1 files changed, 413 insertions, 179 deletions

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 91f27ab970ef..3b0948ad449f 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kaslr.c
  *
@@ -18,30 +19,18 @@
  */
 #define BOOT_CTYPE_H
 
-/*
- * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h.
- * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL
- * which is meaningless and will cause compiling error in some cases.
- * So do not include linux/export.h and define EXPORT_SYMBOL(sym)
- * as empty.
- */
-#define _LINUX_EXPORT_H
-#define EXPORT_SYMBOL(sym)
-
 #include "misc.h"
 #include "error.h"
 #include "../string.h"
+#include "efi.h"
 
 #include <generated/compile.h>
-#include <linux/module.h>
-#include <linux/uts.h>
-#include <linux/utsname.h>
-#include <linux/ctype.h>
+#include <generated/utsversion.h>
 #include <generated/utsrelease.h>
 
-/* Macros used by the included decompressor code below. */
-#define STATIC
-#include <linux/decompress/mm.h>
+#define _SETUP
+#include <asm/setup.h>	/* For COMMAND_LINE_SIZE */
+#undef _SETUP
 
 extern unsigned long get_cmd_line_ptr(void);
 
@@ -70,7 +59,7 @@ static unsigned long get_boot_seed(void)
 	unsigned long hash = 0;
 
 	hash = rotate_xor(hash, build_str, sizeof(build_str));
-	hash = rotate_xor(hash, boot_params, sizeof(*boot_params));
+	hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr));
 
 	return hash;
 }
@@ -78,10 +67,6 @@ static unsigned long get_boot_seed(void)
 #define KASLR_COMPRESSED_BOOT
 #include "../../lib/kaslr.c"
 
-struct mem_vector {
-	unsigned long long start;
-	unsigned long long size;
-};
 
 /* Only supporting at most 4 unusable memmap regions with kaslr */
 #define MAX_MEMMAP_REGIONS	4
@@ -89,9 +74,14 @@ struct mem_vector {
 static bool memmap_too_large;
 
 
-/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+/*
+ * Store memory limit: MAXMEM on 64-bit and KERNEL_IMAGE_SIZE on 32-bit.
+ * It may be reduced by "mem=nn[KMG]" or "memmap=nn[KMG]" command line options.
+ */
+static u64 mem_limit;
 
+/* Number of immovable memory regions */
+static int num_immovable_mem;
 
 enum mem_avoid_index {
 	MEM_AVOID_ZO_RANGE = 0,
@@ -126,7 +116,7 @@ char *skip_spaces(const char *str)
 #include "../../../../lib/cmdline.c"
 
 static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+parse_memmap(char *p, u64 *start, u64 *size)
 {
 	char *oldp;
 
@@ -149,9 +139,12 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 		*start = memparse(p + 1, &p);
 		return 0;
 	case '@':
-		/* memmap=nn@ss specifies usable region, should be skipped */
+		/*
+		 * memmap=nn@ss specifies usable region, should
+		 * be skipped
+		 */
 		*size = 0;
-		/* Fall through */
+		fallthrough;
 	default:
 		/*
 		 * If w/o offset, only size specified, memmap=nn[KMG] has the
@@ -168,14 +161,13 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 static void mem_avoid_memmap(char *str)
 {
 	static int i;
-	int rc;
 
 	if (i >= MAX_MEMMAP_REGIONS)
 		return;
 
 	while (str && (i < MAX_MEMMAP_REGIONS)) {
 		int rc;
-		unsigned long long start, size;
+		u64 start, size;
 		char *k = strchr(str, ',');
 
 		if (k)
@@ -188,7 +180,7 @@ static void mem_avoid_memmap(char *str)
 
 		if (start == 0) {
 			/* Store the specified memory limit if size > 0 */
-			if (size > 0)
+			if (size > 0 && size < mem_limit)
 				mem_limit = size;
 
 			continue;
@@ -204,19 +196,48 @@ static void mem_avoid_memmap(char *str)
 		memmap_too_large = true;
 }
 
