Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 366875a..065152d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -2,130 +2,59 @@
 /*
  *  Copyright (C) 1995  Linus Torvalds
  *
- *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- *
- *  Memory region support
- *	David Parsons <orc@pell.chi.il.us>, July-August 1999
- *
- *  Added E820 sanitization routine (removes overlapping memory regions);
- *  Brian Moyle <bmoyle@mvista.com>, February 2001
- *
- * Moved CPU detection code to cpu/${cpu}.c
- *    Patrick Mochel <mochel@osdl.org>, March 2002
- *
- *  Provisions for empty E820 memory regions (reported by certain BIOSes).
- *  Alex Achenbach <xela@slit.de>, December 2002.
- *
+ * This file contains the setup_arch() code, which handles the architecture-dependent
+ * parts of early kernel initialization.
  */
-
-/*
- * This file handles the architecture-dependent parts of initialization
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/screen_info.h>
-#include <linux/ioport.h>
-#include <linux/acpi.h>
-#include <linux/sfi.h>
-#include <linux/apm_bios.h>
-#include <linux/initrd.h>
-#include <linux/memblock.h>
-#include <linux/seq_file.h>
 #include <linux/console.h>
-#include <linux/root_dev.h>
-#include <linux/highmem.h>
-#include <linux/export.h>
-#include <linux/efi.h>
-#include <linux/init.h>
-#include <linux/edd.h>
-#include <linux/iscsi_ibft.h>
-#include <linux/nodemask.h>
-#include <linux/kexec.h>
+#include <linux/crash_dump.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmi.h>
-#include <linux/pfn.h>
-#include <linux/pci.h>
-#include <asm/pci-direct.h>
+#include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
-#include <linux/kvm_para.h>
-#include <linux/dma-contiguous.h>
-#include <xen/xen.h>
+#include <linux/initrd.h>
+#include <linux/iscsi_ibft.h>
+#include <linux/memblock.h>
+#include <linux/pci.h>
+#include <linux/root_dev.h>
+#include <linux/sfi.h>
+#include <linux/hugetlb.h>
+#include <linux/tboot.h>
+#include <linux/usb/xhci-dbgp.h>
+#include <linux/static_call.h>
+#include <linux/swiotlb.h>
+
 #include <uapi/linux/mount.h>
 
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/delay.h>
+#include <xen/xen.h>
 
-#include <linux/kallsyms.h>
-#include <linux/cpufreq.h>
-#include <linux/dma-mapping.h>
-#include <linux/ctype.h>
-#include <linux/uaccess.h>
-
-#include <linux/percpu.h>
-#include <linux/crash_dump.h>
-#include <linux/tboot.h>
-#include <linux/jiffies.h>
-#include <linux/mem_encrypt.h>
-#include <linux/sizes.h>
-
-#include <linux/usb/xhci-dbgp.h>
-#include <video/edid.h>
-
-#include <asm/mtrr.h>
 #include <asm/apic.h>
-#include <asm/realmode.h>
-#include <asm/e820/api.h>
-#include <asm/mpspec.h>
-#include <asm/setup.h>
-#include <asm/efi.h>
-#include <asm/timer.h>
-#include <asm/i8259.h>
-#include <asm/sections.h>
-#include <asm/io_apic.h>
-#include <asm/ist.h>
-#include <asm/setup_arch.h>
+#include <asm/numa.h>
 #include <asm/bios_ebda.h>
-#include <asm/cacheflush.h>
-#include <asm/processor.h>
 #include <asm/bugs.h>
-#include <asm/kasan.h>
-
-#include <asm/vsyscall.h>
 #include <asm/cpu.h>
-#include <asm/desc.h>
-#include <asm/dma.h>
-#include <asm/iommu.h>
+#include <asm/efi.h>
 #include <asm/gart.h>
-#include <asm/mmu_context.h>
-#include <asm/proto.h>
-
-#include <asm/paravirt.h>
 #include <asm/hypervisor.h>
-#include <asm/olpc_ofw.h>
-
-#include <asm/percpu.h>
-#include <asm/topology.h>
-#include <asm/apicdef.h>
-#include <asm/amd_nb.h>
-#include <asm/mce.h>
-#include <asm/alternative.h>
-#include <asm/prom.h>
-#include <asm/microcode.h>
+#include <asm/io_apic.h>
+#include <asm/kasan.h>
 #include <asm/kaslr.h>
+#include <asm/mce.h>
+#include <asm/mtrr.h>
+#include <asm/realmode.h>
+#include <asm/olpc_ofw.h>
+#include <asm/pci-direct.h>
+#include <asm/prom.h>
+#include <asm/proto.h>
 #include <asm/unwind.h>
+#include <asm/vsyscall.h>
+#include <linux/vmalloc.h>
 
