From: Andy Lutomirski <luto@kernel.org>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Joerg Roedel <jroedel@suse.de>, Andy Lutomirski <luto@kernel.org>,
Joerg Roedel <joro@8bytes.org>,
Dave Hansen <dave.hansen@intel.com>,
Tom Lendacky <Thomas.Lendacky@amd.com>,
Mike Stunes <mstunes@vmware.com>,
Dan Williams <dan.j.williams@intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
"H. Peter Anvin" <hpa@zytor.com>, Juergen Gross <JGross@suse.com>,
Jiri Slaby <jslaby@suse.cz>, Kees Cook <keescook@chromium.org>,
kvm list <kvm@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Thomas Hellstrom <thellstrom@vmware.com>,
Linux Virtualization <virtualization@lists.linux-foundation.org>,
X86 ML <x86@kernel.org>,
Sean Christopherson <sean.j.christopherson@intel.com>
Subject: Re: Should SEV-ES #VC use IST? (Re: [PATCH] Allow RDTSC and RDTSCP from userspace)
Date: Tue, 23 Jun 2020 11:26:52 -0700 [thread overview]
Message-ID: <CALCETrWEUXU_BYd5ypF3XC10hSQUJ=XCVz40n3VfcWELS+roTg@mail.gmail.com> (raw)
In-Reply-To: <9e3f9b2a-505e-dfd7-c936-461227b4033e@citrix.com>
On Tue, Jun 23, 2020 at 8:23 AM Andrew Cooper <andrew.cooper3@citrix.com> wrote:
>
> On 23/06/2020 14:03, Peter Zijlstra wrote:
> > On Tue, Jun 23, 2020 at 02:12:37PM +0200, Joerg Roedel wrote:
> >> On Tue, Jun 23, 2020 at 01:50:14PM +0200, Peter Zijlstra wrote:
> >>> If SNP is the sole reason #VC needs to be IST, then I'd strongly urge
> >>> you to only make it IST if/when you try and make SNP happen, not before.
> >> It is not the only reason, when ES guests gain debug register support
> >> then #VC also needs to be IST, because #DB can be promoted into #VC
> >> then, and as #DB is IST for a reason, #VC needs to be too.
> > Didn't I read somewhere that that is only so for Rome/Naples but not for
> > the later chips (Milan) which have #DB pass-through?
>
> I don't know about hardware timelines, but some future part can now opt
> in to having debug registers as part of the encrypted state, and swapped
> by VMExit, which would make debug facilities generally usable, and
> supposedly safe to the #DB infinite loop issues, at which point the
> hypervisor need not intercept #DB for safety reasons.
>
> Its worth nothing that on current parts, the hypervisor can set up debug
> facilities on behalf of the guest (or behind its back) as the DR state
> is unencrypted, but that attempting to intercept #DB will redirect to
> #VC inside the guest and cause fun. (Also spare a thought for 32bit
> kernels which have to cope with userspace singlestepping the SYSENTER
> path with every #DB turning into #VC.)
What do you mean 32-bit? 64-bit kernels have exactly the same
problem. At least the stack is okay, though.
Anyway, since I'm way behind on this thread, here are some thoughts:
First, I plan to implement actual precise recursion detection for the
IST stacks. We'll be able to reliably panic when unallowed recursion
happens.
Second, I don't object *that* strongly to switching to a second #VC
stack if an NMI or MCE happens, but we really need to make sure we
cover *all* the bases. And #VC is distressingly close to "happens at
all kinds of unfortunate times and the guest doesn't actually have
much ability to predice it" right now. So we have #VC + #DB + #VC,
#VC + NMI + #VC, #VC + MCE + #VC, and even worse options. So doing
the shift in a reliable way is not necessarily possible in a clean
way.
Let me contemplate. And maybe produce some code soon.
