linux/arch/x86/kernel/cpu/perfctr-watchdog.c

161 lines
4.0 KiB
C
Raw Normal View History

/*
* local apic based NMI watchdog for various CPUs.
*
* This file also handles reservation of performance counters for coordination
* with other users (like oprofile).
*
* Note that these events normally don't tick when the CPU idles. This means
* the frequency varies with CPU load.
*
* Original code for K7/P6 written by Keith Owens
*
*/
#include <linux/percpu.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/smp.h>
x86, nmi_watchdog: Remove ARCH_HAS_NMI_WATCHDOG and rely on CONFIG_HARDLOCKUP_DETECTOR The x86 arch has shifted its use of the nmi_watchdog from a local implementation to the global one provide by kernel/watchdog.c. This shift has caused a whole bunch of compile problems under different config options. I attempt to simplify things with the patch below. In order to simplify things, I had to come to terms with the meaning of two terms ARCH_HAS_NMI_WATCHDOG and CONFIG_HARDLOCKUP_DETECTOR. Basically they mean the same thing, the former on a local level and the latter on a global level. With the old x86 nmi watchdog gone, there is no need to rely on defining the ARCH_HAS_NMI_WATCHDOG variable because it doesn't make sense any more. x86 will now use the global implementation. The changes below do a few things. First it changes the few places that relied on ARCH_HAS_NMI_WATCHDOG to use CONFIG_X86_LOCAL_APIC (the former was an alias for the latter anyway, so nothing unusual here). Those pieces of code were relying more on local apic functionality the nmi watchdog functionality, so the change should make sense. Second, I removed the x86 implementation of touch_nmi_watchdog(). It isn't need now, instead x86 will rely on kernel/watchdog.c's implementation. Third, I removed the #define ARCH_HAS_NMI_WATCHDOG itself from x86. And tweaked the include/linux/nmi.h file to tell users to look for an externally defined touch_nmi_watchdog in the case of ARCH_HAS_NMI_WATCHDOG _or_ CONFIG_HARDLOCKUP_DETECTOR. This changes removes some of the ugliness in that file. Finally, I added a Kconfig dependency for CONFIG_HARDLOCKUP_DETECTOR that said you can't have ARCH_HAS_NMI_WATCHDOG _and_ CONFIG_HARDLOCKUP_DETECTOR. You can only have one nmi_watchdog. Tested with ARCH=i386: allnoconfig, defconfig, allyesconfig, (various broken configs) ARCH=x86_64: allnoconfig, defconfig, allyesconfig, (various broken configs) Hopefully, after this patch I won't get any more compile broken emails. :-) v3: changed a couple of 'linux/nmi.h' -> 'asm/nmi.h' to pick-up correct function prototypes when CONFIG_HARDLOCKUP_DETECTOR is not set. Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com LKML-Reference: <1293044403-14117-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-12-23 03:00:03 +08:00
#include <asm/nmi.h>
ftrace: mark lapic_wd_event() notrace it can be called in the NMI path: [ 0.645999] calling ftrace_dynamic_init+0x0/0xd6 [ 0.647521] ------------[ cut here ]------------ [ 0.647521] WARNING: at kernel/trace/ftrace.c:348 ftrace_record_ip+0x4e/0x252() [ 0.647521] Modules linked in: [ 0.647521] Pid: 15, comm: kstop1 Not tainted 2.6.27-rc1-tip #22686 [ 0.647521] [ 0.647521] Call Trace: [ 0.647521] <NMI> [<ffffffff8024593f>] warn_on_slowpath+0x5d/0x84 [ 0.647521] [<ffffffff80220b99>] ? lapic_wd_event+0xb/0x5c [ 0.647521] [<ffffffff80287b3b>] ftrace_record_ip+0x4e/0x252 [ 0.647521] [<ffffffff80211274>] mcount_call+0x5/0x31 [ 0.647521] [<ffffffff80220b9e>] ? lapic_wd_event+0x10/0x5c [ 0.647521] [<ffffffff8083f3ec>] nmi_watchdog_tick+0x19d/0x1ad [ 0.647521] [<ffffffff8083e875>] default_do_nmi+0x75/0x1e3 [ 0.647521] [<ffffffff8083f0b3>] do_nmi+0x5d/0x94 [ 0.647521] [<ffffffff8083e2d2>] nmi+0xa2/0xc2 [ 0.647521] [<ffffffff802b48c3>] ? check_bytes_and_report+0x11/0xcc [ 0.647521] <<EOE>> [<ffffffff80211274>] ? mcount_call+0x5/0x31 [ 0.647521] [<ffffffff802b49df>] check_object+0x61/0x1b0 [ 0.647521] [<ffffffff802b502a>] __slab_free+0x169/0x2ae [ 0.647521] [<ffffffff80242dbf>] ? __cleanup_sighand+0x25/0x27 [ 0.647521] [<ffffffff80242dbf>] ? __cleanup_sighand+0x25/0x27 [ 0.647521] [<ffffffff802b60cd>] kmem_cache_free+0x85/0xb9 [ 0.647521] [<ffffffff80242dbf>] __cleanup_sighand+0x25/0x27 [ 0.647521] [<ffffffff80247b3d>] release_task+0x256/0x339 [ 0.647521] [<ffffffff802490b4>] do_exit+0x764/0x7ef [ 0.647521] [<ffffffff8027624c>] __xchg+0x0/0x38 [ 0.647521] [<ffffffff8027619a>] ? stop_cpu+0x0/0xb2 [ 0.647521] [<ffffffff8027619a>] ? stop_cpu+0x0/0xb2 [ 0.647521] [<ffffffff8025922f>] kthread+0x4e/0x7b [ 0.647521] [<ffffffff80212979>] child_rip+0xa/0x11 [ 0.647521] [<ffffffff80211c17>] ? restore_args+0x0/0x30 [ 0.647521] [<ffffffff802283a5>] ? native_load_tls+0x14/0x2e [ 0.647521] [<ffffffff802591e1>] ? kthread+0x0/0x7b [ 0.647521] [<ffffffff8021296f>] ? child_rip+0x0/0x11 [ 0.647521] [ 0.647521] ---[ end trace 4eaa2a86a8e2da22 ]--- [ 0.672032] initcall ftrace_dynamic_init+0x0/0xd6 returned 0 after 19 msecs also mark it no-kprobes while at it. Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-29 18:36:02 +08:00
#include <linux/kprobes.h>
#include <asm/apic.h>
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
#include <asm/perf_event.h>
/*
* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
* offset from MSR_P4_BSU_ESCR0.
*
* It will be the max for all platforms (for now)
*/
#define NMI_MAX_COUNTER_BITS 66
/*
* perfctr_nmi_owner tracks the ownership of the perfctr registers:
* evtsel_nmi_owner tracks the ownership of the event selection
* - different performance counters/ event selection may be reserved for
* different subsystems this reservation system just tries to coordinate
* things a little
*/
static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
/* converts an msr to an appropriate reservation bit */
static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the performance counter register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTR)
return (msr - MSR_F15H_PERF_CTR) >> 1;
return msr - MSR_K7_PERFCTR0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
return msr - MSR_ARCH_PERFMON_PERFCTR0;
switch (boot_cpu_data.x86) {
case 6:
return msr - MSR_P6_PERFCTR0;
case 11:
return msr - MSR_KNC_PERFCTR0;
case 15:
return msr - MSR_P4_BPU_PERFCTR0;
}
}
return 0;
}
/*
* converts an msr to an appropriate reservation bit
* returns the bit offset of the event selection register
*/
static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the event selection register */
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
if (msr >= MSR_F15H_PERF_CTL)
return (msr - MSR_F15H_PERF_CTL) >> 1;
return msr - MSR_K7_EVNTSEL0;
case X86_VENDOR_INTEL:
if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
return msr - MSR_ARCH_PERFMON_EVENTSEL0;
switch (boot_cpu_data.x86) {
case 6:
return msr - MSR_P6_EVNTSEL0;
case 11:
return msr - MSR_KNC_EVNTSEL0;
case 15:
return msr - MSR_P4_BSU_ESCR0;
}
}
return 0;
}
/* checks for a bit availability (hack for oprofile) */
int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
{
BUG_ON(counter > NMI_MAX_COUNTER_BITS);
return !test_bit(counter, perfctr_nmi_owner);
}
EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
int reserve_perfctr_nmi(unsigned int msr)
{
unsigned int counter;
counter = nmi_perfctr_msr_to_bit(msr);
/* register not managed by the allocator? */
if (counter > NMI_MAX_COUNTER_BITS)
return 1;
if (!test_and_set_bit(counter, perfctr_nmi_owner))
return 1;
return 0;
}
EXPORT_SYMBOL(reserve_perfctr_nmi);
void release_perfctr_nmi(unsigned int msr)
{
unsigned int counter;
counter = nmi_perfctr_msr_to_bit(msr);
/* register not managed by the allocator? */
if (counter > NMI_MAX_COUNTER_BITS)
return;
clear_bit(counter, perfctr_nmi_owner);
}
EXPORT_SYMBOL(release_perfctr_nmi);
int reserve_evntsel_nmi(unsigned int msr)
{
unsigned int counter;
counter = nmi_evntsel_msr_to_bit(msr);
/* register not managed by the allocator? */
if (counter > NMI_MAX_COUNTER_BITS)
return 1;
if (!test_and_set_bit(counter, evntsel_nmi_owner))
return 1;
return 0;
}
EXPORT_SYMBOL(reserve_evntsel_nmi);
void release_evntsel_nmi(unsigned int msr)
{
unsigned int counter;
counter = nmi_evntsel_msr_to_bit(msr);
/* register not managed by the allocator? */
if (counter > NMI_MAX_COUNTER_BITS)
return;
clear_bit(counter, evntsel_nmi_owner);
}
EXPORT_SYMBOL(release_evntsel_nmi);