linux_dsm_epyc7002/arch/x86/events/intel/cqm.c

1392 lines
33 KiB
C
Raw Normal View History

/*
* Intel Cache Quality-of-Service Monitoring (CQM) support.
*
* Based very, very heavily on work by Peter Zijlstra.
*/
#include <linux/perf_event.h>
#include <linux/slab.h>
#include <asm/cpu_device_id.h>
#include "../../kernel/cpu/perf_event.h"
#define MSR_IA32_PQR_ASSOC 0x0c8f
#define MSR_IA32_QM_CTR 0x0c8e
#define MSR_IA32_QM_EVTSEL 0x0c8d
static u32 cqm_max_rmid = -1;
static unsigned int cqm_l3_scale; /* supposedly cacheline size */
/**
* struct intel_pqr_state - State cache for the PQR MSR
* @rmid: The cached Resource Monitoring ID
* @closid: The cached Class Of Service ID
* @rmid_usecnt: The usage counter for rmid
*
* The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
* lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
* contains both parts, so we need to cache them.
*
* The cache also helps to avoid pointless updates if the value does
* not change.
*/
struct intel_pqr_state {
u32 rmid;
u32 closid;
int rmid_usecnt;
};
/*
* The cached intel_pqr_state is strictly per CPU and can never be
* updated from a remote CPU. Both functions which modify the state
* (intel_cqm_event_start and intel_cqm_event_stop) are called with
* interrupts disabled, which is sufficient for the protection.
*/
static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
/*
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
* Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
* Also protects event->hw.cqm_rmid
*
* Hold either for stability, both for modification of ->hw.cqm_rmid.
*/
static DEFINE_MUTEX(cache_mutex);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
static DEFINE_RAW_SPINLOCK(cache_lock);
/*
* Groups of events that have the same target(s), one RMID per group.
*/
static LIST_HEAD(cache_groups);
/*
* Mask of CPUs for reading CQM values. We only need one per-socket.
*/
static cpumask_t cqm_cpumask;
#define RMID_VAL_ERROR (1ULL << 63)
#define RMID_VAL_UNAVAIL (1ULL << 62)
#define QOS_L3_OCCUP_EVENT_ID (1 << 0)
#define QOS_EVENT_MASK QOS_L3_OCCUP_EVENT_ID
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
/*
* This is central to the rotation algorithm in __intel_cqm_rmid_rotate().
*
* This rmid is always free and is guaranteed to have an associated
* near-zero occupancy value, i.e. no cachelines are tagged with this
* RMID, once __intel_cqm_rmid_rotate() returns.
*/
static u32 intel_cqm_rotation_rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
#define INVALID_RMID (-1)
/*
* Is @rmid valid for programming the hardware?
*
* rmid 0 is reserved by the hardware for all non-monitored tasks, which
* means that we should never come across an rmid with that value.
* Likewise, an rmid value of -1 is used to indicate "no rmid currently
* assigned" and is used as part of the rotation code.
*/
static inline bool __rmid_valid(u32 rmid)
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
{
if (!rmid || rmid == INVALID_RMID)
return false;
return true;
}
static u64 __rmid_read(u32 rmid)
{
u64 val;
/*
* Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt,
* it just says that to increase confusion.
*/
wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid);
rdmsrl(MSR_IA32_QM_CTR, val);
/*
* Aside from the ERROR and UNAVAIL bits, assume this thing returns
* the number of cachelines tagged with @rmid.
*/
return val;
}
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
enum rmid_recycle_state {
RMID_YOUNG = 0,
RMID_AVAILABLE,
RMID_DIRTY,
};
struct cqm_rmid_entry {
u32 rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
enum rmid_recycle_state state;
struct list_head list;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned long queue_time;
};
/*
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
* cqm_rmid_free_lru - A least recently used list of RMIDs.
*
* Oldest entry at the head, newest (most recently used) entry at the
* tail. This list is never traversed, it's only used to keep track of
* the lru order. That is, we only pick entries of the head or insert
* them on the tail.
*
* All entries on the list are 'free', and their RMIDs are not currently
* in use. To mark an RMID as in use, remove its entry from the lru
* list.
*
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
*
* cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs.
*
* This list is contains RMIDs that no one is currently using but that
* may have a non-zero occupancy value associated with them. The
* rotation worker moves RMIDs from the limbo list to the free list once
* the occupancy value drops below __intel_cqm_threshold.
*
* Both lists are protected by cache_mutex.
*/
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
static LIST_HEAD(cqm_rmid_free_lru);
static LIST_HEAD(cqm_rmid_limbo_lru);
/*
* We use a simple array of pointers so that we can lookup a struct
* cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid()
* and __put_rmid() from having to worry about dealing with struct
* cqm_rmid_entry - they just deal with rmids, i.e. integers.
*
* Once this array is initialized it is read-only. No locks are required
* to access it.
*
* All entries for all RMIDs can be looked up in the this array at all
* times.
*/
static struct cqm_rmid_entry **cqm_rmid_ptrs;
static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
{
struct cqm_rmid_entry *entry;
entry = cqm_rmid_ptrs[rmid];
WARN_ON(entry->rmid != rmid);
return entry;
}
/*
* Returns < 0 on fail.
*
* We expect to be called with cache_mutex held.
*/
static u32 __get_rmid(void)
{
struct cqm_rmid_entry *entry;
lockdep_assert_held(&cache_mutex);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (list_empty(&cqm_rmid_free_lru))
return INVALID_RMID;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list);
list_del(&entry->list);
return entry->rmid;
}
static void __put_rmid(u32 rmid)
{
struct cqm_rmid_entry *entry;
lockdep_assert_held(&cache_mutex);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
WARN_ON(!__rmid_valid(rmid));
entry = __rmid_entry(rmid);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
entry->queue_time = jiffies;
entry->state = RMID_YOUNG;
list_add_tail(&entry->list, &cqm_rmid_limbo_lru);
}
static int intel_cqm_setup_rmid_cache(void)
{
struct cqm_rmid_entry *entry;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned int nr_rmids;
int r = 0;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
nr_rmids = cqm_max_rmid + 1;
cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) *
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
nr_rmids, GFP_KERNEL);
if (!cqm_rmid_ptrs)
return -ENOMEM;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
for (; r <= cqm_max_rmid; r++) {
struct cqm_rmid_entry *entry;
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
goto fail;
INIT_LIST_HEAD(&entry->list);
entry->rmid = r;
cqm_rmid_ptrs[r] = entry;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
list_add_tail(&entry->list, &cqm_rmid_free_lru);
}
/*
* RMID 0 is special and is always allocated. It's used for all
* tasks that are not monitored.
