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
  ...

1 files changed, 226 insertions, 462 deletions

diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 94dd6af9c963a..6024feb98d29d 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -14,7 +14,6 @@
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -32,11 +31,14 @@
 
 static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
 
+#define UCODE_BSP_LOADED	((struct microcode_intel *)0x1UL)
+
 /* Current microcode patch used in early patching on the APs. */
-static struct microcode_intel *intel_ucode_patch;
+static struct microcode_intel *ucode_patch_va __read_mostly;
+static struct microcode_intel *ucode_patch_late __read_mostly;
 
 /* last level cache size per core */
-static int llc_size_per_core;
+static unsigned int llc_size_per_core __ro_after_init;
 
 /* microcode format is extended from prescott processors */
 struct extended_signature {
@@ -66,60 +68,52 @@ static inline unsigned int exttable_size(struct extended_sigtable *et)
 	return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE;
 }
 
-int intel_cpu_collect_info(struct ucode_cpu_info *uci)
+void intel_collect_cpu_info(struct cpu_signature *sig)
 {
-	unsigned int val[2];
-	unsigned int family, model;
-	struct cpu_signature csig = { 0 };
-	unsigned int eax, ebx, ecx, edx;
-
-	memset(uci, 0, sizeof(*uci));
-
-	eax = 0x00000001;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-	csig.sig = eax;
+	sig->sig = cpuid_eax(1);
+	sig->pf = 0;
+	sig->rev = intel_get_microcode_revision();
 
-	family = x86_family(eax);
-	model  = x86_model(eax);
+	if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) {
+		unsigned int val[2];
 
-	if (model >= 5 || family > 6) {
 		/* get processor flags from MSR 0x17 */
 		native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
-		csig.pf = 1 << ((val[1] >> 18) & 7);
+		sig->pf = 1 << ((val[1] >> 18) & 7);
 	}
+}
+EXPORT_SYMBOL_GPL(intel_collect_cpu_info);
 
-	csig.rev = intel_get_microcode_revision();
-
-	uci->cpu_sig = csig;
+static inline bool cpu_signatures_match(struct cpu_signature *s1, unsigned int sig2,
+					unsigned int pf2)
+{
+	if (s1->sig != sig2)
+		return false;
 
-	return 0;
+	/* Processor flags are either both 0 or they intersect. */
+	return ((!s1->pf && !pf2) || (s1->pf & pf2));
 }
-EXPORT_SYMBOL_GPL(intel_cpu_collect_info);
 
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-int intel_find_matching_signature(void *mc, unsigned int csig, int cpf)
+bool intel_find_matching_signature(void *mc, struct cpu_signature *sig)
 {
 	struct microcode_header_intel *mc_hdr = mc;
-	struct extended_sigtable *ext_hdr;
 	struct extended_signature *ext_sig;
+	struct extended_sigtable *ext_hdr;
 	int i;
 
-	if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
-		return 1;
+	if (cpu_signatures_match(sig, mc_hdr->sig, mc_hdr->pf))
+		return true;
 
 	/* Look for ext. headers: */
 	if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE)
-		return 0;
+		return false;
 
 	ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE;
 	ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
 
 	for (i = 0; i < ext_hdr->count; i++) {
-		if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
-			return 1;
+		if (cpu_signatures_match(sig, ext_sig->sig, ext_sig->pf))
+			return true;
 		ext_sig++;
 	}
 	return 0;
@@ -240,264 +234,91 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
 }
 EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
 
