x86/efistub: Avoid legacy decompressor when doing EFI boot

The bare metal decompressor code was never really intended to run in a
hosted environment such as the EFI boot services, and does a few things
that are becoming problematic in the context of EFI boot now that the
logo requirements are getting tighter: EFI executables will no longer be
allowed to consist of a single executable section that is mapped with
read, write and execute permissions if they are intended for use in a
context where Secure Boot is enabled (and where Microsoft's set of
certificates is used, i.e., every x86 PC built to run Windows).

To avoid stepping on reserved memory before having inspected the E820
tables, and to ensure the correct placement when running a kernel build
that is non-relocatable, the bare metal decompressor moves its own
executable image to the end of the allocation that was reserved for it,
in order to perform the decompression in place. This means the region in
question requires both write and execute permissions, which either need
to be given upfront (which EFI will no longer permit), or need to be
applied on demand using the existing page fault handling framework.

However, the physical placement of the kernel is usually randomized
anyway, and even if it isn't, a dedicated decompression output buffer
can be allocated anywhere in memory using EFI APIs when still running in
the boot services, given that EFI support already implies a relocatable
kernel. This means that decompression in place is never necessary, nor
is moving the compressed image from one end to the other.

Since EFI already maps all of memory 1:1, it is also unnecessary to
create new page tables or handle page faults when decompressing the
kernel. That means there is also no need to replace the special
exception handlers for SEV. Generally, there is little need to do
any of the things that the decompressor does beyond

- initialize SEV encryption, if needed,
- perform the 4/5 level paging switch, if needed,
- decompress the kernel
- relocate the kernel

So do all of this from the EFI stub code, and avoid the bare metal
decompressor altogether.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230807162720.545787-24-ardb@kernel.org

1 files changed, 72 insertions, 94 deletions

diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index b4685da2b8d5..e976288728e9 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -15,17 +15,14 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/boot.h>
+#include <asm/kaslr.h>
 #include <asm/sev.h>
 
 #include "efistub.h"
 #include "x86-stub.h"
 
-/* Maximum physical address for 64-bit kernel with 4-level paging */
-#define MAXMEM_X86_64_4LEVEL (1ull << 46)
-
 const efi_system_table_t *efi_system_table;
 const efi_dxe_services_table_t *efi_dxe_table;
-u32 image_offset __section(".data");
 static efi_loaded_image_t *image = NULL;
 static efi_memory_attribute_protocol_t *memattr;
 
@@ -287,28 +284,6 @@ void efi_adjust_memory_range_protection(unsigned long start,
 	}
 }
 
-extern const u8 startup_32[], startup_64[];
-
-static void
-setup_memory_protection(unsigned long image_base, unsigned long image_size)
-{
-#ifdef CONFIG_64BIT
-	if (image_base != (unsigned long)startup_32)
-		efi_adjust_memory_range_protection(image_base, image_size);
-#else
-	/*
-	 * Clear protection flags on a whole range of possible
-	 * addresses used for KASLR. We don't need to do that
-	 * on x86_64, since KASLR/extraction is performed after
-	 * dedicated identity page tables are built and we only
-	 * need to remove possible protection on relocated image
-	 * itself disregarding further relocations.
-	 */
-	efi_adjust_memory_range_protection(LOAD_PHYSICAL_ADDR,
-					   KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR);
-#endif
-}
-
 static void setup_unaccepted_memory(void)
 {
 	efi_guid_t mem_acceptance_proto = OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID;
@@ -334,9 +309,7 @@ static void setup_unaccepted_memory(void)
 
 static const efi_char16_t apple[] = L"Apple";
 
-static void setup_quirks(struct boot_params *boot_params,
-			 unsigned long image_base,
-			 unsigned long image_size)
+static void setup_quirks(struct boot_params *boot_params)
 {
 	efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long)
 		efi_table_attr(efi_system_table, fw_vendor);
@@ -345,9 +318,6 @@ static void setup_quirks(struct boot_params *boot_params,
 		if (IS_ENABLED(CONFIG_APPLE_PROPERTIES))
 			retrieve_apple_device_properties(boot_params);
 	}
-
-	if (IS_ENABLED(CONFIG_EFI_DXE_MEM_ATTRIBUTES))
-		setup_memory_protection(image_base, image_size);
 }
 
 /*
@@ -500,7 +470,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	}
 
 	image_base = efi_table_attr(image, image_base);
-	image_offset = (void *)startup_32 - image_base;
 
 	status = efi_allocate_pages(sizeof(struct boot_params),
 				    (unsigned long *)&boot_params, ULONG_MAX);
@@ -804,6 +773,61 @@ static bool have_unsupported_snp_features(void)
 	return false;
 }
 
