diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bc25b9f..873e5c5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1450,9 +1450,7 @@ config KEXEC_JUMP
 
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
-	default "0x1000000" if X86_NUMAQ
-	default "0x200000" if X86_64
-	default "0x100000"
+	default "0x1000000"
 	---help---
 	  This gives the physical address where the kernel is loaded.
 
@@ -1511,8 +1509,8 @@ config RELOCATABLE
 config PHYSICAL_ALIGN
 	hex
 	prompt "Alignment value to which kernel should be aligned" if X86_32
-	default "0x100000" if X86_32
-	default "0x200000" if X86_64
+	default "0x200000" if X86_64 || X86_PAE
+	default "0x400000"
 	range 0x2000 0x400000
 	---help---
 	  This value puts the alignment restrictions on physical address
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 3a8a866..a7a2837 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -39,11 +39,11 @@ ENTRY(startup_32)
 
 	cli
 	movl $(__BOOT_DS),%eax
-	movl %eax,%ds
-	movl %eax,%es
-	movl %eax,%fs
-	movl %eax,%gs
-	movl %eax,%ss
+	movl %eax, %ds
+	movl %eax, %es
+	movl %eax, %fs
+	movl %eax, %gs
+	movl %eax, %ss
 1:
 
 /* Calculate the delta between where we were compiled to run
@@ -64,12 +64,18 @@ ENTRY(startup_32)
  */
 
 #ifdef CONFIG_RELOCATABLE
-	movl 	%ebp, %ebx
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
+	movl $LOAD_PHYSICAL_ADDR, %eax
+	movl %ebp, %ebx
+	cmpl %ebx, %eax
+	jbe 1f
+	movl %eax, %ebx
+1:
+	addl $(CONFIG_PHYSICAL_ALIGN - 1), %ebx
+	andl $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebx
 #else
 	movl $LOAD_PHYSICAL_ADDR, %ebx
 #endif
+	movl %ebx, %edi
 
 	/* Replace the compressed data size with the uncompressed size */
 	subl input_len(%ebp), %ebx
@@ -84,28 +90,29 @@ ENTRY(startup_32)
 	addl $4095, %ebx
 	andl $~4095, %ebx
 
+/*
+ * Setup the stack
+ */
+	leal boot_stack_end(%ebx), %esp
+	pushl %edi		/* Saved kernel target address */
+
 /* Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
 	pushl %esi
-	leal _end(%ebp), %esi
-	leal _end(%ebx), %edi
-	movl $(_end - startup_32), %ecx
+	leal (_bss-4)(%ebp), %esi
+	leal (_bss-4)(%ebx), %edi
+	movl $(_bss - startup_32), %ecx
+	shrl $2, %ecx
 	std
-	rep
-	movsb
+	rep; movsl
 	cld
 	popl %esi
 
-/* Compute the kernel start address.
+/*
+ * %ebp -> kernel target address
  */
-#ifdef CONFIG_RELOCATABLE
-	addl    $(CONFIG_PHYSICAL_ALIGN - 1), %ebp
-	andl    $(~(CONFIG_PHYSICAL_ALIGN - 1)), %ebp
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebp
-#endif
-
+	popl %ebp
 /*
  * Jump to the relocated address.
  */
@@ -119,18 +126,12 @@ relocated:
 /*
  * Clear BSS
  */
-	xorl %eax,%eax
-	leal _edata(%ebx),%edi
-	leal _end(%ebx), %ecx
-	subl %edi,%ecx
-	cld
-	rep
-	stosb
-
-/*
- * Setup the stack for the decompressor
- */
-	leal boot_stack_end(%ebx), %esp
+	xorl %eax, %eax
+	leal _bss(%ebx), %edi
+	leal (_ebss+3)(%ebx), %ecx
+	subl %edi, %ecx
+	shrl $2, %ecx
+	rep; stosl
 
 /*
  * Do the decompression, and jump to the new kernel..
@@ -178,14 +179,15 @@ relocated:
 /*
  * Jump to the decompressed kernel.
  */
-	xorl %ebx,%ebx
+	xorl %ebx, %ebx
 	jmp *%ebp
 
-.bss
 /* Stack and heap for uncompression */
-.balign 4
+	.bss
+	.balign 4
 boot_heap:
 	.fill BOOT_HEAP_SIZE, 1, 0
+	.section ".stack","aw"
 boot_stack:
 	.fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
diff --git a/arch/x86/boot/compressed/vmlinux_32.lds b/arch/x86/boot/compressed/vmlinux_32.lds
index bb3c483..952dc63 100644
--- a/arch/x86/boot/compressed/vmlinux_32.lds
+++ b/arch/x86/boot/compressed/vmlinux_32.lds
@@ -33,11 +33,19 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	. = ALIGN(4);
 	.bss : {
 		_bss = . ;
 		*(.bss)
 		*(.bss.*)
 		*(COMMON)
-		_end = . ;
+		_ebss = .;
 	}
+	. = ALIGN(4);
+	.stack : {
+		_stack = .;
+		*(.stack)
+		_estack = .;
+	}
+	_end = . ;
 }