Merge tag 'efi-fixes-for-v7.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi

Pull EFI fix from Ard Biesheuvel:
 "Fix for the x86 EFI workaround keeping boot services code and data
  regions reserved until after SetVirtualAddressMap() completes:
  deferred struct page initialization may result in some of this memory
  being lost permanently"

* tag 'efi-fixes-for-v7.0-2' of git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi:
  x86/efi: defer freeing of boot services memory

4 files changed, 55 insertions, 6 deletions

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index f227a70ac91f..51b4cdbea061 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -138,7 +138,7 @@ 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);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
-extern void efi_free_boot_services(void);
+extern void efi_unmap_boot_services(void);
 
 void arch_efi_call_virt_setup(void);
 void arch_efi_call_virt_teardown(void);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d00c6de7f3b7..d84c6020dda1 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -836,7 +836,7 @@ static void __init __efi_enter_virtual_mode(void)
 	}
 
 	efi_check_for_embedded_firmwares();
-	efi_free_boot_services();
+	efi_unmap_boot_services();
 
 	if (!efi_is_mixed())
 		efi_native_runtime_setup();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 553f330198f2..35caa5746115 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -341,7 +341,7 @@ void __init efi_reserve_boot_services(void)
 
 		/*
 		 * Because the following memblock_reserve() is paired
-		 * with memblock_free_late() for this region in
+		 * with free_reserved_area() for this region in
 		 * efi_free_boot_services(), we must be extremely
 		 * careful not to reserve, and subsequently free,
 		 * critical regions of memory (like the kernel image) or
@@ -404,17 +404,33 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md)
 		pr_err("Failed to unmap VA mapping for 0x%llx\n", va);
 }
 
-void __init efi_free_boot_services(void)
+struct efi_freeable_range {
+	u64 start;
+	u64 end;
+};
+
+static struct efi_freeable_range *ranges_to_free;
+
+void __init efi_unmap_boot_services(void)
 {
 	struct efi_memory_map_data data = { 0 };
 	efi_memory_desc_t *md;
 	int num_entries = 0;
+	int idx = 0;
+	size_t sz;
 	void *new, *new_md;
 
 	/* Keep all regions for /sys/kernel/debug/efi */
 	if (efi_enabled(EFI_DBG))
 		return;
 
+	sz = sizeof(*ranges_to_free) * efi.memmap.nr_map + 1;
+	ranges_to_free = kzalloc(sz, GFP_KERNEL);
+	if (!ranges_to_free) {
+		pr_err("Failed to allocate storage for freeable EFI regions\n");
+		return;
+	}
+
 	for_each_efi_memory_desc(md) {
 		unsigned long long start = md->phys_addr;
 		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
@@ -471,7 +487,15 @@ void __init efi_free_boot_services(void)
 			start = SZ_1M;
 		}
 
-		memblock_free_late(start, size);
+		/*
+		 * With CONFIG_DEFERRED_STRUCT_PAGE_INIT parts of the memory
+		 * map are still not initialized and we can't reliably free
+		 * memory here.
+		 * Queue the ranges to free at a later point.
+		 */
+		ranges_to_free[idx].start = start;
+		ranges_to_free[idx].end = start + size;
+		idx++;
 	}
 
 	if (!num_entries)
@@ -512,6 +536,31 @@ void __init efi_free_boot_services(void)
 	}
 }
 
+static int __init efi_free_boot_services(void)
+{
+	struct efi_freeable_range *range = ranges_to_free;
+	unsigned long freed = 0;
+
+	if (!ranges_to_free)
+		return 0;
+
+	while (range->start) {
+		void *start = phys_to_virt(range->start);
+		void *end = phys_to_virt(range->end);
+
+		free_reserved_area(start, end, -1, NULL);
+		freed += (end - start);
+		range++;
+	}
+	kfree(ranges_to_free);
+
+	if (freed)
+		pr_info("Freeing EFI boot services memory: %ldK\n", freed / SZ_1K);
+
+	return 0;
+}
+arch_initcall(efi_free_boot_services);
+
 /*
  * A number of config table entries get remapped to virtual addresses
  * after entering EFI virtual mode. However, the kexec kernel requires
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 4ff0c2926097..6842aa96d704 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -85,7 +85,7 @@ static struct kobject *mokvar_kobj;
  * as an alternative to ordinary EFI variables, due to platform-dependent
  * limitations. The memory occupied by this table is marked as reserved.
  *
- * This routine must be called before efi_free_boot_services() in order
+ * This routine must be called before efi_unmap_boot_services() in order
  * to guarantee that it can mark the table as reserved.
  *
  * Implicit inputs: