From: "tip-bot2 for Kan Liang" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: Kan Liang <kan.liang@linux.intel.com>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
x86 <x86@kernel.org>, LKML <linux-kernel@vger.kernel.org>
Subject: [tip: perf/core] perf/x86/intel/lbr: Use dynamic data structure for task_ctx
Date: Wed, 08 Jul 2020 09:51:52 -0000 [thread overview]
Message-ID: <159420191288.4006.3420651578991456355.tip-bot2@tip-bot2> (raw)
In-Reply-To: <1593780569-62993-7-git-send-email-kan.liang@linux.intel.com>
The following commit has been merged into the perf/core branch of tip:
Commit-ID: f42be8651a7a9d5cb165e5d176fc0b09621b4f4d
Gitweb: https://git.kernel.org/tip/f42be8651a7a9d5cb165e5d176fc0b09621b4f4d
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Fri, 03 Jul 2020 05:49:12 -07:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 08 Jul 2020 11:38:52 +02:00
perf/x86/intel/lbr: Use dynamic data structure for task_ctx
The type of task_ctx is hardcoded as struct x86_perf_task_context,
which doesn't apply for Architecture LBR. For example, Architecture LBR
doesn't have the TOS MSR. The number of LBR entries is variable. A new
struct will be introduced for Architecture LBR. Perf has to determine
the type of task_ctx at run time.
The type of task_ctx pointer is changed to 'void *', which will be
determined at run time.
The generic LBR optimization can be shared between Architecture LBR and
model-specific LBR. Both need to access the structure for the generic
LBR optimization. A helper task_context_opt() is introduced to retrieve
the pointer of the structure at run time.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-7-git-send-email-kan.liang@linux.intel.com
---
arch/x86/events/intel/lbr.c | 59 +++++++++++++++--------------------
arch/x86/events/perf_event.h | 7 +++-
2 files changed, 32 insertions(+), 34 deletions(-)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index bba9939..e62baa9 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -355,18 +355,17 @@ void intel_pmu_lbr_restore(void *ctx)
wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
}
-static __always_inline bool
-lbr_is_reset_in_cstate(struct x86_perf_task_context *task_ctx)
+static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
{
- return !rdlbr_from(task_ctx->tos);
+ return !rdlbr_from(((struct x86_perf_task_context *)ctx)->tos);
}
-static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
+static void __intel_pmu_lbr_restore(void *ctx)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (task_ctx->opt.lbr_callstack_users == 0 ||
- task_ctx->opt.lbr_stack_state == LBR_NONE) {
+ if (task_context_opt(ctx)->lbr_callstack_users == 0 ||
+ task_context_opt(ctx)->lbr_stack_state == LBR_NONE) {
intel_pmu_lbr_reset();
return;
}
@@ -376,16 +375,16 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
* - No one else touched them, and
* - Was not cleared in Cstate
*/
- if ((task_ctx == cpuc->last_task_ctx) &&
- (task_ctx->opt.log_id == cpuc->last_log_id) &&
- !lbr_is_reset_in_cstate(task_ctx)) {
- task_ctx->opt.lbr_stack_state = LBR_NONE;
+ if ((ctx == cpuc->last_task_ctx) &&
+ (task_context_opt(ctx)->log_id == cpuc->last_log_id) &&
+ !lbr_is_reset_in_cstate(ctx)) {
+ task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
return;
}
- x86_pmu.lbr_restore(task_ctx);
+ x86_pmu.lbr_restore(ctx);
- task_ctx->opt.lbr_stack_state = LBR_NONE;
+ task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
}
void intel_pmu_lbr_save(void *ctx)
@@ -415,27 +414,27 @@ void intel_pmu_lbr_save(void *ctx)
rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
}
-static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
+static void __intel_pmu_lbr_save(void *ctx)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (task_ctx->opt.lbr_callstack_users == 0) {
- task_ctx->opt.lbr_stack_state = LBR_NONE;
+ if (task_context_opt(ctx)->lbr_callstack_users == 0) {
+ task_context_opt(ctx)->lbr_stack_state = LBR_NONE;
return;
}
- x86_pmu.lbr_save(task_ctx);
+ x86_pmu.lbr_save(ctx);
- task_ctx->opt.lbr_stack_state = LBR_VALID;
+ task_context_opt(ctx)->lbr_stack_state = LBR_VALID;
- cpuc->last_task_ctx = task_ctx;
- cpuc->last_log_id = ++task_ctx->opt.log_id;
+ cpuc->last_task_ctx = ctx;
+ cpuc->last_log_id = ++task_context_opt(ctx)->log_id;
}
void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
struct perf_event_context *next)
{
- struct x86_perf_task_context *prev_ctx_data, *next_ctx_data;
+ void *prev_ctx_data, *next_ctx_data;
swap(prev->task_ctx_data, next->task_ctx_data);
@@ -451,14 +450,14 @@ void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
if (!prev_ctx_data || !next_ctx_data)
return;
- swap(prev_ctx_data->opt.lbr_callstack_users,
- next_ctx_data->opt.lbr_callstack_users);
+ swap(task_context_opt(prev_ctx_data)->lbr_callstack_users,
+ task_context_opt(next_ctx_data)->lbr_callstack_users);
}
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- struct x86_perf_task_context *task_ctx;
+ void *task_ctx;
if (!cpuc->lbr_users)
return;
@@ -495,7 +494,6 @@ static inline bool branch_user_callstack(unsigned br_sel)
void intel_pmu_lbr_add(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- struct x86_perf_task_context *task_ctx;
if (!x86_pmu.lbr_nr)
return;
@@ -505,10 +503,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
cpuc->br_sel = event->hw.branch_reg.reg;
- if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
- task_ctx = event->ctx->task_ctx_data;
- task_ctx->opt.lbr_callstack_users++;
- }
+ if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data)
+ task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++;
/*
* Request pmu::sched_task() callback, which will fire inside the
@@ -539,16 +535,13 @@ void intel_pmu_lbr_add(struct perf_event *event)
void intel_pmu_lbr_del(struct perf_event *event)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- struct x86_perf_task_context *task_ctx;
if (!x86_pmu.lbr_nr)
return;
if (branch_user_callstack(cpuc->br_sel) &&
- event->ctx->task_ctx_data) {
- task_ctx = event->ctx->task_ctx_data;
- task_ctx->opt.lbr_callstack_users--;
- }
+ event->ctx->task_ctx_data)
+ task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--;
if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
cpuc->lbr_select = 0;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 96d73cd..7dbf148 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -247,7 +247,7 @@ struct cpu_hw_events {
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
u64 br_sel;
- struct x86_perf_task_context *last_task_ctx;
+ void *last_task_ctx;
int last_log_id;
int lbr_select;
@@ -800,6 +800,11 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \
struct pmu *x86_get_pmu(void);
extern struct x86_pmu x86_pmu __read_mostly;
+static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
+{
+ return &((struct x86_perf_task_context *)ctx)->opt;
+}
+
static inline bool x86_pmu_has_lbr_callstack(void)
{
return x86_pmu.lbr_sel_map &&
next prev parent reply other threads:[~2020-07-08 9:52 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-bot2 for Kan Liang [this message]
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 ` [PATCH V3 09/23] perf/x86/intel/lbr: Support LBR_CTL kan.liang
2020-07-08 9:51 ` [tip: perf/core] " 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=159420191288.4006.3420651578991456355.tip-bot2@tip-bot2 \
--to=tip-bot2@linutronix.de \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=x86@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).