21 files changed, 555 insertions, 398 deletions

diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 485441b7f030..bfeb18fad63f 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -51,7 +51,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback)
 	 * will block the interrupt whose vector is lower than
 	 * HYPERVISOR_CALLBACK_VECTOR.
 	 */
-	ack_APIC_irq();
+	apic_eoi();
 	inc_irq_stat(irq_hv_callback_count);
 
 	if (acrn_intr_handler)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7eca6a8abbb1..dd8379d84445 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1047,7 +1047,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_FSRS);
 
 	/* get apicid instead of initial apic id from cpuid */
-	c->apicid = hard_smp_processor_id();
+	c->apicid = read_apic_id();
 
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 00f043a094fc..382d4e6b848d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -59,7 +59,6 @@
 #include <asm/cacheinfo.h>
 #include <asm/memtype.h>
 #include <asm/microcode.h>
-#include <asm/microcode_intel.h>
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/uv/uv.h>
@@ -588,27 +587,43 @@ __noendbr void ibt_restore(u64 save)
 
 static __always_inline void setup_cet(struct cpuinfo_x86 *c)
 {
-	u64 msr = CET_ENDBR_EN;
+	bool user_shstk, kernel_ibt;
 
-	if (!HAS_KERNEL_IBT ||
-	    !cpu_feature_enabled(X86_FEATURE_IBT))
+	if (!IS_ENABLED(CONFIG_X86_CET))
 		return;
 
-	wrmsrl(MSR_IA32_S_CET, msr);
+	kernel_ibt = HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT);
+	user_shstk = cpu_feature_enabled(X86_FEATURE_SHSTK) &&
+		     IS_ENABLED(CONFIG_X86_USER_SHADOW_STACK);
+
+	if (!kernel_ibt && !user_shstk)
+		return;
+
+	if (user_shstk)
+		set_cpu_cap(c, X86_FEATURE_USER_SHSTK);
+
+	if (kernel_ibt)
+		wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN);
+	else
+		wrmsrl(MSR_IA32_S_CET, 0);
+
 	cr4_set_bits(X86_CR4_CET);
 
-	if (!ibt_selftest()) {
+	if (kernel_ibt && ibt_selftest()) {
 		pr_err("IBT selftest: Failed!\n");
 		wrmsrl(MSR_IA32_S_CET, 0);
 		setup_clear_cpu_cap(X86_FEATURE_IBT);
-		return;
 	}
 }
 
 __noendbr void cet_disable(void)
 {
-	if (cpu_feature_enabled(X86_FEATURE_IBT))
-		wrmsrl(MSR_IA32_S_CET, 0);
+	if (!(cpu_feature_enabled(X86_FEATURE_IBT) ||
+	      cpu_feature_enabled(X86_FEATURE_SHSTK)))
+		return;
+
+	wrmsrl(MSR_IA32_S_CET, 0);
+	wrmsrl(MSR_IA32_U_CET, 0);
 }
 
 /*
@@ -1492,6 +1507,9 @@ static void __init cpu_parse_early_param(void)
 	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
 		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 
+	if (cmdline_find_option_bool(boot_command_line, "nousershstk"))
+		setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK);
+
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
 	if (arglen <= 0)
 		return;
@@ -1959,7 +1977,7 @@ void enable_sep_cpu(void)
 }
 #endif
 
-void __init identify_boot_cpu(void)
+static __init void identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
 	if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
@@ -2300,8 +2318,7 @@ void store_cpu_caps(struct cpuinfo_x86 *curr_info)
  * @prev_info:	CPU capabilities stored before an update.
  *
  * The microcode loader calls this upon late microcode load to recheck features,
- * only when microcode has been updated. Caller holds microcode_mutex and CPU
- * hotplug lock.
+ * only when microcode has been updated. Caller holds and CPU hotplug lock.
  *
  * Return: None
  */
@@ -2343,7 +2360,7 @@ void __init arch_cpu_finalize_init(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology();
+	cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings);
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index f6748c8bd647..e462c1d3800a 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -81,6 +81,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_XFD,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
+	{ X86_FEATURE_SHSTK,			X86_FEATURE_XSAVES    },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 5a2962c492d3..defdc594be14 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 
+#include <asm/apic.h>
 #include <asm/cpu.h>
 #include <asm/smp.h>
 #include <asm/numa.h>
@@ -300,7 +301,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
 	set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
 	/* get apicid instead of initial apic id from cpuid */
-	c->apicid = hard_smp_processor_id();
+	c->apicid = read_apic_id();
 
