linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Like Xu <like.xu.linux@gmail.com>
To: Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>
Cc: Jim Mattson <jmattson@google.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Subject: [PATCH v2 4/7] KVM: x86/pmu: Don't generate PEBS records for emulated instructions
Date: Thu, 21 Jul 2022 18:35:45 +0800	[thread overview]
Message-ID: <20220721103549.49543-5-likexu@tencent.com> (raw)
In-Reply-To: <20220721103549.49543-1-likexu@tencent.com>

From: Like Xu <likexu@tencent.com>

KVM will accumulate an enabled counter for at least INSTRUCTIONS or
BRANCH_INSTRUCTION hw event from any KVM emulated instructions,
generating emulated overflow interrupt on counter overflow, which
in theory should also happen when the PEBS counter overflows but
it currently lacks this part of the underlying support (e.g. through
software injection of records in the irq context or a lazy approach).

In this case, KVM skips the injection of this BUFFER_OVF PMI (effectively
dropping one PEBS record) and let the overflow counter move on. The loss
of a single sample does not introduce a loss of accuracy, but is easily
noticeable for certain specific instructions.

This issue is expected to be addressed along with the issue
of PEBS cross-mapped counters with a slow-path proposal.

Fixes: 79f3e3b58386 ("KVM: x86/pmu: Reprogram PEBS event to emulate guest PEBS counter")
Signed-off-by: Like Xu <likexu@tencent.com>
---
 arch/x86/kvm/pmu.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 02f9e4f245bd..390d697efde1 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -106,9 +106,19 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 		return;
 
 	if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
-		/* Indicate PEBS overflow PMI to guest. */
-		skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
-					      (unsigned long *)&pmu->global_status);
+		if (!in_pmi) {
+			/*
+			 * TODO: KVM is currently _choosing_ to not generate records
+			 * for emulated instructions, avoiding BUFFER_OVF PMI when
+			 * there are no records. Strictly speaking, it should be done
+			 * as well in the right context to improve sampling accuracy.
+			 */
+			skip_pmi = true;
+		} else {
+			/* Indicate PEBS overflow PMI to guest. */
+			skip_pmi = __test_and_set_bit(GLOBAL_STATUS_BUFFER_OVF_BIT,
+						      (unsigned long *)&pmu->global_status);
+		}
 	} else {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 	}
-- 
2.37.1


  parent reply	other threads:[~2022-07-21 10:36 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-21 10:35 [PATCH v2 0/7] KVM: x86/pmu: Fix some corner cases including Intel PEBS Like Xu
2022-07-21 10:35 ` [PATCH v2 1/7] perf/x86/core: Update x86_pmu.pebs_capable for ICELAKE_{X,D} Like Xu
2022-08-12  7:52   ` Paolo Bonzini
2022-08-15  9:31     ` Peter Zijlstra
2022-08-15  9:43       ` Like Xu
2022-08-15 11:51         ` Peter Zijlstra
2022-08-15 12:48           ` Like Xu
2022-08-15 13:14             ` Peter Zijlstra
2022-08-15 13:06           ` Liang, Kan
2022-08-15 14:30             ` Peter Zijlstra
2022-08-16 11:57               ` Like Xu
2022-07-21 10:35 ` [PATCH v2 2/7] perf/x86/core: Completely disable guest PEBS via guest's global_ctrl Like Xu
2022-07-21 10:35 ` [PATCH v2 3/7] KVM: x86/pmu: Avoid setting BIT_ULL(-1) to pmu->host_cross_mapped_mask Like Xu
2022-07-21 10:35 ` Like Xu [this message]
2022-07-21 10:35 ` [PATCH v2 5/7] KVM: x86/pmu: Avoid using PEBS perf_events for normal counters Like Xu
2022-07-21 10:35 ` [PATCH v2 6/7] KVM: x86/pmu: Defer reprogram_counter() to kvm_pmu_handle_event() Like Xu
2022-07-21 10:35 ` [PATCH v2 7/7] KVM: x86/pmu: Defer counter emulated overflow via pmc->stale_counter Like Xu
2022-07-21 10:35 ` [kvm-unit-tests PATCH] x86: Add tests for Guest Processor Event Based Sampling (PEBS) Like Xu
2022-07-27 22:42   ` Sean Christopherson
2022-07-28 11:31     ` Like Xu
2022-08-02 11:07 ` [PATCH v2 0/7] KVM: x86/pmu: Fix some corner cases including Intel PEBS Like Xu
2022-08-11  7:10   ` Wanpeng Li

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=20220721103549.49543-5-likexu@tencent.com \
    --to=like.xu.linux@gmail.com \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=seanjc@google.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).