From a072738e04f0eb26370e39ec679e9a0d65e49aea Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Thu, 11 Mar 2010 19:54:39 +0300 Subject: perf, x86: Implement initial P4 PMU driver The netburst PMU is way different from the "architectural perfomance monitoring" specification that current CPUs use. P4 uses a tuple of ESCR+CCCR+COUNTER MSR registers to handle perfomance monitoring events. A few implementational details: 1) We need a separate x86_pmu::hw_config helper in struct x86_pmu since register bit-fields are quite different from P6, Core and later cpu series. 2) For the same reason is a x86_pmu::schedule_events helper introduced. 3) hw_perf_event::config consists of packed ESCR+CCCR values. It's allowed since in reality both registers only use a half of their size. Of course before making a real write into a particular MSR we need to unpack the value and extend it to a proper size. 4) The tuple of packed ESCR+CCCR in hw_perf_event::config doesn't describe the memory address of ESCR MSR register so that we need to keep a mapping between these tuples used and available ESCR (various P4 events may use same ESCRs but not simultaneously), for this sake every active event has a per-cpu map of hw_perf_event::idx <--> ESCR addresses. 5) Since hw_perf_event::idx is an offset to counter/control register we need to lift X86_PMC_MAX_GENERIC up, otherwise kernel strips it down to 8 registers and event armed may never be turned off (ie the bit in active_mask is set but the loop never reaches this index to check), thanks to Peter Zijlstra Restrictions: - No cascaded counters support (do we ever need them?) - No dependent events support (so PERF_COUNT_HW_INSTRUCTIONS doesn't work for now) - There are events with same counters which can't work simultaneously (need to use intersected ones due to broken counter 1) - No PERF_COUNT_HW_CACHE_ events yet Todo: - Implement dependent events - Need proper hashing for event opcodes (no linear search, good for debugging stage but not in real loads) - Some events counted during a clock cycle -- need to set threshold for them and count every clock cycle just to get summary statistics (ie to behave the same way as other PMUs do) - Need to swicth to use event_constraints - To support RAW events we need to encode a global list of P4 events into p4_templates - Cache events need to be added Event support status matrix: Event status ----------------------------- cycles works cache-references works cache-misses works branch-misses works bus-cycles partially (does not work on 64bit cpu with HT enabled) instruction doesnt work (needs dependent event [mop tagging]) branches doesnt work Signed-off-by: Cyrill Gorcunov Signed-off-by: Lin Ming Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Stephane Eranian Cc: Robert Richter Cc: Frederic Weisbecker LKML-Reference: <20100311165439.GB5129@lenovo> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/perf_event.h | 2 +- arch/x86/include/asm/perf_event_p4.h | 707 +++++++++++++++++++++++++++++++++ arch/x86/kernel/cpu/perf_event.c | 46 ++- arch/x86/kernel/cpu/perf_event_amd.c | 2 + arch/x86/kernel/cpu/perf_event_intel.c | 15 +- arch/x86/kernel/cpu/perf_event_p4.c | 607 ++++++++++++++++++++++++++++ arch/x86/kernel/cpu/perf_event_p6.c | 2 + 7 files changed, 1358 insertions(+), 23 deletions(-) create mode 100644 arch/x86/include/asm/perf_event_p4.h create mode 100644 arch/x86/kernel/cpu/perf_event_p4.c (limited to 'arch/x86') diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index a9038c95161..124dddd598f 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -5,7 +5,7 @@ * Performance event hw details: */ -#define X86_PMC_MAX_GENERIC 8 +#define X86_PMC_MAX_GENERIC 32 #define X86_PMC_MAX_FIXED 3 #define X86_PMC_IDX_GENERIC 0 diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h new file mode 100644 index 00000000000..829f4711645 --- /dev/null +++ b/arch/x86/include/asm/perf_event_p4.h @@ -0,0 +1,707 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + */ + +#ifndef PERF_EVENT_P4_H +#define PERF_EVENT_P4_H + +#include +#include + +/* + * NetBurst has perfomance MSRs shared between + * threads if HT is turned on, ie for both logical + * processors (mem: in turn in Atom with HT support + * perf-MSRs are not shared and every thread has its + * own perf-MSRs set) + */ +#define ARCH_P4_TOTAL_ESCR (46) +#define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ +#define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) +#define ARCH_P4_MAX_CCCR (18) +#define ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) + +#define P4_EVNTSEL_EVENT_MASK 0x7e000000U +#define P4_EVNTSEL_EVENT_SHIFT 25 +#define P4_EVNTSEL_EVENTMASK_MASK 0x01fffe00U +#define P4_EVNTSEL_EVENTMASK_SHIFT 9 +#define P4_EVNTSEL_TAG_MASK 0x000001e0U +#define P4_EVNTSEL_TAG_SHIFT 5 +#define P4_EVNTSEL_TAG_ENABLE 0x00000010U +#define P4_EVNTSEL_T0_OS 0x00000008U +#define P4_EVNTSEL_T0_USR 0x00000004U +#define P4_EVNTSEL_T1_OS 0x00000002U +#define P4_EVNTSEL_T1_USR 0x00000001U + +/* Non HT mask */ +#define P4_EVNTSEL_MASK \ + (P4_EVNTSEL_EVENT_MASK | \ + P4_EVNTSEL_EVENTMASK_MASK | \ + P4_EVNTSEL_TAG_MASK | \ + P4_EVNTSEL_TAG_ENABLE | \ + P4_EVNTSEL_T0_OS | \ + P4_EVNTSEL_T0_USR) + +/* HT mask */ +#define P4_EVNTSEL_MASK_HT \ + (P4_EVNTSEL_MASK | \ + P4_EVNTSEL_T1_OS | \ + P4_EVNTSEL_T1_USR) + +#define P4_CCCR_OVF 0x80000000U +#define P4_CCCR_CASCADE 0x40000000U +#define P4_CCCR_OVF_PMI_T0 0x04000000U +#define P4_CCCR_OVF_PMI_T1 0x08000000U +#define P4_CCCR_FORCE_OVF 0x02000000U +#define P4_CCCR_EDGE 0x01000000U +#define P4_CCCR_THRESHOLD_MASK 0x00f00000U +#define P4_CCCR_THRESHOLD_SHIFT 20 +#define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) +#define P4_CCCR_COMPLEMENT 0x00080000U +#define P4_CCCR_COMPARE 0x00040000U +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000U +#define P4_CCCR_ESCR_SELECT_SHIFT 13 +#define P4_CCCR_ENABLE 0x00001000U +#define P4_CCCR_THREAD_SINGLE 0x00010000U +#define P4_CCCR_THREAD_BOTH 0x00020000U +#define P4_CCCR_THREAD_ANY 0x00030000U + +/* Non HT mask */ +#define P4_CCCR_MASK \ + (P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE | \ + P4_CCCR_ESCR_SELECT_MASK | \ + P4_CCCR_ENABLE) + +/* HT mask */ +#define P4_CCCR_MASK_HT \ + (P4_CCCR_MASK | \ + P4_CCCR_THREAD_ANY) + +/* + * format is 32 bit: ee ss aa aa + * where + * ee - 8 bit event + * ss - 8 bit selector + * aa aa - 16 bits reserved for tags/attributes + */ +#define P4_EVENT_PACK(event, selector) (((event) << 24) | ((selector) << 16)) +#define P4_EVENT_UNPACK_EVENT(packed) (((packed) >> 24) & 0xff) +#define P4_EVENT_UNPACK_SELECTOR(packed) (((packed) >> 16) & 0xff) +#define P4_EVENT_PACK_ATTR(attr) ((attr)) +#define P4_EVENT_UNPACK_ATTR(packed) ((packed) & 0xffff) +#define P4_MAKE_EVENT_ATTR(class, name, bit) class##_##name = (1 << bit) +#define P4_EVENT_ATTR(class, name) class##_##name +#define P4_EVENT_ATTR_STR(class, name) __stringify(class##_##name) + +/* + * config field is 64bit width and consists of + * HT << 63 | ESCR << 32 | CCCR + * where HT is HyperThreading bit (since ESCR + * has it reserved we may use it for own purpose) + * + * note that this is NOT the addresses of respective + * ESCR and CCCR but rather an only packed value should + * be unpacked and written to a proper addresses + * + * the base idea is to pack as much info as + * possible + */ +#define p4_config_pack_escr(v) (((u64)(v)) << 32) +#define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) +#define p4_config_unpack_escr(v) (((u64)(v)) >> 32) +#define p4_config_unpack_cccr(v) (((u64)(v)) & 0xffffffffULL) + +#define p4_config_unpack_emask(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t &= P4_EVNTSEL_EVENTMASK_MASK; \ + t >>= P4_EVNTSEL_EVENTMASK_SHIFT; \ + t; \ + }) + +#define P4_CONFIG_HT_SHIFT 63 +#define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) + +static inline u32 p4_config_unpack_opcode(u64 config) +{ + u32 e, s; + + /* + * we don't care about HT presence here since + * event opcode doesn't depend on it + */ + e = (p4_config_unpack_escr(config) & P4_EVNTSEL_EVENT_MASK) >> P4_EVNTSEL_EVENT_SHIFT; + s = (p4_config_unpack_cccr(config) & P4_CCCR_ESCR_SELECT_MASK) >> P4_CCCR_ESCR_SELECT_SHIFT; + + return P4_EVENT_PACK(e, s); +} + +static inline bool p4_is_event_cascaded(u64 config) +{ + u32 cccr = p4_config_unpack_cccr(config); + return !!(cccr & P4_CCCR_CASCADE); +} + +static inline int p4_ht_config_thread(u64 config) +{ + return !!(config & P4_CONFIG_HT); +} + +static inline u64 p4_set_ht_bit(u64 config) +{ + return config | P4_CONFIG_HT; +} + +static inline u64 p4_clear_ht_bit(u64 config) +{ + return config & ~P4_CONFIG_HT; +} + +static inline int p4_ht_active(void) +{ +#ifdef CONFIG_SMP + return smp_num_siblings > 1; +#endif + return 0; +} + +static inline int p4_ht_thread(int cpu) +{ +#ifdef CONFIG_SMP + if (smp_num_siblings == 2) + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); +#endif + return 0; +} + +static inline int p4_should_swap_ts(u64 config, int cpu) +{ + return p4_ht_config_thread(config) ^ p4_ht_thread(cpu); +} + +static inline u32 p4_default_cccr_conf(int cpu) +{ + /* + * Note that P4_CCCR_THREAD_ANY is "required" on + * non-HT machines (on HT machines we count TS events + * regardless the state of second logical processor + */ + u32 cccr = P4_CCCR_THREAD_ANY; + + if (!p4_ht_thread(cpu)) + cccr |= P4_CCCR_OVF_PMI_T0; + else + cccr |= P4_CCCR_OVF_PMI_T1; + + return cccr; +} + +static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) +{ + u32 escr = 0; + + if (!p4_ht_thread(cpu)) { + if (!exclude_os) + escr |= P4_EVNTSEL_T0_OS; + if (!exclude_usr) + escr |= P4_EVNTSEL_T0_USR; + } else { + if (!exclude_os) + escr |= P4_EVNTSEL_T1_OS; + if (!exclude_usr) + escr |= P4_EVNTSEL_T1_USR; + } + + return escr; +} + +/* + * Comments below the event represent ESCR restriction + * for this event and counter index per ESCR + * + * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early + * processor builds (family 0FH, models 01H-02H). These MSRs + * are not available on later versions, so that we don't use + * them completely + * + * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly + * working so that we should not use this CCCR and respective + * counter as result + */ +#define P4_TC_DELIVER_MODE P4_EVENT_PACK(0x01, 0x01) + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + +#define P4_BPU_FETCH_REQUEST P4_EVENT_PACK(0x03, 0x00) + /* + * MSR_P4_BPU_ESCR0: 0, 1 + * MSR_P4_BPU_ESCR1: 2, 3 + */ + +#define P4_ITLB_REFERENCE P4_EVENT_PACK(0x18, 0x03) + /* + * MSR_P4_ITLB_ESCR0: 0, 1 + * MSR_P4_ITLB_ESCR1: 2, 3 + */ + +#define P4_MEMORY_CANCEL P4_EVENT_PACK(0x02, 0x05) + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + +#define P4_MEMORY_COMPLETE P4_EVENT_PACK(0x08, 0x02) + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + +#define P4_LOAD_PORT_REPLAY P4_EVENT_PACK(0x04, 