Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f02ecaf..69881b2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
  /*
  *	x86 SMP booting functions
  *
@@ -12,9 +13,6 @@
  *	Pentium Pro and Pentium-II/Xeon MP machines.
  *	Original development of Linux SMP code supported by Caldera.
  *
- *	This code is released under the GNU General Public License version 2 or
- *	later.
- *
  *	Fixes
  *		Felix Koop	:	NR_CPUS used properly
  *		Jose Renau	:	Handle single CPU case.
@@ -49,13 +47,14 @@
 #include <linux/sched/hotplug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/percpu.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/err.h>
 #include <linux/nmi.h>
 #include <linux/tboot.h>
 #include <linux/stackprotector.h>
 #include <linux/gfp.h>
 #include <linux/cpuidle.h>
+#include <linux/numa.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -90,6 +89,10 @@
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
+/* representing HT, core, and die siblings of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
+EXPORT_PER_CPU_SYMBOL(cpu_die_map);
+
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
 /* Per CPU bogomips and other parameters */
@@ -100,6 +103,7 @@
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
+static unsigned int logical_die __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
 int __read_mostly __max_smt_threads = 1;
@@ -149,7 +153,7 @@
  */
 static void smp_callin(void)
 {
-	int cpuid, phys_id;
+	int cpuid;
 
 	/*
 	 * If waken up by an INIT in an 82489DX configuration
@@ -160,11 +164,6 @@
 	cpuid = smp_processor_id();
 
 	/*
-	 * (This works even if the APIC is not enabled.)
-	 */
-	phys_id = read_apic_id();
-
-	/*
 	 * the boot CPU has finished the init stage and is spinning
 	 * on callin_map until we finish. We are free to set up this
 	 * CPU, first the APIC. (this is probably redundant on most
@@ -216,17 +215,11 @@
 	 * before cpu_init(), SMP booting is too fragile that we want to
 	 * limit the things done here to the most necessary things.
 	 */
-	if (boot_cpu_has(X86_FEATURE_PCID))
-		__write_cr4(__read_cr4() | X86_CR4_PCIDE);
+	cr4_init();
 
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
 	__flush_tlb_all();
 #endif
 	load_current_idt();
@@ -306,6 +299,26 @@
 	return -1;
 }
 EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+/**
+ * topology_phys_to_logical_die - Map a physical die id to logical
+ *
+ * Returns logical die id or -1 if not found
+ */
+int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
+{
+	int cpu;
+	int proc_id = cpu_data(cur_cpu).phys_proc_id;
+
+	for_each_possible_cpu(cpu) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && c->cpu_die_id == die_id &&
+		    c->phys_proc_id == proc_id)
+			return c->logical_die_id;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_die);
 
 /**
  * topology_update_package_map - Update the physical to logical package map
@@ -330,6 +343,29 @@
 	cpu_data(cpu).logical_proc_id = new;
 	return 0;
 }
+/**
+ * topology_update_die_map - Update the physical to logical die map
+ * @die:	The die id as retrieved via CPUID
+ * @cpu:	The cpu for which this is updated
+ */
+int topology_update_die_map(unsigned int die, unsigned int cpu)
+{
+	int new;
+
+	/* Already available somewhere? */
+	new = topology_phys_to_logical_die(die, cpu);
+	if (new >= 0)
+		goto found;
+
+	new = logical_die++;
+	if (new != die) {
+		pr_info("CPU %u Converting physical %u to logical die %u\n",
+			cpu, die, new);
+	}
+found:
+	cpu_data(cpu).logical_die_id = new;
+	return 0;
+}
 
 void __init smp_store_boot_cpu_info(void)
 {
@@ -339,6 +375,7 @@
 	*c = boot_cpu_data;
 	c->cpu_index = id;
 	topology_update_package_map(c->phys_proc_id, id);
+	topology_update_die_map(c->cpu_die_id, id);
 	c->initialized = true;
 }
 
@@ -393,6 +430,7 @@
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
+		    c->cpu_die_id == o->cpu_die_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
 			if (c->cpu_core_id == o->cpu_core_id)
 				return topology_sane(c, o, "smt");
@@ -404,6 +442,7 @@
 		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
+		   c->cpu_die_id == o->cpu_die_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
 		return topology_sane(c, o, "smt");
 	}
@@ -459,13 +498,22 @@
  * multicore group inside a NUMA node.  If this happens, we will
  * discard the MC level of the topology later.
  */
-static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
 	if (c->phys_proc_id == o->phys_proc_id)
 		return true;
 	return false;
 }
 