-static int handle_mem_memmap(void)
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+	static bool gbpage_sz;
+	char *p;
+
+	if (!strcmp(param, "hugepagesz")) {
+		p = val;
+		if (memparse(p, &p) != PUD_SIZE) {
+			gbpage_sz = false;
+			return;
+		}
+
+		if (gbpage_sz)
+			warn("Repeatedly set hugeTLB page size of 1G!\n");
+		gbpage_sz = true;
+		return;
+	}
+
+	if (!strcmp(param, "hugepages") && gbpage_sz) {
+		p = val;
+		max_gb_huge_pages = simple_strtoull(p, &p, 0);
+		return;
+	}
+}
+
+static void handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
-	size_t len = strlen((char *)args);
+	size_t len;
 	char *tmp_cmdline;
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
-		return 0;
+	if (!args)
+		return;
 
+	len = strnlen(args, COMMAND_LINE_SIZE-1);
 	tmp_cmdline = malloc(len + 1);
-	if (!tmp_cmdline )
+	if (!tmp_cmdline)
 		error("Failed to allocate space for tmp_cmdline");
 
 	memcpy(tmp_cmdline, args, len);
@@ -229,34 +250,35 @@ static int handle_mem_memmap(void)
 	while (*args) {
 		args = next_arg(args, &param, &val);
 		/* Stop at -- */
-		if (!val && strcmp(param, "--") == 0) {
-			warn("Only '--' specified in cmdline");
-			free(tmp_cmdline);
-			return -1;
-		}
+		if (!val && strcmp(param, "--") == 0)
+			break;
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(val);
+		} else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) {
+			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
 
 			if (!strcmp(p, "nopentium"))
 				continue;
 			mem_size = memparse(p, &p);
-			if (mem_size == 0) {
-				free(tmp_cmdline);
-				return -EINVAL;
-			}
-			mem_limit = mem_size;
+			if (mem_size == 0)
+				break;
+
+			if (mem_size < mem_limit)
+				mem_limit = mem_size;
 		}
 	}
 
 	free(tmp_cmdline);
-	return 0;
+	return;
 }
 
 /*
- * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
+ * In theory, KASLR can put the kernel anywhere in the range of [16M, MAXMEM)
+ * on 64-bit, and [16M, KERNEL_IMAGE_SIZE) on 32-bit.
+ *
  * The mem_avoid array is used to store the ranges that need to be avoided
  * when KASLR searches for an appropriate random address. We must avoid any
  * regions that are unsafe to overlap with during decompression, and other
@@ -332,10 +354,9 @@ static int handle_mem_memmap(void)
 static void mem_avoid_init(unsigned long input, unsigned long input_size,
 			   unsigned long output)
 {
-	unsigned long init_size = boot_params->hdr.init_size;
+	unsigned long init_size = boot_params_ptr->hdr.init_size;
 	u64 initrd_start, initrd_size;
-	u64 cmd_line, cmd_line_size;
-	char *ptr;
+	unsigned long cmd_line, cmd_line_size;
 
 	/*
 	 * Avoid the region that is unsafe to overlap during
@@ -343,45 +364,36 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	 */
 	mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
 	mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
-	add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
-			 mem_avoid[MEM_AVOID_ZO_RANGE].size);
 
 	/* Avoid initrd. */
-	initrd_start  = (u64)boot_params->ext_ramdisk_image << 32;
-	initrd_start |= boot_params->hdr.ramdisk_image;
-	initrd_size  = (u64)boot_params->ext_ramdisk_size << 32;
-	initrd_size |= boot_params->hdr.ramdisk_size;
+	initrd_start  = (u64)boot_params_ptr->ext_ramdisk_image << 32;
+	initrd_start |= boot_params_ptr->hdr.ramdisk_image;
+	initrd_size  = (u64)boot_params_ptr->ext_ramdisk_size << 32;
+	initrd_size |= boot_params_ptr->hdr.ramdisk_size;
 	mem_avoid[MEM_AVOID_INITRD].start = initrd_start;
 	mem_avoid[MEM_AVOID_INITRD].size = initrd_size;
 	/* No need to set mapping for initrd, it will be handled in VO. */
 