 /*
- * max_low_pfn_mapped: highest direct mapped pfn under 4GB
- * max_pfn_mapped:     highest direct mapped pfn over 4GB
+ * max_low_pfn_mapped: highest directly mapped pfn < 4 GB
+ * max_pfn_mapped:     highest directly mapped pfn > 4 GB
  *
  * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are
- * represented by pfn_mapped
+ * represented by pfn_mapped[].
  */
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
@@ -135,14 +64,29 @@
 #endif
 
 
-static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
-unsigned long _brk_end = (unsigned long)__brk_base;
+/*
+ * Range of the BSS area. The size of the BSS area is determined
+ * at link time, with RESERVE_BRK*() facility reserving additional
+ * chunks.
+ */
+unsigned long _brk_start = (unsigned long)__brk_base;
+unsigned long _brk_end   = (unsigned long)__brk_base;
 
 struct boot_params boot_params;
 
 /*
- * Machine setup..
+ * These are the four main kernel memory regions, we put them into
+ * the resource tree so that kdump tools and other debugging tools
+ * recover it:
  */
+
+static struct resource rodata_resource = {
+	.name	= "Kernel rodata",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM
+};
+
 static struct resource data_resource = {
 	.name	= "Kernel data",
 	.start	= 0,
@@ -166,16 +110,16 @@
 
 
 #ifdef CONFIG_X86_32
-/* cpu data as detected by the assembly code in head_32.S */
+/* CPU data as detected by the assembly code in head_32.S */
 struct cpuinfo_x86 new_cpu_data;
 
-/* common cpu data for all cpus */
+/* Common CPU data for all CPUs */
 struct cpuinfo_x86 boot_cpu_data __read_mostly;
 EXPORT_SYMBOL(boot_cpu_data);
 
 unsigned int def_to_bigsmp;
 
-/* for MCA, but anyone else can use it if they want */
+/* For MCA, but anyone else can use it if they want */
 unsigned int machine_id;
 unsigned int machine_submodel_id;
 unsigned int BIOS_revision;
@@ -297,6 +241,9 @@
 
 	ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
 
+	if (ramdisk_image == 0)
+		ramdisk_image = phys_initrd_start;
+
 	return ramdisk_image;
 }
 static u64 __init get_ramdisk_size(void)
@@ -305,6 +252,9 @@
 
 	ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
 
+	if (ramdisk_size == 0)
+		ramdisk_size = phys_initrd_size;
+
 	return ramdisk_size;
 }
 
@@ -316,16 +266,12 @@
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 
 	/* We need to move the initrd down into directly mapped mem */
-	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
-						   area_size, PAGE_SIZE);
-
+	relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
+						      PFN_PHYS(max_pfn_mapped));
 	if (!relocated_ramdisk)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 		      ramdisk_size);
 
-	/* Note: this includes all the mem currently occupied by
-	   the initrd, we rely on that fact to keep the data intact. */
-	memblock_reserve(relocated_ramdisk, area_size);
 	initrd_start = relocated_ramdisk + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
@@ -352,13 +298,13 @@
 
 	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
 }
+
 static void __init reserve_initrd(void)
 {
 	/* Assume only end is not page aligned */
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-	u64 mapped_size;
 
 	if (!boot_params.hdr.type_of_loader ||
 	    !ramdisk_image || !ramdisk_size)
@@ -366,12 +312,6 @@
 
 	initrd_start = 0;
 
-	mapped_size = memblock_mem_size(max_pfn_mapped);
-	if (ramdisk_size >= (mapped_size>>1))
-		panic("initrd too large to handle, "
-		       "disabling initrd (%lld needed, %lld available)\n",
-		       ramdisk_size, mapped_size>>1);
-
 	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
 			ramdisk_end - 1);
 