*/
entry = __rmid_entry(0);
list_del(&entry->list);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
mutex_lock(&cache_mutex);
intel_cqm_rotation_rmid = __get_rmid();
mutex_unlock(&cache_mutex);
return 0;
fail:
while (r--)
kfree(cqm_rmid_ptrs[r]);
kfree(cqm_rmid_ptrs);
return -ENOMEM;
}
/*
* Determine if @a and @b measure the same set of tasks.
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
*
* If @a and @b measure the same set of tasks then we want to share a
* single RMID.
*/
static bool __match_event(struct perf_event *a, struct perf_event *b)
{
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
/* Per-cpu and task events don't mix */
if ((a->attach_state & PERF_ATTACH_TASK) !=
(b->attach_state & PERF_ATTACH_TASK))
return false;
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
#ifdef CONFIG_CGROUP_PERF
if (a->cgrp != b->cgrp)
return false;
#endif
/* If not task event, we're machine wide */
if (!(b->attach_state & PERF_ATTACH_TASK))
return true;
/*
* Events that target same task are placed into the same cache group.
*/
if (a->hw.target == b->hw.target)
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
return true;
/*
* Are we an inherited event?
*/
if (b->parent == a)
return true;
return false;
}
#ifdef CONFIG_CGROUP_PERF
static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
{
if (event->attach_state & PERF_ATTACH_TASK)
return perf_cgroup_from_task(event->hw.target, event->ctx);
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
return event->cgrp;
}
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
#endif
/*
* Determine if @a's tasks intersect with @b's tasks
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
*
* There are combinations of events that we explicitly prohibit,
*
* PROHIBITS
* system-wide -> cgroup and task
* cgroup -> system-wide
* -> task in cgroup
* task -> system-wide
* -> task in cgroup
*
* Call this function before allocating an RMID.
*/
static bool __conflict_event(struct perf_event *a, struct perf_event *b)
{
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
#ifdef CONFIG_CGROUP_PERF
/*
* We can have any number of cgroups but only one system-wide
* event at a time.
*/
if (a->cgrp && b->cgrp) {
struct perf_cgroup *ac = a->cgrp;
struct perf_cgroup *bc = b->cgrp;
/*
* This condition should have been caught in
* __match_event() and we should be sharing an RMID.
*/
WARN_ON_ONCE(ac == bc);
if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) ||
cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup))
return true;
return false;
}
if (a->cgrp || b->cgrp) {
struct perf_cgroup *ac, *bc;
/*
* cgroup and system-wide events are mutually exclusive
*/
if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) ||
(b->cgrp && !(a->attach_state & PERF_ATTACH_TASK)))
return true;
/*
* Ensure neither event is part of the other's cgroup
*/
ac = event_to_cgroup(a);
bc = event_to_cgroup(b);
if (ac == bc)
return true;
/*
* Must have cgroup and non-intersecting task events.
*/
if (!ac || !bc)
return false;
/*
* We have cgroup and task events, and the task belongs
* to a cgroup. Check for for overlap.
*/
if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) ||
cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup))
return true;
return false;
}
#endif
/*
* If one of them is not a task, same story as above with cgroups.
*/
if (!(a->attach_state & PERF_ATTACH_TASK) ||
!(b->attach_state & PERF_ATTACH_TASK))
return true;
/*
* Must be non-overlapping.
*/
return false;
}
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
struct rmid_read {
u32 rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
atomic64_t value;
};
static void __intel_cqm_event_count(void *info);
/*
* Exchange the RMID of a group of events.
*/
static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
{
struct perf_event *event;
struct list_head *head = &group->hw.cqm_group_entry;
u32 old_rmid = group->hw.cqm_rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
lockdep_assert_held(&cache_mutex);
/*
* If our RMID is being deallocated, perform a read now.
*/
if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) {
struct rmid_read rr = {
.value = ATOMIC64_INIT(0),
.rmid = old_rmid,
};
on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count,
&rr, 1);
local64_set(&group->count, atomic64_read(&rr.value));
}
raw_spin_lock_irq(&cache_lock);
group->hw.cqm_rmid = rmid;
list_for_each_entry(event, head, hw.cqm_group_entry)
event->hw.cqm_rmid = rmid;
raw_spin_unlock_irq(&cache_lock);
return old_rmid;
}
/*
* If we fail to assign a new RMID for intel_cqm_rotation_rmid because
* cachelines are still tagged with RMIDs in limbo, we progressively
* increment the threshold until we find an RMID in limbo with <=
* __intel_cqm_threshold lines tagged. This is designed to mitigate the
* problem where cachelines tagged with an RMID are not steadily being
* evicted.
*
* On successful rotations we decrease the threshold back towards zero.
*
* __intel_cqm_max_threshold provides an upper bound on the threshold,
* and is measured in bytes because it's exposed to userland.
*/
static unsigned int __intel_cqm_threshold;
static unsigned int __intel_cqm_max_threshold;
/*
* Test whether an RMID has a zero occupancy value on this cpu.
*/
static void intel_cqm_stable(void *arg)
{
struct cqm_rmid_entry *entry;
list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) {
if (entry->state != RMID_AVAILABLE)
break;
if (__rmid_read(entry->rmid) > __intel_cqm_threshold)
entry->state = RMID_DIRTY;
}
}
/*
* If we have group events waiting for an RMID that don't conflict with
* events already running, assign @rmid.
*/
static bool intel_cqm_sched_in_event(u32 rmid)
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
{
struct perf_event *leader, *event;
lockdep_assert_held(&cache_mutex);
leader = list_first_entry(&cache_groups, struct perf_event,
hw.cqm_groups_entry);
event = leader;
list_for_each_entry_continue(event, &cache_groups,
hw.cqm_groups_entry) {
if (__rmid_valid(event->hw.cqm_rmid))
continue;
if (__conflict_event(event, leader))
continue;
intel_cqm_xchg_rmid(event, rmid);
return true;
}
return false;
}
/*
* Initially use this constant for both the limbo queue time and the
* rotation timer interval, pmu::hrtimer_interval_ms.
*
* They don't need to be the same, but the two are related since if you
* rotate faster than you recycle RMIDs, you may run out of available
* RMIDs.
*/
#define RMID_DEFAULT_QUEUE_TIME 250 /* ms */
static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME;
/*
* intel_cqm_rmid_stabilize - move RMIDs from limbo to free list
* @nr_available: number of freeable RMIDs on the limbo list
*
* Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no
* cachelines are tagged with those RMIDs. After this we can reuse them
* and know that the current set of active RMIDs is stable.
