x86, perf: Add raw events support for the P4 PMU

The adding of raw event support lead to complete code
refactoring. I hope is became more readable then it was.

The list of changes:

1)  The 64bit config field is enough to hold all information we need
    to track event details. To achieve it we used *own* enum for
    events selection in ESCR register and map this key into proper
    value at moment of event enabling.

    For the same reason we use 12LSB bits in CCCR register -- to track
    which exactly cache trace event was requested. And we cear this bits
    at real 'write' moment.

2)  There is no per-cpu area reserved for P4 PMU anymore. We
    don't need it. All is held by config.

3)  Now we may use any available counter, ie we try to grab any
    possible counter.

v2:
  - Lin Ming reported the lack of ESCR selector in CCCR for cache events

v3:
  - Don't loose cache event codes at config unpacking procedure, we may
    need it one day so no obscure hack behind our back, better to clear
    reserved bits explicitly when needed (thanks Ming for pointing out)

  - Lin Ming fixed misplaced opcodes in cache events

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Tested-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1269403766.3409.6.camel@minggr.sh.intel.com>
[ v4: did a few whitespace fixlets ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 806 insertions, 631 deletions

diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index facf96186b26..b05400a542ff 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -15,38 +15,40 @@
  * perf-MSRs are not shared and every thread has its
  * own perf-MSRs set)
  */
-#define ARCH_P4_TOTAL_ESCR		(46)
-#define ARCH_P4_RESERVED_ESCR		(2) /* IQ_ESCR(0,1) not always present */
-#define ARCH_P4_MAX_ESCR		(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
-#define ARCH_P4_MAX_CCCR		(18)
-#define ARCH_P4_MAX_COUNTER		(ARCH_P4_MAX_CCCR / 2)
-
-#define P4_EVNTSEL_EVENT_MASK		0x7e000000U
-#define P4_EVNTSEL_EVENT_SHIFT		25
-#define P4_EVNTSEL_EVENTMASK_MASK	0x01fffe00U
-#define P4_EVNTSEL_EVENTMASK_SHIFT	9
-#define P4_EVNTSEL_TAG_MASK		0x000001e0U
-#define P4_EVNTSEL_TAG_SHIFT		5
-#define P4_EVNTSEL_TAG_ENABLE		0x00000010U
-#define P4_EVNTSEL_T0_OS		0x00000008U
-#define P4_EVNTSEL_T0_USR		0x00000004U
-#define P4_EVNTSEL_T1_OS		0x00000002U
-#define P4_EVNTSEL_T1_USR		0x00000001U
+#define ARCH_P4_TOTAL_ESCR	(46)
+#define ARCH_P4_RESERVED_ESCR	(2) /* IQ_ESCR(0,1) not always present */
+#define ARCH_P4_MAX_ESCR	(ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR)
+#define ARCH_P4_MAX_CCCR	(18)
+#define ARCH_P4_MAX_COUNTER	(ARCH_P4_MAX_CCCR / 2)
+
+#define P4_ESCR_EVENT_MASK	0x7e000000U
+#define P4_ESCR_EVENT_SHIFT	25
+#define P4_ESCR_EVENTMASK_MASK	0x01fffe00U
+#define P4_ESCR_EVENTMASK_SHIFT	9
+#define P4_ESCR_TAG_MASK	0x000001e0U
+#define P4_ESCR_TAG_SHIFT	5
+#define P4_ESCR_TAG_ENABLE	0x00000010U
+#define P4_ESCR_T0_OS		0x00000008U
+#define P4_ESCR_T0_USR		0x00000004U
+#define P4_ESCR_T1_OS		0x00000002U
+#define P4_ESCR_T1_USR		0x00000001U
+
+#define P4_ESCR_EVENT(v)	((v) << P4_ESCR_EVENT_SHIFT)
+#define P4_ESCR_EMASK(v)	((v) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_TAG(v)		((v) << P4_ESCR_TAG_SHIFT)
 
 /* Non HT mask */
-#define P4_EVNTSEL_MASK				\
-	(P4_EVNTSEL_EVENT_MASK		|	\
-	P4_EVNTSEL_EVENTMASK_MASK	|	\
-	P4_EVNTSEL_TAG_MASK		|	\
-	P4_EVNTSEL_TAG_ENABLE		|	\
-	P4_EVNTSEL_T0_OS		|	\
-	P4_EVNTSEL_T0_USR)
+#define P4_ESCR_MASK			\
+	(P4_ESCR_EVENT_MASK	|	\
+	P4_ESCR_EVENTMASK_MASK	|	\
+	P4_ESCR_TAG_MASK	|	\
+	P4_ESCR_TAG_ENABLE	|	\
+	P4_ESCR_T0_OS		|	\
+	P4_ESCR_T0_USR)
 
 /* HT mask */
-#define P4_EVNTSEL_MASK_HT			\
-	(P4_EVNTSEL_MASK		|	\
-	P4_EVNTSEL_T1_OS		|	\
-	P4_EVNTSEL_T1_USR)
+#define P4_ESCR_MASK_HT			\
+	(P4_ESCR_MASK |	P4_ESCR_T1_OS | P4_ESCR_T1_USR)
 
 #define P4_CCCR_OVF			0x80000000U
 #define P4_CCCR_CASCADE			0x40000000U
@@ -56,7 +58,6 @@
 #define P4_CCCR_EDGE			0x01000000U
 #define P4_CCCR_THRESHOLD_MASK		0x00f00000U
 #define P4_CCCR_THRESHOLD_SHIFT		20
-#define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
 #define P4_CCCR_COMPLEMENT		0x00080000U
 #define P4_CCCR_COMPARE			0x00040000U
 #define P4_CCCR_ESCR_SELECT_MASK	0x0000e000U
@@ -67,6 +68,13 @@
 #define P4_CCCR_THREAD_ANY		0x00030000U
 #define P4_CCCR_RESERVED		0x00000fffU
 
+#define P4_CCCR_THRESHOLD(v)		((v) << P4_CCCR_THRESHOLD_SHIFT)
+#define P4_CCCR_ESEL(v)			((v) << P4_CCCR_ESCR_SELECT_SHIFT)
+
+/* Custom bits in reerved CCCR area */
+#define P4_CCCR_CACHE_OPS_MASK		0x0000003fU
+
+
 /* Non HT mask */
 #define P4_CCCR_MASK				\
 	(P4_CCCR_OVF			|	\
@@ -81,25 +89,11 @@
 	P4_CCCR_ENABLE)
 
 /* HT mask */
-#define P4_CCCR_MASK_HT				\
-	(P4_CCCR_MASK			|	\
-	P4_CCCR_THREAD_ANY)
+#define P4_CCCR_MASK_HT	(P4_CCCR_MASK | P4_CCCR_THREAD_ANY)
 
-/*
- * format is 32 bit: ee ss aa aa
- * where
- *	ee - 8 bit event
- *	ss - 8 bit selector
- *	aa aa - 16 bits reserved for tags/attributes
- */
-#define P4_EVENT_PACK(event, selector)		(((event) << 24) | ((selector) << 16))
-#define P4_EVENT_UNPACK_EVENT(packed)		(((packed) >> 24) & 0xff)
-#define P4_EVENT_UNPACK_SELECTOR(packed)	(((packed) >> 16) & 0xff)
-#define P4_EVENT_PACK_ATTR(attr)		((attr))
-#define P4_EVENT_UNPACK_ATTR(packed)		((packed) & 0xffff)
-#define P4_MAKE_EVENT_ATTR(class, name, bit)	class##_##name = (1 << bit)
-#define P4_EVENT_ATTR(class, name)		class##_##name
-#define P4_EVENT_ATTR_STR(class, name)		__stringify(class##_##name)
+#define P4_GEN_ESCR_EMASK(class, name, bit)	\
+	class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT)
+#define P4_ESCR_EMASK_BIT(class, name)		class##__##name
 
 /*
  * config field is 64bit width and consists of
@@ -117,35 +111,29 @@
 #define p4_config_pack_escr(v)		(((u64)(v)) << 32)
 #define p4_config_pack_cccr(v)		(((u64)(v)) & 0xffffffffULL)
 #define p4_config_unpack_escr(v)	(((u64)(v)) >> 32)
-#define p4_config_unpack_cccr(v)	(((u64)(v)) & 0xfffff000ULL)
+#define p4_config_unpack_cccr(v)	(((u64)(v)) & 0xffffffffULL)
 
