diff options
author | Linus Torvalds | 2014-10-13 15:58:15 +0200 |
---|---|---|
committer | Linus Torvalds | 2014-10-13 15:58:15 +0200 |
commit | 9d9420f1209a1facea7110d549ac695f5aeeb503 (patch) | |
tree | 7956d1c40420644830decbbc90b8bbdfeb194364 /arch | |
parent | 6d5f0ebfc0be9cbfeaafdd9258d5fa24b7975a36 (diff) | |
parent | cc6cd47e7395bc05c5077009808b820633eb3f18 (diff) |
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar:
"Kernel side updates:
- Fix and enhance poll support (Jiri Olsa)
- Re-enable inheritance optimization (Jiri Olsa)
- Enhance Intel memory events support (Stephane Eranian)
- Refactor the Intel uncore driver to be more maintainable (Zheng
Yan)
- Enhance and fix Intel CPU and uncore PMU drivers (Peter Zijlstra,
Andi Kleen)
- [ plus various smaller fixes/cleanups ]
User visible tooling updates:
- Add +field argument support for --field option, so that one can add
fields to the default list of fields to show, ie now one can just
do:
perf report --fields +pid
And the pid will appear in addition to the default fields (Jiri
Olsa)
- Add +field argument support for --sort option (Jiri Olsa)
- Honour -w in the report tools (report, top), allowing to specify
the widths for the histogram entries columns (Namhyung Kim)
- Properly show submicrosecond times in 'perf kvm stat' (Christian
Borntraeger)
- Add beautifier for mremap flags param in 'trace' (Alex Snast)
- perf script: Allow callchains if any event samples them
- Don't truncate Intel style addresses in 'annotate' (Alex Converse)
- Allow profiling when kptr_restrict == 1 for non root users, kernel
samples will just remain unresolved (Andi Kleen)
- Allow configuring default options for callchains in config file
(Namhyung Kim)
- Support operations for shared futexes. (Davidlohr Bueso)
- "perf kvm stat report" improvements by Alexander Yarygin:
- Save pid string in opts.target.pid
- Enable the target.system_wide flag
- Unify the title bar output
- [ plus lots of other fixes and small improvements. ]
Tooling infrastructure changes:
- Refactor unit and scale function parameters for PMU parsing
routines (Matt Fleming)
- Improve DSO long names lookup with rbtree, resulting in great
speedup for workloads with lots of DSOs (Waiman Long)
- We were not handling POLLHUP notifications for event file
descriptors
Fix it by filtering entries in the events file descriptor array
after poll() returns, refcounting mmaps so that when the last fd
pointing to a perf mmap goes away we do the unmap (Arnaldo Carvalho
de Melo)
- Intel PT prep work, from Adrian Hunter, including:
- Let a user specify a PMU event without any config terms
- Add perf-with-kcore script
- Let default config be defined for a PMU
- Add perf_pmu__scan_file()
- Add a 'perf test' for tracking with sched_switch
- Add 'flush' callback to scripting API
- Use ring buffer consume method to look like other tools (Arnaldo
Carvalho de Melo)
- hists browser (used in top and report) refactorings, getting rid of
unused variables and reducing source code size by handling similar
cases in a fewer functions (Namhyung Kim).
- Replace thread unsafe strerror() with strerror_r() accross the
whole tools/perf/ tree (Masami Hiramatsu)
- Rename ordered_samples to ordered_events and allow setting a queue
size for ordering events (Jiri Olsa)
- [ plus lots of fixes, cleanups and other improvements ]"
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (198 commits)
perf/x86: Tone down kernel messages when the PMU check fails in a virtual environment
perf/x86/intel/uncore: Fix minor race in box set up
perf record: Fix error message for --filter option not coming after tracepoint
perf tools: Fix build breakage on arm64 targets
perf symbols: Improve DSO long names lookup speed with rbtree
perf symbols: Encapsulate dsos list head into struct dsos
perf bench futex: Sanitize -q option in requeue
perf bench futex: Support operations for shared futexes
perf trace: Fix mmap return address truncation to 32-bit
perf tools: Refactor unit and scale function parameters
perf tools: Fix line number in the config file error message
perf tools: Convert {record,top}.call-graph option to call-graph.record-mode
perf tools: Introduce perf_callchain_config()
perf callchain: Move some parser functions to callchain.c
perf tools: Move callchain config from record_opts to callchain_param
perf hists browser: Fix callchain print bug on TUI
perf tools: Use ACCESS_ONCE() instead of volatile cast
perf tools: Modify error code for when perf_session__new() fails
perf tools: Fix perf record as non root with kptr_restrict == 1
perf stat: Fix --per-core on multi socket systems
...
Diffstat (limited to 'arch')
-rw-r--r-- | arch/x86/include/asm/perf_event.h | 8 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/Makefile | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 14 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.h | 49 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 229 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_ds.c | 185 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_lbr.c | 8 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.c | 3175 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.h | 439 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c | 1221 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c | 636 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c | 2258 |
12 files changed, 4588 insertions, 3638 deletions
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8249df45d2f2..8dfc9fd094a3 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -51,6 +51,14 @@ ARCH_PERFMON_EVENTSEL_EDGE | \ ARCH_PERFMON_EVENTSEL_INV | \ ARCH_PERFMON_EVENTSEL_CMASK) +#define X86_ALL_EVENT_FLAGS \ + (ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK | \ + ARCH_PERFMON_EVENTSEL_ANY | \ + ARCH_PERFMON_EVENTSEL_PIN_CONTROL | \ + HSW_IN_TX | \ + HSW_IN_TX_CHECKPOINTED) #define AMD64_RAW_EVENT_MASK \ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 77dcab277710..01d5453b5502 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,9 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_uncore_snb.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o endif diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2879ecdaac43..16c73022306e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -243,7 +243,8 @@ static bool check_hw_exists(void) msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); - printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); + printk(boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR + "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); return false; } @@ -387,7 +388,7 @@ int x86_pmu_hw_config(struct perf_event *event) precise++; /* Support for IP fixup */ - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; } @@ -443,6 +444,12 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + if (event->attr.sample_period && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, event->attr.sample_period) > + event->attr.sample_period) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -980,6 +987,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; + if (x86_pmu.limit_period) + left = x86_pmu.limit_period(event, left); + per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8ade93111e03..d98a34d435d7 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -67,8 +67,10 @@ struct event_constraint { */ #define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */ #define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -252,18 +254,52 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) #define INTEL_PLD_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __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) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) -/* DataLA version of store sampling without extra enable bit. */ -#define INTEL_PST_HSW_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ +/* 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, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + +/* 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) +/* 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) + +/* 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|INTEL_ARCH_EVENT_MASK, \ + 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 @@ -409,6 +445,7 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; + unsigned (*limit_period)(struct perf_event *event, unsigned l); /* * sysfs attrs diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2502d0d9d246..3851def5057c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct event_constraint intel_bdw_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids }; +static __initconst const u64 hsw_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */ + [ C(RESULT_ACCESS) ] = 0x1b7, + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE| + L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x1b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE:ALL_RFO */ + /* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x1b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x108, /* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x6085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x185, /* ITLB_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static __initconst const u64 hsw_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */ + [ C(RESULT_ACCESS) ] = 0x2d5, + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE| + L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x3fbc0202d5ull, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x122, /* OFFCORE_RESPONSE:ALL_RFO */ + /* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x3fbc020122ull, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -1905,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return c; } +/* + * Broadwell: + * The INST_RETIRED.ALL period always needs to have lowest + * 6bits cleared (BDM57). It shall not use a period smaller + * than 100 (BDM11). We combine the two to enforce + * a min-period of 128. + */ +static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +{ + if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (left < 128) + left = 128; + left &= ~0x3fu; + } + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -2367,15 +2514,15 @@ __init int intel_pmu_init(void) * Install the hw-cache-events table: */ switch (boot_cpu_data.x86_model) { - case 14: /* 65 nm core solo/duo, "Yonah" */ + case 14: /* 65nm Core "Yonah" */ pr_cont("Core events, "); break; - case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + case 15: /* 65nm Core2 "Merom" */ x86_add_quirk(intel_clovertown_quirk); - case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 29: /* six-core 45 nm xeon "Dunnington" */ + case 22: /* 65nm Core2 "Merom-L" */ + case 23: /* 45nm Core2 "Penryn" */ + case 29: /* 45nm Core2 "Dunnington (MP) */ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2386,9 +2533,9 @@ __init int intel_pmu_init(void) pr_cont("Core2 events, "); break; - case 26: /* 45 nm nehalem, "Bloomfield" */ - case 30: /* 45 nm nehalem, "Lynnfield" */ - case 46: /* 45 nm nehalem-ex, "Beckton" */ + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2415,11 +2562,11 @@ __init int intel_pmu_init(void) pr_cont("Nehalem events, "); break; - case 28: /* Atom */ - case 38: /* Lincroft */ - case 39: /* Penwell */ - case 53: /* Cloverview */ - case 54: /* Cedarview */ + case 28: /* 45nm Atom "Pineview" */ + case 38: /* 45nm Atom "Lincroft" */ + case 39: /* 32nm Atom "Penwell" */ + case 53: /* 32nm Atom "Cloverview" */ + case 54: /* 32nm Atom "Cedarview" */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2430,8 +2577,8 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; - case 55: /* Atom 22nm "Silvermont" */ - case 77: /* Avoton "Silvermont" */ + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -2446,9 +2593,9 @@ __init int intel_pmu_init(void) pr_cont("Silvermont events, "); break; - case 37: /* 32 nm nehalem, "Clarkdale" */ - case 44: /* 32 nm nehalem, "Gulftown" */ - case 47: /* 32 nm Xeon E7 */ + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2474,8 +2621,8 @@ __init int intel_pmu_init(void) pr_cont("Westmere events, "); break; - case 42: /* SandyBridge */ - case 45: /* SandyBridge, "Romely-EP" */ + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ x86_add_quirk(intel_sandybridge_quirk); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2506,8 +2653,9 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; - case 58: /* IvyBridge */ - case 62: /* IvyBridge EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); /* dTLB-load-misses on IVB is different than SNB */ @@ -2539,20 +2687,19 @@ __init int intel_pmu_init(void) break; - case 60: /* Haswell Client */ - case 70: - case 71: - case 63: - case 69: + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ x86_pmu.late_ack = true; - memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_snb(); x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; - x86_pmu.extra_regs = intel_snb_extra_regs; + x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; @@ -2565,6 +2712,28 @@ __init int intel_pmu_init(void) pr_cont("Haswell events, "); break; + case 61: /* 14nm Broadwell Core-M */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_bdw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snbep_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.limit_period = bdw_limit_period; + pr_cont("Broadwell events, "); + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 696ade311ded..b1553d05a5cb 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status) return val; } -static u64 precise_store_data_hsw(struct perf_event *event, u64 status) +static u64 precise_datala_hsw(struct perf_event *event, u64 status) { union perf_mem_data_src dse; - u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK; - dse.val = 0; - dse.mem_op = PERF_MEM_OP_STORE; - dse.mem_lvl = PERF_MEM_LVL_NA; + dse.val = PERF_MEM_NA; + + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + dse.mem_op = PERF_MEM_OP_STORE; + else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW) + dse.mem_op = PERF_MEM_OP_LOAD; /* * L1 info only valid for following events: @@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status) * MEM_UOPS_RETIRED.SPLIT_STORES * MEM_UOPS_RETIRED.ALL_STORES */ - if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0) - return dse.mem_lvl; - - if (status & 1) - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; - else - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; - - /* Nothing else supported. Sorry. */ + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) { + if (status & 1) + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + else + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + } return dse.val; } @@ -569,28 +568,10 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { }; struct event_constraint intel_slm_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ - INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -626,68 +607,44 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */ - INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */ - INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */ - INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.* */ - /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ - INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), - /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ - INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), - INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ - INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ - /* MEM_UOPS_RETIRED.SPLIT_STORES */ - INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), - INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ - INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ - INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */ - INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */ - INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */ - /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */ - INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), - /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */ - INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), - /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */ - INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), - /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */ - INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), - INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */ - INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */ - + INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; @@ -864,6 +821,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { +#define PERF_X86_EVENT_PEBS_HSW_PREC \ + (PERF_X86_EVENT_PEBS_ST_HSW | \ + PERF_X86_EVENT_PEBS_LD_HSW | \ + PERF_X86_EVENT_PEBS_NA_HSW) /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. @@ -873,42 +834,40 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct perf_sample_data data; struct pt_regs regs; u64 sample_type; - int fll, fst; + int fll, fst, dsrc; + int fl = event->hw.flags; if (!intel_pmu_save_and_restart(event)) return; - fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; - fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST | - PERF_X86_EVENT_PEBS_ST_HSW); + sample_type = event->attr.sample_type; + dsrc = sample_type & PERF_SAMPLE_DATA_SRC; + + fll = fl & PERF_X86_EVENT_PEBS_LDLAT; + fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); perf_sample_data_init(&data, 0, event->hw.last_period); data.period = event->hw.last_period; - sample_type = event->attr.sample_type; /* - * if PEBS-LL or PreciseStore + * Use latency for weight (only avail with PEBS-LL) */ - if (fll || fst) { - /* - * Use latency for weight (only avail with PEBS-LL) - */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; - - /* - * data.data_src encodes the data source - */ - if (sample_type & PERF_SAMPLE_DATA_SRC) { - if (fll) - data.data_src.val = load_latency_data(pebs->dse); - else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) - data.data_src.val = - precise_store_data_hsw(event, pebs->dse); - else - data.data_src.val = precise_store_data(pebs->dse); - } + if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) + data.weight = pebs->lat; + + /* + * data.data_src encodes the data source + */ + if (dsrc) { + u64 val = PERF_MEM_NA; + if (fll) + val = load_latency_data(pebs->dse); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, pebs->dse); + else if (fst) + val = precise_store_data(pebs->dse); + data.data_src.val = val; } /* @@ -935,16 +894,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; - if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) data.addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll) + if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) data.weight = intel_hsw_weight(pebs); - if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION) + if (sample_type & PERF_SAMPLE_TRANSACTION) data.txn = intel_hsw_transaction(pebs); } @@ -1055,7 +1014,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -void intel_ds_init(void) +void __init intel_ds_init(void) { /* * No support for 32bit formats diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 9dd2459a4c73..4af10617de33 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -697,7 +697,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { }; /* core */ -void intel_pmu_lbr_init_core(void) +void __init intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -712,7 +712,7 @@ void intel_pmu_lbr_init_core(void) } /* nehalem/westmere */ -void