Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

14 files changed, 2816 insertions, 0 deletions

diff --git a/arch/x86/tools/.gitignore b/arch/x86/tools/.gitignore
new file mode 100644
index 000000000..51d5c22b3
--- /dev/null
+++ b/arch/x86/tools/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+relocs
+vdso2c
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
new file mode 100644
index 000000000..39a183fff
--- /dev/null
+++ b/arch/x86/tools/Makefile
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0
+PHONY += posttest
+
+ifneq ($(findstring 1, $(KBUILD_VERBOSE)),)
+  posttest_verbose = -v
+else
+  posttest_verbose =
+endif
+
+ifeq ($(CONFIG_64BIT),y)
+  posttest_64bit = -y
+else
+  posttest_64bit = -n
+endif
+
+reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk
+chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk
+
+quiet_cmd_posttest = TEST    $@
+      cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose)
+
+quiet_cmd_sanitytest = TEST    $@
+      cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
+
+posttest: $(obj)/insn_decoder_test vmlinux $(obj)/insn_sanity
+	$(call cmd,posttest)
+	$(call cmd,sanitytest)
+
+hostprogs += insn_decoder_test insn_sanity
+
+# -I needed for generated C source and C source which in the kernel tree.
+HOSTCFLAGS_insn_decoder_test.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
+
+HOSTCFLAGS_insn_sanity.o := -Wall -I$(srctree)/tools/arch/x86/lib/ -I$(srctree)/tools/arch/x86/include/ -I$(objtree)/arch/x86/lib/
+
+# Dependencies are also needed.
+$(obj)/insn_decoder_test.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+
+$(obj)/insn_sanity.o: $(srctree)/tools/arch/x86/lib/insn.c $(srctree)/tools/arch/x86/lib/inat.c $(srctree)/tools/arch/x86/include/asm/inat_types.h $(srctree)/tools/arch/x86/include/asm/inat.h $(srctree)/tools/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi \
+		    -I$(srctree)/arch/$(SUBARCH)/include/uapi
+
+hostprogs	+= relocs vdso2c
+relocs-objs	:= relocs_32.o relocs_64.o relocs_common.o
+
+always-y	:= $(hostprogs)
+
+PHONY += $(hostprogs)
+$(hostprogs): %: $(obj)/%
+	@:
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
new file mode 100755
index 000000000..173d5bf2d
--- /dev/null
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -0,0 +1,88 @@
+#!/usr/bin/awk
+#
+# Convert cpufeatures.h to a list of compile-time masks
+# Note: this blithely assumes that each word has at least one
+# feature defined in it; if not, something else is wrong!
+#
+
+BEGIN {
+	printf "#ifndef _ASM_X86_CPUFEATUREMASKS_H\n";
+	printf "#define _ASM_X86_CPUFEATUREMASKS_H\n\n";
+
+	file = 0
+}
+
+FNR == 1 {
+	++file;
+
+	# arch/x86/include/asm/cpufeatures.h
+	if (file == 1)
+		FS = "[ \t()*+]+";
+
+	# .config
+	if (file == 2)
+		FS = "=";
+}
+
+# Create a dictionary of sorts, containing all defined feature bits
+file == 1 && $1 ~ /^#define$/ && $2 ~ /^X86_FEATURE_/ {
+	nfeat = $3 * $4 + $5;
+	feat = $2;
+	sub(/^X86_FEATURE_/, "", feat);
+	feats[nfeat] = feat;
+}
+file == 1 && $1 ~ /^#define$/ && $2 == "NCAPINTS" {
+	ncapints = int($3);
+}
+
+# Create a dictionary featstat[REQUIRED|DISABLED, FEATURE_NAME] = on | off
+file == 2 && $1 ~ /^CONFIG_X86_(REQUIRED|DISABLED)_FEATURE_/ {
+	on = ($2 == "y");
+	if (split($1, fs, "CONFIG_X86_|_FEATURE_") == 3)
+		featstat[fs[2], fs[3]] = on;
+}
+
+END {
+	sets[1] = "REQUIRED";
+	sets[2] = "DISABLED";
+
+	for (ns in sets) {
+		s = sets[ns];
+
+		printf "/*\n";
+		printf " * %s features:\n", s;
+		printf " *\n";
+		fstr = "";
+		for (i = 0; i < ncapints; i++) {
+			mask = 0;
+			for (j = 0; j < 32; j++) {
+				feat = feats[i*32 + j];
+				if (featstat[s, feat]) {
+					nfstr = fstr " " feat;
+					if (length(nfstr) > 72) {
+						printf " *   %s\n", fstr;
+						nfstr = " " feat;
+					}
+					fstr = nfstr;
+					mask += (2 ^ j);
+				}
+			}
+			masks[i] = mask;
+		}
+		printf " *   %s\n */\n", fstr;
+
+		for (i = 0; i < ncapints; i++)
+			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
+
+		printf "\n#define %s_MASK_BIT_SET(x)\t\t\t\\\n", s;
+		printf "\t((\t\t\t\t\t";
+		for (i = 0; i < ncapints; i++) {
+			if (masks[i])
+				printf "\t\\\n\t\t((x) >> 5) == %2d ? %s_MASK%d :", i, s, i;
+		}
+		printf " 0\t\\\n";
+		printf "\t) & (1U << ((x) & 31)))\n\n";
+	}
+
+	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";
+}
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
new file mode 100644
index 000000000..7ea1b75e5
--- /dev/null
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -0,0 +1,505 @@
+#!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
+# gen-insn-attr-x86.awk: Instruction attribute table generator
+# Written by Masami Hiramatsu <mhiramat@redhat.com>
+#
+# Usage: awk -f gen-insn-attr-x86.awk x86-opcode-map.txt > inat-tables.c
+
+# Awk implementation sanity check
+function check_awk_implement() {
+	if (sprintf("%x", 0) != "0")
+		return "Your awk has a printf-format problem."
+	return ""
+}
+
+# Clear working vars
+function clear_vars() {
+	delete table
+	delete lptable2
+	delete lptable1
+	delete lptable3
+	eid = -1 # escape id
+	gid = -1 # group id
+	aid = -1 # AVX id
+	xopid = -1 # XOP id
+	tname = ""
+}
+
+BEGIN {
+	# Implementation error checking
+	awkchecked = check_awk_implement()
+	if (awkchecked != "") {
+		print "Error: " awkchecked > "/dev/stderr"
+		print "Please try to use gawk." > "/dev/stderr"
+		exit 1
+	}
+
+	# Setup generating tables
+	print "/* x86 opcode map generated from x86-opcode-map.txt */"
+	print "/* Do not change this code. */\n"
+	ggid = 1
+	geid = 1
+	gaid = 0
+	gxopid = 0
+	delete etable
+	delete gtable
+	delete atable
+	delete xoptable
+
+	opnd_expr = "^[A-Za-z/]"
+	ext_expr = "^\\("
+	sep_expr = "^\\|$"
+	group_expr = "^Grp[0-9A-Za-z]+"
+
+	imm_expr = "^[IJAOL][a-z]"
+	imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
+	imm_flag["Id"] = "INAT_MAKE_IMM(INAT_IMM_DWORD)"
+	imm_flag["Iq"] = "INAT_MAKE_IMM(INAT_IMM_QWORD)"
+	imm_flag["Ap"] = "INAT_MAKE_IMM(INAT_IMM_PTR)"
+	imm_flag["Iz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Jz"] = "INAT_MAKE_IMM(INAT_IMM_VWORD32)"
+	imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
+	imm_flag["Ob"] = "INAT_MOFFSET"
+	imm_flag["Ov"] = "INAT_MOFFSET"
+	imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+	imm_flag["Lo"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
+
+	modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
+	force64_expr = "\\([df]64\\)"
+	invalid64_expr = "\\(i64\\)"
+	only64_expr = "\\(o64\\)"
+	rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
+	rex2_expr = "\\(REX2\\)"
+	no_rex2_expr = "\\(!REX2\\)"
+	fpu_expr = "^ESC" # TODO
+
+	lprefix1_expr = "\\((66|!F3)\\)"
+	lprefix2_expr = "\\(F3\\)"
+	lprefix3_expr = "\\((F2|!F3|66&F2)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
+	max_lprefix = 4
+
+	# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
+	# accepts VEX prefix
+	vexok_opcode_expr = "^[vk].*"
+	vexok_expr = "\\(v1\\)"
+	# All opcodes with (v) superscript supports *only* VEX prefix
+	vexonly_expr = "\\(v\\)"
+	# All opcodes with (ev) superscript supports *only* EVEX prefix
+	evexonly_expr = "\\(ev\\)"
+	# (es) is the same as (ev) but also "SCALABLE" i.e. W and pp determine operand size
+	evex_scalable_expr = "\\(es\\)"
+	# All opcodes in XOP table or with (xop) superscript accept XOP prefix
+	xopok_expr = "\\(xop\\)"
+
+	prefix_expr = "\\(Prefix\\)"
+	prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
+	prefix_num["REPNE"] = "INAT_PFX_REPNE"
+	prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+	prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+	prefix_num["XRELEASE"] = "INAT_PFX_REPE"
+	prefix_num["LOCK"] = "INAT_PFX_LOCK"
+	prefix_num["SEG=CS"] = "INAT_PFX_CS"
+	prefix_num["SEG=DS"] = "INAT_PFX_DS"
+	prefix_num["SEG=ES"] = "INAT_PFX_ES"
+	prefix_num["SEG=FS"] = "INAT_PFX_FS"
+	prefix_num["SEG=GS"] = "INAT_PFX_GS"
+	prefix_num["SEG=SS"] = "INAT_PFX_SS"
+	prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
+	prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
+	prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+	prefix_num["EVEX"] = "INAT_PFX_EVEX"
+	prefix_num["REX2"] = "INAT_PFX_REX2"
+	prefix_num["XOP"] = "INAT_PFX_XOP"
+
+	clear_vars()
+}
+
+function semantic_error(msg) {
+	print "Semantic error at " NR ": " msg > "/dev/stderr"
+	exit 1
+}
+
+function debug(msg) {
+	print "DEBUG: " msg
+}
+
+function array_size(arr,   i,c) {
+	c = 0
+	for (i in arr)
+		c++
+	return c
+}
+
+/^Table:/ {
+	print "/* " $0 " */"
+	if (tname != "")
+		semantic_error("Hit Table: before EndTable:.");
+}
+
+/^Referrer:/ {
+	if (NF != 1) {
+		# escape opcode table
+		ref = ""
+		for (i = 2; i <= NF; i++)
+			ref = ref $i
+		eid = escape[ref]
+		tname = sprintf("inat_escape_table_%d", eid)
+	}
+}
+
+/^AVXcode:/ {
+	if (NF != 1) {
+		# AVX/escape opcode table
+		aid = $2
+		xopid = -1
+		if (gaid <= aid)
+			gaid = aid + 1
+		if (tname == "")	# AVX only opcode table
+			tname = sprintf("inat_avx_table_%d", $2)
+	}
+	if (aid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
+/^XOPcode:/ {
+	if (NF != 1) {
+		# XOP opcode table
+		xopid = $2
+		aid = -1
+		if (gxopid <= xopid)
+			gxopid = xopid + 1
+		if (tname == "")	# XOP only opcode table
+			tname = sprintf("inat_xop_table_%d", $2)
+	}
+	if (xopid == -1 && eid == -1)	# primary opcode table
+		tname = "inat_primary_table"
+}
+
+/^GrpTable:/ {
+	print "/* " $0 " */"
+	if (!($2 in group))
+		semantic_error("No group: " $2 )
+	gid = group[$2]
+	tname = "inat_group_table_" gid
+}
+
+function print_table(tbl,name,fmt,n)
+{
+	print "const insn_attr_t " name " = {"
+	for (i = 0; i < n; i++) {
+		id = sprintf(fmt, i)
+		if (tbl[id])
+			print "	[" id "] = " tbl[id] ","
+	}
+	print "};"
+}
+
+/^EndTable/ {
+	if (gid != -1) {
+		# print group tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,0] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1, tname "_1[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2, tname "_2[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3, tname "_3[INAT_GROUP_TABLE_SIZE]",
+				    "0x%x", 8)
+			gtable[gid,3] = tname "_3"
+		}
+	} else {
+		# print primary/escaped tables
+		if (array_size(table) != 0) {
+			print_table(table, tname "[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,0] = tname
+			if (aid >= 0)
+				atable[aid,0] = tname
+			else if (xopid >= 0)
+				xoptable[xopid] = tname
+		}
+		if (array_size(lptable1) != 0) {
+			print_table(lptable1,tname "_1[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,1] = tname "_1"
+			if (aid >= 0)
+				atable[aid,1] = tname "_1"
+		}
+		if (array_size(lptable2) != 0) {
+			print_table(lptable2,tname "_2[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,2] = tname "_2"
+			if (aid >= 0)
+				atable[aid,2] = tname "_2"
+		}
+		if (array_size(lptable3) != 0) {
+			print_table(lptable3,tname "_3[INAT_OPCODE_TABLE_SIZE]",
+				    "0x%02x", 256)
+			etable[eid,3] = tname "_3"
+			if (aid >= 0)
+				atable[aid,3] = tname "_3"
+		}
+	}
+	print ""
+	clear_vars()
+}
+
+function add_flags(old,new) {
+	if (old && new)
+		return old " | " new
+	else if (old)
+		return old
+	else
+		return new
+}
+
+# convert operands to flags.