 	/*
 	 * XXX someone from Hygon needs to confirm this DTRT
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1c4639588ff9..be4045628fd3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -20,7 +20,7 @@
 #include <asm/bugs.h>
 #include <asm/cpu.h>
 #include <asm/intel-family.h>
-#include <asm/microcode_intel.h>
+#include <asm/microcode.h>
 #include <asm/hwcap2.h>
 #include <asm/elf.h>
 #include <asm/cpu_device_id.h>
@@ -184,180 +184,6 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 	return false;
 }
 
-int intel_cpu_collect_info(struct ucode_cpu_info *uci)
-{
-	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;
-
-	family = x86_family(eax);
-	model  = x86_model(eax);
-
-	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);
-	}
-
-	csig.rev = intel_get_microcode_revision();
-
-	uci->cpu_sig = csig;
-
-	return 0;
-}
-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)
-{
-	struct microcode_header_intel *mc_hdr = mc;
-	struct extended_sigtable *ext_hdr;
-	struct extended_signature *ext_sig;
-	int i;
-
-	if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
-		return 1;
-
-	/* Look for ext. headers: */
-	if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
-		return 0;
-
-	ext_hdr = mc + 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;
-		ext_sig++;
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(intel_find_matching_signature);
-
-/**
- * intel_microcode_sanity_check() - Sanity check microcode file.
- * @mc: Pointer to the microcode file contents.
- * @print_err: Display failure reason if true, silent if false.
- * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file.
- *            Validate if the microcode header type matches with the type
- *            specified here.
- *
- * Validate certain header fields and verify if computed checksum matches
- * with the one specified in the header.
- *
- * Return: 0 if the file passes all the checks, -EINVAL if any of the checks
- * fail.
- */
-int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type)
-{
-	unsigned long total_size, data_size, ext_table_size;
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header = NULL;
-	u32 sum, orig_sum, ext_sigcount = 0, i;
-	struct extended_signature *ext_sig;
-
-	total_size = get_totalsize(mc_header);
-	data_size = get_datasize(mc_header);
-
-	if (data_size + MC_HEADER_SIZE > total_size) {
-		if (print_err)
-			pr_err("Error: bad microcode data file size.\n");
-		return -EINVAL;
-	}
-
-	if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) {
-		if (print_err)
-			pr_err("Error: invalid/unknown microcode update format. Header type %d\n",
-			       mc_header->hdrver);
-		return -EINVAL;
-	}
-
-	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
-	if (ext_table_size) {
-		u32 ext_table_sum = 0;
-		u32 *ext_tablep;
-
-		if (ext_table_size < EXT_HEADER_SIZE ||
-		    ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
-			if (print_err)
-				pr_err("Error: truncated extended signature table.\n");
-			return -EINVAL;
-		}
-
-		ext_header = mc + MC_HEADER_SIZE + data_size;
-		if (ext_table_size != exttable_size(ext_header)) {
-			if (print_err)
-				pr_err("Error: extended signature table size mismatch.\n");
-			return -EFAULT;
-		}
-
-		ext_sigcount = ext_header->count;
-
-		/*
-		 * Check extended table checksum: the sum of all dwords that
-		 * comprise a valid table must be 0.
-		 */
-		ext_tablep = (u32 *)ext_header;
-
-		i = ext_table_size / sizeof(u32);
-		while (i--)
-			ext_table_sum += ext_tablep[i];
-
-		if (ext_table_sum) {
-			if (print_err)
-				pr_warn("Bad extended signature table checksum, aborting.\n");
-			return -EINVAL;
-		}
-	}
-
-	/*
-	 * Calculate the checksum of update data and header. The checksum of
-	 * valid update data and header including the extended signature table
-	 * must be 0.
-	 */
-	orig_sum = 0;
-	i = (MC_HEADER_SIZE + data_size) / sizeof(u32);
-	while (i--)
-		orig_sum += ((u32 *)mc)[i];
-
-	if (orig_sum) {
-		if (print_err)
-			pr_err("Bad microcode data checksum, aborting.\n");
-		return -EINVAL;
-	}
-
-	if (!ext_table_size)
-		return 0;
-
-	/*
-	 * Check extended signature checksum: 0 => valid.
-	 */
-	for (i = 0; i < ext_sigcount; i++) {
-		ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
-			  EXT_SIGNATURE_SIZE * i;
-
-		sum = (mc_header->sig + mc_header->pf + mc_header->cksum) -
-		      (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
-		if (sum) {
-			if (print_err)
-				pr_err("Bad extended signature checksum, aborting.\n");
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(intel_microcode_sanity_check);
-
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 3b8476158236..e4c3ba91321c 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -206,7 +206,7 @@ static int intel_epb_offline(unsigned int cpu)
 static const struct x86_cpu_id intel_epb_normal[] = {
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,
 				   ENERGY_PERF_BIAS_NORMAL_POWERSAVE),
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index c4ec4ca47e11..c267f43de39e 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -759,7 +759,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error)
 	inc_irq_stat(irq_deferred_error_count);
 	deferred_error_int_vector();
 	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
-	ack_APIC_irq();
+	apic_eoi();
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 89e2aab5d34d..6f35f724cc14 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -843,6 +843,26 @@ static noinstr bool quirk_skylake_repmov(void)
 }
 
