diff --git a/xen/arch/x86/boot/.gitignore b/xen/arch/x86/boot/.gitignore
index a379db7988..595cef6a2c 100644
--- a/xen/arch/x86/boot/.gitignore
+++ b/xen/arch/x86/boot/.gitignore
@@ -1,3 +1,5 @@
/mkelf32
-/*.bin
-/*.lnk
+/build32.*.lds
+/built-in-32.*.bin
+/built-in-32.*.map
+/built-in-32.S
diff --git a/xen/arch/x86/boot/Makefile b/xen/arch/x86/boot/Makefile
index 1199291d2b..230a99a1e5 100644
--- a/xen/arch/x86/boot/Makefile
+++ b/xen/arch/x86/boot/Makefile
@@ -1,4 +1,5 @@
obj-bin-y += head.o
+obj-bin-y += built-in-32.o
obj32 := cmdline.32.o
obj32 += reloc.32.o
@@ -9,9 +10,6 @@ targets += $(obj32)
obj32 := $(addprefix $(obj)/,$(obj32))
-$(obj)/head.o: AFLAGS-y += -Wa$(comma)-I$(obj)
-$(obj)/head.o: $(obj32:.32.o=.bin)
-
CFLAGS_x86_32 := $(subst -m64,-m32 -march=i686,$(XEN_TREEWIDE_CFLAGS))
$(call cc-options-add,CFLAGS_x86_32,CC,$(EMBEDDED_EXTRA_CFLAGS))
CFLAGS_x86_32 += -Werror -fno-builtin -g0 -msoft-float -mregparm=3
@@ -25,14 +23,66 @@ $(obj32): XEN_CFLAGS := $(CFLAGS_x86_32) -fpic
$(obj)/%.32.o: $(src)/%.c FORCE
$(call if_changed_rule,cc_o_c)
+orphan-handling-$(call ld-option,--orphan-handling=error) := --orphan-handling=error
LDFLAGS_DIRECT-$(call ld-option,--warn-rwx-segments) := --no-warn-rwx-segments
LDFLAGS_DIRECT += $(LDFLAGS_DIRECT-y)
LD32 := $(LD) $(subst x86_64,i386,$(LDFLAGS_DIRECT))
-%.bin: %.lnk
- $(OBJCOPY) -j .text -O binary $< $@
+# The parameters below tweak the generated linker scripts:
+# - text_gap: padding between .text section external symbols and code.
+# - text_diff: address of the .text section.
+#
+# Note external symbols are only affected by text_diff, while internal symbols
+# are affected by both text_diff and text_gap. Ensure the sum of gap and diff
+# is greater than 2^16 so that any 16bit relocations if present in the object
+# file turns into a build-time error.
+text_gap := 0x010200
+text_diff := 0x408020
-%.lnk: %.32.o $(src)/build32.lds
- $(LD32) -N -T $(filter %.lds,$^) -o $@ $<
+$(obj)/build32.base.lds: AFLAGS-y += -DGAP=$(text_gap) -DTEXT_DIFF=$(text_diff)
+$(obj)/build32.offset.lds: AFLAGS-y += -DGAP=$(text_gap) -DTEXT_DIFF=$(text_diff) -DFINAL
+$(obj)/build32.base.lds $(obj)/build32.offset.lds: $(src)/build32.lds.S FORCE
+ $(call if_changed_dep,cpp_lds_S)
-clean-files := *.lnk *.bin
+targets += build32.offset.lds build32.base.lds
+
+# Generate a single 32bit object.
+#
+# Resolve any relocations resulting from references between the translation
+# units. This ensures the same combined object file can be used to generate
+# multiple images with slightly different linker scripts.
+$(obj)/built-in-32.tmp.o: $(obj32)
+ $(LD32) -r -o $@ $^
+
+# Link bundle with a given layout and extract a binary from it.
+# The linker will allocate GOP and resolve symbols specified in the linker
+# script.
+# The conversion to binary avoids polluting global symbols not used externally;
+# also removes conflict with needed 64 bit GOP.
+# If possible we use --orphan-handling=error option to make sure we account
+# for all possible sections from C code.
