Resguardo inicial

linux-7.2.3/arch/x86/platform/efi/Makefile

@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+KASAN_SANITIZE := n
+GCOV_PROFILE := n
+
+obj-$(CONFIG_EFI) 		+= memmap.o quirks.o efi.o efi_$(BITS).o \
+				   efi_stub_$(BITS).o
+obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o
+obj-$(CONFIG_EFI_RUNTIME_MAP)	+= runtime-map.o

linux-7.2.3/arch/x86/platform/efi/efi.c

@@ -0,0 +1,926 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common EFI (Extensible Firmware Interface) support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *	Stephane Eranian <eranian@hpl.hp.com>
+ * Copyright (C) 2005-2008 Intel Co.
+ *	Fenghua Yu <fenghua.yu@intel.com>
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Chandramouli Narayanan <mouli@linux.intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013 SuSE Labs
+ *	Borislav Petkov <bp@suse.de> - runtime services VA mapping
+ *
+ * Copied from efi_32.c to eliminate the duplicated code between EFI
+ * 32/64 support code. --ying 2007-10-26
+ *
+ * All EFI Runtime Services are not implemented yet as EFI only
+ * supports physical mode addressing on SoftSDV. This is to be fixed
+ * in a future version.  --drummond 1999-07-20
+ *
+ * Implemented EFI runtime services and virtual mode calls.  --davidm
+ *
+ * Goutham Rao: <goutham.rao@intel.com>
+ *	Skip non-WB memory and ignore empty memory ranges.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/efi.h>
+#include <linux/efi-bgrt.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/time.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <linux/bcd.h>
+
+#include <asm/setup.h>
+#include <asm/efi.h>
+#include <asm/e820/api.h>
+#include <asm/time.h>
+#include <asm/tlbflush.h>
+#include <asm/x86_init.h>
+#include <asm/uv/uv.h>
+
+static unsigned long efi_systab_phys __initdata;
+static unsigned long efi_runtime, efi_nr_tables;
+
+unsigned long efi_fw_vendor, efi_config_table;
+
+static const efi_config_table_type_t arch_tables[] __initconst = {
+#ifdef CONFIG_X86_UV
+	{UV_SYSTEM_TABLE_GUID,		&uv_systab_phys,	"UVsystab"	},
+#endif
+	{},
+};
+
+static const unsigned long * const efi_tables[] = {
+	&efi.acpi,
+	&efi.acpi20,
+	&efi.smbios,
+	&efi.smbios3,
+#ifdef CONFIG_X86_UV
+	&uv_systab_phys,
+#endif
+	&efi_fw_vendor,
+	&efi_runtime,
+	&efi_config_table,
+	&efi.esrt,
+	&efi_mem_attr_table,
+#ifdef CONFIG_EFI_RCI2_TABLE
+	&rci2_table_phys,
+#endif
+	&efi.tpm_log,
+	&efi.tpm_final_log,
+	&efi_rng_seed,
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	&efi.mokvar_table,
+#endif
+#ifdef CONFIG_EFI_COCO_SECRET
+	&efi.coco_secret,
+#endif
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	&efi.unaccepted,
+#endif
+};
+
+u64 efi_setup;		/* efi setup_data physical address */
+
+static int add_efi_memmap __initdata;
+static int __init setup_add_efi_memmap(char *arg)
+{
+	add_efi_memmap = 1;
+	return 0;
+}
+early_param("add_efi_memmap", setup_add_efi_memmap);
+
+/*
+ * Tell the kernel about the EFI memory map.  This might include
+ * more than the max 128 entries that can fit in the passed in e820
+ * legacy (zeropage) memory map, but the kernel's e820 table can hold
+ * E820_MAX_ENTRIES.
+ */
+
+static void __init do_add_efi_memmap(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
+	for_each_efi_memory_desc(md) {
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		int e820_type;
+
+		switch (md->type) {
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
+		case EFI_BOOT_SERVICES_CODE:
+		case EFI_BOOT_SERVICES_DATA:
+		case EFI_CONVENTIONAL_MEMORY:
+			if (efi_soft_reserve_enabled()
+			    && (md->attribute & EFI_MEMORY_SP))
+				e820_type = E820_TYPE_SOFT_RESERVED;
+			else if (md->attribute & EFI_MEMORY_WB)
+				e820_type = E820_TYPE_RAM;
+			else
+				e820_type = E820_TYPE_RESERVED;
+			break;
+		case EFI_ACPI_RECLAIM_MEMORY:
+			e820_type = E820_TYPE_ACPI;
+			break;
+		case EFI_ACPI_MEMORY_NVS:
+			e820_type = E820_TYPE_NVS;
+			break;
+		case EFI_UNUSABLE_MEMORY:
+			e820_type = E820_TYPE_UNUSABLE;
+			break;
+		case EFI_PERSISTENT_MEMORY:
+			e820_type = E820_TYPE_PMEM;
+			break;
+		default:
+			/*
+			 * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
+			 * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
+			 * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
+			 */
+			e820_type = E820_TYPE_RESERVED;
+			break;
+		}
+
+		e820__range_add(start, size, e820_type);
+	}
+	e820__update_table(e820_table);
+}
+
+/*
+ * Given add_efi_memmap defaults to 0 and there is no alternative
+ * e820 mechanism for soft-reserved memory, import the full EFI memory
+ * map if soft reservations are present and enabled. Otherwise, the
+ * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is
+ * the efi=nosoftreserve option.
+ */
+static bool do_efi_soft_reserve(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return false;
+
+	if (!efi_soft_reserve_enabled())
+		return false;
+
+	for_each_efi_memory_desc(md)
+		if (md->type == EFI_CONVENTIONAL_MEMORY &&
+		    (md->attribute & EFI_MEMORY_SP))
+			return true;
+	return false;
+}
+
+int __init efi_memblock_x86_reserve_range(void)
+{
+	struct efi_info *e = &boot_params.efi_info;
+	struct efi_memory_map_data data;
+	phys_addr_t pmap;
+	int rv;
+
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+	/* Can't handle firmware tables above 4GB on i386 */
+	if (IS_ENABLED(CONFIG_X86_32) && e->efi_memmap_hi > 0) {
+		pr_err("Memory map is above 4GB, disabling EFI.\n");
+		return -EINVAL;
+	}
+	pmap = (phys_addr_t)(e->efi_memmap | ((u64)e->efi_memmap_hi << 32));
+
+	data.phys_map		= pmap;
+	data.size 		= e->efi_memmap_size;
+	data.desc_size		= e->efi_memdesc_size;
+	data.desc_version	= e->efi_memdesc_version;
+
+	if (!efi_enabled(EFI_PARAVIRT)) {
+		rv = efi_memmap_init_early(&data);
+		if (rv)
+			return rv;
+	}
+
+	if (add_efi_memmap || do_efi_soft_reserve())
+		do_add_efi_memmap();
+
+	WARN(efi.memmap.desc_version != 1,
+	     "Unexpected EFI_MEMORY_DESCRIPTOR version %ld",
+	     efi.memmap.desc_version);
+
+	memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size);
+	set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags);
+
+	return 0;
+}
+
+#define OVERFLOW_ADDR_SHIFT	(64 - EFI_PAGE_SHIFT)
+#define OVERFLOW_ADDR_MASK	(U64_MAX << OVERFLOW_ADDR_SHIFT)
+#define U64_HIGH_BIT		(~(U64_MAX >> 1))
+
+static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i)
+{
+	u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1;
+	u64 end_hi = 0;
+	char buf[64];
+
+	if (md->num_pages == 0) {
+		end = 0;
+	} else if (md->num_pages > EFI_PAGES_MAX ||
+		   EFI_PAGES_MAX - md->num_pages <
+		   (md->phys_addr >> EFI_PAGE_SHIFT)) {
+		end_hi = (md->num_pages & OVERFLOW_ADDR_MASK)
+			>> OVERFLOW_ADDR_SHIFT;
+
+		if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT))
+			end_hi += 1;
+	} else {
+		return true;
+	}
+
+	pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n");
+
+	if (end_hi) {
+		pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n",
+			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr, end_hi, end);
+	} else {
+		pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n",
+			i, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr, end);
+	}
+	return false;
+}
+
+static void __init efi_clean_memmap(void)
+{
+	efi_memory_desc_t *out = efi.memmap.map;
+	const efi_memory_desc_t *in = out;
+	const efi_memory_desc_t *end = efi.memmap.map_end;
+	int i, n_removal;
+
+	for (i = n_removal = 0; in < end; i++) {
+		if (efi_memmap_entry_valid(in, i)) {
+			if (out != in)
+				memcpy(out, in, efi.memmap.desc_size);
+			out = (void *)out + efi.memmap.desc_size;
+		} else {
+			n_removal++;
+		}
+		in = (void *)in + efi.memmap.desc_size;
+	}
+
+	if (n_removal > 0) {
+		struct efi_memory_map_data data = {
+			.phys_map	= efi.memmap.phys_map,
+			.desc_version	= efi.memmap.desc_version,
+			.desc_size	= efi.memmap.desc_size,
+			.size		= efi.memmap.desc_size * (efi.memmap.nr_map - n_removal),
+			.flags		= 0,
+		};
+
+		pr_warn("Removing %d invalid memory map entries.\n", n_removal);
+		efi_memmap_install(&data);
+	}
+}
+
+/*
+ * Firmware can use EfiMemoryMappedIO to request that MMIO regions be
+ * mapped by the OS so they can be accessed by EFI runtime services, but
+ * should have no other significance to the OS (UEFI r2.10, sec 7.2).
+ * However, most bootloaders and EFI stubs convert EfiMemoryMappedIO
+ * regions to E820_TYPE_RESERVED entries, which prevent Linux from
+ * allocating space from them (see remove_e820_regions()).
+ *
+ * Some platforms use EfiMemoryMappedIO entries for PCI MMCONFIG space and
+ * PCI host bridge windows, which means Linux can't allocate BAR space for
+ * hot-added devices.
+ *
+ * Remove large EfiMemoryMappedIO regions from the E820 map to avoid this
+ * problem.
+ *
+ * Retain small EfiMemoryMappedIO regions because on some platforms, these
+ * describe non-window space that's included in host bridge _CRS.  If we
+ * assign that space to PCI devices, they don't work.
+ */
+static void __init efi_remove_e820_mmio(void)
+{
+	efi_memory_desc_t *md;
+	u64 size, start, end;
+	int i = 0;
+
+	for_each_efi_memory_desc(md) {
+		if (md->type == EFI_MEMORY_MAPPED_IO) {
+			size = md->num_pages << EFI_PAGE_SHIFT;
+			start = md->phys_addr;
+			end = start + size - 1;
+			if (size >= 256*1024) {
+				pr_info("Remove mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluMB) from e820 map\n",
+					i, start, end, size >> 20);
+				e820__range_remove(start, size, E820_TYPE_RESERVED);
+			} else {
+				pr_info("Not removing mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluKB) from e820 map\n",
+					i, start, end, size >> 10);
+			}
+		}
+		i++;
+	}
+}
+
+void __init efi_print_memmap(void)
+{
+	efi_memory_desc_t *md;
+	int i = 0;
+
+	for_each_efi_memory_desc(md) {
+		char buf[64];
+
+		pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n",
+			i++, efi_md_typeattr_format(buf, sizeof(buf), md),
+			md->phys_addr,
+			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1,
+			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
+	}
+}
+
+static int __init efi_systab_init(unsigned long phys)
+{
+	int size = efi_enabled(EFI_64BIT) ? sizeof(efi_system_table_64_t)
+					  : sizeof(efi_system_table_32_t);
+	const efi_table_hdr_t *hdr;
+	bool over4g = false;
+	void *p;
+	int ret;
+
+	hdr = p = early_memremap_ro(phys, size);
+	if (p == NULL) {
+		pr_err("Couldn't map the system table!\n");
+		return -ENOMEM;
+	}
+
+	ret = efi_systab_check_header(hdr);
+	if (ret) {
+		early_memunmap(p, size);
+		return ret;
+	}
+
+	if (efi_enabled(EFI_64BIT)) {
+		const efi_system_table_64_t *systab64 = p;
+
+		efi_runtime	= systab64->runtime;
+		over4g		= systab64->runtime > U32_MAX;
+
+		if (efi_setup) {
+			struct efi_setup_data *data;
+
+			data = early_memremap_ro(efi_setup, sizeof(*data));
+			if (!data) {
+				early_memunmap(p, size);
+				return -ENOMEM;
+			}
+
+			efi_fw_vendor		= (unsigned long)data->fw_vendor;
+			efi_config_table	= (unsigned long)data->tables;
+
+			over4g |= data->fw_vendor	> U32_MAX ||
+				  data->tables		> U32_MAX;
+
+			early_memunmap(data, sizeof(*data));
+		} else {
+			efi_fw_vendor		= systab64->fw_vendor;
+			efi_config_table	= systab64->tables;
+
+			over4g |= systab64->fw_vendor	> U32_MAX ||
+				  systab64->tables	> U32_MAX;
+		}
+		efi_nr_tables = systab64->nr_tables;
+	} else {
+		const efi_system_table_32_t *systab32 = p;
+
+		efi_fw_vendor		= systab32->fw_vendor;
+		efi_runtime		= systab32->runtime;
+		efi_config_table	= systab32->tables;
+		efi_nr_tables		= systab32->nr_tables;
+	}
+
+	efi.runtime_version = hdr->revision;
+
+	efi_systab_report_header(hdr, efi_fw_vendor);
+	early_memunmap(p, size);
+
+	if (IS_ENABLED(CONFIG_X86_32) && over4g) {
+		pr_err("EFI data located above 4GB, disabling EFI.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __init efi_config_init(const efi_config_table_type_t *arch_tables)
+{
+	void *config_tables;
+	int sz, ret;
+
+	if (efi_nr_tables == 0)
+		return 0;
+
+	if (efi_enabled(EFI_64BIT))
