1 files changed, 67 insertions, 156 deletions

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index a552a08a1741..a65c2d5b9e7b 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -12,6 +12,7 @@
 #include <linux/efi.h>
 #include <linux/fwnode.h>
 #include <linux/init.h>
+#include <linux/kexec_handover.h>
 #include <linux/memblock.h>
 #include <linux/mm_types.h>
 #include <linux/of.h>
@@ -22,6 +23,8 @@
 
 #include <asm/efi.h>
 
+unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
+
 static int __init is_memory(efi_memory_desc_t *md)
 {
 	if (md->attribute & (EFI_MEMORY_WB|EFI_MEMORY_WT|EFI_MEMORY_WC))
@@ -51,37 +54,38 @@ static phys_addr_t __init efi_to_phys(unsigned long addr)
 	return addr;
 }
 
-static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR;
-static __initdata unsigned long cpu_state_table = EFI_INVALID_TABLE_ADDR;
+extern __weak const efi_config_table_type_t efi_arch_tables[];
 
-static const efi_config_table_type_t arch_tables[] __initconst = {
-	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table},
-	{LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table},
-	{}
-};
+/*
+ * x86 defines its own screen_info and uses it even without EFI,
+ * everything else can get it from here.
+ */
+#if !defined(CONFIG_X86) && (defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON))
+struct screen_info screen_info __section(".data");
+EXPORT_SYMBOL_GPL(screen_info);
+#endif
 
 static void __init init_screen_info(void)
 {
 	struct screen_info *si;
 
-	if (IS_ENABLED(CONFIG_ARM) &&
-	    screen_info_table != EFI_INVALID_TABLE_ADDR) {
-		si = early_memremap_ro(screen_info_table, sizeof(*si));
+	if (screen_info_table != EFI_INVALID_TABLE_ADDR) {
+		si = early_memremap(screen_info_table, sizeof(*si));
 		if (!si) {
 			pr_err("Could not map screen_info config table\n");
 			return;
 		}
 		screen_info = *si;
+		memset(si, 0, sizeof(*si));
 		early_memunmap(si, sizeof(*si));
 
-		/* dummycon on ARM needs non-zero values for columns/lines */
-		screen_info.orig_video_cols = 80;
-		screen_info.orig_video_lines = 25;
-	}
+		if (memblock_is_map_memory(screen_info.lfb_base))
+			memblock_mark_nomap(screen_info.lfb_base,
+					    screen_info.lfb_size);
 
-	if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI &&
-	    memblock_is_map_memory(screen_info.lfb_base))
-		memblock_mark_nomap(screen_info.lfb_base, screen_info.lfb_size);
+		if (IS_ENABLED(CONFIG_EFI_EARLYCON))
+			efi_earlycon_reprobe();
+	}
 }
 
 static int __init uefi_init(u64 efi_system_table)
@@ -101,7 +105,7 @@ static int __init uefi_init(u64 efi_system_table)
 	if (IS_ENABLED(CONFIG_64BIT))
 		set_bit(EFI_64BIT, &efi.flags);
 
-	retval = efi_systab_check_header(&systab->hdr, 2);
+	retval = efi_systab_check_header(&systab->hdr);
 	if (retval)
 		goto out;
 
@@ -119,8 +123,7 @@ static int __init uefi_init(u64 efi_system_table)
 		goto out;
 	}
 	retval = efi_config_parse_tables(config_tables, systab->nr_tables,
-					 IS_ENABLED(CONFIG_ARM) ? arch_tables
-								: NULL);
+					 efi_arch_tables);
 
 	early_memunmap(config_tables, table_size);
 out:
@@ -142,15 +145,6 @@ static __init int is_usable_memory(efi_memory_desc_t *md)
 	case EFI_CONVENTIONAL_MEMORY:
 	case EFI_PERSISTENT_MEMORY:
 		/*
-		 * Special purpose memory is 'soft reserved', which means it
-		 * is set aside initially, but can be hotplugged back in or
-		 * be assigned to the dax driver after boot.
-		 */
-		if (efi_soft_reserve_enabled() &&
-		    (md->attribute & EFI_MEMORY_SP))
-			return false;
-
-		/*
 		 * According to the spec, these regions are no longer reserved
 		 * after calling ExitBootServices(). However, we can only use
 		 * them as System RAM if they can be mapped writeback cacheable.
@@ -171,12 +165,32 @@ static __init void reserve_regions(void)
 		pr_info("Processing EFI memory map:\n");
 
 	/*
-	 * Discard memblocks discovered so far: if there are any at this
-	 * point, they originate from memory nodes in the DT, and UEFI
-	 * uses its own memory map instead.
+	 * Discard memblocks discovered so far except for KHO scratch
+	 * regions. Most memblocks at this point originate from memory nodes
+	 * in the DT and UEFI uses its own memory map instead. However, if
+	 * KHO is enabled, scratch regions, which are good known memory
+	 * must be preserved.
 	 */
 	memblock_dump_all();
-	memblock_remove(0, PHYS_ADDR_MAX);
+
+	if (is_kho_boot()) {
+		struct memblock_region *r;
+
+		/* Remove all non-KHO regions */
+		for_each_mem_region(r) {
+			if (!memblock_is_kho_scratch(r)) {
+				memblock_remove(r->base, r->size);
+				r--;
+			}
+		}
+	} else {
+		/*
+		 * KHO is disabled. Discard memblocks discovered so far:
+		 * if there are any at this point, they originate from memory
+		 * nodes in the DT, and UEFI uses its own memory map instead.
+		 */
+		memblock_remove(0, PHYS_ADDR_MAX);
+	}
 
