All of lore.kernel.org
 help / color / mirror / Atom feed
From: Rob Herring <robh@kernel.org>
To: Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>
Cc: linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Raphael Gault <raphael.gault@arm.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Ian Rogers <irogers@google.com>,
	honnappa.nagarahalli@arm.com,
	Itaru Kitayama <itaru.kitayama@gmail.com>
Subject: [PATCH v4 2/9] arm64: perf: Enable pmu counter direct access for perf event on armv8
Date: Thu,  1 Oct 2020 09:01:09 -0500	[thread overview]
Message-ID: <20201001140116.651970-3-robh@kernel.org> (raw)
In-Reply-To: <20201001140116.651970-1-robh@kernel.org>

From: Raphael Gault <raphael.gault@arm.com>

Keep track of event opened with direct access to the hardware counters
and modify permissions while they are open.

The strategy used here is the same which x86 uses: everytime an event
is mapped, the permissions are set if required. The atomic field added
in the mm_context helps keep track of the different event opened and
de-activate the permissions when all are unmapped.
We also need to update the permissions in the context switch code so
that tasks keep the right permissions.

Signed-off-by: Raphael Gault <raphael.gault@arm.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
v2:
 - Move mapped/unmapped into arm64 code. Fixes arm32.
 - Rebase on cap_user_time_short changes

Changes from Raphael's v4:
  - Drop homogeneous check
  - Disable access for chained counters
  - Set pmc_width in user page
---
 arch/arm64/include/asm/mmu.h         |  5 ++++
 arch/arm64/include/asm/mmu_context.h |  2 ++
 arch/arm64/include/asm/perf_event.h  | 14 ++++++++++
 arch/arm64/kernel/perf_event.c       | 41 ++++++++++++++++++++++++++++
 4 files changed, 62 insertions(+)

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index a7a5ecaa2e83..52cfdb676f06 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -19,6 +19,11 @@
 
 typedef struct {
 	atomic64_t	id;
+	/*
+	 * non-zero if userspace have access to hardware
+	 * counters directly.
+	 */
+	atomic_t	pmu_direct_access;
 #ifdef CONFIG_COMPAT
 	void		*sigpage;
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index f2d7537d6f83..d24589ecb07a 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -21,6 +21,7 @@
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
+#include <asm/perf_event.h>
 #include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
@@ -224,6 +225,7 @@ static inline void __switch_mm(struct mm_struct *next)
 	}
 
 	check_and_switch_context(next);
+	perf_switch_user_access(next);
 }
 
 static inline void
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2c2d7dbe8a02..a025d9595d51 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -8,6 +8,7 @@
 
 #include <asm/stack_pointer.h>
 #include <asm/ptrace.h>
+#include <linux/mm_types.h>
 
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
@@ -251,4 +252,17 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	(regs)->pstate = PSR_MODE_EL1h;	\
 }
 
+static inline void perf_switch_user_access(struct mm_struct *mm)
+{
+	if (!IS_ENABLED(CONFIG_PERF_EVENTS))
+		return;
+
+	if (atomic_read(&mm->context.pmu_direct_access)) {
+		write_sysreg(ARMV8_PMU_USERENR_ER|ARMV8_PMU_USERENR_CR,
+			     pmuserenr_el0);
+	} else {
+		write_sysreg(0, pmuserenr_el0);
+	}
+}
+
 #endif
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index e14f360a7883..8344dc030823 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -834,6 +834,41 @@ static int armv8pmu_access_event_idx(struct perf_event *event)
 	return event->hw.idx;
 }
 
+static void refresh_pmuserenr(void *mm)
+{
+	perf_switch_user_access(mm);
+}
+
+static void armv8pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * pmu_direct_access > 1 and return all the way back to
+	 * userspace with user access disabled while another task is still
+	 * doing on_each_cpu_mask() to enable user access.
+	 *
+	 * For now, this can't happen because all callers hold mmap_lock
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_write(&mm->mmap_lock);
+
+	if (atomic_inc_return(&mm->context.pmu_direct_access) == 1)
+		on_each_cpu(refresh_pmuserenr, mm, 1);
+}
+
+static void armv8pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	if (atomic_dec_and_test(&mm->context.pmu_direct_access))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pmuserenr, NULL, 1);
+}
+
 /*
  * Add an event filter to a given event.
  */
@@ -1058,6 +1093,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
 	cpu_pmu->pmu.event_idx		= armv8pmu_access_event_idx;
+	cpu_pmu->pmu.event_mapped	= armv8pmu_event_mapped;
+	cpu_pmu->pmu.event_unmapped	= armv8pmu_event_unmapped;
 