-/*
- * Returns 1 if update has been found, 0 otherwise.
- */
-static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
+static void update_ucode_pointer(struct microcode_intel *mc)
 {
-	struct microcode_header_intel *mc_hdr = mc;
-
-	if (mc_hdr->rev <= new_rev)
-		return 0;
-
-	return intel_find_matching_signature(mc, csig, cpf);
-}
-
-static struct ucode_patch *memdup_patch(void *data, unsigned int size)
-{
-	struct ucode_patch *p;
-
-	p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
-	if (!p)
-		return NULL;
-
-	p->data = kmemdup(data, size, GFP_KERNEL);
-	if (!p->data) {
-		kfree(p);
-		return NULL;
-	}
-
-	return p;
-}
-
-static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size)
-{
-	struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
-	struct ucode_patch *iter, *tmp, *p = NULL;
-	bool prev_found = false;
-	unsigned int sig, pf;
-
-	mc_hdr = (struct microcode_header_intel *)data;
-
-	list_for_each_entry_safe(iter, tmp, &microcode_cache, plist) {
-		mc_saved_hdr = (struct microcode_header_intel *)iter->data;
-		sig	     = mc_saved_hdr->sig;
-		pf	     = mc_saved_hdr->pf;
-
-		if (intel_find_matching_signature(data, sig, pf)) {
-			prev_found = true;
-
-			if (mc_hdr->rev <= mc_saved_hdr->rev)
-				continue;
-
-			p = memdup_patch(data, size);
-			if (!p)
-				pr_err("Error allocating buffer %p\n", data);
-			else {
-				list_replace(&iter->plist, &p->plist);
-				kfree(iter->data);
-				kfree(iter);
-			}
-		}
-	}
+	kvfree(ucode_patch_va);
 
 	/*
-	 * There weren't any previous patches found in the list cache; save the
-	 * newly found.
+	 * Save the virtual address for early loading and for eventual free
+	 * on late loading.
 	 */
-	if (!prev_found) {
-		p = memdup_patch(data, size);
-		if (!p)
-			pr_err("Error allocating buffer for %p\n", data);
-		else
-			list_add_tail(&p->plist, &microcode_cache);
-	}
-
-	if (!p)
-		return;
+	ucode_patch_va = mc;
+}
 
-	if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf))
-		return;
+static void save_microcode_patch(struct microcode_intel *patch)
+{
+	unsigned int size = get_totalsize(&patch->hdr);
+	struct microcode_intel *mc;
 
-	/*
-	 * Save for early loading. On 32-bit, that needs to be a physical
-	 * address as the APs are running from physical addresses, before
-	 * paging has been enabled.
-	 */
-	if (IS_ENABLED(CONFIG_X86_32))
-		intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data);
+	mc = kvmemdup(patch, size, GFP_KERNEL);
+	if (mc)
+		update_ucode_pointer(mc);
 	else
-		intel_ucode_patch = p->data;
+		pr_err("Unable to allocate microcode memory size: %u\n", size);
 }
 
-/*
- * Get microcode matching with BSP's model. Only CPUs with the same model as
- * BSP can stay in the platform.
- */
-static struct microcode_intel *
-scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save)
+/* Scan blob for microcode matching the boot CPUs family, model, stepping */
+static __init struct microcode_intel *scan_microcode(void *data, size_t size,
+						     struct ucode_cpu_info *uci,
+						     bool save)
 {
 	struct microcode_header_intel *mc_header;
 	struct microcode_intel *patch = NULL;
+	u32 cur_rev = uci->cpu_sig.rev;
 	unsigned int mc_size;
 
-	while (size) {
-		if (size < sizeof(struct microcode_header_intel))
-			break;
-
+	for (; size >= sizeof(struct microcode_header_intel); size -= mc_size, data += mc_size) {
 		mc_header = (struct microcode_header_intel *)data;
 
 		mc_size = get_totalsize(mc_header);
-		if (!mc_size ||
-		    mc_size > size ||
+		if (!mc_size || mc_size > size ||
 		    intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0)
 			break;
 
-		size -= mc_size;
-
-		if (!intel_find_matching_signature(data, uci->cpu_sig.sig,
-						   uci->cpu_sig.pf)) {
-			data += mc_size;
+		if (!intel_find_matching_signature(data, &uci->cpu_sig))
 			continue;
-		}
 