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if ((c->phys_proc_id == o->phys_proc_id) &&
+		(c->cpu_die_id == o->cpu_die_id))
+		return true;
+	return false;
+}
+
+
 #if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
@@ -528,6 +576,7 @@
 		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
+		cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
@@ -550,7 +599,7 @@
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mp && match_die(c, o))) {
+		if ((i == cpu) || (has_mp && match_pkg(c, o))) {
 			link_mask(topology_core_cpumask, cpu, i);
 
 			/*
@@ -574,8 +623,11 @@
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
-		if (match_die(c, o) && !topology_same_node(c, o))
+		if (match_pkg(c, o) && !topology_same_node(c, o))
 			x86_has_numa_in_package = true;
+
+		if ((i == cpu) || (has_mp && match_die(c, o)))
+			link_mask(topology_die_cpumask, cpu, i);
 	}
 
 	threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -676,6 +728,7 @@
 
 	/* if modern processor, use no delay */
 	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
 	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
 		init_udelay = 0;
 		return;
@@ -840,7 +893,7 @@
 /* reduce the number of lines printed when booting a large cpu count system */
 static void announce_cpu(int cpu, int apicid)
 {
-	static int current_node = -1;
+	static int current_node = NUMA_NO_NODE;
 	int node = early_cpu_to_node(cpu);
 	static int width, node_width;
 
@@ -938,20 +991,27 @@
 	return boot_error;
 }
 
-void common_cpu_up(unsigned int cpu, struct task_struct *idle)
+int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
+	int ret;
+
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
 	per_cpu(current_task, cpu) = idle;
 
+	/* Initialize the interrupt stack(s) */
+	ret = irq_init_percpu_irqstack(cpu);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	irq_ctx_init(cpu);
 	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif
+	return 0;
 }
 
 /*
@@ -963,8 +1023,6 @@
 static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 		       int *cpu0_nmi_registered)
 {
-	volatile u32 *trampoline_status =
-		(volatile u32 *) __va(real_mode_header->trampoline_status);
 	/* start_ip had better be page-aligned! */
 	unsigned long start_ip = real_mode_header->trampoline_start;
 
@@ -1056,9 +1114,6 @@
 		}
 	}
 
-	/* mark "stuck" area as not stuck */
-	*trampoline_status = 0;
-
 	if (x86_platform.legacy.warm_reset) {
 		/*
 		 * Cleanup possible dangling ends...
@@ -1109,7 +1164,9 @@
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
-	common_cpu_up(cpu, tidle);
+	err = common_cpu_up(cpu, tidle);
+	if (err)
+		return err;
 
 	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
@@ -1170,6 +1227,7 @@
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
 	cpumask_set_cpu(0, topology_sibling_cpumask(0));
 	cpumask_set_cpu(0, topology_core_cpumask(0));
+	cpumask_set_cpu(0, topology_die_cpumask(0));
 }
 
 /*
@@ -1265,6 +1323,7 @@
 	for_each_possible_cpu(i) {
 		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
 
@@ -1304,8 +1363,6 @@
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
-	native_pv_lock_init();
-
 	uv_system_init();
 
 	set_mtrr_aps_delayed_init();
@@ -1335,6 +1392,7 @@
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	cpu_set_state_online(me);
+	native_pv_lock_init();
 }
 
 void __init calculate_max_logical_packages(void)
@@ -1346,7 +1404,7 @@
 	 * extrapolate the boot cpu's data to all packages.
 	 */
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
-	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 }
 
@@ -1485,6 +1543,8 @@
 			cpu_data(sibling).booted_cores--;
 	}
 
+	for_each_cpu(sibling, topology_die_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
 	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
 		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
 	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
@@ -1492,6 +1552,7 @@
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
 	cpumask_clear(topology_core_cpumask(cpu));
+	cpumask_clear(topology_die_cpumask(cpu));
 	c->cpu_core_id = 0;
 	c->booted_cores = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
@@ -1530,7 +1591,12 @@
 	if (ret)
 		return ret;
 
-	clear_local_APIC();
+	/*
+	 * Disable the local APIC. Otherwise IPI broadcasts will reach
+	 * it. It still responds normally to INIT, NMI, SMI, and SIPI
+	 * messages.
+	 */
+	apic_soft_disable();
 	cpu_disable_common();
 
 	return 0;
@@ -1592,7 +1658,8 @@
 	void *mwait_ptr;
 	int i;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 		return;
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;