*
* Return %true or %false depending on whether stabilization needs to be
* reattempted.
*
* If we return %true then @nr_available is updated to indicate the
* number of RMIDs on the limbo list that have been queued for the
* minimum queue time (RMID_AVAILABLE), but whose data occupancy values
* are above __intel_cqm_threshold.
*/
static bool intel_cqm_rmid_stabilize(unsigned int *available)
{
struct cqm_rmid_entry *entry, *tmp;
lockdep_assert_held(&cache_mutex);
*available = 0;
list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) {
unsigned long min_queue_time;
unsigned long now = jiffies;
/*
* We hold RMIDs placed into limbo for a minimum queue
* time. Before the minimum queue time has elapsed we do
* not recycle RMIDs.
*
* The reasoning is that until a sufficient time has
* passed since we stopped using an RMID, any RMID
* placed onto the limbo list will likely still have
* data tagged in the cache, which means we'll probably
* fail to recycle it anyway.
*
* We can save ourselves an expensive IPI by skipping
* any RMIDs that have not been queued for the minimum
* time.
*/
min_queue_time = entry->queue_time +
msecs_to_jiffies(__rmid_queue_time_ms);
if (time_after(min_queue_time, now))
break;
entry->state = RMID_AVAILABLE;
(*available)++;
}
/*
* Fast return if none of the RMIDs on the limbo list have been
* sitting on the queue for the minimum queue time.
*/
if (!*available)
return false;
/*
* Test whether an RMID is free for each package.
*/
on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true);
list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) {
/*
* Exhausted all RMIDs that have waited min queue time.
*/
if (entry->state == RMID_YOUNG)
break;
if (entry->state == RMID_DIRTY)
continue;
list_del(&entry->list); /* remove from limbo */
/*
* The rotation RMID gets priority if it's
* currently invalid. In which case, skip adding
* the RMID to the the free lru.
*/
if (!__rmid_valid(intel_cqm_rotation_rmid)) {
intel_cqm_rotation_rmid = entry->rmid;
continue;
}
/*
* If we have groups waiting for RMIDs, hand
* them one now provided they don't conflict.
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
*/
if (intel_cqm_sched_in_event(entry->rmid))
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
continue;
/*
* Otherwise place it onto the free list.
*/
list_add_tail(&entry->list, &cqm_rmid_free_lru);
}
return __rmid_valid(intel_cqm_rotation_rmid);
}
/*
* Pick a victim group and move it to the tail of the group list.
* @next: The first group without an RMID
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
*/
static void __intel_cqm_pick_and_rotate(struct perf_event *next)
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
{
struct perf_event *rotor;
u32 rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
lockdep_assert_held(&cache_mutex);
rotor = list_first_entry(&cache_groups, struct perf_event,
hw.cqm_groups_entry);
/*
* The group at the front of the list should always have a valid
* RMID. If it doesn't then no groups have RMIDs assigned and we
* don't need to rotate the list.
*/
if (next == rotor)
return;
rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID);
__put_rmid(rmid);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
list_rotate_left(&cache_groups);
}
/*
* Deallocate the RMIDs from any events that conflict with @event, and
* place them on the back of the group list.
*/
static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
{
struct perf_event *group, *g;
u32 rmid;
lockdep_assert_held(&cache_mutex);
list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) {
if (group == event)
continue;
rmid = group->hw.cqm_rmid;
/*
* Skip events that don't have a valid RMID.
*/
if (!__rmid_valid(rmid))
continue;
/*
* No conflict? No problem! Leave the event alone.
*/
if (!__conflict_event(group, event))
continue;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
intel_cqm_xchg_rmid(group, INVALID_RMID);
__put_rmid(rmid);
}
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
}
/*
* Attempt to rotate the groups and assign new RMIDs.
*
* We rotate for two reasons,
* 1. To handle the scheduling of conflicting events
* 2. To recycle RMIDs
*
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
* Rotating RMIDs is complicated because the hardware doesn't give us
* any clues.
*
* There's problems with the hardware interface; when you change the
* task:RMID map cachelines retain their 'old' tags, giving a skewed
* picture. In order to work around this, we must always keep one free
* RMID - intel_cqm_rotation_rmid.
*
* Rotation works by taking away an RMID from a group (the old RMID),
* and assigning the free RMID to another group (the new RMID). We must
* then wait for the old RMID to not be used (no cachelines tagged).
* This ensure that all cachelines are tagged with 'active' RMIDs. At
* this point we can start reading values for the new RMID and treat the
* old RMID as the free RMID for the next rotation.
*
* Return %true or %false depending on whether we did any rotating.
*/
static bool __intel_cqm_rmid_rotate(void)
{
struct perf_event *group, *start = NULL;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned int threshold_limit;
unsigned int nr_needed = 0;
unsigned int nr_available;
bool rotated = false;
mutex_lock(&cache_mutex);
again:
/*
* Fast path through this function if there are no groups and no
* RMIDs that need cleaning.
*/
if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru))
goto out;
list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) {
if (!__rmid_valid(group->hw.cqm_rmid)) {
if (!start)
start = group;
nr_needed++;
}
}
/*
* We have some event groups, but they all have RMIDs assigned
* and no RMIDs need cleaning.
*/
if (!nr_needed && list_empty(&cqm_rmid_limbo_lru))
goto out;
if (!nr_needed)
goto stabilize;
/*
* We have more event groups without RMIDs than available RMIDs,
* or we have event groups that conflict with the ones currently
* scheduled.
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
*
* We force deallocate the rmid of the group at the head of
* cache_groups. The first event group without an RMID then gets
* assigned intel_cqm_rotation_rmid. This ensures we always make
* forward progress.
*
* Rotate the cache_groups list so the previous head is now the
* tail.
*/
__intel_cqm_pick_and_rotate(start);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
/*
* If the rotation is going to succeed, reduce the threshold so
* that we don't needlessly reuse dirty RMIDs.
*/
if (__rmid_valid(intel_cqm_rotation_rmid)) {
intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid);
intel_cqm_rotation_rmid = __get_rmid();
intel_cqm_sched_out_conflicting_events(start);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (__intel_cqm_threshold)
__intel_cqm_threshold--;
}
rotated = true;
stabilize:
/*
* We now need to stablize the RMID we freed above (if any) to
* ensure that the next time we rotate we have an RMID with zero
* occupancy value.
*
* Alternatively, if we didn't need to perform any rotation,
* we'll have a bunch of RMIDs in limbo that need stabilizing.
