x86/efi: Pass necessary EFI data for kexec via setup_data

Add a new setup_data type SETUP_EFI for kexec use.  Passing the saved
fw_vendor, runtime, config tables and EFI runtime mappings.

When entering virtual mode, directly mapping the EFI runtime regions
which we passed in previously. And skip the step to call
SetVirtualAddressMap().

Specially for HP z420 workstation we need save the smbios physical
address.  The kernel boot sequence proceeds in the following order.
Step 2 requires efi.smbios to be the physical address.  However, I found
that on HP z420 EFI system table has a virtual address of SMBIOS in step
1.  Hence, we need set it back to the physical address with the smbios
in efi_setup_data.  (When it is still the physical address, it simply
sets the same value.)

1. efi_init() - Set efi.smbios from EFI system table
2. dmi_scan_machine() - Temporary map efi.smbios to access SMBIOS table
3. efi_enter_virtual_mode() - Map EFI ranges

Tested on ovmf+qemu, lenovo thinkpad, a dell laptop and an
HP z420 workstation.

Signed-off-by: Dave Young <dyoung@redhat.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

arch/x86/include/asm/efi.h

@@ -133,6 +133,18 @@ extern void efi_sync_low_kernel_mappings(void);
 extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
 
+struct efi_setup_data {
+	u64 fw_vendor;
+	u64 runtime;
+	u64 tables;
+	u64 smbios;
+	u64 reserved[8];
+};
+
+extern u64 efi_setup;
+extern u32 efi_data_len;
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
+
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)

arch/x86/include/uapi/asm/bootparam.h

@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF

arch/x86/kernel/setup.c

@@ -447,6 +447,9 @@ static void __init parse_setup_data(void)
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_EFI:
+			parse_efi_setup(pa_data, data_len);
+			break;
 		default:
 			break;
 		}

arch/x86/platform/efi/efi.c

@@ -78,6 +78,8 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 
 static void *efi_runtime_map;
 static int nr_efi_runtime_map;
+u64 efi_setup;		/* efi setup_data physical address */
+u32 efi_data_len;	/* efi setup_data payload length */
 
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
@@ -115,7 +117,6 @@ static int __init setup_storage_paranoia(char *arg)
 }
 early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 
-
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	unsigned long flags;
@@ -494,18 +495,27 @@ static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
+		struct efi_setup_data *data = NULL;
 		u64 tmp = 0;
 
+		if (efi_setup) {
+			data = early_memremap(efi_setup, sizeof(*data));
+			if (!data)
+				return -ENOMEM;
+		}
 		systab64 = early_ioremap((unsigned long)phys,
 					 sizeof(*systab64));
 		if (systab64 == NULL) {
 			pr_err("Couldn't map the system table!\n");
+			if (data)
+				early_iounmap(data, sizeof(*data));
 			return -ENOMEM;
 		}
 
 		efi_systab.hdr = systab64->hdr;
-		efi_systab.fw_vendor = systab64->fw_vendor;
-		tmp |= systab64->fw_vendor;
+		efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
+					      systab64->fw_vendor;
+		tmp |= data ? data->fw_vendor : systab64->fw_vendor;
 		efi_systab.fw_revision = systab64->fw_revision;
 		efi_systab.con_in_handle = systab64->con_in_handle;
 		tmp |= systab64->con_in_handle;
@@ -519,15 +529,20 @@ static int __init efi_systab_init(void *phys)
 		tmp |= systab64->stderr_handle;
 		efi_systab.stderr = systab64->stderr;
 		tmp |= systab64->stderr;
-		efi_systab.runtime = (void *)(unsigned long)systab64->runtime;
-		tmp |= systab64->runtime;
+		efi_systab.runtime = data ?
+				     (void *)(unsigned long)data->runtime :
+				     (void *)(unsigned long)systab64->runtime;
+		tmp |= data ? data->runtime : systab64->runtime;
 		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
 		tmp |= systab64->boottime;
 		efi_systab.nr_tables = systab64->nr_tables;
-		efi_systab.tables = systab64->tables;
-		tmp |= systab64->tables;
+		efi_systab.tables = data ? (unsigned long)data->tables :
+					   systab64->tables;
+		tmp |= data ? data->tables : systab64->tables;
 
 		early_iounmap(systab64, sizeof(*systab64));
+		if (data)
+			early_iounmap(data, sizeof(*data));
 #ifdef CONFIG_X86_32
 		if (tmp >> 32) {
 			pr_err("EFI data located above 4GB, disabling EFI.\n");
@@ -631,6 +646,71 @@ static int __init efi_memmap_init(void)
 	return 0;
 }
 