 	/* Avoid kernel command line. */
-	cmd_line  = (u64)boot_params->ext_cmd_line_ptr << 32;
-	cmd_line |= boot_params->hdr.cmd_line_ptr;
+	cmd_line = get_cmd_line_ptr();
 	/* Calculate size of cmd_line. */
-	ptr = (char *)(unsigned long)cmd_line;
-	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
-		;
-	mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
-	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
-	add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
-			 mem_avoid[MEM_AVOID_CMDLINE].size);
+	if (cmd_line) {
+		cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1;
+		mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
+		mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
+	}
 
 	/* Avoid boot parameters. */
-	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
-	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
-	add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
-			 mem_avoid[MEM_AVOID_BOOTPARAMS].size);
+	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr;
+	mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr);
 
 	/* We don't need to set a mapping for setup_data. */
 
 	/* Mark the memmap regions we need to avoid */
-	handle_mem_memmap();
+	handle_mem_options();
 
-#ifdef CONFIG_X86_VERBOSE_BOOTUP
-	/* Make sure video RAM can be used. */
-	add_identity_map(0, PMD_SIZE);
-#endif
+	/* Enumerate the immovable memory regions */
+	num_immovable_mem = count_immovable_mem_regions();
 }
 
 /*
@@ -393,7 +405,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 {
 	int i;
 	struct setup_data *ptr;
-	unsigned long earliest = img->start + img->size;
+	u64 earliest = img->start + img->size;
 	bool is_overlapping = false;
 
 	for (i = 0; i < MEM_AVOID_MAX; i++) {
@@ -406,7 +418,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 	}
 
 	/* Avoid all entries in the setup_data linked list. */
-	ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
+	ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
 	while (ptr) {
 		struct mem_vector avoid;
 
@@ -419,6 +431,18 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 			is_overlapping = true;
 		}
 
+		if (ptr->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)ptr->data)->type != SETUP_INDIRECT) {
+			avoid.start = ((struct setup_indirect *)ptr->data)->addr;
+			avoid.size = ((struct setup_indirect *)ptr->data)->len;
+
+			if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
+				*overlap = avoid;
+				earliest = overlap->start;
+				is_overlapping = true;
+			}
+		}
+
 		ptr = (struct setup_data *)(unsigned long)ptr->next;
 	}
 
@@ -426,18 +450,16 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 }
 
 struct slot_area {
-	unsigned long addr;
-	int num;
+	u64 addr;
+	unsigned long num;
 };
 
 #define MAX_SLOT_AREA 100
 
 static struct slot_area slot_areas[MAX_SLOT_AREA];
-
+static unsigned int slot_area_index;
 static unsigned long slot_max;
 
-static unsigned long slot_area_index;
-
 static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 {
 	struct slot_area slot_area;
@@ -446,19 +468,66 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 		return;
 
 	slot_area.addr = region->start;
-	slot_area.num = (region->size - image_size) /
-			CONFIG_PHYSICAL_ALIGN + 1;
+	slot_area.num = 1 + (region->size - image_size) / CONFIG_PHYSICAL_ALIGN;
+
+	slot_areas[slot_area_index++] = slot_area;
+	slot_max += slot_area.num;
+}
+
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+	u64 pud_start, pud_end;
+	unsigned long gb_huge_pages;
+	struct mem_vector tmp;
+
+	if (!IS_ENABLED(CONFIG_X86_64) || !max_gb_huge_pages) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/* Are there any 1GB pages in the region? */
+	pud_start = ALIGN(region->start, PUD_SIZE);
+	pud_end = ALIGN_DOWN(region->start + region->size, PUD_SIZE);
 
