6 files changed, 83 insertions, 0 deletions

diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst
index 1096738d50f2..54d935bf283b 100644
--- a/Documentation/x86/mds.rst
+++ b/Documentation/x86/mds.rst
@@ -97,3 +97,55 @@ According to current knowledge additional mitigations inside the kernel
 itself are not required because the necessary gadgets to expose the leaked
 data cannot be controlled in a way which allows exploitation from malicious
 user space or VM guests.
+
+Mitigation points
+-----------------
+
+1. Return to user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   When transitioning from kernel to user space the CPU buffers are flushed
+   on affected CPUs when the mitigation is not disabled on the kernel
+   command line. The migitation is enabled through the static key
+   mds_user_clear.
+
+   The mitigation is invoked in prepare_exit_to_usermode() which covers
+   most of the kernel to user space transitions. There are a few exceptions
+   which are not invoking prepare_exit_to_usermode() on return to user
+   space. These exceptions use the paranoid exit code.
+
+   - Non Maskable Interrupt (NMI):
+
+     Access to sensible data like keys, credentials in the NMI context is
+     mostly theoretical: The CPU can do prefetching or execute a
+     misspeculated code path and thereby fetching data which might end up
+     leaking through a buffer.
+
+     But for mounting other attacks the kernel stack address of the task is
+     already valuable information. So in full mitigation mode, the NMI is
+     mitigated on the return from do_nmi() to provide almost complete
+     coverage.
+
+   - Double fault (#DF):
+
+     A double fault is usually fatal, but the ESPFIX workaround, which can
+     be triggered from user space through modify_ldt(2) is a recoverable
+     double fault. #DF uses the paranoid exit path, so explicit mitigation
+     in the double fault handler is required.
+
+   - Machine Check Exception (#MC):
+
+     Another corner case is a #MC which hits between the CPU buffer clear
+     invocation and the actual return to user. As this still is in kernel
+     space it takes the paranoid exit path which does not clear the CPU
+     buffers. So the #MC handler repopulates the buffers to some
+     extent. Machine checks are not reliably controllable and the window is
+     extremly small so mitigation would just tick a checkbox that this
+     theoretical corner case is covered. To keep the amount of special
+     cases small, ignore #MC.
+
+   - Debug Exception (#DB):
+
+     This takes the paranoid exit path only when the INT1 breakpoint is in
+     kernel space. #DB on a user space address takes the regular exit path,
+     so no extra mitigation required.
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 071582a3b5c0..57be07f27f37 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -28,6 +28,7 @@
 #include <asm/vdso.h>
 #include <asm/uaccess.h>
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -295,6 +296,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 #endif
 
 	user_enter();
+
+	mds_user_clear_cpu_buffers();
 }
 
 #define SYSCALL_EXIT_WORK_FLAGS				\
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index d6f0a33383c8..08d0d7592f98 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -262,6 +262,8 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+
 #include <asm/segment.h>
 
 /**
@@ -287,6 +289,17 @@ static inline void mds_clear_cpu_buffers(void)
 	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
 }
 
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 57cae3757bcc..a7746734ccbc 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -58,6 +58,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 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);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 697f90db0e37..a4df15f3878e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -522,6 +523,9 @@ nmi_restart:
 		write_cr2(this_cpu_read(nmi_cr2));
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
+
+	if (user_mode(regs))
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8c73bf1492b8..6223929fc621 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -61,6 +61,7 @@
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
+#include <asm/nospec-branch.h>
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 
@@ -337,6 +338,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&normal_regs->orig_ax;
 
+		/*
+		 * This situation can be triggered by userspace via
+		 * modify_ldt(2) and the return does not take the regular
+		 * user space exit, so a CPU buffer clear is required when
+		 * MDS mitigation is enabled.
+		 */
+		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif