepoint.h>
|
|
|
|
/*
|
|
* Tracepoint for start/end markers used for utilization calculations.
|
|
* By convention, the string is of the following forms:
|
|
*
|
|
* "Start <activity>" -- Mark the start of the specified activity,
|
|
* such as "context switch". Nesting is permitted.
|
|
* "End <activity>" -- Mark the end of the specified activity.
|
|
*
|
|
* An "@" character within "<activity>" is a comment character: Data
|
|
* reduction scripts will ignore the "@" and the remainder of the line.
|
|
*/
|
|
TRACE_EVENT(rcu_utilization,
|
|
|
|
TP_PROTO(char *s),
|
|
|
|
TP_ARGS(s),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, s)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->s = s;
|
|
),
|
|
|
|
TP_printk("%s", __entry->s)
|
|
);
|
|
|
|
#ifdef CONFIG_RCU_TRACE
|
|
|
|
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
|
|
|
|
/*
|
|
* Tracepoint for grace-period events: starting and ending a grace
|
|
* period ("start" and "end", respectively), a CPU noting the start
|
|
* of a new grace period or the end of an old grace period ("cpustart"
|
|
* and "cpuend", respectively), a CPU passing through a quiescent
|
|
* state ("cpuqs"), a CPU coming online or going offline ("cpuonl"
|
|
* and "cpuofl", respectively), and a CPU being kicked for being too
|
|
* long in dyntick-idle mode ("kick").
|
|
*/
|
|
TRACE_EVENT(rcu_grace_period,
|
|
|
|
TP_PROTO(char *rcuname, unsigned long gpnum, char *gpevent),
|
|
|
|
TP_ARGS(rcuname, gpnum, gpevent),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(char *, gpevent)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->gpevent = gpevent;
|
|
),
|
|
|
|
TP_printk("%s %lu %s",
|
|
__entry->rcuname, __entry->gpnum, __entry->gpevent)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for grace-period-initialization events. These are
|
|
* distinguished by the type of RCU, the new grace-period number, the
|
|
* rcu_node structure level, the starting and ending CPU covered by the
|
|
* rcu_node structure, and the mask of CPUs that will be waited for.
|
|
* All but the type of RCU are extracted from the rcu_node structure.
|
|
*/
|
|
TRACE_EVENT(rcu_grace_period_init,
|
|
|
|
TP_PROTO(char *rcuname, unsigned long gpnum, u8 level,
|
|
int grplo, int grphi, unsigned long qsmask),
|
|
|
|
TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(u8, level)
|
|
__field(int, grplo)
|
|
__field(int, grphi)
|
|
__field(unsigned long, qsmask)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->level = level;
|
|
__entry->grplo = grplo;
|
|
__entry->grphi = grphi;
|
|
__entry->qsmask = qsmask;
|
|
),
|
|
|
|
TP_printk("%s %lu %u %d %d %lx",
|
|
__entry->rcuname, __entry->gpnum, __entry->level,
|
|
__entry->grplo, __entry->grphi, __entry->qsmask)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for tasks blocking within preemptible-RCU read-side
|
|
* critical sections. Track the type of RCU (which one day might
|
|
* include SRCU), the grace-period number that the task is blocking
|
|
* (the current or the next), and the task's PID.
|
|
*/
|
|
TRACE_EVENT(rcu_preempt_task,
|
|
|
|
TP_PROTO(char *rcuname, int pid, unsigned long gpnum),
|
|
|
|
TP_ARGS(rcuname, pid, gpnum),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(int, pid)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->pid = pid;
|
|
),
|
|
|
|
TP_printk("%s %lu %d",
|
|
__entry->rcuname, __entry->gpnum, __entry->pid)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for tasks that blocked within a given preemptible-RCU
|
|
* read-side critical section exiting that critical section. Track the
|
|
* type of RCU (which one day might include SRCU) and the task's PID.
|
|
*/
|
|
TRACE_EVENT(rcu_unlock_preempted_task,
|
|
|
|
TP_PROTO(char *rcuname, unsigned long gpnum, int pid),
|
|
|
|
TP_ARGS(rcuname, gpnum, pid),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(int, pid)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->pid = pid;
|
|
),
|
|
|
|
TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for quiescent-state-reporting events. These are
|
|
* distinguished by the type of RCU, the grace-period number, the
|
|
* mask of quiescent lower-level entities, the rcu_node structure level,
|
|
* the starting and ending CPU covered by the rcu_node structure, and
|
|
* whether there are any blocked tasks blocking the current grace period.
