Merge branch 'x86-microcode-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 microcode updates from Ingo Molnar:
 "The main changes are further simplification and unification of the
  code between the AMD and Intel microcode loaders, plus other
  simplifications - by Borislav Petkov"

* 'x86-microcode-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/microcode/AMD: Remove struct cont_desc.eq_id
  x86/microcode/AMD: Remove AP scanning optimization
  x86/microcode/AMD: Simplify saving from initrd
  x86/microcode/AMD: Unify load_ucode_amd_ap()
  x86/microcode/AMD: Check patch level only on the BSP
  x86/microcode: Remove local vendor variable
  x86/microcode/AMD: Use find_microcode_in_initrd()
  x86/microcode/AMD: Get rid of global this_equiv_id
  x86/microcode: Decrease CPUID use
  x86/microcode/AMD: Rework container parsing
  x86/microcode/AMD: Extend the container struct
  x86/microcode/AMD: Shorten function parameter's name
  x86/microcode/AMD: Clean up find_equiv_id()
  x86/microcode: Convert to bare minimum MSR accessors
  x86/MSR: Carve out bare minimum accessors

arch/x86/include/asm/apic.h

@@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 
 static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
 {
-	wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+	__wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
 }
 
 static inline u32 native_apic_msr_read(u32 reg)

arch/x86/include/asm/microcode.h

@@ -7,17 +7,16 @@
 
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
-	u64 __val = native_read_msr((msr));		\
+	u64 __val = __rdmsr((msr));			\
 	(void)((val1) = (u32)__val);			\
 	(void)((val2) = (u32)(__val >> 32));		\
 } while (0)
 
 #define native_wrmsr(msr, low, high)			\
-	native_write_msr(msr, low, high)
+	__wrmsr(msr, low, high)
 
 #define native_wrmsrl(msr, val)				\
-	native_write_msr((msr),				\
-			 (u32)((u64)(val)),		\
+	__wrmsr((msr), (u32)((u64)(val)),		\
 		       (u32)((u64)(val) >> 32))
 
 struct ucode_patch {

arch/x86/include/asm/microcode_amd.h

@@ -54,6 +54,4 @@ static inline int __init
 save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 void reload_ucode_amd(void) {}
 #endif
-
-extern bool check_current_patch_level(u32 *rev, bool early);
 #endif /* _ASM_X86_MICROCODE_AMD_H */

arch/x86/include/asm/msr.h

@@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
 static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
 #endif
 
-static inline unsigned long long native_read_msr(unsigned int msr)
+/*
+ * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR
+ * accessors and should not have any tracing or other functionality piggybacking
+ * on them - those are *purely* for accessing MSRs and nothing more. So don't even
+ * think of extending them - you will be slapped with a stinking trout or a frozen
+ * shark will reach you, wherever you are! You've been warned.
+ */
+static inline unsigned long long notrace __rdmsr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 		     "2:\n"
 		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
 		     : EAX_EDX_RET(val, low, high) : "c" (msr));
-	if (msr_tracepoint_active(__tracepoint_read_msr))
-		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
+
 	return EAX_EDX_VAL(val, low, high);
 }
 
+static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+{
+	asm volatile("1: wrmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     : : "c" (msr), "a"(low), "d" (high) : "memory");
+}
+
+static inline unsigned long long native_read_msr(unsigned int msr)
+{
+	unsigned long long val;
+
+	val = __rdmsr(msr);
+
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, val, 0);
+
+	return val;
+}
+
 static inline unsigned long long native_read_msr_safe(unsigned int msr,
 						      int *err)
 {
@@ -114,31 +140,16 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 	return EAX_EDX_VAL(val, low, high);
 }
 
-/* Can be uninlined because referenced by paravirt */
-static inline void notrace
-__native_write_msr_notrace(unsigned int msr, u32 low, u32 high)
-{
-	asm volatile("1: wrmsr\n"
-		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
-		     : : "c" (msr), "a"(low), "d" (high) : "memory");
-}
-
 /* Can be uninlined because referenced by paravirt */
 static inline void notrace
 native_write_msr(unsigned int msr, u32 low, u32 high)
 {
-	__native_write_msr_notrace(msr, low, high);
+	__wrmsr(msr, low, high);
+
 	if (msr_tracepoint_active(__tracepoint_write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
-static inline void
-wrmsr_notrace(unsigned int msr, u32 low, u32 high)
-{
-	__native_write_msr_notrace(msr, low, high);
-}
-
 /* Can be uninlined because referenced by paravirt */
 static inline int notrace
 native_write_msr_safe(unsigned int msr, u32 low, u32 high)

arch/x86/kernel/cpu/microcode/core.c

@@ -66,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex);
 
