Import kvm-unit-test into this repo

tests/kvm-unit-tests/.gitignore

@@ -0,0 +1,19 @@
+.gdbinit
+*.a
+*.d
+*.o
+*.flat
+*.elf
+.pc
+patches
+.stgit-*
+cscope.*
+*.swp
+/lib/asm
+/config.mak
+/*-run
+/msr.out
+/tests
+/build-head
+/logs/
+/logs.old/

tests/kvm-unit-tests/COPYRIGHT

@@ -0,0 +1,4 @@
+Copyright (C) 2006 Qumranet.
+
+The files in this directory and its subdirectories are licensed under the
+GNU LGPL, version 2.

tests/kvm-unit-tests/MAINTAINERS

@@ -0,0 +1,84 @@
+KVM Unit Tests Maintainers
+==========================
+
+The intention of this file is not to establish who owns what portions of the
+code base, but to provide a set of names that developers can consult when they
+have a question about a particular subset and also to provide a set of names
+to be CC'd when submitting a patch to obtain appropriate review.
+
+In general, if you have a question about inclusion of a patch, you
+should consult the KVM mailing list <kvm@vger.kernel.org> and not any
+specific individual privately.
+
+Descriptions of section entries:
+
+	M: Mail patches to: FullName <address@domain>
+	L: Mailing list that is relevant to this area
+	W: Web-page with status/info
+	Q: Patchwork web based patch tracking system site
+	T: SCM tree type and location.  Type is one of: git, hg, quilt, stgit.
+	S: Status, one of the following:
+	   Supported:	Someone is actually paid to look after this.
+	   Maintained:	Someone actually looks after it.
+	   Odd Fixes:	It has a maintainer but they don't have time to do
+			much other than throw the odd patch in. See below.
+	   Orphan:	No current maintainer [but maybe you could take the
+			role as you write your new code].
+	   Obsolete:	Old code. Something tagged obsolete generally means
+			it has been replaced by a better system and you
+			should be using that.
+	F: Files and directories with wildcard patterns.
+	   A trailing slash includes all files and subdirectory files.
+	   F:	drivers/net/	all files in and below drivers/net
+	   F:	drivers/net/*	all files in drivers/net, but not below
+	   F:	*/net/*		all files in "any top level directory"/net
+	   One pattern per line.  Multiple F: lines acceptable.
+	X: Files and directories that are NOT maintained, same rules as F:
+	   Files exclusions are tested before file matches.
+	   Can be useful for excluding a specific subdirectory, for instance:
+	   F:	net/
+	   X:	net/ipv6/
+	   matches all files in and below net excluding net/ipv6/
+	K: Keyword perl extended regex pattern to match content in a
+	   patch or file.  For instance:
+	   K: of_get_profile
+	      matches patches or files that contain "of_get_profile"
+	   K: \b(printk|pr_(info|err))\b
+	      matches patches or files that contain one or more of the words
+	      printk, pr_info or pr_err
+	   One regex pattern per line.  Multiple K: lines acceptable.
+
+
+Maintainers
+-----------
+M: Paolo Bonzini <pbonzini@redhat.com>
+M: Radim Krčmář <rkrcmar@redhat.com>
+L: kvm@vger.kernel.org
+T: git://git.kernel.org/pub/scm/virt/kvm/kvm-unit-tests.git
+
+Architecture Specific Code:
+---------------------------
+
+ARM
+M: Drew Jones <drjones@redhat.com>
+L: kvm@vger.kernel.org
+L: kvmarm@lists.cs.columbia.edu
+F: arm/*
+F: lib/arm/*
+F: lib/arm64/*
+
+POWERPC
+M: Laurent Vivier <lvivier@redhat.com>
+M: Thomas Huth <thuth@redhat.com>
+L: kvm@vger.kernel.org
+L: kvm-ppc@vger.kernel.org
+F: powerpc/*
+F: lib/powerpc/*
+F: lib/ppc64/*
+
+X86
+M: Paolo Bonzini <pbonzini@redhat.com>
+M: Radim Krčmář <rkrcmar@redhat.com>
+L: kvm@vger.kernel.org
+F: x86/*
+F: lib/x86/*

tests/kvm-unit-tests/Makefile

@@ -0,0 +1,109 @@
+
+SHELL := /bin/bash
+
+ifeq ($(wildcard config.mak),)
+$(error run ./configure first. See ./configure -h)
+endif
+
+include config.mak
+
+libdirs-get = $(shell [ -d "lib/$(1)" ] && echo "lib/$(1) lib/$(1)/asm")
+ARCH_LIBDIRS := $(call libdirs-get,$(ARCH)) $(call libdirs-get,$(TEST_DIR))
+
+DESTDIR := $(PREFIX)/share/kvm-unit-tests/
+
+.PHONY: arch_clean clean distclean cscope
+
+#make sure env CFLAGS variable is not used
+CFLAGS =
+
+libgcc := $(shell $(CC) --print-libgcc-file-name)
+
+libcflat := lib/libcflat.a
+cflatobjs := \
+	lib/argv.o \
+	lib/printf.o \
+	lib/string.o \
+	lib/abort.o \
+	lib/report.o \
+	lib/stack.o
+
+# libfdt paths
+LIBFDT_objdir = lib/libfdt
+LIBFDT_srcdir = lib/libfdt
+LIBFDT_archive = $(LIBFDT_objdir)/libfdt.a
+LIBFDT_include = $(addprefix $(LIBFDT_srcdir)/,$(LIBFDT_INCLUDES))
+LIBFDT_version = $(addprefix $(LIBFDT_srcdir)/,$(LIBFDT_VERSION))
+
+#include architecure specific make rules
+include $(TEST_DIR)/Makefile
+
+# cc-option
+# Usage: OP_CFLAGS+=$(call cc-option, -falign-functions=0, -malign-functions=0)
+
+cc-option = $(shell if $(CC) $(1) -S -o /dev/null -xc /dev/null \
+              > /dev/null 2>&1; then echo "$(1)"; else echo "$(2)"; fi ;)
+
+CFLAGS += -g
+CFLAGS += $(autodepend-flags) -Wall -Werror
+frame-pointer-flag=-f$(if $(KEEP_FRAME_POINTER),no-,)omit-frame-pointer
+fomit_frame_pointer := $(call cc-option, $(frame-pointer-flag), "")
+fnostack_protector := $(call cc-option, -fno-stack-protector, "")
+fnostack_protector_all := $(call cc-option, -fno-stack-protector-all, "")
+wno_frame_address := $(call cc-option, -Wno-frame-address, "")
+fno_pic := $(call cc-option, -fno-pic, "")
+no_pie := $(call cc-option, -no-pie, "")
+CFLAGS += $(fomit_frame_pointer)
+CFLAGS += $(fno_stack_protector)
+CFLAGS += $(fno_stack_protector_all)
+CFLAGS += $(wno_frame_address)
+CFLAGS += $(if $(U32_LONG_FMT),-D__U32_LONG_FMT__,)
+CFLAGS += $(fno_pic) $(no_pie)
+
+CXXFLAGS += $(CFLAGS)
+
+autodepend-flags = -MMD -MF $(dir $*).$(notdir $*).d
+
+LDFLAGS += $(CFLAGS)
+LDFLAGS += -pthread -lrt
+
+$(libcflat): $(cflatobjs)
+	$(AR) rcs $@ $^
+
+include $(LIBFDT_srcdir)/Makefile.libfdt
+$(LIBFDT_archive): CFLAGS += -ffreestanding -I lib -I lib/libfdt -Wno-sign-compare
+$(LIBFDT_archive): $(addprefix $(LIBFDT_objdir)/,$(LIBFDT_OBJS))
+	$(AR) rcs $@ $^
+
+%.o: %.S
+	$(CC) $(CFLAGS) -c -nostdlib -o $@ $<
+
+-include */.*.d */*/.*.d
+
+all: $(shell git rev-parse --verify --short=8 HEAD >build-head 2>/dev/null)
+
+standalone: all
+	@scripts/mkstandalone.sh
+
+install: standalone
+	mkdir -p $(DESTDIR)
+	install tests/* $(DESTDIR)
+
+clean: arch_clean
+	$(RM) lib/.*.d $(libcflat) $(cflatobjs)
+
+libfdt_clean:
+	$(RM) $(LIBFDT_archive) \
+	$(addprefix $(LIBFDT_objdir)/,$(LIBFDT_OBJS)) \
+	$(LIBFDT_objdir)/.*.d
+
+distclean: clean libfdt_clean
+	$(RM) lib/asm config.mak $(TEST_DIR)-run msr.out cscope.* build-head
+	$(RM) -r tests logs logs.old
+
+cscope: cscope_dirs = lib lib/libfdt lib/linux $(TEST_DIR) $(ARCH_LIBDIRS) lib/asm-generic
+cscope:
+	$(RM) ./cscope.*
+	find -L $(cscope_dirs) -maxdepth 1 \
+		-name '*.[chsS]' -print | sed 's,^\./,,' | sort -u > ./cscope.files
+	cscope -bk