+		sz = sizeof(efi_config_table_64_t);
+	else
+		sz = sizeof(efi_config_table_32_t);
+
+	/*
+	 * Let's see what config tables the firmware passed to us.
+	 */
+	config_tables = early_memremap(efi_config_table, efi_nr_tables * sz);
+	if (config_tables == NULL) {
+		pr_err("Could not map Configuration table!\n");
+		return -ENOMEM;
+	}
+
+	ret = efi_config_parse_tables(config_tables, efi_nr_tables,
+				      arch_tables);
+
+	early_memunmap(config_tables, efi_nr_tables * sz);
+	return ret;
+}
+
+void __init efi_init(void)
+{
+	if (IS_ENABLED(CONFIG_X86_32) &&
+	    (boot_params.efi_info.efi_systab_hi ||
+	     boot_params.efi_info.efi_memmap_hi)) {
+		pr_info("Table located above 4GB, disabling EFI.\n");
+		return;
+	}
+
+	efi_systab_phys = boot_params.efi_info.efi_systab |
+			  ((__u64)boot_params.efi_info.efi_systab_hi << 32);
+
+	if (efi_systab_init(efi_systab_phys))
+		return;
+
+	if (efi_reuse_config(efi_config_table, efi_nr_tables))
+		return;
+
+	if (efi_config_init(arch_tables))
+		return;
+
+	/*
+	 * Note: We currently don't support runtime services on an EFI
+	 * that doesn't match the kernel 32/64-bit mode.
+	 */
+
+	if (!efi_runtime_supported())
+		pr_err("No EFI runtime due to 32/64-bit mismatch with kernel\n");
+
+	if (!efi_runtime_supported() || efi_runtime_disabled()) {
+		efi_memmap_unmap();
+		return;
+	}
+
+	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+	efi_clean_memmap();
+
+	efi_remove_e820_mmio();
+
+	if (efi_enabled(EFI_DBG))
+		efi_print_memmap();
+}
+
+/* Merge contiguous regions of the same type and attribute */
+static void __init efi_merge_regions(void)
+{
+	efi_memory_desc_t *md, *prev_md = NULL;
+
+	for_each_efi_memory_desc(md) {
+		u64 prev_size;
+
+		if (!prev_md) {
+			prev_md = md;
+			continue;
+		}
+
+		if (prev_md->type != md->type ||
+		    prev_md->attribute != md->attribute) {
+			prev_md = md;
+			continue;
+		}
+
+		prev_size = prev_md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->phys_addr == (prev_md->phys_addr + prev_size)) {
+			prev_md->num_pages += md->num_pages;
+			md->type = EFI_RESERVED_TYPE;
+			md->attribute = 0;
+			continue;
+		}
+		prev_md = md;
+	}
+}
+
+static void *realloc_pages(void *old_memmap, int old_shift)
+{
+	void *ret;
+
+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+	if (!ret)
+		goto out;
+
+	/*
+	 * A first-time allocation doesn't have anything to copy.
+	 */
+	if (!old_memmap)
+		return ret;
+
+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+	free_pages((unsigned long)old_memmap, old_shift);
+	return ret;
+}
+
+/*
+ * Iterate the EFI memory map in reverse order because the regions
+ * will be mapped top-down. The end result is the same as if we had
+ * mapped things forward, but doesn't require us to change the
+ * existing implementation of efi_map_region().
+ */
+static inline void *efi_map_next_entry_reverse(void *entry)
+{
+	/* Initial call */
+	if (!entry)
+		return efi.memmap.map_end - efi.memmap.desc_size;
+
+	entry -= efi.memmap.desc_size;
+	if (entry < efi.memmap.map)
+		return NULL;
+
+	return entry;
+}
+
+/*
+ * efi_map_next_entry - Return the next EFI memory map descriptor
+ * @entry: Previous EFI memory map descriptor
+ *
+ * This is a helper function to iterate over the EFI memory map, which
+ * we do in different orders depending on the current configuration.
+ *
+ * To begin traversing the memory map @entry must be %NULL.
+ *
+ * Returns %NULL when we reach the end of the memory map.
+ */
+static void *efi_map_next_entry(void *entry)
+{
+	if (efi_enabled(EFI_64BIT)) {
+		/*
+		 * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
+		 * config table feature requires us to map all entries
+		 * in the same order as they appear in the EFI memory
+		 * map. That is to say, entry N must have a lower
+		 * virtual address than entry N+1. This is because the
+		 * firmware toolchain leaves relative references in
+		 * the code/data sections, which are split and become
+		 * separate EFI memory regions. Mapping things
+		 * out-of-order leads to the firmware accessing
+		 * unmapped addresses.
+		 *
+		 * Since we need to map things this way whether or not
+		 * the kernel actually makes use of
+		 * EFI_PROPERTIES_TABLE, let's just switch to this
+		 * scheme by default for 64-bit.
+		 */
+		return efi_map_next_entry_reverse(entry);
+	}
+
+	/* Initial call */
+	if (!entry)
+		return efi.memmap.map;
+
+	entry += efi.memmap.desc_size;
+	if (entry >= efi.memmap.map_end)
+		return NULL;
+
+	return entry;
+}
+
+static bool should_map_region(efi_memory_desc_t *md)
+{
+	/*
+	 * Runtime regions always require runtime mappings (obviously).
+	 */
+	if (md->attribute & EFI_MEMORY_RUNTIME)
+		return true;
+
+	/*
+	 * 32-bit EFI doesn't suffer from the bug that requires us to
+	 * reserve boot services regions, and mixed mode support
+	 * doesn't exist for 32-bit kernels.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		return false;
+
+	/*
+	 * EFI specific purpose memory may be reserved by default
+	 * depending on kernel config and boot options.
+	 */
+	if (md->type == EFI_CONVENTIONAL_MEMORY &&
+	    efi_soft_reserve_enabled() &&
+	    (md->attribute & EFI_MEMORY_SP))
+		return false;
+
+	/*
+	 * Map all of RAM so that we can access arguments in the 1:1
+	 * mapping when making EFI runtime calls.
+	 */
+	if (efi_is_mixed()) {
+		if (md->type == EFI_CONVENTIONAL_MEMORY ||
+		    md->type == EFI_LOADER_DATA ||
+		    md->type == EFI_LOADER_CODE)
+			return true;
+	}
+
+	/*
+	 * Map boot services regions as a workaround for buggy
+	 * firmware that accesses them even when they shouldn't.
+	 *
+	 * See efi_{reserve,free}_boot_services().
+	 */
+	if (md->type == EFI_BOOT_SERVICES_CODE ||
+	    md->type == EFI_BOOT_SERVICES_DATA)
+		return true;
+
+	return false;
+}
+
+/*
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
+ */
+static void * __init efi_map_regions(int *count, int *pg_shift)
+{
+	void *p, *new_memmap = NULL;
+	unsigned long left = 0;
+	unsigned long desc_size;
+	efi_memory_desc_t *md;
+
+	desc_size = efi.memmap.desc_size;
+
+	p = NULL;
+	while ((p = efi_map_next_entry(p))) {
+		md = p;
+
+		if (!should_map_region(md))
+			continue;
+
+		efi_map_region(md);
+
+		if (left < desc_size) {
+			new_memmap = realloc_pages(new_memmap, *pg_shift);
+			if (!new_memmap)
+				return NULL;
+
+			left += PAGE_SIZE << *pg_shift;
+			(*pg_shift)++;
+		}
+
+		memcpy(new_memmap + (*count * desc_size), md, desc_size);
+
+		left -= desc_size;
+		(*count)++;
+	}
+
+	return new_memmap;
+}
+
+static void __init kexec_enter_virtual_mode(void)
+{
+#ifdef CONFIG_KEXEC_CORE
+	efi_memory_desc_t *md;
+	unsigned int num_pages;
+
+	/*
+	 * We don't do virtual mode, since we don't do runtime services, on
+	 * non-native EFI.
+	 */
+	if (efi_is_mixed()) {
+		efi_memmap_unmap();
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	if (efi_alloc_page_tables()) {
+		pr_err("Failed to allocate EFI page tables\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	/*
+	* Map efi regions which were passed via setup_data. The virt_addr is a
+	* fixed addr which was used in first kernel of a kexec boot.
+	*/
+	for_each_efi_memory_desc(md)
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+
+	/*
+	 * Unregister the early EFI memmap from efi_init() and install
+	 * the new EFI memory map.
+	 */
+	efi_memmap_unmap();
+
+	if (efi_memmap_init_late(efi.memmap.phys_map,
+				 efi.memmap.desc_size * efi.memmap.nr_map)) {
+		pr_err("Failed to remap late EFI memory map\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE);
+	num_pages >>= PAGE_SHIFT;
+
+	if (efi_setup_page_tables(efi.memmap.phys_map, num_pages)) {
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return;
+	}
+
+	efi_sync_low_kernel_mappings();
+	efi_native_runtime_setup();
+	efi_runtime_update_mappings();
+#endif
+}
+
+/*
+ * This function will switch the EFI runtime services to virtual mode.
+ * Essentially, we look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor into the
+ * efi_pgd page table.
+ *
+ * The new method does a pagetable switch in a preemption-safe manner
+ * so that we're in a different address space when calling a runtime
+ * function. For function arguments passing we do copy the PUDs of the
+ * kernel page table into efi_pgd prior to each call.
+ *
+ * Specially for kexec boot, efi runtime maps in previous kernel should
+ * be passed in via setup_data. In that case runtime ranges will be mapped
+ * to the same virtual addresses as the first kernel, see
+ * kexec_enter_virtual_mode().
+ */
+static void __init __efi_enter_virtual_mode(void)
+{
+	int count = 0, pg_shift = 0;
+	void *new_memmap = NULL;
+	efi_status_t status;
+	unsigned long pa;
+
+	if (efi_alloc_page_tables()) {
+		pr_err("Failed to allocate EFI page tables\n");
+		goto err;
+	}
+
+	efi_merge_regions();
+	new_memmap = efi_map_regions(&count, &pg_shift);
+	if (!new_memmap) {
+		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+		goto err;
+	}
+
+	pa = __pa(new_memmap);
+
+	/*
+	 * Unregister the early EFI memmap from efi_init() and install
+	 * the new EFI memory map that we are about to pass to the
+	 * firmware via SetVirtualAddressMap().
+	 */
+	efi_memmap_unmap();
+
+	if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) {
+		pr_err("Failed to remap late EFI memory map\n");
+		goto err;
+	}
+
+	if (efi_enabled(EFI_DBG)) {
+		pr_info("EFI runtime memory map:\n");
+		efi_print_memmap();
+	}
+
+	if (efi_setup_page_tables(pa, 1 << pg_shift))
+		goto err;
+
+	efi_sync_low_kernel_mappings();
+
+	status = efi_set_virtual_address_map(efi.memmap.desc_size * count,
+					     efi.memmap.desc_size,
+					     efi.memmap.desc_version,
+					     (efi_memory_desc_t *)pa,
+					     efi_systab_phys);
+	if (status != EFI_SUCCESS) {
+		pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n",
+		       status);
+		goto err;
+	}
+
+	efi_check_for_embedded_firmwares();
+	efi_unmap_boot_services();
+
+	if (!efi_is_mixed())
+		efi_native_runtime_setup();
+	else
+		efi_thunk_runtime_setup();
+
+	/*
+	 * Apply more restrictive page table mapping attributes now that
+	 * SVAM() has been called and the firmware has performed all
+	 * necessary relocation fixups for the new virtual addresses.
+	 */
+	efi_runtime_update_mappings();
+
+	/* clean DUMMY object */
+	efi_delete_dummy_variable();
+	return;
+
+err:
+	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+}
+
+void __init efi_enter_virtual_mode(void)
+{
+	if (efi_enabled(EFI_PARAVIRT))
+		return;
+
+	efi.runtime = (efi_runtime_services_t *)efi_runtime;
+
+	if (efi_setup)
+		kexec_enter_virtual_mode();
+	else
+		__efi_enter_virtual_mode();
+
+	efi_dump_pagetable();
+}
+
+bool efi_is_table_address(unsigned long phys_addr)
+{
+	unsigned int i;
+
+	if (phys_addr == EFI_INVALID_TABLE_ADDR)
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(efi_tables); i++)
+		if (*(efi_tables[i]) == phys_addr)
+			return true;
+
+	return false;
+}
+
+#define EFI_FIELD(var) efi_ ## var
+
+#define EFI_ATTR_SHOW(name) \
+static ssize_t name##_show(struct kobject *kobj, \
+				struct kobj_attribute *attr, char *buf) \
+{ \
+	return sprintf(buf, "0x%lx\n", EFI_FIELD(name)); \
+}
+
+EFI_ATTR_SHOW(fw_vendor);
+EFI_ATTR_SHOW(runtime);
+EFI_ATTR_SHOW(config_table);
+
+struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor);
+struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime);
+struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table);
+
+umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n)
+{
+	if (attr == &efi_attr_fw_vendor.attr) {
+		if (efi_enabled(EFI_PARAVIRT) ||
+				efi_fw_vendor == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	} else if (attr == &efi_attr_runtime.attr) {
+		if (efi_runtime == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	} else if (attr == &efi_attr_config_table.attr) {
+		if (efi_config_table == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	}
+	return attr->mode;
+}
+
+enum efi_secureboot_mode __x86_efi_boot_mode(void)
+{
+	return boot_params.secure_boot;
+}

