x86/microcode: Prepare for minimal revision check

Applying microcode late can be fatal for the running kernel when the
update changes functionality which is in use already in a non-compatible
way, e.g. by removing a CPUID bit.

There is no way for admins which do not have access to the vendors deep
technical support to decide whether late loading of such a microcode is
safe or not.

Intel has added a new field to the microcode header which tells the
minimal microcode revision which is required to be active in the CPU in
order to be safe.

Provide infrastructure for handling this in the core code and a command
line switch which allows to enforce it.

If the update is considered safe the kernel is not tainted and the annoying
warning message not emitted. If it's enforced and the currently loaded
microcode revision is not safe for late loading then the load is aborted.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20231017211724.079611170@linutronix.de

6 files changed, 49 insertions, 6 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 0a1731a0f0ef..d762e17fd314 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3275,6 +3275,11 @@
 
 	mga=		[HW,DRM]
 
+	microcode.force_minrev=	[X86]
+			Format: <bool>
+			Enable or disable the microcode minimal revision
+			enforcement for the runtime microcode loader.
+
 	min_addr=nn[KMG]	[KNL,BOOT,IA-64] All physical memory below this
 			physical address is ignored.
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index db7512008ff7..cadea3f3161e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1326,7 +1326,28 @@ config MICROCODE_LATE_LOADING
 	  is a tricky business and should be avoided if possible. Just the sequence
 	  of synchronizing all cores and SMT threads is one fragile dance which does
 	  not guarantee that cores might not softlock after the loading. Therefore,
-	  use this at your own risk. Late loading taints the kernel too.
+	  use this at your own risk. Late loading taints the kernel unless the
+	  microcode header indicates that it is safe for late loading via the
+	  minimal revision check. This minimal revision check can be enforced on
+	  the kernel command line with "microcode.minrev=Y".
+
+config MICROCODE_LATE_FORCE_MINREV
+	bool "Enforce late microcode loading minimal revision check"
+	default n
+	depends on MICROCODE_LATE_LOADING
+	help
+	  To prevent that users load microcode late which modifies already
+	  in use features, newer microcode patches have a minimum revision field
+	  in the microcode header, which tells the kernel which minimum
+	  revision must be active in the CPU to safely load that new microcode
+	  late into the running system. If disabled the check will not
+	  be enforced but the kernel will be tainted when the minimal
+	  revision check fails.
+
+	  This minimal revision check can also be controlled via the
+	  "microcode.minrev" parameter on the kernel command line.
+
+	  If unsure say Y.
 
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 102aebcdb766..9373ec01c5ae 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -888,6 +888,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
+	if (force_minrev)
+		return UCODE_NFOUND;
+
 	if (c->x86 >= 0x15)
 		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 718d6487a433..666d25bbc5ad 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -46,6 +46,9 @@
 static struct microcode_ops	*microcode_ops;
 bool dis_ucode_ldr = true;
 
+bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
+module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
+
 /*
  * Synchronization.
  *
@@ -531,15 +534,17 @@ static int load_cpus_stopped(void *unused)
 	return 0;
 }
 
-static int load_late_stop_cpus(void)
+static int load_late_stop_cpus(bool is_safe)
 {
 	unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0;
 	unsigned int nr_offl, offline = 0;
 	int old_rev = boot_cpu_data.microcode;
 	struct cpuinfo_x86 prev_info;
 
-	pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
-	pr_err("You should switch to early loading, if possible.\n");
+	if (!is_safe) {
+		pr_err("Late microcode loading without minimal revision check.\n");
+		pr_err("You should switch to early loading, if possible.\n");
+	}
 
 	atomic_set(&late_cpus_in, num_online_cpus());
 	atomic_set(&offline_in_nmi, 0);
@@ -589,7 +594,9 @@ static int load_late_stop_cpus(void)
 		return -EIO;
 	}
 
-	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	if (!is_safe || failed || timedout)
+		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
 	pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings);
 	if (failed || timedout) {
 		pr_err("load incomplete. %u CPUs timed out or failed\n",
@@ -679,7 +686,9 @@ static int load_late_locked(void)
 
 	switch (microcode_ops->request_microcode_fw(0, &microcode_pdev->dev)) {
 	case UCODE_NEW:
-		return load_late_stop_cpus();
+		return load_late_stop_cpus(false);
+	case UCODE_NEW_SAFE:
+		return load_late_stop_cpus(true);
 	case UCODE_NFOUND:
 		return -ENOENT;
 	default:
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 905ed3b557fb..14aa4c6d4c14 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -480,6 +480,9 @@ static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter)
 	unsigned int curr_mc_size = 0;
 	u8 *new_mc = NULL, *mc = NULL;
 
+	if (force_minrev)
+		return UCODE_NFOUND;
+
 	while (iov_iter_count(iter)) {
 		struct microcode_header_intel mc_header;
 		unsigned int mc_size, data_size;
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 1a396fc65d4e..f8047b12329a 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -13,6 +13,7 @@ struct device;
 enum ucode_state {
 	UCODE_OK	= 0,
 	UCODE_NEW,
+	UCODE_NEW_SAFE,
 	UCODE_UPDATED,
 	UCODE_NFOUND,
 	UCODE_ERROR,
@@ -88,6 +89,7 @@ static inline unsigned int x86_cpuid_family(void)
 }
 
 extern bool dis_ucode_ldr;
+extern bool force_minrev;
 
 #ifdef CONFIG_CPU_SUP_AMD
 void load_ucode_amd_bsp(unsigned int family);