next prev parent reply other threads:[~2020-06-23 18:27 UTC|newest]
Thread overview: 180+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-19 9:12 [RFC PATCH 00/70 v2] x86: SEV-ES Guest Support Joerg Roedel
2020-03-19 9:12 ` [PATCH 01/70] KVM: SVM: Add GHCB definitions Joerg Roedel
2020-03-23 13:23 ` [PATCH] KVM: SVM: Use __packed shorthard Borislav Petkov
2020-03-24 12:43 ` Joerg Roedel
2020-03-19 9:12 ` [PATCH 02/70] KVM: SVM: Add GHCB Accessor functions Joerg Roedel
2020-03-19 9:13 ` [PATCH 03/70] x86/cpufeatures: Add SEV-ES CPU feature Joerg Roedel
2020-03-19 9:13 ` [PATCH 04/70] x86/traps: Move some definitions to <asm/trap_defs.h> Joerg Roedel
2020-03-19 9:13 ` [PATCH 05/70] x86/insn: Make inat-tables.c suitable for pre-decompression code Joerg Roedel
2020-03-25 15:39 ` Borislav Petkov
2020-03-27 3:02 ` Masami Hiramatsu
2020-04-16 15:24 ` Joerg Roedel
2020-04-17 12:50 ` Masami Hiramatsu
2020-04-17 13:39 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 06/70] x86/umip: Factor out instruction fetch Joerg Roedel
2020-03-26 17:21 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 07/70] x86/umip: Factor out instruction decoding Joerg Roedel
2020-03-26 17:24 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 08/70] x86/insn: Add insn_get_modrm_reg_off() Joerg Roedel
2020-03-27 3:57 ` Masami Hiramatsu
2020-03-19 9:13 ` [PATCH 09/70] x86/insn: Add insn_rep_prefix() helper Joerg Roedel
2020-03-27 3:56 ` Masami Hiramatsu
2020-03-19 9:13 ` [PATCH 10/70] x86/boot/compressed: Fix debug_puthex() parameter type Joerg Roedel
2020-03-19 9:13 ` [PATCH 11/70] x86/boot/compressed/64: Disable red-zone usage Joerg Roedel
2020-03-31 13:16 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 12/70] x86/boot/compressed/64: Add IDT Infrastructure Joerg Roedel
2020-04-07 2:21 ` Arvind Sankar
2020-04-16 13:30 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 13/70] x86/boot/compressed/64: Rename kaslr_64.c to ident_map_64.c Joerg Roedel
2020-03-19 9:13 ` [PATCH 14/70] x86/boot/compressed/64: Add page-fault handler Joerg Roedel
2020-04-02 11:49 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 15/70] x86/boot/compressed/64: Always switch to own page-table Joerg Roedel
2020-04-06 11:56 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 16/70] x86/boot/compressed/64: Don't pre-map memory in KASLR code Joerg Roedel
2020-03-19 9:13 ` [PATCH 17/70] x86/boot/compressed/64: Change add_identity_map() to take start and end Joerg Roedel
2020-03-19 9:13 ` [PATCH 18/70] x86/boot/compressed/64: Add stage1 #VC handler Joerg Roedel
2020-03-20 21:16 ` David Rientjes
2020-03-20 22:19 ` Joerg Roedel
2020-04-06 12:41 ` Borislav Petkov
2020-03-19 9:13 ` [PATCH 19/70] x86/boot/compressed/64: Call set_sev_encryption_mask earlier Joerg Roedel
2020-03-19 9:13 ` [PATCH 20/70] x86/boot/compressed/64: Check return value of kernel_ident_mapping_init() Joerg Roedel
2020-03-19 9:13 ` [PATCH 21/70] x86/boot/compressed/64: Add function to map a page unencrypted Joerg Roedel
2020-03-20 20:53 ` David Rientjes
2020-03-20 21:02 ` Dave Hansen
2020-03-20 22:12 ` Joerg Roedel
2020-03-20 22:26 ` Dave Hansen
2020-03-21 15:40 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 22/70] x86/boot/compressed/64: Setup GHCB Based VC Exception handler Joerg Roedel
2020-03-19 9:13 ` [PATCH 23/70] x86/sev-es: Add support for handling IOIO exceptions Joerg Roedel
2020-03-20 21:03 ` David Rientjes
2020-03-20 22:24 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 24/70] x86/fpu: Move xgetbv()/xsetbv() into separate header Joerg Roedel
2020-03-19 9:13 ` [PATCH 25/70] x86/sev-es: Add CPUID handling to #VC handler Joerg Roedel
2020-03-19 9:13 ` [PATCH 26/70] x86/idt: Move IDT to data segment Joerg Roedel
2020-03-19 9:13 ` [PATCH 27/70] x86/idt: Split idt_data setup out of set_intr_gate() Joerg Roedel