@@ -431,15 +371,41 @@
 
 static void __init memblock_x86_reserve_range_setup_data(void)
 {
+	struct setup_indirect *indirect;
 	struct setup_data *data;
-	u64 pa_data;
+	u64 pa_data, pa_next;
+	u32 len;
 
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
+		if (!data) {
+			pr_warn("setup: failed to memremap setup_data entry\n");
+			return;
+		}
+
+		len = sizeof(*data);
+		pa_next = data->next;
+
 		memblock_reserve(pa_data, sizeof(*data) + data->len);
-		pa_data = data->next;
-		early_memunmap(data, sizeof(*data));
+
+		if (data->type == SETUP_INDIRECT) {
+			len += data->len;
+			early_memunmap(data, sizeof(*data));
+			data = early_memremap(pa_data, len);
+			if (!data) {
+				pr_warn("setup: failed to memremap indirect setup_data\n");
+				return;
+			}
+
+			indirect = (struct setup_indirect *)data->data;
+
+			if (indirect->type != SETUP_INDIRECT)
+				memblock_reserve(indirect->addr, indirect->len);
+		}
+
+		pa_data = pa_next;
+		early_memunmap(data, len);
 	}
 }
 
@@ -455,15 +421,15 @@
 /*
  * Keep the crash kernel below this limit.
  *
- * On 32 bits earlier kernels would limit the kernel to the low 512 MiB
+ * Earlier 32-bits kernels would limit the kernel to the low 512 MB range
  * due to mapping restrictions.
  *
- * On 64bit, kdump kernel need be restricted to be under 64TB, which is
- * the upper limit of system RAM in 4-level paing mode. Since the kdump
- * jumping could be from 5-level to 4-level, the jumping will fail if
- * kernel is put above 64TB, and there's no way to detect the paging mode
- * of the kernel which will be loaded for dumping during the 1st kernel
- * bootup.
+ * 64-bit kdump kernels need to be restricted to be under 64 TB, which is
+ * the upper limit of system RAM in 4-level paging mode. Since the kdump
+ * jump could be from 5-level paging to 4-level paging, the jump will fail if
+ * the kernel is put above 64 TB, and during the 1st kernel bootup there's
+ * no good way to detect the paging mode of the target kernel which will be
+ * loaded for dumping.
  */
 #ifdef CONFIG_X86_32
 # define CRASH_ADDR_LOW_MAX	SZ_512M
@@ -477,13 +443,13 @@
 {
 #ifdef CONFIG_X86_64
 	unsigned long long base, low_base = 0, low_size = 0;
-	unsigned long total_low_mem;
+	unsigned long low_mem_limit;
 	int ret;
 
-	total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT));
+	low_mem_limit = min(memblock_phys_mem_size(), CRASH_ADDR_LOW_MAX);
 
 	/* crashkernel=Y,low */
-	ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base);
+	ret = parse_crashkernel_low(boot_command_line, low_mem_limit, &low_size, &base);
 	if (ret) {
 		/*
 		 * two parts from kernel/dma/swiotlb.c:
@@ -501,23 +467,17 @@
 			return 0;
 	}
 
-	low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN);
+	low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX);
 	if (!low_base) {
 		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
 		       (unsigned long)(low_size >> 20));
 		return -ENOMEM;
 	}
 
-	ret = memblock_reserve(low_base, low_size);
-	if (ret) {
-		pr_err("%s: Error reserving crashkernel low memblock.\n", __func__);
-		return ret;
-	}
-
-	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (low RAM limit: %ldMB)\n",
 		(unsigned long)(low_size >> 20),
 		(unsigned long)(low_base >> 20),
-		(unsigned long)(total_low_mem >> 20));
+		(unsigned long)(low_mem_limit >> 20));
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
@@ -561,13 +521,13 @@
 		 * unless "crashkernel=size[KMG],high" is specified.
 		 */
 		if (!high)
-			crash_base = memblock_find_in_range(CRASH_ALIGN,
-						CRASH_ADDR_LOW_MAX,
-						crash_size, CRASH_ALIGN);
+			crash_base = memblock_phys_alloc_range(crash_size,
+						CRASH_ALIGN, CRASH_ALIGN,
+						CRASH_ADDR_LOW_MAX);
 		if (!crash_base)
-			crash_base = memblock_find_in_range(CRASH_ALIGN,
-						CRASH_ADDR_HIGH_MAX,
-						crash_size, CRASH_ALIGN);
+			crash_base = memblock_phys_alloc_range(crash_size,
+						CRASH_ALIGN, CRASH_ALIGN,
+						CRASH_ADDR_HIGH_MAX);
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
@@ -575,19 +535,13 @@
 	} else {
 		unsigned long long start;
 
