linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Yan, Zheng" <zheng.z.yan@intel.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, a.p.zijlstra@chello.nl, eranian@google.com,
	andi@firstfloor.org, "Yan, Zheng" <zheng.z.yan@intel.com>
Subject: [PATCH 1/7] perf, x86: Reduce lbr_sel_map size
Date: Tue, 25 Jun 2013 16:47:13 +0800	[thread overview]
Message-ID: <1372150039-15151-2-git-send-email-zheng.z.yan@intel.com> (raw)
In-Reply-To: <1372150039-15151-1-git-send-email-zheng.z.yan@intel.com>

From: "Yan, Zheng" <zheng.z.yan@intel.com>

The index of lbr_sel_map is bit value of perf branch_sample_type.
We can reduce lbr_sel_map size by using bit shift as index.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.h           |  4 +++
 arch/x86/kernel/cpu/perf_event_intel_lbr.c | 50 ++++++++++++++----------------
 include/uapi/linux/perf_event.h            | 42 +++++++++++++++++--------
 3 files changed, 56 insertions(+), 40 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 108dc75..a74d554 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -447,6 +447,10 @@ struct x86_pmu {
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
+enum {
+	PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE = PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
 #define x86_add_quirk(func_)						\
 do {									\
 	static struct x86_pmu_quirk __quirk __initdata = {		\
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d5be06a..a72e9e9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -69,10 +69,6 @@ static enum {
 #define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
 #define LBR_FROM_FLAG_ABORT    (1ULL << 61)
 
-#define for_each_branch_sample_type(x) \
-	for ((x) = PERF_SAMPLE_BRANCH_USER; \
-	     (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
-
 /*
  * x86control flow change classification
  * x86control flow changes include branches, interrupts, traps, faults
@@ -387,14 +383,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 {
 	struct hw_perf_event_extra *reg;
 	u64 br_type = event->attr.branch_sample_type;
-	u64 mask = 0, m;
-	u64 v;
+	u64 mask = 0, v;
+	int i;
 
-	for_each_branch_sample_type(m) {
-		if (!(br_type & m))
+	for (i = 0; i < PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE; i++) {
+		if (!(br_type & (1U << i)))
 			continue;
 
-		v = x86_pmu.lbr_sel_map[m];
+		v = x86_pmu.lbr_sel_map[i];
 		if (v == LBR_NOT_SUPP)
 			return -EOPNOTSUPP;
 
@@ -649,33 +645,33 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 /*
  * Map interface branch filters onto LBR filters
  */
-static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
-	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
-	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
-	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
-	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
-	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_REL_JMP
-					| LBR_IND_JMP | LBR_FAR,
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_REL_JMP
+						| LBR_IND_JMP | LBR_FAR,
 	/*
 	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
 	 */
-	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
 	 LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
 	/*
 	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
 	 */
-	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
 };
 
-static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
-	[PERF_SAMPLE_BRANCH_ANY]	= LBR_ANY,
-	[PERF_SAMPLE_BRANCH_USER]	= LBR_USER,
-	[PERF_SAMPLE_BRANCH_KERNEL]	= LBR_KERNEL,
-	[PERF_SAMPLE_BRANCH_HV]		= LBR_IGN,
-	[PERF_SAMPLE_BRANCH_ANY_RETURN]	= LBR_RETURN | LBR_FAR,
-	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
-					| LBR_FAR,
-	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
+	[PERF_SAMPLE_BRANCH_ANY_SHIFT]		= LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER_SHIFT]		= LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL_SHIFT]	= LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_HV_SHIFT]		= LBR_IGN,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]	= LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
+						| LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 };
 