 #define p4_config_unpack_emask(v)			\
 	({						\
 		u32 t = p4_config_unpack_escr((v));	\
-		t  &= P4_EVNTSEL_EVENTMASK_MASK;	\
-		t >>= P4_EVNTSEL_EVENTMASK_SHIFT;	\
+		t = t &  P4_ESCR_EVENTMASK_MASK;	\
+		t = t >> P4_ESCR_EVENTMASK_SHIFT;	\
+		t;					\
+	})
+
+#define p4_config_unpack_event(v)			\
+	({						\
+		u32 t = p4_config_unpack_escr((v));	\
+		t = t &  P4_ESCR_EVENT_MASK;		\
+		t = t >> P4_ESCR_EVENT_SHIFT;		\
 		t;					\
 	})
 
-#define p4_config_unpack_key(v)		(((u64)(v)) & P4_CCCR_RESERVED)
+#define p4_config_unpack_cache_event(v)	(((u64)(v)) & P4_CCCR_CACHE_OPS_MASK)
 
 #define P4_CONFIG_HT_SHIFT		63
 #define P4_CONFIG_HT			(1ULL << P4_CONFIG_HT_SHIFT)
 
-static inline u32 p4_config_unpack_opcode(u64 config)
-{
-	u32 e, s;
-
-	/*
-	 * we don't care about HT presence here since
-	 * event opcode doesn't depend on it
-	 */
-	e = (p4_config_unpack_escr(config) & P4_EVNTSEL_EVENT_MASK) >> P4_EVNTSEL_EVENT_SHIFT;
-	s = (p4_config_unpack_cccr(config) & P4_CCCR_ESCR_SELECT_MASK) >> P4_CCCR_ESCR_SELECT_SHIFT;
-
-	return P4_EVENT_PACK(e, s);
-}
-
 static inline bool p4_is_event_cascaded(u64 config)
 {
 	u32 cccr = p4_config_unpack_cccr(config);
@@ -212,19 +200,73 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
 
 	if (!p4_ht_thread(cpu)) {
 		if (!exclude_os)
-			escr |= P4_EVNTSEL_T0_OS;
+			escr |= P4_ESCR_T0_OS;
 		if (!exclude_usr)
-			escr |= P4_EVNTSEL_T0_USR;
+			escr |= P4_ESCR_T0_USR;
 	} else {
 		if (!exclude_os)
-			escr |= P4_EVNTSEL_T1_OS;
+			escr |= P4_ESCR_T1_OS;
 		if (!exclude_usr)
-			escr |= P4_EVNTSEL_T1_USR;
+			escr |= P4_ESCR_T1_USR;
 	}
 
 	return escr;
 }
 
+enum P4_EVENTS {
+	P4_EVENT_TC_DELIVER_MODE,
+	P4_EVENT_BPU_FETCH_REQUEST,
+	P4_EVENT_ITLB_REFERENCE,
+	P4_EVENT_MEMORY_CANCEL,
+	P4_EVENT_MEMORY_COMPLETE,
+	P4_EVENT_LOAD_PORT_REPLAY,
+	P4_EVENT_STORE_PORT_REPLAY,
+	P4_EVENT_MOB_LOAD_REPLAY,
+	P4_EVENT_PAGE_WALK_TYPE,
+	P4_EVENT_BSQ_CACHE_REFERENCE,
+	P4_EVENT_IOQ_ALLOCATION,
+	P4_EVENT_IOQ_ACTIVE_ENTRIES,
+	P4_EVENT_FSB_DATA_ACTIVITY,
+	P4_EVENT_BSQ_ALLOCATION,
+	P4_EVENT_BSQ_ACTIVE_ENTRIES,
+	P4_EVENT_SSE_INPUT_ASSIST,
+	P4_EVENT_PACKED_SP_UOP,
+	P4_EVENT_PACKED_DP_UOP,
+	P4_EVENT_SCALAR_SP_UOP,
+	P4_EVENT_SCALAR_DP_UOP,
+	P4_EVENT_64BIT_MMX_UOP,
+	P4_EVENT_128BIT_MMX_UOP,
+	P4_EVENT_X87_FP_UOP,
+	P4_EVENT_TC_MISC,
+	P4_EVENT_GLOBAL_POWER_EVENTS,
+	P4_EVENT_TC_MS_XFER,
+	P4_EVENT_UOP_QUEUE_WRITES,
+	P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE,
+	P4_EVENT_RETIRED_BRANCH_TYPE,
+	P4_EVENT_RESOURCE_STALL,
+	P4_EVENT_WC_BUFFER,
+	P4_EVENT_B2B_CYCLES,
+	P4_EVENT_BNR,
+	P4_EVENT_SNOOP,
+	P4_EVENT_RESPONSE,
+	P4_EVENT_FRONT_END_EVENT,
+	P4_EVENT_EXECUTION_EVENT,
+	P4_EVENT_REPLAY_EVENT,
+	P4_EVENT_INSTR_RETIRED,
+	P4_EVENT_UOPS_RETIRED,
+	P4_EVENT_UOP_TYPE,
+	P4_EVENT_BRANCH_RETIRED,
+	P4_EVENT_MISPRED_BRANCH_RETIRED,
+	P4_EVENT_X87_ASSIST,
+	P4_EVENT_MACHINE_CLEAR,
+	P4_EVENT_INSTR_COMPLETED,
+};
+
+#define P4_OPCODE(event)		event##_OPCODE
+#define P4_OPCODE_ESEL(opcode)		((opcode & 0x00ff) >> 0)
+#define P4_OPCODE_EVNT(opcode)		((opcode & 0xff00) >> 8)
+#define P4_OPCODE_PACK(event, sel)	(((event) << 8) | sel)
+
 /*
  * Comments below the event represent ESCR restriction
  * for this event and counter index per ESCR
@@ -238,484 +280,515 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr)
  * working so that we should not use this CCCR and respective
  * counter as result
  */
-#define P4_TC_DELIVER_MODE		P4_EVENT_PACK(0x01, 0x01)
+enum P4_EVENT_OPCODES {
+	P4_OPCODE(P4_EVENT_TC_DELIVER_MODE)		= P4_OPCODE_PACK(0x01, 0x01),
 	/*
 	 * MSR_P4_TC_ESCR0:	4, 5
 	 * MSR_P4_TC_ESCR1:	6, 7
 	 */
 
-#define P4_BPU_FETCH_REQUEST		P4_EVENT_PACK(0x03, 0x00)
+	P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST)		= P4_OPCODE_PACK(0x03, 0x00),
 	/*
 	 * MSR_P4_BPU_ESCR0:	0, 1
 	 * MSR_P4_BPU_ESCR1:	2, 3
 	 */
 
-#define P4_ITLB_REFERENCE		P4_EVENT_PACK(0x18, 0x03)
+	P4_OPCODE(P4_EVENT_ITLB_REFERENCE)		= P4_OPCODE_PACK(0x18, 0x03),
 	/*
 	 * MSR_P4_ITLB_ESCR0:	0, 1
 	 * MSR_P4_ITLB_ESCR1:	2, 3
 	 */
 
-#define P4_MEMORY_CANCEL		P4_EVENT_PACK(0x02, 0x05)
+	P4_OPCODE(P4_EVENT_MEMORY_CANCEL)		= P4_OPCODE_PACK(0x02, 0x05),
 	/*
 	 * MSR_P4_DAC_ESCR0:	8, 9
 	 * MSR_P4_DAC_ESCR1:	10, 11
 	 */
 
-#define P4_MEMORY_COMPLETE		P4_EVENT_PACK(0x08, 0x02)
+	P4_OPCODE(P4_EVENT_MEMORY_COMPLETE)		= P4_OPCODE_PACK(0x08, 0x02),
 	/*
 	 * MSR_P4_SAAT_ESCR0:	8, 9
 	 * MSR_P4_SAAT_ESCR1:	10, 11
 	 */
 
-#define P4_LOAD_PORT_REPLAY		P4_EVENT_PACK(0x04, 0x02)
+	P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY)		= P4_OPCODE_PACK(0x04, 0x02),
 	/*
 	 * MSR_P4_SAAT_ESCR0:	8, 9
 	 * MSR_P4_SAAT_ESCR1:	10, 11
 	 */
 
-#define P4_STORE_PORT_REPLAY		P4_EVENT_PACK(0x05, 0x02)
+	P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY)		= P4_OPCODE_PACK(0x05, 0x02),
 	/*
 	 * MSR_P4_SAAT_ESCR0:	8, 9
 	 * MSR_P4_SAAT_ESCR1:	10, 11
 	 */
 
-#define P4_MOB_LOAD_REPLAY		P4_EVENT_PACK(0x03, 0x02)
+	P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY)		= P4_OPCODE_PACK(0x03, 0x02),
 	/*
 	 * MSR_P4_MOB_ESCR0:	0, 1
 	 * MSR_P4_MOB_ESCR1:	2, 3
 	 */
 
