Merge tag 'x86_microcode_for_v6.7_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 microcode loading updates from Borislac Petkov:
 "Major microcode loader restructuring, cleanup and improvements by
  Thomas Gleixner:

   - Restructure the code needed for it and add a temporary initrd
     mapping on 32-bit so that the loader can access the microcode
     blobs. This in itself is a preparation for the next major
     improvement:

   - Do not load microcode on 32-bit before paging has been enabled.

     Handling this has caused an endless stream of headaches, issues,
     ugly code and unnecessary hacks in the past. And there really
     wasn't any sensible reason to do that in the first place. So switch
     the 32-bit loading to happen after paging has been enabled and turn
     the loader code "real purrty" again

   - Drop mixed microcode steppings loading on Intel - there, a single
     patch loaded on the whole system is sufficient

   - Rework late loading to track which CPUs have updated microcode
     successfully and which haven't, act accordingly

   - Move late microcode loading on Intel in NMI context in order to
     guarantee concurrent loading on all threads

   - Make the late loading CPU-hotplug-safe and have the offlined
     threads be woken up for the purpose of the update

   - Add support for a minimum revision which determines whether late
     microcode loading is safe on a machine and the microcode does not
     change software visible features which the machine cannot use
     anyway since feature detection has happened already. Roughly, the
     minimum revision is the smallest revision number which must be
     loaded currently on the system so that late updates can be allowed

   - Other nice leanups, fixess, etc all over the place"

* tag 'x86_microcode_for_v6.7_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  x86/microcode/intel: Add a minimum required revision for late loading
  x86/microcode: Prepare for minimal revision check
  x86/microcode: Handle "offline" CPUs correctly
  x86/apic: Provide apic_force_nmi_on_cpu()
  x86/microcode: Protect against instrumentation
  x86/microcode: Rendezvous and load in NMI
  x86/microcode: Replace the all-in-one rendevous handler
  x86/microcode: Provide new control functions
  x86/microcode: Add per CPU control field
  x86/microcode: Add per CPU result state
  x86/microcode: Sanitize __wait_for_cpus()
  x86/microcode: Clarify the late load logic
  x86/microcode: Handle "nosmt" correctly
  x86/microcode: Clean up mc_cpu_down_prep()
  x86/microcode: Get rid of the schedule work indirection
  x86/microcode: Mop up early loading leftovers
  x86/microcode/amd: Use cached microcode for AP load
  x86/microcode/amd: Cache builtin/initrd microcode early
  x86/microcode/amd: Cache builtin microcode too
  x86/microcode/amd: Use correct per CPU ucode_cpu_info
  ...

21 files changed, 905 insertions, 910 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 01c7082ee999..2a4bc78c27ec 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3333,6 +3333,11 @@
 
 	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 6a917f62eff2..3762f41bb092 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1313,16 +1313,41 @@ config MICROCODE
 	def_bool y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
 
+config MICROCODE_INITRD32
+	def_bool y
+	depends on MICROCODE && X86_32 && BLK_DEV_INITRD
+
 config MICROCODE_LATE_LOADING
 	bool "Late microcode loading (DANGEROUS)"
 	default n
-	depends on MICROCODE
+	depends on MICROCODE && SMP
 	help
 	  Loading microcode late, when the system is up and executing instructions
 	  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/include/asm/apic.h b/arch/x86/include/asm/apic.h
index b0d192f613b7..d21f48f1c242 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -276,7 +276,8 @@ struct apic {
 
 	u32	disable_esr		: 1,
 		dest_mode_logical	: 1,
-		x2apic_set_max_apicid	: 1;
+		x2apic_set_max_apicid	: 1,
+		nmi_to_offline_cpu	: 1;
 
 	u32	(*calc_dest_apicid)(unsigned int cpu);
 
@@ -531,6 +532,8 @@ extern u32 apic_flat_calc_apicid(unsigned int cpu);
 extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
 extern u32 default_cpu_present_to_apicid(int mps_cpu);
 
+void apic_send_nmi_to_offline_cpu(unsigned int cpu);
+
 #else /* CONFIG_X86_LOCAL_APIC */
 
 static inline u32 read_apic_id(void) { return 0; }
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 25050d953eee..fecc4fe1d68a 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -71,26 +71,12 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
 
 extern __noendbr void cet_disable(void);
 
