linux/arch/x86/events/perf_event.h

961 lines
25 KiB
C
Raw Normal View History

/*
* Performance events x86 architecture header
*
* Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
* Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
* Copyright (C) 2009 Jaswinder Singh Rajput
* Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
* Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
* Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
* Copyright (C) 2009 Google, Inc., Stephane Eranian
*
* For licencing details see kernel-base/COPYING
*/
#include <linux/perf_event.h>
/* To enable MSR tracing please use the generic trace points. */
/*
* | NHM/WSM | SNB |
* register -------------------------------
* | HT | no HT | HT | no HT |
*-----------------------------------------
* offcore | core | core | cpu | core |
* lbr_sel | core | core | cpu | core |
* ld_lat | cpu | core | cpu | core |
*-----------------------------------------
*
* Given that there is a small number of shared regs,
* we can pre-allocate their slot in the per-cpu
* per-core reg tables.
*/
enum extra_reg_type {
EXTRA_REG_NONE = -1, /* not used */
EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */
EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
EXTRA_REG_LBR = 2, /* lbr_select */
EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */
EXTRA_REG_FE = 4, /* fe_* */
EXTRA_REG_MAX /* number of entries needed */
};
struct event_constraint {
union {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
u64 code;
u64 cmask;
int weight;
perf, x86: Fix event scheduler for constraints with overlapping counters The current x86 event scheduler fails to resolve scheduling problems of certain combinations of events and constraints. This happens if the counter mask of such an event is not a subset of any other counter mask of a constraint with an equal or higher weight, e.g. constraints of the AMD family 15h pmu: counter mask weight amd_f15_PMC30 0x09 2 <--- overlapping counters amd_f15_PMC20 0x07 3 amd_f15_PMC53 0x38 3 The scheduler does not find then an existing solution. Here is an example: event code counter failure possible solution 0x02E PMC[3,0] 0 3 0x043 PMC[2:0] 1 0 0x045 PMC[2:0] 2 1 0x046 PMC[2:0] FAIL 2 The event scheduler may not select the correct counter in the first cycle because it needs to know which subsequent events will be scheduled. It may fail to schedule the events then. To solve this, we now save the scheduler state of events with overlapping counter counstraints. If we fail to schedule the events we rollback to those states and try to use another free counter. Constraints with overlapping counters are marked with a new introduced overlap flag. We set the overlap flag for such constraints to give the scheduler a hint which events to select for counter rescheduling. The EVENT_CONSTRAINT_OVERLAP() macro can be used for this. Care must be taken as the rescheduling algorithm is O(n!) which will increase scheduling cycles for an over-commited system dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter masks must be kept at a minimum. Thus, the current stack is limited to 2 states to limit the number of loops the algorithm takes in the worst case. On systems with no overlapping-counter constraints, this implementation does not increase the loop count compared to the previous algorithm. V2: * Renamed redo -> overlap. * Reimplementation using perf scheduling helper functions. V3: * Added WARN_ON_ONCE() if out of save states. * Changed function interface of perf_sched_restore_state() to use bool as return value. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-18 19:35:22 +08:00
int overlap;
int flags;
};
/*
perf/x86: Fix shared register mutual exclusion enforcement This patch fixes a problem with the shared registers mutual exclusion code and incremental event scheduling by the generic perf_event code. There was a bug whereby the mutual exclusion on the shared registers was not enforced because of incremental scheduling abort due to event constraints. As an example on Intel Nehalem, consider the following events: group1= L1D_CACHE_LD:E_STATE,OFFCORE_RESPONSE_0:PF_RFO,L1D_CACHE_LD:I_STATE group2= L1D_CACHE_LD:I_STATE The L1D_CACHE_LD event can only be measured by 2 counters. Yet, there are 3 instances here. The first group can be scheduled and is committed. Then, the generic code tries to schedule group2 and this fails (because there is no more counter to support the 3rd instance of L1D_CACHE_LD). But in x86_schedule_events() error path, put_event_contraints() is invoked on ALL the events and not just the ones that just failed. That causes the "lock" on the shared offcore_response MSR to be released. Yet the first group is actually scheduled and is exposed to reprogramming of that shared msr by the sibling HT thread. In other words, there is no guarantee on what is measured. This patch fixes the problem by tagging committed events with the PERF_X86_EVENT_COMMITTED tag. In the error path of x86_schedule_events(), only the events NOT tagged have their constraint released. The tag is eventually removed when the event in descheduled. Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20130620164254.GA3556@quad Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-06-21 00:42:54 +08:00
* struct hw_perf_event.flags flags
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */
#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */
#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */
#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */
#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */
#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
perf/x86/intel: Implement batched PEBS interrupt handling (large PEBS interrupt threshold) PEBS always had the capability to log samples to its buffers without an interrupt. Traditionally perf has not used this but always set the PEBS threshold to one. For frequently occurring events (like cycles or branches or load/store) this in term requires using a relatively high sampling period to avoid overloading the system, by only processing PMIs. This in term increases sampling error. For the common cases we still need to use the PMI because the PEBS hardware has various limitations. The biggest one is that it can not supply a callgraph. It also requires setting a fixed period, as the hardware does not support adaptive period. Another issue is that it cannot supply a time stamp and some other options. To supply a TID it requires flushing on context switch. It can however supply the IP, the load/store address, TSX information, registers, and some other things. So we can make PEBS work for some specific cases, basically as long as you can do without a callgraph and can set the period you can use this new PEBS mode. The main benefit is the ability to support much lower sampling period (down to -c 1000) without extensive overhead. One use cases is for example to increase the resolution of the c2c tool. Another is double checking when you suspect the standard sampling has too much sampling error. Some numbers on the overhead, using cycle soak, comparing the elapsed time from "kernbench -M -H" between plain (threshold set to one) and multi (large threshold). The test command for plain: "perf record --time -e cycles:p -c $period -- kernbench -M -H" The test command for multi: "perf record --no-time -e cycles:p -c $period -- kernbench -M -H" ( The only difference of test command between multi and plain is time stamp options. Since time stamp is not supported by large PEBS threshold, it can be used as a flag to indicate if large threshold is enabled during the test. ) period plain(Sec) multi(Sec) Delta 10003 32.7 16.5 16.2 20003 30.2 16.2 14.0 40003 18.6 14.1 4.5 80003 16.8 14.6 2.2 100003 16.9 14.1 2.8 800003 15.4 15.7 -0.3 1000003 15.3 15.2 0.2 2000003 15.3 15.1 0.1 With periods below 100003, plain (threshold one) cause much more overhead. With 10003 sampling period, the Elapsed Time for multi is even 2X faster than plain. Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1430940834-8964-5-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-07 03:33:50 +08:00
#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
struct perf_event *owners[X86_PMC_IDX_MAX];
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
perf/x86/intel: Implement batched PEBS interrupt handling (large PEBS interrupt threshold) PEBS always had the capability to log samples to its buffers without an interrupt. Traditionally perf has not used this but always set the PEBS threshold to one. For frequently occurring events (like cycles or branches or load/store) this in term requires using a relatively high sampling period to avoid overloading the system, by only processing PMIs. This in term increases sampling error. For the common cases we still need to use the PMI because the PEBS hardware has various limitations. The biggest one is that it can not supply a callgraph. It also requires setting a fixed period, as the hardware does not support adaptive period. Another issue is that it cannot supply a time stamp and some other options. To supply a TID it requires flushing on context switch. It can however supply the IP, the load/store address, TSX information, registers, and some other things. So we can make PEBS work for some specific cases, basically as long as you can do without a callgraph and can set the period you can use this new PEBS mode. The main benefit is the ability to support much lower sampling period (down to -c 1000) without extensive overhead. One use cases is for example to increase the resolution of the c2c tool. Another is double checking when you suspect the standard sampling has too much sampling error. Some numbers on the overhead, using cycle soak, comparing the elapsed time from "kernbench -M -H" between plain (threshold set to one) and multi (large threshold). The test command for plain: "perf record --time -e cycles:p -c $period -- kernbench -M -H" The test command for multi: "perf record --no-time -e cycles:p -c $period -- kernbench -M -H" ( The only difference of test command between multi and plain is time stamp options. Since time stamp is not supported by large PEBS threshold, it can be used as a flag to indicate if large threshold is enabled during the test. ) period plain(Sec) multi(Sec) Delta 10003 32.7 16.5 16.2 20003 30.2 16.2 14.0 40003 18.6 14.1 4.5 80003 16.8 14.6 2.2 100003 16.9 14.1 2.8 800003 15.4 15.7 -0.3 1000003 15.3 15.2 0.2 2000003 15.3 15.1 0.1 With periods below 100003, plain (threshold one) cause much more overhead. With 10003 sampling period, the Elapsed Time for multi is even 2X faster than plain. Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1430940834-8964-5-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-07 03:33:50 +08:00
/*
* Flags PEBS can handle without an PMI.
