LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Sean Christopherson <seanjc@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Marc Zyngier <maz@kernel.org>, Guo Ren <guoren@kernel.org>,
	Nick Hu <nickhu@andestech.com>, Greentime Hu <green.hu@gmail.com>,
	Vincent Chen <deanbo422@gmail.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Thomas Gleixner <tglx@linutronix.de>,
	Borislav Petkov <bp@alien8.de>,
	x86@kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Juergen Gross <jgross@suse.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	James Morse <james.morse@arm.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Sean Christopherson <seanjc@google.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	Stefano Stabellini <sstabellini@kernel.org>,
	linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kvmarm@lists.cs.columbia.edu, linux-csky@vger.kernel.org,
	linux-riscv@lists.infradead.org, kvm@vger.kernel.org,
	xen-devel@lists.xenproject.org,
	Artem Kashkanov <artem.kashkanov@intel.com>,
	Like Xu <like.xu.linux@gmail.com>,
	Zhu Lingshan <lingshan.zhu@intel.com>
Subject: [PATCH v2 07/13] perf/core: Use static_call to optimize perf_guest_info_callbacks
Date: Fri, 27 Aug 2021 17:35:52 -0700	[thread overview]
Message-ID: <20210828003558.713983-8-seanjc@google.com> (raw)
In-Reply-To: <20210828003558.713983-1-seanjc@google.com>

From: Like Xu <like.xu@linux.intel.com>

Use static_call to optimize perf's guest callbacks on arm64 and x86,
which are now the only architectures that define the callbacks.  Use
DEFINE_STATIC_CALL_RET0 as the default/NULL for all guest callbacks, as
the callback semantics are that a return value '0' means "not in guest".

static_call obviously avoids the overhead of CONFIG_RETPOLINE=y, but is
also advantageous versus other solutions, e.g. per-cpu callbacks, in that
a per-cpu memory load is not needed to detect the !guest case.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
[sean: split out patch, drop __weak, tweak updaters, rewrite changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kernel/perf_callchain.c | 31 +++++++++++++++---------
 arch/x86/events/core.c             | 38 ++++++++++++++++++++++--------
 arch/x86/events/intel/core.c       |  7 +++---
 include/linux/perf_event.h         |  9 +------
 kernel/events/core.c               |  2 ++
 5 files changed, 54 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 274dc3e11b6d..18cf6e608778 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2015 ARM Limited
  */
 #include <linux/perf_event.h>
+#include <linux/static_call.h>
 #include <linux/uaccess.h>
 
 #include <asm/pointer_auth.h>
@@ -99,12 +100,24 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
 }
 #endif /* CONFIG_COMPAT */
 
+DEFINE_STATIC_CALL_RET0(arm64_guest_state, *(perf_guest_cbs->state));
+DEFINE_STATIC_CALL_RET0(arm64_guest_get_ip, *(perf_guest_cbs->get_ip));
+
+void arch_perf_update_guest_cbs(struct perf_guest_info_callbacks *guest_cbs)
+{
+	if (guest_cbs) {
+		static_call_update(arm64_guest_state, guest_cbs->state);
+		static_call_update(arm64_guest_get_ip, guest_cbs->get_ip);
+	} else {
+		static_call_update(arm64_guest_state, (void *)&__static_call_return0);
+		static_call_update(arm64_guest_get_ip, (void *)&__static_call_return0);
+	}
+}
+
 void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
-
-	if (guest_cbs && guest_cbs->state()) {
+	if (static_call(arm64_guest_state)()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -149,10 +162,9 @@ static bool callchain_trace(void *data, unsigned long pc)
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct stackframe frame;
 