-#define P4_PAGE_WALK_TYPE		P4_EVENT_PACK(0x01, 0x04)
+	P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE)		= P4_OPCODE_PACK(0x01, 0x04),
 	/*
 	 * MSR_P4_PMH_ESCR0:	0, 1
 	 * MSR_P4_PMH_ESCR1:	2, 3
 	 */
 
-#define P4_BSQ_CACHE_REFERENCE		P4_EVENT_PACK(0x0c, 0x07)
+	P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE)		= P4_OPCODE_PACK(0x0c, 0x07),
 	/*
 	 * MSR_P4_BSU_ESCR0:	0, 1
 	 * MSR_P4_BSU_ESCR1:	2, 3
 	 */
 
-#define P4_IOQ_ALLOCATION		P4_EVENT_PACK(0x03, 0x06)
+	P4_OPCODE(P4_EVENT_IOQ_ALLOCATION)		= P4_OPCODE_PACK(0x03, 0x06),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_IOQ_ACTIVE_ENTRIES		P4_EVENT_PACK(0x1a, 0x06)
+	P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x1a, 0x06),
 	/*
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_FSB_DATA_ACTIVITY		P4_EVENT_PACK(0x17, 0x06)
+	P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY)		= P4_OPCODE_PACK(0x17, 0x06),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_BSQ_ALLOCATION		P4_EVENT_PACK(0x05, 0x07)
+	P4_OPCODE(P4_EVENT_BSQ_ALLOCATION)		= P4_OPCODE_PACK(0x05, 0x07),
 	/*
 	 * MSR_P4_BSU_ESCR0:	0, 1
 	 */
 
-#define P4_BSQ_ACTIVE_ENTRIES		P4_EVENT_PACK(0x06, 0x07)
+	P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES)		= P4_OPCODE_PACK(0x06, 0x07),
 	/*
 	 * NOTE: no ESCR name in docs, it's guessed
 	 * MSR_P4_BSU_ESCR1:	2, 3
 	 */
 
-#define P4_SSE_INPUT_ASSIST		P4_EVENT_PACK(0x34, 0x01)
+	P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST)		= P4_OPCODE_PACK(0x34, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_PACKED_SP_UOP		P4_EVENT_PACK(0x08, 0x01)
+	P4_OPCODE(P4_EVENT_PACKED_SP_UOP)		= P4_OPCODE_PACK(0x08, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_PACKED_DP_UOP		P4_EVENT_PACK(0x0c, 0x01)
+	P4_OPCODE(P4_EVENT_PACKED_DP_UOP)		= P4_OPCODE_PACK(0x0c, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_SCALAR_SP_UOP		P4_EVENT_PACK(0x0a, 0x01)
+	P4_OPCODE(P4_EVENT_SCALAR_SP_UOP)		= P4_OPCODE_PACK(0x0a, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_SCALAR_DP_UOP		P4_EVENT_PACK(0x0e, 0x01)
+	P4_OPCODE(P4_EVENT_SCALAR_DP_UOP)		= P4_OPCODE_PACK(0x0e, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_64BIT_MMX_UOP		P4_EVENT_PACK(0x02, 0x01)
+	P4_OPCODE(P4_EVENT_64BIT_MMX_UOP)		= P4_OPCODE_PACK(0x02, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_128BIT_MMX_UOP		P4_EVENT_PACK(0x1a, 0x01)
+	P4_OPCODE(P4_EVENT_128BIT_MMX_UOP)		= P4_OPCODE_PACK(0x1a, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_X87_FP_UOP			P4_EVENT_PACK(0x04, 0x01)
+	P4_OPCODE(P4_EVENT_X87_FP_UOP)			= P4_OPCODE_PACK(0x04, 0x01),
 	/*
 	 * MSR_P4_FIRM_ESCR0:	8, 9
 	 * MSR_P4_FIRM_ESCR1:	10, 11
 	 */
 
-#define P4_TC_MISC			P4_EVENT_PACK(0x06, 0x01)
+	P4_OPCODE(P4_EVENT_TC_MISC)			= P4_OPCODE_PACK(0x06, 0x01),
 	/*
 	 * MSR_P4_TC_ESCR0:	4, 5
 	 * MSR_P4_TC_ESCR1:	6, 7
 	 */
 
-#define P4_GLOBAL_POWER_EVENTS		P4_EVENT_PACK(0x13, 0x06)
+	P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS)		= P4_OPCODE_PACK(0x13, 0x06),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_TC_MS_XFER			P4_EVENT_PACK(0x05, 0x00)
+	P4_OPCODE(P4_EVENT_TC_MS_XFER)			= P4_OPCODE_PACK(0x05, 0x00),
 	/*
 	 * MSR_P4_MS_ESCR0:	4, 5
 	 * MSR_P4_MS_ESCR1:	6, 7
 	 */
 
-#define P4_UOP_QUEUE_WRITES		P4_EVENT_PACK(0x09, 0x00)
+	P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES)		= P4_OPCODE_PACK(0x09, 0x00),
 	/*
 	 * MSR_P4_MS_ESCR0:	4, 5
 	 * MSR_P4_MS_ESCR1:	6, 7
 	 */
 
-#define P4_RETIRED_MISPRED_BRANCH_TYPE	P4_EVENT_PACK(0x05, 0x02)
+	P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE)	= P4_OPCODE_PACK(0x05, 0x02),
 	/*
 	 * MSR_P4_TBPU_ESCR0:	4, 5
 	 * MSR_P4_TBPU_ESCR1:	6, 7
 	 */
 
-#define P4_RETIRED_BRANCH_TYPE		P4_EVENT_PACK(0x04, 0x02)
+	P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE)		= P4_OPCODE_PACK(0x04, 0x02),
 	/*
 	 * MSR_P4_TBPU_ESCR0:	4, 5
 	 * MSR_P4_TBPU_ESCR1:	6, 7
 	 */
 
-#define P4_RESOURCE_STALL		P4_EVENT_PACK(0x01, 0x01)
+	P4_OPCODE(P4_EVENT_RESOURCE_STALL)		= P4_OPCODE_PACK(0x01, 0x01),
 	/*
 	 * MSR_P4_ALF_ESCR0:	12, 13, 16
 	 * MSR_P4_ALF_ESCR1:	14, 15, 17
 	 */
 
-#define P4_WC_BUFFER			P4_EVENT_PACK(0x05, 0x05)
+	P4_OPCODE(P4_EVENT_WC_BUFFER)			= P4_OPCODE_PACK(0x05, 0x05),
 	/*
 	 * MSR_P4_DAC_ESCR0:	8, 9
 	 * MSR_P4_DAC_ESCR1:	10, 11
 	 */
 
-#define P4_B2B_CYCLES			P4_EVENT_PACK(0x16, 0x03)
+	P4_OPCODE(P4_EVENT_B2B_CYCLES)			= P4_OPCODE_PACK(0x16, 0x03),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_BNR				P4_EVENT_PACK(0x08, 0x03)
+	P4_OPCODE(P4_EVENT_BNR)				= P4_OPCODE_PACK(0x08, 0x03),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_SNOOP			P4_EVENT_PACK(0x06, 0x03)
+	P4_OPCODE(P4_EVENT_SNOOP)			= P4_OPCODE_PACK(0x06, 0x03),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_RESPONSE			P4_EVENT_PACK(0x04, 0x03)
+	P4_OPCODE(P4_EVENT_RESPONSE)			= P4_OPCODE_PACK(0x04, 0x03),
 	/*
 	 * MSR_P4_FSB_ESCR0:	0, 1
 	 * MSR_P4_FSB_ESCR1:	2, 3
 	 */
 
-#define P4_FRONT_END_EVENT		P4_EVENT_PACK(0x08, 0x05)
+	P4_OPCODE(P4_EVENT_FRONT_END_EVENT)		= P4_OPCODE_PACK(0x08, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_EXECUTION_EVENT		P4_EVENT_PACK(0x0c, 0x05)
+	P4_OPCODE(P4_EVENT_EXECUTION_EVENT)		= P4_OPCODE_PACK(0x0c, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_REPLAY_EVENT			P4_EVENT_PACK(0x09, 0x05)
+	P4_OPCODE(P4_EVENT_REPLAY_EVENT)		= P4_OPCODE_PACK(0x09, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_INSTR_RETIRED		P4_EVENT_PACK(0x02, 0x04)
+	P4_OPCODE(P4_EVENT_INSTR_RETIRED)		= P4_OPCODE_PACK(0x02, 0x04),
 	/*
 	 * MSR_P4_CRU_ESCR0:	12, 13, 16
 	 * MSR_P4_CRU_ESCR1:	14, 15, 17
 	 */
 