+function convert_operands(count,opnd,       i,j,imm,mod)
+{
+	imm = null
+	mod = null
+	for (j = 1; j <= count; j++) {
+		i = opnd[j]
+		if (match(i, imm_expr) == 1) {
+			if (!imm_flag[i])
+				semantic_error("Unknown imm opnd: " i)
+			if (imm) {
+				if (i != "Ib")
+					semantic_error("Second IMM error")
+				imm = add_flags(imm, "INAT_SCNDIMM")
+			} else
+				imm = imm_flag[i]
+		} else if (match(i, modrm_expr))
+			mod = "INAT_MODRM"
+	}
+	return add_flags(imm, mod)
+}
+
+/^[0-9a-f]+:/ {
+	if (NR == 1)
+		next
+	# get index
+	idx = "0x" substr($1, 1, index($1,":") - 1)
+	if (idx in table)
+		semantic_error("Redefine " idx " in " tname)
+
+	# check if escaped opcode
+	if ("escape" == $2) {
+		if ($3 != "#")
+			semantic_error("No escaped name")
+		ref = ""
+		for (i = 4; i <= NF; i++)
+			ref = ref $i
+		if (ref in escape)
+			semantic_error("Redefine escape (" ref ")")
+		escape[ref] = geid
+		geid++
+		table[idx] = "INAT_MAKE_ESCAPE(" escape[ref] ")"
+		next
+	}
+
+	variant = null
+	# converts
+	i = 2
+	while (i <= NF) {
+		opcode = $(i++)
+		delete opnds
+		ext = null
+		flags = null
+		opnd = null
+		# parse one opcode
+		if (match($i, opnd_expr)) {
+			opnd = $i
+			count = split($(i++), opnds, ",")
+			flags = convert_operands(count, opnds)
+		}
+		if (match($i, ext_expr))
+			ext = $(i++)
+		if (match($i, sep_expr))
+			i++
+		else if (i < NF)
+			semantic_error($i " is not a separator")
+
+		# check if group opcode
+		if (match(opcode, group_expr)) {
+			if (!(opcode in group)) {
+				group[opcode] = ggid
+				ggid++
+			}
+			flags = add_flags(flags, "INAT_MAKE_GROUP(" group[opcode] ")")
+		}
+		# check force(or default) 64bit
+		if (match(ext, force64_expr))
+			flags = add_flags(flags, "INAT_FORCE64")
+
+		# check invalid in 64-bit (and no only64)
+		if (match(ext, invalid64_expr) &&
+		    !match($0, only64_expr))
+			flags = add_flags(flags, "INAT_INV64")
+
+		# check REX2 not allowed
+		if (match(ext, no_rex2_expr))
+			flags = add_flags(flags, "INAT_NO_REX2")
+
+		# check REX prefix
+		if (match(opcode, rex_expr))
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(INAT_PFX_REX)")
+
+		# check coprocessor escape : TODO
+		if (match(opcode, fpu_expr))
+			flags = add_flags(flags, "INAT_MODRM")
+
+		# check VEX codes
+		if (match(ext, evexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
+		else if (match(ext, evex_scalable_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY | INAT_EVEX_SCALABLE")
+		else if (match(ext, vexonly_expr))
+			flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
+		else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
+			flags = add_flags(flags, "INAT_VEXOK")
+		else if (match(ext, xopok_expr) || xopid >= 0)
+			flags = add_flags(flags, "INAT_XOPOK")
+
+		# check prefixes
+		if (match(ext, prefix_expr)) {
+			if (!prefix_num[opcode])
+				semantic_error("Unknown prefix: " opcode)
+			flags = add_flags(flags, "INAT_MAKE_PREFIX(" prefix_num[opcode] ")")
+		}
+		if (length(flags) == 0)
+			continue
+		# check if last prefix
+		if (match(ext, lprefix1_expr)) {
+			lptable1[idx] = add_flags(lptable1[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix2_expr)) {
+			lptable2[idx] = add_flags(lptable2[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, lprefix3_expr)) {
+			lptable3[idx] = add_flags(lptable3[idx],flags)
+			variant = "INAT_VARIANT"
+		}
+		if (match(ext, rex2_expr))
+			table[idx] = add_flags(table[idx], "INAT_REX2_VARIANT")
+		if (!match(ext, lprefix_expr)){
+			table[idx] = add_flags(table[idx],flags)
+		}
+	}
+	if (variant)
+		table[idx] = add_flags(table[idx],variant)
+}
+
+END {
+	if (awkchecked != "")
+		exit 1
+
+	print "#ifndef __BOOT_COMPRESSED\n"
+
+	# print escape opcode map's array
+	print "/* Escape opcode map array */"
+	print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < geid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (etable[i,j])
+				print "	["i"]["j"] = "etable[i,j]","
+	print "};\n"
+	# print group opcode map's array
+	print "/* Group opcode map array */"
+	print "const insn_attr_t * const inat_group_tables[INAT_GRP_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < ggid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (gtable[i,j])
+				print "	["i"]["j"] = "gtable[i,j]","
+	print "};\n"
+	# print AVX opcode map's array
+	print "/* AVX opcode map array */"
+	print "const insn_attr_t * const inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1] = {"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "	["i"]["j"] = "atable[i,j]","
+	print "};\n"
+
+	print "/* XOP opcode map array */"
+	print "const insn_attr_t * const inat_xop_tables[X86_XOP_M_MAX - X86_XOP_M_MIN + 1]" \
+	      " = {"
+	for (i = 0; i < gxopid; i++)
+		if (xoptable[i])
+			print "	["i"] = "xoptable[i]","
+	print "};"
+
+	print "#else /* !__BOOT_COMPRESSED */\n"
+
+	print "/* Escape opcode map array */"
+	print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \
+	      "[INAT_LSTPFX_MAX + 1];"
+	print ""
+
+	print "/* Group opcode map array */"
+	print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1];"
+	print ""
+
+	print "/* AVX opcode map array */"
+	print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\
+	      "[INAT_LSTPFX_MAX + 1];"
+	print ""
+
+	print "/* XOP opcode map array */"
+	print "static const insn_attr_t *inat_xop_tables[X86_XOP_M_MAX - X86_XOP_M_MIN + 1];"
+	print ""
+
+	print "static void inat_init_tables(void)"
+	print "{"
+
+	# print escape opcode map's array
+	print "\t/* Print Escape opcode map array */"
+	for (i = 0; i < geid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (etable[i,j])
+				print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";"
+	print ""
+
+	# print group opcode map's array
+	print "\t/* Print Group opcode map array */"
+	for (i = 0; i < ggid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (gtable[i,j])
+				print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";"
+	print ""
+	# print AVX opcode map's array
+	print "\t/* Print AVX opcode map array */"
+	for (i = 0; i < gaid; i++)
+		for (j = 0; j < max_lprefix; j++)
+			if (atable[i,j])
+				print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";"
+
+	print ""
+	print "\t/* Print XOP opcode map array */"
+	for (i = 0; i < gxopid; i++)
+		if (xoptable[i])
+			print "\tinat_xop_tables["i"] = "xoptable[i]";"
+
+	print "}"
+	print "#endif"
+}
+
diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c
new file mode 100644
index 000000000..8bf15c4ae
--- /dev/null
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (C) IBM Corporation, 2009
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <unistd.h>
+#include <stdarg.h>
+#include <linux/kallsyms.h>
+
+#include <asm/insn.h>
+#include <inat.c>
+#include <insn.c>
+
+/*
+ * Test of instruction analysis in general and insn_get_length() in
+ * particular.  See if insn_get_length() and the disassembler agree
+ * on the length of each instruction in an elf disassembly.
+ *
+ * Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
+ */
+
+const char *prog;
+static int verbose;
+static int x86_64;
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: objdump -d a.out | awk -f objdump_reformat.awk"
+		" | %s [-y|-n] [-v]\n", prog);
+	fprintf(stderr, "\t-y	64bit mode\n");
+	fprintf(stderr, "\t-n	32bit mode\n");
+	fprintf(stderr, "\t-v	verbose mode\n");
+	exit(1);
+}
+
+static void malformed_line(const char *line, int line_nr)
+{
+	fprintf(stderr, "%s: error: malformed line %d:\n%s",
+		prog, line_nr, line);
+	exit(3);
+}
+
+static void pr_warn(const char *fmt, ...)