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
-/*
- * Operations that are run on a target cpu:
- */
-
 struct cpu_info_ctx {
 	struct cpu_signature	*cpu_sig;
 	int			err;
 };
 
+/*
+ * Those patch levels cannot be updated to newer ones and thus should be final.
+ */
+static u32 final_levels[] = {
+	0x01000098,
+	0x0100009f,
+	0x010000af,
+	0, /* T-101 terminator */
+};
+
+/*
+ * Check the current patch level on this CPU.
+ *
+ * Returns:
+ *  - true: if update should stop
+ *  - false: otherwise
+ */
+static bool amd_check_current_patch_level(void)
+{
+	u32 lvl, dummy, i;
+	u32 *levels;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
+
+	if (IS_ENABLED(CONFIG_X86_32))
+		levels = (u32 *)__pa_nodebug(&final_levels);
+	else
+		levels = final_levels;
+
+	for (i = 0; levels[i]; i++) {
+		if (lvl == levels[i])
+			return true;
+	}
+	return false;
+}
+
 static bool __init check_loader_disabled_bsp(void)
 {
 	static const char *__dis_opt_str = "dis_ucode_ldr";
-	u32 a, b, c, d;
 
 #ifdef CONFIG_X86_32
 	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
@@ -94,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void)
 	if (!have_cpuid_p())
 		return *res;
 
-	a = 1;
-	c = 0;
-	native_cpuid(&a, &b, &c, &d);
-
 	/*
 	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
 	 * completely accurate as xen pv guests don't see that CPUID bit set but
 	 * that's good enough as they don't land on the BSP path anyway.
 	 */
-	if (c & BIT(31))
+	if (native_cpuid_ecx(1) & BIT(31))
 		return *res;
 
+	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
+		if (amd_check_current_patch_level())
+			return *res;
+	}
+
 	if (cmdline_find_option_bool(cmdline, option) <= 0)
 		*res = false;
 
@@ -133,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name)
 
 void __init load_ucode_bsp(void)
 {
-	int vendor;
-	unsigned int family;
+	unsigned int cpuid_1_eax;
 
 	if (check_loader_disabled_bsp())
 		return;
 
-	vendor = x86_cpuid_vendor();
-	family = x86_cpuid_family();
+	cpuid_1_eax = native_cpuid_eax(1);
 
-	switch (vendor) {
+	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (family >= 6)
+		if (x86_family(cpuid_1_eax) >= 6)
 			load_ucode_intel_bsp();
 		break;
 	case X86_VENDOR_AMD:
-		if (family >= 0x10)
-			load_ucode_amd_bsp(family);
+		if (x86_family(cpuid_1_eax) >= 0x10)
+			load_ucode_amd_bsp(cpuid_1_eax);
 		break;
 	default:
 		break;
@@ -167,22 +197,21 @@ static bool check_loader_disabled_ap(void)
 
 void load_ucode_ap(void)
 {
-	int vendor, family;
+	unsigned int cpuid_1_eax;
 
 	if (check_loader_disabled_ap())
 		return;
 
-	vendor = x86_cpuid_vendor();
-	family = x86_cpuid_family();
+	cpuid_1_eax = native_cpuid_eax(1);
 
-	switch (vendor) {
+	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (family >= 6)
+		if (x86_family(cpuid_1_eax) >= 6)
 			load_ucode_intel_ap();
 		break;
 	case X86_VENDOR_AMD:
-		if (family >= 0x10)
-			load_ucode_amd_ap(family);
+		if (x86_family(cpuid_1_eax) >= 0x10)
+			load_ucode_amd_ap(cpuid_1_eax);
 		break;
 	default:
 		break;
@@ -201,7 +230,7 @@ static int __init save_microcode_in_initrd(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			ret = save_microcode_in_initrd_amd(c->x86);
+			return save_microcode_in_initrd_amd(cpuid_eax(1));
 		break;
 	default:
 		break;