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

Pull EFI fixes from Ingo Molnar:
 "This contains a Xen fix, an arm64 fix and a race condition /
  robustization set of fixes related to ExitBootServices() usage and
  boundary conditions"

* 'efi-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/efi: Use efi_exit_boot_services()
  efi/libstub: Use efi_exit_boot_services() in FDT
  efi/libstub: Introduce ExitBootServices helper
  efi/libstub: Allocate headspace in efi_get_memory_map()
  efi: Fix handling error value in fdt_find_uefi_params
  efi: Make for_each_efi_memory_desc_in_map() cope with running on Xen

arch/x86/boot/compressed/eboot.c

@@ -1004,79 +1004,87 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 	return status;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
-{
-	struct efi_info *efi = &boot_params->efi_info;
-	unsigned long map_sz, key, desc_size;
-	efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+	struct boot_params *boot_params;
+	struct efi_info *efi;
 	struct setup_data *e820ext;
-	const char *signature;
 	__u32 e820ext_size;
-	__u32 nr_desc, prev_nr_desc;
-	efi_status_t status;
-	__u32 desc_version;
-	bool called_exit = false;
-	u8 nr_entries;
-	int i;
-
-	nr_desc = 0;
-	e820ext = NULL;
-	e820ext_size = 0;
-
-get_map:
-	status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
-				    &desc_version, &key);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	prev_nr_desc = nr_desc;
-	nr_desc = map_sz / desc_size;
-	if (nr_desc > prev_nr_desc &&
-	    nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
-		u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
-		status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
-		if (status != EFI_SUCCESS)
-			goto free_mem_map;
+	bool is64;
+};
 
-		efi_call_early(free_pool, mem_map);
-		goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+				   struct efi_boot_memmap *map,
+				   void *priv)
+{
+	static bool first = true;
+	const char *signature;
+	__u32 nr_desc;
+	efi_status_t status;
+	struct exit_boot_struct *p = priv;
+
+	if (first) {
+		nr_desc = *map->buff_size / *map->desc_size;
+		if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+			u32 nr_e820ext = nr_desc -
+					ARRAY_SIZE(p->boot_params->e820_map);
+
+			status = alloc_e820ext(nr_e820ext, &p->e820ext,
+					       &p->e820ext_size);
+			if (status != EFI_SUCCESS)
+				return status;
+		}
+		first = false;
 	}
 
-	signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
-	memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	efi->efi_systab = (unsigned long)sys_table;
-	efi->efi_memdesc_size = desc_size;
-	efi->efi_memdesc_version = desc_version;
-	efi->efi_memmap = (unsigned long)mem_map;
-	efi->efi_memmap_size = map_sz;
+	p->efi->efi_systab = (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size = *map->desc_size;
+	p->efi->efi_memdesc_version = *map->desc_ver;
+	p->efi->efi_memmap = (unsigned long)*map->map;
+	p->efi->efi_memmap_size = *map->map_size;
 
 #ifdef CONFIG_X86_64
-	efi->efi_systab_hi = (unsigned long)sys_table >> 32;
-	efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
 #endif
 
+	return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+			      void *handle, bool is64)
+{
+	unsigned long map_sz, key, desc_size, buff_size;
+	efi_memory_desc_t *mem_map;
+	struct setup_data *e820ext;
+	__u32 e820ext_size;
+	efi_status_t status;
+	__u32 desc_version;
+	struct efi_boot_memmap map;
+	struct exit_boot_struct priv;
+
+	map.map =		&mem_map;
+	map.map_size =		&map_sz;
+	map.desc_size =		&desc_size;
+	map.desc_ver =		&desc_version;
+	map.key_ptr =		&key;
+	map.buff_size =		&buff_size;
+	priv.boot_params =	boot_params;
+	priv.efi =		&boot_params->efi_info;
+	priv.e820ext =		NULL;
+	priv.e820ext_size =	0;
+	priv.is64 =		is64;
+
 	/* Might as well exit boot services now */
-	status = efi_call_early(exit_boot_services, handle, key);
-	if (status != EFI_SUCCESS) {
-		/*
-		 * ExitBootServices() will fail if any of the event
-		 * handlers change the memory map. In which case, we
-		 * must be prepared to retry, but only once so that
-		 * we're guaranteed to exit on repeated failures instead
-		 * of spinning forever.
-		 */
-		if (called_exit)
-			goto free_mem_map;
-
-		called_exit = true;
-		efi_call_early(free_pool, mem_map);
-		goto get_map;
-	}
+	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+					exit_boot_func);
+	if (status != EFI_SUCCESS)
+		return status;
 