 /* core */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 0b1df41..2ec219e 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -148,20 +148,36 @@ enum perf_event_sample_format {
  * The branch types can be combined, however BRANCH_ANY covers all types
  * of branches and therefore it supersedes all the other types.
  */
+enum perf_branch_sample_type_shift {
+	PERF_SAMPLE_BRANCH_USER_SHIFT		= 0, /* user branches */
+	PERF_SAMPLE_BRANCH_KERNEL_SHIFT		= 1, /* kernel branches */
+	PERF_SAMPLE_BRANCH_HV_SHIFT		= 2, /* hypervisor branches */
+
+	PERF_SAMPLE_BRANCH_ANY_SHIFT		= 3, /* any branch types */
+	PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT	= 4, /* any call branch */
+	PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT	= 5, /* any return branch */
+	PERF_SAMPLE_BRANCH_IND_CALL_SHIFT	= 6, /* indirect calls */
+	PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT	= 7, /* transaction aborts */
+	PERF_SAMPLE_BRANCH_IN_TX_SHIFT		= 8, /* in transaction */
+	PERF_SAMPLE_BRANCH_NO_TX_SHIFT		= 9, /* not in transaction */
+
+	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
+};
+
 enum perf_branch_sample_type {
-	PERF_SAMPLE_BRANCH_USER		= 1U << 0, /* user branches */
-	PERF_SAMPLE_BRANCH_KERNEL	= 1U << 1, /* kernel branches */
-	PERF_SAMPLE_BRANCH_HV		= 1U << 2, /* hypervisor branches */
-
-	PERF_SAMPLE_BRANCH_ANY		= 1U << 3, /* any branch types */
-	PERF_SAMPLE_BRANCH_ANY_CALL	= 1U << 4, /* any call branch */
-	PERF_SAMPLE_BRANCH_ANY_RETURN	= 1U << 5, /* any return branch */
-	PERF_SAMPLE_BRANCH_IND_CALL	= 1U << 6, /* indirect calls */
-	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
-	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
-	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
-
-	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+	PERF_SAMPLE_BRANCH_USER         = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
+	PERF_SAMPLE_BRANCH_KERNEL       = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
+	PERF_SAMPLE_BRANCH_HV           = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
+
+	PERF_SAMPLE_BRANCH_ANY          = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_CALL     = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ANY_RETURN   = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_CALL     = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
+	PERF_SAMPLE_BRANCH_ABORT_TX     = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_IN_TX        = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
+	PERF_SAMPLE_BRANCH_NO_TX        = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
+
+	PERF_SAMPLE_BRANCH_MAX          = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
-- 
1.8.1.4


  reply	other threads:[~2013-06-25  8:52 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-25  8:47 [PATCH 0/7] perf, x86: Haswell LBR call stack support Yan, Zheng
2013-06-25  8:47 ` Yan, Zheng [this message]
2013-06-25 12:33   ` [PATCH 1/7] perf, x86: Reduce lbr_sel_map size Stephane Eranian
2013-06-26  6:05     ` Yan, Zheng
2013-06-25  8:47 ` [PATCH 2/7] perf, x86: Basic Haswell LBR call stack support Yan, Zheng
2013-06-25 12:37   ` Stephane Eranian
2013-06-26  2:42     ` Yan, Zheng
2013-06-25  8:47 ` [PATCH 3/7] perf, x86: Introduce x86 special perf event context Yan, Zheng
2013-06-25  8:47 ` [PATCH 4/7] perf, x86: Save/resotre LBR stack during context switch Yan, Zheng
2013-06-26 11:47   ` Peter Zijlstra
2013-06-25  8:47 ` [PATCH 5/7] perf, core: Pass perf_sample_data to perf_callchain() Yan, Zheng
2013-06-25  8:47 ` [PATCH 6/7] perf, x86: Use LBR call stack to get user callchain Yan, Zheng
2013-06-26  9:00   ` Stephane Eranian
2013-06-26 12:42   ` Stephane Eranian
2013-06-26 12:45     ` Stephane Eranian
2013-06-27  1:52       ` Yan, Zheng
2013-06-27  1:40     ` Yan, Zheng
2013-06-27  8:58       ` Stephane Eranian
2013-06-28  2:24         ` Yan, Zheng
2013-06-25  8:47 ` [PATCH 7/7] perf, x86: Discard zero length call entries in LBR call stack Yan, Zheng
2013-06-25 12:40 ` [PATCH 0/7] perf, x86: Haswell LBR call stack support Stephane Eranian
2013-06-25 15:27   ` Andi Kleen
2013-06-25 15:30 ` Andi Kleen
2013-06-26 11:54 ` Peter Zijlstra
2013-06-26 16:40   ` Andi Kleen
2013-06-26 16:48   ` Stephane Eranian
2013-06-27  8:07     ` Yan, Zheng
2013-06-26 12:07 ` Peter Zijlstra
2013-06-26 16:59   ` Andi Kleen
2013-06-26 17:11     ` Peter Zijlstra
  -- strict thread matches above, loose matches on Subject: below --
2013-02-25  2:01 [PATCH V3 " Yan, Zheng
2013-02-25  2:01 ` [PATCH 1/7] perf, x86: Reduce lbr_sel_map size Yan, Zheng
2013-01-30  6:30 [PATCH 0/7] perf, x86: Haswell LBR call stack support Yan, Zheng
2013-01-30  6:30 ` [PATCH 1/7] perf, x86: Reduce lbr_sel_map size Yan, Zheng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1372150039-15151-2-git-send-email-zheng.z.yan@intel.com \
    --to=zheng.z.yan@intel.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=andi@firstfloor.org \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).