2009-06-02 02:13:33 +08:00
|
|
|
/*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
* (at your option) any later version.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, write to the Free Software
|
|
|
|
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Alan Stern
|
|
|
|
* Copyright (C) IBM Corporation, 2009
|
2009-09-10 01:22:48 +08:00
|
|
|
* Copyright (C) 2009, Frederic Weisbecker <fweisbec@gmail.com>
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
*
|
|
|
|
* Thanks to Ingo Molnar for his many suggestions.
|
2009-11-23 23:47:13 +08:00
|
|
|
*
|
|
|
|
* Authors: Alan Stern <stern@rowland.harvard.edu>
|
|
|
|
* K.Prasad <prasad@linux.vnet.ibm.com>
|
|
|
|
* Frederic Weisbecker <fweisbec@gmail.com>
|
2009-06-02 02:13:33 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
|
|
|
|
* using the CPU's debug registers.
|
|
|
|
* This file contains the arch-independent routines.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/irqflags.h>
|
|
|
|
#include <linux/kallsyms.h>
|
|
|
|
#include <linux/notifier.h>
|
|
|
|
#include <linux/kprobes.h>
|
|
|
|
#include <linux/kdebug.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/percpu.h>
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/init.h>
|
2010-04-23 11:59:55 +08:00
|
|
|
#include <linux/slab.h>
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
#include <linux/list.h>
|
2009-12-30 14:22:22 +08:00
|
|
|
#include <linux/cpu.h>
|
2009-06-02 02:13:33 +08:00
|
|
|
#include <linux/smp.h>
|
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
#include <linux/hw_breakpoint.h>
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/*
|
|
|
|
* Constraints data
|
|
|
|
*/
|
2009-06-02 02:13:33 +08:00
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/* Number of pinned cpu breakpoints in a cpu */
|
2010-04-12 00:55:56 +08:00
|
|
|
static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned[TYPE_MAX]);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
/* Number of pinned task breakpoints in a cpu */
|
2010-05-03 21:39:45 +08:00
|
|
|
static DEFINE_PER_CPU(unsigned int *, nr_task_bp_pinned[TYPE_MAX]);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
/* Number of non-pinned cpu/task breakpoints in a cpu */
|
2010-04-12 00:55:56 +08:00
|
|
|
static DEFINE_PER_CPU(unsigned int, nr_bp_flexible[TYPE_MAX]);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
2010-04-23 11:59:55 +08:00
|
|
|
static int nr_slots[TYPE_MAX];
|
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
/* Keep track of the breakpoints attached to tasks */
|
|
|
|
static LIST_HEAD(bp_task_head);
|
|
|
|
|
2010-04-23 11:59:55 +08:00
|
|
|
static int constraints_initialized;
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/* Gather the number of total pinned and un-pinned bp in a cpuset */
|
|
|
|
struct bp_busy_slots {
|
|
|
|
unsigned int pinned;
|
|
|
|
unsigned int flexible;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Serialize accesses to the above constraints */
|
|
|
|
static DEFINE_MUTEX(nr_bp_mutex);
|
|
|
|
|
2010-04-13 06:32:30 +08:00
|
|
|
__weak int hw_breakpoint_weight(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
static inline enum bp_type_idx find_slot_idx(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
if (bp->attr.bp_type & HW_BREAKPOINT_RW)
|
|
|
|
return TYPE_DATA;
|
|
|
|
|
|
|
|
return TYPE_INST;
|
|
|
|
}
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/*
|
|
|
|
* Report the maximum number of pinned breakpoints a task
|
|
|
|
* have in this cpu
|
|
|
|
*/
|
2010-04-12 00:55:56 +08:00
|
|
|
static unsigned int max_task_bp_pinned(int cpu, enum bp_type_idx type)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
int i;
|
2010-04-12 00:55:56 +08:00
|
|
|
unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2010-04-23 11:59:55 +08:00
|
|
|
for (i = nr_slots[type] - 1; i >= 0; i--) {
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
if (tsk_pinned[i] > 0)
|
|
|
|
return i + 1;
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
return 0;
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
/*
|
|
|
|
* Count the number of breakpoints of the same type and same task.
|
|
|
|
* The given event must be not on the list.
