powerpc: Make the 64-bit kernel as a position-independent executable

This implements CONFIG_RELOCATABLE for 64-bit by making the kernel as
a position-independent executable (PIE) when it is set.  This involves
processing the dynamic relocations in the image in the early stages of
booting, even if the kernel is being run at the address it is linked at,
since the linker does not necessarily fill in words in the image for
which there are dynamic relocations.  (In fact the linker does fill in
such words for 64-bit executables, though not for 32-bit executables,
so in principle we could avoid calling relocate() entirely when we're
running a 64-bit kernel at the linked address.)

The dynamic relocations are processed by a new function relocate(addr),
where the addr parameter is the virtual address where the image will be
run.  In fact we call it twice; once before calling prom_init, and again
when starting the main kernel.  This means that reloc_offset() returns
0 in prom_init (since it has been relocated to the address it is running
at), which necessitated a few adjustments.

This also changes __va and __pa to use an equivalent definition that is
simpler.  With the relocatable kernel, PAGE_OFFSET and MEMORY_START are
constants (for 64-bit) whereas PHYSICAL_START is a variable (and
KERNELBASE ideally should be too, but isn't yet).

With this, relocatable kernels still copy themselves down to physical
address 0 and run there.

Signed-off-by: Paul Mackerras <paulus@samba.org>

16 files changed, 181 insertions, 19 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 587da5e..17c988b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -806,6 +806,19 @@ config PIN_TLB
 endmenu
 
 if PPC64
+config RELOCATABLE
+	bool "Build a relocatable kernel"
+	help
+	  This builds a kernel image that is capable of running anywhere
+	  in the RMA (real memory area) at any 16k-aligned base address.
+	  The kernel is linked as a position-independent executable (PIE)
+	  and contains dynamic relocations which are processed early
+	  in the bootup process.
+
+	  One use is for the kexec on panic case where the recovery kernel
+	  must live at a different physical address than the primary
+	  kernel.
+
 config PAGE_OFFSET
 	hex
 	default "0xc000000000000000"
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index c6be19e..4df38cb 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -63,7 +63,9 @@ override CC	+= -m$(CONFIG_WORD_SIZE)
 override AR	:= GNUTARGET=elf$(CONFIG_WORD_SIZE)-powerpc $(AR)
 endif
 
-LDFLAGS_vmlinux	:= -Bstatic
+LDFLAGS_vmlinux-yy := -Bstatic
+LDFLAGS_vmlinux-$(CONFIG_PPC64)$(CONFIG_RELOCATABLE) := -pie
+LDFLAGS_vmlinux	:= $(LDFLAGS_vmlinux-yy)
 
 CFLAGS-$(CONFIG_PPC64)	:= -mminimal-toc -mtraceback=none  -mcall-aixdesc
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 -mmultiple
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 717a3bc..6403275 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -310,8 +310,11 @@ $(obj)/dtbImage.%: vmlinux $(wrapperbits) $(obj)/%.dtb
 $(obj)/vmlinux.strip: vmlinux
 	$(STRIP) -s -R .comment $< -o $@
 
+# The iseries hypervisor won't take an ET_DYN executable, so this
+# changes the type (byte 17) in the file to ET_EXEC (2).
 $(obj)/zImage.iseries: vmlinux
 	$(STRIP) -s -R .comment $< -o $@
+	printf "\x02" | dd of=$@ conv=notrunc bs=1 seek=17
 
 $(obj)/uImage: vmlinux $(wrapperbits)
 	$(call if_changed,wrap,uboot)
diff --git a/arch/powerpc/boot/elf_util.c b/arch/powerpc/boot/elf_util.c
index 7454aa4..1567a0c 100644
--- a/arch/powerpc/boot/elf_util.c
+++ b/arch/powerpc/boot/elf_util.c
@@ -27,7 +27,8 @@ int parse_elf64(void *hdr, struct elf_info *info)
 	      elf64->e_ident[EI_MAG3]  == ELFMAG3	&&
 	      elf64->e_ident[EI_CLASS] == ELFCLASS64	&&
 	      elf64->e_ident[EI_DATA]  == ELFDATA2MSB	&&
-	      elf64->e_type            == ET_EXEC	&&
+	      (elf64->e_type            == ET_EXEC ||
+	       elf64->e_type            == ET_DYN)	&&
 	      elf64->e_machine         == EM_PPC64))
 		return 0;
 