-#define P4_UOPS_RETIRED			P4_EVENT_PACK(0x01, 0x04)
+	P4_OPCODE(P4_EVENT_UOPS_RETIRED)		= P4_OPCODE_PACK(0x01, 0x04),
 	/*
 	 * MSR_P4_CRU_ESCR0:	12, 13, 16
 	 * MSR_P4_CRU_ESCR1:	14, 15, 17
 	 */
 
-#define P4_UOP_TYPE			P4_EVENT_PACK(0x02, 0x02)
+	P4_OPCODE(P4_EVENT_UOP_TYPE)			= P4_OPCODE_PACK(0x02, 0x02),
 	/*
 	 * MSR_P4_RAT_ESCR0:	12, 13, 16
 	 * MSR_P4_RAT_ESCR1:	14, 15, 17
 	 */
 
-#define P4_BRANCH_RETIRED		P4_EVENT_PACK(0x06, 0x05)
+	P4_OPCODE(P4_EVENT_BRANCH_RETIRED)		= P4_OPCODE_PACK(0x06, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_MISPRED_BRANCH_RETIRED	P4_EVENT_PACK(0x03, 0x04)
+	P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED)	= P4_OPCODE_PACK(0x03, 0x04),
 	/*
 	 * MSR_P4_CRU_ESCR0:	12, 13, 16
 	 * MSR_P4_CRU_ESCR1:	14, 15, 17
 	 */
 
-#define P4_X87_ASSIST			P4_EVENT_PACK(0x03, 0x05)
+	P4_OPCODE(P4_EVENT_X87_ASSIST)			= P4_OPCODE_PACK(0x03, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_MACHINE_CLEAR		P4_EVENT_PACK(0x02, 0x05)
+	P4_OPCODE(P4_EVENT_MACHINE_CLEAR)		= P4_OPCODE_PACK(0x02, 0x05),
 	/*
 	 * MSR_P4_CRU_ESCR2:	12, 13, 16
 	 * MSR_P4_CRU_ESCR3:	14, 15, 17
 	 */
 
-#define P4_INSTR_COMPLETED		P4_EVENT_PACK(0x07, 0x04)
+	P4_OPCODE(P4_EVENT_INSTR_COMPLETED)		= P4_OPCODE_PACK(0x07, 0x04),
 	/*
 	 * MSR_P4_CRU_ESCR0:	12, 13, 16
 	 * MSR_P4_CRU_ESCR1:	14, 15, 17
 	 */
+};
 
 /*
- * a caller should use P4_EVENT_ATTR helper to
- * pick the attribute needed, for example
+ * a caller should use P4_ESCR_EMASK_NAME helper to
+ * pick the EventMask needed, for example
  *
- *	P4_EVENT_ATTR(P4_TC_DELIVER_MODE, DD)
+ *	P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD)
  */
-enum P4_EVENTS_ATTR {
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DD, 0),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DB, 1),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, DI, 2),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BD, 3),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BB, 4),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, BI, 5),
-	P4_MAKE_EVENT_ATTR(P4_TC_DELIVER_MODE, ID, 6),
-
-	P4_MAKE_EVENT_ATTR(P4_BPU_FETCH_REQUEST, TCMISS, 0),
-
-	P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, HIT, 0),
-	P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, MISS, 1),
-	P4_MAKE_EVENT_ATTR(P4_ITLB_REFERENCE, HIT_UK, 2),
-
-	P4_MAKE_EVENT_ATTR(P4_MEMORY_CANCEL, ST_RB_FULL, 2),
-	P4_MAKE_EVENT_ATTR(P4_MEMORY_CANCEL, 64K_CONF, 3),
-
-	P4_MAKE_EVENT_ATTR(P4_MEMORY_COMPLETE, LSC, 0),
-	P4_MAKE_EVENT_ATTR(P4_MEMORY_COMPLETE, SSC, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_LOAD_PORT_REPLAY, SPLIT_LD, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_STORE_PORT_REPLAY, SPLIT_ST, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, NO_STA, 1),
-	P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, NO_STD, 3),
-	P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, PARTIAL_DATA, 4),
-	P4_MAKE_EVENT_ATTR(P4_MOB_LOAD_REPLAY, UNALGN_ADDR, 5),
-
-	P4_MAKE_EVENT_ATTR(P4_PAGE_WALK_TYPE, DTMISS, 0),
-	P4_MAKE_EVENT_ATTR(P4_PAGE_WALK_TYPE, ITMISS, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10),
-
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, DEFAULT, 0),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, ALL_READ, 5),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, ALL_WRITE, 6),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_UC, 7),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WC, 8),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WT, 9),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WP, 10),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, MEM_WB, 11),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, OWN, 13),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, OTHER, 14),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ALLOCATION, PREFETCH, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, DEFAULT, 0),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, ALL_READ, 5),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_UC, 7),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WC, 8),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WT, 9),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WP, 10),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, MEM_WB, 11),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, OWN, 13),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, OTHER, 14),
-	P4_MAKE_EVENT_ATTR(P4_IOQ_ACTIVE_ENTRIES, PREFETCH, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_DRV, 0),
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OWN, 1),
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OTHER, 2),
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_DRV, 3),
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_OWN, 4),
-	P4_MAKE_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DBSY_OTHER, 5),
-
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_TYPE0, 0),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_TYPE1, 1),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LEN0, 2),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LEN1, 3),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_IO_TYPE, 5),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_DEM_TYPE, 9),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, REQ_ORD_TYPE, 10),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE0, 11),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE1, 12),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ALLOCATION, MEM_TYPE2, 13),
-
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12),
-	P4_MAKE_EVENT_ATTR(P4_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13),
-
-	P4_MAKE_EVENT_ATTR(P4_SSE_INPUT_ASSIST, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_PACKED_SP_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_PACKED_DP_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_SCALAR_SP_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_SCALAR_DP_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_64BIT_MMX_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_128BIT_MMX_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_X87_FP_UOP, ALL, 15),
-
-	P4_MAKE_EVENT_ATTR(P4_TC_MISC, FLUSH, 4),
-
-	P4_MAKE_EVENT_ATTR(P4_GLOBAL_POWER_EVENTS, RUNNING, 0),
-
-	P4_MAKE_EVENT_ATTR(P4_TC_MS_XFER, CISC, 0),
-
-	P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0),
-	P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1),
-	P4_MAKE_EVENT_ATTR(P4_UOP_QUEUE_WRITES, FROM_ROM, 2),
-
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4),
-
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CONDITIONAL, 1),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CALL, 2),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, RETURN, 3),
-	P4_MAKE_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, INDIRECT, 4),
-
-	P4_MAKE_EVENT_ATTR(P4_RESOURCE_STALL, SBFULL, 5),
-
-	P4_MAKE_EVENT_ATTR(P4_WC_BUFFER, WCB_EVICTS, 0),
-	P4_MAKE_EVENT_ATTR(P4_WC_BUFFER, WCB_FULL_EVICTS, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_FRONT_END_EVENT, NBOGUS, 0),
-	P4_MAKE_EVENT_ATTR(P4_FRONT_END_EVENT, BOGUS, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS0, 0),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS1, 1),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS2, 2),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, NBOGUS3, 3),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS0, 4),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS1, 5),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS2, 6),
-	P4_MAKE_EVENT_ATTR(P4_EXECUTION_EVENT, BOGUS3, 7),
-
-	P4_MAKE_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS, 0),
-	P4_MAKE_EVENT_ATTR(P4_REPLAY_EVENT, BOGUS, 1),
-
-	P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSNTAG, 0),
-	P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSTAG, 1),
-	P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSNTAG, 2),
-	P4_MAKE_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSTAG, 3),
-
-	P4_MAKE_EVENT_ATTR(P4_UOPS_RETIRED, NBOGUS, 0),
-	P4_MAKE_EVENT_ATTR(P4_UOPS_RETIRED, BOGUS, 1),
+enum P4_ESCR_EMASKS {
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14),
+	P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6),
+	P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1),
 
-	P4_MAKE_EVENT_ATTR(P4_UOP_TYPE, TAGLOADS, 1),
-	P4_MAKE_EVENT_ATTR(P4_UOP_TYPE, TAGSTORES, 2),
-
-	P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMNP, 0),
-	P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMNM, 1),
-	P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMTP, 2),
-	P4_MAKE_EVENT_ATTR(P4_BRANCH_RETIRED, MMTM, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2),
+
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3),
 