+	e820ext = priv.e820ext;
+	e820ext_size = priv.e820ext_size;
 	/* Historic? */
 	boot_params->alt_mem_k = 32 * 1024;
 
@@ -1085,10 +1093,6 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 		return status;
 
 	return EFI_SUCCESS;
-
-free_mem_map:
-	efi_call_early(free_pool, mem_map);
-	return status;
 }
 
 /*

drivers/firmware/efi/efi.c

@@ -657,9 +657,12 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
 		}
 
 		if (subnode) {
-			node = of_get_flat_dt_subnode_by_name(node, subnode);
-			if (node < 0)
+			int err = of_get_flat_dt_subnode_by_name(node, subnode);
+
+			if (err < 0)
 				return 0;
+
+			node = err;
 		}
 
 		return __find_uefi_params(node, info, dt_params[i].params);

drivers/firmware/efi/libstub/efi-stub-helper.c

@@ -41,6 +41,8 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
 #define EFI_ALLOC_ALIGN		EFI_PAGE_SIZE
 #endif
 
+#define EFI_MMAP_NR_SLACK_SLOTS	8
+
 struct file_info {
 	efi_file_handle_t *handle;
 	u64 size;
@@ -63,49 +65,62 @@ void efi_printk(efi_system_table_t *sys_table_arg, char *str)
 	}
 }
 
+static inline bool mmap_has_headroom(unsigned long buff_size,
+				     unsigned long map_size,
+				     unsigned long desc_size)
+{
+	unsigned long slack = buff_size - map_size;
+
+	return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS;
+}
+
 efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
-				efi_memory_desc_t **map,
-				unsigned long *map_size,
-				unsigned long *desc_size,
-				u32 *desc_ver,
-				unsigned long *key_ptr)
+				struct efi_boot_memmap *map)
 {
 	efi_memory_desc_t *m = NULL;
 	efi_status_t status;
 	unsigned long key;
 	u32 desc_version;
 
-	*map_size = sizeof(*m) * 32;
+	*map->desc_size =	sizeof(*m);
+	*map->map_size =	*map->desc_size * 32;
+	*map->buff_size =	*map->map_size;
 again:
-	/*
-	 * Add an additional efi_memory_desc_t because we're doing an
-	 * allocation which may be in a new descriptor region.
-	 */
-	*map_size += sizeof(*m);
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				*map_size, (void **)&m);
+				*map->map_size, (void **)&m);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
-	*desc_size = 0;
+	*map->desc_size = 0;
 	key = 0;
-	status = efi_call_early(get_memory_map, map_size, m,
-				&key, desc_size, &desc_version);
-	if (status == EFI_BUFFER_TOO_SMALL) {
+	status = efi_call_early(get_memory_map, map->map_size, m,
+				&key, map->desc_size, &desc_version);
+	if (status == EFI_BUFFER_TOO_SMALL ||
+	    !mmap_has_headroom(*map->buff_size, *map->map_size,
+			       *map->desc_size)) {
 		efi_call_early(free_pool, m);
+		/*
+		 * Make sure there is some entries of headroom so that the
+		 * buffer can be reused for a new map after allocations are
+		 * no longer permitted.  Its unlikely that the map will grow to
+		 * exceed this headroom once we are ready to trigger
+		 * ExitBootServices()
+		 */
+		*map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS;
+		*map->buff_size = *map->map_size;
 		goto again;
 	}
 
 	if (status != EFI_SUCCESS)
 		efi_call_early(free_pool, m);
 