@@ -58,7 +59,8 @@ int parse_elf32(void *hdr, struct elf_info *info)
 	      elf32->e_ident[EI_MAG3]  == ELFMAG3	&&
 	      elf32->e_ident[EI_CLASS] == ELFCLASS32	&&
 	      elf32->e_ident[EI_DATA]  == ELFDATA2MSB	&&
-	      elf32->e_type            == ET_EXEC	&&
+	      (elf32->e_type            == ET_EXEC ||
+	       elf32->e_type            == ET_DYN)      &&
 	      elf32->e_machine         == EM_PPC))
 		return 0;
 
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index c2df53c..5a44174 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -437,7 +437,7 @@ typedef struct {
 	})
 #endif /* 1 */
 
-/* This is only valid for addresses >= KERNELBASE */
+/* This is only valid for addresses >= PAGE_OFFSET */
 static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
 {
 	if (ssize == MMU_SEGSIZE_256M)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index e088545..64e1445 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -71,15 +71,21 @@
 #define PAGE_OFFSET	ASM_CONST(CONFIG_PAGE_OFFSET)
 #define LOAD_OFFSET	ASM_CONST((CONFIG_KERNEL_START-CONFIG_PHYSICAL_START))
 
-#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_FLATMEM)
+#if defined(CONFIG_RELOCATABLE)
 #ifndef __ASSEMBLY__
 extern phys_addr_t memstart_addr;
 extern phys_addr_t kernstart_addr;
 #endif
 #define PHYSICAL_START	kernstart_addr
-#define MEMORY_START	memstart_addr
 #else
 #define PHYSICAL_START	ASM_CONST(CONFIG_PHYSICAL_START)
+#endif
+
+#ifdef CONFIG_PPC64
+#define MEMORY_START	0UL
+#elif defined(CONFIG_RELOCATABLE)
+#define MEMORY_START	memstart_addr
+#else
 #define MEMORY_START	(PHYSICAL_START + PAGE_OFFSET - KERNELBASE)
 #endif
 
@@ -92,8 +98,8 @@ extern phys_addr_t kernstart_addr;
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
-#define __va(x) ((void *)((unsigned long)(x) - PHYSICAL_START + KERNELBASE))
-#define __pa(x) ((unsigned long)(x) + PHYSICAL_START - KERNELBASE)
+#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - MEMORY_START))
+#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
 
 /*
  * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 7710e9e..baf318a 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -16,6 +16,12 @@ static inline int in_kernel_text(unsigned long addr)
 	return 0;
 }
 
+static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
+{
+	return start < (unsigned long)__init_end &&
+		(unsigned long)_stext < end;
+}
+
 #undef dereference_function_descriptor
 void *dereference_function_descriptor(void *);
 
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 49b49c0..16326fd 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   paca.o cpu_setup_ppc970.o \
 				   cpu_setup_pa6t.o \
 				   firmware.o nvram_64.o
+obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 6cdfd44..84856be 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -1360,6 +1360,12 @@ _INIT_STATIC(__boot_from_prom)
 	 */
 	rldicr	r1,r1,0,59
 
+#ifdef CONFIG_RELOCATABLE
+	/* Relocate code for where we are now */
+	mr	r3,r26
+	bl	.relocate
+#endif
+
 	/* Restore parameters */
 	mr	r3,r31
 	mr	r4,r30
@@ -1368,11 +1374,19 @@ _INIT_STATIC(__boot_from_prom)
 	mr	r7,r27
 
 	/* Do all of the interaction with OF client interface */
+	mr	r8,r26
 	bl	.prom_init
 	/* We never return */
 	trap
 
 _STATIC(__after_prom_start)
+#ifdef CONFIG_RELOCATABLE
+	/* process relocations for the final address of the kernel */
+	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
+	sldi	r25,r25,32
+	mr	r3,r25
+	bl	.relocate
+#endif
 