+{
+	va_list ap;
+
+	fprintf(stderr, "%s: warning: ", prog);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+}
+
+static void dump_field(FILE *fp, const char *name, const char *indent,
+		       struct insn_field *field)
+{
+	fprintf(fp, "%s.%s = {\n", indent, name);
+	fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n",
+		indent, field->value, field->bytes[0], field->bytes[1],
+		field->bytes[2], field->bytes[3]);
+	fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent,
+		field->got, field->nbytes);
+}
+
+static void dump_insn(FILE *fp, struct insn *insn)
+{
+	fprintf(fp, "Instruction = {\n");
+	dump_field(fp, "prefixes", "\t",	&insn->prefixes);
+	dump_field(fp, "rex_prefix", "\t",	&insn->rex_prefix);
+	dump_field(fp, "vex_prefix", "\t",	&insn->vex_prefix);
+	dump_field(fp, "opcode", "\t",		&insn->opcode);
+	dump_field(fp, "modrm", "\t",		&insn->modrm);
+	dump_field(fp, "sib", "\t",		&insn->sib);
+	dump_field(fp, "displacement", "\t",	&insn->displacement);
+	dump_field(fp, "immediate1", "\t",	&insn->immediate1);
+	dump_field(fp, "immediate2", "\t",	&insn->immediate2);
+	fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n",
+		insn->attr, insn->opnd_bytes, insn->addr_bytes);
+	fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n",
+		insn->length, insn->x86_64, insn->kaddr);
+}
+
+static void parse_args(int argc, char **argv)
+{
+	int c;
+	prog = argv[0];
+	while ((c = getopt(argc, argv, "ynv")) != -1) {
+		switch (c) {
+		case 'y':
+			x86_64 = 1;
+			break;
+		case 'n':
+			x86_64 = 0;
+			break;
+		case 'v':
+			verbose = 1;
+			break;
+		default:
+			usage();
+		}
+	}
+}
+
+#define BUFSIZE (256 + KSYM_NAME_LEN)
+
+int main(int argc, char **argv)
+{
+	char line[BUFSIZE], sym[BUFSIZE] = "<unknown>";
+	unsigned char insn_buff[16];
+	struct insn insn;
+	int insns = 0;
+	int warnings = 0;
+
+	parse_args(argc, argv);
+
+	while (fgets(line, BUFSIZE, stdin)) {
+		char copy[BUFSIZE], *s, *tab1, *tab2;
+		int nb = 0, ret;
+		unsigned int b;
+
+		if (line[0] == '<') {
+			/* Symbol line */
+			strcpy(sym, line);
+			continue;
+		}
+
+		insns++;
+		memset(insn_buff, 0, 16);
+		strcpy(copy, line);
+		tab1 = strchr(copy, '\t');
+		if (!tab1)
+			malformed_line(line, insns);
+		s = tab1 + 1;
+		s += strspn(s, " ");
+		tab2 = strchr(s, '\t');
+		if (!tab2)
+			malformed_line(line, insns);
+		*tab2 = '\0';	/* Characters beyond tab2 aren't examined */
+		while (s < tab2) {
+			if (sscanf(s, "%x", &b) == 1) {
+				insn_buff[nb++] = (unsigned char) b;
+				s += 3;
+			} else
+				break;
+		}
+
+		/* Decode an instruction */
+		ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+				  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+
+		if (ret < 0 || insn.length != nb) {
+			warnings++;
+			pr_warn("Found an x86 instruction decoder bug, "
+				"please report this.\n", sym);
+			pr_warn("%s", line);
+			pr_warn("objdump says %d bytes, but insn_get_length() "
+				"says %d\n", nb, insn.length);
+			if (verbose)
+				dump_insn(stderr, &insn);
+		}
+	}
+	if (warnings)
+		pr_warn("Decoded and checked %d instructions with %d "
+			"failures\n", insns, warnings);
+	else
+		fprintf(stdout, "  %s: success: Decoded and checked %d"
+			" instructions\n", prog, insns);
+	return 0;
+}
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
new file mode 100644
index 000000000..e743f0ea0
--- /dev/null
+++ b/arch/x86/tools/insn_sanity.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * x86 decoder sanity test - based on test_get_insn.c
+ *
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) Hitachi, Ltd., 2011
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <asm/insn.h>
+#include <inat.c>
+#include <insn.c>
+
+/*
+ * Test of instruction analysis against tampering.
+ * Feed random binary to instruction decoder and ensure not to
+ * access out-of-instruction-buffer.
+ */
+
+#define DEFAULT_MAX_ITER	10000
+#define INSN_NOP 0x90
+
+static const char	*prog;		/* Program name */
+static int		verbose;	/* Verbosity */
+static int		x86_64;		/* x86-64 bit mode flag */
+static unsigned int	seed;		/* Random seed */
+static unsigned long	iter_start;	/* Start of iteration number */
+static unsigned long	iter_end = DEFAULT_MAX_ITER;	/* End of iteration number */
+static FILE		*input_file;	/* Input file name */
+
+static void usage(const char *err)
+{
+	if (err)
+		fprintf(stderr, "%s: Error: %s\n\n", prog, err);
+	fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
+	fprintf(stderr, "\t-y	64bit mode\n");
+	fprintf(stderr, "\t-n	32bit mode\n");
+	fprintf(stderr, "\t-v	Verbosity(-vv dumps any decoded result)\n");
+	fprintf(stderr, "\t-s	Give a random seed (and iteration number)\n");
+	fprintf(stderr, "\t-m	Give a maximum iteration number\n");
+	fprintf(stderr, "\t-i	Give an input file with decoded binary\n");
+	exit(1);
+}
+
+static void dump_field(FILE *fp, const char *name, const char *indent,
+		       struct insn_field *field)
+{
+	fprintf(fp, "%s.%s = {\n", indent, name);
+	fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n",
+		indent, field->value, field->bytes[0], field->bytes[1],
+		field->bytes[2], field->bytes[3]);
+	fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent,
+		field->got, field->nbytes);
+}
+
+static void dump_insn(FILE *fp, struct insn *insn)
+{
+	fprintf(fp, "Instruction = {\n");
+	dump_field(fp, "prefixes", "\t",	&insn->prefixes);
+	dump_field(fp, "rex_prefix", "\t",	&insn->rex_prefix);
+	dump_field(fp, "vex_prefix", "\t",	&insn->vex_prefix);
+	dump_field(fp, "opcode", "\t",		&insn->opcode);
+	dump_field(fp, "modrm", "\t",		&insn->modrm);
+	dump_field(fp, "sib", "\t",		&insn->sib);
+	dump_field(fp, "displacement", "\t",	&insn->displacement);
+	dump_field(fp, "immediate1", "\t",	&insn->immediate1);
+	dump_field(fp, "immediate2", "\t",	&insn->immediate2);
+	fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n",
+		insn->attr, insn->opnd_bytes, insn->addr_bytes);
+	fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n",
+		insn->length, insn->x86_64, insn->kaddr);
+}
+
+static void dump_stream(FILE *fp, const char *msg, unsigned long nr_iter,
+			unsigned char *insn_buff, struct insn *insn)
+{
+	int i;
+
+	fprintf(fp, "%s:\n", msg);
+
+	dump_insn(fp, insn);
+
+	fprintf(fp, "You can reproduce this with below command(s);\n");
+
+	/* Input a decoded instruction sequence directly */
+	fprintf(fp, " $ echo ");
+	for (i = 0; i < MAX_INSN_SIZE; i++)
+		fprintf(fp, " %02x", insn_buff[i]);
+	fprintf(fp, " | %s -i -\n", prog);
+
+	if (!input_file) {
+		fprintf(fp, "Or \n");
+		/* Give a seed and iteration number */
+		fprintf(fp, " $ %s -s 0x%x,%lu\n", prog, seed, nr_iter);
+	}
+}
+
+static void init_random_seed(void)
+{
+	int fd;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd < 0)
+		goto fail;
+
+	if (read(fd, &seed, sizeof(seed)) != sizeof(seed))
+		goto fail;
+
+	close(fd);
+	return;
+fail:
+	usage("Failed to open /dev/urandom");
+}
+
+/* Read given instruction sequence from the input file */
+static int read_next_insn(unsigned char *insn_buff)
+{
+	char buf[256]  = "", *tmp;
+	int i;
+
+	tmp = fgets(buf, ARRAY_SIZE(buf), input_file);
+	if (tmp == NULL || feof(input_file))
+		return 0;
+
+	for (i = 0; i < MAX_INSN_SIZE; i++) {
+		insn_buff[i] = (unsigned char)strtoul(tmp, &tmp, 16);
+		if (*tmp != ' ')
+			break;
+	}
+
+	return i;
+}
+
+static int generate_insn(unsigned char *insn_buff)
+{
+	int i;
+
+	if (input_file)
+		return read_next_insn(insn_buff);
+
+	/* Fills buffer with random binary up to MAX_INSN_SIZE */
+	for (i = 0; i < MAX_INSN_SIZE - 1; i += 2)
+		*(unsigned short *)(&insn_buff[i]) = random() & 0xffff;
+
+	while (i < MAX_INSN_SIZE)
+		insn_buff[i++] = random() & 0xff;
+
+	return i;
+}
+
+static void parse_args(int argc, char **argv)
+{
+	int c;
+	char *tmp = NULL;
+	int set_seed = 0;
+
+	prog = argv[0];
+	while ((c = getopt(argc, argv, "ynvs:m:i:")) != -1) {
+		switch (c) {
+		case 'y':
+			x86_64 = 1;
+			break;
+		case 'n':
+			x86_64 = 0;
+			break;
+		case 'v':
+			verbose++;
+			break;
+		case 'i':
+			if (strcmp("-", optarg) == 0)
+				input_file = stdin;
+			else
+				input_file = fopen(optarg, "r");
+			if (!input_file)
+				usage("Failed to open input file");
+			break;
+		case 's':
+			seed = (unsigned int)strtoul(optarg, &tmp, 0);
+			if (*tmp == ',') {
+				optarg = tmp + 1;
+				iter_start = strtoul(optarg, &tmp, 0);
+			}
+			if (*tmp != '\0' || tmp == optarg)
+				usage("Failed to parse seed");
+			set_seed = 1;
+			break;
+		case 'm':
+			iter_end = strtoul(optarg, &tmp, 0);
+			if (*tmp != '\0' || tmp == optarg)
+				usage("Failed to parse max_iter");
+			break;
+		default:
+			usage(NULL);
+		}
+	}
+
+	/* Check errors */
+	if (iter_end < iter_start)
+		usage("Max iteration number must be bigger than iter-num");
+
+	if (set_seed && input_file)
+		usage("Don't use input file (-i) with random seed (-s)");
+
+	/* Initialize random seed */
+	if (!input_file) {
+		if (!set_seed)	/* No seed is given */
+			init_random_seed();
+		srand(seed);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int insns = 0, ret;
+	struct insn insn;
+	int errors = 0;
+	unsigned long i;
+	unsigned char insn_buff[MAX_INSN_SIZE * 2];
+
+	parse_args(argc, argv);
+
+	/* Prepare stop bytes with NOPs */
+	memset(insn_buff + MAX_INSN_SIZE, INSN_NOP, MAX_INSN_SIZE);
+
+	for (i = 0; i < iter_end; i++) {
+		if (generate_insn(insn_buff) <= 0)
+			break;
+
+		if (i < iter_start)	/* Skip to given iteration number */
+			continue;
+
+		/* Decode an instruction */
+		ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+				  x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+
+		if (insn.next_byte <= insn.kaddr ||
+		    insn.kaddr + MAX_INSN_SIZE < insn.next_byte) {
+			/* Access out-of-range memory */
+			dump_stream(stderr, "Error: Found an access violation", i, insn_buff, &insn);
+			errors++;
+		} else if (verbose && ret < 0)
+			dump_stream(stdout, "Info: Found an undecodable input", i, insn_buff, &insn);
+		else if (verbose >= 2)
+			dump_insn(stdout, &insn);
+		insns++;
+	}
+
+	fprintf((errors) ? stderr : stdout,
+		"  %s: %s: Decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+		prog,
+		(errors) ? "failure" : "success",
+		insns,
+		(input_file) ? "given" : "random",
+		errors,
+		seed);
+
+	return errors ? 1 : 0;
+}
diff --git a/arch/x86/tools/objdump_reformat.awk b/arch/x86/tools/objdump_reformat.awk
new file mode 100644
index 000000000..20b08a6c4
--- /dev/null
+++ b/arch/x86/tools/objdump_reformat.awk
@@ -0,0 +1,48 @@
+#!/bin/awk -f
+# SPDX-License-Identifier: GPL-2.0
+# Usage: objdump -d a.out | awk -f objdump_reformat.awk | ./insn_decoder_test
+# Reformats the disassembly as follows:
+# - Removes all lines except the disassembled instructions.