-	P4_MAKE_EVENT_ATTR(P4_MISPRED_BRANCH_RETIRED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0),
 
-	P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, FPSU, 0),
-	P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, FPSO, 1),
-	P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, POAO, 2),
-	P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, POAU, 3),
-	P4_MAKE_EVENT_ATTR(P4_X87_ASSIST, PREA, 4),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3),
+	P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4),
 
-	P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, CLEAR, 0),
-	P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, MOCLEAR, 1),
-	P4_MAKE_EVENT_ATTR(P4_MACHINE_CLEAR, SMCLEAR, 2),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2),
 
-	P4_MAKE_EVENT_ATTR(P4_INSTR_COMPLETED, NBOGUS, 0),
-	P4_MAKE_EVENT_ATTR(P4_INSTR_COMPLETED, BOGUS, 1),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0),
+	P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1),
 };
 
-enum {
-	KEY_P4_L1D_OP_READ_RESULT_MISS = PERF_COUNT_HW_MAX,
-	KEY_P4_LL_OP_READ_RESULT_MISS,
-	KEY_P4_DTLB_OP_READ_RESULT_MISS,
-	KEY_P4_DTLB_OP_WRITE_RESULT_MISS,
-	KEY_P4_ITLB_OP_READ_RESULT_ACCESS,
-	KEY_P4_ITLB_OP_READ_RESULT_MISS,
-	KEY_P4_UOP_TYPE,
+/* P4 PEBS: stale for a while */
+#define P4_PEBS_METRIC_MASK	0x00001fffU
+#define P4_PEBS_UOB_TAG		0x01000000U
+#define P4_PEBS_ENABLE		0x02000000U
+
+/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */
+#define P4_PEBS__1stl_cache_load_miss_retired	0x3000001
+#define P4_PEBS__2ndl_cache_load_miss_retired	0x3000002
+#define P4_PEBS__dtlb_load_miss_retired		0x3000004
+#define P4_PEBS__dtlb_store_miss_retired	0x3000004
+#define P4_PEBS__dtlb_all_miss_retired		0x3000004
+#define P4_PEBS__tagged_mispred_branch		0x3018000
+#define P4_PEBS__mob_load_replay_retired	0x3000200
+#define P4_PEBS__split_load_retired		0x3000400
+#define P4_PEBS__split_store_retired		0x3000400
+
+#define P4_VERT__1stl_cache_load_miss_retired	0x0000001
+#define P4_VERT__2ndl_cache_load_miss_retired	0x0000001
+#define P4_VERT__dtlb_load_miss_retired		0x0000001
+#define P4_VERT__dtlb_store_miss_retired	0x0000002
+#define P4_VERT__dtlb_all_miss_retired		0x0000003
+#define P4_VERT__tagged_mispred_branch		0x0000010
+#define P4_VERT__mob_load_replay_retired	0x0000001
+#define P4_VERT__split_load_retired		0x0000001
+#define P4_VERT__split_store_retired		0x0000002
+
+enum P4_CACHE_EVENTS {
+	P4_CACHE__NONE,
+
+	P4_CACHE__1stl_cache_load_miss_retired,
+	P4_CACHE__2ndl_cache_load_miss_retired,
+	P4_CACHE__dtlb_load_miss_retired,
+	P4_CACHE__dtlb_store_miss_retired,
+	P4_CACHE__itlb_reference_hit,
+	P4_CACHE__itlb_reference_miss,
+
+	P4_CACHE__MAX
 };
 
 #endif /* PERF_EVENT_P4_H */
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index b8a811ab7609..f8fe069f14e2 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -11,35 +11,281 @@
 
 #include <asm/perf_event_p4.h>
 
+#define P4_CNTR_LIMIT 3
 /*
  * array indices: 0,1 - HT threads, used with HT enabled cpu
  */
-struct p4_event_template {
-	u32 opcode;			/* ESCR event + CCCR selector */
-	u64 config;			/* packed predefined bits */
-	int dep;			/* upstream dependency event index */
-	int key;			/* index into p4_templates */
-	u64 msr;			/*
-					 * the high 32 bits set into MSR_IA32_PEBS_ENABLE and
-					 * the low 32 bits set into MSR_P4_PEBS_MATRIX_VERT
-					 * for cache events
-					 */
-	unsigned int emask;		/* ESCR EventMask */
-	unsigned int escr_msr[2];	/* ESCR MSR for this event */
-	unsigned int cntr[2];		/* counter index (offset) */
+struct p4_event_bind {
+	unsigned int opcode;			/* Event code and ESCR selector */
+	unsigned int escr_msr[2];		/* ESCR MSR for this event */
+	unsigned char cntr[2][P4_CNTR_LIMIT];	/* counter index (offset), -1 on abscence */
 };
 
-struct p4_pmu_res {
-	/* maps hw_conf::idx into template for ESCR sake */
-	struct p4_event_template *tpl[ARCH_P4_MAX_CCCR];
+struct p4_cache_event_bind {
+	unsigned int metric_pebs;
+	unsigned int metric_vert;
 };
 
-static DEFINE_PER_CPU(struct p4_pmu_res, p4_pmu_config);
+#define P4_GEN_CACHE_EVENT_BIND(name)		\
+	[P4_CACHE__##name] = {			\
+		.metric_pebs = P4_PEBS__##name,	\
+		.metric_vert = P4_VERT__##name,	\
+	}
+
+static struct p4_cache_event_bind p4_cache_event_bind_map[] = {
+	P4_GEN_CACHE_EVENT_BIND(1stl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(2ndl_cache_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_load_miss_retired),
+	P4_GEN_CACHE_EVENT_BIND(dtlb_store_miss_retired),
+};
+
+/*
+ * Note that we don't use CCCR1 here, there is an
+ * exception for P4_BSQ_ALLOCATION but we just have
+ * no workaround
+ *
+ * consider this binding as resources which particular
+ * event may borrow, it doesn't contain EventMask,
+ * Tags and friends -- they are left to a caller
+ */
+static struct p4_event_bind p4_event_bind_map[] = {
+	[P4_EVENT_TC_DELIVER_MODE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_DELIVER_MODE),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_BPU_FETCH_REQUEST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST),
+		.escr_msr	= { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_ITLB_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_ITLB_REFERENCE),
+		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_MEMORY_CANCEL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_CANCEL),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MEMORY_COMPLETE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MEMORY_COMPLETE),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_LOAD_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_STORE_PORT_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY),
+		.escr_msr	= { MSR_P4_SAAT_ESCR0 ,  MSR_P4_SAAT_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_MOB_LOAD_REPLAY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY),
+		.escr_msr	= { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_PAGE_WALK_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE),
+		.escr_msr	= { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_CACHE_REFERENCE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ALLOCATION] = {
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_IOQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_FSB_ESCR1,  MSR_P4_FSB_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_FSB_DATA_ACTIVITY] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ALLOCATION] = {		/* shared ESCR, broken CCCR1 */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ALLOCATION),
+		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 },
+		.cntr		= { {0, -1, -1}, {1, -1, -1} },
+	},
+	[P4_EVENT_BSQ_ACTIVE_ENTRIES] = {	/* shared ESCR */
+		.opcode		= P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES),
+		.escr_msr	= { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 },
+		.cntr		= { {2, -1, -1}, {3, -1, -1} },
+	},
+	[P4_EVENT_SSE_INPUT_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_PACKED_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_PACKED_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_SP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_SP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_SCALAR_DP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SCALAR_DP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_64BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_64BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_128BIT_MMX_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_128BIT_MMX_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_X87_FP_UOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_FP_UOP),
+		.escr_msr	= { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_TC_MISC] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MISC),
+		.escr_msr	= { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_GLOBAL_POWER_EVENTS] = {
+		.opcode		= P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_TC_MS_XFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_TC_MS_XFER),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_UOP_QUEUE_WRITES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES),
+		.escr_msr	= { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RETIRED_BRANCH_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE),
+		.escr_msr	= { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 },
+		.cntr		= { {4, 5, -1}, {6, 7, -1} },
+	},
+	[P4_EVENT_RESOURCE_STALL] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESOURCE_STALL),
+		.escr_msr	= { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_WC_BUFFER] = {
+		.opcode		= P4_OPCODE(P4_EVENT_WC_BUFFER),
+		.escr_msr	= { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 },
+		.cntr		= { {8, 9, -1}, {10, 11, -1} },
+	},
+	[P4_EVENT_B2B_CYCLES] = {
+		.opcode		= P4_OPCODE(P4_EVENT_B2B_CYCLES),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_BNR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BNR),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_SNOOP] = {
+		.opcode		= P4_OPCODE(P4_EVENT_SNOOP),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_RESPONSE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_RESPONSE),
+		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
+		.cntr		= { {0, -1, -1}, {2, -1, -1} },
+	},
+	[P4_EVENT_FRONT_END_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_FRONT_END_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_EXECUTION_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_EXECUTION_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_REPLAY_EVENT] = {
+		.opcode		= P4_OPCODE(P4_EVENT_REPLAY_EVENT),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOPS_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOPS_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_UOP_TYPE] = {
+		.opcode		= P4_OPCODE(P4_EVENT_UOP_TYPE),
+		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MISPRED_BRANCH_RETIRED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_X87_ASSIST] = {
+		.opcode		= P4_OPCODE(P4_EVENT_X87_ASSIST),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_MACHINE_CLEAR] = {
+		.opcode		= P4_OPCODE(P4_EVENT_MACHINE_CLEAR),
+		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+	[P4_EVENT_INSTR_COMPLETED] = {
+		.opcode		= P4_OPCODE(P4_EVENT_INSTR_COMPLETED),
+		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
+		.cntr		= { {12, 13, 16}, {14, 15, 17} },
+	},
+};
 