-	if (slot_area.num > 0) {
-		slot_areas[slot_area_index++] = slot_area;
-		slot_max += slot_area.num;
+	/* No good 1GB huge pages found: */
+	if (pud_start >= pud_end) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/* Check if the head part of the region is usable. */
+	if (pud_start >= region->start + image_size) {
+		tmp.start = region->start;
+		tmp.size = pud_start - region->start;
+		store_slot_info(&tmp, image_size);
+	}
+
+	/* Skip the good 1GB pages. */
+	gb_huge_pages = (pud_end - pud_start) >> PUD_SHIFT;
+	if (gb_huge_pages > max_gb_huge_pages) {
+		pud_end = pud_start + (max_gb_huge_pages << PUD_SHIFT);
+		max_gb_huge_pages = 0;
+	} else {
+		max_gb_huge_pages -= gb_huge_pages;
+	}
+
+	/* Check if the tail part of the region is usable. */
+	if (region->start + region->size >= pud_end + image_size) {
+		tmp.start = pud_end;
+		tmp.size = region->start + region->size - pud_end;
+		store_slot_info(&tmp, image_size);
 	}
 }
 
-static unsigned long slots_fetch_random(void)
+static u64 slots_fetch_random(void)
 {
 	unsigned long slot;
-	int i;
+	unsigned int i;
 
 	/* Handle case of no slots stored. */
 	if (slot_max == 0)
@@ -471,7 +540,7 @@ static unsigned long slots_fetch_random(void)
 			slot -= slot_areas[i].num;
 			continue;
 		}
-		return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN;
+		return slot_areas[i].addr + ((u64)slot * CONFIG_PHYSICAL_ALIGN);
 	}
 
 	if (i == slot_area_index)
@@ -479,59 +548,28 @@ static unsigned long slots_fetch_random(void)
 	return 0;
 }
 
-static void process_e820_entry(struct boot_e820_entry *entry,
-			       unsigned long minimum,
-			       unsigned long image_size)
+static void __process_mem_region(struct mem_vector *entry,
+				 unsigned long minimum,
+				 unsigned long image_size)
 {
 	struct mem_vector region, overlap;
-	struct slot_area slot_area;
-	unsigned long start_orig, end;
-	struct boot_e820_entry cur_entry;
-
-	/* Skip non-RAM entries. */
-	if (entry->type != E820_TYPE_RAM)
-		return;
-
-	/* On 32-bit, ignore entries entirely above our maximum. */
-	if (IS_ENABLED(CONFIG_X86_32) && entry->addr >= KERNEL_IMAGE_SIZE)
-		return;
-
-	/* Ignore entries entirely below our minimum. */
-	if (entry->addr + entry->size < minimum)
-		return;
-
-	/* Ignore entries above memory limit */
-	end = min(entry->size + entry->addr, mem_limit);
-	if (entry->addr >= end)
-		return;
-	cur_entry.addr = entry->addr;
-	cur_entry.size = end - entry->addr;
+	u64 region_end;
 
-	region.start = cur_entry.addr;
-	region.size = cur_entry.size;
+	/* Enforce minimum and memory limit. */
+	region.start = max_t(u64, entry->start, minimum);
+	region_end = min(entry->start + entry->size, mem_limit);
 
 	/* Give up if slot area array is full. */
 	while (slot_area_index < MAX_SLOT_AREA) {
-		start_orig = region.start;
-
-		/* Potentially raise address to minimum location. */
-		if (region.start < minimum)
-			region.start = minimum;
-
 		/* Potentially raise address to meet alignment needs. */
 		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
 
-		/* Did we raise the address above this e820 region? */
-		if (region.start > cur_entry.addr + cur_entry.size)
+		/* Did we raise the address above the passed in memory entry? */
+		if (region.start > region_end)
 			return;
 