-struct ucode_cpu_info;
+struct cpu_signature;
 
-int intel_cpu_collect_info(struct ucode_cpu_info *uci);
-
-static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1,
-					      unsigned int s2, unsigned int p2)
-{
-	if (s1 != s2)
-		return false;
-
-	/* Processor flags are either both 0 ... */
-	if (!p1 && !p2)
-		return true;
-
-	/* ... or they intersect. */
-	return p1 & p2;
-}
+void intel_collect_cpu_info(struct cpu_signature *sig);
 
 extern u64 x86_read_arch_cap_msr(void);
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf);
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig);
 int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type);
 
 extern struct cpumask cpus_stop_mask;
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index bbbe9d744977..695e569159c1 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -23,6 +23,8 @@ static inline void load_ucode_ap(void) { }
 static inline void microcode_bsp_resume(void) { }
 #endif
 
+extern unsigned long initrd_start_early;
+
 #ifdef CONFIG_CPU_SUP_INTEL
 /* Intel specific microcode defines. Public for IFS */
 struct microcode_header_intel {
@@ -36,7 +38,8 @@ struct microcode_header_intel {
 	unsigned int	datasize;
 	unsigned int	totalsize;
 	unsigned int	metasize;
-	unsigned int	reserved[2];
+	unsigned int	min_req_ver;
+	unsigned int	reserved;
 };
 
 struct microcode_intel {
@@ -68,11 +71,19 @@ static inline u32 intel_get_microcode_revision(void)
 
 	return rev;
 }
+#endif /* !CONFIG_CPU_SUP_INTEL */
 
-void show_ucode_info_early(void);
+bool microcode_nmi_handler(void);
+void microcode_offline_nmi_handler(void);
 
-#else /* CONFIG_CPU_SUP_INTEL */
-static inline void show_ucode_info_early(void) { }
-#endif /* !CONFIG_CPU_SUP_INTEL */
+#ifdef CONFIG_MICROCODE_LATE_LOADING
+DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable);
+static __always_inline bool microcode_nmi_handler_enabled(void)
+{
+	return static_branch_unlikely(&microcode_nmi_handler_enable);
+}
+#else
+static __always_inline bool microcode_nmi_handler_enabled(void) { return false; }
+#endif
 
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f3495623ac99..bf483fcb4e57 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -126,6 +126,7 @@ void clear_bss(void);
 #ifdef __i386__
 
 asmlinkage void __init __noreturn i386_start_kernel(void);
+void __init mk_early_pgtbl_32(void);
 
 #else
 asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 3269a0e23d3a..0000325ab98f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,6 +16,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
+CFLAGS_REMOVE_head32.o = -pg
 CFLAGS_REMOVE_sev.o = -pg
 CFLAGS_REMOVE_rethook.o = -pg
 endif
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 37daa3fd6819..7139867d69cd 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -103,6 +103,7 @@ static struct apic apic_flat __ro_after_init = {
 	.send_IPI_allbutself		= default_send_IPI_allbutself,
 	.send_IPI_all			= default_send_IPI_all,
 	.send_IPI_self			= default_send_IPI_self,
+	.nmi_to_offline_cpu		= true,
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
@@ -173,6 +174,7 @@ static struct apic apic_physflat __ro_after_init = {
 	.send_IPI_allbutself		= default_send_IPI_allbutself,
 	.send_IPI_all			= default_send_IPI_all,
 	.send_IPI_self			= default_send_IPI_self,
+	.nmi_to_offline_cpu		= true,
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 0078730a512e..5da693d633b7 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -97,6 +97,14 @@ sendmask:
 	__apic_send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 }
 