 /*
  * We need to run with _stext at physical address PHYSICAL_START.
@@ -1381,10 +1395,9 @@ _STATIC(__after_prom_start)
  *
  * Note: This process overwrites the OF exception vectors.
  */
-	LOAD_REG_IMMEDIATE(r3, PHYSICAL_START)	/* target addr */
-	cmpd	r3,r26			/* In some cases the loader may  */
+	li	r3,0			/* target addr */
+	mr.	r4,r26			/* In some cases the loader may  */
 	beq	9f			/* have already put us at zero */
-	mr	r4,r26			/* source address */
 	lis	r5,(copy_to_here - _stext)@ha
 	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 	li	r6,0x100		/* Start offset, the first 0x100 */
@@ -1617,6 +1630,13 @@ _INIT_STATIC(start_here_multiplatform)
 	ori	r6,r6,MSR_RI
 	mtmsrd	r6			/* RI on */
 
+#ifdef CONFIG_RELOCATABLE
+	/* Save the physical address we're running at in kernstart_addr */
+	LOAD_REG_ADDR(r4, kernstart_addr)
+	clrldi	r0,r25,2
+	std	r0,0(r4)
+#endif
+
 	/* The following gets the stack set up with the regs */
 	/* pointing to the real addr of the kernel stack.  This is   */
 	/* all done to support the C function call below which sets  */
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 623e8c3..48a3471 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -12,6 +12,7 @@
 
 #include <asm/lppaca.h>
 #include <asm/paca.h>
+#include <asm/sections.h>
 
 /* This symbol is provided by the linker - let it fill in the paca
  * field correctly */
@@ -79,7 +80,7 @@ void __init initialise_pacas(void)
 		new_paca->lock_token = 0x8000;
 		new_paca->paca_index = cpu;
 		new_paca->kernel_toc = kernel_toc;
-		new_paca->kernelbase = KERNELBASE;
+		new_paca->kernelbase = (unsigned long) _stext;
 		new_paca->kernel_msr = MSR_KERNEL;
 		new_paca->hw_cpu_id = 0xffff;
 		new_paca->slb_shadow_ptr = &slb_shadow[cpu];
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 09455e1..3a2dc7e 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -1192,6 +1192,9 @@ void __init early_init_devtree(void *params)
 
 	/* Reserve LMB regions used by kernel, initrd, dt, etc... */
 	lmb_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
+	/* If relocatable, reserve first 32k for interrupt vectors etc. */
+	if (PHYSICAL_START > MEMORY_START)
+		lmb_reserve(MEMORY_START, 0x8000);
 	reserve_kdump_trampoline();
 	reserve_crashkernel();
 	early_reserve_mem();
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1f89885..7cf274a 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2309,13 +2309,14 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 
 unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 			       unsigned long pp,
-			       unsigned long r6, unsigned long r7)
+			       unsigned long r6, unsigned long r7,
+			       unsigned long kbase)
 {	
 	struct prom_t *_prom;
 	unsigned long hdr;
-	unsigned long offset = reloc_offset();
 
 #ifdef CONFIG_PPC32
+	unsigned long offset = reloc_offset();
 	reloc_got2(offset);
 #endif
 
@@ -2349,9 +2350,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	RELOC(of_platform) = prom_find_machine_type();
 
+#ifndef CONFIG_RELOCATABLE
 	/* Bail if this is a kdump kernel. */
 	if (PHYSICAL_START > 0)
 		prom_panic("Error: You can't boot a kdump kernel from OF!\n");
+#endif
 
 	/*
 	 * Check for an initrd
@@ -2371,7 +2374,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Copy the CPU hold code
 	 */
 	if (RELOC(of_platform) != PLATFORM_POWERMAC)
-		copy_and_flush(0, KERNELBASE + offset, 0x100, 0);
+		copy_and_flush(0, kbase, 0x100, 0);
 
 	/*
 	 * Do early parsing of command line
@@ -2474,7 +2477,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	reloc_got2(-offset);
 #endif
 
