From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Jim Mattson <jmattson@google.com>,
Maxim Levitsky <mlevitsk@redhat.com>,
Oliver Upton <oupton@google.com>, Peter Shier <pshier@google.com>
Subject: [PATCH v4 00/24] KVM: x86: Event/exception fixes and cleanups
Date: Sat, 23 Jul 2022 00:51:13 +0000 [thread overview]
Message-ID: <20220723005137.1649592-1-seanjc@google.com> (raw)
The main goal of this series is to fix KVM's longstanding bug of not
honoring L1's exception intercepts wants when handling an exception that
occurs during delivery of a different exception. E.g. if L0 and L1 are
using shadow paging, and L2 hits a #PF, and then hits another #PF while
vectoring the first #PF due to _L1_ not having a shadow page for the IDT,
KVM needs to check L1's intercepts before morphing the #PF => #PF => #DF
so that the #PF is routed to L1, not injected into L2 as a #DF.
nVMX has hacked around the bug for years by overriding the #PF injector
for shadow paging to go straight to VM-Exit, and nSVM has started doing
the same. The hacks mostly work, but they're incomplete, confusing, and
lead to other hacky code, e.g. bailing from the emulator because #PF
injection forced a VM-Exit and suddenly KVM is back in L1.
v4:
- Collect reviews. [Maxim]
- Fix a bug where an intermediate patch dropped the async #PF token
and used a stale payload. [Maxim]
- Tweak comments to call out that AMD CPUs generate error codes with
bits 31:16 != 0. [Maxim]
v3:
- https://lore.kernel.org/all/20220715204226.3655170-1-seanjc@google.com
- Collect reviews. [Maxim, Jim]
- Split a few patches into more consumable chunks. [Maxim]
- Document that KVM doesn't correctly handle SMI+MTF (or SMI priority). [Maxim]
- Add comment to document the instruction boundary (event window) aspect
of block_nested_events. [Maxim]
- Add a patch to rename inject_pending_events() and add a comment to
document KVM's not-quite-architecturally-correct handing of instruction
boundaries and asynchronous events. [Maxim]
v2:
- https://lore.kernel.org/all/20220614204730.3359543-1-seanjc@google.com
- Rebased to kvm/queue (commit 8baacf67c76c) + selftests CPUID
overhaul.
https://lore.kernel.org/all/20220614200707.3315957-1-seanjc@google.com
- Treat KVM_REQ_TRIPLE_FAULT as a pending exception.
v1: https://lore.kernel.org/all/20220614204730.3359543-1-seanjc@google.com
Sean Christopherson (24):
KVM: nVMX: Unconditionally purge queued/injected events on nested
"exit"
KVM: VMX: Drop bits 31:16 when shoving exception error code into VMCS
KVM: x86: Don't check for code breakpoints when emulating on exception
KVM: nVMX: Treat General Detect #DB (DR7.GD=1) as fault-like
KVM: nVMX: Prioritize TSS T-flag #DBs over Monitor Trap Flag
KVM: x86: Treat #DBs from the emulator as fault-like (code and
DR7.GD=1)
KVM: x86: Use DR7_GD macro instead of open coding check in emulator
KVM: nVMX: Ignore SIPI that arrives in L2 when vCPU is not in WFS
KVM: nVMX: Unconditionally clear mtf_pending on nested VM-Exit
KVM: VMX: Inject #PF on ENCLS as "emulated" #PF
KVM: x86: Rename kvm_x86_ops.queue_exception to inject_exception
KVM: x86: Make kvm_queued_exception a properly named, visible struct
KVM: x86: Formalize blocking of nested pending exceptions
KVM: x86: Use kvm_queue_exception_e() to queue #DF
KVM: x86: Hoist nested event checks above event injection logic
KVM: x86: Evaluate ability to inject SMI/NMI/IRQ after potential
VM-Exit
KVM: nVMX: Add a helper to identify low-priority #DB traps
KVM: nVMX: Document priority of all known events on Intel CPUs
KVM: x86: Morph pending exceptions to pending VM-Exits at queue time
KVM: x86: Treat pending TRIPLE_FAULT requests as pending exceptions
KVM: VMX: Update MTF and ICEBP comments to document KVM's subtle
behavior
KVM: x86: Rename inject_pending_events() to
kvm_check_and_inject_events()
KVM: selftests: Use uapi header to get VMX and SVM exit reasons/codes
KVM: selftests: Add an x86-only test to verify nested exception
queueing
arch/x86/include/asm/kvm-x86-ops.h | 2 +-
arch/x86/include/asm/kvm_host.h | 35 +-
arch/x86/kvm/emulate.c | 3 +-
arch/x86/kvm/svm/nested.c | 110 ++---
arch/x86/kvm/svm/svm.c | 20 +-
arch/x86/kvm/vmx/nested.c | 331 ++++++++-----