-	if (key_ptr && status == EFI_SUCCESS)
-		*key_ptr = key;
-	if (desc_ver && status == EFI_SUCCESS)
-		*desc_ver = desc_version;
+	if (map->key_ptr && status == EFI_SUCCESS)
+		*map->key_ptr = key;
+	if (map->desc_ver && status == EFI_SUCCESS)
+		*map->desc_ver = desc_version;
 
 fail:
-	*map = m;
+	*map->map = m;
 	return status;
 }
 
@@ -113,13 +128,20 @@ efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg)
 {
 	efi_status_t status;
-	unsigned long map_size;
+	unsigned long map_size, buff_size;
 	unsigned long membase  = EFI_ERROR;
 	struct efi_memory_map map;
 	efi_memory_desc_t *md;
+	struct efi_boot_memmap boot_map;
 
-	status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
-				    &map_size, &map.desc_size, NULL, NULL);
+	boot_map.map =		(efi_memory_desc_t **)&map.map;
+	boot_map.map_size =	&map_size;
+	boot_map.desc_size =	&map.desc_size;
+	boot_map.desc_ver =	NULL;
+	boot_map.key_ptr =	NULL;
+	boot_map.buff_size =	&buff_size;
+
+	status = efi_get_memory_map(sys_table_arg, &boot_map);
 	if (status != EFI_SUCCESS)
 		return membase;
 
@@ -144,15 +166,22 @@ efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
 			    unsigned long size, unsigned long align,
 			    unsigned long *addr, unsigned long max)
 {
-	unsigned long map_size, desc_size;
+	unsigned long map_size, desc_size, buff_size;
 	efi_memory_desc_t *map;
 	efi_status_t status;
 	unsigned long nr_pages;
 	u64 max_addr = 0;
 	int i;
+	struct efi_boot_memmap boot_map;
+
+	boot_map.map =		↦
+	boot_map.map_size =	&map_size;
+	boot_map.desc_size =	&desc_size;
+	boot_map.desc_ver =	NULL;
+	boot_map.key_ptr =	NULL;
+	boot_map.buff_size =	&buff_size;
 
-	status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
-				    NULL, NULL);
+	status = efi_get_memory_map(sys_table_arg, &boot_map);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
@@ -230,14 +259,21 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 			   unsigned long size, unsigned long align,
 			   unsigned long *addr)
 {
-	unsigned long map_size, desc_size;
+	unsigned long map_size, desc_size, buff_size;
 	efi_memory_desc_t *map;
 	efi_status_t status;
 	unsigned long nr_pages;
 	int i;
+	struct efi_boot_memmap boot_map;
 