+		/*
+		 * For saving the early microcode, find the matching revision which
+		 * was loaded on the BSP.
+		 *
+		 * On the BSP during early boot, find a newer revision than
+		 * actually loaded in the CPU.
+		 */
 		if (save) {
-			save_microcode_patch(uci, data, mc_size);
-			goto next;
-		}
-
-
-		if (!patch) {
-			if (!has_newer_microcode(data,
-						 uci->cpu_sig.sig,
-						 uci->cpu_sig.pf,
-						 uci->cpu_sig.rev))
-				goto next;
-
-		} else {
-			struct microcode_header_intel *phdr = &patch->hdr;
-
-			if (!has_newer_microcode(data,
-						 phdr->sig,
-						 phdr->pf,
-						 phdr->rev))
-				goto next;
+			if (cur_rev != mc_header->rev)
+				continue;
+		} else if (cur_rev >= mc_header->rev) {
+			continue;
 		}
 
-		/* We have a newer patch, save it. */
 		patch = data;
-
-next:
-		data += mc_size;
-	}
-
-	if (size)
-		return NULL;
-
-	return patch;
-}
-
-static bool load_builtin_intel_microcode(struct cpio_data *cp)
-{
-	unsigned int eax = 1, ebx, ecx = 0, edx;
-	struct firmware fw;
-	char name[30];
-
-	if (IS_ENABLED(CONFIG_X86_32))
-		return false;
-
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	sprintf(name, "intel-ucode/%02x-%02x-%02x",
-		      x86_family(eax), x86_model(eax), x86_stepping(eax));
-
-	if (firmware_request_builtin(&fw, name)) {
-		cp->size = fw.size;
-		cp->data = (void *)fw.data;
-		return true;
-	}
-
-	return false;
-}
-
-static void print_ucode_info(int old_rev, int new_rev, unsigned int date)
-{
-	pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
-		     old_rev,
-		     new_rev,
-		     date & 0xffff,
-		     date >> 24,
-		     (date >> 16) & 0xff);
-}
-
-#ifdef CONFIG_X86_32
-
-static int delay_ucode_info;
-static int current_mc_date;
-static int early_old_rev;
-
-/*
- * Print early updated ucode info after printk works. This is delayed info dump.
- */
-void show_ucode_info_early(void)
-{
-	struct ucode_cpu_info uci;
-
-	if (delay_ucode_info) {
-		intel_cpu_collect_info(&uci);
-		print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date);
-		delay_ucode_info = 0;
+		cur_rev = mc_header->rev;
 	}
-}
-
-/*
- * At this point, we can not call printk() yet. Delay printing microcode info in
- * show_ucode_info_early() until printk() works.
- */
-static void print_ucode(int old_rev, int new_rev, int date)
-{
-	int *delay_ucode_info_p;
-	int *current_mc_date_p;
-	int *early_old_rev_p;
-
-	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
-	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
-	early_old_rev_p = (int *)__pa_nodebug(&early_old_rev);
-
-	*delay_ucode_info_p = 1;
-	*current_mc_date_p = date;
-	*early_old_rev_p = old_rev;
-}
-#else
 
-static inline void print_ucode(int old_rev, int new_rev, int date)
-{
-	print_ucode_info(old_rev, new_rev, date);
+	return size ? NULL : patch;
 }
-#endif
 
-static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
+static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
+					  struct microcode_intel *mc,
+					  u32 *cur_rev)
 {
-	struct microcode_intel *mc;
-	u32 rev, old_rev;
+	u32 rev;
 
-	mc = uci->mc;
 	if (!mc)
-		return 0;
+		return UCODE_NFOUND;
 
 	/*
 	 * Save us the MSR write below - which is a particular expensive
 	 * operation - when the other hyperthread has updated the microcode
 	 * already.
 	 */
-	rev = intel_get_microcode_revision();
-	if (rev >= mc->hdr.rev) {
-		uci->cpu_sig.rev = rev;
+	*cur_rev = intel_get_microcode_revision();
+	if (*cur_rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = *cur_rev;
 		return UCODE_OK;
 	}
 