arch/x86/kvm/vmx/sgx.c | 2 +-
arch/x86/kvm/vmx/vmx.c | 54 ++-
arch/x86/kvm/x86.c | 450 ++++++++++++------
arch/x86/kvm/x86.h | 11 +-
tools/testing/selftests/kvm/.gitignore | 1 +
tools/testing/selftests/kvm/Makefile | 1 +
.../selftests/kvm/include/x86_64/svm_util.h | 7 +-
.../selftests/kvm/include/x86_64/vmx.h | 51 +-
.../kvm/x86_64/nested_exceptions_test.c | 295 ++++++++++++
15 files changed, 953 insertions(+), 420 deletions(-)
create mode 100644 tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
base-commit: 1a4d88a361af4f2e91861d632c6a1fe87a9665c2
--
2.37.1.359.gd136c6c3e2-goog
next reply other threads:[~2022-07-23 0:51 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-23 0:51 Sean Christopherson [this message]
2022-07-23 0:51 ` [PATCH v4 01/24] KVM: nVMX: Unconditionally purge queued/injected events on nested "exit" Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 02/24] KVM: VMX: Drop bits 31:16 when shoving exception error code into VMCS Sean Christopherson
2022-08-01 16:00 ` Maxim Levitsky
2022-07-23 0:51 ` [PATCH v4 03/24] KVM: x86: Don't check for code breakpoints when emulating on exception Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 04/24] KVM: nVMX: Treat General Detect #DB (DR7.GD=1) as fault-like Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 05/24] KVM: nVMX: Prioritize TSS T-flag #DBs over Monitor Trap Flag Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 06/24] KVM: x86: Treat #DBs from the emulator as fault-like (code and DR7.GD=1) Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 07/24] KVM: x86: Use DR7_GD macro instead of open coding check in emulator Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 08/24] KVM: nVMX: Ignore SIPI that arrives in L2 when vCPU is not in WFS Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 09/24] KVM: nVMX: Unconditionally clear mtf_pending on nested VM-Exit Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 10/24] KVM: VMX: Inject #PF on ENCLS as "emulated" #PF Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 11/24] KVM: x86: Rename kvm_x86_ops.queue_exception to inject_exception Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 12/24] KVM: x86: Make kvm_queued_exception a properly named, visible struct Sean Christopherson
2022-08-01 16:10 ` Maxim Levitsky
2022-07-23 0:51 ` [PATCH v4 13/24] KVM: x86: Formalize blocking of nested pending exceptions Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 14/24] KVM: x86: Use kvm_queue_exception_e() to queue #DF Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 15/24] KVM: x86: Hoist nested event checks above event injection logic Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 16/24] KVM: x86: Evaluate ability to inject SMI/NMI/IRQ after potential VM-Exit Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 17/24] KVM: nVMX: Add a helper to identify low-priority #DB traps Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 18/24] KVM: nVMX: Document priority of all known events on Intel CPUs Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 19/24] KVM: x86: Morph pending exceptions to pending VM-Exits at queue time Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 20/24] KVM: x86: Treat pending TRIPLE_FAULT requests as pending exceptions Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 21/24] KVM: VMX: Update MTF and ICEBP comments to document KVM's subtle behavior Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 22/24] KVM: x86: Rename inject_pending_events() to kvm_check_and_inject_events() Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 23/24] KVM: selftests: Use uapi header to get VMX and SVM exit reasons/codes Sean Christopherson
2022-07-23 0:51 ` [PATCH v4 24/24] KVM: selftests: Add an x86-only test to verify nested exception queueing Sean Christopherson
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=20220723005137.1649592-1-seanjc@google.com \
--to=seanjc@google.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mlevitsk@redhat.com \
--cc=oupton@google.com \
--cc=pbonzini@redhat.com \
--cc=pshier@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
all inboxes | Powered by JetHome®