+# - For instructions that exceed 1 line (7 bytes), crams all the hex bytes
+# into a single line.
+# - Remove bad(or prefix only) instructions
+
+BEGIN {
+	prev_addr = ""
+	prev_hex = ""
+	prev_mnemonic = ""
+	bad_expr = "(\\(bad\\)|<unknown>|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))"
+	fwait_expr = "^9b[ \t]*fwait"
+	fwait_str="9b\tfwait"
+}
+
+/^ *[0-9a-f]+ <[^>]*>:/ {
+	# Symbol entry
+	printf("%s%s\n", $2, $1)
+}
+
+/^ *[0-9a-f]+:/ {
+	if (split($0, field, /: |\t/) < 3) {
+		# This is a continuation of the same insn.
+		prev_hex = prev_hex field[2]
+	} else {
+		# Skip bad instructions
+		if (match(prev_mnemonic, bad_expr))
+			prev_addr = ""
+		# Split fwait from other f* instructions
+		if (match(prev_hex, fwait_expr) && prev_mnemonic != "fwait") {
+			printf "%s\t%s\n", prev_addr, fwait_str
+			sub(fwait_expr, "", prev_hex)
+		}
+		if (prev_addr != "")
+			printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic
+		prev_addr = field[1]
+		prev_hex = field[2]
+		prev_mnemonic = field[3]
+	}
+}
+
+END {
+	if (prev_addr != "")
+		printf "%s\t%s\t%s\n", prev_addr, prev_hex, prev_mnemonic
+}
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
new file mode 100644
index 000000000..5ea9bc7ee
--- /dev/null
+++ b/arch/x86/tools/relocs.c
@@ -0,0 +1,1079 @@
+// SPDX-License-Identifier: GPL-2.0
+/* This is included from relocs_32/64.c */
+
+#define ElfW(type)		_ElfW(ELF_BITS, type)
+#define _ElfW(bits, type)	__ElfW(bits, type)
+#define __ElfW(bits, type)	Elf##bits##_##type
+
+#define Elf_Addr		ElfW(Addr)
+#define Elf_Ehdr		ElfW(Ehdr)
+#define Elf_Phdr		ElfW(Phdr)
+#define Elf_Shdr		ElfW(Shdr)
+#define Elf_Sym			ElfW(Sym)
+
+static Elf_Ehdr			ehdr;
+static unsigned long		shnum;
+static unsigned int		shstrndx;
+static unsigned int		shsymtabndx;
+static unsigned int		shxsymtabndx;
+
+static int sym_index(Elf_Sym *sym);
+
+struct relocs {
+				uint32_t	*offset;
+				unsigned long	count;
+				unsigned long	size;
+};
+
+static struct relocs		relocs16;
+static struct relocs		relocs32;
+
+#if ELF_BITS == 64
+static struct relocs		relocs64;
+# define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
+#else
+# define FMT PRIu32
+#endif
+
+struct section {
+				Elf_Shdr       shdr;
+				struct section *link;
+				Elf_Sym        *symtab;
+				Elf32_Word     *xsymtab;
+				Elf_Rel        *reltab;
+				char           *strtab;
+};
+static struct section		*secs;
+
+static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
+/*
+ * Following symbols have been audited. There values are constant and do
+ * not change if bzImage is loaded at a different physical address than
+ * the address for which it has been compiled. Don't warn user about
+ * absolute relocations present w.r.t these symbols.
+ */
+	[S_ABS] =
+	"^(xen_irq_disable_direct_reloc$|"
+	"xen_save_fl_direct_reloc$|"
+	"xen_elfnote_.+_offset$|"
+	"VDSO|"
+	"__kcfi_typeid_|"
+	"__crc_)",
+
+/*
+ * These symbols are known to be relative, even if the linker marks them
+ * as absolute (typically defined outside any section in the linker script.)
+ */
+	[S_REL] =
+	"^(__init_(begin|end)|"
+	"__x86_cpu_dev_(start|end)|"
+	"__alt_instructions(_end)?|"
+	"(__iommu_table|__apicdrivers)(_end)?|"
+	"__(start|end)_pci_.*|"
+#if CONFIG_FW_LOADER
+	"__(start|end)_builtin_fw|"
+#endif
+	"__(start|stop)___ksymtab(_gpl)?|"
+	"__(start|stop)___kcrctab(_gpl)?|"
+	"__(start|stop)___param|"
+	"__(start|stop)___modver|"
+	"__(start|stop)___bug_table|"
+	"__tracedata_(start|end)|"
+	"__(start|stop)_notes|"
+	"__end_rodata|"
+	"__end_rodata_aligned|"
+	"__initramfs_start|"
+	"(jiffies|jiffies_64)|"
+#if ELF_BITS == 64
+	"__end_rodata_hpage_align|"
+#endif
+	"_end)$"
+};
+
+
+static const char * const sym_regex_realmode[S_NSYMTYPES] = {
+/*
+ * These symbols are known to be relative, even if the linker marks them
+ * as absolute (typically defined outside any section in the linker script.)
+ */
+	[S_REL] =
+	"^pa_",
+
+/*
+ * These are 16-bit segment symbols when compiling 16-bit code.
+ */
+	[S_SEG] =
+	"^real_mode_seg$",
+
+/*
+ * These are offsets belonging to segments, as opposed to linear addresses,
+ * when compiling 16-bit code.
+ */
+	[S_LIN] =
+	"^pa_",
+};
+
+static const char * const	*sym_regex;
+
+static regex_t			sym_regex_c[S_NSYMTYPES];
+
+static int is_reloc(enum symtype type, const char *sym_name)
+{
+	return sym_regex[type] && !regexec(&sym_regex_c[type], sym_name, 0, NULL, 0);
+}
+
+static void regex_init(int use_real_mode)
+{
+        char errbuf[128];
+        int err;
+	int i;
+
+	if (use_real_mode)
+		sym_regex = sym_regex_realmode;
+	else
+		sym_regex = sym_regex_kernel;
+
+	for (i = 0; i < S_NSYMTYPES; i++) {
+		if (!sym_regex[i])
+			continue;
+
+		err = regcomp(&sym_regex_c[i], sym_regex[i], REG_EXTENDED|REG_NOSUB);
+
+		if (err) {
+			regerror(err, &sym_regex_c[i], errbuf, sizeof(errbuf));
+			die("%s", errbuf);
+		}
+        }
+}
+
+static const char *sym_type(unsigned type)
+{
+	static const char *type_name[] = {
+#define SYM_TYPE(X) [X] = #X
+		SYM_TYPE(STT_NOTYPE),
+		SYM_TYPE(STT_OBJECT),
+		SYM_TYPE(STT_FUNC),
+		SYM_TYPE(STT_SECTION),
+		SYM_TYPE(STT_FILE),
+		SYM_TYPE(STT_COMMON),
+		SYM_TYPE(STT_TLS),
+#undef SYM_TYPE
+	};
+	const char *name = "unknown sym type name";
+
+	if (type < ARRAY_SIZE(type_name))
+		name = type_name[type];
+
+	return name;
+}
+
+static const char *sym_bind(unsigned bind)
+{
+	static const char *bind_name[] = {
+#define SYM_BIND(X) [X] = #X
+		SYM_BIND(STB_LOCAL),
+		SYM_BIND(STB_GLOBAL),
+		SYM_BIND(STB_WEAK),
+#undef SYM_BIND
+	};
+	const char *name = "unknown sym bind name";
+
+	if (bind < ARRAY_SIZE(bind_name))
+		name = bind_name[bind];
+
+	return name;
+}
+
+static const char *sym_visibility(unsigned visibility)
+{
+	static const char *visibility_name[] = {
+#define SYM_VISIBILITY(X) [X] = #X
+		SYM_VISIBILITY(STV_DEFAULT),
+		SYM_VISIBILITY(STV_INTERNAL),
+		SYM_VISIBILITY(STV_HIDDEN),
+		SYM_VISIBILITY(STV_PROTECTED),
+#undef SYM_VISIBILITY
+	};
+	const char *name = "unknown sym visibility name";
+
+	if (visibility < ARRAY_SIZE(visibility_name))
+		name = visibility_name[visibility];
+
+	return name;
+}
+
+static const char *rel_type(unsigned type)
+{
+	static const char *type_name[] = {
+#define REL_TYPE(X) [X] = #X
+#if ELF_BITS == 64
+		REL_TYPE(R_X86_64_NONE),
+		REL_TYPE(R_X86_64_64),
+		REL_TYPE(R_X86_64_PC64),
+		REL_TYPE(R_X86_64_PC32),
+		REL_TYPE(R_X86_64_GOT32),
+		REL_TYPE(R_X86_64_PLT32),
+		REL_TYPE(R_X86_64_COPY),
+		REL_TYPE(R_X86_64_GLOB_DAT),
+		REL_TYPE(R_X86_64_JUMP_SLOT),
+		REL_TYPE(R_X86_64_RELATIVE),
+		REL_TYPE(R_X86_64_GOTPCREL),
+		REL_TYPE(R_X86_64_32),
+		REL_TYPE(R_X86_64_32S),
+		REL_TYPE(R_X86_64_16),
+		REL_TYPE(R_X86_64_PC16),
+		REL_TYPE(R_X86_64_8),
+		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
+#else
+		REL_TYPE(R_386_NONE),
+		REL_TYPE(R_386_32),
+		REL_TYPE(R_386_PC32),
+		REL_TYPE(R_386_GOT32),
+		REL_TYPE(R_386_PLT32),
+		REL_TYPE(R_386_COPY),
+		REL_TYPE(R_386_GLOB_DAT),
+		REL_TYPE(R_386_JMP_SLOT),
+		REL_TYPE(R_386_RELATIVE),
+		REL_TYPE(R_386_GOTOFF),
+		REL_TYPE(R_386_GOTPC),
+		REL_TYPE(R_386_8),
+		REL_TYPE(R_386_PC8),
+		REL_TYPE(R_386_16),
+		REL_TYPE(R_386_PC16),
+#endif
+#undef REL_TYPE
+	};
+	const char *name = "unknown type rel type name";
+
+	if (type < ARRAY_SIZE(type_name) && type_name[type])
+		name = type_name[type];
+
+	return name;
+}
+
+static const char *sec_name(unsigned shndx)
+{
+	const char *sec_strtab;
+	const char *name;
+	sec_strtab = secs[shstrndx].strtab;
+	name = "<noname>";
+
+	if (shndx < shnum)
+		name = sec_strtab + secs[shndx].shdr.sh_name;
+	else if (shndx == SHN_ABS)
+		name = "ABSOLUTE";
+	else if (shndx == SHN_COMMON)
+		name = "COMMON";
+
+	return name;
+}
+
+static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
+{
+	const char *name;
+	name = "<noname>";
+
+	if (sym->st_name)
+		name = sym_strtab + sym->st_name;
+	else
+		name = sec_name(sym_index(sym));
+
+	return name;
+}
+
+#if BYTE_ORDER == LITTLE_ENDIAN
+# define le16_to_cpu(val)	(val)
+# define le32_to_cpu(val)	(val)
+# define le64_to_cpu(val)	(val)
+#endif
+
+#if BYTE_ORDER == BIG_ENDIAN
+# define le16_to_cpu(val)	bswap_16(val)
+# define le32_to_cpu(val)	bswap_32(val)
+# define le64_to_cpu(val)	bswap_64(val)
+#endif
+
+static uint16_t elf16_to_cpu(uint16_t val)
+{
+	return le16_to_cpu(val);
+}
+
+static uint32_t elf32_to_cpu(uint32_t val)
+{
+	return le32_to_cpu(val);
+}
+
+#define elf_half_to_cpu(x)	elf16_to_cpu(x)
+#define elf_word_to_cpu(x)	elf32_to_cpu(x)
+
+#if ELF_BITS == 64
+static uint64_t elf64_to_cpu(uint64_t val)
+{
+        return le64_to_cpu(val);
+}
+# define elf_addr_to_cpu(x)	elf64_to_cpu(x)
