Linux Confidential Computing Development
 help / color / mirror / Atom feed
From: Vishal Annapurve <vannapurve@google.com>
To: dave.hansen@linux.intel.com, kirill.shutemov@linux.intel.com,
	 jgross@suse.com, ajay.kaher@broadcom.com, ak@linux.intel.com,
	 tony.luck@intel.com, thomas.lendacky@amd.com
Cc: tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
	hpa@zytor.com,  pbonzini@redhat.com, seanjc@google.com,
	kai.huang@intel.com,  chao.p.peng@linux.intel.com,
	isaku.yamahata@gmail.com,
	 sathyanarayanan.kuppuswamy@linux.intel.com,
	erdemaktas@google.com,  ackerleytng@google.com, jxgao@google.com,
	sagis@google.com,  afranji@google.com, kees@kernel.org,
	jikos@kernel.org, peterz@infradead.org,  x86@kernel.org,
	linux-kernel@vger.kernel.org, linux-coco@lists.linux.dev,
	 virtualization@lists.linux.dev,
	bcm-kernel-feedback-list@broadcom.com,
	 Vishal Annapurve <vannapurve@google.com>,
	stable@vger.kernel.org
Subject: [PATCH v6 2/3] x86/tdx: Fix arch_safe_halt() execution for TDX VMs
Date: Tue, 25 Feb 2025 00:47:03 +0000	[thread overview]
Message-ID: <20250225004704.603652-3-vannapurve@google.com> (raw)
In-Reply-To: <20250225004704.603652-1-vannapurve@google.com>

Direct HLT instruction execution causes #VEs for TDX VMs which is routed
to hypervisor via TDCALL. If HLT is executed in STI-shadow, resulting #VE
handler will enable interrupts before TDCALL is routed to hypervisor
leading to missed wakeup events.

Current TDX spec doesn't expose interruptibility state information to
allow #VE handler to selectively enable interrupts. To bypass this
issue, TDX VMs need to replace "sti;hlt" execution with direct TDCALL
followed by explicit interrupt flag update.

Commit bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests")
prevented the idle routines from executing HLT instruction in STI-shadow.
But it missed the paravirt routine which can be reached like this as an
example:
        acpi_safe_halt() =>
        raw_safe_halt()  =>
        arch_safe_halt() =>
        irq.safe_halt()  =>
        pv_native_safe_halt()

To reliably handle arch_safe_halt() for TDX VMs, introduce explicit
dependency on CONFIG_PARAVIRT and override paravirt halt()/safe_halt()
routines with TDX-safe versions that execute direct TDCALL and needed
interrupt flag updates. Executing direct TDCALL brings in additional
benefit of avoiding HLT related #VEs altogether.

Cc: stable@vger.kernel.org
Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests")
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
---
 arch/x86/Kconfig           |  1 +
 arch/x86/coco/tdx/tdx.c    | 26 +++++++++++++++++++++++++-
 arch/x86/include/asm/tdx.h |  2 +-
 arch/x86/kernel/process.c  |  2 +-
 4 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118..933c046e8966 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -902,6 +902,7 @@ config INTEL_TDX_GUEST
 	depends on X86_64 && CPU_SUP_INTEL
 	depends on X86_X2APIC
 	depends on EFI_STUB
+	depends on PARAVIRT
 	select ARCH_HAS_CC_PLATFORM
 	select X86_MEM_ENCRYPT
 	select X86_MCE
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 32809a06dab4..6aad910d119d 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -14,6 +14,7 @@
 #include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
+#include <asm/paravirt_types.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/traps.h>
@@ -398,7 +399,7 @@ static int handle_halt(struct ve_info *ve)
 	return ve_instr_len(ve);
 }
 
-void __cpuidle tdx_safe_halt(void)
+void __cpuidle tdx_halt(void)
 {
 	const bool irq_disabled = false;
 
@@ -409,6 +410,16 @@ void __cpuidle tdx_safe_halt(void)
 		WARN_ONCE(1, "HLT instruction emulation failed\n");
 }
 