*
* TID can only be handled by flushing at context switch.
*
perf/x86/intel: Implement batched PEBS interrupt handling (large PEBS interrupt threshold) PEBS always had the capability to log samples to its buffers without an interrupt. Traditionally perf has not used this but always set the PEBS threshold to one. For frequently occurring events (like cycles or branches or load/store) this in term requires using a relatively high sampling period to avoid overloading the system, by only processing PMIs. This in term increases sampling error. For the common cases we still need to use the PMI because the PEBS hardware has various limitations. The biggest one is that it can not supply a callgraph. It also requires setting a fixed period, as the hardware does not support adaptive period. Another issue is that it cannot supply a time stamp and some other options. To supply a TID it requires flushing on context switch. It can however supply the IP, the load/store address, TSX information, registers, and some other things. So we can make PEBS work for some specific cases, basically as long as you can do without a callgraph and can set the period you can use this new PEBS mode. The main benefit is the ability to support much lower sampling period (down to -c 1000) without extensive overhead. One use cases is for example to increase the resolution of the c2c tool. Another is double checking when you suspect the standard sampling has too much sampling error. Some numbers on the overhead, using cycle soak, comparing the elapsed time from "kernbench -M -H" between plain (threshold set to one) and multi (large threshold). The test command for plain: "perf record --time -e cycles:p -c $period -- kernbench -M -H" The test command for multi: "perf record --no-time -e cycles:p -c $period -- kernbench -M -H" ( The only difference of test command between multi and plain is time stamp options. Since time stamp is not supported by large PEBS threshold, it can be used as a flag to indicate if large threshold is enabled during the test. ) period plain(Sec) multi(Sec) Delta 10003 32.7 16.5 16.2 20003 30.2 16.2 14.0 40003 18.6 14.1 4.5 80003 16.8 14.6 2.2 100003 16.9 14.1 2.8 800003 15.4 15.7 -0.3 1000003 15.3 15.2 0.2 2000003 15.3 15.1 0.1 With periods below 100003, plain (threshold one) cause much more overhead. With 10003 sampling period, the Elapsed Time for multi is even 2X faster than plain. Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1430940834-8964-5-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-07 03:33:50 +08:00
*/
#define PEBS_FREERUNNING_FLAGS \
(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
perf/x86/intel: Implement batched PEBS interrupt handling (large PEBS interrupt threshold) PEBS always had the capability to log samples to its buffers without an interrupt. Traditionally perf has not used this but always set the PEBS threshold to one. For frequently occurring events (like cycles or branches or load/store) this in term requires using a relatively high sampling period to avoid overloading the system, by only processing PMIs. This in term increases sampling error. For the common cases we still need to use the PMI because the PEBS hardware has various limitations. The biggest one is that it can not supply a callgraph. It also requires setting a fixed period, as the hardware does not support adaptive period. Another issue is that it cannot supply a time stamp and some other options. To supply a TID it requires flushing on context switch. It can however supply the IP, the load/store address, TSX information, registers, and some other things. So we can make PEBS work for some specific cases, basically as long as you can do without a callgraph and can set the period you can use this new PEBS mode. The main benefit is the ability to support much lower sampling period (down to -c 1000) without extensive overhead. One use cases is for example to increase the resolution of the c2c tool. Another is double checking when you suspect the standard sampling has too much sampling error. Some numbers on the overhead, using cycle soak, comparing the elapsed time from "kernbench -M -H" between plain (threshold set to one) and multi (large threshold). The test command for plain: "perf record --time -e cycles:p -c $period -- kernbench -M -H" The test command for multi: "perf record --no-time -e cycles:p -c $period -- kernbench -M -H" ( The only difference of test command between multi and plain is time stamp options. Since time stamp is not supported by large PEBS threshold, it can be used as a flag to indicate if large threshold is enabled during the test. ) period plain(Sec) multi(Sec) Delta 10003 32.7 16.5 16.2 20003 30.2 16.2 14.0 40003 18.6 14.1 4.5 80003 16.8 14.6 2.2 100003 16.9 14.1 2.8 800003 15.4 15.7 -0.3 1000003 15.3 15.2 0.2 2000003 15.3 15.1 0.1 With periods below 100003, plain (threshold one) cause much more overhead. With 10003 sampling period, the Elapsed Time for multi is even 2X faster than plain. Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1430940834-8964-5-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-07 03:33:50 +08:00
PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
PERF_SAMPLE_TRANSACTION)
/*
* A debug store configuration.
*
* We only support architectures that use 64bit fields.
*/
struct debug_store {
u64 bts_buffer_base;
u64 bts_index;
u64 bts_absolute_maximum;
u64 bts_interrupt_threshold;
u64 pebs_buffer_base;
u64 pebs_index;
u64 pebs_absolute_maximum;
u64 pebs_interrupt_threshold;
u64 pebs_event_reset[MAX_PEBS_EVENTS];
};
/*
* Per register state.
*/
struct er_account {
raw_spinlock_t lock; /* per-core: protect structure */
u64 config; /* extra MSR config */
u64 reg; /* extra MSR number */
atomic_t ref; /* reference count */
};
/*
* Per core/cpu state
*
* Used to coordinate shared registers between HT threads or
* among events on a single PMU.