tests/kvm-unit-tests/README.md

@@ -0,0 +1,131 @@
+# kvm-unit-tests for v86
+
+Run the following to run this test:
+
+```sh
+./configure
+make
+make -C ../../build/libv86.js
+./run.js x86/realmode.flat
+./run.js x86/setjmp.flat
+./run.js x86/cmpxchg8b.flat
+./run.js x86/sieve.flat
+./run.js x86/ioapic.flat
+./run.js x86/apic.flat
+```
+
+Tests can also be run in browser by going to `?profile=test-$name` (for
+example, `?profile=test-realmode`).
+
+
+# Welcome to kvm-unit-tests
+
+See http://www.linux-kvm.org/page/KVM-unit-tests for a high-level
+description of this project, as well as running tests and adding
+tests HOWTOs.
+
+# Building the tests
+
+This directory contains sources for a kvm test suite.
+
+To create the test images do:
+
+    ./configure
+    make
+
+in this directory. Test images are created in ./<ARCH>/*.flat
+
+## Standalone tests
+
+The tests can be built as standalone
+To create and use standalone tests do:
+
+    ./configure
+    make standalone
+    (send tests/some-test somewhere)
+    (go to somewhere)
+    ./some-test
+
+'make install' will install all tests in PREFIX/share/kvm-unit-tests/tests,
+each as a standalone test.
+
+
+# Running the tests
+
+Then use the runner script to detect the correct invocation and
+invoke the test:
+
+    ./x86-run ./x86/msr.flat
+or:
+
+    ./run_tests.sh
+
+to run them all.
+
+To select a specific qemu binary, specify the QEMU=<path>
+environment variable:
+
+    QEMU=/tmp/qemu/x86_64-softmmu/qemu-system-x86_64 ./x86-run ./x86/msr.flat
+
+# Unit test inputs
+
+Unit tests use QEMU's '-append <args...>' parameter for command line
+inputs, i.e. all args will be available as argv strings in main().
+Additionally a file of the form
+
+KEY=VAL
+KEY2=VAL
+...
+
+may be passed with '-initrd <file>' to become the unit test's environ,
+which can then be accessed in the usual ways, e.g. VAL = getenv("KEY")
+Any key=val strings can be passed, but some have reserved meanings in
+the framework. The list of reserved environment variables is below
+
+ QEMU_ACCEL            ... either kvm or tcg
+ QEMU_VERSION_STRING   ... string of the form `qemu -h | head -1`
+ KERNEL_VERSION_STRING ... string of the form `uname -r`
+
+Additionally these self-explanatory variables are reserved
+
+ QEMU_MAJOR, QEMU_MINOR, QEMU_MICRO, KERNEL_VERSION, KERNEL_PATCHLEVEL,
+ KERNEL_SUBLEVEL, KERNEL_EXTRAVERSION
+
+# Contributing
+
+## Directory structure
+
+    .:				configure script, top-level Makefile, and run_tests.sh
+    ./scripts:		helper scripts for building and running tests
+    ./lib:			general architecture neutral services for the tests
+    ./lib/<ARCH>:	architecture dependent services for the tests
+    ./<ARCH>:		the sources of the tests and the created objects/images
+
+See <ARCH>/README for architecture specific documentation.
+
+## Style
+
+Currently there is a mix of indentation styles so any changes to
+existing files should be consistent with the existing style. For new
+files:
+
+  - C: please use standard linux-with-tabs
+  - Shell: use TABs for indentation
+
+## Patches
+
+Patches are welcome at the KVM mailing list <kvm@vger.kernel.org>.
+
+Please prefix messages with: [kvm-unit-tests PATCH]
+
+You can add the following to .git/config to do this automatically for you:
+
+    [format]
+        subjectprefix = kvm-unit-tests PATCH
+
+Additionally it's helpful to have a common order of file types in patches.
+Our chosen order attempts to place the more declarative files before
+the code files. We also start with common code and finish with unit test
+code. git-diff's orderFile feature allows us to specify the order in a
+file. The orderFile we use is `scripts/git.difforder`. Adding the config
+with `git config diff.orderFile scripts/git.difforder` enables it.