-#define P4_CACHE_EVENT_CONFIG(event, bit) \
-	p4_config_pack_escr(P4_EVENT_UNPACK_EVENT(event) << P4_EVNTSEL_EVENT_SHIFT) | \
-	p4_config_pack_escr((event##_##bit) << P4_EVNTSEL_EVENTMASK_SHIFT) | \
-	p4_config_pack_cccr(P4_EVENT_UNPACK_SELECTOR(event) << P4_CCCR_ESCR_SELECT_SHIFT)
+#define P4_GEN_CACHE_EVENT(event, bit, cache_event)			  \
+	p4_config_pack_escr(P4_ESCR_EVENT(event)			| \
+			    P4_ESCR_EMASK_BIT(event, bit))		| \
+	p4_config_pack_cccr(cache_event					| \
+			    P4_CCCR_ESEL(P4_OPCODE_ESEL(P4_OPCODE(event))))
 
 static __initconst u64 p4_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -49,42 +295,35 @@ static __initconst u64 p4_hw_cache_event_ids
  [ C(L1D ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0,
-					/* 1stL_cache_load_miss_retired */
-		[ C(RESULT_MISS)   ] = P4_CACHE_EVENT_CONFIG(P4_REPLAY_EVENT, NBOGUS)
-					| KEY_P4_L1D_OP_READ_RESULT_MISS,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__1stl_cache_load_miss_retired),
 	},
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0,
-					/* 2ndL_cache_load_miss_retired */
-		[ C(RESULT_MISS)   ] = P4_CACHE_EVENT_CONFIG(P4_REPLAY_EVENT, NBOGUS)
-					| KEY_P4_LL_OP_READ_RESULT_MISS,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__2ndl_cache_load_miss_retired),
 	},
- },
+},
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0,
-					/* DTLB_load_miss_retired */
-		[ C(RESULT_MISS)   ] = P4_CACHE_EVENT_CONFIG(P4_REPLAY_EVENT, NBOGUS)
-					| KEY_P4_DTLB_OP_READ_RESULT_MISS,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_load_miss_retired),
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0,
-					/* DTLB_store_miss_retired */
-		[ C(RESULT_MISS)   ] = P4_CACHE_EVENT_CONFIG(P4_REPLAY_EVENT, NBOGUS)
-					| KEY_P4_DTLB_OP_WRITE_RESULT_MISS,
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_REPLAY_EVENT, NBOGUS,
+						P4_CACHE__dtlb_store_miss_retired),
 	},
  },
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
-					/* ITLB_reference.HIT */
-		[ C(RESULT_ACCESS) ] = P4_CACHE_EVENT_CONFIG(P4_ITLB_REFERENCE, HIT)
-					| KEY_P4_ITLB_OP_READ_RESULT_ACCESS,
-
-					/* ITLB_reference.MISS */
-		[ C(RESULT_MISS)   ] = P4_CACHE_EVENT_CONFIG(P4_ITLB_REFERENCE, MISS)
-					| KEY_P4_ITLB_OP_READ_RESULT_MISS,
+		[ C(RESULT_ACCESS) ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, HIT,
+						P4_CACHE__itlb_reference_hit),
+		[ C(RESULT_MISS)   ] = P4_GEN_CACHE_EVENT(P4_EVENT_ITLB_REFERENCE, MISS,
+						P4_CACHE__itlb_reference_miss),
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
@@ -97,220 +336,90 @@ static __initconst u64 p4_hw_cache_event_ids
  },
 };
 
-/*
- * WARN: CCCR1 doesn't have a working enable bit so try to not
- * use it if possible
- *
- * Also as only we start to support raw events we will need to
- * append _all_ P4_EVENT_PACK'ed events here
- */
-struct p4_event_template p4_templates[] = {
-	[0] = {
-		.opcode	= P4_GLOBAL_POWER_EVENTS,
-		.config	= 0,
-		.dep	= -1,
-		.key	= 0,
-		.emask	=
-			P4_EVENT_ATTR(P4_GLOBAL_POWER_EVENTS, RUNNING),
-		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
-		.cntr		= { 0, 2 },
-	},
-	[1] = {
-		.opcode	= P4_INSTR_RETIRED,
-		.config	= 0,
-		.dep	= -1, /* needs front-end tagging */
-		.key	= 1,
-		.emask	=
-			P4_EVENT_ATTR(P4_INSTR_RETIRED, NBOGUSNTAG)	|
-			P4_EVENT_ATTR(P4_INSTR_RETIRED, BOGUSNTAG),
-		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
-		.cntr		= { 12, 14 },
-	},
-	[2] = {
-		.opcode	= P4_BSQ_CACHE_REFERENCE,
-		.config	= 0,
-		.dep	= -1,
-		.key	= 2,
-		.emask	=
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_HITM),
-		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
-		.cntr		= { 0, 2 },
-	},
-	[3] = {
-		.opcode	= P4_BSQ_CACHE_REFERENCE,
-		.config	= 0,
-		.dep	= -1,
-		.key	= 3,
-		.emask	=
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
-			P4_EVENT_ATTR(P4_BSQ_CACHE_REFERENCE, WR_2ndL_MISS),
-		.escr_msr	= { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 },
-		.cntr		= { 0, 3 },
-	},
-	[4] = {
-		.opcode	= P4_RETIRED_BRANCH_TYPE,
-		.config	= 0,
-		.dep	= -1,
-		.key	= 4,
-		.emask	=
-			P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
-			P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, CALL)		|
-			P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, RETURN)		|
-			P4_EVENT_ATTR(P4_RETIRED_BRANCH_TYPE, INDIRECT),
-		.escr_msr	= { MSR_P4_TBPU_ESCR0, MSR_P4_TBPU_ESCR1 },
-		.cntr		= { 4, 6 },
-	},
-	[5] = {
-		.opcode	= P4_MISPRED_BRANCH_RETIRED,
-		.config	= 0,
-		.dep	= -1,
-		.key	= 5,
-		.emask	=
-			P4_EVENT_ATTR(P4_MISPRED_BRANCH_RETIRED, NBOGUS),
-		.escr_msr	= { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 },
-		.cntr		= { 12, 14 },
-	},
-	[6] = {
-		.opcode	= P4_FSB_DATA_ACTIVITY,
-		.config	= p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE),
-		.dep	= -1,
-		.key	= 6,
-		.emask	=
-			P4_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_DRV)	|
-			P4_EVENT_ATTR(P4_FSB_DATA_ACTIVITY, DRDY_OWN),
-		.escr_msr	= { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 },
-		.cntr		= { 0, 2 },
-	},
-	[KEY_P4_L1D_OP_READ_RESULT_MISS] = {
-		.opcode	= P4_REPLAY_EVENT,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= (u64)(1 << 0 | 1 << 24) << 32 | (1 << 0),
-		.key	= KEY_P4_L1D_OP_READ_RESULT_MISS,
-		.emask	=
-			P4_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS),
-		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR2 },
-		.cntr		= { 16, 17 },
-	},
-	[KEY_P4_LL_OP_READ_RESULT_MISS] = {
-		.opcode	= P4_REPLAY_EVENT,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= (u64)(1 << 1 | 1 << 24) << 32 | (1 << 0),
-		.key	= KEY_P4_LL_OP_READ_RESULT_MISS,
-		.emask	=
-			P4_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS),
-		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR2 },
-		.cntr		= { 16, 17 },
-	},
-	[KEY_P4_DTLB_OP_READ_RESULT_MISS] = {
-		.opcode	= P4_REPLAY_EVENT,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= (u64)(1 << 2 | 1 << 24) << 32 | (1 << 0),
-		.key	= KEY_P4_DTLB_OP_READ_RESULT_MISS,
-		.emask	=
-			P4_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS),
-		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR2 },
-		.cntr		= { 16, 17 },
-	},
-	[KEY_P4_DTLB_OP_WRITE_RESULT_MISS] = {
-		.opcode	= P4_REPLAY_EVENT,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= (u64)(1 << 2 | 1 << 24) << 32 | (1 << 1),
-		.key	= KEY_P4_DTLB_OP_WRITE_RESULT_MISS,
-		.emask	=
-			P4_EVENT_ATTR(P4_REPLAY_EVENT, NBOGUS),
-		.escr_msr	= { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR2 },
-		.cntr		= { 16, 17 },
-	},
-	[KEY_P4_ITLB_OP_READ_RESULT_ACCESS] = {
-		.opcode	= P4_ITLB_REFERENCE,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= 0,
-		.key	= KEY_P4_ITLB_OP_READ_RESULT_ACCESS,
-		.emask	=
-			P4_EVENT_ATTR(P4_ITLB_REFERENCE, HIT),
-		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
-		.cntr		= { 0, 2 },
-	},
-	[KEY_P4_ITLB_OP_READ_RESULT_MISS] = {
-		.opcode	= P4_ITLB_REFERENCE,
-		.config	= 0,
-		.dep	= -1,
-		.msr	= 0,
-		.key	= KEY_P4_ITLB_OP_READ_RESULT_MISS,
-		.emask	=
-			P4_EVENT_ATTR(P4_ITLB_REFERENCE, MISS),
-		.escr_msr	= { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 },
-		.cntr		= { 0, 2 },
-	},
-	[KEY_P4_UOP_TYPE] = {
-		.opcode	= P4_UOP_TYPE,
-		.config	= 0,
-		.dep	= -1,
-		.key	= KEY_P4_UOP_TYPE,
-		.emask	=
-			P4_EVENT_ATTR(P4_UOP_TYPE, TAGLOADS)	|
-			P4_EVENT_ATTR(P4_UOP_TYPE, TAGSTORES),
-		.escr_msr	= { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 },
-		.cntr		= { 16, 17 },
-	},
+static u64 p4_general_events[PERF_COUNT_HW_MAX] = {
+  /* non-halted CPU clocks */
+  [PERF_COUNT_HW_CPU_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_GLOBAL_POWER_EVENTS)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING)),
+
+  /*
+   * retired instructions
+   * in a sake of simplicity we don't use the FSB tagging
+   */
+  [PERF_COUNT_HW_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_INSTR_RETIRED)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG)),
+
+  /* cache hits */
+  [PERF_COUNT_HW_CACHE_REFERENCES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM)),
+
+  /* cache misses */
+  [PERF_COUNT_HW_CACHE_MISSES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_BSQ_CACHE_REFERENCE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS)),
+
+  /* branch instructions retired */
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_RETIRED_BRANCH_TYPE)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT)),
+
+  /* mispredicted branches retired */
+  [PERF_COUNT_HW_BRANCH_MISSES]	=
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_MISPRED_BRANCH_RETIRED)	|
+		P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS)),
+
+  /* bus ready clocks (cpu is driving #DRDY_DRV\#DRDY_OWN):  */
+  [PERF_COUNT_HW_BUS_CYCLES] =
+	p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_FSB_DATA_ACTIVITY)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV)		|
+		P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN))	|
+	p4_config_pack_cccr(P4_CCCR_EDGE | P4_CCCR_COMPARE),
 };
 