+$(obj)/built-in-32.%.bin: $(obj)/build32.%.lds $(obj)/built-in-32.tmp.o
+ $(LD32) $(orphan-handling-y) -N -T $< -Map $(@:bin=map) -o $(@:bin=o) $(filter %.o,$^)
+ $(OBJCOPY) -j .text -O binary $(@:bin=o) $@
+ rm -f $(@:bin=o)
+
+quiet_cmd_combine = GEN $@
+cmd_combine = \
+ $(PYTHON) $(srctree)/tools/combine_two_binaries.py \
+ --gap $(text_gap) \
+ --text-diff $(text_diff) \
+ --script $(obj)/build32.offset.lds \
+ --bin1 $(obj)/built-in-32.base.bin \
+ --bin2 $(obj)/built-in-32.offset.bin \
+ --map $(obj)/built-in-32.offset.map \
+ --exports cmdline_parse_early,reloc \
+ --output $@
+
+targets += built-in-32.S
+
+# generate final object file combining and checking above binaries
+$(obj)/built-in-32.S: $(obj)/built-in-32.base.bin $(obj)/built-in-32.offset.bin \
+ $(srctree)/tools/combine_two_binaries.py FORCE
+ $(call if_changed,combine)
+
+clean-files := built-in-32.*.bin built-in-32.*.map build32.*.lds
diff --git a/xen/arch/x86/boot/build32.lds b/xen/arch/x86/boot/build32.lds.S
similarity index 66%
rename from xen/arch/x86/boot/build32.lds
rename to xen/arch/x86/boot/build32.lds.S
index 56edaa727b..d1b9dc6689 100644
--- a/xen/arch/x86/boot/build32.lds
+++ b/xen/arch/x86/boot/build32.lds.S
@@ -15,12 +15,37 @@
* with this program. If not, see .
*/
-ENTRY(_start)
+#ifdef FINAL
+# undef GAP
+# define GAP 0
+# define MULT 0
+# define TEXT_START
+#else
+# define MULT 1
+# define TEXT_START TEXT_DIFF
+#endif
+#define DECLARE_IMPORT(name) name = . + (__LINE__ * MULT)
+
+ENTRY(dummy_start)
SECTIONS
{
/* Merge code and data into one section. */
- .text : {
+ .text TEXT_START : {
+ /* Silence linker warning, we are not going to use it */
+ dummy_start = .;
+
+ /*
+ * Any symbols used should be declared below, this ensures which
+ * symbols are visible to the 32bit C boot code.
+ * With the exception of using external 32 bit function (maybe
+ * exported by head.S) they should point all to variables.
+ * Attention should be paid to pointers taking care of possible later
+ * relocation.
+ */
+ DECLARE_IMPORT(__base_relocs_start);
+ DECLARE_IMPORT(__base_relocs_end);
+ . = . + GAP;
*(.text)
*(.text.*)
*(.data)
@@ -30,7 +55,11 @@ SECTIONS
*(.bss)
*(.bss.*)
}
-
+ /DISCARD/ : {
+ *(.comment)
+ *(.comment.*)
+ *(.note.*)
+ }
/* Dynamic linkage sections. Collected simply so we can check they're empty. */
.got : {
*(.got)
diff --git a/xen/arch/x86/boot/cmdline.c b/xen/arch/x86/boot/cmdline.c
index fc9241ede9..196c580e91 100644
--- a/xen/arch/x86/boot/cmdline.c
+++ b/xen/arch/x86/boot/cmdline.c
@@ -18,18 +18,6 @@
* Linux kernel source (linux/lib/string.c).
*/
-/*
- * This entry point is entered from xen/arch/x86/boot/head.S with:
- * - %eax = &cmdline,
- * - %edx = &early_boot_opts.
- */
-asm (
- " .text \n"
- " .globl _start \n"
- "_start: \n"
- " jmp cmdline_parse_early \n"
- );
-
#include
#include
#include
diff --git a/xen/arch/x86/boot/head.S b/xen/arch/x86/boot/head.S
index c4de1dfab5..e0776e3896 100644
--- a/xen/arch/x86/boot/head.S
+++ b/xen/arch/x86/boot/head.S
@@ -759,18 +759,6 @@ trampoline_setup:
/* Jump into the relocated trampoline. */
lret
- /*
- * cmdline and reloc are written in C, and linked to be 32bit PIC with
- * entrypoints at 0 and using the fastcall convention.