-	__start(hdr, KERNELBASE + offset, 0);
+	__start(hdr, kbase, 0);
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
new file mode 100644
index 0000000..b47a0e1
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -0,0 +1,87 @@
+/*
+ * Code to process dynamic relocations in the kernel.
+ *
+ * Copyright 2008 Paul Mackerras, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+
+RELA = 7
+RELACOUNT = 0x6ffffff9
+R_PPC64_RELATIVE = 22
+
+/*
+ * r3 = desired final address of kernel
+ */
+_GLOBAL(relocate)
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r12		/* r12 has runtime addr of label 0 */
+	mtlr	r0
+	ld	r11,(p_dyn - 0b)(r12)
+	add	r11,r11,r12	/* r11 has runtime addr of .dynamic section */
+	ld	r9,(p_rela - 0b)(r12)
+	add	r9,r9,r12	/* r9 has runtime addr of .rela.dyn section */
+	ld	r10,(p_st - 0b)(r12)
+	add	r10,r10,r12	/* r10 has runtime addr of _stext */
+
+	/*
+	 * Scan the dynamic section for the RELA and RELACOUNT entries.
+	 */
+	li	r7,0
+	li	r8,0
+1:	ld	r6,0(r11)	/* get tag */
+	cmpdi	r6,0
+	beq	4f		/* end of list */
+	cmpdi	r6,RELA
+	bne	2f
+	ld	r7,8(r11)	/* get RELA pointer in r7 */
+	b	3f
+2:	addis	r6,r6,(-RELACOUNT)@ha
+	cmpdi	r6,RELACOUNT@l
+	bne	3f
+	ld	r8,8(r11)	/* get RELACOUNT value in r8 */
+3:	addi	r11,r11,16
+	b	1b
+4:	cmpdi	r7,0		/* check we have both RELA and RELACOUNT */
+	cmpdi	cr1,r8,0
+	beq	6f
+	beq	cr1,6f
+
+	/*
+	 * Work out linktime address of _stext and hence the
+	 * relocation offset to be applied.
+	 * cur_offset [r7] = rela.run [r9] - rela.link [r7]
+	 * _stext.link [r10] = _stext.run [r10] - cur_offset [r7]
+	 * final_offset [r3] = _stext.final [r3] - _stext.link [r10]
+	 */
+	subf	r7,r7,r9	/* cur_offset */
+	subf	r10,r7,r10
+	subf	r3,r10,r3	/* final_offset */
+
+	/*
+	 * Run through the list of relocations and process the
+	 * R_PPC64_RELATIVE ones.
+	 */
+	mtctr	r8
+5:	lwz	r0,12(9)	/* ELF64_R_TYPE(reloc->r_info) */
+	cmpwi	r0,R_PPC64_RELATIVE
+	bne	6f
+	ld	r6,0(r9)	/* reloc->r_offset */
+	ld	r0,16(r9)	/* reloc->r_addend */
+	add	r0,r0,r3
+	stdx	r0,r7,r6
+	addi	r9,r9,24
+	bdnz	5b
+
+6:	blr
+
+p_dyn:	.llong	__dynamic_start - 0b
+p_rela:	.llong	__rela_dyn_start - 0b
+p_st:	.llong	_stext - 0b
+
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 9f6c1ca..e6927fb 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -187,6 +187,21 @@ SECTIONS
 		*(.machine.desc)
 		__machine_desc_end = . ;
 	}
+	. = ALIGN(8);
+	.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) }
+	.dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
+	.dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
+	{
+		__dynamic_start = .;
+		*(.dynamic)
+	}
+	.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
+	.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
+	.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
+	{
+		__rela_dyn_start = .;
+		*(.rela*)
+	}
 
 	/* freed after init ends here */
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d666f71..09db4ef 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -194,7 +194,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		unsigned long tprot = prot;
 
 		/* Make kernel text executable */
-		if (in_kernel_text(vaddr))
+		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
 		hash = hpt_hash(va, shift, ssize);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 4ae3d00..40f72c2 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -787,7 +787,7 @@ static void __devinit smp_core99_kick_cpu(int nr)
 {
 	unsigned int save_vector;
 	unsigned long target, flags;
-	unsigned int *vector = (unsigned int *)(KERNELBASE+0x100);
+	unsigned int *vector = (unsigned int *)(PAGE_OFFSET+0x100);
 
 	if (nr < 0 || nr > 3)
 		return;
@@ -801,7 +801,7 @@ static void __devinit smp_core99_kick_cpu(int nr)
 	save_vector = *vector;
 
 	/* Setup fake reset vector that does
-	 *   b __secondary_start_pmac_0 + nr*8 - KERNELBASE
+	 *   b __secondary_start_pmac_0 + nr*8
 	 */
 	target = (unsigned long) __secondary_start_pmac_0 + nr * 8;
 	patch_branch(vector, target, BRANCH_SET_LINK);