-	old_rev = rev;
-
 	/*
 	 * Writeback and invalidate caches before updating microcode to avoid
 	 * internal issues depending on what the microcode is updating.
@@ -509,247 +330,182 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 
 	rev = intel_get_microcode_revision();
 	if (rev != mc->hdr.rev)
-		return -1;
+		return UCODE_ERROR;
 
 	uci->cpu_sig.rev = rev;
+	return UCODE_UPDATED;
+}
 
-	if (early)
-		print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date);
-	else
-		print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date);
+static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *mc = uci->mc;
+	enum ucode_state ret;
+	u32 cur_rev, date;
 
-	return 0;
+	ret = __apply_microcode(uci, mc, &cur_rev);
+	if (ret == UCODE_UPDATED) {
+		date = mc->hdr.date;
+		pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n",
+			     cur_rev, mc->hdr.rev, date & 0xffff, date >> 24, (date >> 16) & 0xff);
+	}
+	return ret;
 }
 
-int __init save_microcode_in_initrd_intel(void)
+static __init bool load_builtin_intel_microcode(struct cpio_data *cp)
 {
-	struct ucode_cpu_info uci;
-	struct cpio_data cp;
-
-	/*
-	 * initrd is going away, clear patch ptr. We will scan the microcode one
-	 * last time before jettisoning and save a patch, if found. Then we will
-	 * update that pointer too, with a stable patch address to use when
-	 * resuming the cores.
-	 */
-	intel_ucode_patch = NULL;
+	unsigned int eax = 1, ebx, ecx = 0, edx;
+	struct firmware fw;
+	char name[30];
 
-	if (!load_builtin_intel_microcode(&cp))
-		cp = find_microcode_in_initrd(ucode_path, false);
+	if (IS_ENABLED(CONFIG_X86_32))
+		return false;
 
-	if (!(cp.data && cp.size))
-		return 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
 
-	intel_cpu_collect_info(&uci);
+	sprintf(name, "intel-ucode/%02x-%02x-%02x",
+		x86_family(eax), x86_model(eax), x86_stepping(eax));
 
-	scan_microcode(cp.data, cp.size, &uci, true);
-	return 0;
+	if (firmware_request_builtin(&fw, name)) {
+		cp->size = fw.size;
+		cp->data = (void *)fw.data;
+		return true;
+	}
+	return false;
 }
 
-/*
- * @res_patch, output: a pointer to the patch we found.
- */
-static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci)
+static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *uci, bool save)
 {
-	static const char *path;
 	struct cpio_data cp;
-	bool use_pa;
-
-	if (IS_ENABLED(CONFIG_X86_32)) {
-		path	  = (const char *)__pa_nodebug(ucode_path);
-		use_pa	  = true;
-	} else {
-		path	  = ucode_path;
-		use_pa	  = false;
-	}
 
-	/* try built-in microcode first */
 	if (!load_builtin_intel_microcode(&cp))
-		cp = find_microcode_in_initrd(path, use_pa);
+		cp = find_microcode_in_initrd(ucode_path);
 
 	if (!(cp.data && cp.size))
 		return NULL;
 
-	intel_cpu_collect_info(uci);
+	intel_collect_cpu_info(&uci->cpu_sig);
 
-	return scan_microcode(cp.data, cp.size, uci, false);
+	return scan_microcode(cp.data, cp.size, uci, save);
 }
 
-void __init load_ucode_intel_bsp(void)
+/*
+ * Invoked from an early init call to save the microcode blob which was
+ * selected during early boot when mm was not usable. The microcode must be
+ * saved because initrd is going away. It's an early init call so the APs
+ * just can use the pointer and do not have to scan initrd/builtin firmware
+ * again.
+ */
+static int __init save_builtin_microcode(void)
 {
-	struct microcode_intel *patch;
 	struct ucode_cpu_info uci;
 
-	patch = __load_ucode_intel(&uci);
-	if (!patch)
-		return;
+	if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED)
+		return 0;
 
-	uci.mc = patch;
+	if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return 0;
 