 		/* Reduce size by any delta from the original address. */
-		region.size -= region.start - start_orig;
-
-		/* On 32-bit, reduce region size to fit within max size. */
-		if (IS_ENABLED(CONFIG_X86_32) &&
-		    region.start + region.size > KERNEL_IMAGE_SIZE)
-			region.size = KERNEL_IMAGE_SIZE - region.start;
+		region.size = region_end - region.start;
 
 		/* Return if region can't contain decompressed kernel */
 		if (region.size < image_size)
@@ -539,55 +577,264 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 
 		/* If nothing overlaps, store the region and return. */
 		if (!mem_avoid_overlap(&region, &overlap)) {
-			store_slot_info(&region, image_size);
+			process_gb_huge_pages(&region, image_size);
 			return;
 		}
 
 		/* Store beginning of region if holds at least image_size. */
-		if (overlap.start > region.start + image_size) {
-			struct mem_vector beginning;
-
-			beginning.start = region.start;
-			beginning.size = overlap.start - region.start;
-			store_slot_info(&beginning, image_size);
+		if (overlap.start >= region.start + image_size) {
+			region.size = overlap.start - region.start;
+			process_gb_huge_pages(&region, image_size);
 		}
 
-		/* Return if overlap extends to or past end of region. */
-		if (overlap.start + overlap.size >= region.start + region.size)
-			return;
-
 		/* Clip off the overlapping region and start over. */
-		region.size -= overlap.start - region.start + overlap.size;
 		region.start = overlap.start + overlap.size;
 	}
 }
 