0x02) + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + +#define P4_STORE_PORT_REPLAY P4_EVENT_PACK(0x05, 0x02) + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + +#define P4_MOB_LOAD_REPLAY P4_EVENT_PACK(0x03, 0x02) + /* + * MSR_P4_MOB_ESCR0: 0, 1 + * MSR_P4_MOB_ESCR1: 2, 3 + */ + +#define P4_PAGE_WALK_TYPE P4_EVENT_PACK(0x01, 0x04) + /* + * MSR_P4_PMH_ESCR0: 0, 1 + * MSR_P4_PMH_ESCR1: 2, 3 + */ + +#define P4_BSQ_CACHE_REFERENCE P4_EVENT_PACK(0x0c, 0x07) + /* + * MSR_P4_BSU_ESCR0: 0, 1 + * MSR_P4_BSU_ESCR1: 2, 3 + */ + +#define P4_IOQ_ALLOCATION P4_EVENT_PACK(0x03, 0x06) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_IOQ_ACTIVE_ENTRIES P4_EVENT_PACK(0x1a, 0x06) + /* + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_FSB_DATA_ACTIVITY P4_EVENT_PACK(0x17, 0x06) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_BSQ_ALLOCATION P4_EVENT_PACK(0x05, 0x07) + /* + * MSR_P4_BSU_ESCR0: 0, 1 + */ + +#define P4_BSQ_ACTIVE_ENTRIES P4_EVENT_PACK(0x06, 0x07) + /* + * MSR_P4_BSU_ESCR1: 2, 3 + */ + +#define P4_SSE_INPUT_ASSIST P4_EVENT_PACK(0x34, 0x01) + /* + * MSR_P4_FIRM_ESCR: 8, 9 + * MSR_P4_FIRM_ESCR: 10, 11 + */ + +#define P4_PACKED_SP_UOP P4_EVENT_PACK(0x08, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_PACKED_DP_UOP P4_EVENT_PACK(0x0c, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_SCALAR_SP_UOP P4_EVENT_PACK(0x0a, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_SCALAR_DP_UOP P4_EVENT_PACK(0x0e, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_64BIT_MMX_UOP P4_EVENT_PACK(0x02, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_128BIT_MMX_UOP P4_EVENT_PACK(0x1a, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_X87_FP_UOP P4_EVENT_PACK(0x04, 0x01) + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + +#define P4_TC_MISC P4_EVENT_PACK(0x06, 0x01) + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + +#define P4_GLOBAL_POWER_EVENTS P4_EVENT_PACK(0x13, 0x06) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_TC_MS_XFER P4_EVENT_PACK(0x05, 0x00) + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + +#define P4_UOP_QUEUE_WRITES P4_EVENT_PACK(0x09, 0x00) + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + +#define P4_RETIRED_MISPRED_BRANCH_TYPE P4_EVENT_PACK(0x05, 0x02) + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR0: 6, 7 + */ + +#define P4_RETIRED_BRANCH_TYPE P4_EVENT_PACK(0x04, 0x02) + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR0: 6, 7 + */ + +#define P4_RESOURCE_STALL P4_EVENT_PACK(0x01, 0x01) + /* + * MSR_P4_ALF_ESCR0: 12, 13, 16 + * MSR_P4_ALF_ESCR1: 14, 15, 17 + */ + +#define P4_WC_BUFFER P4_EVENT_PACK(0x05, 0x05) + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + +#define P4_B2B_CYCLES P4_EVENT_PACK(0x16, 0x03) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_BNR P4_EVENT_PACK(0x08, 0x03) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_SNOOP P4_EVENT_PACK(0x06, 0x03) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_RESPONSE P4_EVENT_PACK(0x04, 0x03) + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + +#define P4_FRONT_END_EVENT P4_EVENT_PACK(0x08, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_EXECUTION_EVENT P4_EVENT_PACK(0x0c, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_REPLAY_EVENT P4_EVENT_PACK(0x09, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_INSTR_RETIRED P4_EVENT_PACK(0x02, 0x04) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_UOPS_RETIRED P4_EVENT_PACK(0x01, 0x04) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_UOP_TYPE P4_EVENT_PACK(0x02, 0x02) + /* + * MSR_P4_RAT_ESCR0: 12, 13, 16 + * MSR_P4_RAT_ESCR1: 14, 15, 17 + */ + +#define P4_BRANCH_RETIRED P4_EVENT_PACK(0x06, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_MISPRED_BRANCH_RETIRED P4_EVENT_PACK(0x03, 0x04) + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + +#define P4_X87_ASSIST P4_EVENT_PACK(0x03, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_MACHINE_CLEAR P4_EVENT_PACK(0x02, 0x05) + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + +#define P4_INSTR_COMPLETED P4_EVENT_PACK(0x07, 0x04) + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + +/* + * a caller should use P4_EVENT_ATTR helper to + * pick the attribute needed, for example + * + * P4_EVENT_ATTR(P4_TC_DELIVER_MODE, DD) + */ +enum P4_EVENTS_ATTR { + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DD, 0), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DB, 1), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DI, 2), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BD, 3), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BB, 4), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BI, 5), + P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, ID, 6), + + P4_MAKE_EVENT_ATTR(P4_BPU_FETCH_REQUEST, TCMISS, 0), + + P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, HIT, 0), + P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, MISS, 1), + P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, HIT_UK, 2), + + P4_MAKE_EVENT_ATTR(P4_MEMORY_CANCEL, ST_RB_FULL, 2), + P4_MAKE_EVENT_ATTR(P4_MEMORY_CANCEL, 64K_CONF, 3), + + P4_MAKE_EVENT_ATTR(P4_MEMORY_COMPLETE, LSC, 0), + P4_MAKE_EVENT_ATTR(P4_MEMORY_COMPLETE, SSC, 1), + + P4_MAKE_EVENT_ATTR(P4_LOAD_PORT_REPLAY, SPLIT_LD, 1), + + P4_MAKE_EVENT_ATTR(P4_STORE_PORT_REPLAY, SPLIT_ST, 1), + + P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, NO_STA, 1), + P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, NO_STD, 