Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Thomas Gleixner:
 "Assorted updates to kexec/kdump:

   - Proper kexec support for 4/5-level paging and jumping from a
     5-level to a 4-level paging kernel.

   - Make the EFI support for kexec/kdump more robust

   - Enforce that the GDT is properly aligned instead of getting the
     alignment by chance"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kdump/64: Restrict kdump kernel reservation to <64TB
  x86/kexec/64: Prevent kexec from 5-level paging to a 4-level only kernel
  x86/boot: Add xloadflags bits to check for 5-level paging support
  x86/boot: Make the GDT 8-byte aligned
  x86/kexec: Add the ACPI NVS region to the ident map
  x86/boot: Call get_rsdp_addr() after console_init()
  Revert "x86/boot: Disable RSDP parsing temporarily"
  x86/boot: Use efi_setup_data for searching RSDP on kexec-ed kernels
  x86/kexec: Add the EFI system tables and ACPI tables to the ident map

3 files changed, 104 insertions, 3 deletions

diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index f03237e3f192..347fc0be76b2 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -319,6 +319,11 @@ static int bzImage64_probe(const char *buf, unsigned long len)
 		return ret;
 	}
 
+	if (!(header->xloadflags & XLF_5LEVEL) && pgtable_l5_enabled()) {
+		pr_err("bzImage cannot handle 5-level paging mode.\n");
+		return ret;
+	}
+
 	/* I've got a bzImage */
 	pr_debug("It's a relocatable bzImage64\n");
 	ret = 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index d7be2376ac0b..9184037aec62 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/suspend.h>
 #include <linux/vmalloc.h>
+#include <linux/efi.h>
 
 #include <asm/init.h>
 #include <asm/pgtable.h>
@@ -27,6 +28,55 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 
+#ifdef CONFIG_ACPI
+/*
+ * Used while adding mapping for ACPI tables.
+ * Can be reused when other iomem regions need be mapped
+ */
+struct init_pgtable_data {
+	struct x86_mapping_info *info;
+	pgd_t *level4p;
+};
+
+static int mem_region_callback(struct resource *res, void *arg)
+{
+	struct init_pgtable_data *data = arg;
+	unsigned long mstart, mend;
+
+	mstart = res->start;
+	mend = mstart + resource_size(res) - 1;
+
+	return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend);
+}
+
+static int
+map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
+{
+	struct init_pgtable_data data;
+	unsigned long flags;
+	int ret;
+
+	data.info = info;
+	data.level4p = level4p;
+	flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1,
+				  &data, mem_region_callback);
+	if (ret && ret != -EINVAL)
+		return ret;
+
+	/* ACPI tables could be located in ACPI Non-volatile Storage region */
+	ret = walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1,
+				  &data, mem_region_callback);
+	if (ret && ret != -EINVAL)
+		return ret;
+
+	return 0;
+}
+#else
+static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
+#endif
+
 #ifdef CONFIG_KEXEC_FILE
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 		&kexec_bzImage64_ops,
@@ -34,6 +84,31 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 };
 #endif
 
+static int
+map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
+{
+#ifdef CONFIG_EFI
+	unsigned long mstart, mend;
+
+	if (!efi_enabled(EFI_BOOT))
+		return 0;
+
+	mstart = (boot_params.efi_info.efi_systab |
+			((u64)boot_params.efi_info.efi_systab_hi<<32));
+
+	if (efi_enabled(EFI_64BIT))
+		mend = mstart + sizeof(efi_system_table_64_t);
+	else
+		mend = mstart + sizeof(efi_system_table_32_t);
+
+	if (!mstart)
+		return 0;
+
+	return kernel_ident_mapping_init(info, level4p, mstart, mend);
+#endif
+	return 0;
+}
+
 static void free_transition_pgtable(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.p4d);
@@ -157,6 +232,18 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 			return result;
 	}
 
+	/*
+	 * Prepare EFI systab and ACPI tables for kexec kernel since they are
+	 * not covered by pfn_mapped.
+	 */
+	result = map_efi_systab(&info, level4p);
+	if (result)
+		return result;
+
+	result = map_acpi_tables(&info, level4p);
+	if (result)
+		return result;
+
 	return init_transition_pgtable(image, level4p);
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 08a5f4a131f5..dcbdf54fb5c1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -453,15 +453,24 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 #define CRASH_ALIGN		SZ_16M
 
 /*
- * Keep the crash kernel below this limit.  On 32 bits earlier kernels
- * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * Keep the crash kernel below this limit.
+ *
+ * On 32 bits earlier kernels would limit the kernel to the low 512 MiB
+ * due to mapping restrictions.
+ *
+ * On 64bit, kdump kernel need be restricted to be under 64TB, which is
+ * the upper limit of system RAM in 4-level paing mode. Since the kdump
+ * jumping could be from 5-level to 4-level, the jumping will fail if
+ * kernel is put above 64TB, and there's no way to detect the paging mode
+ * of the kernel which will be loaded for dumping during the 1st kernel
+ * bootup.
  */
 #ifdef CONFIG_X86_32
 # define CRASH_ADDR_LOW_MAX	SZ_512M
 # define CRASH_ADDR_HIGH_MAX	SZ_512M
 #else
 # define CRASH_ADDR_LOW_MAX	SZ_4G
-# define CRASH_ADDR_HIGH_MAX	MAXMEM
+# define CRASH_ADDR_HIGH_MAX	SZ_64T
 #endif
 
 static int __init reserve_crashkernel_low(void)