-		start = memblock_find_in_range(crash_base,
-					       crash_base + crash_size,
-					       crash_size, 1 << 20);
+		start = memblock_phys_alloc_range(crash_size, SZ_1M, crash_base,
+						  crash_base + crash_size);
 		if (start != crash_base) {
 			pr_info("crashkernel reservation failed - memory is in use.\n");
 			return;
 		}
 	}
-	ret = memblock_reserve(crash_base, crash_size);
-	if (ret) {
-		pr_err("%s: Error reserving crashkernel memblock.\n", __func__);
-		return;
-	}
 
 	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
 		memblock_free(crash_base, crash_size);
@@ -743,8 +697,8 @@
 	e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
 
 	/*
-	 * special case: Some BIOSen report the PC BIOS
-	 * area (640->1Mb) as ram even though it is not.
+	 * special case: Some BIOSes report the PC BIOS
+	 * area (640Kb -> 1Mb) as RAM even though it is not.
 	 * take them out.
 	 */
 	e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1);
@@ -874,7 +828,7 @@
 	/*
 	 * Note: Quark X1000 CPUs advertise PGE incorrectly and require
 	 * a cr3 based tlb flush, so the following __flush_tlb_all()
-	 * will not flush anything because the cpu quirk which clears
+	 * will not flush anything because the CPU quirk which clears
 	 * X86_FEATURE_PGE has not been invoked yet. Though due to the
 	 * load_cr3() above the TLB has been flushed already. The
 	 * quirk is invoked before subsequent calls to __flush_tlb_all()
@@ -896,6 +850,7 @@
 	early_cpu_init();
 	arch_init_ideal_nops();
 	jump_label_init();
+	static_call_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
@@ -918,8 +873,6 @@
 
 #ifdef CONFIG_BLK_DEV_RAM
 	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
-	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
-	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
 #endif
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
@@ -947,11 +900,11 @@
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
-	mpx_mm_init(&init_mm);
-
 	code_resource.start = __pa_symbol(_text);
 	code_resource.end = __pa_symbol(_etext)-1;
-	data_resource.start = __pa_symbol(_etext);
+	rodata_resource.start = __pa_symbol(__start_rodata);
+	rodata_resource.end = __pa_symbol(__end_rodata)-1;
+	data_resource.start = __pa_symbol(_sdata);
 	data_resource.end = __pa_symbol(_edata)-1;
 	bss_resource.start = __pa_symbol(__bss_start);
 	bss_resource.end = __pa_symbol(__bss_stop)-1;
@@ -1040,6 +993,7 @@
 
 	/* after parse_early_param, so could debug it */
 	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &rodata_resource);
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
@@ -1122,17 +1076,16 @@
 
 	reserve_bios_regions();
 
-	if (efi_enabled(EFI_MEMMAP)) {
-		efi_fake_memmap();
-		efi_find_mirror();
-		efi_esrt_init();
+	efi_fake_memmap();
+	efi_find_mirror();
+	efi_esrt_init();
+	efi_mokvar_table_init();
 
-		/*
-		 * The EFI specification says that boot service code won't be
-		 * called after ExitBootServices(). This is, in fact, a lie.
-		 */
-		efi_reserve_boot_services();
-	}
+	/*
+	 * The EFI specification says that boot service code won't be
+	 * called after ExitBootServices(). This is, in fact, a lie.
+	 */
+	efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
 	e820__memblock_alloc_reserved_mpc_new();
@@ -1210,6 +1163,9 @@
 	initmem_init();
 	dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
 
+	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
+
 	/*
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
 	 * won't consume hotpluggable memory.
@@ -1262,6 +1218,7 @@
 	prefill_possible_map();
 
 	init_cpu_to_node();
+	init_gi_nodes();
 
 	io_apic_init_mappings();
 
@@ -1278,8 +1235,6 @@
 #if defined(CONFIG_VGA_CONSOLE)
 	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
-#elif defined(CONFIG_DUMMY_CONSOLE)
-	conswitchp = &dummy_con;
 #endif
 #endif
 	x86_init.oem.banner();