+static bool process_mem_region(struct mem_vector *region,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	int i;
+	/*
+	 * If no immovable memory found, or MEMORY_HOTREMOVE disabled,
+	 * use @region directly.
+	 */
+	if (!num_immovable_mem) {
+		__process_mem_region(region, minimum, image_size);
+
+		if (slot_area_index == MAX_SLOT_AREA) {
+			debug_putstr("Aborted e820/efi memmap scan (slot_areas full)!\n");
+			return true;
+		}
+		return false;
+	}
+
+#if defined(CONFIG_MEMORY_HOTREMOVE) && defined(CONFIG_ACPI)
+	/*
+	 * If immovable memory found, filter the intersection between
+	 * immovable memory and @region.
+	 */
+	for (i = 0; i < num_immovable_mem; i++) {
+		u64 start, end, entry_end, region_end;
+		struct mem_vector entry;
+
+		if (!mem_overlaps(region, &immovable_mem[i]))
+			continue;
+
+		start = immovable_mem[i].start;
+		end = start + immovable_mem[i].size;
+		region_end = region->start + region->size;
+
+		entry.start = clamp(region->start, start, end);
+		entry_end = clamp(region_end, start, end);
+		entry.size = entry_end - entry.start;
+
+		__process_mem_region(&entry, minimum, image_size);
+
+		if (slot_area_index == MAX_SLOT_AREA) {
+			debug_putstr("Aborted e820/efi memmap scan when walking immovable regions(slot_areas full)!\n");
+			return true;
+		}
+	}
+#endif
+	return false;
+}
+
+#ifdef CONFIG_EFI
+
+/*
+ * Only EFI_CONVENTIONAL_MEMORY and EFI_UNACCEPTED_MEMORY (if supported) are
+ * guaranteed to be free.
+ *
+ * Pick free memory more conservatively than the EFI spec allows: according to
+ * the spec, EFI_BOOT_SERVICES_{CODE|DATA} are also free memory and thus
+ * available to place the kernel image into, but in practice there's firmware
+ * where using that memory leads to crashes. Buggy vendor EFI code registers
+ * for an event that triggers on SetVirtualAddressMap(). The handler assumes
+ * that EFI_BOOT_SERVICES_DATA memory has not been touched by loader yet, which
+ * is probably true for Windows.
+ *
+ * Preserve EFI_BOOT_SERVICES_* regions until after SetVirtualAddressMap().
+ */
+static inline bool memory_type_is_free(efi_memory_desc_t *md)
+{
+	if (md->type == EFI_CONVENTIONAL_MEMORY)
+		return true;
+
+	if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
+	    md->type == EFI_UNACCEPTED_MEMORY)
+		    return true;
+
+	return false;
+}
+
+/*
+ * Returns true if we processed the EFI memmap, which we prefer over the E820
+ * table if it is available.
+ */
+static bool
+process_efi_entries(unsigned long minimum, unsigned long image_size)
+{
+	struct efi_info *e = &boot_params_ptr->efi_info;
+	bool efi_mirror_found = false;
+	struct mem_vector region;
+	efi_memory_desc_t *md;
+	unsigned long pmap;
+	char *signature;
+	u32 nr_desc;
+	int i;
+
+	signature = (char *)&e->efi_loader_signature;
+	if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) &&
+	    strncmp(signature, EFI64_LOADER_SIGNATURE, 4))
+		return false;
+
+#ifdef CONFIG_X86_32
+	/* Can't handle data above 4GB at this time */
+	if (e->efi_memmap_hi) {
+		warn("EFI memmap is above 4GB, can't be handled now on x86_32. EFI should be disabled.\n");
+		return false;
+	}
+	pmap =  e->efi_memmap;
+#else
+	pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32));
+#endif
+
+	nr_desc = e->efi_memmap_size / e->efi_memdesc_size;
+	for (i = 0; i < nr_desc; i++) {
+		md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i);
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			efi_mirror_found = true;
+			break;
+		}
+	}
+
+	for (i = 0; i < nr_desc; i++) {
+		md = efi_early_memdesc_ptr(pmap, e->efi_memdesc_size, i);
+
+		if (!memory_type_is_free(md))
+			continue;
+
+		if (efi_soft_reserve_enabled() &&
+		    (md->attribute & EFI_MEMORY_SP))
+			continue;
+
+		if (efi_mirror_found &&
+		    !(md->attribute & EFI_MEMORY_MORE_RELIABLE))
+			continue;
+
+		region.start = md->phys_addr;
+		region.size = md->num_pages << EFI_PAGE_SHIFT;
+		if (process_mem_region(&region, minimum, image_size))
+			break;
+	}
+	return true;
+}
+#else
+static inline bool
+process_efi_entries(unsigned long minimum, unsigned long image_size)
+{
+	return false;
+}
+#endif
+
+static void process_e820_entries(unsigned long minimum,
+				 unsigned long image_size)
+{
+	int i;
+	struct mem_vector region;
+	struct boot_e820_entry *entry;
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < boot_params_ptr->e820_entries; i++) {
+		entry = &boot_params_ptr->e820_table[i];
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+		region.start = entry->addr;
+		region.size = entry->size;
+		if (process_mem_region(&region, minimum, image_size))
+			break;
+	}
+}
+
+/*
+ * If KHO is active, only process its scratch areas to ensure we are not
+ * stepping onto preserved memory.
+ */
+static bool process_kho_entries(unsigned long minimum, unsigned long image_size)
+{
+	struct kho_scratch *kho_scratch;
+	struct setup_data *ptr;
+	struct kho_data *kho;
+	int i, nr_areas = 0;
+
+	if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+		return false;
+
+	ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
+	while (ptr) {
+		if (ptr->type == SETUP_KEXEC_KHO) {
+			kho = (struct kho_data *)(unsigned long)ptr->data;
+			kho_scratch = (void *)(unsigned long)kho->scratch_addr;
+			nr_areas = kho->scratch_size / sizeof(*kho_scratch);
+			break;
+		}
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
+	if (!nr_areas)
+		return false;
+
+	for (i = 0; i < nr_areas; i++) {
+		struct kho_scratch *area = &kho_scratch[i];
+		struct mem_vector region = {
+			.start = area->addr,
+			.size = area->size,
+		};
+
+		if (process_mem_region(&region, minimum, image_size))
+			break;
+	}
+
+	return true;
+}
+
 static unsigned long find_random_phys_addr(unsigned long minimum,
 					   unsigned long image_size)
 {
-	int i;
-	unsigned long addr;
+	u64 phys_addr;
+
+	/* Bail out early if it's impossible to succeed. */
+	if (minimum + image_size > mem_limit)
+		return 0;
 