|
|
* All but the type of RCU are extracted from the rcu_node structure.
|
|
*/
|
|
TRACE_EVENT(rcu_quiescent_state_report,
|
|
|
|
TP_PROTO(char *rcuname, unsigned long gpnum,
|
|
unsigned long mask, unsigned long qsmask,
|
|
u8 level, int grplo, int grphi, int gp_tasks),
|
|
|
|
TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(unsigned long, mask)
|
|
__field(unsigned long, qsmask)
|
|
__field(u8, level)
|
|
__field(int, grplo)
|
|
__field(int, grphi)
|
|
__field(u8, gp_tasks)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->mask = mask;
|
|
__entry->qsmask = qsmask;
|
|
__entry->level = level;
|
|
__entry->grplo = grplo;
|
|
__entry->grphi = grphi;
|
|
__entry->gp_tasks = gp_tasks;
|
|
),
|
|
|
|
TP_printk("%s %lu %lx>%lx %u %d %d %u",
|
|
__entry->rcuname, __entry->gpnum,
|
|
__entry->mask, __entry->qsmask, __entry->level,
|
|
__entry->grplo, __entry->grphi, __entry->gp_tasks)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for quiescent states detected by force_quiescent_state().
|
|
* These trace events include the type of RCU, the grace-period number
|
|
* that was blocked by the CPU, the CPU itself, and the type of quiescent
|
|
* state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline,
|
|
* or "kick" when kicking a CPU that has been in dyntick-idle mode for
|
|
* too long.
|
|
*/
|
|
TRACE_EVENT(rcu_fqs,
|
|
|
|
TP_PROTO(char *rcuname, unsigned long gpnum, int cpu, char *qsevent),
|
|
|
|
TP_ARGS(rcuname, gpnum, cpu, qsevent),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(unsigned long, gpnum)
|
|
__field(int, cpu)
|
|
__field(char *, qsevent)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->gpnum = gpnum;
|
|
__entry->cpu = cpu;
|
|
__entry->qsevent = qsevent;
|
|
),
|
|
|
|
TP_printk("%s %lu %d %s",
|
|
__entry->rcuname, __entry->gpnum,
|
|
__entry->cpu, __entry->qsevent)
|
|
);
|
|
|
|
#endif /* #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) */
|
|
|
|
/*
|
|
* Tracepoint for dyntick-idle entry/exit events. These take a string
|
|
* as argument: "Start" for entering dyntick-idle mode, "End" for
|
|
* leaving it, "--=" for events moving towards idle, and "++=" for events
|
|
* moving away from idle. "Error on entry: not idle task" and "Error on
|
|
* exit: not idle task" indicate that a non-idle task is erroneously
|
|
* toying with the idle loop.
|
|
*
|
|
* These events also take a pair of numbers, which indicate the nesting
|
|
* depth before and after the event of interest. Note that task-related
|
|
* events use the upper bits of each number, while interrupt-related
|
|
* events use the lower bits.
|
|
*/
|
|
TRACE_EVENT(rcu_dyntick,
|
|
|
|
TP_PROTO(char *polarity, long long oldnesting, long long newnesting),
|
|
|
|
TP_ARGS(polarity, oldnesting, newnesting),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, polarity)
|
|
__field(long long, oldnesting)
|
|
__field(long long, newnesting)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->polarity = polarity;
|
|
__entry->oldnesting = oldnesting;
|
|
__entry->newnesting = newnesting;
|
|
),
|
|
|
|
TP_printk("%s %llx %llx", __entry->polarity,
|
|
__entry->oldnesting, __entry->newnesting)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for RCU preparation for idle, the goal being to get RCU
|
|
* processing done so that the current CPU can shut off its scheduling
|
|
* clock and enter dyntick-idle mode. One way to accomplish this is
|
|
* to drain all RCU callbacks from this CPU, and the other is to have
|
|
* done everything RCU requires for the current grace period. In this
|
|
* latter case, the CPU will be awakened at the end of the current grace
|
|
* period in order to process the remainder of its callbacks.
|
|
*
|
|
* These tracepoints take a string as argument:
|
|
*
|
|
* "No callbacks": Nothing to do, no callbacks on this CPU.
