x86: Remove X86_FEATURE_MFENCE_RDTSC

AMD and Intel both have serializing lfence (X86_FEATURE_LFENCE_RDTSC).
They've both had it for a long time, and AMD has had it enabled in Linux
since Spectre v1 was announced.

Back then, there was a proposal to remove the serializing mfence feature
bit (X86_FEATURE_MFENCE_RDTSC), since both AMD and Intel have
serializing lfence.  At the time, it was (ahem) speculated that some
hypervisors might not yet support its removal, so it remained for the
time being.

Now a year-and-a-half later, it should be safe to remove.

I asked Andrew Cooper about whether it's still needed:

  So if you're virtualised, you've got no choice in the matter.  lfence
  is either dispatch-serialising or not on AMD, and you won't be able to
  change it.

  Furthermore, you can't accurately tell what state the bit is in, because
  the MSR might not be virtualised at all, or may not reflect the true
  state in hardware.  Worse still, attempting to set the bit may not be
  successful even if there isn't a fault for doing so.

  Xen sets the DE_CFG bit unconditionally, as does Linux by the looks of
  things (see MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT).  ISTR other hypervisor
  vendors saying the same, but I don't have any information to hand.

  If you are running under a hypervisor which has been updated, then
  lfence will almost certainly be dispatch-serialising in practice, and
  you'll almost certainly see the bit already set in DE_CFG.  If you're
  running under a hypervisor which hasn't been patched since Spectre,
  you've already lost in many more ways.

  I'd argue that X86_FEATURE_MFENCE_RDTSC is not worth keeping.

So remove it.  This will reduce some code rot, and also make it easier
to hook barrier_nospec() up to a cmdline disable for performance
raisins, without having to need an alternative_3() macro.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/d990aa51e40063acb9888e8c1b688e41355a9588.1562255067.git.jpoimboe@redhat.com

2 files changed, 6 insertions, 36 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8d4e50428b68..3afe07d602dd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -879,12 +879,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	init_amd_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
-		unsigned long long val;
-		int ret;
-
 		/*
-		 * A serializing LFENCE has less overhead than MFENCE, so
-		 * use it for execution serialization.  On families which
+		 * Use LFENCE for execution serialization.  On families which
 		 * don't have that MSR, LFENCE is already serializing.
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
@@ -892,19 +888,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_F10H_DECFG,
 			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
 
-		/*
-		 * Verify that the MSR write was successful (could be running
-		 * under a hypervisor) and only then assume that LFENCE is
-		 * serializing.
-		 */
-		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
-		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
-			/* A serializing LFENCE stops RDTSC speculation */
-			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-		} else {
-			/* MFENCE stops RDTSC speculation */
-			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-		}
+		/* A serializing LFENCE stops RDTSC speculation */
+		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 415621ddb8a2..4e28c1fc8749 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -330,12 +330,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
 	init_hygon_cacheinfo(c);
 
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
-		unsigned long long val;
-		int ret;
-
 		/*
-		 * A serializing LFENCE has less overhead than MFENCE, so
-		 * use it for execution serialization.  On families which
+		 * Use LFENCE for execution serialization.  On families which
 		 * don't have that MSR, LFENCE is already serializing.
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
@@ -343,19 +339,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		msr_set_bit(MSR_F10H_DECFG,
 			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
 
-		/*
-		 * Verify that the MSR write was successful (could be running
-		 * under a hypervisor) and only then assume that LFENCE is
-		 * serializing.
-		 */
-		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
-		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
-			/* A serializing LFENCE stops RDTSC speculation */
-			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-		} else {
-			/* MFENCE stops RDTSC speculation */
-			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
-		}
+		/* A serializing LFENCE stops RDTSC speculation */
+		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 	}
 
 	/*