|
|
|
|
*/
|
|
|
|
static int task_bp_pinned(struct perf_event *bp, enum bp_type_idx type)
|
2009-12-07 13:46:48 +08:00
|
|
|
{
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
struct perf_event_context *ctx = bp->ctx;
|
|
|
|
struct perf_event *iter;
|
2009-12-07 13:46:48 +08:00
|
|
|
int count = 0;
|
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
list_for_each_entry(iter, &bp_task_head, hw.bp_list) {
|
|
|
|
if (iter->ctx == ctx && find_slot_idx(iter) == type)
|
|
|
|
count += hw_breakpoint_weight(iter);
|
2009-12-07 13:46:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/*
|
|
|
|
* Report the number of pinned/un-pinned breakpoints we have in
|
|
|
|
* a given cpu (cpu > -1) or in all of them (cpu = -1).
|
|
|
|
*/
|
2009-12-07 13:46:48 +08:00
|
|
|
static void
|
2010-04-12 00:55:56 +08:00
|
|
|
fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp,
|
|
|
|
enum bp_type_idx type)
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
{
|
2009-12-07 13:46:48 +08:00
|
|
|
int cpu = bp->cpu;
|
|
|
|
struct task_struct *tsk = bp->ctx->task;
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
if (cpu >= 0) {
|
2010-04-12 00:55:56 +08:00
|
|
|
slots->pinned = per_cpu(nr_cpu_bp_pinned[type], cpu);
|
2009-12-07 13:46:48 +08:00
|
|
|
if (!tsk)
|
2010-04-12 00:55:56 +08:00
|
|
|
slots->pinned += max_task_bp_pinned(cpu, type);
|
2009-12-07 13:46:48 +08:00
|
|
|
else
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
slots->pinned += task_bp_pinned(bp, type);
|
2010-04-12 00:55:56 +08:00
|
|
|
slots->flexible = per_cpu(nr_bp_flexible[type], cpu);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for_each_online_cpu(cpu) {
|
|
|
|
unsigned int nr;
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
nr = per_cpu(nr_cpu_bp_pinned[type], cpu);
|
2009-12-07 13:46:48 +08:00
|
|
|
if (!tsk)
|
2010-04-12 00:55:56 +08:00
|
|
|
nr += max_task_bp_pinned(cpu, type);
|
2009-12-07 13:46:48 +08:00
|
|
|
else
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
nr += task_bp_pinned(bp, type);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
if (nr > slots->pinned)
|
|
|
|
slots->pinned = nr;
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
nr = per_cpu(nr_bp_flexible[type], cpu);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
if (nr > slots->flexible)
|
|
|
|
slots->flexible = nr;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-04-13 06:32:30 +08:00
|
|
|
/*
|
|
|
|
* For now, continue to consider flexible as pinned, until we can
|
|
|
|
* ensure no flexible event can ever be scheduled before a pinned event
|
|
|
|
* in a same cpu.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
fetch_this_slot(struct bp_busy_slots *slots, int weight)
|
|
|
|
{
|
|
|
|
slots->pinned += weight;
|
|
|
|
}
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/*
|
|
|
|
* Add a pinned breakpoint for the given task in our constraint table
|
|
|
|
*/
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
static void toggle_bp_task_slot(struct perf_event *bp, int cpu, bool enable,
|
2010-04-13 06:32:30 +08:00
|
|
|
enum bp_type_idx type, int weight)
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
{
|
2009-11-26 15:01:50 +08:00
|
|
|
unsigned int *tsk_pinned;
|
2010-04-13 06:32:30 +08:00
|
|
|
int old_count = 0;
|
|
|
|
int old_idx = 0;
|
|
|
|
int idx = 0;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
old_count = task_bp_pinned(bp, type);
|
2010-04-13 06:32:30 +08:00
|
|
|
old_idx = old_count - 1;
|
|
|
|
idx = old_idx + weight;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
/* tsk_pinned[n] is the number of tasks having n breakpoints */
|
2010-04-12 00:55:56 +08:00
|
|
|
tsk_pinned = per_cpu(nr_task_bp_pinned[type], cpu);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
if (enable) {
|
2010-04-13 06:32:30 +08:00
|
|
|
tsk_pinned[idx]++;
|
|
|
|
if (old_count > 0)
|
|
|
|
tsk_pinned[old_idx]--;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
} else {
|
2010-04-13 06:32:30 +08:00
|
|
|
tsk_pinned[idx]--;
|
|
|
|
if (old_count > 0)
|
|
|
|
tsk_pinned[old_idx]++;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Add/remove the given breakpoint in our constraint table
|
|
|
|
*/
|
2010-04-12 00:55:56 +08:00
|
|
|
static void
|
2010-04-13 06:32:30 +08:00
|
|
|
toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type,
|
|
|
|
int weight)
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
{
|
|
|
|
int cpu = bp->cpu;
|
|
|
|
struct task_struct *tsk = bp->ctx->task;
|
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
/* Pinned counter cpu profiling */
|
|
|
|
if (!tsk) {
|
|
|
|
|
|
|
|
if (enable)
|
|
|
|
per_cpu(nr_cpu_bp_pinned[type], bp->cpu) += weight;
|
|
|
|
else
|
|
|
|
per_cpu(nr_cpu_bp_pinned[type], bp->cpu) -= weight;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/* Pinned counter task profiling */
|
|
|
|
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
if (!enable)
|
|
|
|
list_del(&bp->hw.bp_list);
|
|
|
|
|
|
|
|
if (cpu >= 0) {
|
|
|
|
toggle_bp_task_slot(bp, cpu, enable, type, weight);
|
|
|
|
} else {
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
for_each_online_cpu(cpu)
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
toggle_bp_task_slot(bp, cpu, enable, type, weight);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (enable)
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
list_add_tail(&bp->hw.bp_list, &bp_task_head);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
}
|
|
|
|
|
2010-06-15 14:04:34 +08:00
|
|
|
/*
|
|
|
|
* Function to perform processor-specific cleanup during unregistration
|
|
|
|
*/
|
|
|
|
__weak void arch_unregister_hw_breakpoint(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* A weak stub function here for those archs that don't define
|
|
|
|
* it inside arch/.../kernel/hw_breakpoint.c
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
/*
|
|
|
|
* Contraints to check before allowing this new breakpoint counter:
|
|
|
|
*
|
|
|
|
* == Non-pinned counter == (Considered as pinned for now)
|
|
|
|
*
|
|
|
|
* - If attached to a single cpu, check:
|
|
|
|
*
|
|
|
|
* (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
|
2009-12-08 15:25:15 +08:00
|
|
|
* + max(per_cpu(nr_task_bp_pinned, cpu)))) < HBP_NUM
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
*
|
|
|
|
* -> If there are already non-pinned counters in this cpu, it means
|
|
|
|
* there is already a free slot for them.
|
|
|
|
* Otherwise, we check that the maximum number of per task
|
|
|
|
* breakpoints (for this cpu) plus the number of per cpu breakpoint
|
|
|
|
* (for this cpu) doesn't cover every registers.
|
|
|
|
*
|
|
|
|
* - If attached to every cpus, check:
|
|
|
|
*
|
|
|
|
* (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
|
2009-12-08 15:25:15 +08:00
|
|
|
* + max(per_cpu(nr_task_bp_pinned, *)))) < HBP_NUM
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
*
|
|
|
|
* -> This is roughly the same, except we check the number of per cpu
|
|
|
|
* bp for every cpu and we keep the max one. Same for the per tasks
|
|
|
|
* breakpoints.
|
|
|
|
*
|
|
|
|
*
|
|
|
|
* == Pinned counter ==
|
|
|
|
*
|
|
|
|
* - If attached to a single cpu, check:
|
|
|
|
*
|
|
|
|
* ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
|
2009-12-08 15:25:15 +08:00
|
|
|
* + max(per_cpu(nr_task_bp_pinned, cpu))) < HBP_NUM
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
*
|
|
|
|
* -> Same checks as before. But now the nr_bp_flexible, if any, must keep
|
|
|
|
* one register at least (or they will never be fed).
|
|
|
|
*
|
|
|
|
* - If attached to every cpus, check:
|
|
|
|
*
|
|
|
|
* ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
|
2009-12-08 15:25:15 +08:00
|
|
|
* + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
*/
|
2010-01-29 07:04:43 +08:00
|
|
|
static int __reserve_bp_slot(struct perf_event *bp)
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
{
|
|
|
|
struct bp_busy_slots slots = {0};
|
2010-04-12 00:55:56 +08:00
|
|
|
enum bp_type_idx type;
|
2010-04-13 06:32:30 +08:00
|
|
|
int weight;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
2010-04-23 11:59:55 +08:00
|
|
|
/* We couldn't initialize breakpoint constraints on boot */
|
|
|
|
if (!constraints_initialized)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
/* Basic checks */
|
|
|
|
if (bp->attr.bp_type == HW_BREAKPOINT_EMPTY ||
|
|
|
|
bp->attr.bp_type == HW_BREAKPOINT_INVALID)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
type = find_slot_idx(bp);
|
2010-04-13 06:32:30 +08:00
|
|
|
weight = hw_breakpoint_weight(bp);
|
|
|
|
|
2010-04-12 00:55:56 +08:00
|
|
|
fetch_bp_busy_slots(&slots, bp, type);
|
hw_breakpoints: Fix per task breakpoint tracking
Freeing a perf event can happen in several ways. A task
calls perf_event_exit_task() right before exiting. This helper
will detach all the events from the task context and queue their
removal through free_event() if they are child tasks. The task
also loses its context reference there.