+void apic_send_nmi_to_offline_cpu(unsigned int cpu)
+{
+	if (WARN_ON_ONCE(!apic->nmi_to_offline_cpu))
+		return;
+	if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, &cpus_booted_once_mask)))
+		return;
+	apic->send_IPI(cpu, NMI_VECTOR);
+}
 #endif /* CONFIG_SMP */
 
 static inline int __prepare_ICR2(unsigned int mask)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index affbff65e497..a8306089c91b 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -251,6 +251,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
 	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
 	.send_IPI_all			= x2apic_send_IPI_all,
 	.send_IPI_self			= x2apic_send_IPI_self,
+	.nmi_to_offline_cpu		= true,
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 7c9fe28f742f..558a4a8824f4 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -166,6 +166,7 @@ static struct apic apic_x2apic_phys __ro_after_init = {
 	.send_IPI_allbutself		= x2apic_send_IPI_allbutself,
 	.send_IPI_all			= x2apic_send_IPI_all,
 	.send_IPI_self			= x2apic_send_IPI_self,
+	.nmi_to_offline_cpu		= true,
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5d9591146244..b14fc8c1c953 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2164,8 +2164,6 @@ static inline void setup_getcpu(int cpu)
 }
 
 #ifdef CONFIG_X86_64
-static inline void ucode_cpu_init(int cpu) { }
-
 static inline void tss_setup_ist(struct tss_struct *tss)
 {
 	/* Set up the per-CPU TSS IST stacks */
@@ -2176,16 +2174,8 @@ static inline void tss_setup_ist(struct tss_struct *tss)
 	/* Only mapped when SEV-ES is active */
 	tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC);
 }
-
 #else /* CONFIG_X86_64 */
-
-static inline void ucode_cpu_init(int cpu)
-{
-	show_ucode_info_early();
-}
-
 static inline void tss_setup_ist(struct tss_struct *tss) { }
-
 #endif /* !CONFIG_X86_64 */
 
 static inline void tss_setup_io_bitmap(struct tss_struct *tss)
@@ -2241,8 +2231,6 @@ void cpu_init(void)
 	struct task_struct *cur = current;
 	int cpu = raw_smp_processor_id();
 
-	ucode_cpu_init(cpu);
-
 #ifdef CONFIG_NUMA
 	if (this_cpu_read(numa_node) == 0 &&
 	    early_cpu_to_node(cpu) != NUMA_NO_NODE)
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index bbd1dc38ea03..9373ec01c5ae 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -37,6 +37,16 @@
 
 #include "internal.h"
 
+struct ucode_patch {
+	struct list_head plist;
+	void *data;
+	unsigned int size;
+	u32 patch_id;
+	u16 equiv_cpu;
+};
+
+static LIST_HEAD(microcode_cache);
+
 #define UCODE_MAGIC			0x00414d44
 #define UCODE_EQUIV_CPU_TABLE_TYPE	0x00000000
 #define UCODE_UCODE_TYPE		0x00000001
@@ -121,24 +131,20 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig)
 
 /*
  * Check whether there is a valid microcode container file at the beginning
- * of @buf of size @buf_size. Set @early to use this function in the early path.
+ * of @buf of size @buf_size.
  */
-static bool verify_container(const u8 *buf, size_t buf_size, bool early)
+static bool verify_container(const u8 *buf, size_t buf_size)
 {
 	u32 cont_magic;
 
 	if (buf_size <= CONTAINER_HDR_SZ) {
-		if (!early)
-			pr_debug("Truncated microcode container header.\n");
-
+		pr_debug("Truncated microcode container header.\n");
 		return false;
 	}
 
 	cont_magic = *(const u32 *)buf;
 	if (cont_magic != UCODE_MAGIC) {
-		if (!early)
-			pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
-
+		pr_debug("Invalid magic value (0x%08x).\n", cont_magic);
 		return false;
 	}
 
@@ -147,23 +153,20 @@ static bool verify_container(const u8 *buf, size_t buf_size, bool early)
 
 /*
  * Check whether there is a valid, non-truncated CPU equivalence table at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
  */
-static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
+static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
 {
 	const u32 *hdr = (const u32 *)buf;
 	u32 cont_type, equiv_tbl_len;
 
-	if (!verify_container(buf, buf_size, early))
+	if (!verify_container(buf, buf_size))
 		return false;
 
 	cont_type = hdr[1];
 	if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) {
-		if (!early)
-			pr_debug("Wrong microcode container equivalence table type: %u.\n",
-			       cont_type);
-
+		pr_debug("Wrong microcode container equivalence table type: %u.\n",
+			 cont_type);
 		return false;
 	}
 