-	status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
-				    NULL, NULL);
+	boot_map.map =		↦
+	boot_map.map_size =	&map_size;
+	boot_map.desc_size =	&desc_size;
+	boot_map.desc_ver =	NULL;
+	boot_map.key_ptr =	NULL;
+	boot_map.buff_size =	&buff_size;
+
+	status = efi_get_memory_map(sys_table_arg, &boot_map);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
@@ -704,3 +740,76 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
 	*cmd_line_len = options_bytes;
 	return (char *)cmdline_addr;
 }
+
+/*
+ * Handle calling ExitBootServices according to the requirements set out by the
+ * spec.  Obtains the current memory map, and returns that info after calling
+ * ExitBootServices.  The client must specify a function to perform any
+ * processing of the memory map data prior to ExitBootServices.  A client
+ * specific structure may be passed to the function via priv.  The client
+ * function may be called multiple times.
+ */
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg,
+				    void *handle,
+				    struct efi_boot_memmap *map,
+				    void *priv,
+				    efi_exit_boot_map_processing priv_func)
+{
+	efi_status_t status;
+
+	status = efi_get_memory_map(sys_table_arg, map);
+
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	status = priv_func(sys_table_arg, map, priv);
+	if (status != EFI_SUCCESS)
+		goto free_map;
+
+	status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+
+	if (status == EFI_INVALID_PARAMETER) {
+		/*
+		 * The memory map changed between efi_get_memory_map() and
+		 * exit_boot_services().  Per the UEFI Spec v2.6, Section 6.4:
+		 * EFI_BOOT_SERVICES.ExitBootServices we need to get the
+		 * updated map, and try again.  The spec implies one retry
+		 * should be sufficent, which is confirmed against the EDK2
+		 * implementation.  Per the spec, we can only invoke
+		 * get_memory_map() and exit_boot_services() - we cannot alloc
+		 * so efi_get_memory_map() cannot be used, and we must reuse
+		 * the buffer.  For all practical purposes, the headroom in the
+		 * buffer should account for any changes in the map so the call
+		 * to get_memory_map() is expected to succeed here.
+		 */
+		*map->map_size = *map->buff_size;
+		status = efi_call_early(get_memory_map,
+					map->map_size,
+					*map->map,
+					map->key_ptr,
+					map->desc_size,
+					map->desc_ver);
+
+		/* exit_boot_services() was called, thus cannot free */
+		if (status != EFI_SUCCESS)
+			goto fail;
+
+		status = priv_func(sys_table_arg, map, priv);
+		/* exit_boot_services() was called, thus cannot free */
+		if (status != EFI_SUCCESS)
+			goto fail;
+
+		status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+	}
+
+	/* exit_boot_services() was called, thus cannot free */
+	if (status != EFI_SUCCESS)
+		goto fail;
+
+	return EFI_SUCCESS;
+
+free_map:
+	efi_call_early(free_pool, *map->map);
+fail:
+	return status;
+}

drivers/firmware/efi/libstub/fdt.c

@@ -152,6 +152,27 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 #define EFI_FDT_ALIGN EFI_PAGE_SIZE
 #endif
 
+struct exit_boot_struct {
+	efi_memory_desc_t *runtime_map;
+	int *runtime_entry_count;
+};
+
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+				   struct efi_boot_memmap *map,
+				   void *priv)
+{
+	struct exit_boot_struct *p = priv;
+	/*
+	 * Update the memory map with virtual addresses. The function will also
+	 * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
+	 * entries so that we can pass it straight to SetVirtualAddressMap()
+	 */
+	efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
+			p->runtime_map, p->runtime_entry_count);
+
+	return EFI_SUCCESS;
+}
+
 /*
  * Allocate memory for a new FDT, then add EFI, commandline, and
  * initrd related fields to the FDT.  This routine increases the
@@ -175,13 +196,22 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 					    unsigned long fdt_addr,
 					    unsigned long fdt_size)
 {
-	unsigned long map_size, desc_size;
+	unsigned long map_size, desc_size, buff_size;
 	u32 desc_ver;
 	unsigned long mmap_key;
 	efi_memory_desc_t *memory_map, *runtime_map;
 	unsigned long new_fdt_size;
 	efi_status_t status;
 	int runtime_entry_count = 0;
+	struct efi_boot_memmap map;
+	struct exit_boot_struct priv;
+
+	map.map =	&runtime_map;
+	map.map_size =	&map_size;
+	map.desc_size =	&desc_size;
+	map.desc_ver =	&desc_ver;
+	map.key_ptr =	&mmap_key;
+	map.buff_size =	&buff_size;
 
 	/*
 	 * Get a copy of the current memory map that we will use to prepare
@@ -189,8 +219,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	 * subsequent allocations adding entries, since they could not affect
 	 * the number of EFI_MEMORY_RUNTIME regions.
 	 */
-	status = efi_get_memory_map(sys_table, &runtime_map, &map_size,
-				    &desc_size, &desc_ver, &mmap_key);
+	status = efi_get_memory_map(sys_table, &map);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n");
 		return status;
@@ -199,6 +228,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 	pr_efi(sys_table,
 	       "Exiting boot services and installing virtual address map...\n");
 