intel_pmu_lbr_init_nhm(void) +void __init intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -733,7 +733,7 @@ void intel_pmu_lbr_init_nhm(void) } /* sandy bridge */ -void intel_pmu_lbr_init_snb(void) +void __init intel_pmu_lbr_init_snb(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -753,7 +753,7 @@ void intel_pmu_lbr_init_snb(void) } /* atom */ -void intel_pmu_lbr_init_atom(void) +void __init intel_pmu_lbr_init_atom(void) { /* * only models starting at stepping 10 seems diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0939f86f543d..9762dbd9f3f7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -1,83 +1,39 @@ #include "perf_event_intel_uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; -static struct intel_uncore_type **msr_uncores = empty_uncore; -static struct intel_uncore_type **pci_uncores = empty_uncore; -/* pci bus to socket mapping */ -static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct intel_uncore_type **uncore_msr_uncores = empty_uncore; +struct intel_uncore_type **uncore_pci_uncores = empty_uncore; -static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +static bool pcidrv_registered; +struct pci_driver *uncore_pci_driver; +/* pci bus to socket mapping */ +int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; static DEFINE_RAW_SPINLOCK(uncore_box_lock); - /* mask of cpus that collect uncore events */ static cpumask_t uncore_cpu_mask; /* constraint for the fixed counter */ -static struct event_constraint constraint_fixed = +static struct event_constraint uncore_constraint_fixed = EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); -static struct event_constraint constraint_empty = +struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); -#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ - ((1ULL << (n)) - 1))) - -DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); -DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); -DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); -DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); -DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); -DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); -DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); -DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); -DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); -DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); -DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); - -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); -static void uncore_pmu_event_read(struct perf_event *event); - -static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct intel_uncore_pmu, pmu); } -static struct intel_uncore_box * -uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { struct intel_uncore_box *box; @@ -86,6 +42,9 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) return box; raw_spin_lock(&uncore_box_lock); + /* Recheck in lock to handle races. */ + if (*per_cpu_ptr(pmu->box, cpu)) + goto out; list_for_each_entry(box, &pmu->box_list, list) { if (box->phys_id == topology_physical_package_id(cpu)) { atomic_inc(&box->refcnt); @@ -93,12 +52,13 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) break; } } +out: raw_spin_unlock(&uncore_box_lock); return *per_cpu_ptr(pmu->box, cpu); } -static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) { /* * perf core schedules event on the basis of cpu, uncore events are @@ -107,7 +67,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } -static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { u64 count; @@ -119,7 +79,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve /* * generic get constraint function for shared match/mask registers. */ -static struct event_constraint * +struct event_constraint * uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; @@ -154,10 +114,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) return NULL; } - return &constraint_empty; + return &uncore_constraint_empty; } -static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; @@ -178,7 +138,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even reg1->alloc = 0; } -static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) { struct intel_uncore_extra_reg *er; unsigned long flags; @@ -193,2936 +153,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) return config; } -/* Sandy Bridge-EP uncore support */ -static struct intel_uncore_type snbep_uncore_cbox; -static struct intel_uncore_type snbep_uncore_pcu; - -static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config |= SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config); -} - -static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); - pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); - - return count; -} - -static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); -} - -static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config |= SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) - wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - -static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - - if (msr) - wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); -} - -static struct attribute *snbep_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *snbep_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *snbep_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_nid.attr, - &format_attr_filter_state.attr, - &format_attr_filter_opc.attr, - NULL, -}; - -static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *snbep_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct uncore_event_desc snbep_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), - INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc snbep_uncore_qpi_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), - INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), - { /* end: all zeroes */ }, -}; - -static struct attribute_group snbep_uncore_format_group = { - .name = "format", - .attrs = snbep_uncore_formats_attr, -}; - -static struct attribute_group snbep_uncore_ubox_format_group = { - .name = "format", - .attrs = snbep_uncore_ubox_formats_attr, -}; - -static struct attribute_group snbep_uncore_cbox_format_group = { - .name = "format", - .attrs = snbep_uncore_cbox_formats_attr, -}; - -static struct attribute_group snbep_uncore_pcu_format_group = { - .name = "format", - .attrs = snbep_uncore_pcu_formats_attr, -}; - -static struct attribute_group snbep_uncore_qpi_format_group = { - .name = "format", - .attrs = snbep_uncore_qpi_formats_attr, -}; - -#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops snbep_uncore_msr_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_pci_init_box, \ - .disable_box = snbep_uncore_pci_disable_box, \ - .enable_box = snbep_uncore_pci_enable_box, \ - .disable_event = snbep_uncore_pci_disable_event, \ - .read_counter = snbep_uncore_pci_read_counter - -static struct intel_uncore_ops snbep_uncore_pci_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_uncore_pci_enable_event, \ -}; - -static struct event_constraint snbep_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x01, 0x1), - UNCORE_EVENT_CONSTRAINT(0x02, 0x3), - UNCORE_EVENT_CONSTRAINT(0x04, 0x3), - UNCORE_EVENT_CONSTRAINT(0x05, 0x3), - UNCORE_EVENT_CONSTRAINT(0x07, 0x3), - UNCORE_EVENT_CONSTRAINT(0x09, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x1), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x3), - UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), - EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x35, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x1), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r2pcie_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x1), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r3qpi_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x1), - UNCORE_EVENT_CONSTRAINT(0x20, 0x3), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x22, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x28, 0x3), - UNCORE_EVENT_CONSTRAINT(0x29, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), - UNCORE_EVENT_CONSTRAINT(0x30, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x3), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snbep_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &snbep_uncore_msr_ops, - .format_group = &snbep_uncore_ubox_format_group, -}; - -static struct extra_reg snbep_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), - EVENT_EXTRA_END -}; - -static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i; - - if (uncore_box_is_fake(box)) - return; - - for (i = 0; i < 5; i++) { - if (reg1->alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - reg1->alloc = 0; -} - -static struct event_constraint * -__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, - u64 (*cbox_filter_mask)(int fields)) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i, alloc = 0; - unsigned long flags; - u64 mask; - - if (reg1->idx == EXTRA_REG_NONE) - return NULL; - - raw_spin_lock_irqsave(&er->lock, flags); - for (i = 0; i < 5; i++) { - if (!(reg1->idx & (0x1 << i))) - continue; - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - continue; - - mask = cbox_filter_mask(0x1 << i); - if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || - !((reg1->config ^ er->config) & mask)) { - atomic_add(1 << (i * 6), &er->ref); - er->config &= ~mask; - er->config |= reg1->config & mask; - alloc |= (0x1 << i); - } else { - break; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - if (i < 5) - goto fail; - - if (!uncore_box_is_fake(box)) - reg1->alloc |= alloc; - - return NULL; -fail: - for (; i >= 0; i--) { - if (alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - return &constraint_empty; -} - -static u64 snbep_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x4) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); -} - -static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_cbox_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_cbox_hw_config, - .get_constraint = snbep_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &snbep_uncore_cbox_ops, - .format_group = &snbep_uncore_cbox_format_group, -}; - -static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 config = reg1->config; - - if (new_idx > reg1->idx) - config <<= 8 * (new_idx - reg1->idx); - else - config >>= 8 * (reg1->idx - new_idx); - - if (modify) { - hwc->config += new_idx - reg1->idx; - reg1->config = config; - reg1->idx = new_idx; - } - return config; -} - -static struct event_constraint * -snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - unsigned long flags; - int idx = reg1->idx; - u64 mask, config1 = reg1->config; - bool ok = false; - - if (reg1->idx == EXTRA_REG_NONE || - (!uncore_box_is_fake(box) && reg1->alloc)) - return NULL; -again: - mask = 0xffULL << (idx * 8); - raw_spin_lock_irqsave(&er->lock, flags); - if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || - !((config1 ^ er->config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - idx = (idx + 1) % 4; - if (idx != reg1->idx) { - config1 = snbep_pcu_alter_er(event, idx, false); - goto again; - } - return &constraint_empty; - } - - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx) - snbep_pcu_alter_er(event, idx, true); - reg1->alloc = 1; - } - return NULL; -} - -static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - atomic_sub(1 << (reg1->idx * 8), &er->ref); - reg1->alloc = 0; -} - -static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; - - if (ev_sel >= 0xb && ev_sel <= 0xe) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->idx = ev_sel - 0xb; - reg1->config = event->attr.config1 & (0xff << reg1->idx); - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_pcu_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_pcu_ops, - .format_group = &snbep_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *snbep_msr_uncores[] = { - &snbep_uncore_ubox, - &snbep_uncore_cbox, - &snbep_uncore_pcu, - NULL, -}; - -enum { - SNBEP_PCI_QPI_PORT0_FILTER, - SNBEP_PCI_QPI_PORT1_FILTER, -}; - -static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { - reg1->idx = 0; - reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; - reg1->config = event->attr.config1; - reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; - reg2->config = event->attr.config2; - } - return 0; -} - -static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; - WARN_ON_ONCE(!filter_pdev); - if (filter_pdev) { - pci_write_config_dword(filter_pdev, reg1->reg, - (u32)reg1->config); - pci_write_config_dword(filter_pdev, reg1->reg + 4, - (u32)(reg1->config >> 32)); - pci_write_config_dword(filter_pdev, reg2->reg, - (u32)reg2->config); - pci_write_config_dword(filter_pdev, reg2->reg + 4, - (u32)(reg2->config >> 32)); - } - } - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops snbep_uncore_qpi_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_qpi_enable_event, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -#define SNBEP_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &snbep_uncore_pci_ops, \ - .format_group = &snbep_uncore_format_group - -static struct intel_uncore_type snbep_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 4, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - .event_descs = snbep_uncore_imc_events, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_qpi_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, -}; - - -static struct intel_uncore_type snbep_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - SNBEP_PCI_UNCORE_HA, - SNBEP_PCI_UNCORE_IMC, - SNBEP_PCI_UNCORE_QPI, - SNBEP_PCI_UNCORE_R2PCIE, - SNBEP_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *snbep_pci_uncores[] = { - [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, - [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, - [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, - [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, - [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id snbep_uncore_pci_ids[] = { - { /* Home Agent */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), - }, - { /* MC Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), - }, - { /* MC Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), - }, - { /* MC Channel 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), - }, - { /* MC Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), - }, - { /* QPI Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), - }, - { /* QPI Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver snbep_uncore_pci_driver = { - .name = "snbep_uncore", - .id_table = snbep_uncore_pci_ids, -}; - -/* - * build pci bus to socket mapping - */ -static int snbep_pci2phy_map_init(int devid) -{ - struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid; - int err = 0; - u32 config = 0; - - while (1) { - /* find the UBOX device */ - ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); - if (!ubox_dev) - break; - bus = ubox_dev->bus->number; - /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, 0x40, &config); - if (err) - break; - nodeid = config; - /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, 0x54, &config); - if (err) - break; - /* - * every three bits in the Node ID mapping register maps - * to a particular node. - */ - for (i = 0; i < 8; i++) { - if (nodeid == ((config >> (3 * i)) & 0x7)) { - pcibus_to_physid[bus] = i; - break; - } - } - } - - if (!err) { - /* - * For PCI bus with no UBOX device, find the next bus - * that has UBOX device and use its mapping. - */ - i = -1; - for (bus = 255; bus >= 0; bus--) { - if (pcibus_to_physid[bus] >= 0) - i = pcibus_to_physid[bus]; - else - pcibus_to_physid[bus] = i; - } - } - - if (ubox_dev) - pci_dev_put(ubox_dev); - - return err ? pcibios_err_to_errno(err) : 0; -} -/* end of Sandy Bridge-EP uncore support */ - -/* IvyTown uncore support */ -static void ivt_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - if (msr) - wrmsrl(msr, IVT_PMON_BOX_CTL_INT); -} - -static void ivt_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT); -} - -#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = ivt_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops ivt_uncore_msr_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -static struct intel_uncore_ops ivt_uncore_pci_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, -}; - -#define IVT_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = IVT_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &ivt_uncore_pci_ops, \ - .format_group = &ivt_uncore_format_group - -static struct attribute *ivt_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *ivt_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *ivt_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_link.attr, - &format_attr_filter_state2.attr, - &format_attr_filter_nid2.attr, - &format_attr_filter_opc2.attr, - NULL, -}; - -static struct attribute *ivt_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *ivt_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct attribute_group ivt_uncore_format_group = { - .name = "format", - .attrs = ivt_uncore_formats_attr, -}; - -static struct attribute_group ivt_uncore_ubox_format_group = { - .name = "format", - .attrs = ivt_uncore_ubox_formats_attr, -}; - -static struct attribute_group ivt_uncore_cbox_format_group = { - .name = "format", - .attrs = ivt_uncore_cbox_formats_attr, -}; - -static struct attribute_group ivt_uncore_pcu_format_group = { - .name = "format", - .attrs = ivt_uncore_pcu_formats_attr, -}; - -static struct attribute_group ivt_uncore_qpi_format_group = { - .name = "format", - .attrs = ivt_uncore_qpi_formats_attr, -}; - -static struct intel_uncore_type ivt_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &ivt_uncore_msr_ops, - .format_group = &ivt_uncore_ubox_format_group, -}; - -static struct extra_reg ivt_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), - - SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), - EVENT_EXTRA_END -}; - -static u64 ivt_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK; - if (fields & 0x4) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x10) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask); -} - -static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - u64 filter = uncore_shared_reg_config(box, 0); - wrmsrl(reg1->reg, filter & 0xffffffff); - wrmsrl(reg1->reg + 6, filter >> 32); - } - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops ivt_uncore_cbox_ops = { - .init_box = ivt_uncore_msr_init_box, - .disable_box = snbep_uncore_msr_disable_box, - .enable_box = snbep_uncore_msr_enable_box, - .disable_event = snbep_uncore_msr_disable_event, - .enable_event = ivt_cbox_enable_event, - .read_counter = uncore_msr_read_counter, - .hw_config = ivt_cbox_hw_config, - .get_constraint = ivt_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 15, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &ivt_uncore_cbox_ops, - .format_group = &ivt_uncore_cbox_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_pcu_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_pcu_ops, - .format_group = &ivt_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *ivt_msr_uncores[] = { - &ivt_uncore_ubox, - &ivt_uncore_cbox, - &ivt_uncore_pcu, - NULL, -}; - -static struct intel_uncore_type ivt_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -/* registers in IRP boxes are not properly aligned */ -static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; -static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; - -static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], - hwc->config | SNBEP_PMON_CTL_EN); -} - -static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config); -} - -static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count); - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); - - return count; -} - -static struct intel_uncore_ops ivt_uncore_irp_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = ivt_uncore_irp_disable_event, - .enable_event = ivt_uncore_irp_enable_event, - .read_counter = ivt_uncore_irp_read_counter, -}; - -static struct intel_uncore_type ivt_uncore_irp = { - .name = "irp", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_mask = IVT_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &ivt_uncore_irp_ops, - .format_group = &ivt_uncore_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_qpi_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_qpi_enable_event, - .read_counter = snbep_uncore_pci_read_counter, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 3, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_qpi_ops, - .format_group = &ivt_uncore_qpi_format_group, -}; - -static struct intel_uncore_type ivt_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - IVT_PCI_UNCORE_HA, - IVT_PCI_UNCORE_IMC, - IVT_PCI_UNCORE_IRP, - IVT_PCI_UNCORE_QPI, - IVT_PCI_UNCORE_R2PCIE, - IVT_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *ivt_pci_uncores[] = { - [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, - [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, - [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp, - [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, - [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, - [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id ivt_uncore_pci_ids[] = { - { /* Home Agent 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), - }, - { /* Home Agent 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), - }, - { /* MC0 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), - }, - { /* MC0 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), - }, - { /* MC0 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), - }, - { /* MC0 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), - }, - { /* MC1 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), - }, - { /* MC1 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), - }, - { /* MC1 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), - }, - { /* MC1 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), - }, - { /* IRP */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0), - }, - { /* QPI0 Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), - }, - { /* QPI0 Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), - }, - { /* QPI1 Port 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), - }, - { /* R3QPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver ivt_uncore_pci_driver = { - .name = "ivt_uncore", - .id_table = ivt_uncore_pci_ids, -}; -/* end of IvyTown uncore support */ - -/* Sandy Bridge uncore support */ -static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); -} - -static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void snb_uncore_msr_init_box(struct intel_uncore_box *box) -{ - if (box->pmu->pmu_idx == 0) { - wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, - SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); - } -} - -static struct uncore_event_desc snb_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - { /* end: all zeroes */ }, -}; - -static struct attribute *snb_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask5.attr, - NULL, -}; - -static struct attribute_group snb_uncore_format_group = { - .name = "format", - .attrs = snb_uncore_formats_attr, -}; - -static struct intel_uncore_ops snb_uncore_msr_ops = { - .init_box = snb_uncore_msr_init_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = snb_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct event_constraint snb_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x80, 0x1), - UNCORE_EVENT_CONSTRAINT(0x83, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snb_uncore_cbox = { - .name = "cbox", - .num_counters = 2, - .num_boxes = 4, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, - .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, - .fixed_ctr = SNB_UNC_FIXED_CTR, - .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, - .single_fixed = 1, - .event_mask = SNB_UNC_RAW_EVENT_MASK, - .msr_offset = SNB_UNC_CBO_MSR_OFFSET, - .constraints = snb_uncore_cbox_constraints, - .ops = &snb_uncore_msr_ops, - .format_group = &snb_uncore_format_group, - .event_descs = snb_uncore_events, -}; - -static struct intel_uncore_type *snb_msr_uncores[] = { - &snb_uncore_cbox, - NULL, -}; - -enum { - SNB_PCI_UNCORE_IMC, -}; - -static struct uncore_event_desc snb_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), - INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), - - INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), - INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), - - { /* end: all zeroes */ }, -}; - -#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff -#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 - -/* page size multiple covering all config regs */ -#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 - -#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 -#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 -#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE - -static struct attribute *snb_uncore_imc_formats_attr[] = { - &format_attr_event.attr, - NULL, -}; - -static struct attribute_group snb_uncore_imc_format_group = { - .name = "format", - .attrs = snb_uncore_imc_formats_attr, -}; - -static void snb_uncore_imc_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; - resource_size_t addr; - u32 pci_dword; - - pci_read_config_dword(pdev, where, &pci_dword); - addr = pci_dword; - -#ifdef CONFIG_PHYS_ADDR_T_64BIT - pci_read_config_dword(pdev, where + 4, &pci_dword); - addr |= ((resource_size_t)pci_dword << 32); -#endif - - addr &= ~(PAGE_SIZE - 1); - - box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); - box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; -} - -static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); -} - -/* - * custom event_init() function because we define our own fixed, free - * running counters, so we do not want to conflict with generic uncore - * logic. Also simplifies processing - */ -static int snb_uncore_imc_event_init(struct perf_event *event) -{ - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - struct hw_perf_event *hwc = &event->hw; - u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; - int idx, base; - - if (event->attr.type != event->pmu->type) - return -ENOENT; - - pmu = uncore_event_to_pmu(event); - /* no device found for this pmu */ - if (pmu->func_id < 0) - return -ENOENT; - - /* Sampling not supported yet */ - if (hwc->sample_period) - return -EINVAL; - - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest || - event->attr.sample_period) /* no sampling */ - return -EINVAL; - - /* - * Place all uncore events for a particular physical package - * onto a single cpu - */ - if (event->cpu < 0) - return -EINVAL; - - /* check only supported bits are set */ - if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) - return -EINVAL; - - box = uncore_pmu_to_box(pmu, event->cpu); - if (!box || box->cpu < 0) - return -EINVAL; - - event->cpu = box->cpu; - - event->hw.idx = -1; - event->hw.last_tag = ~0ULL; - event->hw.extra_reg.idx = EXTRA_REG_NONE; - event->hw.branch_reg.idx = EXTRA_REG_NONE; - /* - * check event is known (whitelist, determines counter) - */ - switch (cfg) { - case SNB_UNCORE_PCI_IMC_DATA_READS: - base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; - idx = UNCORE_PMC_IDX_FIXED; - break; - case SNB_UNCORE_PCI_IMC_DATA_WRITES: - base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; - idx = UNCORE_PMC_IDX_FIXED + 1; - break; - default: - return -EINVAL; - } - - /* must be done before validate_group */ - event->hw.event_base = base; - event->hw.config = cfg; - event->hw.idx = idx; - - /* no group validation needed, we have free running counters */ - - return 0; -} - -static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - return 0; -} - -static void snb_uncore_imc_event_start(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - u64 count; - - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) - return; - - event->hw.state = 0; - box->n_active++; - - list_add_tail(&event->active_entry, &box->active_list); - - count = snb_uncore_imc_read_counter(box, event); - local64_set(&event->hw.prev_count, count); - - if (box->n_active == 1) - uncore_pmu_start_hrtimer(box); -} - -static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!(hwc->state & PERF_HES_STOPPED)) { - box->n_active--; - - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - hwc->state |= PERF_HES_STOPPED; - - list_del(&event->active_entry); - - if (box->n_active == 0) - uncore_pmu_cancel_hrtimer(box); - } - - if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { - /* - * Drain the remaining delta count out of a event - * that we are disabling: - */ - uncore_perf_event_update(box, event); - hwc->state |= PERF_HES_UPTODATE; - } -} - -static int snb_uncore_imc_event_add(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!box) - return -ENODEV; - - hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - if (!(flags & PERF_EF_START)) - hwc->state |= PERF_HES_ARCH; - - snb_uncore_imc_event_start(event, 0); - - box->n_events++; - - return 0; -} - -static void snb_uncore_imc_event_del(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - int i; - - snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); - - for (i = 0; i < box->n_events; i++) { - if (event == box->event_list[i]) { - --box->n_events; - break; - } - } -} - -static int snb_pci2phy_map_init(int devid) -{ - struct pci_dev *dev = NULL; - int bus; - - dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); - if (!dev) - return -ENOTTY; - - bus = dev->bus->number; - - pcibus_to_physid[bus] = 0; - - pci_dev_put(dev); - - return 0; -} - -static struct pmu snb_uncore_imc_pmu = { - .task_ctx_nr = perf_invalid_context, - .event_init = snb_uncore_imc_event_init, - .add = snb_uncore_imc_event_add, - .del = snb_uncore_imc_event_del, - .start = snb_uncore_imc_event_start, - .stop = snb_uncore_imc_event_stop, - .read = uncore_pmu_event_read, -}; - -static struct intel_uncore_ops snb_uncore_imc_ops = { - .init_box = snb_uncore_imc_init_box, - .enable_box = snb_uncore_imc_enable_box, - .disable_box = snb_uncore_imc_disable_box, - .disable_event = snb_uncore_imc_disable_event, - .enable_event = snb_uncore_imc_enable_event, - .hw_config = snb_uncore_imc_hw_config, - .read_counter = snb_uncore_imc_read_counter, -}; - -static struct intel_uncore_type snb_uncore_imc = { - .name = "imc", - .num_counters = 2, - .num_boxes = 1, - .fixed_ctr_bits = 32, - .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, - .event_descs = snb_uncore_imc_events, - .format_group = &snb_uncore_imc_format_group, - .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, - .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, - .ops = &snb_uncore_imc_ops, - .pmu = &snb_uncore_imc_pmu, -}; - -static struct intel_uncore_type *snb_pci_uncores[] = { - [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, - NULL, -}; - -static const struct pci_device_id snb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id ivb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id hsw_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static struct pci_driver snb_uncore_pci_driver = { - .name = "snb_uncore", - .id_table = snb_uncore_pci_ids, -}; - -static struct pci_driver ivb_uncore_pci_driver = { - .name = "ivb_uncore", - .id_table = ivb_uncore_pci_ids, -}; - -static struct pci_driver hsw_uncore_pci_driver = { - .name = "hsw_uncore", - .id_table = hsw_uncore_pci_ids, -}; - -/* end of Sandy Bridge uncore support */ - -/* Nehalem uncore support */ -static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); -} - -static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); -} - -static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); -} - -static struct attribute *nhm_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask8.attr, - NULL, -}; - -static struct attribute_group nhm_uncore_format_group = { - .name = "format", - .attrs = nhm_uncore_formats_attr, -}; - -static struct uncore_event_desc nhm_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhm_uncore_msr_ops = { - .disable_box = nhm_uncore_msr_disable_box, - .enable_box = nhm_uncore_msr_enable_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = nhm_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct intel_uncore_type nhm_uncore = { - .name = "", - .num_counters = 8, - .num_boxes = 1, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .event_ctl = NHM_UNC_PERFEVTSEL0, - .perf_ctr = NHM_UNC_UNCORE_PMC0, - .fixed_ctr = NHM_UNC_FIXED_CTR, - .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, - .event_mask = NHM_UNC_RAW_EVENT_MASK, - .event_descs = nhm_uncore_events, - .ops = &nhm_uncore_msr_ops, - .format_group = &nhm_uncore_format_group, -}; - -static struct intel_uncore_type *nhm_msr_uncores[] = { - &nhm_uncore, - NULL, -}; -/* end of Nehalem uncore support */ - -/* Nehalem-EX uncore support */ -DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); -DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); -DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); - -static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) -{ - wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); -} - -static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config &= ~((1ULL << uncore_num_counters(box)) - 1); - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config |= (1ULL << uncore_num_counters(box)) - 1; - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx >= UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); - else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); - else - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -#define NHMEX_UNCORE_OPS_COMMON_INIT() \ - .init_box = nhmex_uncore_msr_init_box, \ - .disable_box = nhmex_uncore_msr_disable_box, \ - .enable_box = nhmex_uncore_msr_enable_box, \ - .disable_event = nhmex_uncore_msr_disable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops nhmex_uncore_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_uncore_msr_enable_event, -}; - -static struct attribute *nhmex_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_edge.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_ubox_format_group = { - .name = "format", - .attrs = nhmex_uncore_ubox_formats_attr, -}; - -static struct intel_uncore_type nhmex_uncore_ubox = { - .name = "ubox", - .num_counters = 1, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, - .perf_ctr = NHMEX_U_MSR_PMON_CTR, - .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_ubox_format_group -}; - -static struct attribute *nhmex_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_cbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_cbox_formats_attr, -}; - -/* msr offset for each instance of cbox */ -static unsigned nhmex_cbox_msr_offsets[] = { - 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, -}; - -static struct intel_uncore_type nhmex_uncore_cbox = { - .name = "cbox", - .num_counters = 6, - .num_boxes = 10, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, - .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, - .msr_offsets = nhmex_cbox_msr_offsets, - .pair_ctr_ctl = 1, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static struct uncore_event_desc nhmex_uncore_wbox_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_type nhmex_uncore_wbox = { - .name = "wbox", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_W_MSR_PMON_CNT0, - .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, - .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, - .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, - .pair_ctr_ctl = 1, - .event_descs = nhmex_uncore_wbox_events, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int ctr, ev_sel; - - ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> - NHMEX_B_PMON_CTR_SHIFT; - ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> - NHMEX_B_PMON_CTL_EV_SEL_SHIFT; - - /* events that do not use the match/mask registers */ - if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || - (ctr == 2 && ev_sel != 0x4) || ctr == 3) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_B0_MSR_MATCH; - else - reg1->reg = NHMEX_B1_MSR_MATCH; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, reg1->config); - wrmsrl(reg1->reg + 1, reg2->config); - } - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); -} - -/* - * The Bbox has 4 counters, but each counter monitors different events. - * Use bits 6-7 in the event config to select counter. - */ -static struct event_constraint nhmex_uncore_bbox_constraints[] = { - EVENT_CONSTRAINT(0 , 1, 0xc0), - EVENT_CONSTRAINT(0x40, 2, 0xc0), - EVENT_CONSTRAINT(0x80, 4, 0xc0), - EVENT_CONSTRAINT(0xc0, 8, 0xc0), - EVENT_CONSTRAINT_END, -}; - -static struct attribute *nhmex_uncore_bbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_counter.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_bbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_bbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_bbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_bbox_msr_enable_event, - .hw_config = nhmex_bbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_bbox = { - .name = "bbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_B0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, - .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_B_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .constraints = nhmex_uncore_bbox_constraints, - .ops = &nhmex_uncore_bbox_ops, - .format_group = &nhmex_uncore_bbox_format_group -}; - -static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - /* only TO_R_PROG_EV event uses the match/mask register */ - if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != - NHMEX_S_EVENT_TO_R_PROG_EV) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_S0_MSR_MM_CFG; - else - reg1->reg = NHMEX_S1_MSR_MM_CFG; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, 0); - wrmsrl(reg1->reg + 1, reg1->config); - wrmsrl(reg1->reg + 2, reg2->config); - wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); - } - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); -} - -static struct attribute *nhmex_uncore_sbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_sbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_sbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_sbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_sbox_msr_enable_event, - .hw_config = nhmex_sbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_sbox = { - .name = "sbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_S0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_S_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .ops = &nhmex_uncore_sbox_ops, - .format_group = &nhmex_uncore_sbox_format_group -}; - -enum { - EXTRA_REG_NHMEX_M_FILTER, - EXTRA_REG_NHMEX_M_DSP, - EXTRA_REG_NHMEX_M_ISS, - EXTRA_REG_NHMEX_M_MAP, - EXTRA_REG_NHMEX_M_MSC_THR, - EXTRA_REG_NHMEX_M_PGT, - EXTRA_REG_NHMEX_M_PLD, - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, -}; - -static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { - MBOX_INC_SEL_EXTAR_REG(0x0, DSP), - MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x9, ISS), - /* event 0xa uses two extra registers */ - MBOX_INC_SEL_EXTAR_REG(0xa, ISS), - MBOX_INC_SEL_EXTAR_REG(0xa, PLD), - MBOX_INC_SEL_EXTAR_REG(0xb, PLD), - /* events 0xd ~ 0x10 use the same extra register */ - MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x16, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), - EVENT_EXTRA_END -}; - -/* Nehalem-EX or Westmere-EX ? */ -static bool uncore_nhmex; - -static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - bool ret = false; - u64 mask; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (!atomic_read(&er->ref) || er->config == config) { - atomic_inc(&er->ref); - er->config = config; - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; - } - /* - * The ZDP_CTL_FVC MSR has 4 fields which are used to control - * events 0xd ~ 0x10. Besides these 4 fields, there are additional - * fields which are shared. - */ - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (WARN_ON_ONCE(idx >= 4)) - return false; - - /* mask of the shared fields */ - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - - raw_spin_lock_irqsave(&er->lock, flags); - /* add mask of the non-shared field if it's in use */ - if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { - if (uncore_nhmex) - mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - } - - if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | - NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | - WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - er->config &= ~mask; - er->config |= (config & mask); - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; -} - -static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - atomic_dec(&er->ref); - return; - } - - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - atomic_sub(1 << (idx * 8), &er->ref); -} - -static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); - u64 config = reg1->config; - - /* get the non-shared control bits and shift them */ - idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (uncore_nhmex) - config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - if (new_idx > orig_idx) { - idx = new_idx - orig_idx; - config <<= 3 * idx; - } else { - idx = orig_idx - new_idx; - config >>= 3 * idx; - } - - /* add the shared control bits back */ - if (uncore_nhmex) - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - else - config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - if (modify) { - /* adjust the main event selector */ - if (new_idx > orig_idx) - hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - else - hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - reg1->config = config; - reg1->idx = ~0xff | new_idx; - } - return config; -} - -static struct event_constraint * -nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int i, idx[2], alloc = 0; - u64 config1 = reg1->config; - - idx[0] = __BITS_VALUE(reg1->idx, 0, 8); - idx[1] = __BITS_VALUE(reg1->idx, 1, 8); -again: - for (i = 0; i < 2; i++) { - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - idx[i] = 0xff; - - if (idx[i] == 0xff) - continue; - - if (!nhmex_mbox_get_shared_reg(box, idx[i], - __BITS_VALUE(config1, i, 32))) - goto fail; - alloc |= (0x1 << i); - } - - /* for the match/mask registers */ - if (reg2->idx != EXTRA_REG_NONE && - (uncore_box_is_fake(box) || !reg2->alloc) && - !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) - goto fail; - - /* - * If it's a fake box -- as per validate_{group,event}() we - * shouldn't touch event state and we can avoid doing so - * since both will only call get_event_constraints() once - * on each event, this avoids the need for reg->alloc. - */ - if (!uncore_box_is_fake(box)) { - if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) - nhmex_mbox_alter_er(event, idx[0], true); - reg1->alloc |= alloc; - if (reg2->idx != EXTRA_REG_NONE) - reg2->alloc = 1; - } - return NULL; -fail: - if (idx[0] != 0xff && !(alloc & 0x1) && - idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - /* - * events 0xd ~ 0x10 are functional identical, but are - * controlled by different fields in the ZDP_CTL_FVC - * register. If we failed to take one field, try the - * rest 3 choices. - */ - BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); - idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - idx[0] = (idx[0] + 1) % 4; - idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { - config1 = nhmex_mbox_alter_er(event, idx[0], false); - goto again; - } - } - - if (alloc & 0x1) - nhmex_mbox_put_shared_reg(box, idx[0]); - if (alloc & 0x2) - nhmex_mbox_put_shared_reg(box, idx[1]); - return &constraint_empty; -} - -static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - - if (uncore_box_is_fake(box)) - return; - - if (reg1->alloc & 0x1) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); - if (reg1->alloc & 0x2) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); - reg1->alloc = 0; - - if (reg2->alloc) { - nhmex_mbox_put_shared_reg(box, reg2->idx); - reg2->alloc = 0; - } -} - -static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) -{ - if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return er->idx; - return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; -} - -static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_type *type = box->pmu->type; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - struct extra_reg *er; - unsigned msr; - int reg_idx = 0; - /* - * The mbox events may require 2 extra MSRs at the most. But only - * the lower 32 bits in these MSRs are significant, so we can use - * config1 to pass two MSRs' config. - */ - for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - if (event->attr.config1 & ~er->valid_mask) - return -EINVAL; - - msr = er->msr + type->msr_offset * box->pmu->pmu_idx; - if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) - return -EINVAL; - - /* always use the 32~63 bits to pass the PLD config */ - if (er->idx == EXTRA_REG_NHMEX_M_PLD) - reg_idx = 1; - else if (WARN_ON_ONCE(reg_idx > 0)) - return -EINVAL; - - reg1->idx &= ~(0xff << (reg_idx * 8)); - reg1->reg &= ~(0xffff << (reg_idx * 16)); - reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); - reg1->reg |= msr << (reg_idx * 16); - reg1->config = event->attr.config1; - reg_idx++; - } - /* - * The mbox only provides ability to perform address matching - * for the PLD events. - */ - if (reg_idx == 2) { - reg2->idx = EXTRA_REG_NHMEX_M_FILTER; - if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) - reg2->config = event->attr.config2; - else - reg2->config = ~0ULL; - if (box->pmu->pmu_idx == 0) - reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; - else - reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; - } - return 0; -} - -static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - u64 config; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return box->shared_regs[idx].config; - - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - raw_spin_lock_irqsave(&er->lock, flags); - config = er->config; - raw_spin_unlock_irqrestore(&er->lock, flags); - return config; -} - -static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx; - - idx = __BITS_VALUE(reg1->idx, 0, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), - nhmex_mbox_shared_reg_config(box, idx)); - idx = __BITS_VALUE(reg1->idx, 1, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), - nhmex_mbox_shared_reg_config(box, idx)); - - if (reg2->idx != EXTRA_REG_NONE) { - wrmsrl(reg2->reg, 0); - if (reg2->config != ~0ULL) { - wrmsrl(reg2->reg + 1, - reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); - wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & - (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); - wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); - } - } - - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); -DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); -DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); -DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); -DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); -DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); -DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); -DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); -DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); -DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); - -static struct attribute *nhmex_uncore_mbox_formats_attr[] = { - &format_attr_count_mode.attr, - &format_attr_storage_mode.attr, - &format_attr_wrap_mode.attr, - &format_attr_flag_mode.attr, - &format_attr_inc_sel.attr, - &format_attr_set_flag_sel.attr, - &format_attr_filter_cfg_en.attr, - &format_attr_filter_match.attr, - &format_attr_filter_mask.attr, - &format_attr_dsp.attr, - &format_attr_thr.attr, - &format_attr_fvc.attr, - &format_attr_pgt.attr, - &format_attr_map.attr, - &format_attr_iss.attr, - &format_attr_pld.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_mbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_mbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc wsmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_mbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_mbox_msr_enable_event, - .hw_config = nhmex_mbox_hw_config, - .get_constraint = nhmex_mbox_get_constraint, - .put_constraint = nhmex_mbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_mbox = { - .name = "mbox", - .num_counters = 6, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_M0_MSR_PMU_CTL0, - .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, - .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_M_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 8, - .event_descs = nhmex_uncore_mbox_events, - .ops = &nhmex_uncore_mbox_ops, - .format_group = &nhmex_uncore_mbox_format_group, -}; - -static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - /* adjust the main event selector and extra register index */ - if (reg1->idx % 2) { - reg1->idx--; - hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } else { - reg1->idx++; - hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } - - /* adjust extra register config */ - switch (reg1->idx % 6) { - case 2: - /* shift the 8~15 bits to the 0~7 bits */ - reg1->config >>= 8; - break; - case 3: - /* shift the 0~7 bits to the 8~15 bits */ - reg1->config <<= 8; - break; - }; -} - -/* - * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. - * An event set consists of 6 events, the 3rd and 4th events in - * an event set use the same extra register. So an event set uses - * 5 extra registers. - */ -static struct event_constraint * -nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - struct intel_uncore_extra_reg *er; - unsigned long flags; - int idx, er_idx; - u64 config1; - bool ok = false; - - if (!uncore_box_is_fake(box) && reg1->alloc) - return NULL; - - idx = reg1->idx % 6; - config1 = reg1->config; -again: - er_idx = idx; - /* the 3rd and 4th events use the same extra register */ - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (idx < 2) { - if (!atomic_read(&er->ref) || er->config == reg1->config) { - atomic_inc(&er->ref); - er->config = reg1->config; - ok = true; - } - } else if (idx == 2 || idx == 3) { - /* - * these two events use different fields in a extra register, - * the 0~7 bits and the 8~15 bits respectively. - */ - u64 mask = 0xff << ((idx - 2) * 8); - if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || - !((er->config ^ config1) & mask)) { - atomic_add(1 << ((idx - 2) * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - } else { - if (!atomic_read(&er->ref) || - (er->config == (hwc->config >> 32) && - er->config1 == reg1->config && - er->config2 == reg2->config)) { - atomic_inc(&er->ref); - er->config = (hwc->config >> 32); - er->config1 = reg1->config; - er->config2 = reg2->config; - ok = true; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - /* - * The Rbox events are always in pairs. The paired - * events are functional identical, but use different - * extra registers. If we failed to take an extra - * register, try the alternative. - */ - idx ^= 1; - if (idx != reg1->idx % 6) { - if (idx == 2) - config1 >>= 8; - else if (idx == 3) - config1 <<= 8; - goto again; - } - } else { - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx % 6) - nhmex_rbox_alter_er(box, event); - reg1->alloc = 1; - } - return NULL; - } - return &constraint_empty; -} - -static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_extra_reg *er; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - int idx, er_idx; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - idx = reg1->idx % 6; - er_idx = idx; - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - if (idx == 2 || idx == 3) - atomic_sub(1 << ((idx - 2) * 8), &er->ref); - else - atomic_dec(&er->ref); - - reg1->alloc = 0; -} - -static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int idx; - - idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> - NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - if (idx >= 0x18) - return -EINVAL; - - reg1->idx = idx; - reg1->config = event->attr.config1; - - switch (idx % 6) { - case 4: - case 5: - hwc->config |= event->attr.config & (~0ULL << 32); - reg2->config = event->attr.config2; - break; - }; - return 0; -} - -static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx, port; - - idx = reg1->idx; - port = idx / 6 + box->pmu->pmu_idx * 4; - - switch (idx % 6) { - case 0: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); - break; - case 1: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); - break; - case 2: - case 3: - wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), - uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); - break; - case 4: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); - break; - case 5: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); - break; - }; - - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); -} - -DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); -DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); - -static struct attribute *nhmex_uncore_rbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_xbr_mm_cfg.attr, - &format_attr_xbr_match.attr, - &format_attr_xbr_mask.attr, - &format_attr_qlx_cfg.attr, - &format_attr_iperf_cfg.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_rbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_rbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_rbox_events[] = { - INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), - INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_rbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_rbox_msr_enable_event, - .hw_config = nhmex_rbox_hw_config, - .get_constraint = nhmex_rbox_get_constraint, - .put_constraint = nhmex_rbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_rbox = { - .name = "rbox", - .num_counters = 8, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_R_MSR_PMON_CTL0, - .perf_ctr = NHMEX_R_MSR_PMON_CNT0, - .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_R_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 20, - .event_descs = nhmex_uncore_rbox_events, - .ops = &nhmex_uncore_rbox_ops, - .format_group = &nhmex_uncore_rbox_format_group -}; - -static struct intel_uncore_type *nhmex_msr_uncores[] = { - &nhmex_uncore_ubox, - &nhmex_uncore_cbox, - &nhmex_uncore_bbox, - &nhmex_uncore_sbox, - &nhmex_uncore_mbox, - &nhmex_uncore_rbox, - &nhmex_uncore_wbox, - NULL, -}; -/* end of Nehalem-EX uncore support */ - static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -3140,7 +170,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve hwc->event_base = uncore_perf_ctr(box, hwc->idx); } -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) { u64 prev_count, new_count, delta; int shift; @@ -3201,14 +231,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { __hrtimer_start_range_ns(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), 0, HRTIMER_MODE_REL_PINNED, 0); } -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) { hrtimer_cancel(&box->hrtimer); } @@ -3291,7 +321,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve } if (event->attr.config == UNCORE_FIXED_EVENT) - return &constraint_fixed; + return &uncore_constraint_fixed; if (type->constraints) { for_each_event_constraint(c, type->constraints) { @@ -3496,7 +526,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags) event->hw.last_tag = ~0ULL; } -static void uncore_pmu_event_read(struct perf_event *event) +void uncore_pmu_event_read(struct perf_event *event) { struct intel_uncore_box *box = uncore_event_to_box(event); uncore_perf_event_update(box, event); @@ -3635,7 +665,7 @@ static struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; -static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) +static int uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -3758,9 +788,6 @@ fail: return ret; } -static struct pci_driver *uncore_pci_driver; -static bool pcidrv_registered; - /* * add a pci uncore device */ @@ -3770,18 +797,20 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id struct intel_uncore_box *box; struct intel_uncore_type *type; int phys_id; + bool first_box = false; - phys_id = pcibus_to_physid[pdev->bus->number]; + phys_id = uncore_pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { - extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + int idx = UNCORE_PCI_DEV_IDX(id->driver_data); + uncore_extra_pci_dev[phys_id][idx] = pdev; pci_set_drvdata(pdev, NULL); return 0; } - type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3803,9 +832,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); + if (list_empty(&pmu->box_list)) + first_box = true; list_add_tail(&box->list, &pmu->box_list); raw_spin_unlock(&uncore_box_lock); + if (first_box) + uncore_pmu_register(pmu); return 0; } @@ -3813,13 +846,14 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + bool last_box = false; box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { - if (extra_pci_dev[phys_id][i] == pdev) { - extra_pci_dev[phys_id][i] = NULL; + if (uncore_extra_pci_dev[phys_id][i] == pdev) { + uncore_extra_pci_dev[phys_id][i] = NULL; break; } } @@ -3835,6 +869,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) raw_spin_lock(&uncore_box_lock); list_del(&box->list); + if (list_empty(&pmu->box_list)) + last_box = true; raw_spin_unlock(&uncore_box_lock); for_each_possible_cpu(cpu) { @@ -3846,6 +882,9 @@ static void uncore_pci_remove(struct pci_dev *pdev) WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); kfree(box); + + if (last_box) + perf_pmu_unregister(&pmu->pmu); } static int __init uncore_pci_init(void) @@ -3854,46 +893,32 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ - ret = snbep_pci2phy_map_init(0x3ce0); - if (ret) - return ret; - pci_uncores = snbep_pci_uncores; - uncore_pci_driver = &snbep_uncore_pci_driver; + ret = snbep_uncore_pci_init(); break; - case 62: /* IvyTown */ - ret = snbep_pci2phy_map_init(0x0e1e); - if (ret) - return ret; - pci_uncores = ivt_pci_uncores; - uncore_pci_driver = &ivt_uncore_pci_driver; + case 62: /* Ivy Bridge-EP */ + ret = ivbep_uncore_pci_init(); + break; + case 63: /* Haswell-EP */ + ret = hswep_uncore_pci_init(); break; case 42: /* Sandy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &snb_uncore_pci_driver; + ret = snb_uncore_pci_init(); break; case 58: /* Ivy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &ivb_uncore_pci_driver; + ret = ivb_uncore_pci_init(); break; case 60: /* Haswell */ case 69: /* Haswell Celeron */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &hsw_uncore_pci_driver; + ret = hsw_uncore_pci_init(); break; default: return 0; } - ret = uncore_types_init(pci_uncores); + if (ret) + return ret; + + ret = uncore_types_init(uncore_pci_uncores); if (ret) return ret; @@ -3904,7 +929,7 @@ static int __init uncore_pci_init(void) if (ret == 0) pcidrv_registered = true; else - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); return ret; } @@ -3914,7 +939,7 @@ static void __init uncore_pci_exit(void) if (pcidrv_registered) { pcidrv_registered = false; pci_unregister_driver(uncore_pci_driver); - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); } } @@ -3940,8 +965,8 @@ static void uncore_cpu_dying(int cpu) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -3961,8 +986,8 @@ static int uncore_cpu_starting(int cpu) phys_id = topology_physical_package_id(cpu); - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -4002,8 +1027,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; if (pmu->func_id < 0) @@ -4083,8 +1108,8 @@ static void uncore_event_exit_cpu(int cpu) if (target >= 0) cpumask_set_cpu(target, &uncore_cpu_mask); - uncore_change_context(msr_uncores, cpu, target); - uncore_change_context(pci_uncores, cpu, target); + uncore_change_context(uncore_msr_uncores, cpu, target); + uncore_change_context(uncore_pci_uncores, cpu, target); } static void uncore_event_init_cpu(int cpu) @@ -4099,8 +1124,8 @@ static void uncore_event_init_cpu(int cpu) cpumask_set_cpu(cpu, &uncore_cpu_mask); - uncore_change_context(msr_uncores, -1, cpu); - uncore_change_context(pci_uncores, -1, cpu); + uncore_change_context(uncore_msr_uncores, -1, cpu); + uncore_change_context(uncore_pci_uncores, -1, cpu); } static int uncore_cpu_notifier(struct notifier_block *self, @@ -4160,47 +1185,37 @@ static void __init uncore_cpu_setup(void *dummy) static int __init uncore_cpu_init(void) { - int ret, max_cores; + int ret; - max_cores = boot_cpu_data.x86_max_cores; switch (boot_cpu_data.x86_model) { case 26: /* Nehalem */ case 30: case 37: /* Westmere */ case 44: - msr_uncores = nhm_msr_uncores; + nhm_uncore_cpu_init(); break; case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ - if (snb_uncore_cbox.num_boxes > max_cores) - snb_uncore_cbox.num_boxes = max_cores; - msr_uncores = snb_msr_uncores; + snb_uncore_cpu_init(); break; case 45: /* Sandy Bridge-EP */ - if (snbep_uncore_cbox.num_boxes > max_cores) - snbep_uncore_cbox.num_boxes = max_cores; - msr_uncores = snbep_msr_uncores; + snbep_uncore_cpu_init(); break; case 46: /* Nehalem-EX */ - uncore_nhmex = true; case 47: /* Westmere-EX aka. Xeon E7 */ - if (!uncore_nhmex) - nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; - if (nhmex_uncore_cbox.num_boxes > max_cores) - nhmex_uncore_cbox.num_boxes = max_cores; - msr_uncores = nhmex_msr_uncores; + nhmex_uncore_cpu_init(); break; - case 62: /* IvyTown */ - if (ivt_uncore_cbox.num_boxes > max_cores) - ivt_uncore_cbox.num_boxes = max_cores; - msr_uncores = ivt_msr_uncores; + case 62: /* Ivy Bridge-EP */ + ivbep_uncore_cpu_init(); + break; + case 63: /* Haswell-EP */ + hswep_uncore_cpu_init(); break; - default: return 0; } - ret = uncore_types_init(msr_uncores); + ret = uncore_types_init(uncore_msr_uncores); if (ret) return ret; @@ -4213,16 +1228,8 @@ static int __init uncore_pmus_register(void) struct intel_uncore_type *type; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - uncore_pmu_register(pmu); - } - } - - for (i = 0; pci_uncores[i]; i++) { - type = pci_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; uncore_pmu_register(pmu); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 90236f0c94a9..18eb78bbdd10 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -24,395 +24,6 @@ #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) -/* SNB event control */ -#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff -#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 -#define SNB_UNC_CTL_EDGE_DET (1 << 18) -#define SNB_UNC_CTL_EN (1 << 22) -#define SNB_UNC_CTL_INVERT (1 << 23) -#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 -#define NHM_UNC_CTL_CMASK_MASK 0xff000000 -#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) - -#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - SNB_UNC_CTL_CMASK_MASK) - -#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - NHM_UNC_CTL_CMASK_MASK) - -/* SNB global control register */ -#define SNB_UNC_PERF_GLOBAL_CTL 0x391 -#define SNB_UNC_FIXED_CTR_CTRL 0x394 -#define SNB_UNC_FIXED_CTR 0x395 - -/* SNB uncore global control */ -#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) -#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) - -/* SNB Cbo register */ -#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 -#define SNB_UNC_CBO_0_PER_CTR0 0x706 -#define SNB_UNC_CBO_MSR_OFFSET 0x10 - -/* NHM global control register */ -#define NHM_UNC_PERF_GLOBAL_CTL 0x391 -#define NHM_UNC_FIXED_CTR 0x394 -#define NHM_UNC_FIXED_CTR_CTRL 0x395 - -/* NHM uncore global control */ -#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) -#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) - -/* NHM uncore register */ -#define NHM_UNC_PERFEVTSEL0 0x3c0 -#define NHM_UNC_UNCORE_PMC0 0x3b0 - -/* SNB-EP Box level control */ -#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) -#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) -#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) -#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) -#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS | \ - SNBEP_PMON_BOX_CTL_FRZ_EN) -/* SNB-EP event control */ -#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff -#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 -#define SNBEP_PMON_CTL_RST (1 << 17) -#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) -#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) -#define SNBEP_PMON_CTL_EN (1 << 22) -#define SNBEP_PMON_CTL_INVERT (1 << 23) -#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 -#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PMON_CTL_TRESH_MASK) - -/* SNB-EP Ubox event control */ -#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) - -#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) -#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -/* SNB-EP PCU event control */ -#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 -#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) -#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) -#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) - -#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* SNB-EP pci control register */ -#define SNBEP_PCI_PMON_BOX_CTL 0xf4 -#define SNBEP_PCI_PMON_CTL0 0xd8 -/* SNB-EP pci counter register */ -#define SNBEP_PCI_PMON_CTR0 0xa0 - -/* SNB-EP home agent register */ -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 -#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 -/* SNB-EP memory controller register */ -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 -/* SNB-EP QPI register */ -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c - -/* SNB-EP Ubox register */ -#define SNBEP_U_MSR_PMON_CTR0 0xc16 -#define SNBEP_U_MSR_PMON_CTL0 0xc10 - -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 - -/* SNB-EP Cbo register */ -#define SNBEP_C0_MSR_PMON_CTR0 0xd16 -#define SNBEP_C0_MSR_PMON_CTL0 0xd10 -#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 -#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 -#define SNBEP_CBO_MSR_OFFSET 0x20 - -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 - -#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ - .event = (e), \ - .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ - .config_mask = (m), \ - .idx = (i) \ -} - -/* SNB-EP PCU register */ -#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 -#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 -#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff -#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc -#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd - -/* IVT event control */ -#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS) -#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_TRESH_MASK) -/* IVT Ubox */ -#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31) -#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) - -#define IVT_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) -/* IVT Cbo */ -#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) -#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) -#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) -#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) -#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) -#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63) - -/* IVT home agent */ -#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) -#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - IVT_HA_PCI_PMON_CTL_Q_OCC_RST) -/* IVT PCU */ -#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) -/* IVT QPI */ -#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* NHM-EX event control */ -#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff -#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 -#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) -#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) -#define NHMEX_PMON_CTL_PMI_EN (1 << 20) -#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) -#define NHMEX_PMON_CTL_INVERT (1 << 23) -#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 -#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_UMASK_MASK | \ - NHMEX_PMON_CTL_EDGE_DET | \ - NHMEX_PMON_CTL_INVERT | \ - NHMEX_PMON_CTL_TRESH_MASK) - -/* NHM-EX Ubox */ -#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define NHMEX_U_MSR_PMON_CTR 0xc11 -#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 - -#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) -#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e -#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) -#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) -#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) - -#define NHMEX_U_PMON_RAW_EVENT_MASK \ - (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_EDGE_DET) - -/* NHM-EX Cbox */ -#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 -#define NHMEX_C0_MSR_PMON_CTR0 0xd11 -#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 -#define NHMEX_C_MSR_OFFSET 0x20 - -/* NHM-EX Bbox */ -#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 -#define NHMEX_B0_MSR_PMON_CTR0 0xc31 -#define NHMEX_B0_MSR_PMON_CTL0 0xc30 -#define NHMEX_B_MSR_OFFSET 0x40 -#define NHMEX_B0_MSR_MATCH 0xe45 -#define NHMEX_B0_MSR_MASK 0xe46 -#define NHMEX_B1_MSR_MATCH 0xe4d -#define NHMEX_B1_MSR_MASK 0xe4e - -#define NHMEX_B_PMON_CTL_EN (1 << 0) -#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_B_PMON_CTR_SHIFT 6 -#define NHMEX_B_PMON_CTR_MASK \ - (0x3 << NHMEX_B_PMON_CTR_SHIFT) -#define NHMEX_B_PMON_RAW_EVENT_MASK \ - (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ - NHMEX_B_PMON_CTR_MASK) - -/* NHM-EX Sbox */ -#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 -#define NHMEX_S0_MSR_PMON_CTR0 0xc51 -#define NHMEX_S0_MSR_PMON_CTL0 0xc50 -#define NHMEX_S_MSR_OFFSET 0x80 -#define NHMEX_S0_MSR_MM_CFG 0xe48 -#define NHMEX_S0_MSR_MATCH 0xe49 -#define NHMEX_S0_MSR_MASK 0xe4a -#define NHMEX_S1_MSR_MM_CFG 0xe58 -#define NHMEX_S1_MSR_MATCH 0xe59 -#define NHMEX_S1_MSR_MASK 0xe5a - -#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) -#define NHMEX_S_EVENT_TO_R_PROG_EV 0 - -/* NHM-EX Mbox */ -#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 -#define NHMEX_M0_MSR_PMU_DSP 0xca5 -#define NHMEX_M0_MSR_PMU_ISS 0xca6 -#define NHMEX_M0_MSR_PMU_MAP 0xca7 -#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 -#define NHMEX_M0_MSR_PMU_PGT 0xca9 -#define NHMEX_M0_MSR_PMU_PLD 0xcaa -#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab -#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 -#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 -#define NHMEX_M_MSR_OFFSET 0x40 -#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 -#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c - -#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) -#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL -#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL -#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 - -#define NHMEX_M_PMON_CTL_EN (1 << 0) -#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) -#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 -#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 -#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) -#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) -#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 -#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ - (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ - (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) -#define NHMEX_M_PMON_RAW_EVENT_MASK \ - (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ - NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ - NHMEX_M_PMON_CTL_WRAP_MODE | \ - NHMEX_M_PMON_CTL_FLAG_MODE | \ - NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) - -#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) -#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) - -#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) -#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) - -/* - * use the 9~13 bits to select event If the 7th bit is not set, - * otherwise use the 19~21 bits to select event. - */ -#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_EXTAR_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) -#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_SET_FLAG_SEL_MASK, \ - (u64)-1, NHMEX_M_##r) - -/* NHM-EX Rbox */ -#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 -#define NHMEX_R_MSR_PMON_CTL0 0xe10 -#define NHMEX_R_MSR_PMON_CNT0 0xe11 -#define NHMEX_R_MSR_OFFSET 0x20 - -#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ - ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) -#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ - (((n) < 4 ? 0 : 0x10) + (n) * 4) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ - (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ - (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) - -#define NHMEX_R_PMON_CTL_EN (1 << 0) -#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) -#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK - -/* NHM-EX Wbox */ -#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 -#define NHMEX_W_MSR_PMON_CNT0 0xc90 -#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 -#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 -#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 - -#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) - struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -505,6 +116,9 @@ struct uncore_event_desc { const char *config; }; +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf); + #define INTEL_UNCORE_EVENT_DESC(_name, _config) \ { \ .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \ @@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) - -static ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - struct uncore_event_desc *event = - container_of(attr, struct uncore_event_desc, attr); - return sprintf(buf, "%s", event->config); -} - static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box) { return box->pmu->type->box_ctl; @@ -694,3 +299,41 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); } + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event); +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu); +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event); +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event); +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_event_read(struct perf_event *event); +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); +struct event_constraint * +uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event); +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event); +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); + +extern struct intel_uncore_type **uncore_msr_uncores; +extern struct intel_uncore_type **uncore_pci_uncores; +extern struct pci_driver *uncore_pci_driver; +extern int uncore_pcibus_to_physid[256]; +extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +extern struct event_constraint uncore_constraint_empty; + +/* perf_event_intel_uncore_snb.c */ +int snb_uncore_pci_init(void); +int ivb_uncore_pci_init(void); +int hsw_uncore_pci_init(void); +void snb_uncore_cpu_init(void); +void nhm_uncore_cpu_init(void); + +/* perf_event_intel_uncore_snbep.c */ +int snbep_uncore_pci_init(void); +void snbep_uncore_cpu_init(void); +int ivbep_uncore_pci_init(void); +void ivbep_uncore_cpu_init(void); +int hswep_uncore_pci_init(void); +void hswep_uncore_cpu_init(void); + +/* perf_event_intel_uncore_nhmex.c */ +void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c new file mode 100644 index 000000000000..2749965afed0 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c @@ -0,0 +1,1221 @@ +/* Nehalem-EX/Westmere-EX uncore support */ +#include "perf_event_intel_uncore.h" + +/* NHM-EX event control */ +#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff +#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 +#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) +#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) +#define NHMEX_PMON_CTL_PMI_EN (1 << 20) +#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) +#define NHMEX_PMON_CTL_INVERT (1 << 23) +#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 +#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_UMASK_MASK | \ + NHMEX_PMON_CTL_EDGE_DET | \ + NHMEX_PMON_CTL_INVERT | \ + NHMEX_PMON_CTL_TRESH_MASK) + +/* NHM-EX Ubox */ +#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define NHMEX_U_MSR_PMON_CTR 0xc11 +#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 + +#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) +#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e +#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) +#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) +#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) + +#define NHMEX_U_PMON_RAW_EVENT_MASK \ + (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_EDGE_DET) + +/* NHM-EX Cbox */ +#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 +#define NHMEX_C0_MSR_PMON_CTR0 0xd11 +#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 +#define NHMEX_C_MSR_OFFSET 0x20 + +/* NHM-EX Bbox */ +#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 +#define NHMEX_B0_MSR_PMON_CTR0 0xc31 +#define NHMEX_B0_MSR_PMON_CTL0 0xc30 +#define NHMEX_B_MSR_OFFSET 0x40 +#define NHMEX_B0_MSR_MATCH 0xe45 +#define NHMEX_B0_MSR_MASK 0xe46 +#define NHMEX_B1_MSR_MATCH 0xe4d +#define NHMEX_B1_MSR_MASK 0xe4e + +#define NHMEX_B_PMON_CTL_EN (1 << 0) +#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_B_PMON_CTR_SHIFT 6 +#define NHMEX_B_PMON_CTR_MASK \ + (0x3 << NHMEX_B_PMON_CTR_SHIFT) +#define NHMEX_B_PMON_RAW_EVENT_MASK \ + (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ + NHMEX_B_PMON_CTR_MASK) + +/* NHM-EX Sbox */ +#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 +#define NHMEX_S0_MSR_PMON_CTR0 0xc51 +#define NHMEX_S0_MSR_PMON_CTL0 0xc50 +#define NHMEX_S_MSR_OFFSET 0x80 +#define NHMEX_S0_MSR_MM_CFG 0xe48 +#define NHMEX_S0_MSR_MATCH 0xe49 +#define NHMEX_S0_MSR_MASK 0xe4a +#define NHMEX_S1_MSR_MM_CFG 0xe58 +#define NHMEX_S1_MSR_MATCH 0xe59 +#define NHMEX_S1_MSR_MASK 0xe5a + +#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) +#define NHMEX_S_EVENT_TO_R_PROG_EV 0 + +/* NHM-EX Mbox */ +#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 +#define NHMEX_M0_MSR_PMU_DSP 0xca5 +#define NHMEX_M0_MSR_PMU_ISS 0xca6 +#define NHMEX_M0_MSR_PMU_MAP 0xca7 +#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 +#define NHMEX_M0_MSR_PMU_PGT 0xca9 +#define NHMEX_M0_MSR_PMU_PLD 0xcaa +#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab +#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 +#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 +#define NHMEX_M_MSR_OFFSET 0x40 +#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 +#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c + +#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) +#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL +#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL +#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 + +#define NHMEX_M_PMON_CTL_EN (1 << 0) +#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) +#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 +#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 +#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) +#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) +#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 +#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ + (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ + (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) +#define NHMEX_M_PMON_RAW_EVENT_MASK \ + (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ + NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ + NHMEX_M_PMON_CTL_WRAP_MODE | \ + NHMEX_M_PMON_CTL_FLAG_MODE | \ + NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) + +#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) +#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) + +#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) + +/* + * use the 9~13 bits to select event If the 7th bit is not set, + * otherwise use the 19~21 bits to select event. + */ +#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_EXTAR_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) +#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_SET_FLAG_SEL_MASK, \ + (u64)-1, NHMEX_M_##r) + +/* NHM-EX Rbox */ +#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 +#define NHMEX_R_MSR_PMON_CTL0 0xe10 +#define NHMEX_R_MSR_PMON_CNT0 0xe11 +#define NHMEX_R_MSR_OFFSET 0x20 + +#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ + ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) +#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ + (((n) < 4 ? 