@@ -172,9 +175,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
 	equiv_tbl_len = hdr[2];
 	if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) ||
 	    buf_size < equiv_tbl_len) {
-		if (!early)
-			pr_debug("Truncated equivalence table.\n");
-
+		pr_debug("Truncated equivalence table.\n");
 		return false;
 	}
 
@@ -183,22 +184,19 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early)
 
 /*
  * Check whether there is a valid, non-truncated microcode patch section at the
- * beginning of @buf of size @buf_size. Set @early to use this function in the
- * early path.
+ * beginning of @buf of size @buf_size.
  *
  * On success, @sh_psize returns the patch size according to the section header,
  * to the caller.
  */
 static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early)
+__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
 {
 	u32 p_type, p_size;
 	const u32 *hdr;
 
 	if (buf_size < SECTION_HDR_SIZE) {
-		if (!early)
-			pr_debug("Truncated patch section.\n");
-
+		pr_debug("Truncated patch section.\n");
 		return false;
 	}
 
@@ -207,17 +205,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early
 	p_size = hdr[1];
 
 	if (p_type != UCODE_UCODE_TYPE) {
-		if (!early)
-			pr_debug("Invalid type field (0x%x) in container file section header.\n",
-				p_type);
-
+		pr_debug("Invalid type field (0x%x) in container file section header.\n",
+			 p_type);
 		return false;
 	}
 
 	if (p_size < sizeof(struct microcode_header_amd)) {
-		if (!early)
-			pr_debug("Patch of size %u too short.\n", p_size);
-
+		pr_debug("Patch of size %u too short.\n", p_size);
 		return false;
 	}
 
@@ -269,7 +263,7 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size
  * 0: success
  */
 static int
-verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early)
+verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size)
 {
 	struct microcode_header_amd *mc_hdr;
 	unsigned int ret;
@@ -277,7 +271,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
 	u16 proc_id;
 	u8 patch_fam;
 
-	if (!__verify_patch_section(buf, buf_size, &sh_psize, early))
+	if (!__verify_patch_section(buf, buf_size, &sh_psize))
 		return -1;
 
 	/*
@@ -292,16 +286,13 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
 	 * size sh_psize, as the section claims.
 	 */
 	if (buf_size < sh_psize) {
-		if (!early)
-			pr_debug("Patch of size %u truncated.\n", sh_psize);
-
+		pr_debug("Patch of size %u truncated.\n", sh_psize);
 		return -1;
 	}
 
 	ret = __verify_patch_size(family, sh_psize, buf_size);
 	if (!ret) {
-		if (!early)
-			pr_debug("Per-family patch size mismatch.\n");
+		pr_debug("Per-family patch size mismatch.\n");
 		return -1;
 	}
 
@@ -309,8 +300,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea
 
 	mc_hdr	= (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE);
 	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
-		if (!early)
-			pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
+		pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id);
 		return -1;
 	}
 
@@ -337,7 +327,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
 	u16 eq_id;
 	u8 *buf;
 
-	if (!verify_equivalence_table(ucode, size, true))
+	if (!verify_equivalence_table(ucode, size))
 		return 0;
 
 	buf = ucode;
@@ -364,7 +354,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc)
 		u32 patch_size;
 		int ret;
 
-		ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true);
+		ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size);
 		if (ret < 0) {
 			/*
 			 * Patch verification failed, skip to the next container, if
@@ -456,14 +446,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
 {
 	struct cont_desc desc = { 0 };
 	struct microcode_amd *mc;
-	u32 rev, dummy, *new_rev;
 	bool ret = false;
-
-#ifdef CONFIG_X86_32
-	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-#else
-	new_rev = &ucode_new_rev;
-#endif
+	u32 rev, dummy;
 
 	desc.cpuid_1_eax = cpuid_1_eax;
 
@@ -484,8 +468,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
 		return ret;
 
 	if (!__apply_microcode_amd(mc)) {
-		*new_rev = mc->hdr.patch_id;
-		ret      = true;
+		ucode_new_rev = mc->hdr.patch_id;
+		ret = true;
 	}
 
 	return ret;
@@ -501,7 +485,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
 
 	if (family >= 0x15)
 		snprintf(fw_name, sizeof(fw_name),
-			 "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+			 "amd-ucode/microcode_amd_fam%02hhxh.bin", family);
 
 	if (firmware_request_builtin(&fw, fw_name)) {
 		cp->size = fw.size;
@@ -512,36 +496,23 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
 	return false;
 }
 