- */
-FUNC_LOCAL(cmdline_parse_early)
- .incbin "cmdline.bin"
-END(cmdline_parse_early)
-
-FUNC_LOCAL(reloc)
- .incbin "reloc.bin"
-END(reloc)
-
ENTRY(trampoline_start)
#include "trampoline.S"
ENTRY(trampoline_end)
diff --git a/xen/arch/x86/boot/reloc.c b/xen/arch/x86/boot/reloc.c
index 8c58affcd9..94b078d7b1 100644
--- a/xen/arch/x86/boot/reloc.c
+++ b/xen/arch/x86/boot/reloc.c
@@ -12,20 +12,6 @@
* Daniel Kiper
*/
-/*
- * This entry point is entered from xen/arch/x86/boot/head.S with:
- * - %eax = MAGIC,
- * - %edx = INFORMATION_ADDRESS,
- * - %ecx = TOPMOST_LOW_MEMORY_STACK_ADDRESS.
- * - 0x04(%esp) = BOOT_VIDEO_INFO_ADDRESS.
- */
-asm (
- " .text \n"
- " .globl _start \n"
- "_start: \n"
- " jmp reloc \n"
- );
-
#include
#include
#include
diff --git a/xen/tools/combine_two_binaries.py b/xen/tools/combine_two_binaries.py
new file mode 100755
index 0000000000..447c0d3bdb
--- /dev/null
+++ b/xen/tools/combine_two_binaries.py
@@ -0,0 +1,220 @@
+#!/usr/bin/env python3
+
+from __future__ import print_function
+import argparse
+import functools
+import re
+import struct
+import sys
+
+parser = argparse.ArgumentParser(description='Generate assembly file to merge into other code.')
+auto_int = functools.update_wrapper(lambda x: int(x, 0), int) # allows hex
+parser.add_argument('--script', dest='script',
+ required=True,
+ help='Linker script for extracting symbols')
+parser.add_argument('--bin1', dest='bin1',
+ required=True,
+ help='First binary')
+parser.add_argument('--bin2', dest='bin2',
+ required=True,
+ help='Second binary')
+parser.add_argument('--gap', dest='gap',
+ required=True,
+ type=auto_int,
+ help='Gap inserted at the start of code section')
+parser.add_argument('--text-diff', dest='text_diff',
+ required=True,
+ type=auto_int,
+ help='Difference between code section start')
+parser.add_argument('--output', dest='output',
+ help='Output file')
+parser.add_argument('--map', dest='mapfile',
+ help='Map file to read for symbols to export')
+parser.add_argument('--exports', dest='exports',
+ help='Symbols to export')
+parser.add_argument('--section-header', dest='section_header',
+ default='.section .init.text, "ax", @progbits',
+ help='Section header declaration')
+parser.add_argument('-v', '--verbose',
+ action='store_true')
+args = parser.parse_args()
+
+gap = args.gap
+text_diff = args.text_diff
+
+# Parse linker script for external symbols to use.
+# Next regex matches expanded DECLARE_IMPORT lines in linker script.
+symbol_re = re.compile(r'\s+(\S+)\s*=\s*\.\s*\+\s*\((\d+)\s*\*\s*0\s*\)\s*;')
+symbols = {}
+lines = {}
+for line in open(args.script):
+ m = symbol_re.match(line)
+ if not m:
+ continue
+ (name, line_num) = (m.group(1), int(m.group(2)))
+ if line_num == 0:
+ raise Exception("Invalid line number found:\n\t" + line)
+ if line_num in symbols:
+ raise Exception("Symbol with this line already present:\n\t" + line)
+ if name in lines:
+ raise Exception("Symbol with this name already present:\n\t" + name)
+ symbols[line_num] = name
+ lines[name] = line_num
+
+exports = []
+if args.exports is not None:
+ exports = dict([(name, None) for name in args.exports.split(',')])
+
+# Parse mapfile, look for ther symbols we want to export.
