[PATCH v4] x86/cpu: clear SME feature flag when not in use

* [PATCH v4] x86/cpu: clear SME feature flag when not in use
@ 2022-02-16  3:44 Mario Limonciello
  2022-02-16 10:33 ` Borislav Petkov
                   ` (2 more replies)
  0 siblings, 3 replies; 5+ messages in thread
From: Mario Limonciello @ 2022-02-16  3:44 UTC (permalink / raw)
  To: Borislav Petkov, maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)
  Cc: Kees Cook, Thomas Lendacky, hughsient, Martin Fernandez,
	linux-kernel, Brijesh Singh, Mario Limonciello

Currently the SME CPU feature flag is reflective of whether the CPU
supports the feature but not whether is has been activated by the
kernel.

Change this around to clear the SME feature flag if the kernel is not
using it so userspace can determine if it is available and in use
from `/proc/cpuinfo`.

As the feature flag is cleared on systems where SME isn't active use
CPUID 0x8000001f to confirm SME availability before calling
`native_wbinvd`.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
Changes from v3->v4:
 * Update block comment to explain SME can get turned off
 * Reword commit message
 arch/x86/kernel/cpu/amd.c | 5 +++++
 arch/x86/kernel/process.c | 5 ++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4edb6f0f628c..dcfbb25b119a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -585,6 +585,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 *	      the SME physical address space reduction value.
 	 *	      If BIOS has not enabled SME then don't advertise the
 	 *	      SME feature (set in scattered.c).
+	 *	      If the kernel has not enabled SME via any means then
+	 *	      don't advertise the SME feature.
 	 *   For SEV: If BIOS has not enabled SEV then don't advertise the
 	 *            SEV and SEV_ES feature (set in scattered.c).
 	 *
@@ -607,6 +609,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 		if (IS_ENABLED(CONFIG_X86_32))
 			goto clear_all;
 
+		if (!sme_me_mask)
+			setup_clear_cpu_cap(X86_FEATURE_SME);
+
 		rdmsrl(MSR_K7_HWCR, msr);
 		if (!(msr & MSR_K7_HWCR_SMMLOCK))
 			goto clear_sev;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 81d8ef036637..e131d71b3cae 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -765,8 +765,11 @@ void stop_this_cpu(void *dummy)
 	 * without the encryption bit, they don't race each other when flushed
 	 * and potentially end up with the wrong entry being committed to
 	 * memory.
+	 *
+	 * Test the CPUID bit directly because the machine might've cleared
+	 * X86_FEATURE_SME due to cmdline options.
 	 */
-	if (boot_cpu_has(X86_FEATURE_SME))
+	if (cpuid_eax(0x8000001f) & BIT(0))
 		native_wbinvd();
 	for (;;) {
 		/*
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 5+ messages in thread