tests/kvm-unit-tests/configure

@@ -0,0 +1,167 @@
+#!/bin/bash
+
+prefix=/usr/local
+cc=gcc
+ld=ld
+objcopy=objcopy
+objdump=objdump
+ar=ar
+addr2line=addr2line
+arch=i386
+host=$arch
+cross_prefix=
+endian=""
+pretty_print_stacks=yes
+u32_long=
+
+usage() {
+    cat <<-EOF
+	Usage: $0 [options]
+
+	Options include:
+	    --arch=ARCH            architecture to compile for ($arch)
+	    --processor=PROCESSOR  processor to compile for ($arch)
+	    --cross-prefix=PREFIX  cross compiler prefix
+	    --cc=CC		   c compiler to use ($cc)
+	    --ld=LD		   ld linker to use ($ld)
+	    --prefix=PREFIX        where to install things ($prefix)
+	    --endian=ENDIAN        endianness to compile for (little or big, ppc64 only)
+	    --[enable|disable]-pretty-print-stacks
+	                           enable or disable pretty stack printing (enabled by default)
+EOF
+    exit 1
+}
+
+while [[ "$1" = -* ]]; do
+    opt="$1"; shift
+    arg=
+    if [[ "$opt" = *=* ]]; then
+	arg="${opt#*=}"
+	opt="${opt%%=*}"
+    fi
+    case "$opt" in
+	--prefix)
+	    prefix="$arg"
+	    ;;
+        --arch)
+	    arch="$arg"
+	    ;;
+        --processor)
+	    processor="$arg"
+	    ;;
+	--cross-prefix)
+	    cross_prefix="$arg"
+	    ;;
+	--endian)
+	    endian="$arg"
+	    ;;
+	--cc)
+	    cc="$arg"
+	    ;;
+	--ld)
+	    ld="$arg"
+	    ;;
+	--enable-pretty-print-stacks)
+	    pretty_print_stacks=yes
+	    ;;
+	--disable-pretty-print-stacks)
+	    pretty_print_stacks=no
+	    ;;
+	--help)
+	    usage
+	    ;;
+	*)
+	    usage
+	    ;;
+    esac
+done
+
+arch_name=$arch
+[ "$arch" = "aarch64" ] && arch="arm64"
+[ "$arch_name" = "arm64" ] && arch_name="aarch64"
+
+[ -z "$processor" ] && processor="$arch"
+
+if [ "$processor" = "arm64" ]; then
+    processor="cortex-a57"
+elif [ "$processor" = "arm" ]; then
+    processor="cortex-a15"
+fi
+
+if [ "$arch" = "i386" ] || [ "$arch" = "x86_64" ]; then
+    testdir=x86
+elif [ "$arch" = "arm" ] || [ "$arch" = "arm64" ]; then
+    testdir=arm
+elif [ "$arch" = "ppc64" ]; then
+    testdir=powerpc
+    firmware="$testdir/boot_rom.bin"
+    if [ "$endian" != "little" ] && [ "$endian" != "big" ]; then
+        echo "You must provide endianness (big or little)!"
+        usage
+    fi
+else
+    testdir=$arch
+fi
+if [ ! -d $testdir ]; then
+    echo "$testdir does not exist!"
+    exit 1
+fi
+if [ -f $testdir/run ]; then
+    ln -fs $testdir/run $testdir-run
+fi
+
+# check if uint32_t needs a long format modifier
+cat << EOF > lib-test.c
+__UINT32_TYPE__
+EOF
+u32_long=$($cross_prefix$cc -E lib-test.c | grep -v '^#' | grep -q long && echo yes)
+rm -f lib-test.c
+
+# check for dependent 32 bit libraries
+if [ "$arch" != "arm" ]; then
+cat << EOF > lib_test.c
+#include <stdc++.h>
+#include <boost_thread-mt.h>
+#include <pthread.h>
+
+int main ()
+{}
+EOF
+$cc -m32 -o /dev/null lib_test.c &> /dev/null
+exit=$?
+if [ $exit -eq 0 ]; then
+    api=true
+fi
+rm -f lib_test.c
+fi
+
+# link lib/asm for the architecture
+rm -f lib/asm
+asm=asm-generic
+if [ -d lib/$arch/asm ]; then
+	asm=$arch/asm
+elif [ -d lib/$testdir/asm ]; then
+	asm=$testdir/asm
+fi
+ln -s $asm lib/asm
+
+# create the config
+cat <<EOF > config.mak
+PREFIX=$prefix
+HOST=$host
+ARCH=$arch
+ARCH_NAME=$arch_name
+PROCESSOR=$processor
+CC=$cross_prefix$cc
+LD=$cross_prefix$ld
+OBJCOPY=$cross_prefix$objcopy
+OBJDUMP=$cross_prefix$objdump
+AR=$cross_prefix$ar
+ADDR2LINE=$cross_prefix$addr2line
+API=$api
+TEST_DIR=$testdir
+FIRMWARE=$firmware
+ENDIAN=$endian
+PRETTY_PRINT_STACKS=$pretty_print_stacks
+U32_LONG_FMT=$u32_long
+EOF

tests/kvm-unit-tests/lib/abort.c

@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+/*
+ * When exit(code) is invoked, qemu will exit with ((code << 1) | 1),
+ * leaving us 128 exit status codes. To avoid confusion with signal
+ * status, we further limit exit codes to those resulting in qemu
+ * exiting with a status < 128. We give abort() the highest (127),
+ * leaving the lower status codes for unit tests.
+ */
+#define ABORT_EXIT_STATUS 63	/* 127 exit status from qemu */
+
+void abort(void)
+{
+	exit(ABORT_EXIT_STATUS);
+}

tests/kvm-unit-tests/lib/alloc.c

@@ -0,0 +1,179 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "alloc.h"
+#include "asm/spinlock.h"
+#include "asm/io.h"
+
+#define PHYS_ALLOC_NR_REGIONS	256
+
+struct phys_alloc_region {
+	phys_addr_t base;
+	phys_addr_t size;
+};
+
+static struct phys_alloc_region regions[PHYS_ALLOC_NR_REGIONS];
+static int nr_regions;
+
+static struct spinlock lock;
+static phys_addr_t base, top, align_min;
+
+void phys_alloc_show(void)
+{
+	int i;
+
+	spin_lock(&lock);
+	printf("phys_alloc minimum alignment: 0x%" PRIx64 "\n",
+		(u64)align_min);
+	for (i = 0; i < nr_regions; ++i)
+		printf("%016" PRIx64 "-%016" PRIx64 " [%s]\n",
+			(u64)regions[i].base,
+			(u64)(regions[i].base + regions[i].size - 1),
+			"USED");
+	printf("%016" PRIx64 "-%016" PRIx64 " [%s]\n",
+		(u64)base, (u64)(top - 1), "FREE");
+	spin_unlock(&lock);
+}
+
+void phys_alloc_init(phys_addr_t base_addr, phys_addr_t size)
+{
+	spin_lock(&lock);
+	base = base_addr;
+	top = base + size;
+	align_min = DEFAULT_MINIMUM_ALIGNMENT;
+	nr_regions = 0;
+	spin_unlock(&lock);
+}
+
+void phys_alloc_set_minimum_alignment(phys_addr_t align)
+{
+	assert(align && !(align & (align - 1)));
+	spin_lock(&lock);
+	align_min = align;
+	spin_unlock(&lock);
+}
+
+static phys_addr_t phys_alloc_aligned_safe(phys_addr_t size,
+					   phys_addr_t align, bool safe)
+{
+	static bool warned = false;
+	phys_addr_t addr, size_orig = size;
+	u64 top_safe;
+
+	spin_lock(&lock);
+
+	top_safe = top;
+
+	if (safe && sizeof(long) == 4)
+		top_safe = MIN(top_safe, 1ULL << 32);
+
+	align = MAX(align, align_min);
+
+	addr = ALIGN(base, align);
+	size += addr - base;
+
+	if ((top_safe - base) < size) {
+		printf("phys_alloc: requested=0x%" PRIx64
+		       " (align=0x%" PRIx64 "), "
+		       "need=0x%" PRIx64 ", but free=0x%" PRIx64 ". "
+		       "top=0x%" PRIx64 ", top_safe=0x%" PRIx64 "\n",
+		       (u64)size_orig, (u64)align, (u64)size, top_safe - base,
+		       (u64)top, top_safe);
+		spin_unlock(&lock);
+		return INVALID_PHYS_ADDR;
+	}
+
+	base += size;
+
+	if (nr_regions < PHYS_ALLOC_NR_REGIONS) {
+		regions[nr_regions].base = addr;
+		regions[nr_regions].size = size_orig;
+		++nr_regions;
+	} else if (!warned) {
+		printf("WARNING: phys_alloc: No free log entries, "
+		       "can no longer log allocations...\n");
+		warned = true;
+	}
+
+	spin_unlock(&lock);
+
+	return addr;
+}
+
+static phys_addr_t phys_zalloc_aligned_safe(phys_addr_t size,
+					    phys_addr_t align, bool safe)
+{
+	phys_addr_t addr = phys_alloc_aligned_safe(size, align, safe);
+	if (addr == INVALID_PHYS_ADDR)
+		return addr;
+
+	memset(phys_to_virt(addr), 0, size);
+	return addr;
+}
+
+phys_addr_t phys_alloc_aligned(phys_addr_t size, phys_addr_t align)
+{
+	return phys_alloc_aligned_safe(size, align, false);
+}
+
+phys_addr_t phys_zalloc_aligned(phys_addr_t size, phys_addr_t align)
+{
+	return phys_zalloc_aligned_safe(size, align, false);
+}
+
+phys_addr_t phys_alloc(phys_addr_t size)
+{
+	return phys_alloc_aligned(size, align_min);
+}
+
+phys_addr_t phys_zalloc(phys_addr_t size)
+{
+	return phys_zalloc_aligned(size, align_min);
+}
+
+static void *early_malloc(size_t size)
+{
+	phys_addr_t addr = phys_alloc_aligned_safe(size, align_min, true);
+	if (addr == INVALID_PHYS_ADDR)
+		return NULL;
+
+	return phys_to_virt(addr);
+}
+
+static void *early_calloc(size_t nmemb, size_t size)
+{
+	phys_addr_t addr = phys_zalloc_aligned_safe(nmemb * size,
+						    align_min, true);
+	if (addr == INVALID_PHYS_ADDR)
+		return NULL;
+
+	return phys_to_virt(addr);
+}
+
+static void early_free(void *ptr __unused)
+{
+}
+
+static void *early_memalign(size_t alignment, size_t size)
+{
+	phys_addr_t addr;
+
+	assert(alignment && !(alignment & (alignment - 1)));
+
+	addr = phys_alloc_aligned_safe(size, alignment, true);
+	if (addr == INVALID_PHYS_ADDR)
+		return NULL;
+
+	return phys_to_virt(addr);
+}
+
+static struct alloc_ops early_alloc_ops = {
+	.malloc = early_malloc,
+	.calloc = early_calloc,
+	.free = early_free,
+	.memalign = early_memalign,
+};
+
+struct alloc_ops *alloc_ops = &early_alloc_ops;

tests/kvm-unit-tests/lib/alloc.h

@@ -0,0 +1,116 @@
+#ifndef _ALLOC_H_
+#define _ALLOC_H_
+/*
+ * alloc supplies three ingredients to the test framework that are all
+ * related to the support of dynamic memory allocation.
+ *
+ * The first is a set of alloc function wrappers for malloc and its
+ * friends. Using wrappers allows test code and common code to use the
+ * same interface for memory allocation at all stages, even though the
+ * implementations may change with the stage, e.g. pre/post paging.
+ *
+ * The second is a set of implementations for the alloc function
+ * interfaces. These implementations are named early_*, as they can be
+ * used almost immediately by the test framework.
+ *
+ * The third is a very simple physical memory allocator, which the
+ * early_* alloc functions build on.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+struct alloc_ops {
+	void *(*malloc)(size_t size);
+	void *(*calloc)(size_t nmemb, size_t size);
+	void (*free)(void *ptr);
+	void *(*memalign)(size_t alignment, size_t size);
+};
+
+/*
+ * alloc_ops is initialized to early_alloc_ops
+ */
+extern struct alloc_ops *alloc_ops;
+
+static inline void *malloc(size_t size)
+{
+	assert(alloc_ops && alloc_ops->malloc);
+	return alloc_ops->malloc(size);
+}
+
+static inline void *calloc(size_t nmemb, size_t size)
+{
+	assert(alloc_ops && alloc_ops->calloc);
+	return alloc_ops->calloc(nmemb, size);
+}
+
+static inline void free(void *ptr)
+{
+	assert(alloc_ops && alloc_ops->free);
+	alloc_ops->free(ptr);
+}
+
+static inline void *memalign(size_t alignment, size_t size)
+{
+	assert(alloc_ops && alloc_ops->memalign);
+	return alloc_ops->memalign(alignment, size);
+}
+
+/*
+ * phys_alloc is a very simple allocator which allows physical memory
+ * to be partitioned into regions until all memory is allocated.
+ *
+ * Note: This is such a simple allocator that there is no way to free
+ * a region. For more complicated memory management a single region
+ * can be allocated, but then have its memory managed by a more
+ * sophisticated allocator, e.g. a page allocator.
+ */
+#define DEFAULT_MINIMUM_ALIGNMENT 32
+
+/*
+ * phys_alloc_init creates the initial free memory region of size @size
+ * at @base. The minimum alignment is set to DEFAULT_MINIMUM_ALIGNMENT.
+ */
+extern void phys_alloc_init(phys_addr_t base, phys_addr_t size);
+
+/*
+ * phys_alloc_set_minimum_alignment sets the minimum alignment to
+ * @align.
+ */
+extern void phys_alloc_set_minimum_alignment(phys_addr_t align);
+
+/*
+ * phys_alloc_aligned returns the base address of a region of size @size,
+ * where the address is aligned to @align, or INVALID_PHYS_ADDR if there
+ * isn't enough free memory to satisfy the request.
+ */
+extern phys_addr_t phys_alloc_aligned(phys_addr_t size, phys_addr_t align);
+
+/*
+ * phys_zalloc_aligned is like phys_alloc_aligned, but zeros the memory
+ * before returning the address.
+ */
+extern phys_addr_t phys_zalloc_aligned(phys_addr_t size, phys_addr_t align);
+
+/*
+ * phys_alloc returns the base address of a region of size @size, or
+ * INVALID_PHYS_ADDR if there isn't enough free memory to satisfy the
+ * request.
+ */
+extern phys_addr_t phys_alloc(phys_addr_t size);
+
+/*
+ * phys_zalloc is like phys_alloc, but zeros the memory before returning.
+ */
+extern phys_addr_t phys_zalloc(phys_addr_t size);
+
+/*
+ * phys_alloc_show outputs all currently allocated regions with the
+ * following format
+ *   <start_addr>-<end_addr> [<USED|FREE>]
+ */
+extern void phys_alloc_show(void);
+
+#endif /* _ALLOC_H_ */

tests/kvm-unit-tests/lib/argv.c

@@ -0,0 +1,141 @@
+#include "libcflat.h"
+#include "auxinfo.h"
+
+int __argc;
+char *__args;
+char *__argv[100];
+char *__environ[200];
+
+char **environ = __environ;
+
+static char args_copy[1000];
+static char *copy_ptr = args_copy;
+
+#define isblank(c) ((c) == ' ' || (c) == '\t')
+#define isalpha(c) (((c) >= 'A' && (c) <= 'Z') || ((c) >= 'a' && (c) <= 'z') || (c) == '_')
+#define isalnum(c) (isalpha(c) || ((c) >= '0' && (c) <= '9'))
+
+static char *skip_blanks(char *p)
+{
+	while (isblank(*p))
+		++p;
+	return p;
+}
+
+void __setup_args(void)
+{
+	char *args = __args;
+	char **argv = __argv + __argc;
+
+	while (*(args = skip_blanks(args)) != '\0') {
+		*argv++ = copy_ptr;
+		while (*args != '\0' && !isblank(*args))
+			*copy_ptr++ = *args++;
+		*copy_ptr++ = '\0';
+	}
+	__argc = argv - __argv;
+}
+
+void setup_args(char *args)
+{
+	if (!args)
+		return;
+
+	__args = args;
+	__setup_args();
+}
+
+void setup_args_progname(char *args)
+{
+	__argv[0] = copy_ptr;
+	strcpy(__argv[0], auxinfo.progname);
+	copy_ptr += strlen(auxinfo.progname) + 1;
+	++__argc;
+	if (args) {
+		__args = args;
+		__setup_args();
+	}
+}
+
+static char *env_eol(char *env)
+{
+	while (*env && *env != '\n')
+		++env;
+	return env;
+}
+
+static char *env_invalid_eol(char *env)
+{
+	char *eol = env_eol(env);
+	char eol_old = *eol;
+
+	*eol = '\0';
+	printf("Invalid environment variable: %s\n", env);
+	*eol = eol_old;
+	return eol;
+}
+
+static char *env_next(char *env)
+{
+	char *p;
+
+	if (!*env)
+		return env;
+
+	if (isalpha(*env)) {
+		bool invalid = false;
+
+		p = env + 1;
+		while (*p && *p != '=' && *p != '\n') {
+			if (!isalnum(*p))
+				invalid = true;
+			++p;
+		}
+
+		if (*p != '=')
+			invalid = true;
+
+		if (invalid) {
+			env = env_invalid_eol(env);
+			return *env ? env_next(env + 1) : env;
+		}
+		return env;
+	}
+
+	p = env;
+	while (isblank(*p))
+		++p;
+
+	if (*p == '\n')
+		return env_next(p + 1);
+
+	if (*p == '#')
+		env = env_eol(env);
+	else
+		env = env_invalid_eol(env);
+
+	return *env ? env_next(env + 1) : env;
+}
+
+void setup_env(char *env, int size)
+{
+	char *eof = env + size, *p = env;
+	bool newline = false;
+	int i = 0;
+
+	while (*p)
+		++p;
+	if (p == eof)
+		newline = true;
+
+	while (env < eof) {
+		if (newline)
+			env = env_next(env);
+		if (!*env || env >= eof)
+			break;
+		__environ[i++] = env;
+		while (env < eof && *env && !(newline && *env == '\n'))
+			++env;
+		*env++ = '\0';
+	}
+}

tests/kvm-unit-tests/lib/asm-generic/atomic.h

@@ -0,0 +1,21 @@
+#ifndef __ASM_GENERIC_ATOMIC_H__
+#define __ASM_GENERIC_ATOMIC_H__
+
+/* From QEMU include/qemu/atomic.h */
+#define atomic_fetch_inc(ptr)  __sync_fetch_and_add(ptr, 1)
+#define atomic_fetch_dec(ptr)  __sync_fetch_and_add(ptr, -1)
+#define atomic_fetch_add(ptr, n) __sync_fetch_and_add(ptr, n)
+#define atomic_fetch_sub(ptr, n) __sync_fetch_and_sub(ptr, n)
+#define atomic_fetch_and(ptr, n) __sync_fetch_and_and(ptr, n)
+#define atomic_fetch_or(ptr, n) __sync_fetch_and_or(ptr, n)
+#define atomic_fetch_xor(ptr, n) __sync_fetch_and_xor(ptr, n)
+
+#define atomic_inc_fetch(ptr)  __sync_add_and_fetch(ptr, 1)
+#define atomic_dec_fetch(ptr)  __sync_add_and_fetch(ptr, -1)
+#define atomic_add_fetch(ptr, n) __sync_add_and_fetch(ptr, n)
+#define atomic_sub_fetch(ptr, n) __sync_sub_and_fetch(ptr, n)
+#define atomic_and_fetch(ptr, n) __sync_and_and_fetch(ptr, n)
+#define atomic_or_fetch(ptr, n) __sync_or_and_fetch(ptr, n)
+#define atomic_xor_fetch(ptr, n) __sync_xor_and_fetch(ptr, n)
+
+#endif

tests/kvm-unit-tests/lib/asm-generic/barrier.h

@@ -0,0 +1,35 @@
+#ifndef _ASM_BARRIER_H_
+#define _ASM_BARRIER_H_
+/*
+ * asm-generic/barrier.h
+ *
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+#ifndef mb
+#define mb()	asm volatile("":::"memory")
+#endif
+#ifndef rmb
+#define rmb()	asm volatile("":::"memory")
+#endif
+#ifndef wmb
+#define wmb()	asm volatile("":::"memory")
+#endif
+
+#ifndef smp_mb
+#define smp_mb()	mb()
+#endif
+#ifndef smp_rmb
+#define smp_rmb()	rmb()
+#endif
+#ifndef smp_wmb
+#define smp_wmb()	wmb()
+#endif
+
+#ifndef cpu_relax
+#define cpu_relax()	asm volatile ("":::"memory")
+#endif
+
+#endif /* _ASM_BARRIER_H_ */

tests/kvm-unit-tests/lib/asm-generic/io.h

@@ -0,0 +1,213 @@
+#ifndef _ASM_GENERIC_IO_H_
+#define _ASM_GENERIC_IO_H_
+/*
+ * asm-generic/io.h
+ *  adapted from the Linux kernel's include/asm-generic/io.h
+ *  and arch/arm/include/asm/io.h
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "asm/page.h"
+#include "asm/barrier.h"
+
+#ifndef __raw_readb
+static inline u8 __raw_readb(const volatile void *addr)
+{
+	return *(const volatile u8 *)addr;
+}
+#endif
+
+#ifndef __raw_readw
+static inline u16 __raw_readw(const volatile void *addr)
+{
+	return *(const volatile u16 *)addr;
+}
+#endif
+
+#ifndef __raw_readl
+static inline u32 __raw_readl(const volatile void *addr)
+{
+	return *(const volatile u32 *)addr;
+}
+#endif
+
+#ifndef __raw_readq
+static inline u64 __raw_readq(const volatile void *addr)
+{
+	assert(sizeof(unsigned long) == sizeof(u64));
+	return *(const volatile u64 *)addr;
+}
+#endif
+
+#ifndef __raw_writeb
+static inline void __raw_writeb(u8 b, volatile void *addr)
+{
+	*(volatile u8 *)addr = b;
+}
+#endif
+
+#ifndef __raw_writew
+static inline void __raw_writew(u16 b, volatile void *addr)
+{
+	*(volatile u16 *)addr = b;
+}
+#endif
+
+#ifndef __raw_writel
+static inline void __raw_writel(u32 b, volatile void *addr)
+{
+	*(volatile u32 *)addr = b;
+}
+#endif
+
+#ifndef __raw_writeq
+static inline void __raw_writeq(u64 b, volatile void *addr)
+{
+	assert(sizeof(unsigned long) == sizeof(u64));
+	*(volatile u64 *)addr = b;
+}
+#endif
+
+#ifndef __bswap16
+static inline u16 __bswap16(u16 x)
+{
+	return ((x >> 8) & 0xff) | ((x & 0xff) << 8);
+}
+#endif
+
+#ifndef __bswap32
+static inline u32 __bswap32(u32 x)
+{
+	return ((x & 0xff000000) >> 24) | ((x & 0x00ff0000) >>  8) |
+	       ((x & 0x0000ff00) <<  8) | ((x & 0x000000ff) << 24);
+}
+#endif
+
+#ifndef __bswap64
+static inline u64 __bswap64(u64 x)
+{
+	return ((x & 0x00000000000000ffULL) << 56) |
+	       ((x & 0x000000000000ff00ULL) << 40) |
+	       ((x & 0x0000000000ff0000ULL) << 24) |
+	       ((x & 0x00000000ff000000ULL) <<  8) |
+	       ((x & 0x000000ff00000000ULL) >>  8) |
+	       ((x & 0x0000ff0000000000ULL) >> 24) |
+	       ((x & 0x00ff000000000000ULL) >> 40) |
+	       ((x & 0xff00000000000000ULL) >> 56);
+}
+#endif
+
+#ifndef __cpu_is_be
+#define __cpu_is_be() (0)
+#endif
+
+#define le16_to_cpu(x) \
+	({ u16 __r = __cpu_is_be() ? __bswap16(x) : ((u16)x); __r; })
+#define cpu_to_le16 le16_to_cpu
+
+#define le32_to_cpu(x) \
+	({ u32 __r = __cpu_is_be() ? __bswap32(x) : ((u32)x); __r; })
+#define cpu_to_le32 le32_to_cpu
+
+#define le64_to_cpu(x) \
+	({ u64 __r = __cpu_is_be() ? __bswap64(x) : ((u64)x); __r; })
+#define cpu_to_le64 le64_to_cpu
+
+#define be16_to_cpu(x) \
+	({ u16 __r = !__cpu_is_be() ? __bswap16(x) : ((u16)x); __r; })
+#define cpu_to_be16 be16_to_cpu
+
+#define be32_to_cpu(x) \
+	({ u32 __r = !__cpu_is_be() ? __bswap32(x) : ((u32)x); __r; })
+#define cpu_to_be32 be32_to_cpu
+
+#define be64_to_cpu(x) \
+	({ u64 __r = !__cpu_is_be() ? __bswap64(x) : ((u64)x); __r; })
+#define cpu_to_be64 be64_to_cpu
+
+#define readb(addr) \
+	({ u8 __r = __raw_readb(addr); rmb(); __r; })
+#define readw(addr) \
+	({ u16 __r = le16_to_cpu(__raw_readw(addr)); rmb(); __r; })
+#define readl(addr) \
+	({ u32 __r = le32_to_cpu(__raw_readl(addr)); rmb(); __r; })
+#define readq(addr) \
+	({ u64 __r = le64_to_cpu(__raw_readq(addr)); rmb(); __r; })
+
+#define writeb(b, addr) \
+	({ wmb(); __raw_writeb(b, addr); })
+#define writew(b, addr) \
+	({ wmb(); __raw_writew(cpu_to_le16(b), addr); })
+#define writel(b, addr) \
+	({ wmb(); __raw_writel(cpu_to_le32(b), addr); })
+#define writeq(b, addr) \
+	({ wmb(); __raw_writeq(cpu_to_le64(b), addr); })
+
+#ifndef inb
+static inline uint8_t inb(unsigned long port)
+{
+	return readb((const volatile void __iomem *)port);
+}
+#endif
+
+#ifndef inw
+static inline uint16_t inw(unsigned long port)
+{
+	return readw((const volatile void __iomem *)port);
+}
+#endif
+
+#ifndef inl
+static inline uint32_t inl(unsigned long port)
+{
+	return readl((const volatile void __iomem *)port);
+}
+#endif
+
+#ifndef outb
+static inline void outb(uint8_t value, unsigned long port)
+{
+	writeb(value, (volatile void __iomem *)port);
+}
+#endif
+
+#ifndef outw
+static inline void outw(uint16_t value, unsigned long port)
+{
+	writew(value, (volatile void __iomem *)port);
+}
+#endif
+
+#ifndef outl
+static inline void outl(uint32_t value, unsigned long port)
+{
+	writel(value, (volatile void __iomem *)port);
+}
+#endif
+
+#ifndef ioremap
+static inline void __iomem *ioremap(phys_addr_t phys_addr, size_t size __unused)
+{
+	assert(sizeof(long) == 8 || !(phys_addr >> 32));
+	return (void __iomem *)(unsigned long)phys_addr;
+}
+#endif
+
+#ifndef virt_to_phys
+static inline unsigned long virt_to_phys(volatile void *address)
+{
+	return __pa((unsigned long)address);
+}
+#endif
+
+#ifndef phys_to_virt
+static inline void *phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+#endif
+
+#endif /* _ASM_GENERIC_IO_H_ */