Releasing the breakpoint slot from the constraint table is made
from free_event() that calls release_bp_slot(). We count the number
of breakpoints this task is running by looking at the task's
perf_event_ctxp and iterating through its attached events.
But at this time, the reference to this context has been cleaned up
already.
So looking at the event->ctx instead of task->perf_event_ctxp
to count the remaining breakpoints should solve the problem.
At least it would for child breakpoints, but not for parent ones.
If the parent exits before the child, it will remove all its
events from the context but free_event() will be called later,
on fd release time. And checking the number of breakpoints the
task has attached to its context at this time is unreliable as all
events have been removed from the context.
To solve this, we keep track of the list of per task breakpoints.
On top of it, we maintain our array of numbers of breakpoints used
by the tasks. We use the context address as a task id.
So, instead of looking at the number of events attached to a context,
we walk through our list of per task breakpoints and count the number
of breakpoints that use the same ctx than the one to be reserved or
released from the constraint table, and update the count on top of this
result.
In the meantime it solves a bad refcounting, it also solves a warning,
reported by Paul.
Badness at /home/paulus/kernel/perf/kernel/hw_breakpoint.c:114
NIP: c0000000000cb470 LR: c0000000000cb46c CTR: c00000000032d9b8
REGS: c000000118e7b570 TRAP: 0700 Not tainted (2.6.35-rc3-perf-00008-g76b0f13
)
MSR: 9000000000029032 <EE,ME,CE,IR,DR> CR: 44004424 XER: 000fffff
TASK = c0000001187dcad0[3143] 'perf' THREAD: c000000118e78000 CPU: 1
GPR00: c0000000000cb46c c000000118e7b7f0 c0000000009866a0 0000000000000020
GPR04: 0000000000000000 000000000000001d 0000000000000000 0000000000000001
GPR08: c0000000009bed68 c00000000086dff8 c000000000a5bf10 0000000000000001
GPR12: 0000000024004422 c00000000ffff200 0000000000000000 0000000000000000
GPR16: 0000000000000000 0000000000000000 0000000000000018 00000000101150f4
GPR20: 0000000010206b40 0000000000000000 0000000000000000 00000000101150f4
GPR24: c0000001199090c0 0000000000000001 0000000000000000 0000000000000001
GPR28: 0000000000000000 0000000000000000 c0000000008ec290 0000000000000000
NIP [c0000000000cb470] .task_bp_pinned+0x5c/0x12c
LR [c0000000000cb46c] .task_bp_pinned+0x58/0x12c
Call Trace:
[c000000118e7b7f0] [c0000000000cb46c] .task_bp_pinned+0x58/0x12c (unreliable)
[c000000118e7b8a0] [c0000000000cb584] .toggle_bp_task_slot+0x44/0xe4
[c000000118e7b940] [c0000000000cb6c8] .toggle_bp_slot+0xa4/0x164
[c000000118e7b9f0] [c0000000000cbafc] .release_bp_slot+0x44/0x6c
[c000000118e7ba80] [c0000000000c4178] .bp_perf_event_destroy+0x10/0x24
[c000000118e7bb00] [c0000000000c4aec] .free_event+0x180/0x1bc
[c000000118e7bbc0] [c0000000000c54c4] .perf_event_release_kernel+0x14c/0x170
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
2010-06-24 05:00:37 +08:00
|
|
|
/*
|
|
|
|
* Simulate the addition of this breakpoint to the constraints
|
|
|
|
* and see the result.
|
|
|
|
*/
|
2010-04-13 06:32:30 +08:00
|
|
|
fetch_this_slot(&slots, weight);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
/* Flexible counters need to keep at least one slot */
|
2010-04-23 11:59:55 +08:00
|
|
|
if (slots.pinned + (!!slots.flexible) > nr_slots[type])
|
2010-01-29 07:04:43 +08:00
|
|
|
return -ENOSPC;
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
2010-04-13 06:32:30 +08:00
|
|
|
toggle_bp_slot(bp, true, type, weight);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
2010-01-29 07:04:43 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int reserve_bp_slot(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
mutex_lock(&nr_bp_mutex);
|
|
|
|
|
|
|
|
ret = __reserve_bp_slot(bp);
|
|
|
|
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
mutex_unlock(&nr_bp_mutex);
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2010-01-29 07:04:43 +08:00
|
|
|
static void __release_bp_slot(struct perf_event *bp)
|
|
|
|
{
|
2010-04-12 00:55:56 +08:00
|
|
|
enum bp_type_idx type;
|
2010-04-13 06:32:30 +08:00
|
|
|
int weight;
|
2010-04-12 00:55:56 +08:00
|
|
|
|
|
|
|
type = find_slot_idx(bp);
|
2010-04-13 06:32:30 +08:00
|
|
|
weight = hw_breakpoint_weight(bp);
|
|
|
|
toggle_bp_slot(bp, false, type, weight);
|
2010-01-29 07:04:43 +08:00
|
|
|
}
|
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
void release_bp_slot(struct perf_event *bp)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
mutex_lock(&nr_bp_mutex);
|
|
|
|
|
2010-06-15 14:04:34 +08:00
|
|
|
arch_unregister_hw_breakpoint(bp);
|
2010-01-29 07:04:43 +08:00
|
|
|
__release_bp_slot(bp);
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
|
|
|
mutex_unlock(&nr_bp_mutex);
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
|
2010-01-29 07:04:43 +08:00
|
|
|
/*
|
|
|
|
* Allow the kernel debugger to reserve breakpoint slots without
|
|
|
|
* taking a lock using the dbg_* variant of for the reserve and
|
|
|
|
* release breakpoint slots.
|
|
|
|
*/
|
|
|
|
int dbg_reserve_bp_slot(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
if (mutex_is_locked(&nr_bp_mutex))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return __reserve_bp_slot(bp);
|
|
|
|
}
|
|
|
|
|
|
|
|
int dbg_release_bp_slot(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
if (mutex_is_locked(&nr_bp_mutex))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
__release_bp_slot(bp);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
hw-breakpoints: Arbitrate access to pmu following registers constraints
Allow or refuse to build a counter using the breakpoints pmu following
given constraints.
We keep track of the pmu users by using three per cpu variables:
- nr_cpu_bp_pinned stores the number of pinned cpu breakpoints counters
in the given cpu
- nr_bp_flexible stores the number of non-pinned breakpoints counters
in the given cpu.
- task_bp_pinned stores the number of pinned task breakpoints in a cpu
The latter is not a simple counter but gathers the number of tasks that
have n pinned breakpoints.
Considering HBP_NUM the number of available breakpoint address
registers:
task_bp_pinned[0] is the number of tasks having 1 breakpoint
task_bp_pinned[1] is the number of tasks having 2 breakpoints
[...]
task_bp_pinned[HBP_NUM - 1] is the number of tasks having the
maximum number of registers (HBP_NUM).
When a breakpoint counter is created and wants an access to the pmu,
we evaluate the following constraints:
== Non-pinned counter ==
- If attached to a single cpu, check:
(per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
-> If there are already non-pinned counters in this cpu, it
means there is already a free slot for them.
Otherwise, we check that the maximum number of per task
breakpoints (for this cpu) plus the number of per cpu
breakpoint (for this cpu) doesn't cover every registers.
- If attached to every cpus, check:
(per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
-> This is roughly the same, except we check the number of per
cpu bp for every cpu and we keep the max one. Same for the
per tasks breakpoints.
== Pinned counter ==
- If attached to a single cpu, check:
((per_cpu(nr_bp_flexible, cpu) > 1)
+ per_cpu(nr_cpu_bp_pinned, cpu)
+ max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
-> Same checks as before. But now the nr_bp_flexible, if any,
must keep one register at least (or flexible breakpoints will
never be be fed).
- If attached to every cpus, check:
((per_cpu(nr_bp_flexible, *) > 1)
+ max(per_cpu(nr_cpu_bp_pinned, *))
+ max(per_cpu(task_bp_pinned, *))) < HBP_NUM
Changes in v2:
- Counter -> event rename
Changes in v5:
- Fix unreleased non-pinned task-bound-only counters. We only released
it in the first cpu. (Thanks to Paul Mackerras for reporting that)
Changes in v6:
- Currently, events scheduling are done in this order: cpu context
pinned + cpu context non-pinned + task context pinned + task context
non-pinned events. Then our current constraints are right theoretically
but not in practice, because non-pinned counters may be scheduled
before we can apply every possible pinned counters. So consider
non-pinned counters as pinned for now.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Prasad <prasad@linux.vnet.ibm.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jan Kiszka <jan.kiszka@web.de>
Cc: Jiri Slaby <jirislaby@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Paul Mundt <lethal@linux-sh.org>
2009-09-10 15:26:21 +08:00
|
|
|
|
2010-04-19 00:11:53 +08:00
|
|
|
static int validate_hw_breakpoint(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = arch_validate_hwbkpt_settings(bp);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (arch_check_bp_in_kernelspace(bp)) {
|
|
|
|
if (bp->attr.exclude_kernel)
|
|
|
|
return -EINVAL;
|
|
|
|
/*
|
|
|
|
* Don't let unprivileged users set a breakpoint in the trap
|
|
|
|
* path to avoid trap recursion attacks.