-static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
+static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret)
 {
-	struct ucode_cpu_info *uci;
 	struct cpio_data cp;
-	const char *path;
-	bool use_pa;
-
-	if (IS_ENABLED(CONFIG_X86_32)) {
-		uci	= (struct ucode_cpu_info *)__pa_nodebug(ucode_cpu_info);
-		path	= (const char *)__pa_nodebug(ucode_path);
-		use_pa	= true;
-	} else {
-		uci     = ucode_cpu_info;
-		path	= ucode_path;
-		use_pa	= false;
-	}
 
 	if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax)))
-		cp = find_microcode_in_initrd(path, use_pa);
-
-	/* Needed in load_microcode_amd() */
-	uci->cpu_sig.sig = cpuid_1_eax;
+		cp = find_microcode_in_initrd(ucode_path);
 
 	*ret = cp;
 }
 
-static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
+void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
 {
 	struct cpio_data cp = { };
 
+	/* Needed in load_microcode_amd() */
+	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
+
 	find_blobs_in_containers(cpuid_1_eax, &cp);
 	if (!(cp.data && cp.size))
 		return;
@@ -549,20 +520,20 @@ static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
 	early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
 }
 
-void load_ucode_amd_early(unsigned int cpuid_1_eax)
-{
-	return apply_ucode_from_containers(cpuid_1_eax);
-}
-
 static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
-int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
+static int __init save_microcode_in_initrd(void)
 {
+	unsigned int cpuid_1_eax = native_cpuid_eax(1);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
 	struct cont_desc desc = { 0 };
 	enum ucode_state ret;
 	struct cpio_data cp;
 
-	cp = find_microcode_in_initrd(ucode_path, false);
+	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+		return 0;
+
+	find_blobs_in_containers(cpuid_1_eax, &cp);
 	if (!(cp.data && cp.size))
 		return -EINVAL;
 
@@ -578,6 +549,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 
 	return 0;
 }
+early_initcall(save_microcode_in_initrd);
 
 /*
  * a small, trivial cache of per-family ucode patches
@@ -631,7 +603,6 @@ static struct ucode_patch *find_patch(unsigned int cpu)
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	u16 equiv_id;
 
-
 	equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
 	if (!equiv_id)
 		return NULL;
@@ -733,12 +704,20 @@ out:
 	return ret;
 }
 
+void load_ucode_amd_ap(unsigned int cpuid_1_eax)
+{
+	unsigned int cpu = smp_processor_id();
+
+	ucode_cpu_info[cpu].cpu_sig.sig = cpuid_1_eax;
+	apply_microcode_amd(cpu);
+}
+
 static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size)
 {
 	u32 equiv_tbl_len;
 	const u32 *hdr;
 
-	if (!verify_equivalence_table(buf, buf_size, false))
+	if (!verify_equivalence_table(buf, buf_size))
 		return 0;
 
 	hdr = (const u32 *)buf;
@@ -784,7 +763,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 	u16 proc_id;
 	int ret;
 
-	ret = verify_patch(family, fw, leftover, patch_size, false);
+	ret = verify_patch(family, fw, leftover, patch_size);
 	if (ret)
 		return ret;
 
@@ -909,6 +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);
 
@@ -918,7 +900,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
 	}
 
 	ret = UCODE_ERROR;
-	if (!verify_container(fw->data, fw->size, false))
+	if (!verify_container(fw->data, fw->size))
 		goto fw_release;
 
 	ret = load_microcode_amd(c->x86, fw->data, fw->size);
@@ -938,10 +920,11 @@ static void microcode_fini_cpu_amd(int cpu)
 }
 
 static struct microcode_ops microcode_amd_ops = {
-	.request_microcode_fw             = request_microcode_amd,
-	.collect_cpu_info                 = collect_cpu_info_amd,
-	.apply_microcode                  = apply_microcode_amd,
-	.microcode_fini_cpu               = microcode_fini_cpu_amd,
+	.request_microcode_fw	= request_microcode_amd,
+	.collect_cpu_info	= collect_cpu_info_amd,
+	.apply_microcode	= apply_microcode_amd,
+	.microcode_fini_cpu	= microcode_fini_cpu_amd,
+	.nmi_safe		= true,
 };
 