tests/kvm-unit-tests/lib/asm-generic/page.h

@@ -0,0 +1,29 @@
+#ifndef _ASM_GENERIC_PAGE_H_
+#define _ASM_GENERIC_PAGE_H_
+/*
+ * asm-generic/page.h
+ *  adapted from the Linux kernel's include/asm-generic/page.h
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+#include <linux/const.h>
+
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_ALIGN(addr)	ALIGN(addr, PAGE_SIZE)
+
+#define __va(x)			((void *)((unsigned long) (x)))
+#define __pa(x)			((unsigned long) (x))
+#define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_GENERIC_PAGE_H_ */

tests/kvm-unit-tests/lib/asm-generic/pci-host-bridge.h

@@ -0,0 +1,28 @@
+#ifndef _ASM_PCI_HOST_BRIDGE_H_
+#define _ASM_PCI_HOST_BRIDGE_H_
+/*
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+phys_addr_t pci_host_bridge_get_paddr(uint64_t addr);
+
+static inline
+phys_addr_t pci_translate_addr(pcidevaddr_t dev __unused, uint64_t addr)
+{
+	/*
+	 * Assume we only have single PCI host bridge in a system.
+	 */
+	return pci_host_bridge_get_paddr(addr);
+}
+
+uint8_t pci_config_readb(pcidevaddr_t dev, uint8_t reg);
+uint16_t pci_config_readw(pcidevaddr_t dev, uint8_t reg);
+uint32_t pci_config_readl(pcidevaddr_t dev, uint8_t reg);
+void pci_config_writeb(pcidevaddr_t dev, uint8_t reg, uint8_t val);
+void pci_config_writew(pcidevaddr_t dev, uint8_t reg, uint16_t val);
+void pci_config_writel(pcidevaddr_t dev, uint8_t reg, uint32_t val);
+
+#endif

tests/kvm-unit-tests/lib/asm-generic/pci.h

@@ -0,0 +1,4 @@
+#ifndef _ASM_GENERIC_PCI_H_
+#define _ASM_GENERIC_PCI_H_
+#error need architecture specific asm/pci.h
+#endif

tests/kvm-unit-tests/lib/asm-generic/spinlock.h

@@ -0,0 +1,4 @@
+#ifndef _ASM_GENERIC_SPINLOCK_H_
+#define _ASM_GENERIC_SPINLOCK_H_
+#error need architecture specific asm/spinlock.h
+#endif

tests/kvm-unit-tests/lib/auxinfo.c

@@ -0,0 +1,2 @@
+#include "auxinfo.h"
+struct auxinfo auxinfo = { PROGNAME };

tests/kvm-unit-tests/lib/auxinfo.h

@@ -0,0 +1,9 @@
+#ifndef _AUXINFO_H_
+#define _AUXINFO_H_
+struct auxinfo {
+	const char *progname;
+};
+
+/* No extern!  Define a common symbol.  */
+struct auxinfo auxinfo;
+#endif

tests/kvm-unit-tests/lib/bitops.h

@@ -0,0 +1,36 @@
+#ifndef _BITOPS_H_
+#define _BITOPS_H_
+
+/*
+ * Adapated from
+ *   include/linux/bitops.h
+ *
+ * Copyright (C) 2015, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+#define BITS_PER_LONG_LONG	64
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+#include <asm/bitops.h>
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif

tests/kvm-unit-tests/lib/chr-testdev.c

@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "virtio.h"
+#include "asm/spinlock.h"
+
+#define TESTDEV_NAME "chr-testdev"
+
+static struct virtio_device *vcon;
+static struct virtqueue *in_vq, *out_vq;
+static struct spinlock lock;
+
+static void __testdev_send(char *buf, unsigned int len)
+{
+	int ret;
+
+	ret = virtqueue_add_outbuf(out_vq, buf, len);
+	virtqueue_kick(out_vq);
+
+	if (ret < 0)
+		return;
+
+	while (!virtqueue_get_buf(out_vq, &len))
+		;
+}
+
+void chr_testdev_exit(int code)
+{
+	unsigned int len;
+	char buf[8];
+
+	snprintf(buf, sizeof(buf), "%dq", code);
+	len = strlen(buf);
+
+	spin_lock(&lock);
+
+	if (!vcon)
+		goto out;
+
+	__testdev_send(buf, len);
+
+out:
+	spin_unlock(&lock);
+}
+
+void chr_testdev_init(void)
+{
+	const char *io_names[] = { "input", "output" };
+	struct virtqueue *vqs[2];
+	int ret;
+
+	vcon = virtio_bind(VIRTIO_ID_CONSOLE);
+	if (vcon == NULL) {
+		printf("%s: %s: can't find a virtio-console\n",
+				__func__, TESTDEV_NAME);
+		return;
+	}
+
+	ret = vcon->config->find_vqs(vcon, 2, vqs, NULL, io_names);
+	if (ret < 0) {
+		printf("%s: %s: can't init virtqueues\n",
+				__func__, TESTDEV_NAME);
+		vcon = NULL;
+		return;
+	}
+
+	in_vq = vqs[0];
+	out_vq = vqs[1];
+}

tests/kvm-unit-tests/lib/chr-testdev.h

@@ -0,0 +1,14 @@
+#ifndef _CHR_TESTDEV_H_
+#define _CHR_TESTDEV_H_
+/*
+ * chr-testdev is a driver for the chr-testdev qemu backend.
+ * The chr-testdev backend exposes a simple control interface to
+ * qemu for kvm-unit-tests accessible through virtio-console.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+extern void chr_testdev_init(void);
+extern void chr_testdev_exit(int code);
+#endif

