x86/speculation/mds: Conditionally clear CPU buffers on idle entry

Add a static key which controls the invocation of the CPU buffer clear
mechanism on idle entry. This is independent of other MDS mitigations
because the idle entry invocation to mitigate the potential leakage due to
store buffer repartitioning is only necessary on SMT systems.

Add the actual invocations to the different halt/mwait variants which
covers all usage sites. mwaitx is not patched as it's not available on
Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent
that stale data from the idling CPU is spilled to the Hyper-Thread sibling
after the Store buffer got repartitioned and all entries are available to
the non idle sibling.

When coming out of idle the store buffer is partitioned again so each
sibling has half of it available. Now CPU which returned from idle could be
speculatively exposed to contents of the sibling, but the buffers are
flushed either on exit to user space or on VMENTER.

When later on conditional buffer clearing is implemented on top of this,
then there is no action required either because before returning to user
space the context switch will set the condition flag which causes a flush
on the return to user path.

Note, that the buffer clearing on idle is only sensible on CPUs which are
solely affected by MSBDS and not any other variant of MDS because the other
MDS variants cannot be mitigated when SMT is enabled, so the buffer
clearing on idle would be a window dressing exercise.

This intentionally does not handle the case in the acpi/processor_idle
driver which uses the legacy IO port interface for C-State transitions for
two reasons:

 - The acpi/processor_idle driver was replaced by the intel_idle driver
   almost a decade ago. Anything Nehalem upwards supports it and defaults
   to that new driver.

 - The legacy IO port interface is likely to be used on older and therefore
   unaffected CPUs or on systems which do not receive microcode updates
   anymore, so there is no point in adding that.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Jon Masters <jcm@redhat.com>
Tested-by: Jon Masters <jcm@redhat.com>

4 files changed, 26 insertions, 0 deletions

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 058e40fed167..8a0e56e1dcc9 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -6,6 +6,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/nospec-branch.h>
+
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
 #define __cpuidle __attribute__((__section__(".cpuidle.text")))
 
@@ -54,11 +56,13 @@ static inline void native_irq_enable(void)
 
 static inline __cpuidle void native_safe_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static inline __cpuidle void native_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 39a2fb29378a..eb0f80ce8524 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -6,6 +6,7 @@
 #include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
@@ -40,6 +41,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx,
 
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	/* "mwait %eax, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xc9;"
 		     :: "a" (eax), "c" (ecx));
@@ -74,6 +77,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 			    unsigned long ecx)
 {
+	/* No MDS buffer clear as this is AMD/HYGON only */
+
 	/* "mwaitx %eax, %ebx, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb;"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
@@ -81,6 +86,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	trace_hardirqs_on();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 65b747286d96..4e970390110f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -319,6 +319,7 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 #include <asm/segment.h>
 
@@ -356,6 +357,17 @@ static inline void mds_user_clear_cpu_buffers(void)
 		mds_clear_cpu_buffers();
 }
 
+/**
+ * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_idle_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_idle_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 29ed8e8dfee2..916995167301 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -66,6 +66,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 /* Control MDS CPU buffer clear before returning to user space */
 DEFINE_STATIC_KEY_FALSE(mds_user_clear);
 EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
 
 void __init check_bugs(void)
 {