x86/efi: Move all workarounds to a separate file quirks.c

Currently, it's difficult to find all the workarounds that are
applied when running on EFI, because they're littered throughout
various code paths. This change moves all of them into a separate
file with the hope that it will be come the single location for all
our well documented quirks.

Signed-off-by: Saurabh Tangri <saurabh.tangri@intel.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

arch/x86/include/asm/efi.h

@@ -104,6 +104,8 @@ extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
 extern void __init efi_dump_pagetable(void);
 extern void __init efi_apply_memmap_quirks(void);
+extern int __init efi_reuse_config(u64 tables, int nr_tables);
+extern void efi_delete_dummy_variable(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;

arch/x86/platform/efi/Makefile

@@ -1,4 +1,4 @@
-obj-$(CONFIG_EFI) 		+= efi.o efi_$(BITS).o efi_stub_$(BITS).o
+obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
 obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o

arch/x86/platform/efi/efi.c

@@ -56,13 +56,6 @@
 
 #define EFI_DEBUG
 
-#define EFI_MIN_RESERVE 5120
-
-#define EFI_DUMMY_GUID \
-	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
-
-static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
-
 struct efi_memory_map memmap;
 
 static struct efi efi_phys __initdata;
@@ -95,15 +88,6 @@ static int __init setup_add_efi_memmap(char *arg)
 }
 early_param("add_efi_memmap", setup_add_efi_memmap);
 
-static bool efi_no_storage_paranoia;
-
-static int __init setup_storage_paranoia(char *arg)
-{
-	efi_no_storage_paranoia = true;
-	return 0;
-}
-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;
@@ -392,37 +376,6 @@ static void __init print_efi_memmap(void)
 #endif  /*  EFI_DEBUG  */
 }
 
-void __init efi_reserve_boot_services(void)
-{
-	void *p;
-
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 start = md->phys_addr;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-
-		if (md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		/* Only reserve where possible:
-		 * - Not within any already allocated areas
-		 * - Not over any memory area (really needed, if above?)
-		 * - Not within any part of the kernel
-		 * - Not the bios reserved area
-		*/
-		if ((start + size > __pa_symbol(_text)
-				&& start <= __pa_symbol(_end)) ||
-			!e820_all_mapped(start, start+size, E820_RAM) ||
-			memblock_is_region_reserved(start, size)) {
-			/* Could not reserve, skip it */
-			md->num_pages = 0;
-			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
-				     start, start+size-1);
-		} else
-			memblock_reserve(start, size);
-	}
-}
-
 void __init efi_unmap_memmap(void)
 {
 	clear_bit(EFI_MEMMAP, &efi.flags);
@@ -432,29 +385,6 @@ void __init efi_unmap_memmap(void)
 	}
 }
 
-void __init efi_free_boot_services(void)
-{
-	void *p;
-
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
-
-		if (md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-
-		/* Could not reserve boot area */
-		if (!size)
-			continue;
-
-		free_bootmem_late(start, size);
-	}
-
-	efi_unmap_memmap();
-}
-
 static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
@@ -649,62 +579,6 @@ 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;
-}
-
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -1057,11 +931,7 @@ static void __init kexec_enter_virtual_mode(void)
 		runtime_code_page_mkexec();
 
 	/* clean DUMMY object */
-	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi_delete_dummy_variable();
 #endif
 }
 
@@ -1179,11 +1049,7 @@ static void __init __efi_enter_virtual_mode(void)
 	free_pages((unsigned long)new_memmap, pg_shift);
 
 	/* clean DUMMY object */
-	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi_delete_dummy_variable();
 }
 
 void __init efi_enter_virtual_mode(void)
@@ -1230,86 +1096,6 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	return 0;
 }
 
-/*
- * 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)
-{
-	efi_status_t status;
-	u64 storage_size, remaining_size, max_size;
-
-	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
-		return 0;
-
-	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_ATOMIC);
-
-		if (!dummy)
-			return EFI_OUT_OF_RESOURCES;
-
-		status = efi.set_variable(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.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-					 EFI_VARIABLE_NON_VOLATILE |
-					 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-					 EFI_VARIABLE_RUNTIME_ACCESS,
-					 0, dummy);
-		}
-
-		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);
-
 static int __init parse_efi_cmdline(char *str)
 {
 	if (*str == '=')
@@ -1321,22 +1107,3 @@ static int __init parse_efi_cmdline(char *str)
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
-
-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("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
-
-	/*
-	 * UV doesn't support the new EFI pagetable mapping yet.
-	 */
-	if (is_uv_system())
-		set_bit(EFI_OLD_MEMMAP, &efi.flags);
-}

arch/x86/platform/efi/quirks.c

@@ -0,0 +1,267 @@
+#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/bootmem.h>
+#include <asm/efi.h>
+#include <asm/uv/uv.h>
+
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
+
+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(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
+}
+
+/*
+ * 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)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
+	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_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
+
+		status = efi.set_variable(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.
+*/
+void __init efi_reserve_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start + size > __pa_symbol(_text)
+				&& start <= __pa_symbol(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_is_region_reserved(start, size)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
+				     start, start+size-1);
+		} else
+			memblock_reserve(start, size);
+	}
+}
+
+void __init efi_free_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
+		free_bootmem_late(start, size);
+	}
+
+	efi_unmap_memmap();
+}
+
+/*
+ * 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 (!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;
+}
+
+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("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+}