*/
threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale;
while (intel_cqm_rmid_stabilize(&nr_available) &&
__intel_cqm_threshold < threshold_limit) {
unsigned int steal_limit;
/*
* Don't spin if nobody is actively waiting for an RMID,
* the rotation worker will be kicked as soon as an
* event needs an RMID anyway.
*/
if (!nr_needed)
break;
/* Allow max 25% of RMIDs to be in limbo. */
steal_limit = (cqm_max_rmid + 1) / 4;
/*
* We failed to stabilize any RMIDs so our rotation
* logic is now stuck. In order to make forward progress
* we have a few options:
*
* 1. rotate ("steal") another RMID
* 2. increase the threshold
* 3. do nothing
*
* We do both of 1. and 2. until we hit the steal limit.
*
* The steal limit prevents all RMIDs ending up on the
* limbo list. This can happen if every RMID has a
* non-zero occupancy above threshold_limit, and the
* occupancy values aren't dropping fast enough.
*
* Note that there is prioritisation at work here - we'd
* rather increase the number of RMIDs on the limbo list
* than increase the threshold, because increasing the
* threshold skews the event data (because we reuse
* dirty RMIDs) - threshold bumps are a last resort.
*/
if (nr_available < steal_limit)
goto again;
__intel_cqm_threshold++;
}
out:
mutex_unlock(&cache_mutex);
return rotated;
}
static void intel_cqm_rmid_rotate(struct work_struct *work);
static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate);
static struct pmu intel_cqm_pmu;
static void intel_cqm_rmid_rotate(struct work_struct *work)
{
unsigned long delay;
__intel_cqm_rmid_rotate();
delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms);
schedule_delayed_work(&intel_cqm_rmid_work, delay);
}
/*
* Find a group and setup RMID.
*
* If we're part of a group, we use the group's RMID.
*/
static void intel_cqm_setup_event(struct perf_event *event,
struct perf_event **group)
{
struct perf_event *iter;
bool conflict = false;
u32 rmid;
list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
rmid = iter->hw.cqm_rmid;
if (__match_event(iter, event)) {
/* All tasks in a group share an RMID */
event->hw.cqm_rmid = rmid;
*group = iter;
return;
}
/*
* We only care about conflicts for events that are
* actually scheduled in (and hence have a valid RMID).
*/
if (__conflict_event(iter, event) && __rmid_valid(rmid))
conflict = true;
}
if (conflict)
rmid = INVALID_RMID;
else
rmid = __get_rmid();
event->hw.cqm_rmid = rmid;
}
static void intel_cqm_event_read(struct perf_event *event)
{
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned long flags;
u32 rmid;
u64 val;
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
/*
* Task events are handled by intel_cqm_event_count().
*/
if (event->cpu == -1)
return;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
raw_spin_lock_irqsave(&cache_lock, flags);
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
rmid = event->hw.cqm_rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (!__rmid_valid(rmid))
goto out;
val = __rmid_read(rmid);
/*
* Ignore this reading on error states and do not update the value.
*/
if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
goto out;
local64_set(&event->count, val);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
out:
raw_spin_unlock_irqrestore(&cache_lock, flags);
}
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
static void __intel_cqm_event_count(void *info)
{
struct rmid_read *rr = info;
u64 val;
val = __rmid_read(rr->rmid);
if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
return;
atomic64_add(val, &rr->value);
}
static inline bool cqm_group_leader(struct perf_event *event)
{
return !list_empty(&event->hw.cqm_groups_entry);
}
static u64 intel_cqm_event_count(struct perf_event *event)
{
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned long flags;
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
struct rmid_read rr = {
.value = ATOMIC64_INIT(0),
};
/*
* We only need to worry about task events. System-wide events
* are handled like usual, i.e. entirely with
* intel_cqm_event_read().
*/
if (event->cpu != -1)
return __perf_event_count(event);
/*
* Only the group leader gets to report values. This stops us
* reporting duplicate values to userspace, and gives us a clear
* rule for which task gets to report the values.
*
* Note that it is impossible to attribute these values to
* specific packages - we forfeit that ability when we create
* task events.
*/
if (!cqm_group_leader(event))
return 0;
perf/x86/intel/cqm: Return cached counter value from IRQ context Peter reported the following potential crash which I was able to reproduce with his test program, [ 148.765788] ------------[ cut here ]------------ [ 148.765796] WARNING: CPU: 34 PID: 2840 at kernel/smp.c:417 smp_call_function_many+0xb6/0x260() [ 148.765797] Modules linked in: [ 148.765800] CPU: 34 PID: 2840 Comm: perf Not tainted 4.2.0-rc1+ #4 [ 148.765803] ffffffff81cdc398 ffff88085f105950 ffffffff818bdfd5 0000000000000007 [ 148.765805] 0000000000000000 ffff88085f105990 ffffffff810e413a 0000000000000000 [ 148.765807] ffffffff82301080 0000000000000022 ffffffff8107f640 ffffffff8107f640 [ 148.765809] Call Trace: [ 148.765810] <NMI> [<ffffffff818bdfd5>] dump_stack+0x45/0x57 [ 148.765818] [<ffffffff810e413a>] warn_slowpath_common+0x8a/0xc0 [ 148.765822] [<ffffffff8107f640>] ? intel_cqm_stable+0x60/0x60 [ 148.765824] [<ffffffff8107f640>] ? intel_cqm_stable+0x60/0x60 [ 148.765825] [<ffffffff810e422a>] warn_slowpath_null+0x1a/0x20 [ 148.765827] [<ffffffff811613f6>] smp_call_function_many+0xb6/0x260 [ 148.765829] [<ffffffff8107f640>] ? intel_cqm_stable+0x60/0x60 [ 148.765831] [<ffffffff81161748>] on_each_cpu_mask+0x28/0x60 [ 148.765832] [<ffffffff8107f6ef>] intel_cqm_event_count+0x7f/0xe0 [ 148.765836] [<ffffffff811cdd35>] perf_output_read+0x2a5/0x400 [ 148.765839] [<ffffffff811d2e5a>] perf_output_sample+0x31a/0x590 [ 148.765840] [<ffffffff811d333d>] ? perf_prepare_sample+0x26d/0x380 [ 148.765841] [<ffffffff811d3497>] perf_event_output+0x47/0x60 [ 148.765843] [<ffffffff811d36c5>] __perf_event_overflow+0x215/0x240 [ 148.765844] [<ffffffff811d4124>] perf_event_overflow+0x14/0x20 [ 148.765847] [<ffffffff8107e7f4>] intel_pmu_handle_irq+0x1d4/0x440 [ 148.765849] [<ffffffff811d07a6>] ? __perf_event_task_sched_in+0x36/0xa0 [ 148.765853] [<ffffffff81219bad>] ? vunmap_page_range+0x19d/0x2f0 [ 148.765854] [<ffffffff81219d11>] ? unmap_kernel_range_noflush+0x11/0x20 [ 148.765859] [<ffffffff814ce6fe>] ? ghes_copy_tofrom_phys+0x11e/0x2a0 [ 148.765863] [<ffffffff8109e5db>] ? native_apic_msr_write+0x2b/0x30 [ 148.765865] [<ffffffff8109e44d>] ? x2apic_send_IPI_self+0x1d/0x20 [ 148.765869] [<ffffffff81065135>] ? arch_irq_work_raise+0x35/0x40 [ 148.765872] [<ffffffff811c8d86>] ? irq_work_queue+0x66/0x80 [ 148.765875] [<ffffffff81075306>] perf_event_nmi_handler+0x26/0x40 [ 148.765877] [<ffffffff81063ed9>] nmi_handle+0x79/0x100 [ 148.765879] [<ffffffff81064422>] default_do_nmi+0x42/0x100 [ 148.765880] [<ffffffff81064563>] do_nmi+0x83/0xb0 [ 148.765884] [<ffffffff818c7c0f>] end_repeat_nmi+0x1e/0x2e [ 148.765886] [<ffffffff811d07a6>] ? __perf_event_task_sched_in+0x36/0xa0 [ 148.765888] [<ffffffff811d07a6>] ? __perf_event_task_sched_in+0x36/0xa0 [ 148.765890] [<ffffffff811d07a6>] ? __perf_event_task_sched_in+0x36/0xa0 [ 148.765891] <<EOE>> [<ffffffff8110ab66>] finish_task_switch+0x156/0x210 [ 148.765898] [<ffffffff818c1671>] __schedule+0x341/0x920 [ 148.765899] [<ffffffff818c1c87>] schedule+0x37/0x80 [ 148.765903] [<ffffffff810ae1af>] ? do_page_fault+0x2f/0x80 [ 148.765905] [<ffffffff818c1f4a>] schedule_user+0x1a/0x50 [ 148.765907] [<ffffffff818c666c>] retint_careful+0x14/0x32 [ 148.765908] ---[ end trace e33ff2be78e14901 ]--- The CQM task events are not safe to be called from within interrupt context because they require performing an IPI to read the counter value on all sockets. And performing IPIs from within IRQ context is a "no-no". Make do with the last read counter value currently event in event->count when we're invoked in this context. Reported-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vikas Shivappa <vikas.shivappa@intel.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Will Auld <will.auld@intel.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1437490509-15373-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2015-07-21 21:55:09 +07:00
/*
* Getting up-to-date values requires an SMP IPI which is not
* possible if we're being called in interrupt context. Return
* the cached values instead.
*/
if (unlikely(in_interrupt()))
goto out;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
/*
* Notice that we don't perform the reading of an RMID
* atomically, because we can't hold a spin lock across the
* IPIs.
*
* Speculatively perform the read, since @event might be
* assigned a different (possibly invalid) RMID while we're
* busying performing the IPI calls. It's therefore necessary to
* check @event's RMID afterwards, and if it has changed,
* discard the result of the read.
*/
rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid);
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (!__rmid_valid(rr.rmid))
goto out;
on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, &rr, 1);
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
raw_spin_lock_irqsave(&cache_lock, flags);
if (event->hw.cqm_rmid == rr.rmid)
local64_set(&event->count, atomic64_read(&rr.value));
raw_spin_unlock_irqrestore(&cache_lock, flags);
out:
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
return __perf_event_count(event);
}
static void intel_cqm_event_start(struct perf_event *event, int mode)
{
struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
u32 rmid = event->hw.cqm_rmid;
if (!(event->hw.cqm_state & PERF_HES_STOPPED))
return;
event->hw.cqm_state &= ~PERF_HES_STOPPED;
if (state->rmid_usecnt++) {
if (!WARN_ON_ONCE(state->rmid != rmid))
return;
} else {
WARN_ON_ONCE(state->rmid);
}
state->rmid = rmid;
wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
}
static void intel_cqm_event_stop(struct perf_event *event, int mode)
{
struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
if (event->hw.cqm_state & PERF_HES_STOPPED)
return;
event->hw.cqm_state |= PERF_HES_STOPPED;
intel_cqm_event_read(event);
if (!--state->rmid_usecnt) {
state->rmid = 0;
wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
} else {
WARN_ON_ONCE(!state->rmid);
}
}
static int intel_cqm_event_add(struct perf_event *event, int mode)
{
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
unsigned long flags;
u32 rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
raw_spin_lock_irqsave(&cache_lock, flags);
event->hw.cqm_state = PERF_HES_STOPPED;
rmid = event->hw.cqm_rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (__rmid_valid(rmid) && (mode & PERF_EF_START))
intel_cqm_event_start(event, mode);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
raw_spin_unlock_irqrestore(&cache_lock, flags);
return 0;
}
static void intel_cqm_event_destroy(struct perf_event *event)
{
struct perf_event *group_other = NULL;
mutex_lock(&cache_mutex);
/*
* If there's another event in this group...
*/
if (!list_empty(&event->hw.cqm_group_entry)) {
group_other = list_first_entry(&event->hw.cqm_group_entry,
struct perf_event,
hw.cqm_group_entry);
list_del(&event->hw.cqm_group_entry);
}
/*
* And we're the group leader..
*/
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
if (cqm_group_leader(event)) {
/*
* If there was a group_other, make that leader, otherwise
* destroy the group and return the RMID.
*/
if (group_other) {
list_replace(&event->hw.cqm_groups_entry,
&group_other->hw.cqm_groups_entry);
} else {
u32 rmid = event->hw.cqm_rmid;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (__rmid_valid(rmid))
__put_rmid(rmid);
list_del(&event->hw.cqm_groups_entry);
}
}
mutex_unlock(&cache_mutex);
}
static int intel_cqm_event_init(struct perf_event *event)
{
struct perf_event *group = NULL;
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
bool rotate = false;
if (event->attr.type != intel_cqm_pmu.type)
return -ENOENT;
if (event->attr.config & ~QOS_EVENT_MASK)
return -EINVAL;
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
event->attr.exclude_hv ||
event->attr.exclude_idle ||
event->attr.exclude_host ||
event->attr.exclude_guest ||
event->attr.sample_period) /* no sampling */
return -EINVAL;
INIT_LIST_HEAD(&event->hw.cqm_group_entry);
INIT_LIST_HEAD(&event->hw.cqm_groups_entry);
event->destroy = intel_cqm_event_destroy;
mutex_lock(&cache_mutex);
perf/x86/intel: Support task events with Intel CQM Add support for task events as well as system-wide events. This change has a big impact on the way that we gather LLC occupancy values in intel_cqm_event_read(). Currently, for system-wide (per-cpu) events we defer processing to userspace which knows how to discard all but one cpu result per package. Things aren't so simple for task events because we need to do the value aggregation ourselves. To do this, we defer updating the LLC occupancy value in event->count from intel_cqm_event_read() and do an SMP cross-call to read values for all packages in intel_cqm_event_count(). We need to ensure that we only do this for one task event per cache group, otherwise we'll report duplicate values. If we're a system-wide event we want to fallback to the default perf_event_count() implementation. Refactor this into a common function so that we don't duplicate the code. Also, introduce PERF_TYPE_INTEL_CQM, since we need a way to track an event's task (if the event isn't per-cpu) inside of the Intel CQM PMU driver. This task information is only availble in the upper layers of the perf infrastructure. Other perf backends stash the target task in event->hw.*target so we need to do something similar. The task is used to determine whether events should share a cache group and an RMID. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/1422038748-21397-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:46 +07:00
/* Will also set rmid */
intel_cqm_setup_event(event, &group);
if (group) {
list_add_tail(&event->hw.cqm_group_entry,
&group->hw.cqm_group_entry);
} else {
list_add_tail(&event->hw.cqm_groups_entry,
&cache_groups);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
/*
* All RMIDs are either in use or have recently been
* used. Kick the rotation worker to clean/free some.
*
* We only do this for the group leader, rather than for
* every event in a group to save on needless work.
*/
if (!__rmid_valid(event->hw.cqm_rmid))
rotate = true;
}
mutex_unlock(&cache_mutex);
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
if (rotate)
schedule_delayed_work(&intel_cqm_rmid_work, 0);
return 0;
}
EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01");
EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1");
EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes");
EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL);
EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1");
static struct attribute *intel_cqm_events_attr[] = {
EVENT_PTR(intel_cqm_llc),
EVENT_PTR(intel_cqm_llc_pkg),
EVENT_PTR(intel_cqm_llc_unit),
EVENT_PTR(intel_cqm_llc_scale),
EVENT_PTR(intel_cqm_llc_snapshot),
NULL,
};
static struct attribute_group intel_cqm_events_group = {
.name = "events",
.attrs = intel_cqm_events_attr,
};
PMU_FORMAT_ATTR(event, "config:0-7");
static struct attribute *intel_cqm_formats_attr[] = {
&format_attr_event.attr,
NULL,
};
static struct attribute_group intel_cqm_format_group = {
.name = "format",
.attrs = intel_cqm_formats_attr,
};
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
static ssize_t
max_recycle_threshold_show(struct device *dev, struct device_attribute *attr,
char *page)
{
ssize_t rv;
mutex_lock(&cache_mutex);
rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold);
mutex_unlock(&cache_mutex);
return rv;
}
static ssize_t
max_recycle_threshold_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
unsigned int bytes, cachelines;
int ret;
ret = kstrtouint(buf, 0, &bytes);
if (ret)
return ret;
mutex_lock(&cache_mutex);
__intel_cqm_max_threshold = bytes;
cachelines = bytes / cqm_l3_scale;
/*
* The new maximum takes effect immediately.
*/
if (__intel_cqm_threshold > cachelines)
__intel_cqm_threshold = cachelines;
mutex_unlock(&cache_mutex);
return count;
}
static DEVICE_ATTR_RW(max_recycle_threshold);
static struct attribute *intel_cqm_attrs[] = {
&dev_attr_max_recycle_threshold.attr,
NULL,
};
static const struct attribute_group intel_cqm_group = {
.attrs = intel_cqm_attrs,
};
static const struct attribute_group *intel_cqm_attr_groups[] = {
&intel_cqm_events_group,
&intel_cqm_format_group,
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
&intel_cqm_group,
NULL,
};
static struct pmu intel_cqm_pmu = {
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
.hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME,
.attr_groups = intel_cqm_attr_groups,
.task_ctx_nr = perf_sw_context,
.event_init = intel_cqm_event_init,
.add = intel_cqm_event_add,
.del = intel_cqm_event_stop,
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
.start = intel_cqm_event_start,
.stop = intel_cqm_event_stop,
.read = intel_cqm_event_read,
.count = intel_cqm_event_count,
};
static inline void cqm_pick_event_reader(int cpu)
{
int phys_id = topology_physical_package_id(cpu);
int i;
for_each_cpu(i, &cqm_cpumask) {
if (phys_id == topology_physical_package_id(i))
return; /* already got reader for this socket */
}
cpumask_set_cpu(cpu, &cqm_cpumask);
}
perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler Tony reports that booting his 144-cpu machine with maxcpus=10 triggers the following WARN_ON(): [ 21.045727] WARNING: CPU: 8 PID: 647 at arch/x86/kernel/cpu/perf_event_intel_cqm.c:1267 intel_cqm_cpu_prepare+0x75/0x90() [ 21.045744] CPU: 8 PID: 647 Comm: systemd-udevd Not tainted 4.2.0-rc4 #1 [ 21.045745] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0066.R00.1506021730 06/02/2015 [ 21.045747] 0000000000000000 0000000082771b09 ffff880856333ba8 ffffffff81669b67 [ 21.045748] 0000000000000000 0000000000000000 ffff880856333be8 ffffffff8107b02a [ 21.045750] ffff88085b789800 ffff88085f68a020 ffffffff819e2470 000000000000000a [ 21.045750] Call Trace: [ 21.045757] [<ffffffff81669b67>] dump_stack+0x45/0x57 [ 21.045759] [<ffffffff8107b02a>] warn_slowpath_common+0x8a/0xc0 [ 21.045761] [<ffffffff8107b15a>] warn_slowpath_null+0x1a/0x20 [ 21.045762] [<ffffffff81036725>] intel_cqm_cpu_prepare+0x75/0x90 [ 21.045764] [<ffffffff81036872>] intel_cqm_cpu_notifier+0x42/0x160 [ 21.045767] [<ffffffff8109a33d>] notifier_call_chain+0x4d/0x80 [ 21.045769] [<ffffffff8109a44e>] __raw_notifier_call_chain+0xe/0x10 [ 21.045770] [<ffffffff8107b538>] _cpu_up+0xe8/0x190 [ 21.045771] [<ffffffff8107b65a>] cpu_up+0x7a/0xa0 [ 21.045774] [<ffffffff8165e920>] cpu_subsys_online+0x40/0x90 [ 21.045777] [<ffffffff81433b37>] device_online+0x67/0x90 [ 21.045778] [<ffffffff81433bea>] online_store+0x8a/0xa0 [ 21.045782] [<ffffffff81430e78>] dev_attr_store+0x18/0x30 [ 21.045785] [<ffffffff8126b6ba>] sysfs_kf_write+0x3a/0x50 [ 21.045786] [<ffffffff8126ad40>] kernfs_fop_write+0x120/0x170 [ 21.045789] [<ffffffff811f0b77>] __vfs_write+0x37/0x100 [ 21.045791] [<ffffffff811f38b8>] ? __sb_start_write+0x58/0x110 [ 21.045795] [<ffffffff81296d2d>] ? security_file_permission+0x3d/0xc0 [ 21.045796] [<ffffffff811f1279>] vfs_write+0xa9/0x190 [ 21.045797] [<ffffffff811f2075>] SyS_write+0x55/0xc0 [ 21.045800] [<ffffffff81067300>] ? do_page_fault+0x30/0x80 [ 21.045804] [<ffffffff816709ae>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 21.045805] ---[ end trace fe228b836d8af405 ]--- The root cause is that CPU_UP_PREPARE is completely the wrong notifier action from which to access cpu_data(), because smp_store_cpu_info() won't have been executed by the target CPU at that point, which in turn means that ->x86_cache_max_rmid and ->x86_cache_occ_scale haven't been filled out. Instead let's invoke our handler from CPU_STARTING and rename it appropriately. Reported-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vikas Shivappa <vikas.shivappa@intel.com> Link: http://lkml.kernel.org/r/1438863163-14083-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-06 19:12:43 +07:00
static void intel_cqm_cpu_starting(unsigned int cpu)
{
struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);
state->rmid = 0;
state->closid = 0;
state->rmid_usecnt = 0;
WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
}
static void intel_cqm_cpu_exit(unsigned int cpu)
{
int phys_id = topology_physical_package_id(cpu);
int i;
/*
* Is @cpu a designated cqm reader?
*/
if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
return;
for_each_online_cpu(i) {
if (i == cpu)
continue;
if (phys_id == topology_physical_package_id(i)) {
cpumask_set_cpu(i, &cqm_cpumask);
break;
}
}
}
static int intel_cqm_cpu_notifier(struct notifier_block *nb,
unsigned long action, void *hcpu)
{
unsigned int cpu = (unsigned long)hcpu;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
intel_cqm_cpu_exit(cpu);
break;
case CPU_STARTING:
perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler Tony reports that booting his 144-cpu machine with maxcpus=10 triggers the following WARN_ON(): [ 21.045727] WARNING: CPU: 8 PID: 647 at arch/x86/kernel/cpu/perf_event_intel_cqm.c:1267 intel_cqm_cpu_prepare+0x75/0x90() [ 21.045744] CPU: 8 PID: 647 Comm: systemd-udevd Not tainted 4.2.0-rc4 #1 [ 21.045745] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0066.R00.1506021730 06/02/2015 [ 21.045747] 0000000000000000 0000000082771b09 ffff880856333ba8 ffffffff81669b67 [ 21.045748] 0000000000000000 0000000000000000 ffff880856333be8 ffffffff8107b02a [ 21.045750] ffff88085b789800 ffff88085f68a020 ffffffff819e2470 000000000000000a [ 21.045750] Call Trace: [ 21.045757] [<ffffffff81669b67>] dump_stack+0x45/0x57 [ 21.045759] [<ffffffff8107b02a>] warn_slowpath_common+0x8a/0xc0 [ 21.045761] [<ffffffff8107b15a>] warn_slowpath_null+0x1a/0x20 [ 21.045762] [<ffffffff81036725>] intel_cqm_cpu_prepare+0x75/0x90 [ 21.045764] [<ffffffff81036872>] intel_cqm_cpu_notifier+0x42/0x160 [ 21.045767] [<ffffffff8109a33d>] notifier_call_chain+0x4d/0x80 [ 21.045769] [<ffffffff8109a44e>] __raw_notifier_call_chain+0xe/0x10 [ 21.045770] [<ffffffff8107b538>] _cpu_up+0xe8/0x190 [ 21.045771] [<ffffffff8107b65a>] cpu_up+0x7a/0xa0 [ 21.045774] [<ffffffff8165e920>] cpu_subsys_online+0x40/0x90 [ 21.045777] [<ffffffff81433b37>] device_online+0x67/0x90 [ 21.045778] [<ffffffff81433bea>] online_store+0x8a/0xa0 [ 21.045782] [<ffffffff81430e78>] dev_attr_store+0x18/0x30 [ 21.045785] [<ffffffff8126b6ba>] sysfs_kf_write+0x3a/0x50 [ 21.045786] [<ffffffff8126ad40>] kernfs_fop_write+0x120/0x170 [ 21.045789] [<ffffffff811f0b77>] __vfs_write+0x37/0x100 [ 21.045791] [<ffffffff811f38b8>] ? __sb_start_write+0x58/0x110 [ 21.045795] [<ffffffff81296d2d>] ? security_file_permission+0x3d/0xc0 [ 21.045796] [<ffffffff811f1279>] vfs_write+0xa9/0x190 [ 21.045797] [<ffffffff811f2075>] SyS_write+0x55/0xc0 [ 21.045800] [<ffffffff81067300>] ? do_page_fault+0x30/0x80 [ 21.045804] [<ffffffff816709ae>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 21.045805] ---[ end trace fe228b836d8af405 ]--- The root cause is that CPU_UP_PREPARE is completely the wrong notifier action from which to access cpu_data(), because smp_store_cpu_info() won't have been executed by the target CPU at that point, which in turn means that ->x86_cache_max_rmid and ->x86_cache_occ_scale haven't been filled out. Instead let's invoke our handler from CPU_STARTING and rename it appropriately. Reported-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vikas Shivappa <vikas.shivappa@intel.com> Link: http://lkml.kernel.org/r/1438863163-14083-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-06 19:12:43 +07:00
intel_cqm_cpu_starting(cpu);
cqm_pick_event_reader(cpu);
break;
}
return NOTIFY_OK;
}
static const struct x86_cpu_id intel_cqm_match[] = {
{ .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC },
{}
};
static int __init intel_cqm_init(void)
{
char *str, scale[20];
int i, cpu, ret;
if (!x86_match_cpu(intel_cqm_match))
return -ENODEV;
cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale;
/*
* It's possible that not all resources support the same number
* of RMIDs. Instead of making scheduling much more complicated
* (where we have to match a task's RMID to a cpu that supports
* that many RMIDs) just find the minimum RMIDs supported across
* all cpus.