 /*
+ * Some Zen-based Instruction Fetch Units set EIPV=RIPV=0 on poison consumption
+ * errors. This means mce_gather_info() will not save the "ip" and "cs" registers.
+ *
+ * However, the context is still valid, so save the "cs" register for later use.
+ *
+ * The "ip" register is truly unknown, so don't save it or fixup EIPV/RIPV.
+ *
+ * The Instruction Fetch Unit is at MCA bank 1 for all affected systems.
+ */
+static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_regs *regs)
+{
+	if (bank != 1)
+		return;
+	if (!(m->status & MCI_STATUS_POISON))
+		return;
+
+	m->cs = regs->cs;
+}
+
+/*
  * Do a quick check if any of the events requires a panic.
  * This decides if we keep the events around or clear them.
  */
@@ -861,6 +881,9 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo
 		if (mce_flags.snb_ifu_quirk)
 			quirk_sandybridge_ifu(i, m, regs);
 
+		if (mce_flags.zen_ifu_quirk)
+			quirk_zen_ifu(i, m, regs);
+
 		m->bank = i;
 		if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) {
 			mce_read_aux(m, i);
@@ -1608,6 +1631,13 @@ static void __start_timer(struct timer_list *t, unsigned long interval)
 	local_irq_restore(flags);
 }
 
+static void mc_poll_banks_default(void)
+{
+	machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+}
+
+void (*mc_poll_banks)(void) = mc_poll_banks_default;
+
 static void mce_timer_fn(struct timer_list *t)
 {
 	struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1618,7 +1648,7 @@ static void mce_timer_fn(struct timer_list *t)
 	iv = __this_cpu_read(mce_next_interval);
 
 	if (mce_available(this_cpu_ptr(&cpu_info))) {
-		machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+		mc_poll_banks();
 
 		if (mce_intel_cmci_poll()) {
 			iv = mce_adjust_timer(iv);
@@ -1842,6 +1872,9 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
 		if (c->x86 == 0x15 && c->x86_model <= 0xf)
 			mce_flags.overflow_recov = 1;
 
+		if (c->x86 >= 0x17 && c->x86 <= 0x1A)
+			mce_flags.zen_ifu_quirk = 1;
+
 	}
 
 	if (c->x86_vendor == X86_VENDOR_INTEL) {
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 12cf2e7ca33c..4d8d4bcf915d 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -270,8 +270,7 @@ static void __maybe_unused raise_mce(struct mce *m)
 					mce_irq_ipi, NULL, 0);
 				preempt_enable();
 			} else if (m->inject_flags & MCJ_NMI_BROADCAST)
-				apic->send_IPI_mask(mce_inject_cpumask,
-						NMI_VECTOR);
+				__apic_send_IPI_mask(mce_inject_cpumask, NMI_VECTOR);
 		}
 		start = jiffies;
 		while (!cpumask_empty(mce_inject_cpumask)) {
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 95275a5e57e0..f5323551c1a9 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -56,6 +56,13 @@ static DEFINE_PER_CPU(int, cmci_backoff_cnt);
  */
 static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
 