+static void __cpuidle tdx_safe_halt(void)
+{
+	tdx_halt();
+	/*
+	 * "__cpuidle" section doesn't support instrumentation, so stick
+	 * with raw_* variant that avoids tracing hooks.
+	 */
+	raw_local_irq_enable();
+}
+
 static int read_msr(struct pt_regs *regs, struct ve_info *ve)
 {
 	struct tdx_module_args args = {
@@ -1109,6 +1120,19 @@ void __init tdx_early_init(void)
 	x86_platform.guest.enc_kexec_begin	     = tdx_kexec_begin;
 	x86_platform.guest.enc_kexec_finish	     = tdx_kexec_finish;
 
+	/*
+	 * Avoid "sti;hlt" execution in TDX guests as HLT induces a #VE that
+	 * will enable interrupts before HLT TDCALL invocation if executed
+	 * in STI-shadow, possibly resulting in missed wakeup events.
+	 *
+	 * Modify all possible HLT execution paths to use TDX specific routines
+	 * that directly execute TDCALL and toggle the interrupt state as
+	 * needed after TDCALL completion. This also reduces HLT related #VEs
+	 * in addition to having a reliable halt logic execution.
+	 */
+	pv_ops.irq.safe_halt = tdx_safe_halt;
+	pv_ops.irq.halt = tdx_halt;
+
 	/*
 	 * TDX intercepts the RDMSR to read the X2APIC ID in the parallel
 	 * bringup low level code. That raises #VE which cannot be handled
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index b4b16dafd55e..393ee2dfaab1 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -58,7 +58,7 @@ void tdx_get_ve_info(struct ve_info *ve);
 
 bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve);
 
-void tdx_safe_halt(void);
+void tdx_halt(void);
 
 bool tdx_early_handle_ve(struct pt_regs *regs);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254..d11956a178df 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -934,7 +934,7 @@ void __init select_idle_routine(void)
 		static_call_update(x86_idle, mwait_idle);
 	} else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
 		pr_info("using TDX aware idle routine\n");
-		static_call_update(x86_idle, tdx_safe_halt);
+		static_call_update(x86_idle, tdx_halt);
 	} else {
 		static_call_update(x86_idle, default_idle);
 	}
-- 
2.48.1.658.g4767266eb4-goog


  parent reply	other threads:[~2025-02-25  0:47 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-25  0:47 [PATCH v6 0/3] x86/tdx: Fix HLT logic execution for TDX VMs Vishal Annapurve
2025-02-25  0:47 ` [PATCH v6 1/3] x86/paravirt: Move halt paravirt calls under CONFIG_PARAVIRT Vishal Annapurve
2025-02-25  6:44   ` Juergen Gross
2025-02-25  0:47 ` Vishal Annapurve [this message]
2025-02-26 11:49   ` [PATCH v6 2/3] x86/tdx: Fix arch_safe_halt() execution for TDX VMs Kirill A. Shutemov
2025-02-27 19:26     ` Vishal Annapurve
2025-02-27 16:19   ` kernel test robot
2025-02-27 19:30     ` Vishal Annapurve
2025-02-25  0:47 ` [PATCH v6 3/3] x86/tdx: Emit warning if IRQs are enabled during HLT #VE handling Vishal Annapurve

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=20250225004704.603652-3-vannapurve@google.com \
    --to=vannapurve@google.com \
    --cc=ackerleytng@google.com \
    --cc=afranji@google.com \
    --cc=ajay.kaher@broadcom.com \
    --cc=ak@linux.intel.com \
    --cc=bcm-kernel-feedback-list@broadcom.com \
    --cc=bp@alien8.de \
    --cc=chao.p.peng@linux.intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=erdemaktas@google.com \
    --cc=hpa@zytor.com \
    --cc=isaku.yamahata@gmail.com \
    --cc=jgross@suse.com \
    --cc=jikos@kernel.org \
    --cc=jxgao@google.com \
    --cc=kai.huang@intel.com \
    --cc=kees@kernel.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-coco@lists.linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=sagis@google.com \
    --cc=sathyanarayanan.kuppuswamy@linux.intel.com \
    --cc=seanjc@google.com \
    --cc=stable@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tony.luck@intel.com \
    --cc=virtualization@lists.linux.dev \
    --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