*
* Also, check that the scales match on all cpus.
*/
cpu_notifier_register_begin();
for_each_online_cpu(cpu) {
struct cpuinfo_x86 *c = &cpu_data(cpu);
if (c->x86_cache_max_rmid < cqm_max_rmid)
cqm_max_rmid = c->x86_cache_max_rmid;
if (c->x86_cache_occ_scale != cqm_l3_scale) {
pr_err("Multiple LLC scale values, disabling\n");
ret = -EINVAL;
goto out;
}
}
perf/x86/intel: Perform rotation on Intel CQM RMIDs There are many use cases where people will want to monitor more tasks than there exist RMIDs in the hardware, meaning that we have to perform some kind of multiplexing. We do this by "rotating" the RMIDs in a workqueue, and assigning an RMID to a waiting event when the RMID becomes unused. This scheme reserves one RMID at all times for rotation. When we need to schedule a new event we give it the reserved RMID, pick a victim event from the front of the global CQM list and wait for the victim's RMID to drop to zero occupancy, before it becomes the new reserved RMID. We put the victim's RMID onto the limbo list, where it resides for a "minimum queue time", which is intended to save ourselves an expensive smp IPI when the RMID is unlikely to have a occupancy value below __intel_cqm_threshold. If we fail to recycle an RMID, even after waiting the minimum queue time then we need to increment __intel_cqm_threshold. There is an upper bound on this threshold, __intel_cqm_max_threshold, which is programmable from userland as /sys/devices/intel_cqm/max_recycling_threshold. The comments above __intel_cqm_rmid_rotate() have more details. Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com> Link: http://lkml.kernel.org/r/1422038748-21397-9-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-24 01:45:47 +07:00
/*
* A reasonable upper limit on the max threshold is the number
* of lines tagged per RMID if all RMIDs have the same number of
* lines tagged in the LLC.
*
* For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
*/
__intel_cqm_max_threshold =
boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1);
snprintf(scale, sizeof(scale), "%u", cqm_l3_scale);
str = kstrdup(scale, GFP_KERNEL);
if (!str) {
ret = -ENOMEM;
goto out;
}
event_attr_intel_cqm_llc_scale.event_str = str;
ret = intel_cqm_setup_rmid_cache();
if (ret)
goto out;
for_each_online_cpu(i) {
perf/x86/intel/cqm: Do not access cpu_data() from CPU_UP_PREPARE handler Tony reports that booting his 144-cpu machine with maxcpus=10 triggers the following WARN_ON(): [ 21.045727] WARNING: CPU: 8 PID: 647 at arch/x86/kernel/cpu/perf_event_intel_cqm.c:1267 intel_cqm_cpu_prepare+0x75/0x90() [ 21.045744] CPU: 8 PID: 647 Comm: systemd-udevd Not tainted 4.2.0-rc4 #1 [ 21.045745] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0066.R00.1506021730 06/02/2015 [ 21.045747] 0000000000000000 0000000082771b09 ffff880856333ba8 ffffffff81669b67 [ 21.045748] 0000000000000000 0000000000000000 ffff880856333be8 ffffffff8107b02a [ 21.045750] ffff88085b789800 ffff88085f68a020 ffffffff819e2470 000000000000000a [ 21.045750] Call Trace: [ 21.045757] [<ffffffff81669b67>] dump_stack+0x45/0x57 [ 21.045759] [<ffffffff8107b02a>] warn_slowpath_common+0x8a/0xc0 [ 21.045761] [<ffffffff8107b15a>] warn_slowpath_null+0x1a/0x20 [ 21.045762] [<ffffffff81036725>] intel_cqm_cpu_prepare+0x75/0x90 [ 21.045764] [<ffffffff81036872>] intel_cqm_cpu_notifier+0x42/0x160 [ 21.045767] [<ffffffff8109a33d>] notifier_call_chain+0x4d/0x80 [ 21.045769] [<ffffffff8109a44e>] __raw_notifier_call_chain+0xe/0x10 [ 21.045770] [<ffffffff8107b538>] _cpu_up+0xe8/0x190 [ 21.045771] [<ffffffff8107b65a>] cpu_up+0x7a/0xa0 [ 21.045774] [<ffffffff8165e920>] cpu_subsys_online+0x40/0x90 [ 21.045777] [<ffffffff81433b37>] device_online+0x67/0x90 [ 21.045778] [<ffffffff81433bea>] online_store+0x8a/0xa0 [ 21.045782] [<ffffffff81430e78>] dev_attr_store+0x18/0x30 [ 21.045785] [<ffffffff8126b6ba>] sysfs_kf_write+0x3a/0x50 [ 21.045786] [<ffffffff8126ad40>] kernfs_fop_write+0x120/0x170 [ 21.045789] [<ffffffff811f0b77>] __vfs_write+0x37/0x100 [ 21.045791] [<ffffffff811f38b8>] ? __sb_start_write+0x58/0x110 [ 21.045795] [<ffffffff81296d2d>] ? security_file_permission+0x3d/0xc0 [ 21.045796] [<ffffffff811f1279>] vfs_write+0xa9/0x190 [ 21.045797] [<ffffffff811f2075>] SyS_write+0x55/0xc0 [ 21.045800] [<ffffffff81067300>] ? do_page_fault+0x30/0x80 [ 21.045804] [<ffffffff816709ae>] entry_SYSCALL_64_fastpath+0x12/0x71 [ 21.045805] ---[ end trace fe228b836d8af405 ]--- The root cause is that CPU_UP_PREPARE is completely the wrong notifier action from which to access cpu_data(), because smp_store_cpu_info() won't have been executed by the target CPU at that point, which in turn means that ->x86_cache_max_rmid and ->x86_cache_occ_scale haven't been filled out. Instead let's invoke our handler from CPU_STARTING and rename it appropriately. Reported-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Matt Fleming <matt.fleming@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ashok Raj <ashok.raj@intel.com> Cc: Kanaka Juvva <kanaka.d.juvva@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vikas Shivappa <vikas.shivappa@intel.com> Link: http://lkml.kernel.org/r/1438863163-14083-1-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-06 19:12:43 +07:00
intel_cqm_cpu_starting(i);
cqm_pick_event_reader(i);
}
__perf_cpu_notifier(intel_cqm_cpu_notifier);
ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1);
if (ret)
pr_err("Intel CQM perf registration failed: %d\n", ret);
else
pr_info("Intel CQM monitoring enabled\n");
out:
cpu_notifier_register_done();
return ret;
}
device_initcall(intel_cqm_init);