+/*
+ * 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.
+ */
+static int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	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 < efi.systab->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;
+		p += sz;
+	}
+	early_iounmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_iounmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
+static void get_nr_runtime_map(void)
+{
+	if (!efi_setup)
+		return;
+
+	nr_efi_runtime_map = (efi_data_len - sizeof(struct efi_setup_data)) /
+			     sizeof(efi_memory_desc_t);
+}
+
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -638,6 +718,7 @@ void __init efi_init(void)
 	int i = 0;
 	void *tmp;
 
+	get_nr_runtime_map();
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
@@ -676,6 +757,9 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
+	if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables))
+		return;
+
 	if (efi_config_init(arch_tables))
 		return;
 
@@ -860,6 +944,23 @@ out:
 	return -ENOMEM;
 }
 
+/*
+ * 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.
+ */
+static void __init efi_map_regions_fixed(void)
+{
+	void *p;
+	efi_memory_desc_t *md;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+		get_systab_virt_addr(md);
+	}
+
+}
+
 /*
  * Map efi memory ranges for runtime serivce and update new_memmap with virtual
  * addresses.
@@ -914,6 +1015,10 @@ out:
  * so that we're in a different address space when calling a runtime
  * function. For function arguments passing we do copy the PGDs of the
  * kernel page table into ->trampoline_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.
  */
 void __init efi_enter_virtual_mode(void)
 {
@@ -932,12 +1037,15 @@ void __init efi_enter_virtual_mode(void)
 		return;
 	}
 
-	efi_merge_regions();
-
-	new_memmap = efi_map_regions(&count);
-	if (!new_memmap) {
-		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
-		return;
+	if (efi_setup) {
+		efi_map_regions_fixed();
+	} else {
+		efi_merge_regions();
+		new_memmap = efi_map_regions(&count);
+		if (!new_memmap) {
+			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+			return;
+		}
 	}
 
 	err = save_runtime_map();
@@ -949,16 +1057,18 @@ void __init efi_enter_virtual_mode(void)
 	efi_setup_page_tables();
 	efi_sync_low_kernel_mappings();
 
-	status = phys_efi_set_virtual_address_map(
-		memmap.desc_size * count,
-		memmap.desc_size,
-		memmap.desc_version,
-		(efi_memory_desc_t *)__pa(new_memmap));
-
-	if (status != EFI_SUCCESS) {
-		pr_alert("Unable to switch EFI into virtual mode "
-			 "(status=%lx)!\n", status);
-		panic("EFI call to SetVirtualAddressMap() failed!");
+	if (!efi_setup) {
+		status = phys_efi_set_virtual_address_map(
+			memmap.desc_size * count,
+			memmap.desc_size,
+			memmap.desc_version,
+			(efi_memory_desc_t *)__pa(new_memmap));
+
+		if (status != EFI_SUCCESS) {
+			pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+				 status);
+			panic("EFI call to SetVirtualAddressMap() failed!");
+		}
 	}
 
 	/*
@@ -993,8 +1103,6 @@ void __init efi_enter_virtual_mode(void)
 			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
 			 EFI_VARIABLE_RUNTIME_ACCESS,
 			 0, NULL);
-
-	return;
 }
 
 /*

arch/x86/platform/efi/efi_32.c

@@ -48,6 +48,7 @@ void __init efi_map_region(efi_memory_desc_t *md)
 }
 
 void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
 
 void efi_call_phys_prelog(void)
 {

arch/x86/platform/efi/efi_64.c

@@ -228,3 +228,9 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 
 	return (void __iomem *)__va(phys_addr);
 }
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+	efi_data_len = data_len - sizeof(struct setup_data);
+}