+static struct p4_event_bind *p4_config_get_bind(u64 config)
+{
+	unsigned int evnt = p4_config_unpack_event(config);
+	struct p4_event_bind *bind = NULL;
+
+	if (evnt < ARRAY_SIZE(p4_event_bind_map))
+		bind = &p4_event_bind_map[evnt];
+
+	return bind;
+}
+
 static u64 p4_pmu_event_map(int hw_event)
 {
-	struct p4_event_template *tpl;
+	struct p4_event_bind *bind;
+	unsigned int esel;
 	u64 config;
 
-	if (hw_event > ARRAY_SIZE(p4_templates)) {
-		printk_once(KERN_ERR "PMU: Incorrect event index\n");
+	if (hw_event > ARRAY_SIZE(p4_general_events)) {
+		printk_once(KERN_ERR "P4 PMU: Bad index: %i\n", hw_event);
 		return 0;
 	}
-	tpl = &p4_templates[hw_event];
 
-	/*
-	 * fill config up according to
-	 * a predefined event template
-	 */
-	config  = tpl->config;
-	config |= p4_config_pack_escr(P4_EVENT_UNPACK_EVENT(tpl->opcode) << P4_EVNTSEL_EVENT_SHIFT);
-	config |= p4_config_pack_escr(tpl->emask << P4_EVNTSEL_EVENTMASK_SHIFT);
-	config |= p4_config_pack_cccr(P4_EVENT_UNPACK_SELECTOR(tpl->opcode) << P4_CCCR_ESCR_SELECT_SHIFT);
-	config |= p4_config_pack_cccr(hw_event & P4_CCCR_RESERVED);
+	config = p4_general_events[hw_event];
+	bind = p4_config_get_bind(config);
+	esel = P4_OPCODE_ESEL(bind->opcode);
+	config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel));
 
 	return config;
 }
 
 /*
- * Note that we still have 5 events (from global events SDM list)
- * intersected in opcode+emask bits so we will need another
- * scheme there do distinguish templates.
- */
-static inline int p4_pmu_emask_match(unsigned int dst, unsigned int src)
-{
-	return dst & src;
-}
-
-static struct p4_event_template *p4_pmu_template_lookup(u64 config)
-{
-	int key = p4_config_unpack_key(config);
-
-	if (key < ARRAY_SIZE(p4_templates))
-		return &p4_templates[key];
-	else
-		return NULL;
-}
-
-/*
  * We don't control raw events so it's up to the caller
  * to pass sane values (and we don't count the thread number
  * on HT machine but allow HT-compatible specifics to be
@@ -319,13 +428,14 @@ static struct p4_event_template *p4_pmu_template_lookup(u64 config)
 static u64 p4_pmu_raw_event(u64 hw_event)
 {
 	return hw_event &
-		(p4_config_pack_escr(P4_EVNTSEL_MASK_HT) |
+		(p4_config_pack_escr(P4_ESCR_MASK_HT) |
 		 p4_config_pack_cccr(P4_CCCR_MASK_HT));
 }
 
 static int p4_hw_config(struct perf_event_attr *attr, struct hw_perf_event *hwc)
 {
 	int cpu = raw_smp_processor_id();
+	u32 escr, cccr;
 
 	/*
 	 * the reason we use cpu that early is that: if we get scheduled
@@ -333,13 +443,10 @@ static int p4_hw_config(struct perf_event_attr *attr, struct hw_perf_event *hwc)
 	 * specific flags in config (and will save some cpu cycles)
 	 */
 
-	/* CCCR by default */
-	hwc->config = p4_config_pack_cccr(p4_default_cccr_conf(cpu));
+	cccr = p4_default_cccr_conf(cpu);
+	escr = p4_default_escr_conf(cpu, attr->exclude_kernel, attr->exclude_user);
+	hwc->config = p4_config_pack_escr(escr) | p4_config_pack_cccr(cccr);
 
-	/* Count user and OS events unless not requested to */
-	hwc->config |= p4_config_pack_escr(p4_default_escr_conf(cpu, attr->exclude_kernel,
-								attr->exclude_user));
-	/* on HT machine we need a special bit */
 	if (p4_ht_active() && p4_ht_thread(cpu))
 		hwc->config = p4_set_ht_bit(hwc->config);
 
@@ -368,7 +475,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
 	 */
 	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
 		(u64)(p4_config_unpack_cccr(hwc->config)) &
-			~P4_CCCR_ENABLE & ~P4_CCCR_OVF);
+			~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
 }
 
 static void p4_pmu_disable_all(void)
@@ -389,27 +496,14 @@ static void p4_pmu_enable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int thread = p4_ht_config_thread(hwc->config);
 	u64 escr_conf = p4_config_unpack_escr(p4_clear_ht_bit(hwc->config));
-	u64 escr_base;
-	struct p4_event_template *tpl;
-	struct p4_pmu_res *c;
+	unsigned int idx = p4_config_unpack_event(hwc->config);
+	unsigned int idx_cache = p4_config_unpack_cache_event(hwc->config);
+	struct p4_event_bind *bind;
+	struct p4_cache_event_bind *bind_cache;
+	u64 escr_addr, cccr;
 