3), + P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, PARTIAL_DATA, 4), + P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, UNALGN_ADDR, 5), + + P4_MAKE_EVENT_ATTR(P4_PAGE_WALK_TYPE, DTMISS, 0), + P4_MAKE_EVENT_ATTR(P4_PAGE_WALK_TYPE, ITMISS, 1), + + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9), + P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10), + + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, DEFAULT, 0), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, ALL_READ, 5), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, ALL_WRITE, 6), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_UC, 7), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WC, 8), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WT, 9), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WP, 10), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WB, 11), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, OWN, 13), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, OTHER, 14), + P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, PREFETCH, 15), + + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, DEFAULT, 0), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, ALL_READ, 5), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_UC, 7), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WC, 8), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WT, 9), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WP, 10), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WB, 11), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, OWN, 13), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, OTHER, 14), + P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, PREFETCH, 15), + + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_DRV, 0), + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OWN, 1), + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OTHER, 2), + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_DRV, 3), + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_OWN, 4), + P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_OTHER, 5), + + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_TYPE0, 0), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_TYPE1, 1), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LEN0, 2), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LEN1, 3), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_IO_TYPE, 5), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_DEM_TYPE, 9), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_ORD_TYPE, 10), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE0, 11), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE1, 12), + P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE2, 13), + + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12), + P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13), + + P4_MAKE_EVENT_ATTR(P4_SSE_INPUT_ASSIST, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_PACKED_SP_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_PACKED_DP_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_SCALAR_SP_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_SCALAR_DP_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_64BIT_MMX_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_128BIT_MMX_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_X87_FP_UOP, ALL, 15), + + P4_MAKE_EVENT_ATTR(P4_TC_MISC, FLUSH, 4), + + P4_MAKE_EVENT_ATTR(P4_GLOBAL_POWER_EVENTS, RUNNING, 0), + + P4_MAKE_EVENT_ATTR(P4_TC_MS_XFER, CISC, 0), + + P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0), + P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1), + P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_ROM, 2), + + P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2), + P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3), + P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4), + + P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CALL, 2), + P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, RETURN, 3), + P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, INDIRECT, 4), + + P4_MAKE_EVENT_ATTR(P4_RESOURCE_STALL, SBFULL, 5), + + P4_MAKE_EVENT_ATTR(P4_WC_BUFFER, WCB_EVICTS, 0), + P4_MAKE_EVENT_ATTR(P4_WC_BUFFER, WCB_FULL_EVICTS, 1), + + P4_MAKE_EVENT_ATTR(P4_FRONT_END_EVENT, NBOGUS, 0), + P4_MAKE_EVENT_ATTR(P4_FRONT_END_EVENT, BOGUS, 1), + + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS0, 0), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS1, 1), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS2, 2), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS3, 3), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS0, 4), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS1, 5), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS2, 6), + P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS3, 7), + + P4_MAKE_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS, 0), + P4_MAKE_EVENT_ATTR(P4_REPLAY_EVENT, BOGUS, 1), + + P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSNTAG, 0), + P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSTAG, 1), + P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSNTAG, 2), + P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSTAG, 3), + + P4_MAKE_EVENT_ATTR(P4_UOPS_RETIRED, NBOGUS, 0), + P4_MAKE_EVENT_ATTR(P4_UOPS_RETIRED, BOGUS, 1), + + P4_MAKE_EVENT_ATTR(P4_UOP_TYPE, TAGLOADS, 