Simplify EFI handover to decompressor

The EFI stub in the ARM kernel runs in the context of the firmware, which
 means it usually runs with the caches and MMU on. Currently, we relocate
 the zImage so it appears in the first 128 MiB, disable the MMU and caches
 and invoke the decompressor via its ordinary entry point. However, since we
 can pass the base of DRAM directly, there is no need to relocate the zImage,
 which also means there is no need to disable and re-enable the caches and
 create new page tables etc.
 
 This also allows systems whose DRAM start address is not a round multiple
 of 128 MB to decompress the kernel proper to the base of memory, ensuring
 that all memory is usable at runtime.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCgAdFiEEnNKg2mrY9zMBdeK7wjcgfpV0+n0FAl7FbMMACgkQwjcgfpV0
 +n15TAgAmWgczY35HCM4Hosv8c7N1xG3HAo5Dn/M6I0twTtAYki33Nb2UgX771sq
 tkk8eetDCOtDmfGP0ZED/n2EstXIRcpmCl2cqPdZjX/0XrSpUEyyuTZ+jGoaL6Tb
 l8joWq9cr9aCDd0jIKLdwFhusk+dXJWyyoXguFZnIkwMsTauBeNCwMbuUgTyOFro
 6R5iF9CFnWl+yNheNQe/F2QKbsCdExW22gBaR2z3sMCeuJKSviy9nwJZGafmm/+S
 ySKhFnzREdAdTfk9BEzOm4J3kZFrSOn5YxEOAde/zYB1kcPg/+t0xFdIEu2C0iQp
 ruTaJmq0YLSr7psZm3CMmMe0P2lBiw==
 =2BnA
 -----END PGP SIGNATURE-----

Merge tag 'efi-arm-no-relocate-for-rmk' of git://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux into misc

Simplify EFI handover to decompressor

The EFI stub in the ARM kernel runs in the context of the firmware, which
means it usually runs with the caches and MMU on. Currently, we relocate
the zImage so it appears in the first 128 MiB, disable the MMU and caches
and invoke the decompressor via its ordinary entry point. However, since we
can pass the base of DRAM directly, there is no need to relocate the zImage,
which also means there is no need to disable and re-enable the caches and
create new page tables etc.

This also allows systems whose DRAM start address is not a round multiple
of 128 MB to decompress the kernel proper to the base of memory, ensuring
that all memory is usable at runtime.

arch/arm/boot/compressed/head.S

@@ -287,28 +287,22 @@ not_angel:
 		 */
 		mov	r0, pc
 		cmp	r0, r4
-		ldrcc	r0, LC0+28
+		ldrcc	r0, .Lheadroom
 		addcc	r0, r0, pc
 		cmpcc	r4, r0
 		orrcc	r4, r4, #1		@ remember we skipped cache_on
 		blcs	cache_on
 
-restart:	adr	r0, LC0
+restart:	adr	r0, LC1
-		ldmia	r0, {r1, r2, r3, r6, r11, r12}
+		ldr	sp, [r0]
-		ldr	sp, [r0, #24]
+		ldr	r6, [r0, #4]
-
+		add	sp, sp, r0
-		/*
+		add	r6, r6, r0
-		 * We might be running at a different address.  We need
-		 * to fix up various pointers.
-		 */
-		sub	r0, r0, r1		@ calculate the delta offset
-		add	r6, r6, r0		@ _edata
 