|
|
* "In holdoff": Nothing to do, holding off after unsuccessful attempt.
|
|
* "Begin holdoff": Attempt failed, don't retry until next jiffy.
|
|
* "Dyntick with callbacks": Entering dyntick-idle despite callbacks.
|
|
* "More callbacks": Still more callbacks, try again to clear them out.
|
|
* "Callbacks drained": All callbacks processed, off to dyntick idle!
|
|
* "Timer": Timer fired to cause CPU to continue processing callbacks.
|
|
*/
|
|
TRACE_EVENT(rcu_prep_idle,
|
|
|
|
TP_PROTO(char *reason),
|
|
|
|
TP_ARGS(reason),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, reason)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->reason = reason;
|
|
),
|
|
|
|
TP_printk("%s", __entry->reason)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for the registration of a single RCU callback function.
|
|
* The first argument is the type of RCU, the second argument is
|
|
* a pointer to the RCU callback itself, the third element is the
|
|
* number of lazy callbacks queued, and the fourth element is the
|
|
* total number of callbacks queued.
|
|
*/
|
|
TRACE_EVENT(rcu_callback,
|
|
|
|
TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy,
|
|
long qlen),
|
|
|
|
TP_ARGS(rcuname, rhp, qlen_lazy, qlen),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(void *, rhp)
|
|
__field(void *, func)
|
|
__field(long, qlen_lazy)
|
|
__field(long, qlen)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->rhp = rhp;
|
|
__entry->func = rhp->func;
|
|
__entry->qlen_lazy = qlen_lazy;
|
|
__entry->qlen = qlen;
|
|
),
|
|
|
|
TP_printk("%s rhp=%p func=%pf %ld/%ld",
|
|
__entry->rcuname, __entry->rhp, __entry->func,
|
|
__entry->qlen_lazy, __entry->qlen)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for the registration of a single RCU callback of the special
|
|
* kfree() form. The first argument is the RCU type, the second argument
|
|
* is a pointer to the RCU callback, the third argument is the offset
|
|
* of the callback within the enclosing RCU-protected data structure,
|
|
* the fourth argument is the number of lazy callbacks queued, and the
|
|
* fifth argument is the total number of callbacks queued.
|
|
*/
|
|
TRACE_EVENT(rcu_kfree_callback,
|
|
|
|
TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset,
|
|
long qlen_lazy, long qlen),
|
|
|
|
TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(void *, rhp)
|
|
__field(unsigned long, offset)
|
|
__field(long, qlen_lazy)
|
|
__field(long, qlen)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->rhp = rhp;
|
|
__entry->offset = offset;
|
|
__entry->qlen_lazy = qlen_lazy;
|
|
__entry->qlen = qlen;
|
|
),
|
|
|
|
TP_printk("%s rhp=%p func=%ld %ld/%ld",
|
|
__entry->rcuname, __entry->rhp, __entry->offset,
|
|
__entry->qlen_lazy, __entry->qlen)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for marking the beginning rcu_do_batch, performed to start
|
|
* RCU callback invocation. The first argument is the RCU flavor,
|
|
* the second is the number of lazy callbacks queued, the third is
|
|
* the total number of callbacks queued, and the fourth argument is
|
|
* the current RCU-callback batch limit.
|
|
*/
|
|
TRACE_EVENT(rcu_batch_start,
|
|
|
|
TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit),
|
|
|
|
TP_ARGS(rcuname, qlen_lazy, qlen, blimit),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(long, qlen_lazy)
|
|
__field(long, qlen)
|
|
__field(int, blimit)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->qlen_lazy = qlen_lazy;
|
|
__entry->qlen = qlen;
|
|
__entry->blimit = blimit;
|
|
),
|
|
|
|
TP_printk("%s CBs=%ld/%ld bl=%d",
|
|
__entry->rcuname, __entry->qlen_lazy, __entry->qlen,
|
|
__entry->blimit)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for the invocation of a single RCU callback function.
|
|
* The first argument is the type of RCU, and the second argument is
|
|
* a pointer to the RCU callback itself.