*/
struct intel_shared_regs {
struct er_account regs[EXTRA_REG_MAX];
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
enum intel_excl_state_type {
INTEL_EXCL_UNUSED = 0, /* counter is unused */
INTEL_EXCL_SHARED = 1, /* counter can be used by both threads */
INTEL_EXCL_EXCLUSIVE = 2, /* counter can be used by one thread only */
};
struct intel_excl_states {
enum intel_excl_state_type state[X86_PMC_IDX_MAX];
perf/x86/intel: Implement cross-HT corruption bug workaround This patch implements a software workaround for a HW erratum on Intel SandyBridge, IvyBridge and Haswell processors with Hyperthreading enabled. The errata are documented for each processor in their respective specification update documents: - SandyBridge: BJ122 - IvyBridge: BV98 - Haswell: HSD29 The bug causes silent counter corruption across hyperthreads only when measuring certain memory events (0xd0, 0xd1, 0xd2, 0xd3). Counters measuring those events may leak counts to the sibling counter. For instance, counter 0, thread 0 measuring event 0xd0, may leak to counter 0, thread 1, regardless of the event measured there. The size of the leak is not predictible. It all depends on the workload and the state of each sibling hyper-thread. The corrupting events do undercount as a consequence of the leak. The leak is compensated automatically only when the sibling counter measures the exact same corrupting event AND the workload is on the two threads is the same. Given, there is no way to guarantee this, a work-around is necessary. Furthermore, there is a serious problem if the leaked count is added to a low-occurrence event. In that case the corruption on the low occurrence event can be very large, e.g., orders of magnitude. There is no HW or FW workaround for this problem. The bug is very easy to reproduce on a loaded system. Here is an example on a Haswell client, where CPU0, CPU4 are siblings. We load the CPUs with a simple triad app streaming large floating-point vector. We use 0x81d0 corrupting event (MEM_UOPS_RETIRED:ALL_LOADS) and 0x20cc (ROB_MISC_EVENTS:LBR_INSERTS). Given we are not using the LBR, the 0x20cc event should be zero. $ taskset -c 0 triad & $ taskset -c 4 triad & $ perf stat -a -C 0 -e r81d0 sleep 100 & $ perf stat -a -C 4 -r20cc sleep 10 Performance counter stats for 'system wide': 139 277 291 r20cc 10,000969126 seconds time elapsed In this example, 0x81d0 and r20cc ar eusing sinling counters on CPU0 and CPU4. 0x81d0 leaks into 0x20cc and corrupts it from 0 to 139 millions occurrences. This patch provides a software workaround to this problem by modifying the way events are scheduled onto counters by the kernel. The patch forces cross-thread mutual exclusion between counters in case a corrupting event is measured by one of the hyper-threads. If thread 0, counter 0 is measuring event 0xd0, then nothing can be measured on counter 0, thread 1. If no corrupting event is measured on any hyper-thread, event scheduling proceeds as before. The same example run with the workaround enabled, yield the correct answer: $ taskset -c 0 triad & $ taskset -c 4 triad & $ perf stat -a -C 0 -e r81d0 sleep 100 & $ perf stat -a -C 4 -r20cc sleep 10 Performance counter stats for 'system wide': 0 r20cc 10,000969126 seconds time elapsed The patch does provide correctness for all non-corrupting events. It does not "repatriate" the leaked counts back to the leaking counter. This is planned for a second patch series. This patch series makes this repatriation more easy by guaranteeing the sibling counter is not measuring any useful event. The patch introduces dynamic constraints for events. That means that events which did not have constraints, i.e., could be measured on any counters, may now be constrained to a subset of the counters depending on what is going on the sibling thread. The algorithm is similar to a cache coherency protocol. We call it XSU in reference to Exclusive, Shared, Unused, the 3 possible states of a PMU counter. As a consequence of the workaround, users may see an increased amount of event multiplexing, even in situtations where there are fewer events than counters measured on a CPU. Patch has been tested on all three impacted processors. Note that when HT is off, there is no corruption. However, the workaround is still enabled, yet not costing too much. Adding a dynamic detection of HT on turned out to be complex are requiring too much to code to be justified. This patch addresses the issue when PEBS is not used. A subsequent patch fixes the problem when PEBS is used. Signed-off-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> [spinlock_t -> raw_spinlock_t] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Stephane Eranian <eranian@google.com> Cc: bp@alien8.de Cc: jolsa@redhat.com Cc: kan.liang@intel.com Link: http://lkml.kernel.org/r/1416251225-17721-7-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-11-18 03:06:58 +08:00
bool sched_started; /* true if scheduling has started */
};
struct intel_excl_cntrs {
raw_spinlock_t lock;
struct intel_excl_states states[2];
union {
u16 has_exclusive[2];
u32 exclusive_present;
};
int refcnt; /* per-core: #HT threads */
unsigned core_id; /* per-core: core id */
};
#define MAX_LBR_ENTRIES 32
enum {
X86_PERF_KFREE_SHARED = 0,
X86_PERF_KFREE_EXCL = 1,
X86_PERF_KFREE_MAX
};
struct cpu_hw_events {
/*
* Generic x86 PMC bits
*/
struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */
unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
int enabled;
int n_events; /* the # of events in the below arrays */
int n_added; /* the # last events in the below arrays;
they've never been enabled yet */
int n_txn; /* the # last events in the below arrays;
added in the current transaction */
int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
u64 tags[X86_PMC_IDX_MAX];
perf/x86: Fix event/group validation Commit 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") violated the rule that 'fake' scheduling; as used for event/group validation; should not change the event state. This went mostly un-noticed because repeated calls of x86_pmu::get_event_constraints() would give the same result. And x86_pmu::put_event_constraints() would mostly not do anything. Commit e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") made the situation much worse by actually setting the event->hw.constraint value to NULL, so when validation and actual scheduling interact we get NULL ptr derefs. Fix it by removing the constraint pointer from the event and move it back to an array, this time in cpuc instead of on the stack. validate_group() x86_schedule_events() event->hw.constraint = c; # store <context switch> perf_task_event_sched_in() ... x86_schedule_events(); event->hw.constraint = c2; # store ... put_event_constraints(event); # assume failure to schedule intel_put_event_constraints() event->hw.constraint = NULL; <context switch end> c = event->hw.constraint; # read -> NULL if (!test_bit(hwc->idx, c->idxmsk)) # <- *BOOM* NULL deref This in particular is possible when the event in question is a cpu-wide event and group-leader, where the validate_group() tries to add an event to the group. Reported-by: Vince Weaver <vincent.weaver@maine.edu> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Hunter <ahh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") Fixes: e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-21 16:57:13 +08:00
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
perf/x86: Fix event/group validation Commit 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") violated the rule that 'fake' scheduling; as used for event/group validation; should not change the event state. This went mostly un-noticed because repeated calls of x86_pmu::get_event_constraints() would give the same result. And x86_pmu::put_event_constraints() would mostly not do anything. Commit e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") made the situation much worse by actually setting the event->hw.constraint value to NULL, so when validation and actual scheduling interact we get NULL ptr derefs. Fix it by removing the constraint pointer from the event and move it back to an array, this time in cpuc instead of on the stack. validate_group() x86_schedule_events() event->hw.constraint = c; # store <context switch> perf_task_event_sched_in() ... x86_schedule_events(); event->hw.constraint = c2; # store ... put_event_constraints(event); # assume failure to schedule intel_put_event_constraints() event->hw.constraint = NULL; <context switch end> c = event->hw.constraint; # read -> NULL if (!test_bit(hwc->idx, c->idxmsk)) # <- *BOOM* NULL deref This in particular is possible when the event in question is a cpu-wide event and group-leader, where the validate_group() tries to add an event to the group. Reported-by: Vince Weaver <vincent.weaver@maine.edu> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Hunter <ahh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") Fixes: e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-21 16:57:13 +08:00
