Merge branch 'zImage_fixes' of git://git.linaro.org/people/nico/linux into devel-stable

5 files changed, 70 insertions, 35 deletions

diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 8ebbb511c783..23aad0722303 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -74,7 +74,7 @@ ZTEXTADDR	:= $(CONFIG_ZBOOT_ROM_TEXT)
 ZBSSADDR        := $(CONFIG_ZBOOT_ROM_BSS)
 else
 ZTEXTADDR       := 0
-ZBSSADDR        := ALIGN(4)
+ZBSSADDR        := ALIGN(8)
 endif
 
 SEDFLAGS        = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
@@ -98,8 +98,6 @@ endif
 ccflags-y := -fpic -fno-builtin
 asflags-y := -Wa,-march=all
 
-# Provide size of uncompressed kernel to the decompressor via a linker symbol.
-LDFLAGS_vmlinux = --defsym _image_size=$(shell stat -c "%s" $(obj)/../Image)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
 LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)
@@ -122,10 +120,23 @@ lib1funcs = $(obj)/lib1funcs.o
 $(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S FORCE
         $(call cmd,shipped)
 
+# We need to prevent any GOTOFF relocs being used with references
+# to symbols in the .bss section since we cannot relocate them
+# independently from the rest at run time.  This can be achieved by
+# ensuring that no private .bss symbols exist, as global symbols
+# always have a GOT entry which is what we need.
+# The .data section is already discarded by the linker script so no need
+# to bother about it here.
+check_for_bad_syms = \
+bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \
+[ -z "$$bad_syms" ] || \
+  ( echo "following symbols must have non local/private scope:" >&2; \
+    echo "$$bad_syms" >&2; rm -f $@; false )
+
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
                 $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
         $(call if_changed,ld)
-        @:
+        @$(check_for_bad_syms)
 
 $(obj)/piggy.$(suffix_y): $(obj)/../Image FORCE
         $(call if_changed,$(suffix_y))
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index 4c72a97bc3e1..07be5a2f8302 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -44,7 +44,7 @@ extern void error(char *);
 #include "../../../../lib/decompress_unlzma.c"
 #endif
 
-void do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
+int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
 {
-        decompress(input, len, NULL, NULL, output, NULL, error);
+        return decompress(input, len, NULL, NULL, output, NULL, error);
 }
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index a36f4526689b..c363458a4e63 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -179,16 +179,29 @@ not_angel:
                 bl      cache_on
 
 restart:        adr     r0, LC0
-                ldmia   r0, {r1, r2, r3, r5, r6, r9, r11, r12}
-                ldr     sp, [r0, #32]
+                ldmia   r0, {r1, r2, r3, r6, r10, r11, r12}
+                ldr     sp, [r0, #28]
 
                 /*
                  * We might be running at a different address.  We need
                  * to fix up various pointers.
                  */
                 sub     r0, r0, r1              @ calculate the delta offset
-                add     r5, r5, r0              @ _start
                 add     r6, r6, r0              @ _edata
+                add     r10, r10, r0            @ inflated kernel size location
+
+                /*
+                 * The kernel build system appends the size of the
+                 * decompressed kernel at the end of the compressed data
+                 * in little-endian form.
+                 */
+                ldrb    r9, [r10, #0]
+                ldrb    lr, [r10, #1]
+                orr     r9, r9, lr, lsl #8
+                ldrb    lr, [r10, #2]
+                ldrb    r10, [r10, #3]
+                orr     r9, r9, lr, lsl #16
+                orr     r9, r9, r10, lsl #24
 
 #ifndef CONFIG_ZBOOT_ROM
                 /* malloc space is above the relocated stack (64k max) */
@@ -206,31 +219,40 @@ restart:	adr	r0, LC0
 /*
  * Check to see if we will overwrite ourselves.
  *   r4  = final kernel address
- *   r5  = start of this image
  *   r9  = size of decompressed image
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
  * We basically want:
- *   r4 >= r10 -> OK
- *   r4 + image length <= r5 -> OK
+ *   r4 - 16k page directory >= r10 -> OK
+ *   r4 + image length <= current position (pc) -> OK
  */
+                add     r10, r10, #16384
                 cmp     r4, r10
                 bhs     wont_overwrite
                 add     r10, r4, r9
-                cmp     r10, r5
+   ARM(         cmp     r10, pc         )
+ THUMB(         mov     lr, pc          )
+ THUMB(         cmp     r10, lr         )
                 bls     wont_overwrite
 
 /*
  * Relocate ourselves past the end of the decompressed kernel.
- *   r5  = start of this image
  *   r6  = _edata
  *   r10 = end of the decompressed kernel
  * Because we always copy ahead, we need to do it from the end and go
  * backward in case the source and destination overlap.
  */
-                /* Round up to next 256-byte boundary. */
-                add     r10, r10, #256
+                /*
+                 * Bump to the next 256-byte boundary with the size of
+                 * the relocation code added. This avoids overwriting
+                 * ourself when the offset is small.
+                 */
+                add     r10, r10, #((reloc_code_end - restart + 256) & ~255)
                 bic     r10, r10, #255
 
+                /* Get start of code we want to copy and align it down. */
+                adr     r5, restart
+                bic     r5, r5, #31
+
                 sub     r9, r6, r5              @ size to copy
                 add     r9, r9, #31             @ rounded up to a multiple
                 bic     r9, r9, #31             @ ... of 32 bytes
@@ -245,6 +267,11 @@ restart:	adr	r0, LC0
                 /* Preserve offset to relocated code. */
                 sub     r6, r9, r6
 
+#ifndef CONFIG_ZBOOT_ROM
+                /* cache_clean_flush may use the stack, so relocate it */
+                add     sp, sp, r6
+#endif
+
                 bl      cache_clean_flush
 
                 adr     r0, BSYM(restart)
@@ -333,12 +360,11 @@ not_relocated:	mov	r0, #0
 LC0:            .word   LC0                     @ r1
                 .word   __bss_start             @ r2
                 .word   _end                    @ r3
-                .word   _start                  @ r5
                 .word   _edata                  @ r6
-                .word   _image_size             @ r9
+                .word   input_data_end - 4      @ r10 (inflated size location)
                 .word   _got_start              @ r11
                 .word   _got_end                @ ip
-                .word   user_stack_end          @ sp
+                .word   .L_user_stack_end       @ sp
                 .size   LC0, . - LC0
 
 #ifdef CONFIG_ARCH_RPC
@@ -1056,8 +1082,9 @@ memdump:	mov	r12, r0
 #endif
 
                 .ltorg
+reloc_code_end:
 
                 .align
                 .section ".stack", "aw", %nobits
-user_stack:     .space  4096
-user_stack_end:
+.L_user_stack:  .space  4096
+.L_user_stack_end:
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 2df38263124c..832d37236c59 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -26,8 +26,6 @@ unsigned int __machine_arch_type;
 #include <linux/linkage.h>
 #include <asm/string.h>
 
-#include <asm/unaligned.h>
-
 
 static void putstr(const char *ptr);
 extern void error(char *x);
@@ -139,13 +137,12 @@ void *memcpy(void *__dest, __const void *__src, size_t __n)
 }
 
 /*
- * gzip delarations
+ * gzip declarations
  */
 extern char input_data[];
 extern char input_data_end[];
 
 unsigned char *output_data;
-unsigned long output_ptr;
 
 unsigned long free_mem_ptr;
 unsigned long free_mem_end_ptr;
@@ -170,15 +167,15 @@ asmlinkage void __div0(void)
         error("Attempting division by 0!");
 }
 
-extern void do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
+extern int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
 
 
-unsigned long
+void
 decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
                 unsigned long free_mem_ptr_end_p,
                 int arch_id)
 {
-        unsigned char *tmp;
+        int ret;
 
         output_data             = (unsigned char *)output_start;
         free_mem_ptr            = free_mem_ptr_p;
@@ -187,12 +184,11 @@ decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
 
         arch_decomp_setup();
 
-        tmp = (unsigned char *) (((unsigned long)input_data_end) - 4);
-        output_ptr = get_unaligned_le32(tmp);
-
         putstr("Uncompressing Linux...");
-        do_decompress(input_data, input_data_end - input_data,
-                        output_data, error);
-        putstr(" done, booting the kernel.\n");
-        return output_ptr;
+        ret = do_decompress(input_data, input_data_end - input_data,
+                            output_data, error);
+        if (ret)
+                error("decompressor returned an error");
+        else
+                putstr(" done, booting the kernel.\n");
 }
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
index 5309909d7282..ea80abe78844 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -54,6 +54,7 @@ SECTIONS
   .bss                  : { *(.bss) }
   _end = .;
 
+  . = ALIGN(8);         /* the stack must be 64-bit aligned */
   .stack                : { *(.stack) }
 
   .stab 0               : { *(.stab) }