linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org,
	tglx@linutronix.de, bp@alien8.de, x86@kernel.org,
	linux-kernel@vger.kernel.org
Cc: mark.rutland@arm.com, alexander.shishkin@linux.intel.com,
	jolsa@redhat.com, namhyung@kernel.org, dave.hansen@intel.com,
	yu-cheng.yu@intel.com, bigeasy@linutronix.de, gorcunov@gmail.com,
	hpa@zytor.com, alexey.budankov@linux.intel.com,
	eranian@google.com, ak@linux.intel.com, like.xu@linux.intel.com,
	yao.jin@linux.intel.com, wei.w.wang@intel.com,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V3 09/23] perf/x86/intel/lbr: Support LBR_CTL
Date: Fri,  3 Jul 2020 05:49:15 -0700	[thread overview]
Message-ID: <1593780569-62993-10-git-send-email-kan.liang@linux.intel.com> (raw)
In-Reply-To: <1593780569-62993-1-git-send-email-kan.liang@linux.intel.com>

From: Kan Liang <kan.liang@linux.intel.com>

An IA32_LBR_CTL is introduced for Architecture LBR to enable and config
LBR registers to replace the previous LBR_SELECT.

All the related members in struct cpu_hw_events and struct x86_pmu
have to be renamed.

Some new macros are added to reflect the layout of LBR_CTL.

The mapping from PERF_SAMPLE_BRANCH_* to the corresponding bits in
LBR_CTL MSR is saved in lbr_ctl_map now, which is not a const value.
The value relies on the CPUID enumeration.

For the previous model-specific LBR, most of the bits in LBR_SELECT
operate in the suppressed mode. For the bits in LBR_CTL, the polarity is
inverted.

For the previous model-specific LBR format 5 (LBR_FORMAT_INFO), if the
NO_CYCLES and NO_FLAGS type are set, the flag LBR_NO_INFO will be set to
avoid the unnecessary LBR_INFO MSR read. Although Architecture LBR also
has a dedicated LBR_INFO MSR, perf doesn't need to check and set the
flag LBR_NO_INFO. For Architecture LBR, XSAVES instruction will be used
as the default way to read the LBR MSRs all together. The overhead which
the flag tries to avoid doesn't exist anymore. Dropping the flag can
save the extra check for the flag in the lbr_read() later, and make the
code cleaner.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/intel/lbr.c  | 43 +++++++++++++++++++++++++++++++++++++++++++
 arch/x86/events/perf_event.h | 15 ++++++++++++---
 2 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index e62baa9..7742562 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -132,6 +132,44 @@ enum {
 	 X86_BR_IRQ		|\
 	 X86_BR_INT)
 
+/*
+ * Intel LBR_CTL bits
+ *
+ * Hardware branch filter for Arch LBR
+ */
+#define ARCH_LBR_KERNEL_BIT		1  /* capture at ring0 */
+#define ARCH_LBR_USER_BIT		2  /* capture at ring > 0 */
+#define ARCH_LBR_CALL_STACK_BIT		3  /* enable call stack */
+#define ARCH_LBR_JCC_BIT		16 /* capture conditional branches */
+#define ARCH_LBR_REL_JMP_BIT		17 /* capture relative jumps */
+#define ARCH_LBR_IND_JMP_BIT		18 /* capture indirect jumps */
+#define ARCH_LBR_REL_CALL_BIT		19 /* capture relative calls */
+#define ARCH_LBR_IND_CALL_BIT		20 /* capture indirect calls */
+#define ARCH_LBR_RETURN_BIT		21 /* capture near returns */
+#define ARCH_LBR_OTHER_BRANCH_BIT	22 /* capture other branches */
+
+#define ARCH_LBR_KERNEL			(1ULL << ARCH_LBR_KERNEL_BIT)
+#define ARCH_LBR_USER			(1ULL << ARCH_LBR_USER_BIT)
+#define ARCH_LBR_CALL_STACK		(1ULL << ARCH_LBR_CALL_STACK_BIT)
+#define ARCH_LBR_JCC			(1ULL << ARCH_LBR_JCC_BIT)
+#define ARCH_LBR_REL_JMP		(1ULL << ARCH_LBR_REL_JMP_BIT)
+#define ARCH_LBR_IND_JMP		(1ULL << ARCH_LBR_IND_JMP_BIT)
+#define ARCH_LBR_REL_CALL		(1ULL << ARCH_LBR_REL_CALL_BIT)
+#define ARCH_LBR_IND_CALL		(1ULL << ARCH_LBR_IND_CALL_BIT)
+#define ARCH_LBR_RETURN			(1ULL << ARCH_LBR_RETURN_BIT)
+#define ARCH_LBR_OTHER_BRANCH		(1ULL << ARCH_LBR_OTHER_BRANCH_BIT)
+
+#define ARCH_LBR_ANY			 \
+	(ARCH_LBR_JCC			|\
+	 ARCH_LBR_REL_JMP		|\
+	 ARCH_LBR_IND_JMP		|\
+	 ARCH_LBR_REL_CALL		|\
+	 ARCH_LBR_IND_CALL		|\
+	 ARCH_LBR_RETURN		|\
+	 ARCH_LBR_OTHER_BRANCH)
+
+#define ARCH_LBR_CTL_MASK			0x7f000e
+
 static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
 