struct event_constraint *event_constraint[X86_PMC_IDX_MAX];
int n_excl; /* the number of exclusive events */
2015-09-04 11:07:45 +08:00
unsigned int txn_flags;
int is_fake;
/*
* Intel DebugStore bits
*/
struct debug_store *ds;
u64 pebs_enabled;
/*
* Intel LBR bits
*/
int lbr_users;
void *lbr_context;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
u64 br_sel;
/*
* Intel host/guest exclude bits
*/
u64 intel_ctrl_guest_mask;
u64 intel_ctrl_host_mask;
struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
/*
* Intel checkpoint mask
*/
u64 intel_cp_status;
/*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
*/
struct intel_shared_regs *shared_regs;
/*
* manage exclusive counter access between hyperthread
*/
struct event_constraint *constraint_list; /* in enable order */
struct intel_excl_cntrs *excl_cntrs;
int excl_thread_id; /* 0 or 1 */
/*
* AMD specific bits
*/
struct amd_nb *amd_nb;
/* Inverted mask of bits to clear in the perf_ctr ctrl registers */
u64 perf_ctr_virt_mask;
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
{ .idxmsk64 = (n) }, \
.code = (c), \
.cmask = (m), \
.weight = (w), \
perf, x86: Fix event scheduler for constraints with overlapping counters The current x86 event scheduler fails to resolve scheduling problems of certain combinations of events and constraints. This happens if the counter mask of such an event is not a subset of any other counter mask of a constraint with an equal or higher weight, e.g. constraints of the AMD family 15h pmu: counter mask weight amd_f15_PMC30 0x09 2 <--- overlapping counters amd_f15_PMC20 0x07 3 amd_f15_PMC53 0x38 3 The scheduler does not find then an existing solution. Here is an example: event code counter failure possible solution 0x02E PMC[3,0] 0 3 0x043 PMC[2:0] 1 0 0x045 PMC[2:0] 2 1 0x046 PMC[2:0] FAIL 2 The event scheduler may not select the correct counter in the first cycle because it needs to know which subsequent events will be scheduled. It may fail to schedule the events then. To solve this, we now save the scheduler state of events with overlapping counter counstraints. If we fail to schedule the events we rollback to those states and try to use another free counter. Constraints with overlapping counters are marked with a new introduced overlap flag. We set the overlap flag for such constraints to give the scheduler a hint which events to select for counter rescheduling. The EVENT_CONSTRAINT_OVERLAP() macro can be used for this. Care must be taken as the rescheduling algorithm is O(n!) which will increase scheduling cycles for an over-commited system dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter masks must be kept at a minimum. Thus, the current stack is limited to 2 states to limit the number of loops the algorithm takes in the worst case. On systems with no overlapping-counter constraints, this implementation does not increase the loop count compared to the previous algorithm. V2: * Renamed redo -> overlap. * Reimplementation using perf scheduling helper functions. V3: * Added WARN_ON_ONCE() if out of save states. * Changed function interface of perf_sched_restore_state() to use bool as return value. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-18 19:35:22 +08:00
.overlap = (o), \
.flags = f, \
}
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
perf, x86: Fix event scheduler for constraints with overlapping counters The current x86 event scheduler fails to resolve scheduling problems of certain combinations of events and constraints. This happens if the counter mask of such an event is not a subset of any other counter mask of a constraint with an equal or higher weight, e.g. constraints of the AMD family 15h pmu: counter mask weight amd_f15_PMC30 0x09 2 <--- overlapping counters amd_f15_PMC20 0x07 3 amd_f15_PMC53 0x38 3 The scheduler does not find then an existing solution. Here is an example: event code counter failure possible solution 0x02E PMC[3,0] 0 3 0x043 PMC[2:0] 1 0 0x045 PMC[2:0] 2 1 0x046 PMC[2:0] FAIL 2 The event scheduler may not select the correct counter in the first cycle because it needs to know which subsequent events will be scheduled. It may fail to schedule the events then. To solve this, we now save the scheduler state of events with overlapping counter counstraints. If we fail to schedule the events we rollback to those states and try to use another free counter. Constraints with overlapping counters are marked with a new introduced overlap flag. We set the overlap flag for such constraints to give the scheduler a hint which events to select for counter rescheduling. The EVENT_CONSTRAINT_OVERLAP() macro can be used for this. Care must be taken as the rescheduling algorithm is O(n!) which will increase scheduling cycles for an over-commited system dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter masks must be kept at a minimum. Thus, the current stack is limited to 2 states to limit the number of loops the algorithm takes in the worst case. On systems with no overlapping-counter constraints, this implementation does not increase the loop count compared to the previous algorithm. V2: * Renamed redo -> overlap. * Reimplementation using perf scheduling helper functions. V3: * Added WARN_ON_ONCE() if out of save states. * Changed function interface of perf_sched_restore_state() to use bool as return value. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-18 19:35:22 +08:00
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
perf, x86: Fix event scheduler for constraints with overlapping counters The current x86 event scheduler fails to resolve scheduling problems of certain combinations of events and constraints. This happens if the counter mask of such an event is not a subset of any other counter mask of a constraint with an equal or higher weight, e.g. constraints of the AMD family 15h pmu: counter mask weight amd_f15_PMC30 0x09 2 <--- overlapping counters amd_f15_PMC20 0x07 3 amd_f15_PMC53 0x38 3 The scheduler does not find then an existing solution. Here is an example: event code counter failure possible solution 0x02E PMC[3,0] 0 3 0x043 PMC[2:0] 1 0 0x045 PMC[2:0] 2 1 0x046 PMC[2:0] FAIL 2 The event scheduler may not select the correct counter in the first cycle because it needs to know which subsequent events will be scheduled. It may fail to schedule the events then. To solve this, we now save the scheduler state of events with overlapping counter counstraints. If we fail to schedule the events we rollback to those states and try to use another free counter. Constraints with overlapping counters are marked with a new introduced overlap flag. We set the overlap flag for such constraints to give the scheduler a hint which events to select for counter rescheduling. The EVENT_CONSTRAINT_OVERLAP() macro can be used for this. Care must be taken as the rescheduling algorithm is O(n!) which will increase scheduling cycles for an over-commited system dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter masks must be kept at a minimum. Thus, the current stack is limited to 2 states to limit the number of loops the algorithm takes in the worst case. On systems with no overlapping-counter constraints, this implementation does not increase the loop count compared to the previous algorithm. V2: * Renamed redo -> overlap. * Reimplementation using perf scheduling helper functions. V3: * Added WARN_ON_ONCE() if out of save states. * Changed function interface of perf_sched_restore_state() to use bool as return value. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-18 19:35:22 +08:00
/*
* The overlap flag marks event constraints with overlapping counter
* masks. This is the case if the counter mask of such an event is not
* a subset of any other counter mask of a constraint with an equal or
* higher weight, e.g.:
*
* c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
* c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
* c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
*
* The event scheduler may not select the correct counter in the first
* cycle because it needs to know which subsequent events will be
* scheduled. It may fail to schedule the events then. So we set the
* overlap flag for such constraints to give the scheduler a hint which
* events to select for counter rescheduling.