|
|
*/
|
|
TRACE_EVENT(rcu_invoke_callback,
|
|
|
|
TP_PROTO(char *rcuname, struct rcu_head *rhp),
|
|
|
|
TP_ARGS(rcuname, rhp),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(void *, rhp)
|
|
__field(void *, func)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->rhp = rhp;
|
|
__entry->func = rhp->func;
|
|
),
|
|
|
|
TP_printk("%s rhp=%p func=%pf",
|
|
__entry->rcuname, __entry->rhp, __entry->func)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for the invocation of a single RCU callback of the special
|
|
* kfree() form. The first argument is the RCU flavor, the second
|
|
* argument is a pointer to the RCU callback, and the third argument
|
|
* is the offset of the callback within the enclosing RCU-protected
|
|
* data structure.
|
|
*/
|
|
TRACE_EVENT(rcu_invoke_kfree_callback,
|
|
|
|
TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset),
|
|
|
|
TP_ARGS(rcuname, rhp, offset),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(void *, rhp)
|
|
__field(unsigned long, offset)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->rhp = rhp;
|
|
__entry->offset = offset;
|
|
),
|
|
|
|
TP_printk("%s rhp=%p func=%ld",
|
|
__entry->rcuname, __entry->rhp, __entry->offset)
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for exiting rcu_do_batch after RCU callbacks have been
|
|
* invoked. The first argument is the name of the RCU flavor,
|
|
* the second argument is number of callbacks actually invoked,
|
|
* the third argument (cb) is whether or not any of the callbacks that
|
|
* were ready to invoke at the beginning of this batch are still
|
|
* queued, the fourth argument (nr) is the return value of need_resched(),
|
|
* the fifth argument (iit) is 1 if the current task is the idle task,
|
|
* and the sixth argument (risk) is the return value from
|
|
* rcu_is_callbacks_kthread().
|
|
*/
|
|
TRACE_EVENT(rcu_batch_end,
|
|
|
|
TP_PROTO(char *rcuname, int callbacks_invoked,
|
|
bool cb, bool nr, bool iit, bool risk),
|
|
|
|
TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcuname)
|
|
__field(int, callbacks_invoked)
|
|
__field(bool, cb)
|
|
__field(bool, nr)
|
|
__field(bool, iit)
|
|
__field(bool, risk)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcuname = rcuname;
|
|
__entry->callbacks_invoked = callbacks_invoked;
|
|
__entry->cb = cb;
|
|
__entry->nr = nr;
|
|
__entry->iit = iit;
|
|
__entry->risk = risk;
|
|
),
|
|
|
|
TP_printk("%s CBs-invoked=%d idle=%c%c%c%c",
|
|
__entry->rcuname, __entry->callbacks_invoked,
|
|
__entry->cb ? 'C' : '.',
|
|
__entry->nr ? 'S' : '.',
|
|
__entry->iit ? 'I' : '.',
|
|
__entry->risk ? 'R' : '.')
|
|
);
|
|
|
|
/*
|
|
* Tracepoint for rcutorture readers. The first argument is the name
|
|
* of the RCU flavor from rcutorture's viewpoint and the second argument
|
|
* is the callback address.
|
|
*/
|
|
TRACE_EVENT(rcu_torture_read,
|
|
|
|
TP_PROTO(char *rcutorturename, struct rcu_head *rhp),
|
|
|
|
TP_ARGS(rcutorturename, rhp),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(char *, rcutorturename)
|
|
__field(struct rcu_head *, rhp)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->rcutorturename = rcutorturename;
|
|
__entry->rhp = rhp;
|
|
),
|
|
|
|
TP_printk("%s torture read %p",
|
|
__entry->rcutorturename, __entry->rhp)
|
|
);
|
|
|
|
#else /* #ifdef CONFIG_RCU_TRACE */
|
|
|
|
#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
|
|
#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
|
|
qsmask) do { } while (0)
|
|
#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
|
|
#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
|
|
#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
|
|
grplo, grphi, gp_tasks) do { } \
|
|
while (0)
|
|
#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
|
|
#define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0)
|
|
#define trace_rcu_prep_idle(reason) do { } while (0)
|
|
#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
|
|
#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
|
|
do { } while (0)
|
|
#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \
|
|
do { } while (0)
|
|
#define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0)
|
|
#define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0)
|
|
#define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \
|
|
do { } while (0)
|
|
#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0)
|
|
|
|
#endif /* #else #ifdef CONFIG_RCU_TRACE */
|
|
|
|
#endif /* _TRACE_RCU_H */
|
|
|
|
/* This part must be outside protection */
|
|
#include <trace/define_trace.h>
|