-	if (guest_cbs && guest_cbs->state()) {
+	if (static_call(arm64_guest_state)()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -163,18 +175,15 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
-
-	if (guest_cbs && guest_cbs->state())
-		return guest_cbs->get_ip();
+	if (static_call(arm64_guest_state)())
+		return static_call(arm64_guest_get_ip)();
 
 	return instruction_pointer(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
-	unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0;
+	unsigned int guest_state = static_call(arm64_guest_state)();
 	int misc = 0;
 
 	if (guest_state) {
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3a7630fdd340..508a677edd8c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -90,6 +90,29 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
  */
 DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
 
+DEFINE_STATIC_CALL_RET0(x86_guest_state, *(perf_guest_cbs->state));
+DEFINE_STATIC_CALL_RET0(x86_guest_get_ip, *(perf_guest_cbs->get_ip));
+DEFINE_STATIC_CALL_RET0(x86_guest_handle_intel_pt_intr, *(perf_guest_cbs->handle_intel_pt_intr));
+
+void arch_perf_update_guest_cbs(struct perf_guest_info_callbacks *guest_cbs)
+{
+	if (guest_cbs) {
+		static_call_update(x86_guest_state, guest_cbs->state);
+		static_call_update(x86_guest_get_ip, guest_cbs->get_ip);
+	} else {
+		static_call_update(x86_guest_state, (void *)&__static_call_return0);
+		static_call_update(x86_guest_get_ip, (void *)&__static_call_return0);
+	}
+
+	/* Implementing ->handle_intel_pt_intr is optional. */
+	if (guest_cbs && guest_cbs->handle_intel_pt_intr)
+		static_call_update(x86_guest_handle_intel_pt_intr,
+				   guest_cbs->handle_intel_pt_intr);
+	else
+		static_call_update(x86_guest_handle_intel_pt_intr,
+				   (void *)&__static_call_return0);
+}
+
 u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2761,11 +2784,10 @@ static bool perf_hw_regs(struct pt_regs *regs)
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (guest_cbs && guest_cbs->state()) {
+	if (static_call(x86_guest_state)()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2865,11 +2887,10 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
 
-	if (guest_cbs && guest_cbs->state()) {
+	if (static_call(x86_guest_state)()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2946,18 +2967,15 @@ static unsigned long code_segment_base(struct pt_regs *regs)
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
-
-	if (guest_cbs && guest_cbs->state())
-		return guest_cbs->get_ip();
+	if (static_call(x86_guest_state)())
+		return static_call(x86_guest_get_ip)();
 
 	return regs->ip + code_segment_base(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
-	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
-	unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0;
+	unsigned int guest_state = static_call(x86_guest_state)();
 	int misc = 0;
 
 	if (guest_state) {
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 524ad1f747bd..fb1bd7a0e1a6 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2782,11 +2782,12 @@ static void intel_pmu_reset(void)
 	local_irq_restore(flags);
 }
 
+DECLARE_STATIC_CALL(x86_guest_handle_intel_pt_intr, *(perf_guest_cbs->handle_intel_pt_intr));
+
 static int handle_pmi_common(struct pt_regs *regs, u64 status)
 {
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct perf_guest_info_callbacks *guest_cbs;
 	int bit;
 	int handled = 0;
 	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
@@ -2853,9 +2854,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
 		handled++;
-
-		guest_cbs = perf_get_guest_cbs();
-		if (likely(!guest_cbs || !guest_cbs->handle_intel_pt_intr()))
+		if (!static_call(x86_guest_handle_intel_pt_intr)())
 			intel_pt_interrupt();
 	}
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a5d5893b80b0..3fa1014218f4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1240,14 +1240,7 @@ extern void perf_event_bpf_event(struct bpf_prog *prog,
 
 #ifdef CONFIG_HAVE_GUEST_PERF_EVENTS
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
-static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void)
-{
-	/* Reg/unreg perf_guest_cbs waits for readers via synchronize_rcu(). */
-	lockdep_assert_preemption_disabled();
-
-	/* Prevent reloading between a !NULL check and dereferences. */
-	return READ_ONCE(perf_guest_cbs);
-}
+extern void arch_perf_update_guest_cbs(struct perf_guest_info_callbacks *guest_cbs);
 extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern void perf_unregister_guest_info_callbacks(void);
 #endif /* CONFIG_HAVE_GUEST_PERF_EVENTS */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ec36e7aded89..fb0fd670ab23 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6491,6 +6491,7 @@ void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
 		return;
 
