x86/tdx: Fix arch_safe_halt() execution for TDX VMs

commit 9f98a4f4e7216dbe366010b4cdcab6b220f229c4 upstream.

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, as current TDX spec doesn't expose
interruptibility state information to allow #VE handler to selectively
enable interrupts.

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 via this path
as an example:

	kvm_wait()       =>
        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.

As tested by Ryan Afranji:

  "Tested with the specjbb2015 benchmark. It has heavy lock contention which leads
   to many halt calls. TDX VMs suffered a poor score before this patchset.

   Verified the major performance improvement with this patchset applied."

Fixes: bfe6ed0c6727 ("x86/tdx: Add HLT support for TDX guests")
Signed-off-by: Vishal Annapurve <vannapurve@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Ryan Afranji <afranji@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250228014416.3925664-3-vannapurve@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a0af6e8d584b02247bc32e658d51a483ce70d8c7..d874ea22512b5cc08df79dda453d28cd8907cf91 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -881,6 +881,7 @@ 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 2f67e196a2ead2ab334d3c2a72055bc94c20eeb9..98d0ee9600eb54fe29fae068182f3f297a3c44a9 100644 (file)
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -13,6 +13,7 @@
 #include <asm/ia32.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
+#include <asm/paravirt_types.h>
 #include <asm/pgtable.h>
 #include <asm/traps.h>
 
@@ -334,7 +335,7 @@ 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;
 
@@ -345,6 +346,16 @@ 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_hypercall_args args = {
@@ -888,6 +899,19 @@ void __init tdx_early_init(void)
        x86_platform.guest.enc_cache_flush_required  = tdx_cache_flush_required;
        x86_platform.guest.enc_tlb_flush_required    = tdx_tlb_flush_required;
 
+       /*
+        * 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 603e6d1e9d4aac6e0e145f8832ce2a52483a6910..c632f09f0c9721ccb63007b431d22e5d3d576e79 100644 (file)
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -46,7 +46,7 @@ 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);
 
@@ -55,7 +55,7 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport);
 #else
 
 static inline void tdx_early_init(void) { };
-static inline void tdx_safe_halt(void) { };
+static inline void tdx_halt(void) { };
 
 static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; }
 

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index bbe11363550bea28820b24a2af2f646b659970da..419353904173ff3ce6569c491f9853872afbcd0a 100644 (file)
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -955,7 +955,7 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
                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);
 }