linux-7.2.3/arch/x86/platform/efi/efi_32.c

@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *	Stephane Eranian <eranian@hpl.hp.com>
+ *
+ * All EFI Runtime Services are not implemented yet as EFI only
+ * supports physical mode addressing on SoftSDV. This is to be fixed
+ * in a future version.  --drummond 1999-07-20
+ *
+ * Implemented EFI runtime services and virtual mode calls.  --davidm
+ *
+ * Goutham Rao: <goutham.rao@intel.com>
+ *	Skip non-WB memory and ignore empty memory ranges.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/efi.h>
+#include <linux/pgtable.h>
+
+#include <asm/io.h>
+#include <asm/desc.h>
+#include <asm/page.h>
+#include <asm/set_memory.h>
+#include <asm/tlbflush.h>
+#include <asm/efi.h>
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	u64 start_pfn, end_pfn, end;
+	unsigned long size;
+	void *va;
+
+	start_pfn	= PFN_DOWN(md->phys_addr);
+	size		= md->num_pages << PAGE_SHIFT;
+	end		= md->phys_addr + size;
+	end_pfn 	= PFN_UP(end);
+
+	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
+		va = __va(md->phys_addr);
+
+		if (!(md->attribute & EFI_MEMORY_WB))
+			set_memory_uc((unsigned long)va, md->num_pages);
+	} else {
+		va = ioremap_cache(md->phys_addr, size);
+	}
+
+	md->virt_addr = (unsigned long)va;
+	if (!va)
+		pr_err("ioremap of 0x%llX failed!\n", md->phys_addr);
+}
+
+/*
+ * To make EFI call EFI runtime service in physical addressing mode we need
+ * prolog/epilog before/after the invocation to claim the EFI runtime service
+ * handler exclusively and to duplicate a memory mapping in low memory space,
+ * say 0 - 3G.
+ */
+
+int __init efi_alloc_page_tables(void)
+{
+	return 0;
+}
+
+void efi_sync_low_kernel_mappings(void) {}
+
+void __init efi_dump_pagetable(void)
+{
+#ifdef CONFIG_EFI_PGT_DUMP
+	ptdump_walk_pgd_level(NULL, &init_mm);
+#endif
+}
+
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	return 0;
+}
+
+void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
+
+efi_status_t efi_call_svam(efi_runtime_services_t * const *,
+			   u32, u32, u32, void *, u32);
+
+efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size,
+						unsigned long descriptor_size,
+						u32 descriptor_version,
+						efi_memory_desc_t *virtual_map,
+						unsigned long systab_phys)
+{
+	const efi_system_table_t *systab = (efi_system_table_t *)systab_phys;
+	struct desc_ptr gdt_descr;
+	efi_status_t status;
+	unsigned long flags;
+	pgd_t *save_pgd;
+
+	/* Current pgd is swapper_pg_dir, we'll restore it later: */
+	save_pgd = swapper_pg_dir;
+	load_cr3(initial_page_table);
+	__flush_tlb_all();
+
+	gdt_descr.address = get_cpu_gdt_paddr(0);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+
+	/* Disable interrupts around EFI calls: */
+	local_irq_save(flags);
+	status = efi_call_svam(&systab->runtime,
+			       memory_map_size, descriptor_size,
+			       descriptor_version, virtual_map,
+			       __pa(&efi.runtime));
+	local_irq_restore(flags);
+
+	load_fixmap_gdt(0);
+	load_cr3(save_pgd);
+	__flush_tlb_all();
+
+	return status;
+}
+
+void __init efi_runtime_update_mappings(void)
+{
+	if (__supported_pte_mask & _PAGE_NX) {
+		efi_memory_desc_t *md;
+
+		/* Make EFI runtime service code area executable */
+		for_each_efi_memory_desc(md) {
+			if (md->type != EFI_RUNTIME_SERVICES_CODE)
+				continue;
+
+			set_memory_x(md->virt_addr, md->num_pages);
+		}
+	}
+}
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}