0 : 0x10) + (n) * 4) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ + (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ + (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) + +#define NHMEX_R_PMON_CTL_EN (1 << 0) +#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) +#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK + +/* NHM-EX Wbox */ +#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 +#define NHMEX_W_MSR_PMON_CNT0 0xc90 +#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 +#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 +#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 + +#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); +DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); + +static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); +} + +static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config &= ~((1ULL << uncore_num_counters(box)) - 1); + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config |= (1ULL << uncore_num_counters(box)) - 1; + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx >= UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); + else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); + else + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +#define NHMEX_UNCORE_OPS_COMMON_INIT() \ + .init_box = nhmex_uncore_msr_init_box, \ + .disable_box = nhmex_uncore_msr_disable_box, \ + .enable_box = nhmex_uncore_msr_enable_box, \ + .disable_event = nhmex_uncore_msr_disable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops nhmex_uncore_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_uncore_msr_enable_event, +}; + +static struct attribute *nhmex_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_edge.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_ubox_format_group = { + .name = "format", + .attrs = nhmex_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type nhmex_uncore_ubox = { + .name = "ubox", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, + .perf_ctr = NHMEX_U_MSR_PMON_CTR, + .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_ubox_format_group +}; + +static struct attribute *nhmex_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_cbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_cbox_formats_attr, +}; + +/* msr offset for each instance of cbox */ +static unsigned nhmex_cbox_msr_offsets[] = { + 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, +}; + +static struct intel_uncore_type nhmex_uncore_cbox = { + .name = "cbox", + .num_counters = 6, + .num_boxes = 10, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, + .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, + .msr_offsets = nhmex_cbox_msr_offsets, + .pair_ctr_ctl = 1, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static struct uncore_event_desc nhmex_uncore_wbox_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type nhmex_uncore_wbox = { + .name = "wbox", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_W_MSR_PMON_CNT0, + .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, + .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, + .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, + .pair_ctr_ctl = 1, + .event_descs = nhmex_uncore_wbox_events, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int ctr, ev_sel; + + ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> + NHMEX_B_PMON_CTR_SHIFT; + ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> + NHMEX_B_PMON_CTL_EV_SEL_SHIFT; + + /* events that do not use the match/mask registers */ + if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || + (ctr == 2 && ev_sel != 0x4) || ctr == 3) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_B0_MSR_MATCH; + else + reg1->reg = NHMEX_B1_MSR_MATCH; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg + 1, reg2->config); + } + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); +} + +/* + * The Bbox has 4 counters, but each counter monitors different events. + * Use bits 6-7 in the event config to select counter. + */ +static struct event_constraint nhmex_uncore_bbox_constraints[] = { + EVENT_CONSTRAINT(0 , 1, 0xc0), + EVENT_CONSTRAINT(0x40, 2, 0xc0), + EVENT_CONSTRAINT(0x80, 4, 0xc0), + EVENT_CONSTRAINT(0xc0, 8, 0xc0), + EVENT_CONSTRAINT_END, +}; + +static struct attribute *nhmex_uncore_bbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_counter.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_bbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_bbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_bbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_bbox_msr_enable_event, + .hw_config = nhmex_bbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_bbox = { + .name = "bbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_B0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, + .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_B_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .constraints = nhmex_uncore_bbox_constraints, + .ops = &nhmex_uncore_bbox_ops, + .format_group = &nhmex_uncore_bbox_format_group +}; + +static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + /* only TO_R_PROG_EV event uses the match/mask register */ + if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != + NHMEX_S_EVENT_TO_R_PROG_EV) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_S0_MSR_MM_CFG; + else + reg1->reg = NHMEX_S1_MSR_MM_CFG; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, 0); + wrmsrl(reg1->reg + 1, reg1->config); + wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); + } + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); +} + +static struct attribute *nhmex_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_sbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_sbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_sbox_msr_enable_event, + .hw_config = nhmex_sbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_S0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_S_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .ops = &nhmex_uncore_sbox_ops, + .format_group = &nhmex_uncore_sbox_format_group +}; + +enum { + EXTRA_REG_NHMEX_M_FILTER, + EXTRA_REG_NHMEX_M_DSP, + EXTRA_REG_NHMEX_M_ISS, + EXTRA_REG_NHMEX_M_MAP, + EXTRA_REG_NHMEX_M_MSC_THR, + EXTRA_REG_NHMEX_M_PGT, + EXTRA_REG_NHMEX_M_PLD, + EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, +}; + +static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { + MBOX_INC_SEL_EXTAR_REG(0x0, DSP), + MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x9, ISS), + /* event 0xa uses two extra registers */ + MBOX_INC_SEL_EXTAR_REG(0xa, ISS), + MBOX_INC_SEL_EXTAR_REG(0xa, PLD), + MBOX_INC_SEL_EXTAR_REG(0xb, PLD), + /* events 0xd ~ 0x10 use the same extra register */ + MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x16, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), + EVENT_EXTRA_END +}; + +/* Nehalem-EX or Westmere-EX ? */ +static bool uncore_nhmex; + +static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + bool ret = false; + u64 mask; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config == config) { + atomic_inc(&er->ref); + er->config = config; + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; + } + /* + * The ZDP_CTL_FVC MSR has 4 fields which are used to control + * events 0xd ~ 0x10. Besides these 4 fields, there are additional + * fields which are shared. + */ + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (WARN_ON_ONCE(idx >= 4)) + return false; + + /* mask of the shared fields */ + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + + raw_spin_lock_irqsave(&er->lock, flags); + /* add mask of the non-shared field if it's in use */ + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { + if (uncore_nhmex) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + } + + if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | + WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + er->config &= ~mask; + er->config |= (config & mask); + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; +} + +static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + atomic_dec(&er->ref); + return; + } + + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + atomic_sub(1 << (idx * 8), &er->ref); +} + +static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 config = reg1->config; + + /* get the non-shared control bits and shift them */ + idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (uncore_nhmex) + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (new_idx > orig_idx) { + idx = new_idx - orig_idx; + config <<= 3 * idx; + } else { + idx = orig_idx - new_idx; + config >>= 3 * idx; + } + + /* add the shared control bits back */ + if (uncore_nhmex) + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + else + config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + if (modify) { + /* adjust the main event selector */ + if (new_idx > orig_idx) + hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + else + hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + reg1->config = config; + reg1->idx = ~0xff | new_idx; + } + return config; +} + +static struct event_constraint * +nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int i, idx[2], alloc = 0; + u64 config1 = reg1->config; + + idx[0] = __BITS_VALUE(reg1->idx, 0, 8); + idx[1] = __BITS_VALUE(reg1->idx, 1, 8); +again: + for (i = 0; i < 2; i++) { + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + idx[i] = 0xff; + + if (idx[i] == 0xff) + continue; + + if (!nhmex_mbox_get_shared_reg(box, idx[i], + __BITS_VALUE(config1, i, 32))) + goto fail; + alloc |= (0x1 << i); + } + + /* for the match/mask registers */ + if (reg2->idx != EXTRA_REG_NONE && + (uncore_box_is_fake(box) || !reg2->alloc) && + !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) + goto fail; + + /* + * If it's a fake box -- as per validate_{group,event}() we + * shouldn't touch event state and we can avoid doing so + * since both will only call get_event_constraints() once + * on each event, this avoids the need for reg->alloc. + */ + if (!uncore_box_is_fake(box)) { + if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) + nhmex_mbox_alter_er(event, idx[0], true); + reg1->alloc |= alloc; + if (reg2->idx != EXTRA_REG_NONE) + reg2->alloc = 1; + } + return NULL; +fail: + if (idx[0] != 0xff && !(alloc & 0x1) && + idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + /* + * events 0xd ~ 0x10 are functional identical, but are + * controlled by different fields in the ZDP_CTL_FVC + * register. If we failed to take one field, try the + * rest 3 choices. + */ + BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); + idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + idx[0] = (idx[0] + 1) % 4; + idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { + config1 = nhmex_mbox_alter_er(event, idx[0], false); + goto again; + } + } + + if (alloc & 0x1) + nhmex_mbox_put_shared_reg(box, idx[0]); + if (alloc & 0x2) + nhmex_mbox_put_shared_reg(box, idx[1]); + return &uncore_constraint_empty; +} + +static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + + if (uncore_box_is_fake(box)) + return; + + if (reg1->alloc & 0x1) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); + if (reg1->alloc & 0x2) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); + reg1->alloc = 0; + + if (reg2->alloc) { + nhmex_mbox_put_shared_reg(box, reg2->idx); + reg2->alloc = 0; + } +} + +static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) +{ + if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return er->idx; + return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; +} + +static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct extra_reg *er; + unsigned msr; + int reg_idx = 0; + /* + * The mbox events may require 2 extra MSRs at the most. But only + * the lower 32 bits in these MSRs are significant, so we can use + * config1 to pass two MSRs' config. + */ + for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + + msr = er->msr + type->msr_offset * box->pmu->pmu_idx; + if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) + return -EINVAL; + + /* always use the 32~63 bits to pass the PLD config */ + if (er->idx == EXTRA_REG_NHMEX_M_PLD) + reg_idx = 1; + else if (WARN_ON_ONCE(reg_idx > 0)) + return -EINVAL; + + reg1->idx &= ~(0xff << (reg_idx * 8)); + reg1->reg &= ~(0xffff << (reg_idx * 16)); + reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); + reg1->reg |= msr << (reg_idx * 16); + reg1->config = event->attr.config1; + reg_idx++; + } + /* + * The mbox only provides ability to perform address matching + * for the PLD events. + */ + if (reg_idx == 2) { + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + } + return 0; +} + +static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return box->shared_regs[idx].config; + + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + return config; +} + +static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx; + + idx = __BITS_VALUE(reg1->idx, 0, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), + nhmex_mbox_shared_reg_config(box, idx)); + idx = __BITS_VALUE(reg1->idx, 1, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), + nhmex_mbox_shared_reg_config(box, idx)); + + if (reg2->idx != EXTRA_REG_NONE) { + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } + } + + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); + +static struct attribute *nhmex_uncore_mbox_formats_attr[] = { + &format_attr_count_mode.attr, + &format_attr_storage_mode.attr, + &format_attr_wrap_mode.attr, + &format_attr_flag_mode.attr, + &format_attr_inc_sel.attr, + &format_attr_set_flag_sel.attr, + &format_attr_filter_cfg_en.attr, + &format_attr_filter_match.attr, + &format_attr_filter_mask.attr, + &format_attr_dsp.attr, + &format_attr_thr.attr, + &format_attr_fvc.attr, + &format_attr_pgt.attr, + &format_attr_map.attr, + &format_attr_iss.attr, + &format_attr_pld.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_mbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_mbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc wsmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_mbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_mbox_msr_enable_event, + .hw_config = nhmex_mbox_hw_config, + .get_constraint = nhmex_mbox_get_constraint, + .put_constraint = nhmex_mbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_mbox = { + .name = "mbox", + .num_counters = 6, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_M0_MSR_PMU_CTL0, + .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, + .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_M_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 8, + .event_descs = nhmex_uncore_mbox_events, + .ops = &nhmex_uncore_mbox_ops, + .format_group = &nhmex_uncore_mbox_format_group, +}; + +static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + /* adjust the main event selector and extra register index */ + if (reg1->idx % 2) { + reg1->idx--; + hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } else { + reg1->idx++; + hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } + + /* adjust extra register config */ + switch (reg1->idx % 6) { + case 2: + /* shift the 8~15 bits to the 0~7 bits */ + reg1->config >>= 8; + break; + case 3: + /* shift the 0~7 bits to the 8~15 bits */ + reg1->config <<= 8; + break; + } +} + +/* + * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. + * An event set consists of 6 events, the 3rd and 4th events in + * an event set use the same extra register. So an event set uses + * 5 extra registers. + */ +static struct event_constraint * +nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + struct intel_uncore_extra_reg *er; + unsigned long flags; + int idx, er_idx; + u64 config1; + bool ok = false; + + if (!uncore_box_is_fake(box) && reg1->alloc) + return NULL; + + idx = reg1->idx % 6; + config1 = reg1->config; +again: + er_idx = idx; + /* the 3rd and 4th events use the same extra register */ + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (idx < 2) { + if (!atomic_read(&er->ref) || er->config == reg1->config) { + atomic_inc(&er->ref); + er->config = reg1->config; + ok = true; + } + } else if (idx == 2 || idx == 3) { + /* + * these two events use different fields in a extra register, + * the 0~7 bits and the 8~15 bits respectively. + */ + u64 mask = 0xff << ((idx - 2) * 8); + if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || + !((er->config ^ config1) & mask)) { + atomic_add(1 << ((idx - 2) * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + } else { + if (!atomic_read(&er->ref) || + (er->config == (hwc->config >> 32) && + er->config1 == reg1->config && + er->config2 == reg2->config)) { + atomic_inc(&er->ref); + er->config = (hwc->config >> 32); + er->config1 = reg1->config; + er->config2 = reg2->config; + ok = true; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + /* + * The Rbox events are always in pairs. The paired + * events are functional identical, but use different + * extra registers. If we failed to take an extra + * register, try the alternative. + */ + idx ^= 1; + if (idx != reg1->idx % 6) { + if (idx == 2) + config1 >>= 8; + else if (idx == 3) + config1 <<= 8; + goto again; + } + } else { + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx % 6) + nhmex_rbox_alter_er(box, event); + reg1->alloc = 1; + } + return NULL; + } + return &uncore_constraint_empty; +} + +static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + int idx, er_idx; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + idx = reg1->idx % 6; + er_idx = idx; + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + if (idx == 2 || idx == 3) + atomic_sub(1 << ((idx - 2) * 8), &er->ref); + else + atomic_dec(&er->ref); + + reg1->alloc = 0; +} + +static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int idx; + + idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> + NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + if (idx >= 0x18) + return -EINVAL; + + reg1->idx = idx; + reg1->config = event->attr.config1; + + switch (idx % 6) { + case 4: + case 5: + hwc->config |= event->attr.config & (~0ULL << 32); + reg2->config = event->attr.config2; + break; + } + return 0; +} + +static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx, port; + + idx = reg1->idx; + port = idx / 6 + box->pmu->pmu_idx * 4; + + switch (idx % 6) { + case 0: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); + break; + case 1: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); + break; + case 2: + case 3: + wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), + uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); + break; + case 4: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); + break; + case 5: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); + break; + } + + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); +} + +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); +DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); + +static struct attribute *nhmex_uncore_rbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_xbr_mm_cfg.attr, + &format_attr_xbr_match.attr, + &format_attr_xbr_mask.attr, + &format_attr_qlx_cfg.attr, + &format_attr_iperf_cfg.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_rbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_rbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_rbox_events[] = { + INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), + INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_rbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_rbox_msr_enable_event, + .hw_config = nhmex_rbox_hw_config, + .get_constraint = nhmex_rbox_get_constraint, + .put_constraint = nhmex_rbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_rbox = { + .name = "rbox", + .num_counters = 8, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_R_MSR_PMON_CTL0, + .perf_ctr = NHMEX_R_MSR_PMON_CNT0, + .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_R_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 20, + .event_descs = nhmex_uncore_rbox_events, + .ops = &nhmex_uncore_rbox_ops, + .format_group = &nhmex_uncore_rbox_format_group +}; + +static struct intel_uncore_type *nhmex_msr_uncores[] = { + &nhmex_uncore_ubox, + &nhmex_uncore_cbox, + &nhmex_uncore_bbox, + &nhmex_uncore_sbox, + &nhmex_uncore_mbox, + &nhmex_uncore_rbox, + &nhmex_uncore_wbox, + NULL, +}; + +void nhmex_uncore_cpu_init(void) +{ + if (boot_cpu_data.x86_model == 46) + uncore_nhmex = true; + else + nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; + if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = nhmex_msr_uncores; +} +/* end of Nehalem-EX uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c new file mode 100644 index 000000000000..3001015b755c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -0,0 +1,636 @@ +/* Nehalem/SandBridge/Haswell uncore support */ +#include "perf_event_intel_uncore.h" + +/* SNB event control */ +#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff +#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 +#define SNB_UNC_CTL_EDGE_DET (1 << 18) +#define SNB_UNC_CTL_EN (1 << 22) +#define SNB_UNC_CTL_INVERT (1 << 23) +#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 +#define NHM_UNC_CTL_CMASK_MASK 0xff000000 +#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + SNB_UNC_CTL_CMASK_MASK) + +#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + NHM_UNC_CTL_CMASK_MASK) + +/* SNB global control register */ +#define SNB_UNC_PERF_GLOBAL_CTL 0x391 +#define SNB_UNC_FIXED_CTR_CTRL 0x394 +#define SNB_UNC_FIXED_CTR 0x395 + +/* SNB uncore global control */ +#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) +#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) + +/* SNB Cbo register */ +#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 +#define SNB_UNC_CBO_0_PER_CTR0 0x706 +#define SNB_UNC_CBO_MSR_OFFSET 0x10 + +/* NHM global control register */ +#define NHM_UNC_PERF_GLOBAL_CTL 0x391 +#define NHM_UNC_FIXED_CTR 0x394 +#define NHM_UNC_FIXED_CTR_CTRL 0x395 + +/* NHM uncore global control */ +#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) +#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* NHM uncore register */ +#define NHM_UNC_PERFEVTSEL0 0x3c0 +#define NHM_UNC_UNCORE_PMC0 0x3b0 + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); + +/* Sandy Bridge uncore support */ +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); +} + +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void snb_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) { + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); + } +} + +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + +static struct attribute *snb_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask5.attr, + NULL, +}; + +static struct attribute_group snb_uncore_format_group = { + .name = "format", + .attrs = snb_uncore_formats_attr, +}; + +static struct intel_uncore_ops snb_uncore_msr_ops = { + .init_box = snb_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct event_constraint snb_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x80, 0x1), + UNCORE_EVENT_CONSTRAINT(0x83, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snb_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .num_boxes = 4, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .constraints = snb_uncore_cbox_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, +}; + +static struct intel_uncore_type *snb_msr_uncores[] = { + &snb_uncore_cbox, + NULL, +}; + +void snb_uncore_cpu_init(void) +{ + uncore_msr_uncores = snb_msr_uncores; + if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; +} + +enum { + SNB_PCI_UNCORE_IMC, +}; + +static struct uncore_event_desc snb_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), + INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), + INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + + { /* end: all zeroes */ }, +}; + +#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff +#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 + +/* page size multiple covering all config regs */ +#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 + +#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 +#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 +#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE + +static struct attribute *snb_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group snb_uncore_imc_format_group = { + .name = "format", + .attrs = snb_uncore_imc_formats_attr, +}; + +static void snb_uncore_imc_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; + resource_size_t addr; + u32 pci_dword; + + pci_read_config_dword(pdev, where, &pci_dword); + addr = pci_dword; + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + pci_read_config_dword(pdev, where + 4, &pci_dword); + addr |= ((resource_size_t)pci_dword << 32); +#endif + + addr &= ~(PAGE_SIZE - 1); + + box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); + box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; +} + +static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); +} + +/* + * custom event_init() function because we define our own fixed, free + * running counters, so we do not want to conflict with generic uncore + * logic. Also simplifies processing + */ +static int snb_uncore_imc_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; + int idx, base; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + + /* check only supported bits are set */ + if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) + return -EINVAL; + + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + /* + * check event is known (whitelist, determines counter) + */ + switch (cfg) { + case SNB_UNCORE_PCI_IMC_DATA_READS: + base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; + idx = UNCORE_PMC_IDX_FIXED; + break; + case SNB_UNCORE_PCI_IMC_DATA_WRITES: + base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; + idx = UNCORE_PMC_IDX_FIXED + 1; + break; + default: + return -EINVAL; + } + + /* must be done before validate_group */ + event->hw.event_base = base; + event->hw.config = cfg; + event->hw.idx = idx; + + /* no group validation needed, we have free running counters */ + + return 0; +} + +static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + return 0; +} + +static void snb_uncore_imc_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + u64 count; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->n_active++; + + list_add_tail(&event->active_entry, &box->active_list); + + count = snb_uncore_imc_read_counter(box, event); + local64_set(&event->hw.prev_count, count); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + box->n_active--; + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + list_del(&event->active_entry); + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int snb_uncore_imc_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!box) + return -ENODEV; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + snb_uncore_imc_event_start(event, 0); + + box->n_events++; + + return 0; +} + +static void snb_uncore_imc_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + --box->n_events; + break; + } + } +} + +static int snb_pci2phy_map_init(int devid) +{ + struct pci_dev *dev = NULL; + int bus; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); + if (!dev) + return -ENOTTY; + + bus = dev->bus->number; + + uncore_pcibus_to_physid[bus] = 0; + + pci_dev_put(dev); + + return 0; +} + +static struct pmu snb_uncore_imc_pmu = { + .task_ctx_nr = perf_invalid_context, + .event_init = snb_uncore_imc_event_init, + .add = snb_uncore_imc_event_add, + .del = snb_uncore_imc_event_del, + .start = snb_uncore_imc_event_start, + .stop = snb_uncore_imc_event_stop, + .read = uncore_pmu_event_read, +}; + +static struct intel_uncore_ops snb_uncore_imc_ops = { + .init_box = snb_uncore_imc_init_box, + .enable_box = snb_uncore_imc_enable_box, + .disable_box = snb_uncore_imc_disable_box, + .disable_event = snb_uncore_imc_disable_event, + .enable_event = snb_uncore_imc_enable_event, + .hw_config = snb_uncore_imc_hw_config, + .read_counter = snb_uncore_imc_read_counter, +}; + +static struct intel_uncore_type snb_uncore_imc = { + .name = "imc", + .num_counters = 2, + .num_boxes = 1, + .fixed_ctr_bits = 32, + .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, + .event_descs = snb_uncore_imc_events, + .format_group = &snb_uncore_imc_format_group, + .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, + .ops = &snb_uncore_imc_ops, + .pmu = &snb_uncore_imc_pmu, +}; + +static struct intel_uncore_type *snb_pci_uncores[] = { + [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, + NULL, +}; + +static const struct pci_device_id snb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id ivb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id hsw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static struct pci_driver snb_uncore_pci_driver = { + .name = "snb_uncore", + .id_table = snb_uncore_pci_ids, +}; + +static struct pci_driver ivb_uncore_pci_driver = { + .name = "ivb_uncore", + .id_table = ivb_uncore_pci_ids, +}; + +static struct pci_driver hsw_uncore_pci_driver = { + .name = "hsw_uncore", + .id_table = hsw_uncore_pci_ids, +}; + +struct imc_uncore_pci_dev { + __u32 pci_id; + struct pci_driver *driver; +}; +#define IMC_DEV(a, d) \ + { .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) } + +static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { + IMC_DEV(SNB_IMC, &snb_uncore_pci_driver), + IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */ + IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ + IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ + { /* end marker */ } +}; + + +#define for_each_imc_pci_id(x, t) \ + for (x = (t); (x)->pci_id; x++) + +static struct pci_driver *imc_uncore_find_dev(void) +{ + const struct imc_uncore_pci_dev *p; + int ret; + + for_each_imc_pci_id(p, desktop_imc_pci_ids) { + ret = snb_pci2phy_map_init(p->pci_id); + if (ret == 0) + return p->driver; + } + return NULL; +} + +static int imc_uncore_pci_init(void) +{ + struct pci_driver *imc_drv = imc_uncore_find_dev(); + + if (!imc_drv) + return -ENODEV; + + uncore_pci_uncores = snb_pci_uncores; + uncore_pci_driver = imc_drv; + + return 0; +} + +int snb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +int ivb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} +int hsw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +/* end of Sandy Bridge uncore support */ + +/* Nehalem uncore support */ +static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); +} + +static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); +} + +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *nhm_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group nhm_uncore_format_group = { + .name = "format", + .attrs = nhm_uncore_formats_attr, +}; + +static struct uncore_event_desc nhm_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhm_uncore_msr_ops = { + .disable_box = nhm_uncore_msr_disable_box, + .enable_box = nhm_uncore_msr_enable_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = nhm_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct intel_uncore_type nhm_uncore = { + .name = "", + .num_counters = 8, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = NHM_UNC_PERFEVTSEL0, + .perf_ctr = NHM_UNC_UNCORE_PMC0, + .fixed_ctr = NHM_UNC_FIXED_CTR, + .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, + .event_mask = NHM_UNC_RAW_EVENT_MASK, + .event_descs = nhm_uncore_events, + .ops = &nhm_uncore_msr_ops, + .format_group = &nhm_uncore_format_group, +}; + +static struct intel_uncore_type *nhm_msr_uncores[] = { + &nhm_uncore, + NULL, +}; + +void nhm_uncore_cpu_init(void) +{ + uncore_msr_uncores = nhm_msr_uncores; +} + +/* end of Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c new file mode 100644 index 000000000000..adf138eac85c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -0,0 +1,2258 @@ +/* SandyBridge-EP/IvyTown uncore support */ +#include "perf_event_intel_uncore.h" + + +/* SNB-EP Box level control */ +#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) +#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) +#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) +#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) +#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS | \ + SNBEP_PMON_BOX_CTL_FRZ_EN) +/* SNB-EP event control */ +#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff +#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 +#define SNBEP_PMON_CTL_RST (1 << 17) +#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) +#define SNBEP_PMON_CTL_EN (1 << 22) +#define SNBEP_PMON_CTL_INVERT (1 << 23) +#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 +#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PMON_CTL_TRESH_MASK) + +/* SNB-EP Ubox event control */ +#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) + +#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) +#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* SNB-EP PCU event control */ +#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 +#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) +#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) +#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) + +#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +/* SNB-EP pci control register */ +#define SNBEP_PCI_PMON_BOX_CTL 0xf4 +#define SNBEP_PCI_PMON_CTL0 0xd8 +/* SNB-EP pci counter register */ +#define SNBEP_PCI_PMON_CTR0 0xa0 + +/* SNB-EP home agent register */ +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 +#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 +/* SNB-EP memory controller register */ +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 +/* SNB-EP QPI register */ +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c + +/* SNB-EP Ubox register */ +#define SNBEP_U_MSR_PMON_CTR0 0xc16 +#define SNBEP_U_MSR_PMON_CTL0 0xc10 + +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 + +/* SNB-EP Cbo register */ +#define SNBEP_C0_MSR_PMON_CTR0 0xd16 +#define SNBEP_C0_MSR_PMON_CTL0 0xd10 +#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 +#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 +#define SNBEP_CBO_MSR_OFFSET 0x20 + +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 + +#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ + .event = (e), \ + .