 	WRITE_ONCE(perf_guest_cbs, cbs);
+	arch_perf_update_guest_cbs(cbs);
 	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
@@ -6498,6 +6499,7 @@ EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks);
 void perf_unregister_guest_info_callbacks(void)
 {
 	WRITE_ONCE(perf_guest_cbs, NULL);
+	arch_perf_update_guest_cbs(NULL);
 	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
-- 
2.33.0.259.gc128427fd7-goog


  parent reply	other threads:[~2021-08-28  0:36 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-28  0:35 [PATCH v2 00/13] perf: KVM: Fix, optimize, and clean up callbacks Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 01/13] perf: Ensure perf_guest_cbs aren't reloaded between !NULL check and deref Sean Christopherson
2021-08-28 19:44   ` Peter Zijlstra
2021-09-16 21:41     ` Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 02/13] KVM: x86: Register perf callbacks after calling vendor's hardware_setup() Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 03/13] KVM: x86: Register Processor Trace interrupt hook iff PT enabled in guest Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 04/13] perf: Stop pretending that perf can handle multiple guest callbacks Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 05/13] perf: Force architectures to opt-in to " Sean Christopherson
2021-08-28 19:47   ` Peter Zijlstra
2021-09-16 22:30     ` Sean Christopherson
2021-09-21 16:44     ` Paolo Bonzini
2021-09-21 21:29       ` Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 06/13] perf/core: Rework guest callbacks to prepare for static_call support Sean Christopherson
2021-08-28  0:35 ` Sean Christopherson [this message]
2021-08-28  0:35 ` [PATCH v2 08/13] KVM: x86: Drop current_vcpu for kvm_running_vcpu + kvm_arch_vcpu variable Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 09/13] KVM: x86: More precisely identify NMI from guest when handling PMI Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 10/13] KVM: Move x86's perf guest info callbacks to generic KVM Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 11/13] KVM: x86: Move Intel Processor Trace interrupt handler to vmx.c Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 12/13] KVM: arm64: Convert to the generic perf callbacks Sean Christopherson
2021-08-28  0:35 ` [PATCH v2 13/13] KVM: arm64: Drop perf.c and fold its tiny bits of code into arm.c / pmu.c Sean Christopherson
2021-08-28 20:13 ` [PATCH v2 00/13] perf: KVM: Fix, optimize, and clean up callbacks Peter Zijlstra
2021-09-16 21:37   ` Sean Christopherson
2021-09-17  7:28     ` Peter Zijlstra
2021-09-17 16:53       ` Sean Christopherson
2021-09-20 12:05       ` Paolo Bonzini
2021-09-20 12:22         ` Marc Zyngier
2021-09-20 13:18           ` Paolo Bonzini
2021-09-20 13:40             ` Marc Zyngier
2021-09-20 18:22               ` Paolo Bonzini

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=20210828003558.713983-8-seanjc@google.com \
    --to=seanjc@google.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=alexandru.elisei@arm.com \
    --cc=aou@eecs.berkeley.edu \
    --cc=artem.kashkanov@intel.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=deanbo422@gmail.com \
    --cc=green.hu@gmail.com \
    --cc=guoren@kernel.org \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jgross@suse.com \
    --cc=jmattson@google.com \
    --cc=jolsa@redhat.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=like.xu.linux@gmail.com \
    --cc=lingshan.zhu@intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-csky@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=nickhu@andestech.com \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=sstabellini@kernel.org \
    --cc=suzuki.poulose@arm.com \
    --cc=tglx@linutronix.de \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    --cc=will@kernel.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH v2 07/13] perf/core: Use static_call to optimize perf_guest_info_callbacks' \
    /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 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).