linux-7.2.3/arch/x86/platform/efi/efi_64.c

@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86_64 specific EFI support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * Copyright (C) 2005-2008 Intel Co.
+ *	Fenghua Yu <fenghua.yu@intel.com>
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Chandramouli Narayanan <mouli@linux.intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ *
+ * Code to convert EFI to E820 map has been implemented in elilo bootloader
+ * based on a EFI patch by Edgar Hucek. Based on the E820 map, the page table
+ * is setup appropriately for EFI runtime code.
+ * - mouli 06/14/2007.
+ *
+ */
+
+#define pr_fmt(fmt) "efi: " fmt
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/memblock.h>
+#include <linux/ioport.h>
+#include <linux/mc146818rtc.h>
+#include <linux/efi.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/ucs2_string.h>
+#include <linux/cc_platform.h>
+#include <linux/sched/task.h>
+
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/e820/api.h>
+#include <asm/tlbflush.h>
+#include <asm/proto.h>
+#include <asm/efi.h>
+#include <asm/cacheflush.h>
+#include <asm/fixmap.h>
+#include <asm/realmode.h>
+#include <asm/time.h>
+#include <asm/pgalloc.h>
+#include <asm/sev.h>
+
+/*
+ * We allocate runtime services regions top-down, starting from -4G, i.e.
+ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
+ */
+static u64 efi_va = EFI_VA_START;
+static struct mm_struct *efi_prev_mm;
+static unsigned long efi_cr4_lass;
+
+/*
+ * We need our own copy of the higher levels of the page tables
+ * because we want to avoid inserting EFI region mappings (EFI_VA_END
+ * to EFI_VA_START) into the standard kernel page tables. Everything
+ * else can be shared, see efi_sync_low_kernel_mappings().
+ *
+ * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
+ * allocation.
+ */
+int __init efi_alloc_page_tables(void)
+{
+	pgd_t *pgd, *efi_pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	gfp_t gfp_mask;
+
+	gfp_mask = GFP_KERNEL | __GFP_ZERO;
+	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
+	if (!efi_pgd)
+		goto fail;
+
+	pgd = efi_pgd + pgd_index(EFI_VA_END);
+	p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
+	if (!p4d)
+		goto free_pgd;
+
+	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
+	if (!pud)
+		goto free_p4d;
+
+	efi_mm.pgd = efi_pgd;
+	mm_init_cpumask(&efi_mm);
+	init_new_context(NULL, &efi_mm);
+	set_notrack_mm(&efi_mm);
+
+	return 0;
+
+free_p4d:
+	if (pgtable_l5_enabled())
+		free_page((unsigned long)pgd_page_vaddr(*pgd));
+free_pgd:
+	free_pages((unsigned long)efi_pgd, pgd_allocation_order());
+fail:
+	return -ENOMEM;
+}
+
+/*
+ * Add low kernel mappings for passing arguments to EFI functions.
+ */
+void efi_sync_low_kernel_mappings(void)
+{
+	unsigned num_entries;
+	pgd_t *pgd_k, *pgd_efi;
+	p4d_t *p4d_k, *p4d_efi;
+	pud_t *pud_k, *pud_efi;
+	pgd_t *efi_pgd = efi_mm.pgd;
+
+	pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET);
+	pgd_k = pgd_offset_k(PAGE_OFFSET);
+
+	num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET);
+	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
+
+	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
+	pgd_k = pgd_offset_k(EFI_VA_END);
+	p4d_efi = p4d_offset(pgd_efi, 0);
+	p4d_k = p4d_offset(pgd_k, 0);
+
+	num_entries = p4d_index(EFI_VA_END);
+	memcpy(p4d_efi, p4d_k, sizeof(p4d_t) * num_entries);
+
+	/*
+	 * We share all the PUD entries apart from those that map the
+	 * EFI regions. Copy around them.
+	 */
+	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
+	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
+
+	p4d_efi = p4d_offset(pgd_efi, EFI_VA_END);
+	p4d_k = p4d_offset(pgd_k, EFI_VA_END);
+	pud_efi = pud_offset(p4d_efi, 0);
+	pud_k = pud_offset(p4d_k, 0);
+
+	num_entries = pud_index(EFI_VA_END);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
+
+	pud_efi = pud_offset(p4d_efi, EFI_VA_START);
+	pud_k = pud_offset(p4d_k, EFI_VA_START);
+
+	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
+	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
+}
+
+/*
+ * Wrapper for slow_virt_to_phys() that handles NULL addresses.
+ */
+static inline phys_addr_t
+virt_to_phys_or_null_size(void *va, unsigned long size)
+{
+	phys_addr_t pa;
+
+	if (!va)
+		return 0;
+
+	if (virt_addr_valid(va))
+		return virt_to_phys(va);
+
+	pa = slow_virt_to_phys(va);
+
+	/* check if the object crosses a page boundary */
+	if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK))
+		return 0;
+
+	return pa;
+}
+
+#define virt_to_phys_or_null(addr)				\
+	virt_to_phys_or_null_size((addr), sizeof(*(addr)))
+
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+	extern const u8 __efi64_thunk_ret_tramp[];
+	unsigned long pfn, text, pf, rodata, tramp;
+	struct page *page;
+	unsigned npages;
+	pgd_t *pgd = efi_mm.pgd;
+
+	/*
+	 * It can happen that the physical address of new_memmap lands in memory
+	 * which is not mapped in the EFI page table. Therefore we need to go
+	 * and ident-map those pages containing the map before calling
+	 * phys_efi_set_virtual_address_map().
+	 */
+	pfn = pa_memmap >> PAGE_SHIFT;
+	pf = _PAGE_NX | _PAGE_RW | _PAGE_ENC;
+	if (kernel_map_pages_in_pgd(pgd, pfn, pa_memmap, num_pages, pf)) {
+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+		return 1;
+	}
+
+	/*
+	 * Certain firmware versions are way too sentimental and still believe
+	 * they are exclusive and unquestionable owners of the first physical page,
+	 * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
+	 * (but then write-access it later during SetVirtualAddressMap()).
+	 *
+	 * Create a 1:1 mapping for this page, to avoid triple faults during early
+	 * boot with such firmware. We are free to hand this page to the BIOS,
+	 * as trim_bios_range() will reserve the first page and isolate it away
+	 * from memory allocators anyway.
+	 */
+	if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, pf)) {
+		pr_err("Failed to create 1:1 mapping for the first page!\n");
+		return 1;
+	}
+
+	/*
+	 * When SEV-ES is active, the GHCB as set by the kernel will be used
+	 * by firmware. Create a 1:1 unencrypted mapping for each GHCB.
+	 */
+	if (sev_es_efi_map_ghcbs_cas(pgd)) {
+		pr_err("Failed to create 1:1 mapping for the GHCBs and CAs!\n");
+		return 1;
+	}
+
+	/*
+	 * When making calls to the firmware everything needs to be 1:1
+	 * mapped and addressable with 32-bit pointers. Map the kernel
+	 * text and allocate a new stack because we can't rely on the
+	 * stack pointer being < 4GB.
+	 */
+	if (!efi_is_mixed())
+		return 0;
+
+	page = alloc_page(GFP_KERNEL|__GFP_DMA32);
+	if (!page) {
+		pr_err("Unable to allocate EFI runtime stack < 4GB\n");
+		return 1;
+	}
+
+	efi_mixed_mode_stack_pa = page_to_phys(page + 1); /* stack grows down */
+
+	npages = (_etext - _text) >> PAGE_SHIFT;
+	text = __pa(_text);
+
+	if (kernel_unmap_pages_in_pgd(pgd, text, npages)) {
+		pr_err("Failed to unmap kernel text 1:1 mapping\n");
+		return 1;
+	}
+
+	npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT;
+	rodata = __pa(__start_rodata);
+	pfn = rodata >> PAGE_SHIFT;
+
+	pf = _PAGE_NX | _PAGE_ENC;
+	if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) {
+		pr_err("Failed to map kernel rodata 1:1\n");
+		return 1;
+	}
+
+	tramp = __pa(__efi64_thunk_ret_tramp);
+	pfn = tramp >> PAGE_SHIFT;
+
+	pf = _PAGE_ENC;
+	if (kernel_map_pages_in_pgd(pgd, pfn, tramp, 1, pf)) {
+		pr_err("Failed to map mixed mode return trampoline\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static void __init __map_region(efi_memory_desc_t *md, u64 va)
+{
+	unsigned long flags = _PAGE_RW;
+	unsigned long pfn;
+	pgd_t *pgd = efi_mm.pgd;
+
+	/*
+	 * EFI_RUNTIME_SERVICES_CODE regions typically cover PE/COFF
+	 * executable images in memory that consist of both R-X and
+	 * RW- sections, so we cannot apply read-only or non-exec
+	 * permissions just yet. However, modern EFI systems provide
+	 * a memory attributes table that describes those sections
+	 * with the appropriate restricted permissions, which are
+	 * applied in efi_runtime_update_mappings() below. All other
+	 * regions can be mapped non-executable at this point, with
+	 * the exception of boot services code regions, but those will
+	 * be unmapped again entirely in efi_free_boot_services().
+	 */
+	if (md->type != EFI_BOOT_SERVICES_CODE &&
+	    md->type != EFI_RUNTIME_SERVICES_CODE)
+		flags |= _PAGE_NX;
+
+	if (!(md->attribute & EFI_MEMORY_WB))
+		flags |= _PAGE_PCD;
+
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) &&
+	    md->type != EFI_MEMORY_MAPPED_IO)
+		flags |= _PAGE_ENC;
+
+	pfn = md->phys_addr >> PAGE_SHIFT;
+	if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags))
+		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, va);
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	unsigned long size = md->num_pages << PAGE_SHIFT;
+	u64 pa = md->phys_addr;
+
+	/*
+	 * Make sure the 1:1 mappings are present as a catch-all for b0rked
+	 * firmware which doesn't update all internal pointers after switching
+	 * to virtual mode and would otherwise crap on us.
+	 */
+	__map_region(md, md->phys_addr);
+
+	/*
+	 * Enforce the 1:1 mapping as the default virtual address when
+	 * booting in EFI mixed mode, because even though we may be
+	 * running a 64-bit kernel, the firmware may only be 32-bit.
+	 */
+	if (efi_is_mixed()) {
+		md->virt_addr = md->phys_addr;
+		return;
+	}
+
+	efi_va -= size;
+
+	/* Is PA 2M-aligned? */
+	if (!(pa & (PMD_SIZE - 1))) {
+		efi_va &= PMD_MASK;
+	} else {
+		u64 pa_offset = pa & (PMD_SIZE - 1);
+		u64 prev_va = efi_va;
+
+		/* get us the same offset within this 2M page */
+		efi_va = (efi_va & PMD_MASK) + pa_offset;
+
+		if (efi_va > prev_va)
+			efi_va -= PMD_SIZE;
+	}
+
+	if (efi_va < EFI_VA_END) {
+		pr_warn(FW_WARN "VA address range overflow!\n");
+		return;
+	}
+
+	/* Do the VA map */
+	__map_region(md, efi_va);
+	md->virt_addr = efi_va;
+}
+
+/*
+ * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
+ * md->virt_addr is the original virtual address which had been mapped in kexec
+ * 1st kernel.
+ */
+void __init efi_map_region_fixed(efi_memory_desc_t *md)
+{
+	__map_region(md, md->phys_addr);
+	__map_region(md, md->virt_addr);
+}
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+}
+
+static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
+{
+	unsigned long pfn;
+	pgd_t *pgd = efi_mm.pgd;
+	int err1, err2;
+
+	/* Update the 1:1 mapping */
+	pfn = md->phys_addr >> PAGE_SHIFT;
+	err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf);
+	if (err1) {
+		pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, md->virt_addr);
+	}
+
+	err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf);
+	if (err2) {
+		pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, md->virt_addr);
+	}
+
+	return err1 || err2;
+}
+
+bool efi_disable_ibt_for_runtime __ro_after_init = true;
+
+static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md,
+				      bool has_ibt)
+{
+	unsigned long pf = 0;
+
+	efi_disable_ibt_for_runtime |= !has_ibt;
+
+	if (md->attribute & EFI_MEMORY_XP)
+		pf |= _PAGE_NX;
+
+	if (!(md->attribute & EFI_MEMORY_RO))
+		pf |= _PAGE_RW;
+
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		pf |= _PAGE_ENC;
+
+	return efi_update_mappings(md, pf);
+}
+
+void __init efi_runtime_update_mappings(void)
+{
+	if (efi_enabled(EFI_MEM_ATTR)) {
+		efi_disable_ibt_for_runtime = false;
+		efi_memattr_apply_permissions(NULL, efi_update_mem_attr);
+	}
+}
+
+void __init efi_dump_pagetable(void)
+{
+#ifdef CONFIG_EFI_PGT_DUMP
+	ptdump_walk_pgd_level(NULL, &efi_mm);
+#endif
+}
+
+/*
+ * Makes the calling thread switch to/from efi_mm context. Can be used
+ * in a kernel thread and user context. Preemption needs to remain disabled
+ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm
+ * can not change under us.
+ * It should be ensured that there are no concurrent calls to this function.
+ */
+static void efi_enter_mm(void)
+{
+	efi_prev_mm = use_temporary_mm(&efi_mm);
+}
+
+static void efi_leave_mm(void)
+{
+	unuse_temporary_mm(efi_prev_mm);
+}
+
+/*
+ * Toggle LASS to allow EFI to access any 1:1 mapped region in the lower
+ * half.
+ *
+ * Disable LASS only after switching to EFI-mm, as userspace is not
+ * mapped in it. Similar to EFI-mm, these rely on preemption being
+ * disabled and the calls being serialized.
+ */
+
+static void efi_disable_lass(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_LASS))
+		return;
+
+	lockdep_assert_preemption_disabled();
+
+	/* Save current CR4.LASS state */
+	efi_cr4_lass = cr4_read_shadow() & X86_CR4_LASS;
+	cr4_clear_bits(efi_cr4_lass);
+}
+
+static void efi_enable_lass(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_LASS))
+		return;
+
+	lockdep_assert_preemption_disabled();
+
+	/* Reprogram CR4.LASS only if it was set earlier */
+	cr4_set_bits(efi_cr4_lass);
+}
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_sync_low_kernel_mappings();
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+	efi_enter_mm();
+	efi_disable_lass();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	efi_enable_lass();
+	efi_leave_mm();
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
+
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
+/*
+ * DS and ES contain user values.  We need to save them.
+ * The 32-bit EFI code needs a valid DS, ES, and SS.  There's no
+ * need to save the old SS: __KERNEL_DS is always acceptable.
+ */
+#define __efi_thunk(func, ...)						\
+({									\
+	unsigned short __ds, __es;					\
+	efi_status_t ____s;						\
+									\
+	savesegment(ds, __ds);						\
+	savesegment(es, __es);						\
+									\
+	loadsegment(ss, __KERNEL_DS);					\
+	loadsegment(ds, __KERNEL_DS);					\
+	loadsegment(es, __KERNEL_DS);					\
+									\
+	____s = efi64_thunk(efi.runtime->mixed_mode.func, __VA_ARGS__);	\
+									\
+	loadsegment(ds, __ds);						\
+	loadsegment(es, __es);						\
+									\
+	____s ^= (____s & BIT(31)) | (____s & BIT_ULL(31)) << 32;	\
+	____s;								\
+})
+
+/*
+ * Switch to the EFI page tables early so that we can access the 1:1
+ * runtime services mappings which are not mapped in any other page
+ * tables.
+ *
+ * Also, disable interrupts because the IDT points to 64-bit handlers,
+ * which aren't going to function correctly when we switch to 32-bit.
+ */
+#define efi_thunk(func...)						\
+({									\
+	efi_status_t __s;						\
+									\
+	arch_efi_call_virt_setup();					\
+									\
+	__s = __efi_thunk(func);					\
+									\
+	arch_efi_call_virt_teardown();					\
+									\
+	__s;								\
+})
+
+static efi_status_t __init __no_sanitize_address
+efi_thunk_set_virtual_address_map(unsigned long memory_map_size,
+				  unsigned long descriptor_size,
+				  u32 descriptor_version,
+				  efi_memory_desc_t *virtual_map)
+{
+	efi_status_t status;
+	unsigned long flags;
+
+	efi_sync_low_kernel_mappings();
+	local_irq_save(flags);
+
+	efi_enter_mm();
+
+	status = __efi_thunk(set_virtual_address_map, memory_map_size,
+			     descriptor_size, descriptor_version, virtual_map);
+
+	efi_leave_mm();
+	local_irq_restore(flags);
+
+	return status;
+}
+
+static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t efi_thunk_set_time(efi_time_t *tm)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
+			  efi_time_t *tm)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static unsigned long efi_name_size(efi_char16_t *name)
+{
+	return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1;
+}
+
+static efi_status_t
+efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 *attr, unsigned long *data_size, void *data)
+{
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
+	efi_status_t status;
+	u32 phys_name, phys_vendor, phys_attr;
+	u32 phys_data_size, phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	*vnd = *vendor;
+
+	phys_data_size = virt_to_phys_or_null(data_size);
+	phys_vendor = virt_to_phys_or_null(vnd);
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_attr = virt_to_phys_or_null(attr);
+	phys_data = virt_to_phys_or_null_size(data, *data_size);
+
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(get_variable, phys_name, phys_vendor,
+				   phys_attr, phys_data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+		       u32 attr, unsigned long data_size, void *data)
+{
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	*vnd = *vendor;
+
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vnd);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(set_variable, phys_name, phys_vendor,
+				   attr, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+				   u32 attr, unsigned long data_size,
+				   void *data)
+{
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
+
+	*vnd = *vendor;
+
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vnd);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	if (!phys_name || (data && !phys_data))
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(set_variable, phys_name, phys_vendor,
+				   attr, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_variable(unsigned long *name_size,
+			    efi_char16_t *name,
+			    efi_guid_t *vendor)
+{
+	u8 buf[24] __aligned(8);
+	efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd));
+	efi_status_t status;
+	u32 phys_name_size, phys_name, phys_vendor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	*vnd = *vendor;
+
+	phys_name_size = virt_to_phys_or_null(name_size);
+	phys_vendor = virt_to_phys_or_null(vnd);
+	phys_name = virt_to_phys_or_null_size(name, *name_size);
+
+	if (!phys_name)
+		status = EFI_INVALID_PARAMETER;
+	else
+		status = efi_thunk(get_next_variable, phys_name_size,
+				   phys_name, phys_vendor);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	*vendor = *vnd;
+	return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_high_mono_count(u32 *count)
+{
+	return EFI_UNSUPPORTED;
+}
+
+static void
+efi_thunk_reset_system(int reset_type, efi_status_t status,
+		       unsigned long data_size, efi_char16_t *data)
+{
+	u32 phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+}
+
+static efi_status_t
+efi_thunk_update_capsule(efi_capsule_header_t **capsules,
+			 unsigned long count, unsigned long sg_list)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
+			      u64 *remaining_space,
+			      u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space,
+					  u64 *remaining_space,
+					  u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
+
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules,
+			     unsigned long count, u64 *max_size,
+			     int *reset_type)
+{
+	/*
+	 * To properly support this function we would need to repackage
+	 * 'capsules' because the firmware doesn't understand 64-bit
+	 * pointers.
+	 */
+	return EFI_UNSUPPORTED;
+}
+
+void __init efi_thunk_runtime_setup(void)
+{
+	if (!IS_ENABLED(CONFIG_EFI_MIXED))
+		return;
+
+	efi.get_time = efi_thunk_get_time;
+	efi.set_time = efi_thunk_set_time;
+	efi.get_wakeup_time = efi_thunk_get_wakeup_time;
+	efi.set_wakeup_time = efi_thunk_set_wakeup_time;
+	efi.get_variable = efi_thunk_get_variable;
+	efi.get_next_variable = efi_thunk_get_next_variable;
+	efi.set_variable = efi_thunk_set_variable;
+	efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking;
+	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
+	efi.reset_system = efi_thunk_reset_system;
+	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking;
+	efi.update_capsule = efi_thunk_update_capsule;
+	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
+}
+
+efi_status_t __init __no_sanitize_address
+efi_set_virtual_address_map(unsigned long memory_map_size,
+			    unsigned long descriptor_size,
+			    u32 descriptor_version,
+			    efi_memory_desc_t *virtual_map,
+			    unsigned long systab_phys)
+{
+	const efi_system_table_t *systab = (efi_system_table_t *)systab_phys;
+	efi_status_t status;
+	unsigned long flags;
+
+	if (efi_is_mixed())
+		return efi_thunk_set_virtual_address_map(memory_map_size,
+							 descriptor_size,
+							 descriptor_version,
+							 virtual_map);
+	efi_enter_mm();
+
+	efi_fpu_begin();
+
+	/* Disable interrupts around EFI calls: */
+	local_irq_save(flags);
+	status = arch_efi_call_virt(efi.runtime, set_virtual_address_map,
+				    memory_map_size, descriptor_size,
+				    descriptor_version, virtual_map);
+	local_irq_restore(flags);
+
+	efi_fpu_end();
+
+	/* grab the virtually remapped EFI runtime services table pointer */
+	efi.runtime = READ_ONCE(systab->runtime);
+
+	efi_leave_mm();
+
+	return status;
+}