+	map.map = &memory_map;
 	/*
 	 * Estimate size of new FDT, and allocate memory for it. We
 	 * will allocate a bigger buffer if this ends up being too
@@ -218,8 +248,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 		 * we can get the memory map key  needed for
 		 * exit_boot_services().
 		 */
-		status = efi_get_memory_map(sys_table, &memory_map, &map_size,
-					    &desc_size, &desc_ver, &mmap_key);
+		status = efi_get_memory_map(sys_table, &map);
 		if (status != EFI_SUCCESS)
 			goto fail_free_new_fdt;
 
@@ -250,16 +279,11 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 		}
 	}
 
-	/*
-	 * Update the memory map with virtual addresses. The function will also
-	 * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
-	 * entries so that we can pass it straight into SetVirtualAddressMap()
-	 */
-	efi_get_virtmap(memory_map, map_size, desc_size, runtime_map,
-			&runtime_entry_count);
-
-	/* Now we are ready to exit_boot_services.*/
-	status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+	sys_table->boottime->free_pool(memory_map);
+	priv.runtime_map = runtime_map;
+	priv.runtime_entry_count = &runtime_entry_count;
+	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+					exit_boot_func);
 
 	if (status == EFI_SUCCESS) {
 		efi_set_virtual_address_map_t *svam;

drivers/firmware/efi/libstub/random.c

@@ -73,12 +73,20 @@ efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg,
 			      unsigned long random_seed)
 {
 	unsigned long map_size, desc_size, total_slots = 0, target_slot;
+	unsigned long buff_size;
 	efi_status_t status;
 	efi_memory_desc_t *memory_map;
 	int map_offset;
+	struct efi_boot_memmap map;
 
-	status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size,
-				    &desc_size, NULL, NULL);
+	map.map =	&memory_map;
+	map.map_size =	&map_size;
+	map.desc_size =	&desc_size;
+	map.desc_ver =	NULL;
+	map.key_ptr =	NULL;
+	map.buff_size =	&buff_size;
+
+	status = efi_get_memory_map(sys_table_arg, &map);
 	if (status != EFI_SUCCESS)
 		return status;
 

include/linux/efi.h

@@ -118,6 +118,15 @@ typedef struct {
 	u32 imagesize;
 } efi_capsule_header_t;
 
+struct efi_boot_memmap {
+	efi_memory_desc_t	**map;
+	unsigned long		*map_size;
+	unsigned long		*desc_size;
+	u32			*desc_ver;
+	unsigned long		*key_ptr;
+	unsigned long		*buff_size;
+};
+
 /*
  * EFI capsule flags
  */
@@ -946,7 +955,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm,
 /* Iterate through an efi_memory_map */
 #define for_each_efi_memory_desc_in_map(m, md)				   \
 	for ((md) = (m)->map;						   \
-	     ((void *)(md) + (m)->desc_size) <= (m)->map_end;		   \
+	     (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end;	   \
 	     (md) = (void *)(md) + (m)->desc_size)
 
 /**
@@ -1371,11 +1380,7 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
 			  efi_loaded_image_t *image, int *cmd_line_len);
 
 efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
-				efi_memory_desc_t **map,
-				unsigned long *map_size,
-				unsigned long *desc_size,
-				u32 *desc_ver,
-				unsigned long *key_ptr);
+				struct efi_boot_memmap *map);
 
 efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 			   unsigned long size, unsigned long align,
@@ -1457,4 +1462,14 @@ extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
 	arch_efi_call_virt_teardown();					\
 })
 
+typedef efi_status_t (*efi_exit_boot_map_processing)(
+	efi_system_table_t *sys_table_arg,
+	struct efi_boot_memmap *map,
+	void *priv);
+
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table,
+				    void *handle,
+				    struct efi_boot_memmap *map,
+				    void *priv,
+				    efi_exit_boot_map_processing priv_func);
 #endif /* _LINUX_EFI_H */