 	cpu_pmu->name			= name;
 	cpu_pmu->map_event		= map_event;
@@ -1218,6 +1255,10 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
 	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = !!(event->hw.flags & ARMPMU_EL0_RD_CNTR);
+
+	if (userpg->cap_user_rdpmc)
+		userpg->pmc_width = armv8pmu_event_is_64bit(event) ? 64 : 32;
 
 	do {
 		rd = sched_clock_read_begin(&seq);
-- 
2.25.1


WARNING: multiple messages have this Message-ID
From: Rob Herring <robh@kernel.org>
To: Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
	Ian Rogers <irogers@google.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	linux-kernel@vger.kernel.org, honnappa.nagarahalli@arm.com,
	Raphael Gault <raphael.gault@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Itaru Kitayama <itaru.kitayama@gmail.com>,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 2/9] arm64: perf: Enable pmu counter direct access for perf event on armv8
Date: Thu,  1 Oct 2020 09:01:09 -0500	[thread overview]
Message-ID: <20201001140116.651970-3-robh@kernel.org> (raw)
In-Reply-To: <20201001140116.651970-1-robh@kernel.org>

From: Raphael Gault <raphael.gault@arm.com>

Keep track of event opened with direct access to the hardware counters
and modify permissions while they are open.

The strategy used here is the same which x86 uses: everytime an event
is mapped, the permissions are set if required. The atomic field added
in the mm_context helps keep track of the different event opened and
de-activate the permissions when all are unmapped.
We also need to update the permissions in the context switch code so
that tasks keep the right permissions.

Signed-off-by: Raphael Gault <raphael.gault@arm.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
v2:
 - Move mapped/unmapped into arm64 code. Fixes arm32.
 - Rebase on cap_user_time_short changes

Changes from Raphael's v4:
  - Drop homogeneous check
  - Disable access for chained counters
  - Set pmc_width in user page
---
 arch/arm64/include/asm/mmu.h         |  5 ++++
 arch/arm64/include/asm/mmu_context.h |  2 ++
 arch/arm64/include/asm/perf_event.h  | 14 ++++++++++
 arch/arm64/kernel/perf_event.c       | 41 ++++++++++++++++++++++++++++
 4 files changed, 62 insertions(+)

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index a7a5ecaa2e83..52cfdb676f06 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -19,6 +19,11 @@
 
 typedef struct {
 	atomic64_t	id;
+	/*
+	 * non-zero if userspace have access to hardware
+	 * counters directly.
+	 */
+	atomic_t	pmu_direct_access;
 #ifdef CONFIG_COMPAT
 	void		*sigpage;
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index f2d7537d6f83..d24589ecb07a 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -21,6 +21,7 @@
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
+#include <asm/perf_event.h>
 #include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
@@ -224,6 +225,7 @@ static inline void __switch_mm(struct mm_struct *next)
 	}
 
 	check_and_switch_context(next);
+	perf_switch_user_access(next);
 }
 
 static inline void
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2c2d7dbe8a02..a025d9595d51 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -8,6 +8,7 @@
 
 #include <asm/stack_pointer.h>
 #include <asm/ptrace.h>
+#include <linux/mm_types.h>
 
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
@@ -251,4 +252,17 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	(regs)->pstate = PSR_MODE_EL1h;	\
 }
 
+static inline void perf_switch_user_access(struct mm_struct *mm)
+{
+	if (!IS_ENABLED(CONFIG_PERF_EVENTS))
+		return;
+
+	if (atomic_read(&mm->context.pmu_direct_access)) {
+		write_sysreg(ARMV8_PMU_USERENR_ER|ARMV8_PMU_USERENR_CR,
+			     pmuserenr_el0);
+	} else {
+		write_sysreg(0, pmuserenr_el0);
+	}
+}
+
 #endif
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index e14f360a7883..8344dc030823 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -834,6 +834,41 @@ static int armv8pmu_access_event_idx(struct perf_event *event)
 	return event->hw.idx;
 }
 