linux-7.2.3/arch/x86/platform/efi/efi_stub_32.S

@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * EFI call stub for IA32.
+ *
+ * This stub allows us to make EFI calls in physical mode with interrupts
+ * turned off.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/asm-offsets.h>
+#include <asm/page_types.h>
+
+	__INIT
+SYM_FUNC_START(efi_call_svam)
+	push	%ebp
+	movl	%esp, %ebp
+	push	%ebx
+
+	push	16(%esp)
+	push	16(%esp)
+	push	%ecx
+	push	%edx
+	movl	%eax, %ebx		// &systab_phys->runtime
+
+	/*
+	 * Switch to the flat mapped alias of this routine, by jumping to the
+	 * address of label '1' after subtracting PAGE_OFFSET from it.
+	 */
+	movl	$1f, %edx
+	subl	$__PAGE_OFFSET, %edx
+	jmp	*%edx
+1:
+
+	/* disable paging */
+	movl	%cr0, %edx
+	andl	$0x7fffffff, %edx
+	movl	%edx, %cr0
+
+	/* convert the stack pointer to a flat mapped address */
+	subl	$__PAGE_OFFSET, %esp
+
+	/* call the EFI routine */
+	movl	(%eax), %eax
+	call	*EFI_svam(%eax)
+
+	/* grab the virtually remapped EFI runtime services table pointer */
+	movl	(%ebx), %ecx
+	movl	36(%esp), %edx		// &efi.runtime
+	movl	%ecx, (%edx)
+
+	/* re-enable paging */
+	movl	%cr0, %edx
+	orl	$0x80000000, %edx
+	movl	%edx, %cr0
+
+	movl	16(%esp), %ebx
+	leave
+	RET
+SYM_FUNC_END(efi_call_svam)

linux-7.2.3/arch/x86/platform/efi/efi_stub_64.S

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Function calling ABI conversion from Linux to EFI for x86_64
+ *
+ * Copyright (C) 2007 Intel Corp
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/nospec-branch.h>
+
+SYM_FUNC_START(__efi_call)
+	/*
+	 * The EFI code doesn't have any CFI, annotate away the CFI violation.
+	 */
+	ANNOTATE_NOCFI_SYM
+	pushq %rbp
+	movq %rsp, %rbp
+	and $~0xf, %rsp
+	mov 16(%rbp), %rax
+	subq $48, %rsp
+	mov %r9, 32(%rsp)
+	mov %rax, 40(%rsp)
+	mov %r8, %r9
+	mov %rcx, %r8
+	mov %rsi, %rcx
+	CALL_NOSPEC rdi
+	leave
+	RET
+SYM_FUNC_END(__efi_call)

linux-7.2.3/arch/x86/platform/efi/efi_thunk_64.S

@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
+ */
+
+#include <linux/linkage.h>
+#include <linux/objtool.h>
+#include <asm/page_types.h>
+#include <asm/segment.h>
+
+	.text
+	.code64
+SYM_FUNC_START(__efi64_thunk)
+STACK_FRAME_NON_STANDARD __efi64_thunk
+	push	%rbp
+	push	%rbx
+
+	/*
+	 * Switch to 1:1 mapped 32-bit stack pointer.
+	 */
+	movq	%rsp, %rax
+	movq	efi_mixed_mode_stack_pa(%rip), %rsp
+	push	%rax
+
+	/*
+	 * Copy args passed via the stack
+	 */
+	subq	$0x24, %rsp
+	movq	0x18(%rax), %rbp
+	movq	0x20(%rax), %rbx
+	movq	0x28(%rax), %rax
+	movl	%ebp, 0x18(%rsp)
+	movl	%ebx, 0x1c(%rsp)
+	movl	%eax, 0x20(%rsp)
+
+	/*
+	 * Calculate the physical address of the kernel text.
+	 */
+	movq	$__START_KERNEL_map, %rax
+	subq	phys_base(%rip), %rax
+
+	leaq	1f(%rip), %rbp
+	leaq	2f(%rip), %rbx
+	subq	%rax, %rbp
+	subq	%rax, %rbx
+
+	movl	%ebx, 0x0(%rsp)		/* return address */
+	movl	%esi, 0x4(%rsp)
+	movl	%edx, 0x8(%rsp)
+	movl	%ecx, 0xc(%rsp)
+	movl	%r8d, 0x10(%rsp)
+	movl	%r9d, 0x14(%rsp)
+
+	/* Switch to 32-bit descriptor */
+	pushq	$__KERNEL32_CS
+	pushq	%rdi			/* EFI runtime service address */
+	lretq
+
+	// This return instruction is not needed for correctness, as it will
+	// never be reached. It only exists to make objtool happy, which will
+	// otherwise complain about unreachable instructions in the callers.
+	RET
+SYM_FUNC_END(__efi64_thunk)
+
+	.section ".rodata", "a", @progbits
+	.balign	16
+SYM_DATA_START(__efi64_thunk_ret_tramp)
+1:	movq	0x20(%rsp), %rsp
+	pop	%rbx
+	pop	%rbp
+	ret
+	int3
+
+	.code32
+2:	pushl	$__KERNEL_CS
+	pushl	%ebp
+	lret
+SYM_DATA_END(__efi64_thunk_ret_tramp)
+
+	.bss
+	.balign 8
+SYM_DATA(efi_mixed_mode_stack_pa, .quad 0)