+/*
+ * On systems that do support CMCI but it's disabled, polling for MCEs can
+ * cause the same event to be reported multiple times because IA32_MCi_STATUS
+ * is shared by the same package.
+ */
+static DEFINE_SPINLOCK(cmci_poll_lock);
+
 #define CMCI_THRESHOLD		1
 #define CMCI_POLL_INTERVAL	(30 * HZ)
 #define CMCI_STORM_INTERVAL	(HZ)
@@ -426,12 +433,22 @@ void cmci_disable_bank(int bank)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
+/* Bank polling function when CMCI is disabled. */
+static void cmci_mc_poll_banks(void)
+{
+	spin_lock(&cmci_poll_lock);
+	machine_check_poll(0, this_cpu_ptr(&mce_poll_banks));
+	spin_unlock(&cmci_poll_lock);
+}
+
 void intel_init_cmci(void)
 {
 	int banks;
 
-	if (!cmci_supported(&banks))
+	if (!cmci_supported(&banks)) {
+		mc_poll_banks = cmci_mc_poll_banks;
 		return;
+	}
 
 	mce_threshold_vector = intel_threshold_interrupt;
 	cmci_discover(banks);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index d2412ce2d312..bcf1b3c66c9c 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -157,6 +157,9 @@ struct mce_vendor_flags {
 	 */
 	smca			: 1,
 
+	/* Zen IFU quirk */
+	zen_ifu_quirk		: 1,
+
 	/* AMD-style error thresholding banks present. */
 	amd_threshold		: 1,
 
@@ -172,7 +175,7 @@ struct mce_vendor_flags {
 	/* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */
 	skx_repmov_quirk	: 1,
 
-	__reserved_0		: 56;
+	__reserved_0		: 55;
 };
 
 extern struct mce_vendor_flags mce_flags;
@@ -274,4 +277,5 @@ static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
 	return 0;
 }
 
+extern void (*mc_poll_banks)(void);
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index 6a059a035021..ef4e7bb5fd88 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -27,5 +27,5 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold)
 	inc_irq_stat(irq_threshold_count);
 	mce_threshold_vector();
 	trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR);
-	ack_APIC_irq();
+	apic_eoi();
 }
diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile
index 34098d48c48f..193d98b33a0a 100644
--- a/arch/x86/kernel/cpu/microcode/Makefile
+++ b/arch/x86/kernel/cpu/microcode/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 microcode-y				:= core.o
 obj-$(CONFIG_MICROCODE)			+= microcode.o
-microcode-$(CONFIG_MICROCODE_INTEL)	+= intel.o
-microcode-$(CONFIG_MICROCODE_AMD)	+= amd.o
+microcode-$(CONFIG_CPU_SUP_INTEL)	+= intel.o
+microcode-$(CONFIG_CPU_SUP_AMD)		+= amd.o
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 87208e46f7ed..bbd1dc38ea03 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -29,13 +29,53 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 
-#include <asm/microcode_amd.h>
 #include <asm/microcode.h>
 #include <asm/processor.h>
 #include <asm/setup.h>
 #include <asm/cpu.h>
 #include <asm/msr.h>
 