+# define elf_off_to_cpu(x)	elf64_to_cpu(x)
+# define elf_xword_to_cpu(x)	elf64_to_cpu(x)
+#else
+# define elf_addr_to_cpu(x)	elf32_to_cpu(x)
+# define elf_off_to_cpu(x)	elf32_to_cpu(x)
+# define elf_xword_to_cpu(x)	elf32_to_cpu(x)
+#endif
+
+static int sym_index(Elf_Sym *sym)
+{
+	Elf_Sym *symtab = secs[shsymtabndx].symtab;
+	Elf32_Word *xsymtab = secs[shxsymtabndx].xsymtab;
+	unsigned long offset;
+	int index;
+
+	if (sym->st_shndx != SHN_XINDEX)
+		return sym->st_shndx;
+
+	/* calculate offset of sym from head of table. */
+	offset = (unsigned long)sym - (unsigned long)symtab;
+	index = offset / sizeof(*sym);
+
+	return elf32_to_cpu(xsymtab[index]);
+}
+
+static void read_ehdr(FILE *fp)
+{
+	if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+		die("Cannot read ELF header: %s\n", strerror(errno));
+	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0)
+		die("No ELF magic\n");
+	if (ehdr.e_ident[EI_CLASS] != ELF_CLASS)
+		die("Not a %d bit executable\n", ELF_BITS);
+	if (ehdr.e_ident[EI_DATA] != ELFDATA2LSB)
+		die("Not a LSB ELF executable\n");
+	if (ehdr.e_ident[EI_VERSION] != EV_CURRENT)
+		die("Unknown ELF version\n");
+
+	/* Convert the fields to native endian */
+	ehdr.e_type      = elf_half_to_cpu(ehdr.e_type);
+	ehdr.e_machine   = elf_half_to_cpu(ehdr.e_machine);
+	ehdr.e_version   = elf_word_to_cpu(ehdr.e_version);
+	ehdr.e_entry     = elf_addr_to_cpu(ehdr.e_entry);
+	ehdr.e_phoff     = elf_off_to_cpu(ehdr.e_phoff);
+	ehdr.e_shoff     = elf_off_to_cpu(ehdr.e_shoff);
+	ehdr.e_flags     = elf_word_to_cpu(ehdr.e_flags);
+	ehdr.e_ehsize    = elf_half_to_cpu(ehdr.e_ehsize);
+	ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize);
+	ehdr.e_phnum     = elf_half_to_cpu(ehdr.e_phnum);
+	ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize);
+	ehdr.e_shnum     = elf_half_to_cpu(ehdr.e_shnum);
+	ehdr.e_shstrndx  = elf_half_to_cpu(ehdr.e_shstrndx);
+
+	shnum = ehdr.e_shnum;
+	shstrndx = ehdr.e_shstrndx;
+
+	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN))
+		die("Unsupported ELF header type\n");
+	if (ehdr.e_machine != ELF_MACHINE)
+		die("Not for %s\n", ELF_MACHINE_NAME);
+	if (ehdr.e_version != EV_CURRENT)
+		die("Unknown ELF version\n");
+	if (ehdr.e_ehsize != sizeof(Elf_Ehdr))
+		die("Bad ELF header size\n");
+	if (ehdr.e_phentsize != sizeof(Elf_Phdr))
+		die("Bad program header entry\n");
+	if (ehdr.e_shentsize != sizeof(Elf_Shdr))
+		die("Bad section header entry\n");
+
+
+	if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) {
+		Elf_Shdr shdr;
+
+		if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+			die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+			die("Cannot read initial ELF section header: %s\n", strerror(errno));
+
+		if (shnum == SHN_UNDEF)
+			shnum = elf_xword_to_cpu(shdr.sh_size);
+
+		if (shstrndx == SHN_XINDEX)
+			shstrndx = elf_word_to_cpu(shdr.sh_link);
+	}
+
+	if (shstrndx >= shnum)
+		die("String table index out of bounds\n");
+}
+
+static void read_shdrs(FILE *fp)
+{
+	int i;
+	Elf_Shdr shdr;
+
+	secs = calloc(shnum, sizeof(struct section));
+	if (!secs)
+		die("Unable to allocate %ld section headers\n", shnum);
+
+	if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+		die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+			die("Cannot read ELF section headers %d/%ld: %s\n", i, shnum, strerror(errno));
+
+		sec->shdr.sh_name      = elf_word_to_cpu(shdr.sh_name);
+		sec->shdr.sh_type      = elf_word_to_cpu(shdr.sh_type);
+		sec->shdr.sh_flags     = elf_xword_to_cpu(shdr.sh_flags);
+		sec->shdr.sh_addr      = elf_addr_to_cpu(shdr.sh_addr);
+		sec->shdr.sh_offset    = elf_off_to_cpu(shdr.sh_offset);
+		sec->shdr.sh_size      = elf_xword_to_cpu(shdr.sh_size);
+		sec->shdr.sh_link      = elf_word_to_cpu(shdr.sh_link);
+		sec->shdr.sh_info      = elf_word_to_cpu(shdr.sh_info);
+		sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
+		sec->shdr.sh_entsize   = elf_xword_to_cpu(shdr.sh_entsize);
+		if (sec->shdr.sh_link < shnum)
+			sec->link = &secs[sec->shdr.sh_link];
+	}
+
+}
+
+static void read_strtabs(FILE *fp)
+{
+	int i;
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_STRTAB)
+			continue;
+
+		sec->strtab = malloc(sec->shdr.sh_size);
+		if (!sec->strtab)
+			die("malloc of %" FMT " bytes for strtab failed\n", sec->shdr.sh_size);
+
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+			die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+		if (fread(sec->strtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+			die("Cannot read symbol table: %s\n", strerror(errno));
+	}
+}
+
+static void read_symtabs(FILE *fp)
+{
+	int i, j;
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+		int num_syms;
+
+		switch (sec->shdr.sh_type) {
+		case SHT_SYMTAB_SHNDX:
+			sec->xsymtab = malloc(sec->shdr.sh_size);
+			if (!sec->xsymtab)
+				die("malloc of %" FMT " bytes for xsymtab failed\n", sec->shdr.sh_size);
+
+			if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+				die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+			if (fread(sec->xsymtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+				die("Cannot read extended symbol table: %s\n", strerror(errno));
+
+			shxsymtabndx = i;
+			continue;
+
+		case SHT_SYMTAB:
+			num_syms = sec->shdr.sh_size / sizeof(Elf_Sym);
+
+			sec->symtab = malloc(sec->shdr.sh_size);
+			if (!sec->symtab)
+				die("malloc of %" FMT " bytes for symtab failed\n", sec->shdr.sh_size);
+
+			if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+				die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+			if (fread(sec->symtab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+				die("Cannot read symbol table: %s\n", strerror(errno));
+
+			for (j = 0; j < num_syms; j++) {
+				Elf_Sym *sym = &sec->symtab[j];
+
+				sym->st_name  = elf_word_to_cpu(sym->st_name);
+				sym->st_value = elf_addr_to_cpu(sym->st_value);
+				sym->st_size  = elf_xword_to_cpu(sym->st_size);
+				sym->st_shndx = elf_half_to_cpu(sym->st_shndx);
+			}
+			shsymtabndx = i;
+			continue;
+
+		default:
+			continue;
+		}
+	}
+}
+
+
+static void read_relocs(FILE *fp)
+{
+	int i, j;
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_REL_TYPE)
+			continue;
+
+		sec->reltab = malloc(sec->shdr.sh_size);
+		if (!sec->reltab)
+			die("malloc of %" FMT " bytes for relocs failed\n", sec->shdr.sh_size);
+
+		if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0)
+			die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno));
+
+		if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size)
+			die("Cannot read symbol table: %s\n", strerror(errno));
+
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+			Elf_Rel *rel = &sec->reltab[j];
+
+			rel->r_offset = elf_addr_to_cpu(rel->r_offset);
+			rel->r_info   = elf_xword_to_cpu(rel->r_info);
+#if (SHT_REL_TYPE == SHT_RELA)
+			rel->r_addend = elf_xword_to_cpu(rel->r_addend);
+#endif
+		}
+	}
+}
+
+
+static void print_absolute_symbols(void)
+{
+	int i;
+	const char *format;
+
+	if (ELF_BITS == 64)
+		format = "%5d %016"PRIx64" %5"PRId64" %10s %10s %12s %s\n";
+	else
+		format = "%5d %08"PRIx32"  %5"PRId32" %10s %10s %12s %s\n";
+
+	printf("Absolute symbols\n");
+	printf(" Num:    Value Size  Type       Bind        Visibility  Name\n");
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+		char *sym_strtab;
+		int j;
+
+		if (sec->shdr.sh_type != SHT_SYMTAB)
+			continue;
+
+		sym_strtab = sec->link->strtab;
+
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Sym); j++) {
+			Elf_Sym *sym;
+			const char *name;
+
+			sym = &sec->symtab[j];
+			name = sym_name(sym_strtab, sym);
+
+			if (sym->st_shndx != SHN_ABS)
+				continue;
+
+			printf(format,
+				j, sym->st_value, sym->st_size,
+				sym_type(ELF_ST_TYPE(sym->st_info)),
+				sym_bind(ELF_ST_BIND(sym->st_info)),
+				sym_visibility(ELF_ST_VISIBILITY(sym->st_other)),
+				name);
+		}
+	}
+	printf("\n");
+}
+
+static void print_absolute_relocs(void)
+{
+	int i, printed = 0;
+	const char *format;
+
+	if (ELF_BITS == 64)
+		format = "%016"PRIx64" %016"PRIx64" %10s %016"PRIx64"  %s\n";
+	else
+		format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32"  %s\n";
+
+	for (i = 0; i < shnum; i++) {
+		struct section *sec = &secs[i];
+		struct section *sec_applies, *sec_symtab;
+		char *sym_strtab;
+		Elf_Sym *sh_symtab;
+		int j;
+
+		if (sec->shdr.sh_type != SHT_REL_TYPE)
+			continue;
+
+		sec_symtab  = sec->link;
+		sec_applies = &secs[sec->shdr.sh_info];
+		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
+			continue;
+
+		/*
+		 * Do not perform relocations in .notes section; any
+		 * values there are meant for pre-boot consumption (e.g.