-	/*
-	 * some preparation work from per-cpu private fields
-	 * since we need to find out which ESCR to use
-	 */
-	c = &__get_cpu_var(p4_pmu_config);
-	tpl = c->tpl[hwc->idx];
-	if (!tpl) {
-		pr_crit("%s: Wrong index: %d\n", __func__, hwc->idx);
-		return;
-	}
-
-	if (tpl->msr) {
-		(void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, tpl->msr >> 32);
-		(void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, tpl->msr & 0xffffffff);
-	}
-
-	escr_base = (u64)tpl->escr_msr[thread];
+	bind = &p4_event_bind_map[idx];
+	escr_addr = (u64)bind->escr_msr[thread];
 
 	/*
 	 * - we dont support cascaded counters yet
@@ -418,9 +512,27 @@ static void p4_pmu_enable_event(struct perf_event *event)
 	WARN_ON_ONCE(p4_is_event_cascaded(hwc->config));
 	WARN_ON_ONCE(hwc->idx == 1);
 
-	(void)checking_wrmsrl(escr_base, escr_conf);
+	/* we need a real Event value */
+	escr_conf &= ~P4_ESCR_EVENT_MASK;
+	escr_conf |= P4_ESCR_EVENT(P4_OPCODE_EVNT(bind->opcode));
+
+	cccr = p4_config_unpack_cccr(hwc->config);
+
+	/*
+	 * it could be Cache event so that we need to
+	 * set metrics into additional MSRs
+	 */
+	BUILD_BUG_ON(P4_CACHE__MAX > P4_CCCR_CACHE_OPS_MASK);
+	if (idx_cache > P4_CACHE__NONE &&
+		idx_cache < ARRAY_SIZE(p4_cache_event_bind_map)) {
+		bind_cache = &p4_cache_event_bind_map[idx_cache];
+		(void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind_cache->metric_pebs);
+		(void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind_cache->metric_vert);
+	}
+
+	(void)checking_wrmsrl(escr_addr, escr_conf);
 	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-		(u64)(p4_config_unpack_cccr(hwc->config)) | P4_CCCR_ENABLE);
+				(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
 }
 
 static void p4_pmu_enable_all(void)
@@ -516,13 +628,13 @@ static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
 	if (p4_ht_thread(cpu)) {
 		cccr &= ~P4_CCCR_OVF_PMI_T0;
 		cccr |= P4_CCCR_OVF_PMI_T1;
-		if (escr & P4_EVNTSEL_T0_OS) {
-			escr &= ~P4_EVNTSEL_T0_OS;
-			escr |= P4_EVNTSEL_T1_OS;
+		if (escr & P4_ESCR_T0_OS) {
+			escr &= ~P4_ESCR_T0_OS;
+			escr |= P4_ESCR_T1_OS;
 		}
-		if (escr & P4_EVNTSEL_T0_USR) {
-			escr &= ~P4_EVNTSEL_T0_USR;
-			escr |= P4_EVNTSEL_T1_USR;
+		if (escr & P4_ESCR_T0_USR) {
+			escr &= ~P4_ESCR_T0_USR;
+			escr |= P4_ESCR_T1_USR;
 		}
 		hwc->config  = p4_config_pack_escr(escr);
 		hwc->config |= p4_config_pack_cccr(cccr);
@@ -530,13 +642,13 @@ static void p4_pmu_swap_config_ts(struct hw_perf_event *hwc, int cpu)
 	} else {
 		cccr &= ~P4_CCCR_OVF_PMI_T1;
 		cccr |= P4_CCCR_OVF_PMI_T0;
-		if (escr & P4_EVNTSEL_T1_OS) {
-			escr &= ~P4_EVNTSEL_T1_OS;
-			escr |= P4_EVNTSEL_T0_OS;
+		if (escr & P4_ESCR_T1_OS) {
+			escr &= ~P4_ESCR_T1_OS;
+			escr |= P4_ESCR_T0_OS;
 		}
-		if (escr & P4_EVNTSEL_T1_USR) {
-			escr &= ~P4_EVNTSEL_T1_USR;
-			escr |= P4_EVNTSEL_T0_USR;
+		if (escr & P4_ESCR_T1_USR) {
+			escr &= ~P4_ESCR_T1_USR;
+			escr |= P4_ESCR_T0_USR;
 		}
 		hwc->config  = p4_config_pack_escr(escr);
 		hwc->config |= p4_config_pack_cccr(cccr);
@@ -606,66 +718,56 @@ static int p4_get_escr_idx(unsigned int addr)
 	return -1;
 }
 
+static int p4_next_cntr(int thread, unsigned long *used_mask,
+			struct p4_event_bind *bind)
+{
+	int i = 0, j;
+
+	for (i = 0; i < P4_CNTR_LIMIT; i++) {
+		j = bind->cntr[thread][i++];
+		if (j == -1 || !test_bit(j, used_mask))
+			return j;
+	}
+
+	return -1;
+}
+
 static int p4_pmu_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
 	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	unsigned long escr_mask[BITS_TO_LONGS(ARCH_P4_TOTAL_ESCR)];
-
-	struct hw_perf_event *hwc;
-	struct p4_event_template *tpl;
-	struct p4_pmu_res *c;
 	int cpu = raw_smp_processor_id();
-	int escr_idx, thread, i, num;
+	struct hw_perf_event *hwc;
+	struct p4_event_bind *bind;
+	unsigned int i, thread, num;
+	int cntr_idx, escr_idx;
 
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 	bitmap_zero(escr_mask, ARCH_P4_TOTAL_ESCR);
 
-	c = &__get_cpu_var(p4_pmu_config);
-	/*
-	 * Firstly find out which resource events are going
-	 * to use, if ESCR+CCCR tuple is already borrowed
-	 * then get out of here
-	 */
 	for (i = 0, num = n; i < n; i++, num--) {
+
 		hwc = &cpuc->event_list[i]->hw;
-		tpl = p4_pmu_template_lookup(hwc->config);
-		if (!tpl)
-			goto done;
 		thread = p4_ht_thread(cpu);
-		escr_idx = p4_get_escr_idx(tpl->escr_msr[thread]);
-		if (escr_idx == -1)
-			goto done;
+		bind = p4_config_get_bind(hwc->config);
+		escr_idx = p4_get_escr_idx(bind->escr_msr[thread]);
 
-		/* already allocated and remains on the same cpu */
 		if (hwc->idx != -1 && !p4_should_swap_ts(hwc->config, cpu)) {
+			cntr_idx = hwc->idx;
 			if (assign)
 				assign[i] = hwc->idx;
-			/* upstream dependent event */
-			if (unlikely(tpl->dep != -1))
-				printk_once(KERN_WARNING "PMU: Dep events are "
-					"not implemented yet\n");
 			goto reserve;
 		}
 
-		/* it may be already borrowed */
-		if (test_bit(tpl->cntr[thread], used_mask) ||
-			test_bit(escr_idx, escr_mask))
+		cntr_idx = p4_next_cntr(thread, used_mask, bind);
+		if (cntr_idx == -1 || test_bit(escr_idx, escr_mask))
 			goto done;
 
-		/*
-		 * ESCR+CCCR+COUNTERs are available to use lets swap
-		 * thread specific bits, push assigned bits
-		 * back and save template into per-cpu
-		 * area (which will allow us to find out the ESCR
-		 * to be used at moment of "enable event via real MSR")
-		 */
 		p4_pmu_swap_config_ts(hwc, cpu);
-		if (assign) {
-			assign[i] = tpl->cntr[thread];
-			c->tpl[assign[i]] = tpl;
-		}
+		if (assign)
+			assign[i] = cntr_idx;
 reserve:
-		set_bit(tpl->cntr[thread], used_mask);
+		set_bit(cntr_idx, used_mask);
 		set_bit(escr_idx, escr_mask);
 	}
 
@@ -684,7 +786,7 @@ static __initconst struct x86_pmu p4_pmu = {
 	.perfctr		= MSR_P4_BPU_PERFCTR0,
 	.event_map		= p4_pmu_event_map,
 	.raw_event		= p4_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(p4_templates),
+	.max_events		= ARRAY_SIZE(p4_general_events),
 	.get_event_constraints	= x86_get_event_constraints,
 	/*
 	 * IF HT disabled we may need to use all
@@ -716,7 +818,7 @@ static __init int p4_pmu_init(void)
 	}
 
 	memcpy(hw_cache_event_ids, p4_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
+		sizeof(hw_cache_event_ids));
 
 	pr_cont("Netburst events, ");