+#include "internal.h"
+
+#define UCODE_MAGIC			0x00414d44
+#define UCODE_EQUIV_CPU_TABLE_TYPE	0x00000000
+#define UCODE_UCODE_TYPE		0x00000001
+
+#define SECTION_HDR_SIZE		8
+#define CONTAINER_HDR_SZ		12
+
+struct equiv_cpu_entry {
+	u32	installed_cpu;
+	u32	fixed_errata_mask;
+	u32	fixed_errata_compare;
+	u16	equiv_cpu;
+	u16	res;
+} __packed;
+
+struct microcode_header_amd {
+	u32	data_code;
+	u32	patch_id;
+	u16	mc_patch_data_id;
+	u8	mc_patch_data_len;
+	u8	init_flag;
+	u32	mc_patch_data_checksum;
+	u32	nb_dev_id;
+	u32	sb_dev_id;
+	u16	processor_rev_id;
+	u8	nb_rev_id;
+	u8	sb_rev_id;
+	u8	bios_api_rev;
+	u8	reserved1[3];
+	u32	match_reg[8];
+} __packed;
+
+struct microcode_amd {
+	struct microcode_header_amd	hdr;
+	unsigned int			mpb[];
+};
+
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
+
 static struct equiv_cpu_table {
 	unsigned int num_entries;
 	struct equiv_cpu_entry *entry;
@@ -56,9 +96,6 @@ struct cont_desc {
 
 static u32 ucode_new_rev;
 
-/* One blob per node. */
-static u8 amd_ucode_patch[MAX_NUMNODES][PATCH_MAX_SIZE];
-
 /*
  * Microcode patch container file is prepended to the initrd in cpio
  * format. See Documentation/arch/x86/microcode.rst
@@ -415,20 +452,17 @@ static int __apply_microcode_amd(struct microcode_amd *mc)
  *
  * Returns true if container found (sets @desc), false otherwise.
  */
-static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
+static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size)
 {
 	struct cont_desc desc = { 0 };
-	u8 (*patch)[PATCH_MAX_SIZE];
 	struct microcode_amd *mc;
 	u32 rev, dummy, *new_rev;
 	bool ret = false;
 
 #ifdef CONFIG_X86_32
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-	patch	= (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
 #else
 	new_rev = &ucode_new_rev;
-	patch	= &amd_ucode_patch[0];
 #endif
 
 	desc.cpuid_1_eax = cpuid_1_eax;
@@ -452,9 +486,6 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size, boo
 	if (!__apply_microcode_amd(mc)) {
 		*new_rev = mc->hdr.patch_id;
 		ret      = true;
-
-		if (save_patch)
-			memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE));
 	}
 
 	return ret;
@@ -507,7 +538,7 @@ static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data
 	*ret = cp;
 }
 
-void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
+static void apply_ucode_from_containers(unsigned int cpuid_1_eax)
 {
 	struct cpio_data cp = { };
 
@@ -515,42 +546,12 @@ void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
 	if (!(cp.data && cp.size))
 		return;
 
-	early_apply_microcode(cpuid_1_eax, cp.data, cp.size, true);
+	early_apply_microcode(cpuid_1_eax, cp.data, cp.size);
 }
 
-void load_ucode_amd_ap(unsigned int cpuid_1_eax)
+void load_ucode_amd_early(unsigned int cpuid_1_eax)
 {
-	struct microcode_amd *mc;
-	struct cpio_data cp;
-	u32 *new_rev, rev, dummy;
-
-	if (IS_ENABLED(CONFIG_X86_32)) {
-		mc	= (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
-		new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-	} else {
-		mc	= (struct microcode_amd *)amd_ucode_patch;
-		new_rev = &ucode_new_rev;
-	}
-
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	/*
-	 * Check whether a new patch has been saved already. Also, allow application of
-	 * the same revision in order to pick up SMT-thread-specific configuration even
-	 * if the sibling SMT thread already has an up-to-date revision.
-	 */
-	if (*new_rev && rev <= mc->hdr.patch_id) {
-		if (!__apply_microcode_amd(mc)) {
-			*new_rev = mc->hdr.patch_id;
-			return;
-		}
-	}
-
-	find_blobs_in_containers(cpuid_1_eax, &cp);
-	if (!(cp.data && cp.size))
-		return;
-
-	early_apply_microcode(cpuid_1_eax, cp.data, cp.size, false);
+	return apply_ucode_from_containers(cpuid_1_eax);
 }
 
 static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
@@ -578,23 +579,6 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 	return 0;
 }
 