2020-03-19 9:13 ` [PATCH 28/70] x86/idt: Move two function from k/idt.c to i/a/desc.h Joerg Roedel
2020-03-19 9:13 ` [PATCH 29/70] x86/head/64: Install boot GDT Joerg Roedel
2020-03-19 9:13 ` [PATCH 30/70] x86/head/64: Reload GDT after switch to virtual addresses Joerg Roedel
2020-03-19 9:13 ` [PATCH 31/70] x86/head/64: Load segment registers earlier Joerg Roedel
2020-03-19 9:13 ` [PATCH 32/70] x86/head/64: Switch to initial stack earlier Joerg Roedel
2020-03-19 9:13 ` [PATCH 33/70] x86/head/64: Build k/head64.c with -fno-stack-protector Joerg Roedel
2020-03-19 9:13 ` [PATCH 34/70] x86/head/64: Load IDT earlier Joerg Roedel
2020-03-19 9:13 ` [PATCH 35/70] x86/head/64: Move early exception dispatch to C code Joerg Roedel
2020-03-19 9:13 ` [PATCH 36/70] x86/sev-es: Add SEV-ES Feature Detection Joerg Roedel
2020-03-19 9:13 ` [PATCH 37/70] x86/sev-es: Compile early handler code into kernel image Joerg Roedel
2020-03-19 9:13 ` [PATCH 38/70] x86/sev-es: Setup early #VC handler Joerg Roedel
2020-03-19 9:13 ` [PATCH 39/70] x86/sev-es: Setup GHCB based boot " Joerg Roedel
2020-03-19 9:13 ` [PATCH 40/70] x86/sev-es: Setup per-cpu GHCBs for the runtime handler Joerg Roedel
2020-04-14 19:03 ` Mike Stunes
2020-04-14 20:04 ` Tom Lendacky
2020-04-14 20:12 ` Dave Hansen
2020-04-14 20:16 ` Tom Lendacky
2020-04-14 20:18 ` Tom Lendacky
2020-04-15 15:54 ` Joerg Roedel
2020-04-15 15:53 ` Joerg Roedel
2020-04-23 1:33 ` Bo Gan
2020-04-23 11:30 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 41/70] x86/sev-es: Add Runtime #VC Exception Handler Joerg Roedel
2020-03-19 15:44 ` Andy Lutomirski
2020-03-19 16:24 ` Joerg Roedel
2020-03-19 18:43 ` Andy Lutomirski
2020-03-19 19:38 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 42/70] x86/sev-es: Support nested #VC exceptions Joerg Roedel
2020-03-19 15:46 ` Andy Lutomirski
2020-03-19 16:12 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 43/70] x86/sev-es: Wire up existing #VC exit-code handlers Joerg Roedel
2020-03-19 9:13 ` [PATCH 44/70] x86/sev-es: Handle instruction fetches from user-space Joerg Roedel
2020-03-19 9:13 ` [PATCH 45/70] x86/sev-es: Harden runtime #VC handler for exceptions " Joerg Roedel
2020-03-19 9:13 ` [PATCH 46/70] x86/sev-es: Filter exceptions not supported " Joerg Roedel
2020-03-19 9:13 ` [PATCH 47/70] x86/sev-es: Handle MMIO events Joerg Roedel
2020-03-19 9:13 ` [PATCH 48/70] x86/sev-es: Handle MMIO String Instructions Joerg Roedel
2020-03-19 9:13 ` [PATCH 49/70] x86/sev-es: Handle MSR events Joerg Roedel
2020-03-19 9:13 ` [PATCH 50/70] x86/sev-es: Handle DR7 read/write events Joerg Roedel
2020-03-19 9:13 ` [PATCH 51/70] x86/sev-es: Handle WBINVD Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 52/70] x86/sev-es: Handle RDTSC Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 53/70] x86/sev-es: Handle RDPMC Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 54/70] x86/sev-es: Handle INVD Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 55/70] x86/sev-es: Handle RDTSCP Events Joerg Roedel
2020-04-24 21:03 ` [PATCH] Allow RDTSC and RDTSCP from userspace Mike Stunes
2020-04-24 21:24 ` Dave Hansen
2020-04-24 21:27 ` Tom Lendacky
2020-04-24 22:53 ` Dave Hansen
2020-04-25 12:49 ` Joerg Roedel
2020-04-25 18:15 ` Andy Lutomirski
2020-04-25 19:10 ` Joerg Roedel
2020-04-25 19:47 ` Andy Lutomirski
2020-04-25 20:23 ` Joerg Roedel
2020-04-25 22:10 ` Andy Lutomirski
2020-04-27 17:37 ` Should SEV-ES #VC use IST? (Re: [PATCH] Allow RDTSC and RDTSCP from userspace) Andy Lutomirski
2020-04-27 18:15 ` Andrew Cooper
2020-04-27 18:43 ` Tom Lendacky
2020-04-28 7:55 ` Joerg Roedel
2020-04-28 16:34 ` Andrew Cooper
2020-06-23 11:07 ` Peter Zijlstra
2020-06-23 11:30 ` Joerg Roedel
2020-06-23 11:48 ` Peter Zijlstra
