powerpc: Process dynamic relocations for kernel

The following patch implements the dynamic relocation processing for
PPC32 kernel. relocate() accepts the target virtual address and relocates
 the kernel image to the same.

Currently the following relocation types are handled :

	R_PPC_RELATIVE
	R_PPC_ADDR16_LO
	R_PPC_ADDR16_HI
	R_PPC_ADDR16_HA

The last 3 relocations in the above list depends on value of Symbol indexed
whose index is encoded in the Relocation entry. Hence we need the Symbol
Table for processing such relocations.

Note: The GNU ld for ppc32 produces buggy relocations for relocation types
that depend on symbols. The value of the symbols with STB_LOCAL scope
should be assumed to be zero. - Alan Modra

Signed-off-by: Suzuki K. Poulose <suzuki@in.ibm.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@linux.vnet.ibm.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Alan Modra <amodra@au1.ibm.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Signed-off-by: Josh Boyer <jwboyer@gmail.com>

6 files changed, 256 insertions, 23 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8b323b7b0a61..2ad5ea827820 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -847,23 +847,30 @@ config DYNAMIC_MEMSTART
           load address. When this option is enabled, the compile time physical 
           address CONFIG_PHYSICAL_START is ignored.
 
-# Mapping based RELOCATABLE is moved to DYNAMIC_MEMSTART
-# config RELOCATABLE
-#       bool "Build a relocatable kernel (EXPERIMENTAL)"
-#       depends on EXPERIMENTAL && ADVANCED_OPTIONS && FLATMEM && (FSL_BOOKE || PPC_47x)
-#       help
-#         This builds a kernel image that is capable of running at the
-#         location the kernel is loaded at, without any alignment restrictions.
-#
-#         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 the kernel runs from the address
-#         it has been loaded at and the compile time physical addresses
-#         CONFIG_PHYSICAL_START is ignored.  However CONFIG_PHYSICAL_START
-#         setting can still be useful to bootwrappers that need to know the
-#         load location of the kernel (eg. u-boot/mkimage).
+          This option is overridden by CONFIG_RELOCATABLE
+
+config RELOCATABLE
+        bool "Build a relocatable kernel (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && ADVANCED_OPTIONS && FLATMEM
+        select NONSTATIC_KERNEL
+        help
+          This builds a kernel image that is capable of running at the
+          location the kernel is loaded at, without any alignment restrictions.
+          This feature is a superset of DYNAMIC_MEMSTART and hence overrides it.
+
+          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 the kernel runs from the address
+          it has been loaded at and the compile time physical addresses
+          CONFIG_PHYSICAL_START is ignored.  However CONFIG_PHYSICAL_START
+          setting can still be useful to bootwrappers that need to know the
+          load address of the kernel (eg. u-boot/mkimage).
+
+config RELOCATABLE_PPC32
+        def_bool y
+        depends on PPC32 && RELOCATABLE
 
 config PAGE_OFFSET_BOOL
         bool "Set custom page offset address"
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index ffe4d88f5a8a..b8b105c01c64 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -63,9 +63,9 @@ override CC	+= -m$(CONFIG_WORD_SIZE)
 override AR     := GNUTARGET=elf$(CONFIG_WORD_SIZE)-powerpc $(AR)
 endif
 
-LDFLAGS_vmlinux-yy := -Bstatic
-LDFLAGS_vmlinux-$(CONFIG_PPC64)$(CONFIG_RELOCATABLE) := -pie
-LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-yy)
+LDFLAGS_vmlinux-y := -Bstatic
+LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
+LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y)
 
 CFLAGS-$(CONFIG_PPC64)  := -mminimal-toc -mtraceback=no -mcall-aixdesc
 CFLAGS-$(CONFIG_PPC32)  := -ffixed-r2 -mmultiple
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ce4f7f179117..ee728e433aa2 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -85,6 +85,8 @@ extra-$(CONFIG_FSL_BOOKE)	:= head_fsl_booke.o
 extra-$(CONFIG_8xx)             := head_8xx.o
 extra-y                         += vmlinux.lds
 