 	for_each_efi_memory_desc(md) {
 		paddr = md->phys_addr;
@@ -194,6 +208,16 @@ static __init void reserve_regions(void)
 		size = npages << PAGE_SHIFT;
 
 		if (is_memory(md)) {
+			/*
+			 * Special purpose memory is 'soft reserved', which
+			 * means it is set aside initially. Don't add a memblock
+			 * for it now so that it can be hotplugged back in or
+			 * be assigned to the dax driver after boot.
+			 */
+			if (efi_soft_reserve_enabled() &&
+			    (md->attribute & EFI_MEMORY_SP))
+				continue;
+
 			early_init_dt_add_memory_arch(paddr, size);
 
 			if (!is_usable_memory(md))
@@ -235,133 +259,20 @@ void __init efi_init(void)
 	}
 
 	reserve_regions();
+	/*
+	 * For memblock manipulation, the cap should come after the memblock_add().
+	 * And now, memblock is fully populated, it is time to do capping.
+	 */
+	early_init_dt_check_for_usable_mem_range();
+	efi_find_mirror();
 	efi_esrt_init();
 	efi_mokvar_table_init();
 
 	memblock_reserve(data.phys_map & PAGE_MASK,
 			 PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
 
-	init_screen_info();
-
-#ifdef CONFIG_ARM
-	/* ARM does not permit early mappings to persist across paging_init() */
-	efi_memmap_unmap();
-
-	if (cpu_state_table != EFI_INVALID_TABLE_ADDR) {
-		struct efi_arm_entry_state *state;
-		bool dump_state = true;
-
-		state = early_memremap_ro(cpu_state_table,
-					  sizeof(struct efi_arm_entry_state));
-		if (state == NULL) {
-			pr_warn("Unable to map CPU entry state table.\n");
-			return;
-		}
-
-		if ((state->sctlr_before_ebs & 1) == 0)
-			pr_warn(FW_BUG "EFI stub was entered with MMU and Dcache disabled, please fix your firmware!\n");
-		else if ((state->sctlr_after_ebs & 1) == 0)
-			pr_warn(FW_BUG "ExitBootServices() returned with MMU and Dcache disabled, please fix your firmware!\n");
-		else
-			dump_state = false;
-
-		if (dump_state || efi_enabled(EFI_DBG)) {
-			pr_info("CPSR at EFI stub entry        : 0x%08x\n", state->cpsr_before_ebs);
-			pr_info("SCTLR at EFI stub entry       : 0x%08x\n", state->sctlr_before_ebs);
-			pr_info("CPSR after ExitBootServices() : 0x%08x\n", state->cpsr_after_ebs);
-			pr_info("SCTLR after ExitBootServices(): 0x%08x\n", state->sctlr_after_ebs);
-		}
-		early_memunmap(state, sizeof(struct efi_arm_entry_state));
-	}
-#endif
-}
-
-static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
-{
-	u64 fb_base = screen_info.lfb_base;
-
-	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
-		fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32;
-
-	return fb_base >= range->cpu_addr &&
-	       fb_base < (range->cpu_addr + range->size);
-}
-
-static struct device_node *find_pci_overlap_node(void)
-{
-	struct device_node *np;
-
-	for_each_node_by_type(np, "pci") {
-		struct of_pci_range_parser parser;
-		struct of_pci_range range;
-		int err;
-
-		err = of_pci_range_parser_init(&parser, np);
-		if (err) {
-			pr_warn("of_pci_range_parser_init() failed: %d\n", err);
-			continue;
-		}
-
-		for_each_of_pci_range(&parser, &range)
-			if (efifb_overlaps_pci_range(&range))
-				return np;
-	}
-	return NULL;
-}
-
-/*
- * If the efifb framebuffer is backed by a PCI graphics controller, we have
- * to ensure that this relation is expressed using a device link when
- * running in DT mode, or the probe order may be reversed, resulting in a
- * resource reservation conflict on the memory window that the efifb
- * framebuffer steals from the PCIe host bridge.
- */
-static int efifb_add_links(struct fwnode_handle *fwnode)
-{
-	struct device_node *sup_np;
-
-	sup_np = find_pci_overlap_node();
-
-	/*
-	 * If there's no PCI graphics controller backing the efifb, we are
-	 * done here.
-	 */
-	if (!sup_np)
-		return 0;
-
-	fwnode_link_add(fwnode, of_fwnode_handle(sup_np));
-	of_node_put(sup_np);
-
-	return 0;
-}
-
-static const struct fwnode_operations efifb_fwnode_ops = {
-	.add_links = efifb_add_links,
-};
-
-static struct fwnode_handle efifb_fwnode;
-
-static int __init register_gop_device(void)
-{
-	struct platform_device *pd;
-	int err;
-
-	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
-		return 0;
-
-	pd = platform_device_alloc("efi-framebuffer", 0);
-	if (!pd)
-		return -ENOMEM;
-
-	if (IS_ENABLED(CONFIG_PCI)) {
-		fwnode_init(&efifb_fwnode, &efifb_fwnode_ops);
-		pd->dev.fwnode = &efifb_fwnode;
-	}
-
-	err = platform_device_add_data(pd, &screen_info, sizeof(screen_info));
-	if (err)
-		return err;
-
-	return platform_device_add(pd);
+	if (IS_ENABLED(CONFIG_X86) ||
+	    IS_ENABLED(CONFIG_SYSFB) ||
+	    IS_ENABLED(CONFIG_EFI_EARLYCON))
+		init_screen_info();
 }
-subsys_initcall(register_gop_device);