*
* Care must be taken as the rescheduling algorithm is O(n!) which
* will increase scheduling cycles for an over-committed system
perf, x86: Fix event scheduler for constraints with overlapping counters The current x86 event scheduler fails to resolve scheduling problems of certain combinations of events and constraints. This happens if the counter mask of such an event is not a subset of any other counter mask of a constraint with an equal or higher weight, e.g. constraints of the AMD family 15h pmu: counter mask weight amd_f15_PMC30 0x09 2 <--- overlapping counters amd_f15_PMC20 0x07 3 amd_f15_PMC53 0x38 3 The scheduler does not find then an existing solution. Here is an example: event code counter failure possible solution 0x02E PMC[3,0] 0 3 0x043 PMC[2:0] 1 0 0x045 PMC[2:0] 2 1 0x046 PMC[2:0] FAIL 2 The event scheduler may not select the correct counter in the first cycle because it needs to know which subsequent events will be scheduled. It may fail to schedule the events then. To solve this, we now save the scheduler state of events with overlapping counter counstraints. If we fail to schedule the events we rollback to those states and try to use another free counter. Constraints with overlapping counters are marked with a new introduced overlap flag. We set the overlap flag for such constraints to give the scheduler a hint which events to select for counter rescheduling. The EVENT_CONSTRAINT_OVERLAP() macro can be used for this. Care must be taken as the rescheduling algorithm is O(n!) which will increase scheduling cycles for an over-commited system dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros and its counter masks must be kept at a minimum. Thus, the current stack is limited to 2 states to limit the number of loops the algorithm takes in the worst case. On systems with no overlapping-counter constraints, this implementation does not increase the loop count compared to the previous algorithm. V2: * Renamed redo -> overlap. * Reimplementation using perf scheduling helper functions. V3: * Added WARN_ON_ONCE() if out of save states. * Changed function interface of perf_sched_restore_state() to use bool as return value. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1321616122-1533-3-git-send-email-robert.richter@amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-18 19:35:22 +08:00
* dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros
* and its counter masks must be kept at a minimum.
*/
#define EVENT_CONSTRAINT_OVERLAP(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
/*
* Constraint on the Event code.
*/
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
/*
* Constraint on the Event code + UMask + fixed-mask
*
* filter mask to validate fixed counter events.
* the following filters disqualify for fixed counters:
* - inv
* - edge
* - cnt-mask
* - in_tx
* - in_tx_checkpointed
* The other filters are supported by fixed counters.
* The any-thread option is supported starting with v3.
*/
#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)
#define FIXED_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS)
/*
* Constraint on the Event code + UMask
*/
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
/* Constraint on specific umask bit only + event */
#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c))
/* Like UEVENT_CONSTRAINT, but match flags too */
#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
perf/x86/intel: Implement cross-HT corruption bug workaround This patch implements a software workaround for a HW erratum on Intel SandyBridge, IvyBridge and Haswell processors with Hyperthreading enabled. The errata are documented for each processor in their respective specification update documents: - SandyBridge: BJ122 - IvyBridge: BV98 - Haswell: HSD29 The bug causes silent counter corruption across hyperthreads only when measuring certain memory events (0xd0, 0xd1, 0xd2, 0xd3). Counters measuring those events may leak counts to the sibling counter. For instance, counter 0, thread 0 measuring event 0xd0, may leak to counter 0, thread 1, regardless of the event measured there. The size of the leak is not predictible. It all depends on the workload and the state of each sibling hyper-thread. The corrupting events do undercount as a consequence of the leak. The leak is compensated automatically only when the sibling counter measures the exact same corrupting event AND the workload is on the two threads is the same. Given, there is no way to guarantee this, a work-around is necessary. Furthermore, there is a serious problem if the leaked count is added to a low-occurrence event. In that case the corruption on the low occurrence event can be very large, e.g., orders of magnitude. There is no HW or FW workaround for this problem. The bug is very easy to reproduce on a loaded system. Here is an example on a Haswell client, where CPU0, CPU4 are siblings. We load the CPUs with a simple triad app streaming large floating-point vector. We use 0x81d0 corrupting event (MEM_UOPS_RETIRED:ALL_LOADS) and 0x20cc (ROB_MISC_EVENTS:LBR_INSERTS). Given we are not using the LBR, the 0x20cc event should be zero. $ taskset -c 0 triad & $ taskset -c 4 triad & $ perf stat -a -C 0 -e r81d0 sleep 100 & $ perf stat -a -C 4 -r20cc sleep 10 Performance counter stats for 'system wide': 139 277 291 r20cc 10,000969126 seconds time elapsed In this example, 0x81d0 and r20cc ar eusing sinling counters on CPU0 and CPU4. 0x81d0 leaks into 0x20cc and corrupts it from 0 to 139 millions occurrences. This patch provides a software workaround to this problem by modifying the way events are scheduled onto counters by the kernel. The patch forces cross-thread mutual exclusion between counters in case a corrupting event is measured by one of the hyper-threads. If thread 0, counter 0 is measuring event 0xd0, then nothing can be measured on counter 0, thread 1. If no corrupting event is measured on any hyper-thread, event scheduling proceeds as before. The same example run with the workaround enabled, yield the correct answer: $ taskset -c 0 triad & $ taskset -c 4 triad & $ perf stat -a -C 0 -e r81d0 sleep 100 & $ perf stat -a -C 4 -r20cc sleep 10 Performance counter stats for 'system wide': 0 r20cc 10,000969126 seconds time elapsed The patch does provide correctness for all non-corrupting events. It does not "repatriate" the leaked counts back to the leaking counter. This is planned for a second patch series. This patch series makes this repatriation more easy by guaranteeing the sibling counter is not measuring any useful event. The patch introduces dynamic constraints for events. That means that events which did not have constraints, i.e., could be measured on any counters, may now be constrained to a subset of the counters depending on what is going on the sibling thread. The algorithm is similar to a cache coherency protocol. We call it XSU in reference to Exclusive, Shared, Unused, the 3 possible states of a PMU counter. As a consequence of the workaround, users may see an increased amount of event multiplexing, even in situtations where there are fewer events than counters measured on a CPU. Patch has been tested on all three impacted processors. Note that when HT is off, there is no corruption. However, the workaround is still enabled, yet not costing too much. Adding a dynamic detection of HT on turned out to be complex are requiring too much to code to be justified. This patch addresses the issue when PEBS is not used. A subsequent patch fixes the problem when PEBS is used. Signed-off-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> [spinlock_t -> raw_spinlock_t] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Stephane Eranian <eranian@google.com> Cc: bp@alien8.de Cc: jolsa@redhat.com Cc: kan.liang@intel.com Link: http://lkml.kernel.org/r/1416251225-17721-7-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-11-18 03:06:58 +08:00
#define INTEL_EXCLUEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
HWEIGHT(n), 0, PERF_X86_EVENT_EXCL)
#define INTEL_PLD_CONSTRAINT(c, n) \
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
#define INTEL_PST_CONSTRAINT(c, n) \
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
/* Event constraint, but match on all event flags too. */
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
/* Check flags and event code, and set the HSW store flag */
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
/* Check flags and event code, and set the HSW load flag */
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
__EVENT_CONSTRAINT(code, n, \
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
/* Check flags and event code/umask, and set the HSW store flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_ST_HSW|PERF_X86_EVENT_EXCL)
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
/* Check flags and event code/umask, and set the HSW load flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, \
PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL)
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
/* Check flags and event code/umask, and set the HSW N/A flag */
#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
__EVENT_CONSTRAINT(code, n, \
INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
perf/x86: Revamp PEBS event selection The basic idea is that it does not make sense to list all PEBS events individually. The list is very long, sometimes outdated and the hardware doesn't need it. If an event does not support PEBS it will just not count, there is no security issue. We need to only list events that something special, like supporting load or store addresses. This vastly simplifies the PEBS event selection. It also speeds up the scheduling because the scheduler doesn't have to walk as many constraints. Bugs fixed: - We do not allow setting forbidden flags with PEBS anymore (SDM 18.9.4), except for the special cycle event. This is done using a new constraint macro that also matches on the event flags. - Correct DataLA and load/store/na flags reporting on Haswell [Requires a followon patch] - We did not allow all PEBS events on Haswell: We were missing some valid subevents in d1-d2 (MEM_LOAD_UOPS_RETIRED.*, MEM_LOAD_UOPS_RETIRED_L3_HIT_RETIRED.*) This includes the changes proposed by Stephane earlier and obsoletes his patchkit (except for some changes on pre Sandy Bridge/Silvermont CPUs) I only did Sandy Bridge and Silvermont and later so far, mostly because these are the parts I could directly confirm the hardware behavior with hardware architects. Also I do not believe the older CPUs have any missing events in their PEBS list, so there's no pressing need to change them. I did not implement the flag proposed by Peter to allow setting forbidden flags. If really needed this could be implemented on to of this patch. v2: Fix broken store events on SNB/IVB (Stephane Eranian) v3: More fixes. Rename some arguments (Stephane Eranian) v4: List most Haswell events individually again to report memory operation type correctly. Add new flags to describe load/store/na for datala. Update description. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1407785233-32193-2-git-send-email-eranian@google.com Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Mark Davies <junk@eslaf.co.uk> Cc: Paul Mackerras <paulus@samba.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yan, Zheng <zheng.z.yan@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-12 03:27:10 +08:00
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We define the end marker as having a weight of -1
* to enable blacklisting of events using a counter bitmask
* of zero and thus a weight of zero.