+obj-$(CONFIG_RELOCATABLE_PPC32) += reloc_32.o
+
 obj-$(CONFIG_PPC32)             += entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)             += dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)              += kgdb.o
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
new file mode 100644
index 000000000000..ef46ba6e094f
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -0,0 +1,208 @@
+/*
+ * Code to process dynamic relocations for PPC32.
+ *
+ * Copyrights (C) IBM Corporation, 2011.
+ *      Author: Suzuki Poulose <suzuki@in.ibm.com>
+ *
+ *  - Based on ppc64 code - reloc_64.S
+ *
+ *  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>
+
+/* Dynamic section table entry tags */
+DT_RELA = 7                     /* Tag for Elf32_Rela section */
+DT_RELASZ = 8                   /* Size of the Rela relocs */
+DT_RELAENT = 9                  /* Size of one Rela reloc entry */
+
+STN_UNDEF = 0                   /* Undefined symbol index */
+STB_LOCAL = 0                   /* Local binding for the symbol */
+
+R_PPC_ADDR16_LO = 4             /* Lower half of (S+A) */
+R_PPC_ADDR16_HI = 5             /* Upper half of (S+A) */
+R_PPC_ADDR16_HA = 6             /* High Adjusted (S+A) */
+R_PPC_RELATIVE = 22
+
+/*
+ * r3 = desired final address
+ */
+
+_GLOBAL(relocate)
+
+        mflr    r0              /* Save our LR */
+        bl      0f              /* Find our current runtime address */
+0:      mflr    r12             /* Make it accessible */
+        mtlr    r0
+
+        lwz     r11, (p_dyn - 0b)(r12)
+        add     r11, r11, r12   /* runtime address of .dynamic section */
+        lwz     r9, (p_rela - 0b)(r12)
+        add     r9, r9, r12     /* runtime address of .rela.dyn section */
+        lwz     r10, (p_st - 0b)(r12)
+        add     r10, r10, r12   /* runtime address of _stext section */
+        lwz     r13, (p_sym - 0b)(r12)
+        add     r13, r13, r12   /* runtime address of .dynsym section */
+
+        /*
+         * Scan the dynamic section for RELA, RELASZ entries
+         */
+        li      r6, 0
+        li      r7, 0
+        li      r8, 0
+1:      lwz     r5, 0(r11)      /* ELF_Dyn.d_tag */
+        cmpwi   r5, 0           /* End of ELF_Dyn[] */
+        beq     eodyn
+        cmpwi   r5, DT_RELA
+        bne     relasz
+        lwz     r7, 4(r11)      /* r7 = rela.link */
+        b       skip
+relasz:
+        cmpwi   r5, DT_RELASZ
+        bne     relaent
+        lwz     r8, 4(r11)      /* r8 = Total Rela relocs size */
+        b       skip
+relaent:
+        cmpwi   r5, DT_RELAENT
+        bne     skip
+        lwz     r6, 4(r11)      /* r6 = Size of one Rela reloc */
+skip:
+        addi    r11, r11, 8
+        b       1b
+eodyn:                          /* End of Dyn Table scan */
+
+        /* Check if we have found all the entries */
+        cmpwi   r7, 0
+        beq     done
+        cmpwi   r8, 0
+        beq     done
+        cmpwi   r6, 0
+        beq     done
+
+
+        /*
+         * Work out the current offset from the link time address of .rela
+         * section.
+         *  cur_offset[r7] = rela.run[r9] - rela.link [r7]
+         *  _stext.link[r12] = _stext.run[r10] - cur_offset[r7]
+         *  final_offset[r3] = _stext.final[r3] - _stext.link[r12]
+         */
+        subf    r7, r7, r9      /* cur_offset */
+        subf    r12, r7, r10
+        subf    r3, r12, r3     /* final_offset */
+
+        subf    r8, r6, r8      /* relaz -= relaent */
+        /*
+         * Scan through the .rela table and process each entry
+         * r9   - points to the current .rela table entry
+         * r13  - points to the symbol table
+         */
+
+        /*
+         * Check if we have a relocation based on symbol
+         * r5 will hold the value of the symbol.
+         */
+applyrela:
+        lwz     r4, 4(r9)               /* r4 = rela.r_info */
+        srwi    r5, r4, 8               /* ELF32_R_SYM(r_info) */
+        cmpwi   r5, STN_UNDEF   /* sym == STN_UNDEF ? */
+        beq     get_type        /* value = 0 */
+        /* Find the value of the symbol at index(r5) */
+        slwi    r5, r5, 4               /* r5 = r5 * sizeof(Elf32_Sym) */
+        add     r12, r13, r5    /* r12 = &__dyn_sym[Index] */
+
+        /*
+         * GNU ld has a bug, where dynamic relocs based on
+         * STB_LOCAL symbols, the value should be assumed
+         * to be zero. - Alan Modra
+         */
+        /* XXX: Do we need to check if we are using GNU ld ? */
+        lbz     r5, 12(r12)     /* r5 = dyn_sym[Index].st_info */
+        extrwi  r5, r5, 4, 24   /* r5 = ELF32_ST_BIND(r5) */
+        cmpwi   r5, STB_LOCAL   /* st_value = 0, ld bug */