1), + P4_MAKE_EVENT_ATTR(P4_UOP_TYPE, TAGSTORES, 2), + + P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMNP, 0), + P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMNM, 1), + P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMTP, 2), + P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMTM, 3), + + P4_MAKE_EVENT_ATTR(P4_MISPRED_BRANCH_RETIRED, NBOGUS, 0), + + P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, FPSU, 0), + P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, FPSO, 1), + P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, POAO, 2), + P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, POAU, 3), + P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, PREA, 4), + + P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, CLEAR, 0), + P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, MOCLEAR, 1), + P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, SMCLEAR, 2), + + P4_MAKE_EVENT_ATTR(P4_INSTR_COMPLETED, NBOGUS, 0), + P4_MAKE_EVENT_ATTR(P4_INSTR_COMPLETED, BOGUS, 1), +}; + +#endif /* PERF_EVENT_P4_H */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index e24f6374f9f..e6a3f5f81c9 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -190,6 +190,8 @@ struct x86_pmu { void (*enable_all)(void); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event_attr *attr, struct hw_perf_event *hwc); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; unsigned perfctr; u64 (*event_map)(int); @@ -415,6 +417,25 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return 0; } +static int x86_hw_config(struct perf_event_attr *attr, struct hw_perf_event *hwc) +{ + /* + * Generate PMC IRQs: + * (keep 'enabled' bit clear for now) + */ + hwc->config = ARCH_PERFMON_EVENTSEL_INT; + + /* + * Count user and OS events unless requested not to + */ + if (!attr->exclude_user) + hwc->config |= ARCH_PERFMON_EVENTSEL_USR; + if (!attr->exclude_kernel) + hwc->config |= ARCH_PERFMON_EVENTSEL_OS; + + return 0; +} + /* * Setup the hardware configuration for a given attr_type */ @@ -446,23 +467,13 @@ static int __hw_perf_event_init(struct perf_event *event) event->destroy = hw_perf_event_destroy; - /* - * Generate PMC IRQs: - * (keep 'enabled' bit clear for now) - */ - hwc->config = ARCH_PERFMON_EVENTSEL_INT; - hwc->idx = -1; hwc->last_cpu = -1; hwc->last_tag = ~0ULL; - /* - * Count user and OS events unless requested not to. - */ - if (!attr->exclude_user) - hwc->config |= ARCH_PERFMON_EVENTSEL_USR; - if (!attr->exclude_kernel) - hwc->config |= ARCH_PERFMON_EVENTSEL_OS; + /* Processor specifics */ + if (x86_pmu.hw_config(attr, hwc)) + return -EOPNOTSUPP; if (!hwc->sample_period) { hwc->sample_period = x86_pmu.max_period; @@ -517,7 +528,7 @@ static int __hw_perf_event_init(struct perf_event *event) return -EOPNOTSUPP; /* BTS is currently only allowed for user-mode. */ - if (hwc->config & ARCH_PERFMON_EVENTSEL_OS) + if (!attr->exclude_kernel) return -EOPNOTSUPP; } @@ -931,7 +942,7 @@ static int x86_pmu_enable(struct perf_event *event) if (n < 0) return n; - ret = x86_schedule_events(cpuc, n, assign); + ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) return ret; /* @@ -1263,7 +1274,7 @@ int hw_perf_group_sched_in(struct perf_event *leader, if (n0 < 0) return n0; - ret = x86_schedule_events(cpuc, n0, assign); + ret = x86_pmu.schedule_events(cpuc, n0, assign); if (ret) return ret; @@ -1313,6 +1324,7 @@ undo: #include "perf_event_amd.c" #include "perf_event_p6.c" +#include "perf_event_p4.c" #include "perf_event_intel_lbr.c" #include "perf_event_intel_ds.c" #include "perf_event_intel.c" @@ -1515,7 +1527,7 @@ static int validate_group(struct perf_event *event) fake_cpuc->n_events = n; - ret = x86_schedule_events(fake_cpuc, n, NULL); + ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); out_free: kfree(fake_cpuc); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 573458f1caf..358a8e3d05f 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -363,6 +363,8 @@ static __initconst struct x86_pmu amd_pmu = { .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = x86_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 971dc6e7d54..044b8436b19 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -749,6 +749,8 @@ static __initconst struct x86_pmu core_pmu = { .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, .disable = x86_pmu_disable_event, + .hw_config = x86_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, @@ -786,6 +788,8 @@ static __initconst struct x86_pmu intel_pmu = { .enable_all = intel_pmu_enable_all, .enable = intel_pmu_enable_event, .disable = intel_pmu_disable_event, + .hw_config = x86_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, .event_map = intel_pmu_event_map, @@ -839,12 +843,13 @@ static __init int intel_pmu_init(void) int version; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { - /* check for P6 processor family */ - if (boot_cpu_data.x86 == 6) { - return p6_pmu_init(); - } else { + switch (boot_cpu_data.x86) { + case 0x6: + return p6_pmu_init(); + case 0xf: + return p4_pmu_init(); + } return -ENODEV; - } } /* diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c new file mode 100644 index 00000000000..381f593e829 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -0,0 +1,607 @@ +/* + * Netburst Perfomance Events (P4, old Xeon) + * + * Copyright (C) 2010 Parallels, Inc., Cyrill Gorcunov + * Copyright (C) 2010 Intel Corporation, Lin Ming + * + * For licencing details see kernel-base/COPYING + */ + +#ifdef CONFIG_CPU_SUP_INTEL + +#include + +/* + * array indices: 0,1 - HT threads, used with HT enabled cpu + */ +struct p4_event_template { + u32 opcode; /* ESCR event + CCCR selector */ + u64 config; /* packed predefined bits */ + int dep; /* upstream dependency event index */ + unsigned int emask; /* ESCR EventMask */ + unsigned int escr_msr[2]; /* ESCR MSR for this event */ + unsigned int cntr[2]; /* counter index (offset) */ +}; + +struct p4_pmu_res { + /* maps hw_conf::idx into template for ESCR sake */ + struct p4_event_template *tpl[ARCH_P4_MAX_CCCR]; +}; + +static DEFINE_PER_CPU(struct p4_pmu_res, p4_pmu_config); + +/* + * WARN: CCCR1 doesn't have a working enable bit so try to not + * use it if possible + * + * Also as only we start to support raw events we will need to + * append _all_ P4_EVENT_PACK'ed events here + */ +struct p4_event_template p4_templates[] = { + [0] = { + .opcode = P4_UOP_TYPE, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_UOP_TYPE, TAGLOADS) | + P4_EVENT_ATTR(P4_UOP_TYPE, TAGSTORES), + .escr_msr = { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 }, + .cntr = { 16, 17 }, + }, + [1] = { + .opcode = P4_GLOBAL_POWER_EVENTS, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_GLOBAL_POWER_EVENTS, RUNNING), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { 0, 2 }, + }, + [2] = { + .opcode = P4_INSTR_RETIRED, + .config = 0, + .dep = 0, /* needs front-end tagging */ + .emask = + P4_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSNTAG) | + P4_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSTAG) | + P4_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSNTAG) | + P4_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSTAG), + .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .cntr = { 12, 14 }, + }, + [3] = { + .opcode = P4_BSQ_CACHE_REFERENCE, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITS) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITE) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITM) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITS) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITE) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITM), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 }, + .cntr = { 0, 2 }, + }, + [4] = { + .opcode = P4_BSQ_CACHE_REFERENCE, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_MISS) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_MISS) | + P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, WR_2ndL_MISS), + .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 }, + .cntr = { 0, 3 }, + }, + [5] = { + .opcode = P4_RETIRED_BRANCH_TYPE, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CONDITIONAL) | + P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CALL) | + P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, RETURN) | + P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, INDIRECT), + .escr_msr = { MSR_P4_TBPU_ESCR0, MSR_P4_TBPU_ESCR1 }, + .cntr = { 4, 6 }, + }, + [6] = { + .opcode = P4_MISPRED_BRANCH_RETIRED, + .config = 0, + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_MISPRED_BRANCH_RETIRED, NBOGUS), + .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .cntr = { 12, 14 }, + }, + [7] = { + .opcode = P4_FSB_DATA_ACTIVITY, + .config = p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE), + .dep = -1, + .emask = + P4_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_DRV) | + P4_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OWN), + .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .cntr = { 0, 2 }, + }, +}; + +static struct p4_event_template *p4_event_map[PERF_COUNT_HW_MAX] = { + /* non-halted CPU clocks */ + [PERF_COUNT_HW_CPU_CYCLES] = &p4_templates[1], + + /* retired instructions: dep on tagging the FSB */ + [PERF_COUNT_HW_INSTRUCTIONS] = &p4_templates[2], + + /* cache hits */ + [PERF_COUNT_HW_CACHE_REFERENCES] = &p4_templates[3], + + /* cache misses */ + [PERF_COUNT_HW_CACHE_MISSES] = &p4_templates[4], + + /* branch instructions retired */ + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = &p4_templates[5], + + /* mispredicted branches retired */ + [PERF_COUNT_HW_BRANCH_MISSES] = &p4_templates[6], + + /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN): */ + [PERF_COUNT_HW_BUS_CYCLES] = &p4_templates[7], +}; + +static u64 p4_pmu_event_map(int hw_event) +{ + struct p4_event_template *tpl; + u64 config; + + if (hw_event > ARRAY_SIZE(p4_event_map)) { + printk_once(KERN_ERR "PMU: Incorrect event index\n"); + return 0; + } + tpl = p4_event_map[hw_event]; + + /* + * fill config up according to + * a predefined event template + */ + config = tpl->config; + config |= p4_config_pack_escr(P4_EVENT_UNPACK_EVENT(tpl->opcode) << P4_EVNTSEL_EVENT_SHIFT); + config |= p4_config_pack_escr(tpl->emask << P4_EVNTSEL_EVENTMASK_SHIFT); + config |= p4_config_pack_cccr(P4_EVENT_UNPACK_SELECTOR(tpl->opcode) << P4_CCCR_ESCR_SELECT_SHIFT); + + /* on HT machine we need a special bit */ + if (p4_ht_active() && p4_ht_thread(raw_smp_processor_id())) + config = p4_set_ht_bit(config); + + return config; +} + +/* + * Note that we still have 5 events (from global events SDM list) + * intersected in opcode+emask bits so we will need another + * scheme there do distinguish templates. + */ +static inline int p4_pmu_emask_match(unsigned int dst, unsigned int src) +{ + return dst & src; +} + +static