-void reload_ucode_amd(unsigned int cpu)
-{
-	u32 rev, dummy __always_unused;
-	struct microcode_amd *mc;
-
-	mc = (struct microcode_amd *)amd_ucode_patch[cpu_to_node(cpu)];
-
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	if (rev < mc->hdr.patch_id) {
-		if (!__apply_microcode_amd(mc)) {
-			ucode_new_rev = mc->hdr.patch_id;
-			pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
-		}
-	}
-}
-
 /*
  * a small, trivial cache of per-family ucode patches
  */
@@ -655,6 +639,28 @@ static struct ucode_patch *find_patch(unsigned int cpu)
 	return cache_find_patch(equiv_id);
 }
 
+void reload_ucode_amd(unsigned int cpu)
+{
+	u32 rev, dummy __always_unused;
+	struct microcode_amd *mc;
+	struct ucode_patch *p;
+
+	p = find_patch(cpu);
+	if (!p)
+		return;
+
+	mc = p->data;
+
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	if (rev < mc->hdr.patch_id) {
+		if (!__apply_microcode_amd(mc)) {
+			ucode_new_rev = mc->hdr.patch_id;
+			pr_info("reload patch_level=0x%08x\n", ucode_new_rev);
+		}
+	}
+}
+
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -875,9 +881,6 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 			continue;
 
 		ret = UCODE_NEW;
-
-		memset(&amd_ucode_patch[nid], 0, PATCH_MAX_SIZE);
-		memcpy(&amd_ucode_patch[nid], p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
 	}
 
 	return ret;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 3afcf3de0dd4..6cc7a2c181da 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -31,15 +31,14 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 
-#include <asm/microcode_intel.h>
 #include <asm/cpu_device_id.h>
-#include <asm/microcode_amd.h>
 #include <asm/perf_event.h>
-#include <asm/microcode.h>
 #include <asm/processor.h>
 #include <asm/cmdline.h>
 #include <asm/setup.h>
 
+#include "internal.h"
+
 #define DRIVER_VERSION	"2.2"
 
 static struct microcode_ops	*microcode_ops;
@@ -54,15 +53,12 @@ LIST_HEAD(microcode_cache);
  *
  * All non cpu-hotplug-callback call sites use:
  *
- * - microcode_mutex to synchronize with each other;
  * - cpus_read_lock/unlock() to synchronize with
  *   the cpu-hotplug-callback call sites.
  *
  * We guarantee that only a single cpu is being
  * updated at any particular moment of time.
  */
-static DEFINE_MUTEX(microcode_mutex);
-
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -172,7 +168,7 @@ void __init load_ucode_bsp(void)
 	if (intel)
 		load_ucode_intel_bsp();
 	else
-		load_ucode_amd_bsp(cpuid_1_eax);
+		load_ucode_amd_early(cpuid_1_eax);
 }
 
 static bool check_loader_disabled_ap(void)
@@ -200,7 +196,7 @@ void load_ucode_ap(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (x86_family(cpuid_1_eax) >= 0x10)
-			load_ucode_amd_ap(cpuid_1_eax);
+			load_ucode_amd_early(cpuid_1_eax);
 		break;
 	default:
 		break;
@@ -298,7 +294,7 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 #endif
 }
 
-void reload_early_microcode(unsigned int cpu)
+static void reload_early_microcode(unsigned int cpu)
 {
 	int vendor, family;
 
@@ -488,10 +484,7 @@ static ssize_t reload_store(struct device *dev,
 	if (tmp_ret != UCODE_NEW)
 		goto put;
 
-	mutex_lock(&microcode_mutex);
 	ret = microcode_reload_late();
-	mutex_unlock(&microcode_mutex);
-
 put:
 	cpus_read_unlock();
 
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 467cf37ea90a..94dd6af9c963 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -10,15 +10,7 @@
  * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
  *		      H Peter Anvin" <hpa@zytor.com>
  */
-
-/*
- * This needs to be before all headers so that pr_debug in printk.h doesn't turn
- * printk calls into no_printk().
- *
- *#define DEBUG
- */
 #define pr_fmt(fmt) "microcode: " fmt
-
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
 #include <linux/uaccess.h>
@@ -30,13 +22,14 @@
 #include <linux/uio.h>
 #include <linux/mm.h>
 
-#include <asm/microcode_intel.h>
 #include <asm/intel-family.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>