+        beq     get_type        /* We have r5 = 0 */
+        lwz     r5, 4(r12)      /* r5 = __dyn_sym[Index].st_value */
+
+get_type:
+        /* Load the relocation type to r4 */
+        extrwi  r4, r4, 8, 24   /* r4 = ELF32_R_TYPE(r_info) = ((char*)r4)[3] */
+
+        /* R_PPC_RELATIVE */
+        cmpwi   r4, R_PPC_RELATIVE
+        bne     hi16
+        lwz     r4, 0(r9)       /* r_offset */
+        lwz     r0, 8(r9)       /* r_addend */
+        add     r0, r0, r3      /* final addend */
+        stwx    r0, r4, r7      /* memory[r4+r7]) = (u32)r0 */
+        b       nxtrela         /* continue */
+
+        /* R_PPC_ADDR16_HI */
+hi16:
+        cmpwi   r4, R_PPC_ADDR16_HI
+        bne     ha16
+        lwz     r4, 0(r9)       /* r_offset */
+        lwz     r0, 8(r9)       /* r_addend */
+        add     r0, r0, r3
+        add     r0, r0, r5      /* r0 = (S+A+Offset) */
+        extrwi  r0, r0, 16, 0   /* r0 = (r0 >> 16) */
+        b       store_half
+
+        /* R_PPC_ADDR16_HA */
+ha16:
+        cmpwi   r4, R_PPC_ADDR16_HA
+        bne     lo16
+        lwz     r4, 0(r9)       /* r_offset */
+        lwz     r0, 8(r9)       /* r_addend */
+        add     r0, r0, r3
+        add     r0, r0, r5      /* r0 = (S+A+Offset) */
+        extrwi  r5, r0, 1, 16   /* Extract bit 16 */
+        extrwi  r0, r0, 16, 0   /* r0 = (r0 >> 16) */
+        add     r0, r0, r5      /* Add it to r0 */
+        b       store_half
+
+        /* R_PPC_ADDR16_LO */
+lo16:
+        cmpwi   r4, R_PPC_ADDR16_LO
+        bne     nxtrela
+        lwz     r4, 0(r9)       /* r_offset */
+        lwz     r0, 8(r9)       /* r_addend */
+        add     r0, r0, r3
+        add     r0, r0, r5      /* r0 = (S+A+Offset) */
+        extrwi  r0, r0, 16, 16  /* r0 &= 0xffff */
+        /* Fall through to */
+
+        /* Store half word */
+store_half:
+        sthx    r0, r4, r7      /* memory[r4+r7] = (u16)r0 */
+
+nxtrela:
+        /*
+         * We have to flush the modified instructions to the
+         * main storage from the d-cache. And also, invalidate the
+         * cached instructions in i-cache which has been modified.
+         *
+         * We delay the sync / isync operation till the end, since
+         * we won't be executing the modified instructions until
+         * we return from here.
+         */
+        dcbst   r4,r7
+        sync                    /* Ensure the data is flushed before icbi */
+        icbi    r4,r7
+        cmpwi   r8, 0           /* relasz = 0 ? */
+        ble     done
+        add     r9, r9, r6      /* move to next entry in the .rela table */
+        subf    r8, r6, r8      /* relasz -= relaent */
+        b       applyrela
+
+done:
+        sync                    /* Wait for the flush to finish */
+        isync                   /* Discard prefetched instructions */
+        blr
+
+p_dyn:          .long   __dynamic_start - 0b
+p_rela:         .long   __rela_dyn_start - 0b
+p_sym:          .long   __dynamic_symtab - 0b
+p_st:           .long   _stext - 0b
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 920276c0f6a1..710a54005dfb 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -170,7 +170,13 @@ SECTIONS
         }
 #ifdef CONFIG_RELOCATABLE
         . = ALIGN(8);
-        .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) }
+        .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET)
+        {
+#ifdef CONFIG_RELOCATABLE_PPC32
+                __dynamic_symtab = .;
+#endif
+                *(.dynsym)
+        }
         .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
         .dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
         {
diff --git a/arch/powerpc/relocs_check.pl b/arch/powerpc/relocs_check.pl
index d2571096c3e9..7f5b83808862 100755
--- a/arch/powerpc/relocs_check.pl
+++ b/arch/powerpc/relocs_check.pl
@@ -32,8 +32,18 @@ while (<FD>) {
         next if (!/\s+R_/);
 
         # These relocations are okay
-        next if (/R_PPC64_RELATIVE/ or /R_PPC64_NONE/ or
-                 /R_PPC64_ADDR64\s+mach_/);
+        # On PPC64:
+        #       R_PPC64_RELATIVE, R_PPC64_NONE, R_PPC64_ADDR64
+        # On PPC:
+        #       R_PPC_RELATIVE, R_PPC_ADDR16_HI, 
+        #       R_PPC_ADDR16_HA,R_PPC_ADDR16_LO,
+        #       R_PPC_NONE
+
+        next if (/\bR_PPC64_RELATIVE\b/ or /\bR_PPC64_NONE\b/ or
+                 /\bR_PPC64_ADDR64\s+mach_/);
+        next if (/\bR_PPC_ADDR16_LO\b/ or /\bR_PPC_ADDR16_HI\b/ or
+                 /\bR_PPC_ADDR16_HA\b/ or /\bR_PPC_RELATIVE\b/ or
+                 /\bR_PPC_NONE\b/);
 
         # If we see this type of relcoation it's an idication that
         # we /may/ be using an old version of binutils.