+static void refresh_pmuserenr(void *mm)
+{
+	perf_switch_user_access(mm);
+}
+
+static void armv8pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * pmu_direct_access > 1 and return all the way back to
+	 * userspace with user access disabled while another task is still
+	 * doing on_each_cpu_mask() to enable user access.
+	 *
+	 * For now, this can't happen because all callers hold mmap_lock
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_write(&mm->mmap_lock);
+
+	if (atomic_inc_return(&mm->context.pmu_direct_access) == 1)
+		on_each_cpu(refresh_pmuserenr, mm, 1);
+}
+
+static void armv8pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	if (atomic_dec_and_test(&mm->context.pmu_direct_access))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pmuserenr, NULL, 1);
+}
+
 /*
  * Add an event filter to a given event.
  */
@@ -1058,6 +1093,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
 	cpu_pmu->pmu.event_idx		= armv8pmu_access_event_idx;
+	cpu_pmu->pmu.event_mapped	= armv8pmu_event_mapped;
+	cpu_pmu->pmu.event_unmapped	= armv8pmu_event_unmapped;
 
 	cpu_pmu->name			= name;
 	cpu_pmu->map_event		= map_event;
@@ -1218,6 +1255,10 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
 	userpg->cap_user_time_short = 0;
+	userpg->cap_user_rdpmc = !!(event->hw.flags & ARMPMU_EL0_RD_CNTR);
+
+	if (userpg->cap_user_rdpmc)
+		userpg->pmc_width = armv8pmu_event_is_64bit(event) ? 64 : 32;
 
 	do {
 		rd = sched_clock_read_begin(&seq);
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2020-10-01 14:01 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-01 14:01 [PATCH v4 0/9] libperf and arm64 userspace counter access support Rob Herring
2020-10-01 14:01 ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 1/9] arm64: pmu: Add function implementation to update event index in userpage Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` Rob Herring [this message]
2020-10-01 14:01   ` [PATCH v4 2/9] arm64: perf: Enable pmu counter direct access for perf event on armv8 Rob Herring
2020-11-13 18:06   ` Mark Rutland
2020-11-13 18:06     ` Mark Rutland
2020-11-19 18:35     ` Rob Herring
2020-11-19 18:35       ` Rob Herring
2020-11-19 19:15     ` Will Deacon
2020-11-19 19:15       ` Will Deacon
2020-11-20 20:03       ` Rob Herring
2020-11-20 20:03         ` Rob Herring
2020-11-20 22:08         ` Rob Herring
2020-11-20 22:08           ` Rob Herring
2020-12-02 14:57         ` Rob Herring
2020-12-02 14:57           ` Rob Herring
2021-01-07  0:17           ` Rob Herring
2021-01-07  0:17             ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 3/9] tools/include: Add an initial math64.h Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 4/9] libperf: Add libperf_evsel__mmap() Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-14 11:05   ` Jiri Olsa
2020-10-14 11:05     ` Jiri Olsa
2020-10-16 21:39     ` Rob Herring
2020-10-16 21:39       ` Rob Herring
2020-10-19 20:15       ` Jiri Olsa
2020-10-19 20:15         ` Jiri Olsa
2020-10-20 14:38         ` Rob Herring
2020-10-20 14:38           ` Rob Herring
2020-10-20 15:35           ` Jiri Olsa
2020-10-20 15:35             ` Jiri Olsa
2020-10-20 17:11             ` Rob Herring
2020-10-20 17:11               ` Rob Herring
2020-10-21 11:24               ` Jiri Olsa
2020-10-21 11:24                 ` Jiri Olsa
2020-11-05 16:19                 ` Rob Herring
2020-11-05 16:19                   ` Rob Herring
2020-11-05 22:41                   ` Jiri Olsa
2020-11-05 22:41                     ` Jiri Olsa
2020-11-06 21:56                     ` Rob Herring
2020-11-06 21:56                       ` Rob Herring
2020-11-11 12:00                       ` Jiri Olsa
2020-11-11 12:00                         ` Jiri Olsa
2020-11-11 14:50                         ` Rob Herring
2020-11-11 14:50                           ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 5/9] libperf: tests: Add support for verbose printing Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 6/9] libperf: Add support for user space counter access Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 7/9] libperf: Add arm64 support to perf_mmap__read_self() Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 8/9] perf: arm64: Add test for userspace counter access on heterogeneous systems Rob Herring
2020-10-01 14:01   ` Rob Herring
2020-10-01 14:01 ` [PATCH v4 9/9] Documentation: arm64: Document PMU counters access from userspace Rob Herring
2020-10-01 14:01   ` Rob Herring

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=20201001140116.651970-3-robh@kernel.org \
    --to=robh@kernel.org \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=catalin.marinas@arm.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=irogers@google.com \
    --cc=itaru.kitayama@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=raphael.gault@arm.com \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v4 2/9] arm64: perf: Enable pmu counter direct access for perf event on armv8' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.