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ + .config_mask = (m), \ + .idx = (i) \ +} + +/* SNB-EP PCU register */ +#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 +#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 +#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff +#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc +#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd + +/* IVBEP event control */ +#define IVBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS) +#define IVBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_TRESH_MASK) +/* IVBEP Ubox */ +#define IVBEP_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define IVBEP_U_PMON_GLOBAL_FRZ_ALL (1 << 31) +#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) + +#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) +/* IVBEP Cbo */ +#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + +/* IVBEP home agent */ +#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) +#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST) +/* IVBEP PCU */ +#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* IVBEP QPI */ +#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +/* Haswell-EP Ubox */ +#define HSWEP_U_MSR_PMON_CTR0 0x705 +#define HSWEP_U_MSR_PMON_CTL0 0x709 +#define HSWEP_U_MSR_PMON_FILTER 0x707 + +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703 +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTR 0x704 + +#define HSWEP_U_MSR_PMON_BOX_FILTER_TID (0x1 << 0) +#define HSWEP_U_MSR_PMON_BOX_FILTER_CID (0x1fULL << 1) +#define HSWEP_U_MSR_PMON_BOX_FILTER_MASK \ + (HSWEP_U_MSR_PMON_BOX_FILTER_TID | \ + HSWEP_U_MSR_PMON_BOX_FILTER_CID) + +/* Haswell-EP CBo */ +#define HSWEP_C0_MSR_PMON_CTR0 0xe08 +#define HSWEP_C0_MSR_PMON_CTL0 0xe01 +#define HSWEP_C0_MSR_PMON_BOX_CTL 0xe00 +#define HSWEP_C0_MSR_PMON_BOX_FILTER0 0xe05 +#define HSWEP_CBO_MSR_OFFSET 0x10 + + +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_TID (0x3fULL << 0) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 6) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x7fULL << 17) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + + +/* Haswell-EP Sbox */ +#define HSWEP_S0_MSR_PMON_CTR0 0x726 +#define HSWEP_S0_MSR_PMON_CTL0 0x721 +#define HSWEP_S0_MSR_PMON_BOX_CTL 0x720 +#define HSWEP_SBOX_MSR_OFFSET 0xa +#define HSWEP_S_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* Haswell-EP PCU */ +#define HSWEP_PCU_MSR_PMON_CTR0 0x717 +#define HSWEP_PCU_MSR_PMON_CTL0 0x711 +#define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 +#define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 + + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); +DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); +DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); +DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); + +static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); + pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + + return count; +} + +static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); +} + +static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + + if (msr) + wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); +} + +static struct attribute *snbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *snbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *snbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_nid.attr, + &format_attr_filter_state.attr, + &format_attr_filter_opc.attr, + NULL, +}; + +static struct attribute *snbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *snbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct uncore_event_desc snbep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc snbep_uncore_qpi_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), + INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), + { /* end: all zeroes */ }, +}; + +static struct attribute_group snbep_uncore_format_group = { + .name = "format", + .attrs = snbep_uncore_formats_attr, +}; + +static struct attribute_group snbep_uncore_ubox_format_group = { + .name = "format", + .attrs = snbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group snbep_uncore_cbox_format_group = { + .name = "format", + .attrs = snbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group snbep_uncore_pcu_format_group = { + .name = "format", + .attrs = snbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group snbep_uncore_qpi_format_group = { + .name = "format", + .attrs = snbep_uncore_qpi_formats_attr, +}; + +#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops snbep_uncore_msr_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + +static struct intel_uncore_ops snbep_uncore_pci_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ +}; + +static struct event_constraint snbep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x04, 0x3), + UNCORE_EVENT_CONSTRAINT(0x05, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), + EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x30, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_ubox_format_group, +}; + +static struct extra_reg snbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), + EVENT_EXTRA_END +}; + +static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i; + + if (uncore_box_is_fake(box)) + return; + + for (i = 0; i < 5; i++) { + if (reg1->alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + reg1->alloc = 0; +} + +static struct event_constraint * +__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, + u64 (*cbox_filter_mask)(int fields)) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i, alloc = 0; + unsigned long flags; + u64 mask; + + if (reg1->idx == EXTRA_REG_NONE) + return NULL; + + raw_spin_lock_irqsave(&er->lock, flags); + for (i = 0; i < 5; i++) { + if (!(reg1->idx & (0x1 << i))) + continue; + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + continue; + + mask = cbox_filter_mask(0x1 << i); + if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || + !((reg1->config ^ er->config) & mask)) { + atomic_add(1 << (i * 6), &er->ref); + er->config &= ~mask; + er->config |= reg1->config & mask; + alloc |= (0x1 << i); + } else { + break; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + if (i < 5) + goto fail; + + if (!uncore_box_is_fake(box)) + reg1->alloc |= alloc; + + return NULL; +fail: + for (; i >= 0; i--) { + if (alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + return &uncore_constraint_empty; +} + +static u64 snbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x4) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); +} + +static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_cbox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_cbox_hw_config, + .get_constraint = snbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &snbep_uncore_cbox_ops, + .format_group = &snbep_uncore_cbox_format_group, +}; + +static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 config = reg1->config; + + if (new_idx > reg1->idx) + config <<= 8 * (new_idx - reg1->idx); + else + config >>= 8 * (reg1->idx - new_idx); + + if (modify) { + hwc->config += new_idx - reg1->idx; + reg1->config = config; + reg1->idx = new_idx; + } + return config; +} + +static struct event_constraint * +snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + unsigned long flags; + int idx = reg1->idx; + u64 mask, config1 = reg1->config; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; +again: + mask = 0xffULL << (idx * 8); + raw_spin_lock_irqsave(&er->lock, flags); + if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || + !((config1 ^ er->config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + idx = (idx + 1) % 4; + if (idx != reg1->idx) { + config1 = snbep_pcu_alter_er(event, idx, false); + goto again; + } + return &uncore_constraint_empty; + } + + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx) + snbep_pcu_alter_er(event, idx, true); + reg1->alloc = 1; + } + return NULL; +} + +static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + atomic_sub(1 << (reg1->idx * 8), &er->ref); + reg1->alloc = 0; +} + +static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << (reg1->idx * 8)); + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *snbep_msr_uncores[] = { + &snbep_uncore_ubox, + &snbep_uncore_cbox, + &snbep_uncore_pcu, + NULL, +}; + +void snbep_uncore_cpu_init(void) +{ + if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = snbep_msr_uncores; +} + +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx]; + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +#define SNBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &snbep_uncore_pci_ops, \ + .format_group = &snbep_uncore_format_group + +static struct intel_uncore_type snbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, +}; + + +static struct intel_uncore_type snbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + SNBEP_PCI_UNCORE_HA, + SNBEP_PCI_UNCORE_IMC, + SNBEP_PCI_UNCORE_QPI, + SNBEP_PCI_UNCORE_R2PCIE, + SNBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *snbep_pci_uncores[] = { + [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, + [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, + [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, + [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, + [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id snbep_uncore_pci_ids[] = { + { /* Home Agent */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), + }, + { /* MC Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), + }, + { /* QPI Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snbep_uncore_pci_driver = { + .name = "snbep_uncore", + .id_table = snbep_uncore_pci_ids, +}; + +/* + * build pci bus to socket mapping + */ +static int snbep_pci2phy_map_init(int devid) +{ + struct pci_dev *ubox_dev = NULL; + int i, bus, nodeid; + int err = 0; + u32 config = 0; + + while (1) { + /* find the UBOX device */ + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); + if (!ubox_dev) + break; + bus = ubox_dev->bus->number; + /* get the Node ID of the local register */ + err = pci_read_config_dword(ubox_dev, 0x40, &config); + if (err) + break; + nodeid = config; + /* get the Node ID mapping */ + err = pci_read_config_dword(ubox_dev, 0x54, &config); + if (err) + break; + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + uncore_pcibus_to_physid[bus] = i; + break; + } + } + } + + if (!err) { + /* + * For PCI bus with no UBOX device, find the next bus + * that has UBOX device and use its mapping. + */ + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (uncore_pcibus_to_physid[bus] >= 0) + i = uncore_pcibus_to_physid[bus]; + else + uncore_pcibus_to_physid[bus] = i; + } + } + + if (ubox_dev) + pci_dev_put(ubox_dev); + + return err ? pcibios_err_to_errno(err) : 0; +} + +int snbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x3ce0); + if (ret) + return ret; + uncore_pci_uncores = snbep_pci_uncores; + uncore_pci_driver = &snbep_uncore_pci_driver; + return 0; +} +/* end of Sandy Bridge-EP uncore support */ + +/* IvyTown uncore support */ +static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT); +} + +static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT); +} + +#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = ivbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops ivbep_uncore_msr_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +static struct intel_uncore_ops ivbep_uncore_pci_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +#define IVBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &ivbep_uncore_pci_ops, \ + .format_group = &ivbep_uncore_format_group + +static struct attribute *ivbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_link.attr, + &format_attr_filter_state2.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct attribute_group ivbep_uncore_format_group = { + .name = "format", + .attrs = ivbep_uncore_formats_attr, +}; + +static struct attribute_group ivbep_uncore_ubox_format_group = { + .name = "format", + .attrs = ivbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_cbox_format_group = { + .name = "format", + .attrs = ivbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_pcu_format_group = { + .name = "format", + .attrs = ivbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group ivbep_uncore_qpi_format_group = { + .name = "format", + .attrs = ivbep_uncore_qpi_formats_attr, +}; + +static struct intel_uncore_type ivbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = IVBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct extra_reg ivbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + EVENT_EXTRA_END +}; + +static u64 ivbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + + return mask; +} + +static struct event_constraint * +ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask); +} + +static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 6, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops ivbep_uncore_cbox_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = ivbep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = ivbep_cbox_hw_config, + .get_constraint = ivbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 15, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &ivbep_uncore_cbox_ops, + .format_group = &ivbep_uncore_cbox_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_pcu_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_pcu_ops, + .format_group = &ivbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *ivbep_msr_uncores[] = { + &ivbep_uncore_ubox, + &ivbep_uncore_cbox, + &ivbep_uncore_pcu, + NULL, +}; + +void ivbep_uncore_cpu_init(void) +{ + if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = ivbep_msr_uncores; +} + +static struct intel_uncore_type ivbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +/* registers in IRP boxes are not properly aligned */ +static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; +static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; + +static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], + hwc->config | SNBEP_PMON_CTL_EN); +} + +static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config); +} + +static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops ivbep_uncore_irp_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = ivbep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type ivbep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_irp_ops, + .format_group = &ivbep_uncore_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_qpi_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_qpi_enable_event, + .read_counter = snbep_uncore_pci_read_counter, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_qpi_ops, + .format_group = &ivbep_uncore_qpi_format_group, +}; + +static struct intel_uncore_type ivbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + IVBEP_PCI_UNCORE_HA, + IVBEP_PCI_UNCORE_IMC, + IVBEP_PCI_UNCORE_IRP, + IVBEP_PCI_UNCORE_QPI, + IVBEP_PCI_UNCORE_R2PCIE, + IVBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *ivbep_pci_uncores[] = { + [IVBEP_PCI_UNCORE_HA] = &ivbep_uncore_ha, + [IVBEP_PCI_UNCORE_IMC] = &ivbep_uncore_imc, + [IVBEP_PCI_UNCORE_IRP] = &ivbep_uncore_irp, + [IVBEP_PCI_UNCORE_QPI] = &ivbep_uncore_qpi, + [IVBEP_PCI_UNCORE_R2PCIE] = &ivbep_uncore_r2pcie, + [IVBEP_PCI_UNCORE_R3QPI] = &ivbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id ivbep_uncore_pci_ids[] = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver ivbep_uncore_pci_driver = { + .name = "ivbep_uncore", + .id_table = ivbep_uncore_pci_ids, +}; + +int ivbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x0e1e); + if (ret) + return ret; + uncore_pci_uncores = ivbep_pci_uncores; + uncore_pci_driver = &ivbep_uncore_pci_driver; + return 0; +} +/* end of IvyTown uncore support */ + +/* Haswell-EP uncore support */ +static struct attribute *hswep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_filter_tid2.attr, + &format_attr_filter_cid.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_ubox_format_group = { + .name = "format", + .attrs = hswep_uncore_ubox_formats_attr, +}; + +static int hswep_ubox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + reg1->reg = HSWEP_U_MSR_PMON_FILTER; + reg1->config = event->attr.config1 & HSWEP_U_MSR_PMON_BOX_FILTER_MASK; + reg1->idx = 0; + return 0; +} + +static struct intel_uncore_ops hswep_uncore_ubox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_ubox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_ubox_ops, + .format_group = &hswep_uncore_ubox_format_group, +}; + +static struct attribute *hswep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid3.attr, + &format_attr_filter_link2.attr, + &format_attr_filter_state3.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_cbox_format_group = { + .name = "format", + .attrs = hswep_uncore_cbox_formats_attr, +}; + +static struct event_constraint hswep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x09, 0x1), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg hswep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4028, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4032, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4029, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4033, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x402A, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x12), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + EVENT_EXTRA_END +}; + +static u64 hswep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + if (fields & 0x1) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + return mask; +} + +static struct event_constraint * +hswep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, hswep_cbox_filter_mask); +} + +static int hswep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = hswep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & hswep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 1, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops hswep_uncore_cbox_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = hswep_cbox_hw_config, + .get_constraint = hswep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 18, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = hswep_uncore_cbox_constraints, + .ops = &hswep_uncore_cbox_ops, + .format_group = &hswep_uncore_cbox_format_group, +}; + +static struct attribute *hswep_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_sbox_format_group = { + .name = "format", + .attrs = hswep_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_type hswep_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &snbep_uncore_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +static int hswep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = HSWEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << reg1->idx); + } + return 0; +} + +static struct intel_uncore_ops hswep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *hswep_msr_uncores[] = { + &hswep_uncore_ubox, + &hswep_uncore_cbox, + &hswep_uncore_sbox, + &hswep_uncore_pcu, + NULL, +}; + +void hswep_uncore_cpu_init(void) +{ + if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = hswep_msr_uncores; +} + +static struct intel_uncore_type hswep_uncore_ha = { + .name = "ha", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct uncore_event_desc hswep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type hswep_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_ops hswep_uncore_irp_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = ivbep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type hswep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &hswep_uncore_irp_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type hswep_uncore_qpi = { + .name = "qpi", + .num_counters = 5, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; + +static struct event_constraint hswep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x1), + UNCORE_EVENT_CONSTRAINT(0x24, 0x1), + UNCORE_EVENT_CONSTRAINT(0x25, 0x1), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x27, 0x1), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x1), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = hswep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct event_constraint hswep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 44, + .constraints = hswep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + HSWEP_PCI_UNCORE_HA, + HSWEP_PCI_UNCORE_IMC, + HSWEP_PCI_UNCORE_IRP, + HSWEP_PCI_UNCORE_QPI, + HSWEP_PCI_UNCORE_R2PCIE, + HSWEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *hswep_pci_uncores[] = { + [HSWEP_PCI_UNCORE_HA] = &hswep_uncore_ha, + [HSWEP_PCI_UNCORE_IMC] = &hswep_uncore_imc, + [HSWEP_PCI_UNCORE_IRP] = &hswep_uncore_irp, + [HSWEP_PCI_UNCORE_QPI] = &hswep_uncore_qpi, + [HSWEP_PCI_UNCORE_R2PCIE] = &hswep_uncore_r2pcie, + [HSWEP_PCI_UNCORE_R3QPI] = &hswep_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f38), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f39), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f32), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f33), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3a), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f34), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f36), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f37), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3e), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver hswep_uncore_pci_driver = { + .name = "hswep_uncore", + .id_table = hswep_uncore_pci_ids, +}; + +int hswep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x2f1e); + if (ret) + return ret; + uncore_pci_uncores = hswep_pci_uncores; + uncore_pci_driver = &hswep_uncore_pci_driver; + return 0; +} +/* end of Haswell-EP uncore support */ |