|
|
|
|
*/
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
|
|
return -EPERM;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-12-05 16:44:31 +08:00
|
|
|
int register_perf_hw_breakpoint(struct perf_event *bp)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2009-09-10 01:22:48 +08:00
|
|
|
int ret;
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
ret = reserve_bp_slot(bp);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2010-04-19 00:11:53 +08:00
|
|
|
ret = validate_hw_breakpoint(bp);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2010-01-21 20:55:16 +08:00
|
|
|
/* if arch_validate_hwbkpt_settings() fails then release bp slot */
|
|
|
|
if (ret)
|
|
|
|
release_bp_slot(bp);
|
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
return ret;
|
|
|
|
}
|
2009-06-02 02:13:33 +08:00
|
|
|
|
|
|
|
/**
|
|
|
|
* register_user_hw_breakpoint - register a hardware breakpoint for user space
|
2009-11-27 11:55:53 +08:00
|
|
|
* @attr: breakpoint attributes
|
2009-09-10 01:22:48 +08:00
|
|
|
* @triggered: callback to trigger when we hit the breakpoint
|
2009-06-02 02:13:33 +08:00
|
|
|
* @tsk: pointer to 'task_struct' of the process to which the address belongs
|
|
|
|
*/
|
2009-09-10 01:22:48 +08:00
|
|
|
struct perf_event *
|
2009-11-27 11:55:53 +08:00
|
|
|
register_user_hw_breakpoint(struct perf_event_attr *attr,
|
2009-12-05 16:44:31 +08:00
|
|
|
perf_overflow_handler_t triggered,
|
2009-11-27 11:55:53 +08:00
|
|
|
struct task_struct *tsk)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2009-11-27 11:55:53 +08:00
|
|
|
return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* modify_user_hw_breakpoint - modify a user-space hardware breakpoint
|
2009-09-10 01:22:48 +08:00
|
|
|
* @bp: the breakpoint structure to modify
|
2009-11-27 11:55:53 +08:00
|
|
|
* @attr: new breakpoint attributes
|
2009-09-10 01:22:48 +08:00
|
|
|
* @triggered: callback to trigger when we hit the breakpoint
|
2009-06-02 02:13:33 +08:00
|
|
|
* @tsk: pointer to 'task_struct' of the process to which the address belongs
|
|
|
|
*/
|
2009-12-09 16:25:48 +08:00
|
|
|
int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2009-12-09 16:25:48 +08:00
|
|
|
u64 old_addr = bp->attr.bp_addr;
|
2010-01-30 12:55:18 +08:00
|
|
|
u64 old_len = bp->attr.bp_len;
|
2009-12-09 16:25:48 +08:00
|
|
|
int old_type = bp->attr.bp_type;
|
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
perf_event_disable(bp);
|
|
|
|
|
|
|
|
bp->attr.bp_addr = attr->bp_addr;
|
|
|
|
bp->attr.bp_type = attr->bp_type;
|
|
|
|
bp->attr.bp_len = attr->bp_len;
|
|
|
|
|
|
|
|
if (attr->disabled)
|
|
|
|
goto end;
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2010-04-19 00:11:53 +08:00
|
|
|
err = validate_hw_breakpoint(bp);
|
2009-12-09 16:25:48 +08:00
|
|
|
if (!err)
|
|
|
|
perf_event_enable(bp);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
bp->attr.bp_addr = old_addr;
|
|
|
|
bp->attr.bp_type = old_type;
|
|
|
|
bp->attr.bp_len = old_len;
|
|
|
|
if (!bp->attr.disabled)
|
|
|
|
perf_event_enable(bp);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
end:
|
|
|
|
bp->attr.disabled = attr->disabled;
|
|
|
|
|
|
|
|
return 0;
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
|
|
|
|
|
|
|
|
/**
|
2009-09-10 01:22:48 +08:00
|
|
|
* unregister_hw_breakpoint - unregister a user-space hardware breakpoint
|
2009-06-02 02:13:33 +08:00
|
|
|
* @bp: the breakpoint structure to unregister
|
|
|
|
*/
|
2009-09-10 01:22:48 +08:00
|
|
|