* The end marker has a weight that cannot possibly be
* obtained from counting the bits in the bitmask.
*/
#define EVENT_CONSTRAINT_END { .weight = -1 }
/*
* Check for end marker with weight == -1
*/
#define for_each_event_constraint(e, c) \
for ((e) = (c); (e)->weight != -1; (e)++)
/*
* Extra registers for specific events.
*
* Some events need large masks and require external MSRs.
* Those extra MSRs end up being shared for all events on
* a PMU and sometimes between PMU of sibling HT threads.
* In either case, the kernel needs to handle conflicting
* accesses to those extra, shared, regs. The data structure
* to manage those registers is stored in cpu_hw_event.
*/
struct extra_reg {
unsigned int event;
unsigned int msr;
u64 config_mask;
u64 valid_mask;
int idx; /* per_xxx->regs[] reg index */
bool extra_msr_access;
};
#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \
.event = (e), \
.msr = (ms), \
.config_mask = (m), \
.valid_mask = (vm), \
.idx = EXTRA_REG_##i, \
.extra_msr_access = true, \
}
#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \
EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
INTEL_UEVENT_EXTRA_REG(c, \
MSR_PEBS_LD_LAT_THRESHOLD, \
0xffff, \
LDLAT)
#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
union perf_capabilities {
struct {
u64 lbr_format:6;
u64 pebs_trap:1;
u64 pebs_arch_reg:1;
u64 pebs_format:4;
u64 smm_freeze:1;
/*
* PMU supports separate counter range for writing
* values > 32bit.
*/
u64 full_width_write:1;
};
u64 capabilities;
};
struct x86_pmu_quirk {
struct x86_pmu_quirk *next;
void (*func)(void);
};
union x86_pmu_config {
struct {
u64 event:8,
umask:8,
usr:1,
os:1,
edge:1,
pc:1,
interrupt:1,
__reserved1:1,
en:1,
inv:1,
cmask:8,
event2:4,
__reserved2:4,
go:1,
ho:1;
} bits;
u64 value;
};
#define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value
enum {
x86_lbr_exclusive_lbr,
x86_lbr_exclusive_bts,
x86_lbr_exclusive_pt,
x86_lbr_exclusive_max,
};
/*
* struct x86_pmu - generic x86 pmu
*/
struct x86_pmu {
/*
* Generic x86 PMC bits
*/
const char *name;
int version;
int (*handle_irq)(struct pt_regs *);
void (*disable_all)(void);
void (*enable_all)(int added);
void (*enable)(struct perf_event *);
void (*disable)(struct perf_event *);
int (*hw_config)(struct perf_event *event);
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
unsigned eventsel;
unsigned perfctr;
int (*addr_offset)(int index, bool eventsel);
int (*rdpmc_index)(int index);
u64 (*event_map)(int);
int max_events;
int num_counters;
int num_counters_fixed;
int cntval_bits;
u64 cntval_mask;
union {
unsigned long events_maskl;
unsigned long events_mask[BITS_TO_LONGS(ARCH_PERFMON_EVENTS_COUNT)];
};
int events_mask_len;
int apic;
u64 max_period;
struct event_constraint *
(*get_event_constraints)(struct cpu_hw_events *cpuc,
int idx,
struct perf_event *event);
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
void (*start_scheduling)(struct cpu_hw_events *cpuc);
void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
void (*stop_scheduling)(struct cpu_hw_events *cpuc);
struct event_constraint *event_constraints;
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
bool late_ack;
perf/x86/intel: Add INST_RETIRED.ALL workarounds On Broadwell INST_RETIRED.ALL cannot be used with any period that doesn't have the lowest 6 bits cleared. And the period should not be smaller than 128. This is erratum BDM11 and BDM55: http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/5th-gen-core-family-spec-update.pdf BDM11: When using a period < 100; we may get incorrect PEBS/PMI interrupts and/or an invalid counter state. BDM55: When bit0-5 of the period are !0 we may get redundant PEBS records on overflow. Add a new callback to enforce this, and set it for Broadwell. How does this handle the case when an app requests a specific period with some of the bottom bits set? Short answer: Any useful instruction sampling period needs to be 4-6 orders of magnitude larger than 128, as an PMI every 128 instructions would instantly overwhelm the system and be throttled. So the +-64 error from this is really small compared to the period, much smaller than normal system jitter. Long answer (by Peterz): IFF we guarantee perf_event_attr::sample_period >= 128. Suppose we start out with sample_period=192; then we'll set period_left to 192, we'll end up with left = 128 (we truncate the lower bits). We get an interrupt, find that period_left = 64 (>0 so we return 0 and don't get an overflow handler), up that to 128. Then we trigger again, at n=256. Then we find period_left = -64 (<=0 so we return 1 and do get an overflow). We increment with sample_period so we get left = 128. We fire again, at n=384, period_left = 0 (<=0 so we return 1 and get an overflow). And on and on. So while the individual interrupts are 'wrong' we get then with interval=256,128 in exactly the right ratio to average out at 192. And this works for everything >=128. So the num_samples*fixed_period thing is still entirely correct +- 127, which is good enough I'd say, as you already have that error anyhow. So no need to 'fix' the tools, al we need to do is refuse to create INST_RETIRED:ALL events with sample_period < 128. Signed-off-by: Andi Kleen <ak@linux.intel.com> [ Updated comments and changelog a bit. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/1424225886-18652-3-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-02-18 10:18:06 +08:00
unsigned (*limit_period)(struct perf_event *event, unsigned l);
/*
* sysfs attrs
*/
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
struct attribute **event_attrs;
perf/x86: Make hardware event translations available in sysfs Add support to display hardware events translations available through the sysfs. Add 'events' group attribute under the sysfs x86 PMU record with attribute/file for each hardware event. This patch adds only backbone for PMUs to display config under 'events' directory. The specific PMU support itself will come in next patches, however this is how the sysfs group will look like: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend The file - hw event ID mapping is: file hw event ID --------------------------------------------------------------- cpu-cycles PERF_COUNT_HW_CPU_CYCLES instructions PERF_COUNT_HW_INSTRUCTIONS cache-references PERF_COUNT_HW_CACHE_REFERENCES cache-misses PERF_COUNT_HW_CACHE_MISSES branch-instructions PERF_COUNT_HW_BRANCH_INSTRUCTIONS branch-misses PERF_COUNT_HW_BRANCH_MISSES bus-cycles PERF_COUNT_HW_BUS_CYCLES stalled-cycles-frontend PERF_COUNT_HW_STALLED_CYCLES_FRONTEND stalled-cycles-backend PERF_COUNT_HW_STALLED_CYCLES_BACKEND ref-cycles PERF_COUNT_HW_REF_CPU_CYCLES Each file in the 'events' directory contains the term translation for the symbolic hw event for the currently running cpu model. # cat /sys/devices/cpu/events/stalled-cycles-backend event=0xb1,umask=0x01,inv,cmask=0x01 Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1349873598-12583-2-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-10 20:53:11 +08:00