+static void efi_get_seed(void *seed, int size)
+{
+	efi_get_random_bytes(size, seed);
+
+	/*
+	 * This only updates seed[0] when running on 32-bit, but in that case,
+	 * seed[1] is not used anyway, as there is no virtual KASLR on 32-bit.
+	 */
+	*(unsigned long *)seed ^= kaslr_get_random_long("EFI");
+}
+
+static void error(char *str)
+{
+	efi_warn("Decompression failed: %s\n", str);
+}
+
+static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry)
+{
+	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
+	unsigned long addr, alloc_size, entry;
+	efi_status_t status;
+	u32 seed[2] = {};
+
+	/* determine the required size of the allocation */
+	alloc_size = ALIGN(max_t(unsigned long, output_len, kernel_total_size),
+			   MIN_KERNEL_ALIGN);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) {
+		u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size;
+
+		efi_get_seed(seed, sizeof(seed));
+
+		virt_addr += (range * seed[1]) >> 32;
+		virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1);
+	}
+
+	status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr,
+				  seed[0], EFI_LOADER_CODE,
+				  EFI_X86_KERNEL_ALLOC_LIMIT);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	entry = decompress_kernel((void *)addr, virt_addr, error);
+	if (entry == ULONG_MAX) {
+		efi_free(alloc_size, addr);
+		return EFI_LOAD_ERROR;
+	}
+
+	*kernel_entry = addr + entry;
+
+	efi_adjust_memory_range_protection(addr, kernel_total_size);
+
+	return EFI_SUCCESS;
+}
+
 static void __noreturn enter_kernel(unsigned long kernel_addr,
 				    struct boot_params *boot_params)
 {
@@ -823,10 +847,9 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 			       struct boot_params *boot_params)
 {
 	efi_guid_t guid = EFI_MEMORY_ATTRIBUTE_PROTOCOL_GUID;
-	unsigned long bzimage_addr = (unsigned long)startup_32;
-	unsigned long buffer_start, buffer_end;
 	struct setup_header *hdr = &boot_params->hdr;
 	const struct linux_efi_initrd *initrd = NULL;
+	unsigned long kernel_entry;
 	efi_status_t status;
 
 	efi_system_table = sys_table_arg;
@@ -855,60 +878,6 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 		goto fail;
 	}
 
-	/*
-	 * If the kernel isn't already loaded at a suitable address,
-	 * relocate it.
-	 *
-	 * It must be loaded above LOAD_PHYSICAL_ADDR.
-	 *
-	 * The maximum address for 64-bit is 1 << 46 for 4-level paging. This
-	 * is defined as the macro MAXMEM, but unfortunately that is not a
-	 * compile-time constant if 5-level paging is configured, so we instead
-	 * define our own macro for use here.
-	 *
-	 * For 32-bit, the maximum address is complicated to figure out, for
-	 * now use KERNEL_IMAGE_SIZE, which will be 512MiB, the same as what
-	 * KASLR uses.
-	 *
-	 * Also relocate it if image_offset is zero, i.e. the kernel wasn't
-	 * loaded by LoadImage, but rather by a bootloader that called the
-	 * handover entry. The reason we must always relocate in this case is
-	 * to handle the case of systemd-boot booting a unified kernel image,
-	 * which is a PE executable that contains the bzImage and an initrd as
-	 * COFF sections. The initrd section is placed after the bzImage
-	 * without ensuring that there are at least init_size bytes available
-	 * for the bzImage, and thus the compressed kernel's startup code may
-	 * overwrite the initrd unless it is moved out of the way.
-	 */
-
-	buffer_start = ALIGN(bzimage_addr - image_offset,
-			     hdr->kernel_alignment);
-	buffer_end = buffer_start + hdr->init_size;
-
-	if ((buffer_start < LOAD_PHYSICAL_ADDR)				     ||
-	    (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE)    ||
-	    (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) ||
-	    (image_offset == 0)) {
-		extern char _bss[];
-
-		status = efi_relocate_kernel(&bzimage_addr,
-					     (unsigned long)_bss - bzimage_addr,
-					     hdr->init_size,
-					     hdr->pref_address,
-					     hdr->kernel_alignment,
-					     LOAD_PHYSICAL_ADDR);
-		if (status != EFI_SUCCESS) {
-			efi_err("efi_relocate_kernel() failed!\n");
-			goto fail;
-		}
-		/*
-		 * Now that we've copied the kernel elsewhere, we no longer
-		 * have a set up block before startup_32(), so reset image_offset
-		 * to zero in case it was set earlier.
-		 */
-		image_offset = 0;
-	}
-
 #ifdef CONFIG_CMDLINE_BOOL
 	status = efi_parse_options(CONFIG_CMDLINE);
 	if (status != EFI_SUCCESS) {
@@ -926,6 +895,12 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 		}
 	}
 
+	status = efi_decompress_kernel(&kernel_entry);
+	if (status != EFI_SUCCESS) {
+		efi_err("Failed to decompress kernel\n");
+		goto fail;
+	}
+
 	/*
 	 * At this point, an initrd may already have been loaded by the
 	 * bootloader and passed via bootparams. We permit an initrd loaded
@@ -965,7 +940,7 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 
 	setup_efi_pci(boot_params);
 
-	setup_quirks(boot_params, bzimage_addr, buffer_end - buffer_start);
+	setup_quirks(boot_params);
 
 	setup_unaccepted_memory();
 
@@ -975,12 +950,15 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
 		goto fail;
 	}
 
-	efi_5level_switch();
+	/*
+	 * Call the SEV init code while still running with the firmware's
+	 * GDT/IDT, so #VC exceptions will be handled by EFI.
+	 */
+	sev_enable(boot_params);
 
-	if (IS_ENABLED(CONFIG_X86_64))
-		bzimage_addr += startup_64 - startup_32;
+	efi_5level_switch();
 
-	enter_kernel(bzimage_addr, boot_params);
+	enter_kernel(kernel_entry, boot_params);
 fail:
 	efi_err("efi_stub_entry() failed!\n");