[PATCH] x86-64: Relocatable Kernel Support

This patch modifies the x86_64 kernel so that it can be loaded and run
at any 2M aligned address, below 512G.  The technique used is to
compile the decompressor with -fPIC and modify it so the decompressor
is fully relocatable.  For the main kernel the page tables are
modified so the kernel remains at the same virtual address.  In
addition a variable phys_base is kept that holds the physical address
the kernel is loaded at.  __pa_symbol is modified to add that when
we take the address of a kernel symbol.

When loaded with a normal bootloader the decompressor will decompress
the kernel to 2M and it will run there.  This both ensures the
relocation code is always working, and makes it easier to use 2M
pages for the kernel and the cpu.

AK: changed to not make RELOCATABLE default in Kconfig

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andi Kleen <ak@suse.de>

arch/x86_64/Kconfig

@@ -565,23 +565,56 @@ config CRASH_DUMP
 	  PHYSICAL_START.
           For more details see Documentation/kdump/kdump.txt
 
+config RELOCATABLE
+	bool "Build a relocatable kernel(EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	help
+	  Builds a relocatable kernel. This enables loading and running
+	  a kernel binary from a different physical address than it has
+	  been compiled for.
+
+	  One use is for the kexec on panic case where the recovery kernel
+	  must live at a different physical address than the primary
+	  kernel.
+
+	  Note: If CONFIG_RELOCATABLE=y, then kernel run from the address
+	  it has been loaded at and compile time physical address
+	  (CONFIG_PHYSICAL_START) is ignored.
+
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
-	default "0x1000000" if CRASH_DUMP
 	default "0x200000"
 	help
-	  This gives the physical address where the kernel is loaded. Normally
-	  for regular kernels this value is 0x200000 (2MB). But in the case
-	  of kexec on panic the fail safe kernel needs to run at a different
-	  address than the panic-ed kernel. This option is used to set the load
-	  address for kernels used to capture crash dump on being kexec'ed
-	  after panic. The default value for crash dump kernels is
-	  0x1000000 (16MB). This can also be set based on the "X" value as
+	  This gives the physical address where the kernel is loaded. It
+	  should be aligned to 2MB boundary.
+
+	  If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then
+	  bzImage will decompress itself to above physical address and
+	  run from there. Otherwise, bzImage will run from the address where
+	  it has been loaded by the boot loader and will ignore above physical
+	  address.
+
+	  In normal kdump cases one does not have to set/change this option
+	  as now bzImage can be compiled as a completely relocatable image
+	  (CONFIG_RELOCATABLE=y) and be used to load and run from a different
+	  address. This option is mainly useful for the folks who don't want
+	  to use a bzImage for capturing the crash dump and want to use a
+	  vmlinux instead.
+
+	  So if you are using bzImage for capturing the crash dump, leave
+	  the value here unchanged to 0x200000 and set CONFIG_RELOCATABLE=y.
+	  Otherwise if you plan to use vmlinux for capturing the crash dump
+	  change this value to start of the reserved region (Typically 16MB
+	  0x1000000). In other words, it can be set based on the "X" value as
 	  specified in the "crashkernel=YM@XM" command line boot parameter
 	  passed to the panic-ed kernel. Typically this parameter is set as
 	  crashkernel=64M@16M. Please take a look at
 	  Documentation/kdump/kdump.txt for more details about crash dumps.
 
+	  Usage of bzImage for capturing the crash dump is advantageous as
+	  one does not have to build two kernels. Same kernel can be used
+	  as production kernel and capture kernel.
+
 	  Don't change this unless you know what you are doing.
 
 config SECCOMP

arch/x86_64/boot/compressed/Makefile

@@ -8,16 +8,14 @@
 
 targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o
 EXTRA_AFLAGS	:= -traditional
-AFLAGS		:= $(subst -m64,-m32,$(AFLAGS))
 
 # cannot use EXTRA_CFLAGS because base CFLAGS contains -mkernel which conflicts with
 # -m32
-CFLAGS := -m32 -D__KERNEL__ -Iinclude -O2  -fno-strict-aliasing
-LDFLAGS := -m elf_i386
+CFLAGS := -m64 -D__KERNEL__ -Iinclude -O2  -fno-strict-aliasing -fPIC -mcmodel=small -fno-builtin
+LDFLAGS := -m elf_x86_64
 
-LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -e startup_32 -m elf_i386
-
-$(obj)/vmlinux: $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE
+LDFLAGS_vmlinux := -T
+$(obj)/vmlinux: $(src)/vmlinux.lds $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o FORCE
 	$(call if_changed,ld)
 	@:
 
@@ -27,7 +25,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE
 $(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,gzip)
 
-LDFLAGS_piggy.o := -r --format binary --oformat elf32-i386 -T
+LDFLAGS_piggy.o := -r --format binary --oformat elf64-x86-64 -T
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,ld)