ssize_t (*events_sysfs_show)(char *page, u64 config);
struct attribute **cpu_events;
perf/x86: Make hardware event translations available in sysfs Add support to display hardware events translations available through the sysfs. Add 'events' group attribute under the sysfs x86 PMU record with attribute/file for each hardware event. This patch adds only backbone for PMUs to display config under 'events' directory. The specific PMU support itself will come in next patches, however this is how the sysfs group will look like: # ls /sys/devices/cpu/events/ branch-instructions branch-misses bus-cycles cache-misses cache-references cpu-cycles instructions ref-cycles stalled-cycles-backend stalled-cycles-frontend The file - hw event ID mapping is: file hw event ID --------------------------------------------------------------- cpu-cycles PERF_COUNT_HW_CPU_CYCLES instructions PERF_COUNT_HW_INSTRUCTIONS cache-references PERF_COUNT_HW_CACHE_REFERENCES cache-misses PERF_COUNT_HW_CACHE_MISSES branch-instructions PERF_COUNT_HW_BRANCH_INSTRUCTIONS branch-misses PERF_COUNT_HW_BRANCH_MISSES bus-cycles PERF_COUNT_HW_BUS_CYCLES stalled-cycles-frontend PERF_COUNT_HW_STALLED_CYCLES_FRONTEND stalled-cycles-backend PERF_COUNT_HW_STALLED_CYCLES_BACKEND ref-cycles PERF_COUNT_HW_REF_CPU_CYCLES Each file in the 'events' directory contains the term translation for the symbolic hw event for the currently running cpu model. # cat /sys/devices/cpu/events/stalled-cycles-backend event=0xb1,umask=0x01,inv,cmask=0x01 Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1349873598-12583-2-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-10-10 20:53:11 +08:00
/*
* CPU Hotplug hooks
*/
int (*cpu_prepare)(int cpu);
void (*cpu_starting)(int cpu);
void (*cpu_dying)(int cpu);
void (*cpu_dead)(int cpu);
void (*check_microcode)(void);
void (*sched_task)(struct perf_event_context *ctx,
bool sched_in);
/*
* Intel Arch Perfmon v2+
*/
u64 intel_ctrl;
union perf_capabilities intel_cap;
/*
* Intel DebugStore bits
*/
unsigned int bts :1,
bts_active :1,
pebs :1,
pebs_active :1,
perf/x86: Use INST_RETIRED.PREC_DIST for cycles: ppp Add a new 'three-p' precise level, that uses INST_RETIRED.PREC_DIST as base. The basic mechanism of abusing the inverse cmask to get all cycles works the same as before. PREC_DIST is available on Sandy Bridge or later. It had some problems on Sandy Bridge, so we only use it on IvyBridge and later. I tested it on Broadwell and Skylake. PREC_DIST has special support for avoiding shadow effects, which can give better results compare to UOPS_RETIRED. The drawback is that PREC_DIST can only schedule on counter 1, but that is ok for cycle sampling, as there is normally no need to do multiple cycle sampling runs in parallel. It is still possible to run perf top in parallel, as that doesn't use precise mode. Also of course the multiplexing can still allow parallel operation. :pp stays with the previous event. Example: Sample a loop with 10 sqrt with old cycles:pp 0.14 │10: sqrtps %xmm1,%xmm0 <-------------- 9.13 │ sqrtps %xmm1,%xmm0 11.58 │ sqrtps %xmm1,%xmm0 11.51 │ sqrtps %xmm1,%xmm0 6.27 │ sqrtps %xmm1,%xmm0 10.38 │ sqrtps %xmm1,%xmm0 12.20 │ sqrtps %xmm1,%xmm0 12.74 │ sqrtps %xmm1,%xmm0 5.40 │ sqrtps %xmm1,%xmm0 10.14 │ sqrtps %xmm1,%xmm0 10.51 │ ↑ jmp 10 We expect all 10 sqrt to get roughly the sample number of samples. But you can see that the instruction directly after the JMP is systematically underestimated in the result, due to sampling shadow effects. With the new PREC_DIST based sampling this problem is gone and all instructions show up roughly evenly: 9.51 │10: sqrtps %xmm1,%xmm0 11.74 │ sqrtps %xmm1,%xmm0 11.84 │ sqrtps %xmm1,%xmm0 6.05 │ sqrtps %xmm1,%xmm0 10.46 │ sqrtps %xmm1,%xmm0 12.25 │ sqrtps %xmm1,%xmm0 12.18 │ sqrtps %xmm1,%xmm0 5.26 │ sqrtps %xmm1,%xmm0 10.13 │ sqrtps %xmm1,%xmm0 10.43 │ sqrtps %xmm1,%xmm0 0.16 │ ↑ jmp 10 Even with PREC_DIST there is still sampling skid and the result is not completely even, but systematic shadow effects are significantly reduced. The improvements are mainly expected to make a difference in high IPC code. With low IPC it should be similar. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: hpa@zytor.com Link: http://lkml.kernel.org/r/1448929689-13771-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-12-04 19:50:52 +08:00
pebs_broken :1,
pebs_prec_dist :1;
int pebs_record_size;
int pebs_buffer_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
int max_pebs_events;
unsigned long free_running_flags;
/*
* Intel LBR
*/
unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
int lbr_nr; /* hardware stack size */
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
bool lbr_double_abort; /* duplicated lbr aborts */
/*
* Intel PT/LBR/BTS are exclusive
*/
atomic_t lbr_exclusive[x86_lbr_exclusive_max];
/*
* Extra registers for events
*/
struct extra_reg *extra_regs;
unsigned int flags;
/*
* Intel host/guest support (KVM)
*/
struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
};
struct x86_perf_task_context {
u64 lbr_from[MAX_LBR_ENTRIES];
u64 lbr_to[MAX_LBR_ENTRIES];
u64 lbr_info[MAX_LBR_ENTRIES];
int tos;
int lbr_callstack_users;
int lbr_stack_state;
};
#define x86_add_quirk(func_) \
do { \
static struct x86_pmu_quirk __quirk __initdata = { \
.func = func_, \
}; \
__quirk.next = x86_pmu.quirks; \
x86_pmu.quirks = &__quirk; \
} while (0)
/*
* x86_pmu flags
*/
#define PMU_FL_NO_HT_SHARING 0x1 /* no hyper-threading resource sharing */
#define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */
#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */
#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
#define EVENT_ATTR(_name, _id) \
static struct perf_pmu_events_attr EVENT_VAR(_id) = { \
.attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
.id = PERF_COUNT_HW_##_id, \
.event_str = NULL, \
};
#define EVENT_ATTR_STR(_name, v, str) \
static struct perf_pmu_events_attr event_attr_##v = { \
.attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \
.id = 0, \
.event_str = str, \
};
extern struct x86_pmu x86_pmu __read_mostly;
2014-11-05 10:56:00 +08:00
static inline bool x86_pmu_has_lbr_callstack(void)
{
return x86_pmu.lbr_sel_map &&
x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
}
DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
int x86_perf_event_set_period(struct perf_event *event);
/*
* Generalized hw caching related hw_event table, filled
* in on a per model basis. A value of 0 means
* 'not supported', -1 means 'hw_event makes no sense on
* this CPU', any other value means the raw hw_event
* ID.
