| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210828003558.713983-8-seanjc@google.com>
Date: Fri, 27 Aug 2021 17:35:52 -0700
From: Sean Christopherson <seanjc@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Will Deacon <will@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Catalin Marinas <catalin.marinas@....com>,
Marc Zyngier <maz@...nel.org>, Guo Ren <guoren@...nel.org>,
Nick Hu <nickhu@...estech.com>,
Greentime Hu <green.hu@...il.com>,
Vincent Chen <deanbo422@...il.com>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Thomas Gleixner <tglx@...utronix.de>,
Borislav Petkov <bp@...en8.de>, x86@...nel.org,
Paolo Bonzini <pbonzini@...hat.com>,
Boris Ostrovsky <boris.ostrovsky@...cle.com>,
Juergen Gross <jgross@...e.com>
Cc: Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
James Morse <james.morse@....com>,
Alexandru Elisei <alexandru.elisei@....com>,
Suzuki K Poulose <suzuki.poulose@....com>,
"H. Peter Anvin" <hpa@...or.com>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Stefano Stabellini <sstabellini@...nel.org>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, kvmarm@...ts.cs.columbia.edu,
linux-csky@...r.kernel.org, linux-riscv@...ts.infradead.org,
kvm@...r.kernel.org, xen-devel@...ts.xenproject.org,
Artem Kashkanov <artem.kashkanov@...el.com>,
Like Xu <like.xu.linux@...il.com>,
Zhu Lingshan <lingshan.zhu@...el.com>
Subject: [PATCH v2 07/13] perf/core: Use static_call to optimize perf_guest_info_callbacks
From: Like Xu <like.xu@...ux.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@...radead.org>
Originally-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Signed-off-by: Like Xu <like.xu@...ux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@...el.com>
[sean: split out patch, drop __weak, tweak updaters, rewrite changelog]
Signed-off-by: Sean Christopherson <seanjc@...gle.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
Powered by blists - more mailing lists