 		get_inflated_image_size	r9, r10, lr
 
 #ifndef CONFIG_ZBOOT_ROM
 		/* malloc space is above the relocated stack (64k max) */
-		add	sp, sp, r0
 		add	r10, sp, #0x10000
 #else
 		/*
@@ -322,9 +316,6 @@ restart:	adr	r0, LC0
 		mov	r5, #0			@ init dtb size to 0
 #ifdef CONFIG_ARM_APPENDED_DTB
 /*
- *   r0  = delta
- *   r2  = BSS start
- *   r3  = BSS end
  *   r4  = final kernel address (possibly with LSB set)
  *   r5  = appended dtb size (still unknown)
  *   r6  = _edata
@@ -332,8 +323,6 @@ restart:	adr	r0, LC0
  *   r8  = atags/device tree pointer
  *   r9  = size of decompressed image
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
- *   r11 = GOT start
- *   r12 = GOT end
  *   sp  = stack pointer
  *
  * if there are device trees (dtb) appended to zImage, advance r10 so that the
@@ -381,7 +370,6 @@ restart:	adr	r0, LC0
 		/* temporarily relocate the stack past the DTB work space */
 		add	sp, sp, r5
 
-		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
 		mov	r2, r5
@@ -400,7 +388,6 @@ restart:	adr	r0, LC0
 		mov	r2, r5
 		bleq	atags_to_fdt
 
-		ldmfd	sp!, {r0-r3, ip, lr}
 		sub	sp, sp, r5
 #endif
 
@@ -537,6 +524,10 @@ dtb_check_done:
 		mov	pc, r0
 
 wont_overwrite:
+		adr	r0, LC0
+		ldmia	r0, {r1, r2, r3, r11, r12}
+		sub	r0, r0, r1		@ calculate the delta offset
+
 /*
  * If delta is zero, we are running at the address we were linked at.
  *   r0  = delta
@@ -660,13 +651,18 @@ not_relocated:	mov	r0, #0
 LC0:		.word	LC0			@ r1
 		.word	__bss_start		@ r2
 		.word	_end			@ r3
-		.word	_edata			@ r6
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
-		.word	.L_user_stack_end	@ sp
-		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0
 
+		.type	LC1, #object
+LC1:		.word	.L_user_stack_end - LC1	@ sp
+		.word	_edata - LC1		@ r6
+		.size	LC1, . - LC1
+
+.Lheadroom:
+		.word	_end - restart + 16384 + 1024*1024
+
 .Linflated_image_size_offset:
 		.long	(input_data_end - 4) - .
 
@@ -1434,37 +1430,26 @@ reloc_code_end:
 
 #ifdef CONFIG_EFI_STUB
 ENTRY(efi_enter_kernel)
-		mov	r7, r0				@ preserve image base
+		mov	r4, r0			@ preserve image base
-		mov	r4, r1				@ preserve DT pointer
+		mov	r8, r1			@ preserve DT pointer
 
-		mov	r0, r4				@ DT start
+		mrc	p15, 0, r0, c1, c0, 0	@ read SCTLR
-		add	r1, r4, r2			@ DT end
+		tst	r0, #0x1		@ MMU enabled?
+		orreq	r4, r4, #1		@ set LSB if not
+
+		mov	r0, r8			@ DT start
+		add	r1, r8, r2		@ DT end
 		bl	cache_clean_flush
 
-		mov	r0, r7				@ relocated zImage
+		adr	r0, 0f			@ switch to our stack
-		ldr	r1, =_edata			@ size of zImage
+		ldr	sp, [r0]
-		add	r1, r1, r0			@ end of zImage
+		add	sp, sp, r0
-		bl	cache_clean_flush
 
-		@ The PE/COFF loader might not have cleaned the code we are
+		mov	r5, #0			@ appended DTB size
-		@ running beyond the PoU, and so calling cache_off below from
+		mov	r7, #0xFFFFFFFF		@ machine ID
-		@ inside the PE/COFF loader allocated region is unsafe unless
+		b	wont_overwrite
-		@ we explicitly clean it to the PoC.
-		adr	r0, call_cache_fn		@ region of code we will
-		adr	r1, 0f				@ run with MMU off
-		bl	cache_clean_flush
-		bl	cache_off
-
-		@ Set parameters for booting zImage according to boot protocol
-		@ put FDT address in r2, it was returned by efi_entry()
-		@ r1 is the machine type, and r0 needs to be 0
-		mov	r0, #0
-		mov	r1, #0xFFFFFFFF
-		mov	r2, r4
-		add	r7, r7, #(__efi_start - start)
-		mov	pc, r7				@ no mode switch
 ENDPROC(efi_enter_kernel)
-0:
+0:		.long	.L_user_stack_end - .
 #endif
 
 		.align

arch/arm/boot/compressed/vmlinux.lds.S

@@ -63,9 +63,11 @@ SECTIONS
   _etext = .;
 
   .got.plt		: { *(.got.plt) }
+#ifndef CONFIG_EFI_STUB
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
+#endif
 
   /* ensure the zImage file size is always a multiple of 64 bits */
   /* (without a dummy byte, ld just ignores the empty section) */
@@ -74,6 +76,9 @@ SECTIONS
 #ifdef CONFIG_EFI_STUB
   .data : ALIGN(4096) {
     __pecoff_data_start = .;
+    _got_start = .;
+    *(.got)
+    _got_end = .;
     /*
      * The EFI stub always executes from RAM, and runs strictly before the
      * decompressor, so we can make an exception for its r/w data, and keep it

drivers/firmware/efi/libstub/arm32-stub.c

@@ -199,14 +199,8 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	unsigned long kernel_base;
 	efi_status_t status;
 
-	/*
+	/* use a 16 MiB aligned base for the decompressed kernel */
-	 * Verify that the DRAM base address is compatible with the ARM
+	kernel_base = round_up(dram_base, SZ_16M) + TEXT_OFFSET;
-	 * boot protocol, which determines the base of DRAM by masking
-	 * off the low 27 bits of the address at which the zImage is
-	 * loaded. These assumptions are made by the decompressor,
-	 * before any memory map is available.
-	 */
-	kernel_base = round_up(dram_base, SZ_128M);
 
 	/*
 	 * Note that some platforms (notably, the Raspberry Pi 2) put
@@ -215,41 +209,14 @@ efi_status_t handle_kernel_image(unsigned long *image_addr,
 	 * base of the kernel image is only partially used at the moment.
 	 * (Up to 5 pages are used for the swapper page tables)
 	 */
-	kernel_base += TEXT_OFFSET - 5 * PAGE_SIZE;
+	status = reserve_kernel_base(kernel_base - 5 * PAGE_SIZE, reserve_addr,
-
+				     reserve_size);
-	status = reserve_kernel_base(kernel_base, reserve_addr, reserve_size);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err("Unable to allocate memory for uncompressed kernel.\n");
 		return status;
 	}
 
-	/*
+	*image_addr = kernel_base;
-	 * Relocate the zImage, so that it appears in the lowest 128 MB
+	*image_size = 0;
-	 * memory window.
-	 */
-	*image_addr = (unsigned long)image->image_base;
-	*image_size = image->image_size;
-	status = efi_relocate_kernel(image_addr, *image_size, *image_size,
-				     kernel_base + MAX_UNCOMP_KERNEL_SIZE, 0, 0);
-	if (status != EFI_SUCCESS) {
-		pr_efi_err("Failed to relocate kernel.\n");
-		efi_free(*reserve_size, *reserve_addr);
-		*reserve_size = 0;
-		return status;
-	}
-
-	/*
-	 * Check to see if we were able to allocate memory low enough
-	 * in memory. The kernel determines the base of DRAM from the
-	 * address at which the zImage is loaded.
-	 */
-	if (*image_addr + *image_size > dram_base + ZIMAGE_OFFSET_LIMIT) {
-		pr_efi_err("Failed to relocate kernel, no low memory available.\n");
-		efi_free(*reserve_size, *reserve_addr);
-		*reserve_size = 0;
-		efi_free(*image_size, *image_addr);
-		*image_size = 0;
-		return EFI_LOAD_ERROR;
-	}
 	return EFI_SUCCESS;
 }