void unregister_hw_breakpoint(struct perf_event *bp)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2009-09-10 01:22:48 +08:00
|
|
|
if (!bp)
|
|
|
|
return;
|
|
|
|
perf_event_release_kernel(bp);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
|
|
|
|
|
2009-06-02 02:13:33 +08:00
|
|
|
/**
|
2009-09-10 01:22:48 +08:00
|
|
|
* register_wide_hw_breakpoint - register a wide breakpoint in the kernel
|
2009-11-27 11:55:54 +08:00
|
|
|
* @attr: breakpoint attributes
|
2009-09-10 01:22:48 +08:00
|
|
|
* @triggered: callback to trigger when we hit the breakpoint
|
2009-06-02 02:13:33 +08:00
|
|
|
*
|
2009-09-10 01:22:48 +08:00
|
|
|
* @return a set of per_cpu pointers to perf events
|
2009-06-02 02:13:33 +08:00
|
|
|
*/
|
2010-02-17 09:50:50 +08:00
|
|
|
struct perf_event * __percpu *
|
2009-11-27 11:55:54 +08:00
|
|
|
register_wide_hw_breakpoint(struct perf_event_attr *attr,
|
2009-12-05 16:44:31 +08:00
|
|
|
perf_overflow_handler_t triggered)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2010-02-17 09:50:50 +08:00
|
|
|
struct perf_event * __percpu *cpu_events, **pevent, *bp;
|
2009-09-10 01:22:48 +08:00
|
|
|
long err;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
cpu_events = alloc_percpu(typeof(*cpu_events));
|
|
|
|
if (!cpu_events)
|
2010-02-17 09:50:50 +08:00
|
|
|
return (void __percpu __force *)ERR_PTR(-ENOMEM);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-12-30 14:22:22 +08:00
|
|
|
get_online_cpus();
|
|
|
|
for_each_online_cpu(cpu) {
|
2009-09-10 01:22:48 +08:00
|
|
|
pevent = per_cpu_ptr(cpu_events, cpu);
|
2009-11-27 11:55:54 +08:00
|
|
|
bp = perf_event_create_kernel_counter(attr, cpu, -1, triggered);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
*pevent = bp;
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-11-26 12:35:42 +08:00
|
|
|
if (IS_ERR(bp)) {
|
2009-09-10 01:22:48 +08:00
|
|
|
err = PTR_ERR(bp);
|
|
|
|
goto fail;
|
|
|
|
}
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
2009-12-30 14:22:22 +08:00
|
|
|
put_online_cpus();
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
return cpu_events;
|
|
|
|
|
|
|
|
fail:
|
2009-12-30 14:22:22 +08:00
|
|
|
for_each_online_cpu(cpu) {
|
2009-09-10 01:22:48 +08:00
|
|
|
pevent = per_cpu_ptr(cpu_events, cpu);
|
2009-11-26 12:35:42 +08:00
|
|
|
if (IS_ERR(*pevent))
|
2009-09-10 01:22:48 +08:00
|
|
|
break;
|
|
|
|
unregister_hw_breakpoint(*pevent);
|
|
|
|
}
|
2009-12-30 14:22:22 +08:00
|
|
|
put_online_cpus();
|
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
free_percpu(cpu_events);
|
2010-02-17 09:50:50 +08:00
|
|
|
return (void __percpu __force *)ERR_PTR(err);
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
2009-11-10 17:17:07 +08:00
|
|
|
EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
|
|
|
/**
|
2009-09-10 01:22:48 +08:00
|
|
|
* unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
|
|
|
|
* @cpu_events: the per cpu set of events to unregister
|
2009-06-02 02:13:33 +08:00
|
|
|
*/
|
2010-02-17 09:50:50 +08:00
|
|
|
void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
|
2009-06-02 02:13:33 +08:00
|
|
|
{
|
2009-09-10 01:22:48 +08:00
|
|
|
int cpu;
|
|
|
|
struct perf_event **pevent;
|
2009-06-02 02:13:33 +08:00
|
|
|
|
2009-09-10 01:22:48 +08:00
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
pevent = per_cpu_ptr(cpu_events, cpu);
|
|
|
|
unregister_hw_breakpoint(*pevent);
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
2009-09-10 01:22:48 +08:00
|
|
|
free_percpu(cpu_events);