linux-7.2.3/arch/x86/platform/efi/memmap.c

@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common EFI memory map functions.
+ */
+
+#define pr_fmt(fmt) "efi: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <asm/early_ioremap.h>
+#include <asm/efi.h>
+#include <linux/memblock.h>
+#include <linux/slab.h>
+
+static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size)
+{
+	return memblock_phys_alloc(size, SMP_CACHE_BYTES);
+}
+
+static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size)
+{
+	unsigned int order = get_order(size);
+	struct page *p = alloc_pages(GFP_KERNEL, order);
+
+	if (!p)
+		return 0;
+
+	return PFN_PHYS(page_to_pfn(p));
+}
+
+static
+void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags)
+{
+	if (flags & EFI_MEMMAP_MEMBLOCK) {
+		memblock_phys_free(phys, size);
+	} else if (flags & EFI_MEMMAP_SLAB) {
+		struct page *p = pfn_to_page(PHYS_PFN(phys));
+		unsigned int order = get_order(size);
+
+		__free_pages(p, order);
+	}
+}
+
+/**
+ * efi_memmap_alloc - Allocate memory for the EFI memory map
+ * @num_entries: Number of entries in the allocated map.
+ * @data: efi memmap installation parameters
+ *
+ * Depending on whether mm_init() has already been invoked or not,
+ * either memblock or "normal" page allocation is used.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+int __init efi_memmap_alloc(unsigned int num_entries,
+		struct efi_memory_map_data *data)
+{
+	/* Expect allocation parameters are zero initialized */
+	WARN_ON(data->phys_map || data->size);
+
+	data->size = num_entries * efi.memmap.desc_size;
+	data->desc_version = efi.memmap.desc_version;
+	data->desc_size = efi.memmap.desc_size;
+	data->flags &= ~(EFI_MEMMAP_SLAB | EFI_MEMMAP_MEMBLOCK);
+	data->flags |= efi.memmap.flags & EFI_MEMMAP_LATE;
+
+	if (slab_is_available()) {
+		data->flags |= EFI_MEMMAP_SLAB;
+		data->phys_map = __efi_memmap_alloc_late(data->size);
+	} else {
+		data->flags |= EFI_MEMMAP_MEMBLOCK;
+		data->phys_map = __efi_memmap_alloc_early(data->size);
+	}
+
+	if (!data->phys_map)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * efi_memmap_install - Install a new EFI memory map in efi.memmap
+ * @data: efi memmap installation parameters
+ *
+ * Unlike efi_memmap_init_*(), this function does not allow the caller
+ * to switch from early to late mappings. It simply uses the existing
+ * mapping function and installs the new memmap.
+ *
+ * Returns zero on success, a negative error code on failure.
+ */
+int __init efi_memmap_install(struct efi_memory_map_data *data)
+{
+	unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map;
+	unsigned long flags = efi.memmap.flags;
+	u64 phys = efi.memmap.phys_map;
+	int ret;
+
+	efi_memmap_unmap();
+
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
+	ret = __efi_memmap_init(data);
+	if (ret)
+		return ret;
+
+	__efi_memmap_free(phys, size, flags);
+	return 0;
+}
+
+/**
+ * efi_memmap_split_count - Count number of additional EFI memmap entries
+ * @md: EFI memory descriptor to split
+ * @range: Address range (start, end) to split around
+ *
+ * Returns the number of additional EFI memmap entries required to
+ * accommodate @range.
+ */
+int __init efi_memmap_split_count(efi_memory_desc_t *md, struct range *range)
+{
+	u64 m_start, m_end;
+	u64 start, end;
+	int count = 0;
+
+	start = md->phys_addr;
+	end = start + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+	/* modifying range */
+	m_start = range->start;
+	m_end = range->end;
+
+	if (m_start <= start) {
+		/* split into 2 parts */
+		if (start < m_end && m_end < end)
+			count++;
+	}
+
+	if (start < m_start && m_start < end) {
+		/* split into 3 parts */
+		if (m_end < end)
+			count += 2;
+		/* split into 2 parts */
+		if (end <= m_end)
+			count++;
+	}
+
+	return count;
+}
+
+/**
+ * efi_memmap_insert - Insert a memory region in an EFI memmap
+ * @old_memmap: The existing EFI memory map structure
+ * @buf: Address of buffer to store new map
+ * @mem: Memory map entry to insert
+ *
+ * It is suggested that you call efi_memmap_split_count() first
+ * to see how large @buf needs to be.
+ */
+void __init efi_memmap_insert(struct efi_memory_map *old_memmap, void *buf,
+			      struct efi_mem_range *mem)
+{
+	u64 m_start, m_end, m_attr;
+	efi_memory_desc_t *md;
+	u64 start, end;
+	void *old, *new;
+
+	/* modifying range */
+	m_start = mem->range.start;
+	m_end = mem->range.end;
+	m_attr = mem->attribute;
+
+	/*
+	 * The EFI memory map deals with regions in EFI_PAGE_SIZE
+	 * units. Ensure that the region described by 'mem' is aligned
+	 * correctly.
+	 */
+	if (!IS_ALIGNED(m_start, EFI_PAGE_SIZE) ||
+	    !IS_ALIGNED(m_end + 1, EFI_PAGE_SIZE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (old = old_memmap->map, new = buf;
+	     old < old_memmap->map_end;
+	     old += old_memmap->desc_size, new += old_memmap->desc_size) {
+
+		/* copy original EFI memory descriptor */
+		memcpy(new, old, old_memmap->desc_size);
+		md = new;
+		start = md->phys_addr;
+		end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+
+		if (m_start <= start && end <= m_end)
+			md->attribute |= m_attr;
+
+		if (m_start <= start &&
+		    (start < m_end && m_end < end)) {
+			/* first part */
+			md->attribute |= m_attr;
+			md->num_pages = (m_end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+			/* latter part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_end + 1;
+			md->num_pages = (end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+		}
+
+		if ((start < m_start && m_start < end) && m_end < end) {
+			/* first part */
+			md->num_pages = (m_start - md->phys_addr) >>
+				EFI_PAGE_SHIFT;
+			/* middle part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->attribute |= m_attr;
+			md->phys_addr = m_start;
+			md->num_pages = (m_end - m_start + 1) >>
+				EFI_PAGE_SHIFT;
+			/* last part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_end + 1;
+			md->num_pages = (end - m_end) >>
+				EFI_PAGE_SHIFT;
+		}
+
+		if ((start < m_start && m_start < end) &&
+		    (end <= m_end)) {
+			/* first part */
+			md->num_pages = (m_start - md->phys_addr) >>
+				EFI_PAGE_SHIFT;
+			/* latter part */
+			new += old_memmap->desc_size;
+			memcpy(new, old, old_memmap->desc_size);
+			md = new;
+			md->phys_addr = m_start;
+			md->num_pages = (end - md->phys_addr + 1) >>
+				EFI_PAGE_SHIFT;
+			md->attribute |= m_attr;
+		}
+	}
+}