 /*
@@ -820,6 +858,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	reg = &event->hw.branch_reg;
 	reg->idx = EXTRA_REG_LBR;
 
+	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
+		reg->config = mask;
+		return 0;
+	}
+
 	/*
 	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
 	 * in suppress mode. So LBR_SELECT should be set to
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index cc81177..ba89e56 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -245,7 +245,10 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
-	struct er_account		*lbr_sel;
+	union {
+		struct er_account		*lbr_sel;
+		struct er_account		*lbr_ctl;
+	};
 	u64				br_sel;
 	void				*last_task_ctx;
 	int				last_log_id;
@@ -688,8 +691,14 @@ struct x86_pmu {
 	 */
 	unsigned int	lbr_tos, lbr_from, lbr_to,
 			lbr_nr;			   /* LBR base regs and size */
-	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
-	const int	*lbr_sel_map;		   /* lbr_select mappings */
+	union {
+		u64	lbr_sel_mask;		   /* LBR_SELECT valid bits */
+		u64	lbr_ctl_mask;		   /* LBR_CTL valid bits */
+	};
+	union {
+		const int	*lbr_sel_map;	   /* lbr_select mappings */
+		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
+	};
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
 	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
 
-- 
2.7.4


  parent reply	other threads:[~2020-07-03 12:54 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-03 12:49 [PATCH V3 00/23] Support Architectural LBR kan.liang
2020-07-03 12:49 ` [PATCH V3 01/23] x86/cpufeatures: Add Architectural LBRs feature bit kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-09 23:00     ` Dave Hansen
2020-07-10  9:51       ` Peter Zijlstra
2020-07-10 14:09       ` Liang, Kan
2020-07-03 12:49 ` [PATCH V3 02/23] perf/x86/intel/lbr: Add a function pointer for LBR reset kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 03/23] perf/x86/intel/lbr: Add a function pointer for LBR read kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 04/23] perf/x86/intel/lbr: Add the function pointers for LBR save and restore kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 05/23] perf/x86/intel/lbr: Factor out a new struct for generic optimization kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 06/23] perf/x86/intel/lbr: Use dynamic data structure for task_ctx kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 07/23] x86/msr-index: Add bunch of MSRs for Arch LBR kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 08/23] perf/x86: Expose CPUID enumeration bits for arch LBR kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` kan.liang [this message]
2020-07-08  9:51   ` [tip: perf/core] perf/x86/intel/lbr: Support LBR_CTL tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 10/23] perf/x86/intel/lbr: Unify the stored format of LBR information kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 11/23] perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 12/23] perf/x86/intel/lbr: Factor out rdlbr_all() and wrlbr_all() kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 13/23] perf/x86/intel/lbr: Factor out intel_pmu_store_lbr kan.liang
2020-07-03 19:50   ` Peter Zijlstra
2020-07-03 20:59     ` Liang, Kan
2020-07-06 10:25       ` Peter Zijlstra
2020-07-06 13:32         ` Liang, Kan
2020-07-06 14:25           ` Peter Zijlstra
2020-07-06 22:29       ` Liang, Kan
2020-07-07  7:40         ` Peter Zijlstra
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 14/23] perf/x86/intel/lbr: Support Architectural LBR kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 15/23] perf/core: Factor out functions to allocate/free the task_ctx_data kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 16/23] perf/core: Use kmem_cache to allocate the PMU specific data kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 17/23] perf/x86/intel/lbr: Create kmem_cache for the LBR context data kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 18/23] perf/x86: Remove task_ctx_size kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 19/23] x86/fpu: Use proper mask to replace full instruction mask kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 20/23] x86/fpu/xstate: Support dynamic supervisor feature for LBR kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2021-05-27 22:15     ` Thomas Gleixner
2020-07-03 12:49 ` [PATCH V3 21/23] x86/fpu/xstate: Add helpers for LBR dynamic supervisor feature kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 22/23] perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 12:49 ` [PATCH V3 23/23] perf/x86/intel/lbr: Support XSAVES for arch LBR read kan.liang
2020-07-08  9:51   ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-03 19:34 ` [PATCH V3 00/23] Support Architectural LBR Peter Zijlstra

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=1593780569-62993-10-git-send-email-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=alexey.budankov@linux.intel.com \
    --cc=bigeasy@linutronix.de \
    --cc=bp@alien8.de \
    --cc=dave.hansen@intel.com \
    --cc=eranian@google.com \
    --cc=gorcunov@gmail.com \
    --cc=hpa@zytor.com \
    --cc=jolsa@redhat.com \
    --cc=like.xu@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=wei.w.wang@intel.com \
    --cc=x86@kernel.org \
    --cc=yao.jin@linux.intel.com \
    --cc=yu-cheng.yu@intel.com \
    /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).