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
2009-11-10 17:17:07 +08:00
|
|
|
EXPORT_SYMBOL_GPL(unregister_wide_hw_breakpoint);
|
2009-06-02 02:13:33 +08:00
|
|
|
|
|
|
|
static struct notifier_block hw_breakpoint_exceptions_nb = {
|
|
|
|
.notifier_call = hw_breakpoint_exceptions_notify,
|
|
|
|
/* we need to be notified first */
|
|
|
|
.priority = 0x7fffffff
|
|
|
|
};
|
|
|
|
|
2010-06-11 19:35:08 +08:00
|
|
|
static void bp_perf_event_destroy(struct perf_event *event)
|
|
|
|
{
|
|
|
|
release_bp_slot(event);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int hw_breakpoint_event_init(struct perf_event *bp)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (bp->attr.type != PERF_TYPE_BREAKPOINT)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
err = register_perf_hw_breakpoint(bp);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
bp->destroy = bp_perf_event_destroy;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 20:37:10 +08:00
|
|
|
static int hw_breakpoint_add(struct perf_event *bp, int flags)
|
|
|
|
{
|
|
|
|
if (!(flags & PERF_EF_START))
|
|
|
|
bp->hw.state = PERF_HES_STOPPED;
|
|
|
|
|
|
|
|
return arch_install_hw_breakpoint(bp);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void hw_breakpoint_del(struct perf_event *bp, int flags)
|
|
|
|
{
|
|
|
|
arch_uninstall_hw_breakpoint(bp);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void hw_breakpoint_start(struct perf_event *bp, int flags)
|
|
|
|
{
|
|
|
|
bp->hw.state = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void hw_breakpoint_stop(struct perf_event *bp, int flags)
|
|
|
|
{
|
|
|
|
bp->hw.state = PERF_HES_STOPPED;
|
|
|
|
}
|
|
|
|
|
2010-06-11 19:35:08 +08:00
|
|
|
static struct pmu perf_breakpoint = {
|
2010-09-07 23:34:50 +08:00
|
|
|
.task_ctx_nr = perf_sw_context, /* could eventually get its own */
|
|
|
|
|
2010-06-11 19:35:08 +08:00
|
|
|
.event_init = hw_breakpoint_event_init,
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 20:37:10 +08:00
|
|
|
.add = hw_breakpoint_add,
|
|
|
|
.del = hw_breakpoint_del,
|
|
|
|
.start = hw_breakpoint_start,
|
|
|
|
.stop = hw_breakpoint_stop,
|
2010-06-11 19:35:08 +08:00
|
|
|
.read = hw_breakpoint_pmu_read,
|
|
|
|
};
|
|
|
|
|
2009-06-02 02:13:33 +08:00
|
|
|
static int __init init_hw_breakpoint(void)
|
|
|
|
{
|
2010-04-23 11:59:55 +08:00
|
|
|
unsigned int **task_bp_pinned;
|
|
|
|
int cpu, err_cpu;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < TYPE_MAX; i++)
|
|
|
|
nr_slots[i] = hw_breakpoint_slots(i);
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
for (i = 0; i < TYPE_MAX; i++) {
|
|
|
|
task_bp_pinned = &per_cpu(nr_task_bp_pinned[i], cpu);
|
|
|
|
*task_bp_pinned = kzalloc(sizeof(int) * nr_slots[i],
|
|
|
|
GFP_KERNEL);
|
|
|
|
if (!*task_bp_pinned)
|
|
|
|
goto err_alloc;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
constraints_initialized = 1;
|
|
|
|
|
2010-06-11 19:35:08 +08:00
|
|
|
perf_pmu_register(&perf_breakpoint);
|
|
|
|
|
2009-06-02 02:13:33 +08:00
|
|
|
return register_die_notifier(&hw_breakpoint_exceptions_nb);
|
2010-04-23 11:59:55 +08:00
|
|
|
|
|
|
|
err_alloc:
|
|
|
|
for_each_possible_cpu(err_cpu) {
|
|
|
|
if (err_cpu == cpu)
|
|
|
|
break;
|
|
|
|
for (i = 0; i < TYPE_MAX; i++)
|
|
|
|
kfree(per_cpu(nr_task_bp_pinned[i], cpu));
|
|
|
|
}
|
|
|
|
|
|
|
|
return -ENOMEM;
|
2009-06-02 02:13:33 +08:00
|
|
|
}
|
|
|
|
core_initcall(init_hw_breakpoint);
|
2009-09-10 01:22:48 +08:00
|
|
|
|
|
|
|
|