struct p4_event_template *p4_pmu_template_lookup(u64 config) +{ + u32 opcode = p4_config_unpack_opcode(config); + unsigned int emask = p4_config_unpack_emask(config); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(p4_templates); i++) { + if (opcode == p4_templates[i].opcode && + p4_pmu_emask_match(emask, p4_templates[i].emask)) + return &p4_templates[i]; + } + + return NULL; +} + +/* + * We don't control raw events so it's up to the caller + * to pass sane values (and we don't count the thread number + * on HT machine but allow HT-compatible specifics to be + * passed on) + */ +static u64 p4_pmu_raw_event(u64 hw_event) +{ + return hw_event & + (p4_config_pack_escr(P4_EVNTSEL_MASK_HT) | + p4_config_pack_cccr(P4_CCCR_MASK_HT)); +} + +static int p4_hw_config(struct perf_event_attr *attr, struct hw_perf_event *hwc) +{ + int cpu = raw_smp_processor_id(); + + /* + * the reason we use cpu that early is that: if we get scheduled + * first time on the same cpu -- we will not need swap thread + * specific flags in config (and will save some cpu cycles) + */ + + /* CCCR by default */ + hwc->config = p4_config_pack_cccr(p4_default_cccr_conf(cpu)); + + /* Count user and OS events unless not requested to */ + hwc->config |= p4_config_pack_escr(p4_default_escr_conf(cpu, attr->exclude_kernel, + attr->exclude_user)); + return 0; +} + +static inline void p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) +{ + unsigned long dummy; + + rdmsrl(hwc->config_base + hwc->idx, dummy); + if (dummy & P4_CCCR_OVF) { + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + ((u64)dummy) & ~P4_CCCR_OVF); + } +} + +static inline void p4_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + /* + * If event gets disabled while counter is in overflowed + * state we need to clear P4_CCCR_OVF, otherwise interrupt get + * asserted again and again + */ + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (u64)(p4_config_unpack_cccr(hwc->config)) & + ~P4_CCCR_ENABLE & ~P4_CCCR_OVF); +} + +static void p4_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_events; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_disable_event(event); + } +} + +static void p4_pmu_enable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int thread = p4_ht_config_thread(hwc->config); + u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config)); + u64 escr_base; + struct p4_event_template *tpl; + struct p4_pmu_res *c; + + /* + * some preparation work from per-cpu private fields + * since we need to find out which ESCR to use + */ + c = &__get_cpu_var(p4_pmu_config); + tpl = c->tpl[hwc->idx]; + if (!tpl) { + pr_crit("%s: Wrong index: %d\n", __func__, hwc->idx); + return; + } + escr_base = (u64)tpl->escr_msr[thread]; + + /* + * - we dont support cascaded counters yet + * - and counter 1 is broken (erratum) + */ + WARN_ON_ONCE(p4_is_event_cascaded(hwc->config)); + WARN_ON_ONCE(hwc->idx == 1); + + (void)checking_wrmsrl(escr_base, escr_conf); + (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (u64)(p4_config_unpack_cccr(hwc->config)) | P4_CCCR_ENABLE); +} + +static void p4_pmu_enable_all(void) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_events; idx++) { + struct perf_event *event = cpuc->events[idx]; + if (!test_bit(idx, cpuc->active_mask)) + continue; + p4_pmu_enable_event(event); + } +} + +static int p4_pmu_handle_irq(struct pt_regs *regs) +{ + struct perf_sample_data data; + struct cpu_hw_events *cpuc; + struct perf_event *event; + struct hw_perf_event *hwc; + int idx, handled = 0; + u64 val; + + data.addr = 0; + data.raw = NULL; + + cpuc = &__get_cpu_var(cpu_hw_events); + + for (idx = 0; idx < x86_pmu.num_events; idx++) { + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + event = cpuc->events[idx]; + hwc = &event->hw; + + WARN_ON_ONCE(hwc->idx != idx); + + /* + * FIXME: Redundant call, actually not needed + * but just to check if we're screwed + */ + p4_pmu_clear_cccr_ovf(hwc); + + val = x86_perf_event_update(event); + if (val & (1ULL << (x86_pmu.event_bits - 1))) + continue; + + /* + * event overflow + */ + handled = 1; + data.period = event->hw.last_period; + + if (!x86_perf_event_set_period(event)) + continue; + if (perf_event_overflow(event, 1, &data, regs)) + p4_pmu_disable_event(event); + } + + if (handled) { + /* p4 quirk: unmask it again */ + apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); + inc_irq_stat(apic_perf_irqs); + } + + return handled; +} + +/* + * swap thread specific fields according to a thread + * we are going to run on + */ +static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu) +{ + u32 escr, cccr; + + /* + * we either lucky and continue on same cpu or no HT support + */ + if (!p4_should_swap_ts(hwc->config, cpu)) + return; + + /* + * the event is migrated from an another logical + * cpu, so we need to swap thread specific flags + */ + + escr = p4_config_unpack_escr(hwc->config); + cccr = p4_config_unpack_cccr(hwc->config); + + if (p4_ht_thread(cpu)) { + cccr &= ~P4_CCCR_OVF_PMI_T0; + cccr |= P4_CCCR_OVF_PMI_T1; + if (escr & P4_EVNTSEL_T0_OS) { + escr &= ~P4_EVNTSEL_T0_OS; + escr |= P4_EVNTSEL_T1_OS; + } + if (escr & P4_EVNTSEL_T0_USR) { + escr &= ~P4_EVNTSEL_T0_USR; + escr |= P4_EVNTSEL_T1_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config |= P4_CONFIG_HT; + } else { + cccr &= ~P4_CCCR_OVF_PMI_T1; + cccr |= P4_CCCR_OVF_PMI_T0; + if (escr & P4_EVNTSEL_T1_OS) { + escr &= ~P4_EVNTSEL_T1_OS; + escr |= P4_EVNTSEL_T0_OS; + } + if (escr & P4_EVNTSEL_T1_USR) { + escr &= ~P4_EVNTSEL_T1_USR; + escr |= P4_EVNTSEL_T0_USR; + } + hwc->config = p4_config_pack_escr(escr); + hwc->config |= p4_config_pack_cccr(cccr); + hwc->config &= ~P4_CONFIG_HT; + } +} + +/* ESCRs are not sequential in memory so we need a map */ +static unsigned int p4_escr_map[ARCH_P4_TOTAL_ESCR] = { + MSR_P4_ALF_ESCR0, /* 0 */ + MSR_P4_ALF_ESCR1, /* 1 */ + MSR_P4_BPU_ESCR0, /* 2 */ + MSR_P4_BPU_ESCR1, /* 3 */ + MSR_P4_BSU_ESCR0, /* 4 */ + MSR_P4_BSU_ESCR1, /* 5 */ + MSR_P4_CRU_ESCR0, /* 6 */ + MSR_P4_CRU_ESCR1, /* 7 */ + MSR_P4_CRU_ESCR2, /* 8 */ + MSR_P4_CRU_ESCR3, /* 9 */ + MSR_P4_CRU_ESCR4, /* 10 */ + MSR_P4_CRU_ESCR5, /* 11 */ + MSR_P4_DAC_ESCR0, /* 12 */ + MSR_P4_DAC_ESCR1, /* 13 */ + MSR_P4_FIRM_ESCR0, /* 14 */ + MSR_P4_FIRM_ESCR1, /* 15 */ + MSR_P4_FLAME_ESCR0, /* 16 */ + MSR_P4_FLAME_ESCR1, /* 17 */ + MSR_P4_FSB_ESCR0, /* 18 */ + MSR_P4_FSB_ESCR1, /* 19 */ + MSR_P4_IQ_ESCR0, /* 20 */ + MSR_P4_IQ_ESCR1, /* 21 */ + MSR_P4_IS_ESCR0, /* 22 */ + MSR_P4_IS_ESCR1, /* 23 */ + MSR_P4_ITLB_ESCR0, /* 24 */ + MSR_P4_ITLB_ESCR1, /* 25 */ + MSR_P4_IX_ESCR0, /* 26 */ + MSR_P4_IX_ESCR1, /* 27 */ + MSR_P4_MOB_ESCR0, /* 28 */ + MSR_P4_MOB_ESCR1, /* 29 */ + MSR_P4_MS_ESCR0, /* 30 */ + MSR_P4_MS_ESCR1, /* 31 */ + MSR_P4_PMH_ESCR0, /* 32 */ + MSR_P4_PMH_ESCR1, /* 33 */ + MSR_P4_RAT_ESCR0, /* 34 */ + MSR_P4_RAT_ESCR1, /* 35 */ + MSR_P4_SAAT_ESCR0, /* 36 */ + MSR_P4_SAAT_ESCR1, /* 37 */ + MSR_P4_SSU_ESCR0, /* 38 */ + MSR_P4_SSU_ESCR1, /* 39 */ + MSR_P4_TBPU_ESCR0, /* 40 */ + MSR_P4_TBPU_ESCR1, /* 41 */ + MSR_P4_TC_ESCR0, /* 42 */ + MSR_P4_TC_ESCR1, /* 43 */ + MSR_P4_U2L_ESCR0, /* 44 */ + MSR_P4_U2L_ESCR1, /* 45 */ +}; + +static int p4_get_escr_idx(unsigned int addr) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(p4_escr_map); i++) { + if (addr == p4_escr_map[i]) + return i; + } + + return -1; +} + +static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +{ + unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long escr_mask[BITS_TO_LONGS(ARCH_P4_TOTAL_ESCR)]; + + struct hw_perf_event *hwc; + struct p4_event_template *tpl; + struct p4_pmu_res *c; + int cpu = raw_smp_processor_id(); + int escr_idx, thread, i, num; + + bitmap_zero(used_mask, X86_PMC_IDX_MAX); + bitmap_zero(escr_mask, ARCH_P4_TOTAL_ESCR); + + c = &__get_cpu_var(p4_pmu_config); + /* + * Firstly find out which resource events are going + * to use, if ESCR+CCCR tuple is already borrowed + * then get out of here + */ + for (i = 0, num = n; i < n; i++, num--) { + hwc = &cpuc->event_list[i]->hw; + tpl = p4_pmu_template_lookup(hwc->config); + if (!tpl) + goto done; + thread = p4_ht_thread(cpu); + escr_idx = p4_get_escr_idx(tpl->escr_msr[thread]); + if (escr_idx == -1) + goto done; + + /* already allocated and remains on the same cpu */ + if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) { + if (assign) + assign[i] = hwc->idx; + /* upstream dependent event */ + if (unlikely(tpl->dep != -1)) + printk_once(KERN_WARNING "PMU: Dep events are " + "not implemented yet\n"); + goto reserve; + } + + /* it may be already borrowed */ + if (test_bit(tpl->cntr[thread], used_mask) || + test_bit(escr_idx, escr_mask)) + goto done; + + /* + * ESCR+CCCR+COUNTERs are available to use lets swap + * thread specific bits, push assigned bits + * back and save template into per-cpu + * area (which will allow us to find out the ESCR + * to be used at moment of "enable event via real MSR") + */ + p4_pmu_swap_config_ts(hwc, cpu); + if (assign) { + assign[i] = tpl->cntr[thread]; + c->tpl[assign[i]] = tpl; + } +reserve: + set_bit(tpl->cntr[thread], used_mask); + set_bit(escr_idx, escr_mask); + } + +done: + return num ? -ENOSPC : 0; +} + +static __initconst struct x86_pmu p4_pmu = { + .name = "Netburst P4/Xeon", + .handle_irq = p4_pmu_handle_irq, + .disable_all = p4_pmu_disable_all, + .enable_all = p4_pmu_enable_all, + .enable = p4_pmu_enable_event, + .disable = p4_pmu_disable_event, + .eventsel = MSR_P4_BPU_CCCR0, + .perfctr = MSR_P4_BPU_PERFCTR0, + .event_map = p4_pmu_event_map, + .raw_event = p4_pmu_raw_event, + .max_events = ARRAY_SIZE(p4_event_map), + .get_event_constraints = x86_get_event_constraints, + /* + * IF HT disabled we may need to use all + * ARCH_P4_MAX_CCCR counters simulaneously + * though leave it restricted at moment assuming + * HT is on + */ + .num_events = ARCH_P4_MAX_CCCR, + .apic = 1, + .event_bits = 40, + .event_mask = (1ULL << 40) - 1, + .max_period = (1ULL << 39) - 1, + .hw_config = p4_hw_config, + .schedule_events = p4_pmu_schedule_events, +}; + +static __init int p4_pmu_init(void) +{ + unsigned int low, high; + + /* If we get stripped -- indexig fails */ + BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC); + + rdmsr(MSR_IA32_MISC_ENABLE, low, high); + if (!(low & (1 << 7))) { + pr_cont("unsupported Netburst CPU model %d ", + boot_cpu_data.x86_model); + return -ENODEV; + } + + pr_cont("Netburst events, "); + + x86_pmu = p4_pmu; + + return 0; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index a330485d14d..6ff4d01d880 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -109,6 +109,8 @@ static __initconst struct x86_pmu p6_pmu = { .enable_all = p6_pmu_enable_all, .enable = p6_pmu_enable_event, .disable = p6_pmu_disable_event, + .hw_config = x86_hw_config, + .schedule_events = x86_schedule_events, .eventsel = MSR_P6_EVNTSEL0, .perfctr = MSR_P6_PERFCTR0, .event_map = p6_pmu_event_map, -- cgit v1.2.3