-	apply_microcode_early(&uci, true);
+	uci.mc = get_microcode_blob(&uci, true);
+	if (uci.mc)
+		save_microcode_patch(uci.mc);
+	return 0;
 }
+early_initcall(save_builtin_microcode);
 
-void load_ucode_intel_ap(void)
+/* Load microcode on BSP from initrd or builtin blobs */
+void __init load_ucode_intel_bsp(void)
 {
-	struct microcode_intel *patch, **iup;
 	struct ucode_cpu_info uci;
 
-	if (IS_ENABLED(CONFIG_X86_32))
-		iup = (struct microcode_intel **) __pa_nodebug(&intel_ucode_patch);
-	else
-		iup = &intel_ucode_patch;
-
-	if (!*iup) {
-		patch = __load_ucode_intel(&uci);
-		if (!patch)
-			return;
-
-		*iup = patch;
-	}
-
-	uci.mc = *iup;
-
-	apply_microcode_early(&uci, true);
+	uci.mc = get_microcode_blob(&uci, false);
+	if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED)
+		ucode_patch_va = UCODE_BSP_LOADED;
 }
 
-static struct microcode_intel *find_patch(struct ucode_cpu_info *uci)
+void load_ucode_intel_ap(void)
 {
-	struct microcode_header_intel *phdr;
-	struct ucode_patch *iter, *tmp;
-
-	list_for_each_entry_safe(iter, tmp, &microcode_cache, plist) {
-
-		phdr = (struct microcode_header_intel *)iter->data;
-
-		if (phdr->rev <= uci->cpu_sig.rev)
-			continue;
-
-		if (!intel_find_matching_signature(phdr,
-						   uci->cpu_sig.sig,
-						   uci->cpu_sig.pf))
-			continue;
+	struct ucode_cpu_info uci;
 
-		return iter->data;
-	}
-	return NULL;
+	uci.mc = ucode_patch_va;
+	if (uci.mc)
+		apply_microcode_early(&uci);
 }
 
+/* Reload microcode on resume */
 void reload_ucode_intel(void)
 {
-	struct microcode_intel *p;
-	struct ucode_cpu_info uci;
-
-	intel_cpu_collect_info(&uci);
-
-	p = find_patch(&uci);
-	if (!p)
-		return;
-
-	uci.mc = p;
+	struct ucode_cpu_info uci = { .mc = ucode_patch_va, };
 
-	apply_microcode_early(&uci, false);
+	if (uci.mc)
+		apply_microcode_early(&uci);
 }
 
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-	unsigned int val[2];
-
-	memset(csig, 0, sizeof(*csig));
-
-	csig->sig = cpuid_eax(0x00000001);
-
-	if ((c->x86_model >= 5) || (c->x86 > 6)) {
-		/* get processor flags from MSR 0x17 */
-		rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
-		csig->pf = 1 << ((val[1] >> 18) & 7);
-	}
-
-	csig->rev = c->microcode;
-
+	intel_collect_cpu_info(csig);
 	return 0;
 }
 
-static enum ucode_state apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_late(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
-	struct microcode_intel *mc;
+	struct microcode_intel *mc = ucode_patch_late;
 	enum ucode_state ret;
-	static int prev_rev;
-	u32 rev;
+	u32 cur_rev;
 
-	/* We should bind the task to the CPU */
-	if (WARN_ON(raw_smp_processor_id() != cpu))
+	if (WARN_ON_ONCE(smp_processor_id() != cpu))
 		return UCODE_ERROR;
 
-	/* Look for a newer patch in our cache: */
-	mc = find_patch(uci);
-	if (!mc) {
-		mc = uci->mc;
-		if (!mc)
-			return UCODE_NFOUND;
-	}
+	ret = __apply_microcode(uci, mc, &cur_rev);
+	if (ret != UCODE_UPDATED && ret != UCODE_OK)
+		return ret;
 