 	/* Check if we had too many memmaps. */
 	if (memmap_too_large) {
-		debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
+		debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n");
 		return 0;
 	}
 
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+	/*
+	 * During kexec handover only process KHO scratch areas that are known
+	 * not to contain any data that must be preserved.
+	 */
+	if (!process_kho_entries(minimum, image_size) &&
+	    !process_efi_entries(minimum, image_size))
+		process_e820_entries(minimum, image_size);
 
-	/* Verify potential e820 positions, appending to slots list. */
-	for (i = 0; i < boot_params->e820_entries; i++) {
-		process_e820_entry(&boot_params->e820_table[i], minimum,
-				   image_size);
-		if (slot_area_index == MAX_SLOT_AREA) {
-			debug_putstr("Aborted e820 scan (slot_areas full)!\n");
-			break;
-		}
+	phys_addr = slots_fetch_random();
+
+	/* Perform a final check to make sure the address is in range. */
+	if (phys_addr < minimum || phys_addr + image_size > mem_limit) {
+		warn("Invalid physical address chosen!\n");
+		return 0;
 	}
 
-	return slots_fetch_random();
+	return (unsigned long)phys_addr;
 }
 
 static unsigned long find_random_virt_addr(unsigned long minimum,
@@ -595,18 +842,12 @@ static unsigned long find_random_virt_addr(unsigned long minimum,
 {
 	unsigned long slots, random_addr;
 
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
-	/* Align image_size for easy slot calculations. */
-	image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);
-
 	/*
 	 * There are how many CONFIG_PHYSICAL_ALIGN-sized slots
 	 * that can hold image_size within the range of minimum to
 	 * KERNEL_IMAGE_SIZE?
 	 */
-	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
-		 CONFIG_PHYSICAL_ALIGN + 1;
+	slots = 1 + (KERNEL_IMAGE_SIZE - minimum - image_size) / CONFIG_PHYSICAL_ALIGN;
 
 	random_addr = kaslr_get_random_long("Virtual") % slots;
 
@@ -630,10 +871,12 @@ void choose_random_location(unsigned long input,
 		return;
 	}
 
-	boot_params->hdr.loadflags |= KASLR_FLAG;
+	boot_params_ptr->hdr.loadflags |= KASLR_FLAG;
 
-	/* Prepare to add new identity pagetables on demand. */
-	initialize_identity_maps();
+	if (IS_ENABLED(CONFIG_X86_32))
+		mem_limit = KERNEL_IMAGE_SIZE;
+	else
+		mem_limit = MAXMEM;
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init(input, input_size, *output);
@@ -644,26 +887,17 @@ void choose_random_location(unsigned long input,
 	 * location:
 	 */
 	min_addr = min(*output, 512UL << 20);
+	/* Make sure minimum is aligned. */
+	min_addr = ALIGN(min_addr, CONFIG_PHYSICAL_ALIGN);
 
-	/* Walk e820 and find a random address. */
+	/* Walk available memory entries to find a random address. */
 	random_addr = find_random_phys_addr(min_addr, output_size);
 	if (!random_addr) {
 		warn("Physical KASLR disabled: no suitable memory region!");
 	} else {
 		/* Update the new physical address location. */
-		if (*output != random_addr) {
-			add_identity_map(random_addr, output_size);
+		if (*output != random_addr)
 			*output = random_addr;
-		}
-
-		/*
-		 * This loads the identity mapping page table.
-		 * This should only be done if a new physical address
-		 * is found for the kernel, otherwise we should keep
-		 * the old page table to make it be like the "nokaslr"
-		 * case.
-		 */
-		finalize_identity_maps();
 	}