linux-7.2.3/arch/x86/platform/efi/quirks.c

@@ -0,0 +1,843 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt) "efi: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/acpi.h>
+#include <linux/dmi.h>
+
+#include <asm/e820/api.h>
+#include <asm/efi.h>
+#include <asm/uv/uv.h>
+#include <asm/cpu_device_id.h>
+#include <asm/realmode.h>
+#include <asm/reboot.h>
+
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+#define QUARK_CSH_SIGNATURE		0x5f435348	/* _CSH */
+#define QUARK_SECURITY_HEADER_SIZE	0x400
+
+/*
+ * Header prepended to the standard EFI capsule on Quark systems the are based
+ * on Intel firmware BSP.
+ * @csh_signature:	Unique identifier to sanity check signed module
+ * 			presence ("_CSH").
+ * @version:		Current version of CSH used. Should be one for Quark A0.
+ * @modulesize:		Size of the entire module including the module header
+ * 			and payload.
+ * @security_version_number_index: Index of SVN to use for validation of signed
+ * 			module.
+ * @security_version_number: Used to prevent against roll back of modules.
+ * @rsvd_module_id:	Currently unused for Clanton (Quark).
+ * @rsvd_module_vendor:	Vendor Identifier. For Intel products value is
+ * 			0x00008086.
+ * @rsvd_date:		BCD representation of build date as yyyymmdd, where
+ * 			yyyy=4 digit year, mm=1-12, dd=1-31.
+ * @headersize:		Total length of the header including including any
+ * 			padding optionally added by the signing tool.
+ * @hash_algo:		What Hash is used in the module signing.
+ * @cryp_algo:		What Crypto is used in the module signing.
+ * @keysize:		Total length of the key data including including any
+ * 			padding optionally added by the signing tool.
+ * @signaturesize:	Total length of the signature including including any
+ * 			padding optionally added by the signing tool.
+ * @rsvd_next_header:	32-bit pointer to the next Secure Boot Module in the
+ * 			chain, if there is a next header.
+ * @rsvd:		Reserved, padding structure to required size.
+ *
+ * See also QuartSecurityHeader_t in
+ * Quark_EDKII_v1.2.1.1/QuarkPlatformPkg/Include/QuarkBootRom.h
+ * from https://downloadcenter.intel.com/download/23197/Intel-Quark-SoC-X1000-Board-Support-Package-BSP
+ */
+struct quark_security_header {
+	u32 csh_signature;
+	u32 version;
+	u32 modulesize;
+	u32 security_version_number_index;
+	u32 security_version_number;
+	u32 rsvd_module_id;
+	u32 rsvd_module_vendor;
+	u32 rsvd_date;
+	u32 headersize;
+	u32 hash_algo;
+	u32 cryp_algo;
+	u32 keysize;
+	u32 signaturesize;
+	u32 rsvd_next_header;
+	u32 rsvd[2];
+};
+
+static const efi_char16_t efi_dummy_name[] = L"DUMMY";
+
+static bool efi_no_storage_paranoia;
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient
+ * space in the variable store. The implementation of garbage collection
+ * in some FW versions causes stale (deleted) variables to take up space
+ * longer than intended and space is only freed once the store becomes
+ * almost completely full.
+ *
+ * Enabling this option disables the space checks in
+ * efi_query_variable_store() and forces garbage collection.
+ *
+ * Only enable this option if deleting EFI variables does not free up
+ * space in your variable store, e.g. if despite deleting variables
+ * you're unable to create new ones.
+ */
+static int __init setup_storage_paranoia(char *arg)
+{
+	efi_no_storage_paranoia = true;
+	return 0;
+}
+early_param("efi_no_storage_paranoia", setup_storage_paranoia);
+
+/*
+ * Deleting the dummy variable which kicks off garbage collection
+*/
+void efi_delete_dummy_variable(void)
+{
+	efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name,
+				     &EFI_DUMMY_GUID,
+				     EFI_VARIABLE_NON_VOLATILE |
+				     EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				     EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL);
+}
+
+u64 efivar_reserved_space(void)
+{
+	if (efi_no_storage_paranoia)
+		return 0;
+	return EFI_MIN_RESERVE;
+}
+EXPORT_SYMBOL_GPL(efivar_reserved_space);
+
+/*
+ * In the nonblocking case we do not attempt to perform garbage
+ * collection if we do not have enough free space. Rather, we do the
+ * bare minimum check and give up immediately if the available space
+ * is below EFI_MIN_RESERVE.
+ *
+ * This function is intended to be small and simple because it is
+ * invoked from crash handler paths.
+ */
+static efi_status_t
+query_variable_store_nonblocking(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	status = efi.query_variable_info_nonblocking(attributes, &storage_size,
+						     &remaining_size,
+						     &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (remaining_size - size < EFI_MIN_RESERVE)
+		return EFI_OUT_OF_RESOURCES;
+
+	return EFI_SUCCESS;
+}
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient space
+ * in the variable store. Ensure that we never use more than a safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size,
+				      bool nonblocking)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
+	if (nonblocking)
+		return query_variable_store_nonblocking(attributes, size);
+
+	status = efi.query_variable_info(attributes, &storage_size,
+					 &remaining_size, &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	/*
+	 * We account for that by refusing the write if permitting it would
+	 * reduce the available space to under 5KB. This figure was provided by
+	 * Samsung, so should be safe.
+	 */
+	if ((remaining_size - size < EFI_MIN_RESERVE) &&
+		!efi_no_storage_paranoia) {
+
+		/*
+		 * Triggering garbage collection may require that the firmware
+		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
+		 * that by attempting to use more space than is available.
+		 */
+		unsigned long dummy_size = remaining_size + 1024;
+		void *dummy = kzalloc(dummy_size, GFP_KERNEL);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
+
+		status = efi.set_variable((efi_char16_t *)efi_dummy_name,
+					  &EFI_DUMMY_GUID,
+					  EFI_VARIABLE_NON_VOLATILE |
+					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					  EFI_VARIABLE_RUNTIME_ACCESS,
+					  dummy_size, dummy);
+
+		if (status == EFI_SUCCESS) {
+			/*
+			 * This should have failed, so if it didn't make sure
+			 * that we delete it...
+			 */
+			efi_delete_dummy_variable();
+		}
+
+		kfree(dummy);
+
+		/*
+		 * The runtime code may now have triggered a garbage collection
+		 * run, so check the variable info again
+		 */
+		status = efi.query_variable_info(attributes, &storage_size,
+						 &remaining_size, &max_size);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		/*
+		 * There still isn't enough room, so return an error
+		 */
+		if (remaining_size - size < EFI_MIN_RESERVE)
+			return EFI_OUT_OF_RESOURCES;
+	}
+
+	return EFI_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(efi_query_variable_store);
+
+/*
+ * The UEFI specification makes it clear that the operating system is
+ * free to do whatever it wants with boot services code after
+ * ExitBootServices() has been called. Ignoring this recommendation a
+ * significant bunch of EFI implementations continue calling into boot
+ * services code (SetVirtualAddressMap). In order to work around such
+ * buggy implementations we reserve boot services region during EFI
+ * init and make sure it stays executable. Then, after
+ * SetVirtualAddressMap(), it is discarded.
+ *
+ * However, some boot services regions contain data that is required
+ * by drivers, so we need to track which memory ranges can never be
+ * freed. This is done by tagging those regions with the
+ * EFI_MEMORY_RUNTIME attribute.
+ *
+ * Any driver that wants to mark a region as reserved must use
+ * efi_mem_reserve() which will insert a new EFI memory descriptor
+ * into efi.memmap (splitting existing regions if necessary) and tag
+ * it with EFI_MEMORY_RUNTIME.
+ */
+void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
+{
+	struct efi_memory_map_data data = { 0 };
+	struct efi_mem_range mr;
+	efi_memory_desc_t md;
+	int num_entries;
+	void *new;
+
+	if (efi_mem_desc_lookup(addr, &md) ||
+	    md.type != EFI_BOOT_SERVICES_DATA) {
+		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
+		return;
+	}
+
+	if (addr + size > md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT)) {
+		pr_err("Region spans EFI memory descriptors, %pa\n", &addr);
+		return;
+	}
+
+	size += addr % EFI_PAGE_SIZE;
+	size = round_up(size, EFI_PAGE_SIZE);
+	addr = round_down(addr, EFI_PAGE_SIZE);
+
+	mr.range.start = addr;
+	mr.range.end = addr + size - 1;
+	mr.attribute = md.attribute | EFI_MEMORY_RUNTIME;
+
+	num_entries = efi_memmap_split_count(&md, &mr.range);
+	num_entries += efi.memmap.nr_map;
+
+	if (efi_memmap_alloc(num_entries, &data) != 0) {
+		pr_err("Could not allocate boot services memmap\n");
+		return;
+	}
+
+	new = early_memremap_prot(data.phys_map, data.size,
+				  pgprot_val(pgprot_encrypted(FIXMAP_PAGE_NORMAL)));
+	if (!new) {
+		pr_err("Failed to map new boot services memmap\n");
+		return;
+	}
+
+	efi_memmap_insert(&efi.memmap, new, &mr);
+	early_memunmap(new, data.size);
+
+	efi_memmap_install(&data);
+	e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+	e820__update_table(e820_table);
+}
+
+/*
+ * Helper function for efi_reserve_boot_services() to figure out if we
+ * can free regions in efi_free_boot_services().
+ *
+ * Use this function to ensure we do not free regions owned by somebody
+ * else. We must only reserve (and then free) regions:
+ *
+ * - Not within any part of the kernel
+ * - Not the BIOS reserved area (E820_TYPE_RESERVED, E820_TYPE_NVS, etc)
+ */
+static __init bool can_free_region(u64 start, u64 size)
+{
+	if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
+		return false;
+
+	if (!e820__mapped_all(start, start+size, E820_TYPE_RAM))
+		return false;
+
+	return true;
+}
+
+void __init efi_reserve_boot_services(void)
+{
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
+	for_each_efi_memory_desc(md) {
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+		bool already_reserved;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		already_reserved = memblock_is_region_reserved(start, size);
+
+		/*
+		 * Because the following memblock_reserve() is paired
+		 * with free_reserved_area() for this region in
+		 * efi_free_boot_services(), we must be extremely
+		 * careful not to reserve, and subsequently free,
+		 * critical regions of memory (like the kernel image) or
+		 * those regions that somebody else has already
+		 * reserved.
+		 *
+		 * A good example of a critical region that must not be
+		 * freed is page zero (first 4Kb of memory), which may
+		 * contain boot services code/data but is marked
+		 * E820_TYPE_RESERVED by trim_bios_range().
+		 */
+		if (!already_reserved) {
+			memblock_reserve(start, size);
+
+			/*
+			 * If we are the first to reserve the region, no
+			 * one else cares about it. We own it and can
+			 * free it later.
+			 */
+			if (can_free_region(start, size))
+				continue;
+		}
+
+		/*
+		 * We don't own the region. We must not free it.
+		 *
+		 * Setting this bit for a boot services region really
+		 * doesn't make sense as far as the firmware is
+		 * concerned, but it does provide us with a way to tag
+		 * those regions that must not be paired with
+		 * memblock_phys_free().
+		 */
+		md->attribute |= EFI_MEMORY_RUNTIME;
+	}
+}
+
+/*
+ * Apart from having VA mappings for EFI boot services code/data regions,
+ * (duplicate) 1:1 mappings were also created as a quirk for buggy firmware. So,
+ * unmap both 1:1 and VA mappings.
+ */
+static void __init efi_unmap_pages(efi_memory_desc_t *md)
+{
+	pgd_t *pgd = efi_mm.pgd;
+	u64 pa = md->phys_addr;
+	u64 va = md->virt_addr;
+
+	/*
+	 * EFI mixed mode has all RAM mapped to access arguments while making
+	 * EFI runtime calls, hence don't unmap EFI boot services code/data
+	 * regions.
+	 */
+	if (efi_is_mixed())
+		return;
+
+	if (kernel_unmap_pages_in_pgd(pgd, pa, md->num_pages))
+		pr_err("Failed to unmap 1:1 mapping for 0x%llx\n", pa);
+
+	if (kernel_unmap_pages_in_pgd(pgd, va, md->num_pages))
+		pr_err("Failed to unmap VA mapping for 0x%llx\n", va);
+}
+
+struct efi_freeable_range {
+	u64 start;
+	u64 end;
+};
+
+static struct efi_freeable_range *ranges_to_free;
+
+void __init efi_unmap_boot_services(void)
+{
+	struct efi_memory_map_data data = { 0 };
+	efi_memory_desc_t *md;
+	int num_entries = 0;
+	int idx = 0;
+	size_t sz;
+	void *new, *new_md;
+
+	/* Keep all regions for /sys/kernel/debug/efi */
+	if (efi_enabled(EFI_DBG))
+		return;
+
+	sz = sizeof(*ranges_to_free) * (efi.memmap.nr_map + 1);
+	ranges_to_free = kzalloc(sz, GFP_KERNEL);
+	if (!ranges_to_free) {
+		pr_err("Failed to allocate storage for freeable EFI regions\n");
+		return;
+	}
+
+	for_each_efi_memory_desc(md) {
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		size_t rm_size;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA) {
+			num_entries++;
+			continue;
+		}
+
+		/* Do not free, someone else owns it: */
+		if (md->attribute & EFI_MEMORY_RUNTIME) {
+			num_entries++;
+			continue;
+		}
+
+		/*
+		 * Before calling set_virtual_address_map(), EFI boot services
+		 * code/data regions were mapped as a quirk for buggy firmware.
+		 * Unmap them from efi_pgd before freeing them up.
+		 */
+		efi_unmap_pages(md);
+
+		/*
+		 * Nasty quirk: if all sub-1MB memory is used for boot
+		 * services, we can get here without having allocated the
+		 * real mode trampoline.  It's too late to hand boot services
+		 * memory back to the memblock allocator, so instead
+		 * try to manually allocate the trampoline if needed.
+		 *
+		 * I've seen this on a Dell XPS 13 9350 with firmware
+		 * 1.4.4 with SGX enabled booting Linux via Fedora 24's
+		 * grub2-efi on a hard disk.  (And no, I don't know why
+		 * this happened, but Linux should still try to boot rather
+		 * panicking early.)
+		 */
+		rm_size = real_mode_size_needed();
+		if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
+			set_real_mode_mem(start);
+			start += rm_size;
+			size -= rm_size;
+		}
+
+		/*
+		 * Don't free memory under 1M for two reasons:
+		 * - BIOS might clobber it
+		 * - Crash kernel needs it to be reserved
+		 */
+		if (start + size < SZ_1M)
+			continue;
+		if (start < SZ_1M) {
+			size -= (SZ_1M - start);
+			start = SZ_1M;
+		}
+
+		/*
+		 * With CONFIG_DEFERRED_STRUCT_PAGE_INIT parts of the memory
+		 * map are still not initialized and we can't reliably free
+		 * memory here.
+		 * Queue the ranges to free at a later point.
+		 */
+		ranges_to_free[idx].start = start;
+		ranges_to_free[idx].end = start + size;
+		idx++;
+	}
+
+	if (!num_entries)
+		return;
+
+	if (efi_memmap_alloc(num_entries, &data) != 0) {
+		pr_err("Failed to allocate new EFI memmap\n");
+		return;
+	}
+
+	new = memremap(data.phys_map, data.size, MEMREMAP_WB);
+	if (!new) {
+		pr_err("Failed to map new EFI memmap\n");
+		return;
+	}
+
+	/*
+	 * Build a new EFI memmap that excludes any boot services
+	 * regions that are not tagged EFI_MEMORY_RUNTIME, since those
+	 * regions have now been freed.
+	 */
+	new_md = new;
+	for_each_efi_memory_desc(md) {
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    (md->type == EFI_BOOT_SERVICES_CODE ||
+		     md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+
+		memcpy(new_md, md, efi.memmap.desc_size);
+		new_md += efi.memmap.desc_size;
+	}
+
+	memunmap(new);
+
+	if (efi_memmap_install(&data) != 0) {
+		pr_err("Could not install new EFI memmap\n");
+		return;
+	}
+}
+
+static int __init efi_free_boot_services(void)
+{
+	struct efi_freeable_range *range = ranges_to_free;
+	unsigned long freed = 0;
+
+	if (!ranges_to_free)
+		return 0;
+
+	while (range->start) {
+		void *start = phys_to_virt(range->start);
+		void *end = phys_to_virt(range->end);
+
+		free_reserved_area(start, end, -1, NULL);
+		freed += (end - start);
+		range++;
+	}
+	kfree(ranges_to_free);
+
+	if (freed)
+		pr_info("Freeing EFI boot services memory: %ldK\n", freed / SZ_1K);
+
+	return 0;
+}
+arch_initcall(efi_free_boot_services);
+
+/*
+ * A number of config table entries get remapped to virtual addresses
+ * after entering EFI virtual mode. However, the kexec kernel requires
+ * their physical addresses therefore we pass them via setup_data and
+ * correct those entries to their respective physical addresses here.
+ *
+ * Currently only handles smbios which is necessary for some firmware
+ * implementation.
+ */
+int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	if (nr_tables == 0)
+		return 0;
+
+	if (!efi_setup)
+		return 0;
+
+	if (!efi_enabled(EFI_64BIT))
+		return 0;
+
+	data = early_memremap(efi_setup, sizeof(*data));
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->smbios)
+		goto out_memremap;
+
+	sz = sizeof(efi_config_table_64_t);
+
+	p = tablep = early_memremap(tables, nr_tables * sz);
+	if (!p) {
+		pr_err("Could not map Configuration table!\n");
+		ret = -ENOMEM;
+		goto out_memremap;
+	}
+
+	for (i = 0; i < nr_tables; i++) {
+		efi_guid_t guid;
+
+		guid = ((efi_config_table_64_t *)p)->guid;
+
+		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = data->smbios;
+
+		/* Do not bother to play with mem attr table across kexec */
+		if (!efi_guidcmp(guid, EFI_MEMORY_ATTRIBUTES_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = EFI_INVALID_TABLE_ADDR;
+
+		p += sz;
+	}
+	early_memunmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_memunmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_runtime_supported()) {
+		pr_info("Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_memmap_unmap();
+	}
+}
+
+/*
+ * For most modern platforms the preferred method of powering off is via
+ * ACPI. However, there are some that are known to require the use of
+ * EFI runtime services and for which ACPI does not work at all.
+ *
+ * Using EFI is a last resort, to be used only if no other option
+ * exists.
+ */
+bool efi_reboot_required(void)
+{
+	if (!acpi_gbl_reduced_hardware)
+		return false;
+
+	efi_reboot_quirk_mode = EFI_RESET_WARM;
+	return true;
+}
+
+bool efi_poweroff_required(void)
+{
+	return acpi_gbl_reduced_hardware || acpi_no_s5;
+}
+
+#ifdef CONFIG_EFI_CAPSULE_QUIRK_QUARK_CSH
+
+static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff,
+				  size_t hdr_bytes)
+{
+	struct quark_security_header *csh = *pkbuff;
+
+	/* Only process data block that is larger than the security header */
+	if (hdr_bytes < sizeof(struct quark_security_header))
+		return 0;
+
+	if (csh->csh_signature != QUARK_CSH_SIGNATURE ||
+	    csh->headersize != QUARK_SECURITY_HEADER_SIZE)
+		return 1;
+
+	/* Only process data block if EFI header is included */
+	if (hdr_bytes < QUARK_SECURITY_HEADER_SIZE +
+			sizeof(efi_capsule_header_t))
+		return 0;
+
+	pr_debug("Quark security header detected\n");
+
+	if (csh->rsvd_next_header != 0) {
+		pr_err("multiple Quark security headers not supported\n");
+		return -EINVAL;
+	}
+
+	*pkbuff += csh->headersize;
+	cap_info->total_size = csh->headersize;
+
+	/*
+	 * Update the first page pointer to skip over the CSH header.
+	 */
+	cap_info->phys[0] += csh->headersize;
+
+	/*
+	 * cap_info->capsule should point at a virtual mapping of the entire
+	 * capsule, starting at the capsule header. Our image has the Quark
+	 * security header prepended, so we cannot rely on the default vmap()
+	 * mapping created by the generic capsule code.
+	 * Given that the Quark firmware does not appear to care about the
+	 * virtual mapping, let's just point cap_info->capsule at our copy
+	 * of the capsule header.
+	 */
+	cap_info->capsule = &cap_info->header;
+
+	return 1;
+}
+
+static const struct x86_cpu_id efi_capsule_quirk_ids[] = {
+	X86_MATCH_VFM(INTEL_QUARK_X1000, &qrk_capsule_setup_info),
+	{ }
+};
+
+int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
+			   size_t hdr_bytes)
+{
+	int (*quirk_handler)(struct capsule_info *, void **, size_t);
+	const struct x86_cpu_id *id;
+	int ret;
+
+	if (hdr_bytes < sizeof(efi_capsule_header_t))
+		return 0;
+
+	cap_info->total_size = 0;
+
+	id = x86_match_cpu(efi_capsule_quirk_ids);
+	if (id) {
+		/*
+		 * The quirk handler is supposed to return
+		 *  - a value > 0 if the setup should continue, after advancing
+		 *    kbuff as needed
+		 *  - 0 if not enough hdr_bytes are available yet
+		 *  - a negative error code otherwise
+		 */
+		quirk_handler = (typeof(quirk_handler))id->driver_data;
+		ret = quirk_handler(cap_info, &kbuff, hdr_bytes);
+		if (ret <= 0)
+			return ret;
+	}
+
+	memcpy(&cap_info->header, kbuff, sizeof(cap_info->header));
+
+	cap_info->total_size += cap_info->header.imagesize;
+
+	return __efi_capsule_setup_info(cap_info);
+}
+
+#endif
+
+/*
+ * If any access by any efi runtime service causes a page fault, then,
+ * 1. If it's efi_reset_system(), reboot through BIOS.
+ * 2. If any other efi runtime service, then
+ *    a. Return error status to the efi caller process.
+ *    b. Disable EFI Runtime Services forever and
+ *    c. Freeze efi_rts_wq and schedule new process.
+ *
+ * @return: Returns, if the page fault is not handled. This function
+ * will never return if the page fault is handled successfully.
+ */
+void efi_crash_gracefully_on_page_fault(unsigned long phys_addr,
+					const struct pt_regs *regs)
+{
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	/*
+	 * If we get an interrupt/NMI while processing an EFI runtime service
+	 * then this is a regular OOPS, not an EFI failure.
+	 */
+	if (!in_task())
+		return;
+
+	/*
+	 * Make sure that an efi runtime service caused the page fault.
+	 * READ_ONCE() because we might be OOPSing in a different thread,
+	 * and we don't want to trip KTSAN while trying to OOPS.
+	 */
+	if (READ_ONCE(efi_rts_work.efi_rts_id) == EFI_NONE ||
+	    current_work() != &efi_rts_work.work)
+		return;
+
+	/*
+	 * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
+	 * page faulting on these addresses isn't expected.
+	 */
+	if (phys_addr <= 0x0fff)
+		return;
+
+	/*
+	 * Print stack trace as it might be useful to know which EFI Runtime
+	 * Service is buggy.
+	 */
+	WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n",
+	     phys_addr);
+
+	/*
+	 * Buggy efi_reset_system() is handled differently from other EFI
+	 * Runtime Services as it doesn't use efi_rts_wq. Although,
+	 * native_machine_emergency_restart() says that machine_real_restart()
+	 * could fail, it's better not to complicate this fault handler
+	 * because this case occurs *very* rarely and hence could be improved
+	 * on a need by basis.
+	 */
+	if (efi_rts_work.efi_rts_id == EFI_RESET_SYSTEM) {
+		pr_info("efi_reset_system() buggy! Reboot through BIOS\n");
+		machine_real_restart(MRR_BIOS);
+		return;
+	}
+
+	/*
+	 * The API does not permit entering a kernel mode FPU section with
+	 * interrupts enabled and leaving it with interrupts disabled.  So
+	 * re-enable interrupts now if they were enabled when the page fault
+	 * occurred.
+	 */
+	local_irq_restore(regs->flags);
+
+	/*
+	 * Before calling EFI Runtime Service, the kernel has switched the
+	 * calling process to efi_mm. Hence, switch back to task_mm.
+	 */
+	arch_efi_call_virt_teardown();
+
+	/* Signal error status to the efi caller process */
+	efi_rts_work.status = EFI_ABORTED;
+	complete(&efi_rts_work.efi_rts_comp);
+
+	clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+	pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n");
+
+	/*
+	 * Call schedule() in an infinite loop, so that any spurious wake ups
+	 * will never run efi_rts_wq again.
+	 */
+	for (;;) {
+		set_current_state(TASK_IDLE);
+		schedule();
+	}
+}