+		 * startup_xen).
+		 */
+		if (sec_applies->shdr.sh_type == SHT_NOTE)
+			continue;
+
+		sh_symtab  = sec_symtab->symtab;
+		sym_strtab = sec_symtab->link->strtab;
+
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+			Elf_Rel *rel;
+			Elf_Sym *sym;
+			const char *name;
+
+			rel = &sec->reltab[j];
+			sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
+			name = sym_name(sym_strtab, sym);
+
+			if (sym->st_shndx != SHN_ABS)
+				continue;
+
+			/* Absolute symbols are not relocated if bzImage is
+			 * loaded at a non-compiled address. Display a warning
+			 * to user at compile time about the absolute
+			 * relocations present.
+			 *
+			 * User need to audit the code to make sure
+			 * some symbols which should have been section
+			 * relative have not become absolute because of some
+			 * linker optimization or wrong programming usage.
+			 *
+			 * Before warning check if this absolute symbol
+			 * relocation is harmless.
+			 */
+			if (is_reloc(S_ABS, name) || is_reloc(S_REL, name))
+				continue;
+
+			if (!printed) {
+				printf("WARNING: Absolute relocations present\n");
+				printf("Offset     Info     Type     Sym.Value Sym.Name\n");
+				printed = 1;
+			}
+
+			printf(format,
+				rel->r_offset,
+				rel->r_info,
+				rel_type(ELF_R_TYPE(rel->r_info)),
+				sym->st_value,
+				name);
+		}
+	}
+
+	if (printed)
+		printf("\n");
+}
+
+static void add_reloc(struct relocs *r, uint32_t offset)
+{
+	if (r->count == r->size) {
+		unsigned long newsize = r->size + 50000;
+		void *mem = realloc(r->offset, newsize * sizeof(r->offset[0]));
+
+		if (!mem)
+			die("realloc of %ld entries for relocs failed\n", newsize);
+
+		r->offset = mem;
+		r->size = newsize;
+	}
+	r->offset[r->count++] = offset;
+}
+
+static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
+			Elf_Sym *sym, const char *symname))
+{
+	int i;
+
+	/* Walk through the relocations */
+	for (i = 0; i < shnum; i++) {
+		char *sym_strtab;
+		Elf_Sym *sh_symtab;
+		struct section *sec_applies, *sec_symtab;
+		int j;
+		struct section *sec = &secs[i];
+
+		if (sec->shdr.sh_type != SHT_REL_TYPE)
+			continue;
+
+		sec_symtab  = sec->link;
+		sec_applies = &secs[sec->shdr.sh_info];
+		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
+			continue;
+
+		/*
+		 * Do not perform relocations in .notes sections; any
+		 * values there are meant for pre-boot consumption (e.g.
+		 * startup_xen).
+		 */
+		if (sec_applies->shdr.sh_type == SHT_NOTE)
+			continue;
+
+		sh_symtab = sec_symtab->symtab;
+		sym_strtab = sec_symtab->link->strtab;
+
+		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf_Rel); j++) {
+			Elf_Rel *rel = &sec->reltab[j];
+			Elf_Sym *sym = &sh_symtab[ELF_R_SYM(rel->r_info)];
+			const char *symname = sym_name(sym_strtab, sym);
+
+			process(sec, rel, sym, symname);
+		}
+	}
+}
+
+#if ELF_BITS == 64
+
+static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
+		      const char *symname)
+{
+	unsigned r_type = ELF64_R_TYPE(rel->r_info);
+	ElfW(Addr) offset = rel->r_offset;
+	int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+	if (sym->st_shndx == SHN_UNDEF)
+		return 0;
+
+	switch (r_type) {
+	case R_X86_64_NONE:
+		/* NONE can be ignored. */
+		break;
+
+	case R_X86_64_PC32:
+	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
+		/*
+		 * PC relative relocations don't need to be adjusted.
+		 *
+		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
+		 */
+		break;
+
+	case R_X86_64_PC64:
+		/*
+		 * Only used by jump labels
+		 */
+		break;
+
+	case R_X86_64_32:
+	case R_X86_64_32S:
+	case R_X86_64_64:
+		if (shn_abs) {
+			/*
+			 * Whitelisted absolute symbols do not require
+			 * relocation.
+			 */
+			if (is_reloc(S_ABS, symname))
+				break;
+
+			die("Invalid absolute %s relocation: %s\n", rel_type(r_type), symname);
+			break;
+		}
+
+		/*
+		 * Relocation offsets for 64 bit kernels are output
+		 * as 32 bits and sign extended back to 64 bits when
+		 * the relocations are processed.
+		 * Make sure that the offset will fit.
+		 */
+		if ((int32_t)offset != (int64_t)offset)
+			die("Relocation offset doesn't fit in 32 bits\n");
+
+		if (r_type == R_X86_64_64)
+			add_reloc(&relocs64, offset);
+		else
+			add_reloc(&relocs32, offset);
+		break;
+
+	default:
+		die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
+		break;
+	}
+
+	return 0;
+}
+
+#else
+
+static int do_reloc32(struct section *sec, Elf_Rel *rel, Elf_Sym *sym,
+		      const char *symname)
+{
+	unsigned r_type = ELF32_R_TYPE(rel->r_info);
+	int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+	switch (r_type) {
+	case R_386_NONE:
+	case R_386_PC32:
+	case R_386_PC16:
+	case R_386_PC8:
+	case R_386_PLT32:
+		/*
+		 * NONE can be ignored and PC relative relocations don't need
+		 * to be adjusted. Because sym must be defined, R_386_PLT32 can
+		 * be treated the same way as R_386_PC32.
+		 */
+		break;
+
+	case R_386_32:
+		if (shn_abs) {
+			/*
+			 * Whitelisted absolute symbols do not require
+			 * relocation.
+			 */
+			if (is_reloc(S_ABS, symname))
+				break;
+
+			die("Invalid absolute %s relocation: %s\n", rel_type(r_type), symname);
+			break;
+		}
+
+		add_reloc(&relocs32, rel->r_offset);
+		break;
+
+	default:
+		die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
+		break;
+	}
+
+	return 0;
+}
+
+static int do_reloc_real(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, const char *symname)
+{
+	unsigned r_type = ELF32_R_TYPE(rel->r_info);
+	int shn_abs = (sym->st_shndx == SHN_ABS) && !is_reloc(S_REL, symname);
+
+	switch (r_type) {
+	case R_386_NONE:
+	case R_386_PC32:
+	case R_386_PC16:
+	case R_386_PC8:
+	case R_386_PLT32:
+		/*
+		 * NONE can be ignored and PC relative relocations don't need
+		 * to be adjusted. Because sym must be defined, R_386_PLT32 can
+		 * be treated the same way as R_386_PC32.
+		 */
+		break;
+
+	case R_386_16:
+		if (shn_abs) {
+			/*
+			 * Whitelisted absolute symbols do not require
+			 * relocation.
+			 */
+			if (is_reloc(S_ABS, symname))
+				break;
+
+			if (is_reloc(S_SEG, symname)) {
+				add_reloc(&relocs16, rel->r_offset);
+				break;
+			}
+		} else {
+			if (!is_reloc(S_LIN, symname))
+				break;
+		}
+		die("Invalid %s %s relocation: %s\n", shn_abs ? "absolute" : "relative", rel_type(r_type), symname);
+		break;
+
+	case R_386_32:
+		if (shn_abs) {
+			/*
+			 * Whitelisted absolute symbols do not require
+			 * relocation.
+			 */
+			if (is_reloc(S_ABS, symname))
+				break;
+
+			if (is_reloc(S_REL, symname)) {
+				add_reloc(&relocs32, rel->r_offset);
+				break;
+			}
+		} else {
+			if (is_reloc(S_LIN, symname))
+				add_reloc(&relocs32, rel->r_offset);
+			break;
+		}
+		die("Invalid %s %s relocation: %s\n", shn_abs ? "absolute" : "relative", rel_type(r_type), symname);
+		break;
+
+	default:
+		die("Unsupported relocation type: %s (%d)\n", rel_type(r_type), r_type);
+		break;
+	}
+
+	return 0;
+}
+
+#endif
+
+static int cmp_relocs(const void *va, const void *vb)
+{
+	const uint32_t *a, *b;
+
+	a = va;
+	b = vb;
+
+	return (*a == *b)? 0 : (*a > *b)? 1 : -1;
+}
+
+static void sort_relocs(struct relocs *r)
+{
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+}
+
+static int write32(uint32_t v, FILE *f)
+{
+	unsigned char buf[4];
+
+	put_unaligned_le32(v, buf);
+
+	return fwrite(buf, 1, 4, f) == 4 ? 0 : -1;
+}
+
+static int write32_as_text(uint32_t v, FILE *f)
+{
+	return fprintf(f, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1;
+}
+
+static void emit_relocs(int as_text, int use_real_mode)
+{
+	int i;
+	int (*write_reloc)(uint32_t, FILE *) = write32;
+	int (*do_reloc)(struct section *sec, Elf_Rel *rel, Elf_Sym *sym, const char *symname);
+
+#if ELF_BITS == 64
+	if (!use_real_mode)
+		do_reloc = do_reloc64;
+	else
+		die("--realmode not valid for a 64-bit ELF file");
+#else
+	if (!use_real_mode)
+		do_reloc = do_reloc32;
+	else
+		do_reloc = do_reloc_real;
+#endif
+
+	/* Collect up the relocations */
+	walk_relocs(do_reloc);
+
+	if (relocs16.count && !use_real_mode)
+		die("Segment relocations found but --realmode not specified\n");
+
+	/* Order the relocations for more efficient processing */
+	sort_relocs(&relocs32);
+#if ELF_BITS == 64
+	sort_relocs(&relocs64);
+#else
+	sort_relocs(&relocs16);
+#endif
+
+	/* Print the relocations */
+	if (as_text) {
+		/* Print the relocations in a form suitable that
+		 * gas will like.