*/
#define C(x) PERF_COUNT_HW_CACHE_##x
extern u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
extern u64 __read_mostly hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
u64 x86_perf_event_update(struct perf_event *event);
static inline unsigned int x86_pmu_config_addr(int index)
{
return x86_pmu.eventsel + (x86_pmu.addr_offset ?
x86_pmu.addr_offset(index, true) : index);
}
static inline unsigned int x86_pmu_event_addr(int index)
{
return x86_pmu.perfctr + (x86_pmu.addr_offset ?
x86_pmu.addr_offset(index, false) : index);
}
static inline int x86_pmu_rdpmc_index(int index)
{
return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
}
int x86_add_exclusive(unsigned int what);
void x86_del_exclusive(unsigned int what);
int x86_reserve_hardware(void);
void x86_release_hardware(void);
void hw_perf_lbr_event_destroy(struct perf_event *event);
int x86_setup_perfctr(struct perf_event *event);
int x86_pmu_hw_config(struct perf_event *event);
void x86_pmu_disable_all(void);
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 enable_mask)
{
u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
if (hwc->extra_reg.reg)
wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
}
void x86_pmu_enable_all(int added);
perf/x86: Fix event/group validation Commit 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") violated the rule that 'fake' scheduling; as used for event/group validation; should not change the event state. This went mostly un-noticed because repeated calls of x86_pmu::get_event_constraints() would give the same result. And x86_pmu::put_event_constraints() would mostly not do anything. Commit e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") made the situation much worse by actually setting the event->hw.constraint value to NULL, so when validation and actual scheduling interact we get NULL ptr derefs. Fix it by removing the constraint pointer from the event and move it back to an array, this time in cpuc instead of on the stack. validate_group() x86_schedule_events() event->hw.constraint = c; # store <context switch> perf_task_event_sched_in() ... x86_schedule_events(); event->hw.constraint = c2; # store ... put_event_constraints(event); # assume failure to schedule intel_put_event_constraints() event->hw.constraint = NULL; <context switch end> c = event->hw.constraint; # read -> NULL if (!test_bit(hwc->idx, c->idxmsk)) # <- *BOOM* NULL deref This in particular is possible when the event in question is a cpu-wide event and group-leader, where the validate_group() tries to add an event to the group. Reported-by: Vince Weaver <vincent.weaver@maine.edu> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Hunter <ahh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: 43b4578071c0 ("perf/x86: Reduce stack usage of x86_schedule_events()") Fixes: e979121b1b15 ("perf/x86/intel: Implement cross-HT corruption bug workaround") Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-21 16:57:13 +08:00
int perf_assign_events(struct event_constraint **constraints, int n,
int wmin, int wmax, int gpmax, int *assign);
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
void x86_pmu_stop(struct perf_event *event, int flags);
static inline void x86_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
wrmsrl(hwc->config_base, hwc->config);
}
void x86_pmu_enable_event(struct perf_event *event);
int x86_pmu_handle_irq(struct pt_regs *regs);
extern struct event_constraint emptyconstraint;
extern struct event_constraint unconstrained;
static inline bool kernel_ip(unsigned long ip)
{
#ifdef CONFIG_X86_32
return ip > PAGE_OFFSET;
#else
return (long)ip < 0;
#endif
}
/*
* Not all PMUs provide the right context information to place the reported IP
* into full context. Specifically segment registers are typically not
* supplied.
*
* Assuming the address is a linear address (it is for IBS), we fake the CS and
* vm86 mode using the known zero-based code segment and 'fix up' the registers
* to reflect this.
*
* Intel PEBS/LBR appear to typically provide the effective address, nothing
* much we can do about that but pray and treat it like a linear address.
*/
static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
{
regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
if (regs->flags & X86_VM_MASK)
regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
regs->ip = ip;
}
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
struct attribute **merge_attr(struct attribute **a, struct attribute **b);
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
#else /* CONFIG_CPU_SUP_AMD */
static inline int amd_pmu_init(void)
{
return 0;
}
#endif /* CONFIG_CPU_SUP_AMD */
#ifdef CONFIG_CPU_SUP_INTEL
static inline bool intel_pmu_has_bts(struct perf_event *event)
{
if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
!event->attr.freq && event->hw.sample_period == 1)
return true;
return false;
}
int intel_pmu_save_and_restart(struct perf_event *event);
struct event_constraint *
x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event);
struct intel_shared_regs *allocate_shared_regs(int cpu);
int intel_pmu_init(void);
void init_debug_store_on_cpu(int cpu);
void fini_debug_store_on_cpu(int cpu);
void release_ds_buffers(void);
void reserve_ds_buffers(void);
extern struct event_constraint bts_constraint;
void intel_pmu_enable_bts(u64 config);
void intel_pmu_disable_bts(void);
int intel_pmu_drain_bts_buffer(void);
extern struct event_constraint intel_core2_pebs_event_constraints[];
extern struct event_constraint intel_atom_pebs_event_constraints[];
extern struct event_constraint intel_slm_pebs_event_constraints[];
extern struct event_constraint intel_nehalem_pebs_event_constraints[];
extern struct event_constraint intel_westmere_pebs_event_constraints[];
extern struct event_constraint intel_snb_pebs_event_constraints[];
extern struct event_constraint intel_ivb_pebs_event_constraints[];
extern struct event_constraint intel_hsw_pebs_event_constraints[];
extern struct event_constraint intel_bdw_pebs_event_constraints[];
extern struct event_constraint intel_skl_pebs_event_constraints[];
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_enable(struct perf_event *event);
void intel_pmu_pebs_disable(struct perf_event *event);
void intel_pmu_pebs_enable_all(void);
void intel_pmu_pebs_disable_all(void);
void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_lbr_reset(void);
void intel_pmu_lbr_enable(struct perf_event *event);
void intel_pmu_lbr_disable(struct perf_event *event);
void intel_pmu_lbr_enable_all(bool pmi);
void intel_pmu_lbr_disable_all(void);
void intel_pmu_lbr_read(void);
void intel_pmu_lbr_init_core(void);
void intel_pmu_lbr_init_nhm(void);
void intel_pmu_lbr_init_atom(void);
void intel_pmu_lbr_init_snb(void);
2014-11-05 10:56:00 +08:00
void intel_pmu_lbr_init_hsw(void);
void intel_pmu_lbr_init_skl(void);
2015-12-08 06:28:18 +08:00
void intel_pmu_lbr_init_knl(void);
void intel_pmu_pebs_data_source_nhm(void);
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
int intel_bts_interrupt(void);
void intel_bts_enable_local(void);
void intel_bts_disable_local(void);
int p4_pmu_init(void);
int p6_pmu_init(void);
int knc_pmu_init(void);
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
static inline int is_ht_workaround_enabled(void)
{
return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
}
#else /* CONFIG_CPU_SUP_INTEL */
static inline void reserve_ds_buffers(void)
{
}
static inline void release_ds_buffers(void)
{
}
static inline int intel_pmu_init(void)
{
return 0;
}
static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
{
return NULL;
}
static inline int is_ht_workaround_enabled(void)
{
return 0;
}
#endif /* CONFIG_CPU_SUP_INTEL */