-	/*
-	 * Save us the MSR write below - which is a particular expensive
-	 * operation - when the other hyperthread has updated the microcode
-	 * already.
-	 */
-	rev = intel_get_microcode_revision();
-	if (rev >= mc->hdr.rev) {
-		ret = UCODE_OK;
-		goto out;
+	if (!cpu && uci->cpu_sig.rev != cur_rev) {
+		pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n",
+			uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24,
+			(mc->hdr.date >> 16) & 0xff);
 	}
 
-	/*
-	 * Writeback and invalidate caches before updating microcode to avoid
-	 * internal issues depending on what the microcode is updating.
-	 */
-	native_wbinvd();
+	cpu_data(cpu).microcode	 = uci->cpu_sig.rev;
+	if (!cpu)
+		boot_cpu_data.microcode = uci->cpu_sig.rev;
 
-	/* write microcode via MSR 0x79 */
-	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+	return ret;
+}
 
-	rev = intel_get_microcode_revision();
+static bool ucode_validate_minrev(struct microcode_header_intel *mc_header)
+{
+	int cur_rev = boot_cpu_data.microcode;
 
-	if (rev != mc->hdr.rev) {
-		pr_err("CPU%d update to revision 0x%x failed\n",
-		       cpu, mc->hdr.rev);
-		return UCODE_ERROR;
+	/*
+	 * When late-loading, ensure the header declares a minimum revision
+	 * required to perform a late-load. The previously reserved field
+	 * is 0 in older microcode blobs.
+	 */
+	if (!mc_header->min_req_ver) {
+		pr_info("Unsafe microcode update: Microcode header does not specify a required min version\n");
+		return false;
 	}
 
-	if (bsp && rev != prev_rev) {
-		pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
-			rev,
-			mc->hdr.date & 0xffff,
-			mc->hdr.date >> 24,
-			(mc->hdr.date >> 16) & 0xff);
-		prev_rev = rev;
+	/*
+	 * Check whether the current revision is either greater or equal to
+	 * to the minimum revision specified in the header.
+	 */
+	if (cur_rev < mc_header->min_req_ver) {
+		pr_info("Unsafe microcode update: Current revision 0x%x too old\n", cur_rev);
+		pr_info("Current should be at 0x%x or higher. Use early loading instead\n", mc_header->min_req_ver);
+		return false;
 	}
-
-	ret = UCODE_UPDATED;
-
-out:
-	uci->cpu_sig.rev = rev;
-	c->microcode	 = rev;
-
-	/* Update boot_cpu_data's revision too, if we're on the BSP: */
-	if (bsp)
-		boot_cpu_data.microcode = rev;
-
-	return ret;
+	return true;
 }
 
-static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
+static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	unsigned int curr_mc_size = 0, new_mc_size = 0;
-	enum ucode_state ret = UCODE_OK;
-	int new_rev = uci->cpu_sig.rev;
+	bool is_safe, new_is_safe = false;
+	int cur_rev = uci->cpu_sig.rev;
+	unsigned int curr_mc_size = 0;
 	u8 *new_mc = NULL, *mc = NULL;
-	unsigned int csig, cpf;
 
 	while (iov_iter_count(iter)) {
 		struct microcode_header_intel mc_header;
@@ -758,68 +514,66 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
 
 		if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
 			pr_err("error! Truncated or inaccessible header in microcode data file\n");
-			break;
+			goto fail;
 		}
 
 		mc_size = get_totalsize(&mc_header);
 		if (mc_size < sizeof(mc_header)) {
 			pr_err("error! Bad data in microcode data file (totalsize too small)\n");
-			break;
+			goto fail;
 		}
 		data_size = mc_size - sizeof(mc_header);
 		if (data_size > iov_iter_count(iter)) {
 			pr_err("error! Bad data in microcode data file (truncated file?)\n");
-			break;
+			goto fail;
 		}
 