+		 */
+		printf(".section \".data.reloc\",\"a\"\n");
+		printf(".balign 4\n");
+		write_reloc = write32_as_text;
+	}
+
+	if (use_real_mode) {
+		write_reloc(relocs16.count, stdout);
+		for (i = 0; i < relocs16.count; i++)
+			write_reloc(relocs16.offset[i], stdout);
+
+		write_reloc(relocs32.count, stdout);
+		for (i = 0; i < relocs32.count; i++)
+			write_reloc(relocs32.offset[i], stdout);
+	} else {
+#if ELF_BITS == 64
+		/* Print a stop */
+		write_reloc(0, stdout);
+
+		/* Now print each relocation */
+		for (i = 0; i < relocs64.count; i++)
+			write_reloc(relocs64.offset[i], stdout);
+#endif
+
+		/* Print a stop */
+		write_reloc(0, stdout);
+
+		/* Now print each relocation */
+		for (i = 0; i < relocs32.count; i++)
+			write_reloc(relocs32.offset[i], stdout);
+	}
+}
+
+/*
+ * As an aid to debugging problems with different linkers
+ * print summary information about the relocs.
+ * Since different linkers tend to emit the sections in
+ * different orders we use the section names in the output.
+ */
+static int do_reloc_info(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
+				const char *symname)
+{
+	printf("%s\t%s\t%s\t%s\n",
+		sec_name(sec->shdr.sh_info),
+		rel_type(ELF_R_TYPE(rel->r_info)),
+		symname,
+		sec_name(sym_index(sym)));
+
+	return 0;
+}
+
+static void print_reloc_info(void)
+{
+	printf("reloc section\treloc type\tsymbol\tsymbol section\n");
+	walk_relocs(do_reloc_info);
+}
+
+#if ELF_BITS == 64
+# define process process_64
+#else
+# define process process_32
+#endif
+
+void process(FILE *fp, int use_real_mode, int as_text,
+	     int show_absolute_syms, int show_absolute_relocs,
+	     int show_reloc_info)
+{
+	regex_init(use_real_mode);
+	read_ehdr(fp);
+	read_shdrs(fp);
+	read_strtabs(fp);
+	read_symtabs(fp);
+	read_relocs(fp);
+
+	if (show_absolute_syms) {
+		print_absolute_symbols();
+		return;
+	}
+
+	if (show_absolute_relocs) {
+		print_absolute_relocs();
+		return;
+	}
+
+	if (show_reloc_info) {
+		print_reloc_info();
+		return;
+	}
+
+	emit_relocs(as_text, use_real_mode);
+}
diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h
new file mode 100644
index 000000000..4c49c8244
--- /dev/null
+++ b/arch/x86/tools/relocs.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef RELOCS_H
+#define RELOCS_H
+
+#include <stdio.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <elf.h>
+#include <byteswap.h>
+#define USE_BSD
+#include <endian.h>
+#include <regex.h>
+#include <tools/le_byteshift.h>
+
+__attribute__((__format__(printf, 1, 2)))
+void die(char *fmt, ...) __attribute__((noreturn));
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+enum symtype {
+	S_ABS,
+	S_REL,
+	S_SEG,
+	S_LIN,
+	S_NSYMTYPES
+};
+
+void process_32(FILE *fp, int use_real_mode, int as_text,
+		int show_absolute_syms, int show_absolute_relocs,
+		int show_reloc_info);
+void process_64(FILE *fp, int use_real_mode, int as_text,
+		int show_absolute_syms, int show_absolute_relocs,
+		int show_reloc_info);
+#endif /* RELOCS_H */
diff --git a/arch/x86/tools/relocs_32.c b/arch/x86/tools/relocs_32.c
new file mode 100644
index 000000000..9442ff78b
--- /dev/null
+++ b/arch/x86/tools/relocs_32.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "relocs.h"
+
+#define ELF_BITS 32
+
+#define ELF_MACHINE		EM_386
+#define ELF_MACHINE_NAME	"i386"
+#define SHT_REL_TYPE		SHT_REL
+#define Elf_Rel			ElfW(Rel)
+
+#define ELF_CLASS		ELFCLASS32
+#define ELF_R_SYM(val)		ELF32_R_SYM(val)
+#define ELF_R_TYPE(val)		ELF32_R_TYPE(val)
+#define ELF_ST_TYPE(o)		ELF32_ST_TYPE(o)
+#define ELF_ST_BIND(o)		ELF32_ST_BIND(o)
+#define ELF_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY(o)
+
+#include "relocs.c"
diff --git a/arch/x86/tools/relocs_64.c b/arch/x86/tools/relocs_64.c
new file mode 100644
index 000000000..9029cb619
--- /dev/null
+++ b/arch/x86/tools/relocs_64.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "relocs.h"
+
+#define ELF_BITS 64
+
+#define ELF_MACHINE             EM_X86_64
+#define ELF_MACHINE_NAME        "x86_64"
+#define SHT_REL_TYPE            SHT_RELA
+#define Elf_Rel                 Elf64_Rela
+
+#define ELF_CLASS               ELFCLASS64
+#define ELF_R_SYM(val)          ELF64_R_SYM(val)
+#define ELF_R_TYPE(val)         ELF64_R_TYPE(val)
+#define ELF_ST_TYPE(o)          ELF64_ST_TYPE(o)
+#define ELF_ST_BIND(o)          ELF64_ST_BIND(o)
+#define ELF_ST_VISIBILITY(o)    ELF64_ST_VISIBILITY(o)
+
+#include "relocs.c"
diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c
new file mode 100644
index 000000000..6634352a2
--- /dev/null
+++ b/arch/x86/tools/relocs_common.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "relocs.h"
+
+void die(char *fmt, ...)
+{
+	va_list ap;
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(1);
+}
+
+static void usage(void)
+{
+	die("relocs [--abs-syms|--abs-relocs|--reloc-info|--text|--realmode]" \
+	    " vmlinux\n");
+}
+
+int main(int argc, char **argv)
+{
+	int show_absolute_syms, show_absolute_relocs, show_reloc_info;
+	int as_text, use_real_mode;
+	const char *fname;
+	FILE *fp;
+	int i;
+	unsigned char e_ident[EI_NIDENT];
+
+	show_absolute_syms = 0;
+	show_absolute_relocs = 0;
+	show_reloc_info = 0;
+	as_text = 0;
+	use_real_mode = 0;
+	fname = NULL;
+	for (i = 1; i < argc; i++) {
+		char *arg = argv[i];
+		if (*arg == '-') {
+			if (strcmp(arg, "--abs-syms") == 0) {
+				show_absolute_syms = 1;
+				continue;
+			}
+			if (strcmp(arg, "--abs-relocs") == 0) {
+				show_absolute_relocs = 1;
+				continue;
+			}
+			if (strcmp(arg, "--reloc-info") == 0) {
+				show_reloc_info = 1;
+				continue;
+			}
+			if (strcmp(arg, "--text") == 0) {
+				as_text = 1;
+				continue;
+			}
+			if (strcmp(arg, "--realmode") == 0) {
+				use_real_mode = 1;
+				continue;
+			}
+		}
+		else if (!fname) {
+			fname = arg;
+			continue;
+		}
+		usage();
+	}
+	if (!fname) {
+		usage();
+	}
+	fp = fopen(fname, "r");
+	if (!fp) {
+		die("Cannot open %s: %s\n", fname, strerror(errno));
+	}
+	if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT) {
+		die("Cannot read %s: %s", fname, strerror(errno));
+	}
+	rewind(fp);
+	if (e_ident[EI_CLASS] == ELFCLASS64)
+		process_64(fp, use_real_mode, as_text,
+			   show_absolute_syms, show_absolute_relocs,
+			   show_reloc_info);
+	else
+		process_32(fp, use_real_mode, as_text,
+			   show_absolute_syms, show_absolute_relocs,
+			   show_reloc_info);
+	fclose(fp);
+	return 0;
+}
diff --git a/arch/x86/tools/vdso2c.c b/arch/x86/tools/vdso2c.c
new file mode 100644
index 000000000..64a636b9f
--- /dev/null
+++ b/arch/x86/tools/vdso2c.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vdso2c - A vdso image preparation tool
+ * Copyright (c) 2014 Andy Lutomirski and others
+ *
+ * vdso2c requires stripped and unstripped input.  It would be trivial
+ * to fully strip the input in here, but, for reasons described below,
+ * we need to write a section table.  Doing this is more or less
+ * equivalent to dropping all non-allocatable sections, but it's
+ * easier to let objcopy handle that instead of doing it ourselves.
+ * If we ever need to do something fancier than what objcopy provides,
+ * it would be straightforward to add here.
+ *
+ * We're keep a section table for a few reasons:
+ *
+ * The Go runtime had a couple of bugs: it would read the section
+ * table to try to figure out how many dynamic symbols there were (it
+ * shouldn't have looked at the section table at all) and, if there
+ * were no SHT_SYNDYM section table entry, it would use an
+ * uninitialized value for the number of symbols.  An empty DYNSYM
+ * table would work, but I see no reason not to write a valid one (and
+ * keep full performance for old Go programs).  This hack is only
+ * needed on x86_64.
+ *
+ * The bug was introduced on 2012-08-31 by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b
+ * and was fixed on 2014-06-13 by:
+ * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
+ *
+ * Binutils has issues debugging the vDSO: it reads the section table to
+ * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
+ * would break build-id if we removed the section table.  Binutils
+ * also requires that shstrndx != 0.  See:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
+ *
+ * elfutils might not look for PT_NOTE if there is a section table at
+ * all.  I don't know whether this matters for any practical purpose.
+ *
+ * For simplicity, rather than hacking up a partial section table, we
+ * just write a mostly complete one.  We omit non-dynamic symbols,
+ * though, since they're rather large.
+ *
+ * Once binutils gets fixed, we might be able to drop this for all but
+ * the 64-bit vdso, since build-id only works in kernel RPMs, and
+ * systems that update to new enough kernel RPMs will likely update
+ * binutils in sync.  build-id has never worked for home-built kernel
+ * RPMs without manual symlinking, and I suspect that no one ever does
+ * that.