2020-06-23 12:04 ` Joerg Roedel
2020-06-23 12:52 ` Peter Zijlstra
2020-06-23 13:40 ` Joerg Roedel
2020-06-23 13:59 ` Peter Zijlstra
2020-06-23 14:53 ` Peter Zijlstra
2020-06-23 14:59 ` Joerg Roedel
2020-06-23 15:23 ` Peter Zijlstra
2020-06-23 15:38 ` Peter Zijlstra
2020-06-23 15:38 ` Joerg Roedel
2020-06-23 16:02 ` Peter Zijlstra
2020-06-23 15:39 ` Andrew Cooper
2020-06-23 15:52 ` Peter Zijlstra
2020-06-23 16:03 ` Dave Hansen
2020-06-23 16:13 ` Peter Zijlstra
2020-06-23 16:13 ` Borislav Petkov
2020-06-23 11:51 ` Andrew Cooper
2020-06-23 12:47 ` Peter Zijlstra
2020-06-23 13:57 ` Andrew Cooper
2020-06-23 15:51 ` Borislav Petkov
2020-06-23 9:45 ` Joerg Roedel
2020-06-23 10:45 ` Peter Zijlstra
2020-06-23 11:11 ` Joerg Roedel
2020-06-23 11:14 ` Peter Zijlstra
2020-06-23 11:43 ` Joerg Roedel
2020-06-23 11:50 ` Peter Zijlstra
2020-06-23 12:12 ` Joerg Roedel
2020-06-23 13:03 ` Peter Zijlstra
2020-06-23 14:49 ` Joerg Roedel
2020-06-23 15:16 ` Peter Zijlstra
2020-06-23 15:32 ` Andrew Cooper
2020-06-23 16:10 ` Borislav Petkov
2020-06-23 15:22 ` Andrew Cooper
2020-06-23 18:26 ` Andy Lutomirski [this message]
2020-06-23 18:56 ` Andrew Cooper
2020-04-27 18:47 ` [PATCH] Allow RDTSC and RDTSCP from userspace Dave Hansen
2020-04-25 12:28 ` Joerg Roedel
2020-03-19 9:13 ` [PATCH 56/70] x86/sev-es: Handle MONITOR/MONITORX Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 57/70] x86/sev-es: Handle MWAIT/MWAITX Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 58/70] x86/sev-es: Handle VMMCALL Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 59/70] x86/sev-es: Handle #AC Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 60/70] x86/sev-es: Handle #DB Events Joerg Roedel
2020-03-19 9:13 ` [PATCH 61/70] x86/paravirt: Allow hypervisor specific VMMCALL handling under SEV-ES Joerg Roedel
2020-03-19 9:13 ` [PATCH 62/70] x86/kvm: Add KVM " Joerg Roedel
2020-03-20 21:23 ` David Rientjes
2020-03-20 22:21 ` Joerg Roedel
2020-03-19 9:14 ` [PATCH 63/70] x86/vmware: Add VMware specific handling for VMMCALL " Joerg Roedel
2020-03-19 10:18 ` Thomas Hellstrom
2020-03-19 9:14 ` [PATCH 64/70] x86/realmode: Add SEV-ES specific trampoline entry point Joerg Roedel
2020-03-19 9:14 ` [PATCH 65/70] x86/realmode: Setup AP jump table Joerg Roedel
2020-03-19 9:14 ` [PATCH 66/70] x86/head/64: Don't call verify_cpu() on starting APs Joerg Roedel
2020-03-19 9:14 ` [PATCH 67/70] x86/head/64: Rename start_cpu0 Joerg Roedel
2020-03-19 9:14 ` [PATCH 68/70] x86/sev-es: Support CPU offline/online Joerg Roedel
2020-03-19 9:14 ` [PATCH 69/70] x86/cpufeature: Add SEV_ES_GUEST CPU Feature Joerg Roedel
2020-03-19 9:14 ` [PATCH 70/70] x86/sev-es: Add NMI state tracking Joerg Roedel
2020-03-19 15:35 ` Andy Lutomirski
2020-03-19 16:07 ` Joerg Roedel
2020-03-19 18:40 ` Andy Lutomirski
2020-03-19 19:26 ` Joerg Roedel
2020-03-19 21:27 ` Andy Lutomirski
2020-03-20 19:48 ` Joerg Roedel
2020-03-20 13:17 ` [RFC PATCH v2.1] x86/sev-es: Handle NMI State Joerg Roedel
2020-03-20 14:42 ` Dave Hansen
2020-03-20 19:42 ` Joerg Roedel
2020-03-19 16:53 ` [PATCH 70/70] x86/sev-es: Add NMI state tracking Mika Penttilä
2020-03-19 19:41 ` Joerg Roedel
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='CALCETrWEUXU_BYd5ypF3XC10hSQUJ=XCVz40n3VfcWELS+roTg@mail.gmail.com' \
--to=luto@kernel.org \
--cc=JGross@suse.com \
--cc=Thomas.Lendacky@amd.com \
--cc=andrew.cooper3@citrix.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=joro@8bytes.org \
--cc=jroedel@suse.de \
--cc=jslaby@suse.cz \
--cc=keescook@chromium.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mstunes@vmware.com \
--cc=peterz@infradead.org \
--cc=sean.j.christopherson@intel.com \
--cc=thellstrom@vmware.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=x86@kernel.org \
/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).