+if args.mapfile is not None:
+ symbol_re = re.compile(r'\s{15,}0x([0-9a-f]+)\s+(\S+)\n')
+ for line in open(args.mapfile):
+ m = symbol_re.match(line)
+ if not m or m.group(2) not in exports:
+ continue
+ addr = int(m.group(1), 16)
+ exports[m.group(2)] = addr
+for (name, addr) in exports.items():
+ if addr is None:
+ raise Exception("Required export symbols %s not found" % name)
+
+file1 = open(args.bin1, 'rb')
+file2 = open(args.bin2, 'rb')
+file1.seek(0, 2)
+size1 = file1.tell()
+file2.seek(0, 2)
+size2 = file2.tell()
+if size1 > size2:
+ file1, file2 = file2, file1
+ size1, size2 = size2, size1
+if size2 != size1 + gap:
+ raise Exception('File sizes do not match')
+del size2
+
+file1.seek(0, 0)
+data1 = file1.read(size1)
+del file1
+file2.seek(gap, 0)
+data2 = file2.read(size1)
+del file2
+
+max_line = max(symbols.keys())
+
+def to_int32(n):
+ '''Convert a number to signed 32 bit integer truncating if needed'''
+ mask = (1 << 32) - 1
+ h = 1 << 31
+ return (n & mask) ^ h - h
+
+i = 0
+references = {}
+internals = 0
+while i <= size1 - 4:
+ n1 = struct.unpack('= 10:
+ break
+ continue
+ # This is a relative relocation to a symbol, accepted, code/data is
+ # relocatable.
+ if diff < gap and diff >= gap - max_line:
+ n = gap - diff
+ symbol = symbols.get(n)
+ # check we have a symbol
+ if symbol is None:
+ raise Exception("Cannot find symbol for line %d" % n)
+ pos = i - 1
+ if args.verbose:
+ print('Position %#x %d %s' % (pos, n, symbol), file=sys.stderr)
+ i += 3
+ references[pos] = symbol
+ continue
+ # First byte is the same, move to next byte
+ if diff & 0xff == 0 and i <= size1 - 4:
+ continue
+ # Probably a type of relocation we don't want or support
+ pos = i - 1
+ suggestion = ''
+ symbol = symbols.get(-diff - text_diff)
+ if symbol is not None:
+ suggestion = " Maybe %s is not defined as hidden?" % symbol
+ raise Exception("Unexpected difference found at %#x "
+ "n1=%#x n2=%#x diff=%#x gap=%#x.%s" % \
+ (pos, n1, n2, diff, gap, suggestion))
+if internals != 0:
+ raise Exception("Previous relocations found")
+
+def line_bytes(buf, out):
+ '''Output an assembly line with all bytes in "buf"'''
+ # Python 2 compatibility
+ if type(buf) == str:
+ print("\t.byte " + ','.join([str(ord(c)) for c in buf]), file=out)
+ else:
+ print("\t.byte " + ','.join([str(n) for n in buf]), file=out)
+
+def part(start, end, out):
+ '''Output bytes of "data" from "start" to "end"'''
+ while start < end:
+ e = min(start + 16, end)
+ line_bytes(data1[start:e], out)
+ start = e
+
+def reference(pos, out):
+ name = references[pos]
+ n = struct.unpack('= (1 << 31):
+ n -= (1 << 32)
+ n += pos
+ if n < 0:
+ n = -n
+ sign = '-'
+ print("\t.hidden %s\n"
+ "\t.long %s %s %#x - ." % (name, name, sign, n),
+ file=out)
+
+def output(out):
+ prev = 0
+ exports_by_addr = {}
+ for (sym, addr) in exports.items():
+ exports_by_addr.setdefault(addr, []).append(sym)
+ positions = list(references.keys())
+ positions += list(exports_by_addr.keys())
+ for pos in sorted(positions):
+ part(prev, pos, out)
+ prev = pos
+ if pos in references:
+ reference(pos, out)
+ prev = pos + 4
+ if pos in exports_by_addr:
+ for sym in exports_by_addr[pos]:
+ print("\t.global %s\n"
+ "\t.hidden %s\n"
+ "%s:" % (sym, sym, sym),
+ file=out)
+ part(prev, size1, out)
+
+out = sys.stdout
+if args.output is not None:
+ out = open(args.output, 'w')
+print('''/*
+ * File autogenerated by combine_two_binaries.py DO NOT EDIT
+ */''', file=out)
+print('\t' + args.section_header, file=out)
+print('obj32_start:', file=out)
+output(out)
+print('\n\t.section .note.GNU-stack,"",@progbits', file=out)
+out.flush()