+ */
+
+#include <inttypes.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <fcntl.h>
+#include <err.h>
+
+#include <sys/mman.h>
+#include <sys/types.h>
+
+#include <tools/le_byteshift.h>
+
+#include <linux/elf.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+const char *outfilename;
+
+struct vdso_sym {
+	const char *name;
+	bool export;
+};
+
+struct vdso_sym required_syms[] = {
+	{"__kernel_vsyscall",				true},
+	{"__kernel_sigreturn",				true},
+	{"__kernel_rt_sigreturn",			true},
+	{"int80_landing_pad",				true},
+	{"vdso32_rt_sigreturn_landing_pad",		true},
+	{"vdso32_sigreturn_landing_pad",		true},
+	{"__futex_list64_try_unlock_cs_start",		true},
+	{"__futex_list64_try_unlock_cs_end",		true},
+	{"__futex_list32_try_unlock_cs_start",		true},
+	{"__futex_list32_try_unlock_cs_end",		true},
+};
+
+__attribute__((format(printf, 1, 2))) __attribute__((noreturn))
+static void fail(const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	fprintf(stderr, "Error: ");
+	vfprintf(stderr, format, ap);
+	if (outfilename)
+		unlink(outfilename);
+	exit(1);
+	va_end(ap);
+}
+
+/*
+ * Evil macros for little-endian reads and writes
+ */
+#define GLE(x, bits, ifnot)						\
+	__builtin_choose_expr(						\
+		(sizeof(*(x)) == bits/8),				\
+		(__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
+
+extern void bad_get_le(void);
+#define LAST_GLE(x)							\
+	__builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
+
+#define GET_LE(x)							\
+	GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
+
+#define PLE(x, val, bits, ifnot)					\
+	__builtin_choose_expr(						\
+		(sizeof(*(x)) == bits/8),				\
+		put_unaligned_le##bits((val), (x)), ifnot)
+
+extern void bad_put_le(void);
+#define LAST_PLE(x, val)						\
+	__builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
+
+#define PUT_LE(x, val)					\
+	PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
+
+
+#define NSYMS ARRAY_SIZE(required_syms)
+
+#define BITSFUNC3(name, bits, suffix) name##bits##suffix
+#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix)
+#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, )
+
+#define INT_BITS BITSFUNC2(int, ELF_BITS, _t)
+
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
+#define ELF_BITS 64
+#include "vdso2c.h"
+#undef ELF_BITS
+
+#define ELF_BITS 32
+#include "vdso2c.h"
+#undef ELF_BITS
+
+static void go(void *raw_addr, size_t raw_len,
+	       void *stripped_addr, size_t stripped_len,
+	       FILE *outfile, const char *name)
+{
+	Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr;
+
+	if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
+		go64(raw_addr, raw_len, stripped_addr, stripped_len,
+		     outfile, name);
+	} else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
+		go32(raw_addr, raw_len, stripped_addr, stripped_len,
+		     outfile, name);
+	} else {
+		fail("unknown ELF class\n");
+	}
+}
+
+static void map_input(const char *name, void **addr, size_t *len, int prot)
+{
+	off_t tmp_len;
+
+	int fd = open(name, O_RDONLY);
+	if (fd == -1)
+		err(1, "open(%s)", name);
+
+	tmp_len = lseek(fd, 0, SEEK_END);
+	if (tmp_len == (off_t)-1)
+		err(1, "lseek");
+	*len = (size_t)tmp_len;
+
+	*addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0);
+	if (*addr == MAP_FAILED)
+		err(1, "mmap");
+
+	close(fd);
+}
+
+int main(int argc, char **argv)
+{
+	size_t raw_len, stripped_len;
+	void *raw_addr, *stripped_addr;
+	FILE *outfile;
+	char *name, *tmp;
+	int namelen;
+
+	if (argc != 4) {
+		printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n");
+		return 1;
+	}
+
+	/*
+	 * Figure out the struct name.  If we're writing to a .so file,
+	 * generate raw output instead.
+	 */
+	name = strdup(argv[3]);
+	namelen = strlen(name);
+	if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) {
+		name = NULL;
+	} else {
+		tmp = strrchr(name, '/');
+		if (tmp)
+			name = tmp + 1;
+		tmp = strchr(name, '.');
+		if (tmp)
+			*tmp = '\0';
+		for (tmp = name; *tmp; tmp++)
+			if (*tmp == '-')
+				*tmp = '_';
+	}
+
+	map_input(argv[1], &raw_addr, &raw_len, PROT_READ);
+	map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ);
+
+	outfilename = argv[3];
+	outfile = fopen(outfilename, "w");
+	if (!outfile)
+		err(1, "fopen(%s)", outfilename);
+
+	go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
+
+	munmap(raw_addr, raw_len);
+	munmap(stripped_addr, stripped_len);
+	fclose(outfile);
+
+	return 0;
+}
diff --git a/arch/x86/tools/vdso2c.h b/arch/x86/tools/vdso2c.h
new file mode 100644
index 000000000..78ed1c1f2
--- /dev/null
+++ b/arch/x86/tools/vdso2c.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file is included twice from vdso2c.c.  It generates code for 32-bit
+ * and 64-bit vDSOs.  We need both for 64-bit builds, since 32-bit vDSOs
+ * are built for 32-bit userspace.
+ */
+
+static void BITSFUNC(copy)(FILE *outfile, const unsigned char *data, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (i % 10 == 0)
+			fprintf(outfile, "\n\t");
+		fprintf(outfile, "0x%02X, ", (int)(data)[i]);
+	}
+}
+
+
+/*
+ * Extract a section from the input data into a standalone blob.  Used to
+ * capture kernel-only data that needs to persist indefinitely, e.g. the
+ * exception fixup tables, but only in the kernel, i.e. the section can
+ * be stripped from the final vDSO image.
+ */
+static void BITSFUNC(extract)(const unsigned char *data, size_t data_len,
+			      FILE *outfile, ELF(Shdr) *sec, const char *name)
+{
+	unsigned long offset;
+	size_t len;
+
+	offset = (unsigned long)GET_LE(&sec->sh_offset);
+	len = (size_t)GET_LE(&sec->sh_size);
+
+	if (offset + len > data_len)
+		fail("section to extract overruns input data");
+
+	fprintf(outfile, "static const unsigned char %s[%zu] = {", name, len);
+	BITSFUNC(copy)(outfile, data + offset, len);
+	fprintf(outfile, "\n};\n\n");
+}
+
+static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
+			 void *stripped_addr, size_t stripped_len,
+			 FILE *outfile, const char *image_name)
+{
+	int found_load = 0;
+	unsigned long load_size = -1;  /* Work around bogus warning */
+	unsigned long mapping_size;
+	ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
+	unsigned long i, syms_nr;
+	ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
+		*alt_sec = NULL, *extable_sec = NULL;
+	ELF(Dyn) *dyn = 0, *dyn_end = 0;
+	const char *secstrings;
+	INT_BITS syms[NSYMS] = {};
+
+	ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
+
+	if (GET_LE(&hdr->e_type) != ET_DYN)
+		fail("input is not a shared object\n");
+
+	/* Walk the segment table. */
+	for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
+		if (GET_LE(&pt[i].p_type) == PT_LOAD) {
+			if (found_load)
+				fail("multiple PT_LOAD segs\n");
+
+			if (GET_LE(&pt[i].p_offset) != 0 ||
+			    GET_LE(&pt[i].p_vaddr) != 0)
+				fail("PT_LOAD in wrong place\n");
+
+			if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz))
+				fail("cannot handle memsz != filesz\n");
+
+			load_size = GET_LE(&pt[i].p_memsz);
+			found_load = 1;
+		} else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) {
+			dyn = raw_addr + GET_LE(&pt[i].p_offset);
+			dyn_end = raw_addr + GET_LE(&pt[i].p_offset) +
+				GET_LE(&pt[i].p_memsz);
+		}
+	}
+	if (!found_load)
+		fail("no PT_LOAD seg\n");
+
+	if (stripped_len < load_size)
+		fail("stripped input is too short\n");
+
+	if (!dyn)
+		fail("input has no PT_DYNAMIC section -- your toolchain is buggy\n");
+
+	/* Walk the dynamic table */
+	for (i = 0; dyn + i < dyn_end &&
+		     GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {
+		typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag);
+		if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA ||
+		    tag == DT_RELENT || tag == DT_TEXTREL)
+			fail("vdso image contains dynamic relocations\n");
+	}
+
+	/* Walk the section table */
+	secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+		GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
+	secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset);
+	for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
+		ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) +
+			GET_LE(&hdr->e_shentsize) * i;
+		if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
+			symtab_hdr = sh;
+
+		if (!strcmp(secstrings + GET_LE(&sh->sh_name),
+			    ".altinstructions"))
+			alt_sec = sh;
+		if (!strcmp(secstrings + GET_LE(&sh->sh_name), "__ex_table"))
+			extable_sec = sh;
+	}
+
+	if (!symtab_hdr)
+		fail("no symbol table\n");
+
+	strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+		GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
+
+	syms_nr = GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
+	/* Walk the symbol table */
+	for (i = 0; i < syms_nr; i++) {
+		unsigned int k;
+		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
+			GET_LE(&symtab_hdr->sh_entsize) * i;
+		const char *sym_name = raw_addr +
+				       GET_LE(&strtab_hdr->sh_offset) +
+				       GET_LE(&sym->st_name);
+
+		for (k = 0; k < NSYMS; k++) {
+			if (!strcmp(sym_name, required_syms[k].name)) {
+				if (syms[k]) {
+					fail("duplicate symbol %s\n",
+					     required_syms[k].name);
+				}
+
+				/*
+				 * Careful: we use negative addresses, but
+				 * st_value is unsigned, so we rely
+				 * on syms[k] being a signed type of the
+				 * correct width.
+				 */
+				syms[k] = GET_LE(&sym->st_value);
+			}
+		}
+	}
+
+	if (!image_name) {
+		fwrite(stripped_addr, stripped_len, 1, outfile);
+		return;
+	}
+
+	mapping_size = (stripped_len + 4095) / 4096 * 4096;
+
+	fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");
+	fprintf(outfile, "#include <linux/linkage.h>\n");
+	fprintf(outfile, "#include <linux/init.h>\n");
+	fprintf(outfile, "#include <asm/page_types.h>\n");
+	fprintf(outfile, "#include <asm/vdso.h>\n");
+	fprintf(outfile, "\n");
+	fprintf(outfile,
+		"static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
+		mapping_size);
+	for (i = 0; i < stripped_len; i++) {
+		if (i % 10 == 0)
+			fprintf(outfile, "\n\t");
+		fprintf(outfile, "0x%02X, ",
+			(int)((unsigned char *)stripped_addr)[i]);
+	}
+	fprintf(outfile, "\n};\n\n");
+	if (extable_sec)
+		BITSFUNC(extract)(raw_addr, raw_len, outfile,
+				  extable_sec, "extable");
+
+	fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
+	fprintf(outfile, "\t.data = raw_data,\n");
+	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
+	if (alt_sec) {
+		fprintf(outfile, "\t.alt = %lu,\n",
+			(unsigned long)GET_LE(&alt_sec->sh_offset));
+		fprintf(outfile, "\t.alt_len = %lu,\n",
+			(unsigned long)GET_LE(&alt_sec->sh_size));
+	}
+	if (extable_sec) {
+		fprintf(outfile, "\t.extable_base = %lu,\n",
+			(unsigned long)GET_LE(&extable_sec->sh_offset));
+		fprintf(outfile, "\t.extable_len = %lu,\n",
+			(unsigned long)GET_LE(&extable_sec->sh_size));
+		fprintf(outfile, "\t.extable = extable,\n");
+	}
+
+	for (i = 0; i < NSYMS; i++) {
+		if (required_syms[i].export && syms[i])
+			fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
+				required_syms[i].name, (int64_t)syms[i]);
+	}
+	fprintf(outfile, "};\n\n");
+	fprintf(outfile, "static __init int init_%s(void) {\n", image_name);
+	fprintf(outfile, "\treturn init_vdso_image(&%s);\n", image_name);
+	fprintf(outfile, "};\n");
+	fprintf(outfile, "subsys_initcall(init_%s);\n", image_name);
+
+}