 struct microcode_ops * __init init_amd_microcode(void)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 6cc7a2c181da..666d25bbc5ad 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -23,6 +23,7 @@
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
+#include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
@@ -31,6 +32,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 
+#include <asm/apic.h>
 #include <asm/cpu_device_id.h>
 #include <asm/perf_event.h>
 #include <asm/processor.h>
@@ -42,11 +44,10 @@
 #define DRIVER_VERSION	"2.2"
 
 static struct microcode_ops	*microcode_ops;
-static bool dis_ucode_ldr = true;
+bool dis_ucode_ldr = true;
 
-bool initrd_gone;
-
-LIST_HEAD(microcode_cache);
+bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV);
+module_param(force_minrev, bool, S_IRUSR | S_IWUSR);
 
 /*
  * Synchronization.
@@ -90,10 +91,7 @@ static bool amd_check_current_patch_level(void)
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
 
-	if (IS_ENABLED(CONFIG_X86_32))
-		levels = (u32 *)__pa_nodebug(&final_levels);
-	else
-		levels = final_levels;
+	levels = final_levels;
 
 	for (i = 0; levels[i]; i++) {
 		if (lvl == levels[i])
@@ -105,17 +103,8 @@ static bool amd_check_current_patch_level(void)
 static bool __init check_loader_disabled_bsp(void)
 {
 	static const char *__dis_opt_str = "dis_ucode_ldr";
-
-#ifdef CONFIG_X86_32
-	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
-	const char *option  = (const char *)__pa_nodebug(__dis_opt_str);
-	bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr);
-
-#else /* CONFIG_X86_64 */
 	const char *cmdline = boot_command_line;
 	const char *option  = __dis_opt_str;
-	bool *res = &dis_ucode_ldr;
-#endif
 
 	/*
 	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
@@ -123,17 +112,17 @@ static bool __init check_loader_disabled_bsp(void)
 	 * that's good enough as they don't land on the BSP path anyway.
 	 */
 	if (native_cpuid_ecx(1) & BIT(31))
-		return *res;
+		return true;
 
 	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
 		if (amd_check_current_patch_level())
-			return *res;
+			return true;
 	}
 
 	if (cmdline_find_option_bool(cmdline, option) <= 0)
-		*res = false;
+		dis_ucode_ldr = false;
 
-	return *res;
+	return dis_ucode_ldr;
 }
 
 void __init load_ucode_bsp(void)
@@ -168,23 +157,14 @@ void __init load_ucode_bsp(void)
 	if (intel)
 		load_ucode_intel_bsp();
 	else
-		load_ucode_amd_early(cpuid_1_eax);
-}
-
-static bool check_loader_disabled_ap(void)
-{
-#ifdef CONFIG_X86_32
-	return *((bool *)__pa_nodebug(&dis_ucode_ldr));
-#else
-	return dis_ucode_ldr;
-#endif
+		load_ucode_amd_bsp(cpuid_1_eax);
 }
 
 void load_ucode_ap(void)
 {
 	unsigned int cpuid_1_eax;
 
-	if (check_loader_disabled_ap())
+	if (dis_ucode_ldr)
 		return;
 
 	cpuid_1_eax = native_cpuid_eax(1);
@@ -196,97 +176,44 @@ void load_ucode_ap(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (x86_family(cpuid_1_eax) >= 0x10)
-			load_ucode_amd_early(cpuid_1_eax);
-		break;
-	default:
-		break;
-	}
-}
-
-static int __init save_microcode_in_initrd(void)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-	int ret = -EINVAL;
-
-	switch (c->x86_vendor) {
-	case X86_VENDOR_INTEL:
-		if (c->x86 >= 6)
-			ret = save_microcode_in_initrd_intel();
-		break;
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0x10)
-			ret = save_microcode_in_initrd_amd(cpuid_eax(1));
+			load_ucode_amd_ap(cpuid_1_eax);
 		break;
 	default:
 		break;
 	}
-
-	initrd_gone = tr