linux-7.2.3/arch/x86/platform/efi/runtime-map.c

@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+
+#include <asm/efi.h>
+#include <asm/setup.h>
+
+struct efi_runtime_map_entry {
+	efi_memory_desc_t md;
+	struct kobject kobj;   /* kobject for each entry */
+};
+
+static struct efi_runtime_map_entry **map_entries;
+
+struct map_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf);
+};
+
+static inline struct map_attribute *to_map_attr(struct attribute *attr)
+{
+	return container_of(attr, struct map_attribute, attr);
+}
+
+static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type);
+}
+
+#define EFI_RUNTIME_FIELD(var) entry->md.var
+
+#define EFI_RUNTIME_U64_ATTR_SHOW(name) \
+static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \
+{ \
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \
+}
+
+EFI_RUNTIME_U64_ATTR_SHOW(phys_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(virt_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(num_pages);
+EFI_RUNTIME_U64_ATTR_SHOW(attribute);
+
+static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct efi_runtime_map_entry, kobj);
+}
+
+static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct efi_runtime_map_entry *entry = to_map_entry(kobj);
+	struct map_attribute *map_attr = to_map_attr(attr);
+
+	return map_attr->show(entry, buf);
+}
+
+static struct map_attribute map_type_attr = __ATTR_RO_MODE(type, 0400);
+static struct map_attribute map_phys_addr_attr = __ATTR_RO_MODE(phys_addr, 0400);
+static struct map_attribute map_virt_addr_attr = __ATTR_RO_MODE(virt_addr, 0400);
+static struct map_attribute map_num_pages_attr = __ATTR_RO_MODE(num_pages, 0400);
+static struct map_attribute map_attribute_attr = __ATTR_RO_MODE(attribute, 0400);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&map_type_attr.attr,
+	&map_phys_addr_attr.attr,
+	&map_virt_addr_attr.attr,
+	&map_num_pages_attr.attr,
+	&map_attribute_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(def);
+
+static const struct sysfs_ops map_attr_ops = {
+	.show = map_attr_show,
+};
+
+static void map_release(struct kobject *kobj)
+{
+	struct efi_runtime_map_entry *entry;
+
+	entry = to_map_entry(kobj);
+	kfree(entry);
+}
+
+static const struct kobj_type __refconst map_ktype = {
+	.sysfs_ops	= &map_attr_ops,
+	.default_groups	= def_groups,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr,
+			    efi_memory_desc_t *md)
+{
+	int ret;
+	struct efi_runtime_map_entry *entry;
+
+	if (!map_kset) {
+		map_kset = kset_create_and_add("runtime-map", NULL, kobj);
+		if (!map_kset)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	entry = kzalloc_obj(*entry);
+	if (!entry) {
+		kset_unregister(map_kset);
+		map_kset = NULL;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	memcpy(&entry->md, md, sizeof(efi_memory_desc_t));
+
+	kobject_init(&entry->kobj, &map_ktype);
+	entry->kobj.kset = map_kset;
+	ret = kobject_add(&entry->kobj, NULL, "%d", nr);
+	if (ret) {
+		kobject_put(&entry->kobj);
+		kset_unregister(map_kset);
+		map_kset = NULL;
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+int efi_get_runtime_map_size(void)
+{
+	return efi.memmap.nr_map * efi.memmap.desc_size;
+}
+
+int efi_get_runtime_map_desc_size(void)
+{
+	return efi.memmap.desc_size;
+}
+
+int efi_runtime_map_copy(void *buf, size_t bufsz)
+{
+	size_t sz = efi_get_runtime_map_size();
+
+	if (sz > bufsz)
+		sz = bufsz;
+
+	memcpy(buf, efi.memmap.map, sz);
+	return 0;
+}
+
+static int __init efi_runtime_map_init(void)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+	efi_memory_desc_t *md;
+
+	if (!efi_enabled(EFI_MEMMAP) || !efi_kobj)
+		return 0;
+
+	map_entries = kzalloc_objs(entry, efi.memmap.nr_map);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	i = 0;
+	for_each_efi_memory_desc(md) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i, md);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto out_add_entry;
+		}
+		*(map_entries + i++) = entry;
+	}
+
+	return 0;
+out_add_entry:
+	for (j = i - 1; j >= 0; j--) {
+		entry = *(map_entries + j);
+		kobject_put(&entry->kobj);
+	}
+out:
+	return ret;
+}
+subsys_initcall_sync(efi_runtime_map_init);