 		/* For performance reasons, reuse mc area when possible */
 		if (!mc || mc_size > curr_mc_size) {
-			vfree(mc);
-			mc = vmalloc(mc_size);
+			kvfree(mc);
+			mc = kvmalloc(mc_size, GFP_KERNEL);
 			if (!mc)
-				break;
+				goto fail;
 			curr_mc_size = mc_size;
 		}
 
 		memcpy(mc, &mc_header, sizeof(mc_header));
 		data = mc + sizeof(mc_header);
 		if (!copy_from_iter_full(data, data_size, iter) ||
-		    intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) {
-			break;
-		}
+		    intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0)
+			goto fail;
 
-		csig = uci->cpu_sig.sig;
-		cpf = uci->cpu_sig.pf;
-		if (has_newer_microcode(mc, csig, cpf, new_rev)) {
-			vfree(new_mc);
-			new_rev = mc_header.rev;
-			new_mc  = mc;
-			new_mc_size = mc_size;
-			mc = NULL;	/* trigger new vmalloc */
-			ret = UCODE_NEW;
-		}
-	}
+		if (cur_rev >= mc_header.rev)
+			continue;
 
-	vfree(mc);
+		if (!intel_find_matching_signature(mc, &uci->cpu_sig))
+			continue;
 
-	if (iov_iter_count(iter)) {
-		vfree(new_mc);
-		return UCODE_ERROR;
+		is_safe = ucode_validate_minrev(&mc_header);
+		if (force_minrev && !is_safe)
+			continue;
+
+		kvfree(new_mc);
+		cur_rev = mc_header.rev;
+		new_mc  = mc;
+		new_is_safe = is_safe;
+		mc = NULL;
 	}
 
+	if (iov_iter_count(iter))
+		goto fail;
+
+	kvfree(mc);
 	if (!new_mc)
 		return UCODE_NFOUND;
 
-	vfree(uci->mc);
-	uci->mc = (struct microcode_intel *)new_mc;
-
-	/* Save for CPU hotplug */
-	save_microcode_patch(uci, new_mc, new_mc_size);
+	ucode_patch_late = (struct microcode_intel *)new_mc;
+	return new_is_safe ? UCODE_NEW_SAFE : UCODE_NEW;
 
-	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
-		 cpu, new_rev, uci->cpu_sig.rev);
-
-	return ret;
+fail:
+	kvfree(mc);
+	kvfree(new_mc);
+	return UCODE_ERROR;
 }
 
 static bool is_blacklisted(unsigned int cpu)
@@ -868,26 +622,36 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device)
 	kvec.iov_base = (void *)firmware->data;
 	kvec.iov_len = firmware->size;
 	iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size);
-	ret = generic_load_microcode(cpu, &iter);
+	ret = parse_microcode_blobs(cpu, &iter);
 
 	release_firmware(firmware);
 
 	return ret;
 }
 
+static void finalize_late_load(int result)
+{
+	if (!result)
+		update_ucode_pointer(ucode_patch_late);
+	else
+		kvfree(ucode_patch_late);
+	ucode_patch_late = NULL;
+}
+
 static struct microcode_ops microcode_intel_ops = {
-	.request_microcode_fw             = request_microcode_fw,
-	.collect_cpu_info                 = collect_cpu_info,
-	.apply_microcode                  = apply_microcode_intel,
+	.request_microcode_fw	= request_microcode_fw,
+	.collect_cpu_info	= collect_cpu_info,
+	.apply_microcode	= apply_microcode_late,
+	.finalize_late_load	= finalize_late_load,
+	.use_nmi		= IS_ENABLED(CONFIG_X86_64),
 };
 
-static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
+static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c)
 {
 	u64 llc_size = c->x86_cache_size * 1024ULL;
 
 	do_div(llc_size, c->x86_max_cores);
-
-	return (int)llc_size;
+	llc_size_per_core = (unsigned int)llc_size;
 }
 
 struct microcode_ops * __init init_intel_microcode(void)
@@ -900,7 +664,7 @@ struct microcode_ops * __init init_intel_microcode(void)
 		return NULL;
 	}
 
-	llc_size_per_core = calc_llc_size_per_core(c);
+	calc_llc_size_per_core(c);
 
 	return &microcode_intel_ops;
 }