tests/kvm-unit-tests/lib/devicetree.c

@@ -0,0 +1,334 @@
+/*
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "libfdt/libfdt.h"
+#include "devicetree.h"
+
+static const void *fdt;
+
+const void *dt_fdt(void)
+{
+	return fdt;
+}
+
+bool dt_available(void)
+{
+	return fdt_check_header(fdt) == 0;
+}
+
+int dt_get_nr_cells(int fdtnode, u32 *nr_address_cells, u32 *nr_size_cells)
+{
+	const struct fdt_property *prop;
+	u32 *nr_cells;
+	int len, nac, nsc;
+
+	prop = fdt_get_property(fdt, fdtnode, "#address-cells", &len);
+	if (prop == NULL)
+		return len;
+
+	nr_cells = (u32 *)prop->data;
+	nac = fdt32_to_cpu(*nr_cells);
+
+	prop = fdt_get_property(fdt, fdtnode, "#size-cells", &len);
+	if (prop == NULL)
+		return len;
+
+	nr_cells = (u32 *)prop->data;
+	nsc = fdt32_to_cpu(*nr_cells);
+
+	*nr_address_cells = nac;
+	*nr_size_cells = nsc;
+
+	return 0;
+}
+
+void dt_reg_init(struct dt_reg *reg, u32 nr_address_cells, u32 nr_size_cells)
+{
+	memset(reg, 0, sizeof(struct dt_reg));
+	reg->nr_address_cells = nr_address_cells;
+	reg->nr_size_cells = nr_size_cells;
+}
+
+int dt_get_reg(int fdtnode, int regidx, struct dt_reg *reg)
+{
+	const struct fdt_property *prop;
+	u32 *cells, i;
+	unsigned nr_tuple_cells;
+	int len;
+
+	prop = fdt_get_property(fdt, fdtnode, "reg", &len);
+	if (prop == NULL)
+		return len;
+
+	cells = (u32 *)prop->data;
+	nr_tuple_cells = reg->nr_address_cells + reg->nr_size_cells;
+	regidx *= nr_tuple_cells;
+
+	if (regidx + nr_tuple_cells > len/sizeof(u32))
+		return -FDT_ERR_NOTFOUND;
+
+	for (i = 0; i < reg->nr_address_cells; ++i)
+		reg->address_cells[i] = fdt32_to_cpu(cells[regidx + i]);
+
+	regidx += reg->nr_address_cells;
+	for (i = 0; i < reg->nr_size_cells; ++i)
+		reg->size_cells[i] = fdt32_to_cpu(cells[regidx + i]);
+
+	return 0;
+}
+
+int dt_pbus_translate_node(int fdtnode, int regidx,
+			   struct dt_pbus_reg *pbus_reg)
+{
+	struct dt_reg raw_reg;
+	u32 nac, nsc;
+	int parent, ret;
+
+	parent = fdt_parent_offset(fdt, fdtnode);
+	if (parent < 0)
+		return parent;
+
+	ret = dt_get_nr_cells(parent, &nac, &nsc);
+	if (ret != 0)
+		return ret;
+
+	dt_reg_init(&raw_reg, nac, nsc);
+
+	ret = dt_get_reg(fdtnode, regidx, &raw_reg);
+	if (ret < 0)
+		return ret;
+
+	pbus_reg->addr = dt_pbus_read_cells(raw_reg.nr_address_cells,
+					    raw_reg.address_cells);
+	pbus_reg->size = dt_pbus_read_cells(raw_reg.nr_size_cells,
+					    raw_reg.size_cells);
+
+	return 0;
+}
+
+int dt_pbus_translate(const struct dt_device *dev, int regidx,
+		      void *reg)
+{
+	return dt_pbus_translate_node(dev->fdtnode, regidx, reg);
+}
+
+int dt_bus_match_any(const struct dt_device *dev __unused, int fdtnode)
+{
+	/* matches any device with a valid node */
+	return fdtnode < 0 ? fdtnode : 1;
+}
+
+static const struct dt_bus dt_default_bus = {
+	.match = dt_bus_match_any,
+	.translate = dt_pbus_translate,
+};
+
+void dt_bus_init_defaults(struct dt_bus *bus)
+{
+	memcpy(bus, &dt_default_bus, sizeof(struct dt_bus));
+}
+
+void dt_device_init(struct dt_device *dev, const struct dt_bus *bus,
+		    void *info)
+{
+	memset(dev, 0, sizeof(struct dt_device));
+	dev->bus = bus;
+	dev->info = info;
+}
+
+int dt_device_find_compatible(const struct dt_device *dev,
+			      const char *compatible)
+{
+	int node, ret;
+
+	node = fdt_node_offset_by_compatible(fdt, -1, compatible);
+	while (node >= 0) {
+		ret = dev->bus->match(dev, node);
+		if (ret < 0)
+			return ret;
+		else if (ret)
+			break;
+		node = fdt_node_offset_by_compatible(fdt, node, compatible);
+	}
+	return node;
+}
+
+int dt_pbus_get_base_compatible(const char *compatible,
+				struct dt_pbus_reg *base)
+{
+	struct dt_device dev;
+	int node;
+
+	dt_device_init(&dev, &dt_default_bus, NULL);
+
+	node = dt_device_find_compatible(&dev, compatible);
+	if (node < 0)
+		return node;
+
+	dt_device_bind_node(&dev, node);
+
+	return dt_pbus_get_base(&dev, base);
+}
+
+int dt_get_memory_params(struct dt_pbus_reg *regs, int nr_regs)
+{
+	const char *pn = "device_type", *pv = "memory";
+	int node, ret, reg_idx, pl = strlen(pv) + 1, nr = 0;
+	struct dt_pbus_reg reg;
+
+	node = fdt_node_offset_by_prop_value(fdt, -1, pn, pv, pl);
+
+	while (node >= 0) {
+
+		reg_idx = 0;
+
+		while (nr < nr_regs) {
+			ret = dt_pbus_translate_node(node, reg_idx, &reg);
+			if (ret == -FDT_ERR_NOTFOUND)
+				break;
+			if (ret < 0)
+				return ret;
+			regs[nr].addr = reg.addr;
+			regs[nr].size = reg.size;
+			++nr, ++reg_idx;
+		}
+
+		node = fdt_node_offset_by_prop_value(fdt, node, pn, pv, pl);
+	}
+
+	return node != -FDT_ERR_NOTFOUND ? node : nr;
+}
+
+int dt_for_each_cpu_node(void (*func)(int fdtnode, u64 regval, void *info),
+			 void *info)
+{
+	const struct fdt_property *prop;
+	int cpus, cpu, ret, len;
+	struct dt_reg raw_reg;
+	u32 nac, nsc;
+	u64 regval;
+
+	cpus = fdt_path_offset(fdt, "/cpus");
+	if (cpus < 0)
+		return cpus;
+
+	ret = dt_get_nr_cells(cpus, &nac, &nsc);
+	if (ret < 0)
+		return ret;
+
+	dt_reg_init(&raw_reg, nac, nsc);
+
+	dt_for_each_subnode(cpus, cpu) {
+
+		prop = fdt_get_property(fdt, cpu, "device_type", &len);
+		if (prop == NULL)
+			return len;
+
+		if (len != 4 || strcmp((char *)prop->data, "cpu"))
+			continue;
+
+		ret = dt_get_reg(cpu, 0, &raw_reg);
+		if (ret < 0)
+			return ret;
+
+		regval = raw_reg.address_cells[0];
+		if (nac == 2)
+			regval = (regval << 32) | raw_reg.address_cells[1];
+
+		func(cpu, regval, info);
+	}
+
+	return 0;
+}
+
+int dt_get_bootargs(const char **bootargs)
+{
+	const struct fdt_property *prop;
+	int node, len;
+
+	*bootargs = NULL;
+
+	node = fdt_path_offset(fdt, "/chosen");
+	if (node < 0)
+		return node;
+
+	prop = fdt_get_property(fdt, node, "bootargs", &len);
+	if (!prop)
+		return len;
+
+	*bootargs = prop->data;
+	return 0;
+}
+
+int dt_get_default_console_node(void)
+{
+	const struct fdt_property *prop;
+	int node, len;
+
+	node = fdt_path_offset(fdt, "/chosen");
+	if (node < 0)
+		return node;
+
+	prop = fdt_get_property(fdt, node, "stdout-path", &len);
+	if (!prop) {
+		prop = fdt_get_property(fdt, node, "linux,stdout-path", &len);
+		if (!prop)
+			return len;
+	}
+
+	return fdt_path_offset(fdt, prop->data);
+}
+
+int dt_get_initrd(const char **initrd, u32 *size)
+{
+	const struct fdt_property *prop;
+	const char *start, *end;
+	int node, len;
+	u32 *data;
+
+	*initrd = NULL;
+	*size = 0;
+
+	node = fdt_path_offset(fdt, "/chosen");
+	if (node < 0)
+		return node;
+
+	prop = fdt_get_property(fdt, node, "linux,initrd-start", &len);
+	if (!prop)
+		return len;
+	data = (u32 *)prop->data;
+	start = (const char *)(unsigned long)fdt32_to_cpu(*data);
+
+	prop = fdt_get_property(fdt, node, "linux,initrd-end", &len);
+	if (!prop) {
+		assert(len != -FDT_ERR_NOTFOUND);
+		return len;
+	}
+	data = (u32 *)prop->data;
+	end = (const char *)(unsigned long)fdt32_to_cpu(*data);
+
+	*initrd = start;
+	*size = (unsigned long)end - (unsigned long)start;
+
+	return 0;
+}
+
+int dt_init(const void *fdt_ptr)
+{
+	int ret;
+
+	ret = fdt_check_header(fdt_ptr);
+	if (ret < 0)
+		return ret;
+
+	/* Sanity check the path.  */
+	ret = fdt_path_offset(fdt_ptr, "/");
+	if (ret < 0)
+		return ret;
+
+	fdt = fdt_ptr;
+	return 0;
+}

tests/kvm-unit-tests/lib/devicetree.h

@@ -0,0 +1,251 @@
+#ifndef _DEVICETREE_H_
+#define _DEVICETREE_H_
+/*
+ * devicetree builds on libfdt to implement abstractions and accessors
+ * for Linux required device tree content. The accessors provided are
+ * common across architectures. See section III of the kernel doc
+ * Documentation/devicetree/booting-without-of.txt
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "libfdt/libfdt.h"
+
+/**********************************************************************
+ * devicetree init and libfdt helpers
+ **********************************************************************/
+
+/* dt_init initializes devicetree with a pointer to an fdt, @fdt_ptr */
+extern int dt_init(const void *fdt_ptr);
+
+/* get the fdt pointer that devicetree is using */
+extern const void *dt_fdt(void);
+
+/* check for an initialized, valid devicetree */
+extern bool dt_available(void);
+
+/* traverse child nodes */
+#define dt_for_each_subnode(n, s)					\
+	for (s = fdt_first_subnode(dt_fdt(), n);			\
+	     s != -FDT_ERR_NOTFOUND;					\
+	     s = fdt_next_subnode(dt_fdt(), s))
+
+/**********************************************************************
+ * Abstractions for required node types and properties
+ **********************************************************************/
+
+struct dt_device {
+	int fdtnode;
+	const struct dt_bus *bus;
+
+	/*
+	 * info is a pointer to device specific data, which may be
+	 * used by the bus match() and translate() functions
+	 */
+	void *info;
+};
+
+struct dt_bus {
+	/*
+	 * match a device @dev to an fdt node @fdtnode
+	 * returns
+	 *  - a positive value on match
+	 *  - zero on no match
+	 *  - a negative FDT_ERR_* value on failure
+	 */
+	int (*match)(const struct dt_device *dev, int fdtnode);
+
+	/*
+	 * translate the @regidx'th "address size" tuple of
+	 * @dev's fdt node's "reg" property, and store the result
+	 * in @reg, a bus specific structure
+	 * returns
+	 *  - zero on success
+	 *  - a negative FDT_ERR_* value on failure
+	 */
+	int (*translate)(const struct dt_device *dev, int regidx, void *reg);
+};
+
+/* dt_bus_match_any matches any fdt node, i.e. it always returns true */
+extern int dt_bus_match_any(const struct dt_device *dev, int fdtnode);
+
+/* the processor bus (pbus) address type and register tuple */
+typedef u64 dt_pbus_addr_t;
+struct dt_pbus_reg {
+	dt_pbus_addr_t addr;
+	dt_pbus_addr_t size;
+};
+
+static inline dt_pbus_addr_t dt_pbus_read_cells(u32 nr_cells, u32 *cells)
+{
+	switch (nr_cells) {
+	case 1: return cells[0];
+	case 2: return ((u64)cells[0] << 32) | cells[1];
+	}
+	return (~0ULL);
+}
+
+/*
+ * dt_pbus_translate translates device node regs for the
+ * processor bus using the parent node's #address-cells
+ * and #size-cells and dt_pbus_read_cells()
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_pbus_translate(const struct dt_device *dev, int regidx,
+			     void *reg);
+
+/*
+ * dt_pbus_translate_node is the same as dt_pbus_translate but
+ * operates on an fdt node instead of a dt_device
+ */
+extern int dt_pbus_translate_node(int fdtnode, int regidx,
+				  struct dt_pbus_reg *reg);
+
+/*
+ * dt_pbus_get_base is an alias for
+ *     dt_pbus_translate(dev, 0, base)
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+static inline int dt_pbus_get_base(const struct dt_device *dev,
+				   struct dt_pbus_reg *base)
+{
+	return dt_pbus_translate(dev, 0, base);
+}
+
+/*
+ * dt_bus_init_defaults initializes @bus with
+ *  match		<- dt_bus_match_any
+ *  translate		<- dt_pbus_translate
+ */
+extern void dt_bus_init_defaults(struct dt_bus *bus);
+
+/*
+ * dt_device_init initializes a dt_device with the given parameters
+ */
+extern void dt_device_init(struct dt_device *dev, const struct dt_bus *bus,
+			   void *info);
+
+static inline void dt_device_bind_node(struct dt_device *dev, int fdtnode)
+{
+	dev->fdtnode = fdtnode;
+}
+
+/*
+ * dt_device_find_compatible finds a @compatible node
+ * returns
+ *  - node (>= 0) on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_device_find_compatible(const struct dt_device *dev,
+				     const char *compatible);
+
+/*
+ * dt_pbus_get_base_compatible simply bundles many functions into one.
+ * It finds the first @compatible fdt node, then translates the 0th reg
+ * tuple (the base) using the processor bus translation, and finally it
+ * stores that result in @base.
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_pbus_get_base_compatible(const char *compatible,
+				       struct dt_pbus_reg *base);
+
+/**********************************************************************
+ * Low-level accessors for required node types and properties
+ **********************************************************************/
+
+/*
+ * dt_get_nr_cells sets @nr_address_cells and @nr_size_cells to the
+ * #address-cells and #size-cells properties of @fdtnode
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_get_nr_cells(int fdtnode, u32 *nr_address_cells,
+					u32 *nr_size_cells);
+
+/* dt_reg is a structure for "raw" reg tuples */
+#define MAX_ADDRESS_CELLS	4
+#define MAX_SIZE_CELLS		4
+struct dt_reg {
+	u32 nr_address_cells, nr_size_cells;
+	u32 address_cells[MAX_ADDRESS_CELLS];
+	u32 size_cells[MAX_SIZE_CELLS];
+};
+
+/*
+ * dt_reg_init initialize a dt_reg struct to zero and sets
+ * nr_address_cells and nr_size_cells to @nr_address_cells and
+ * @nr_size_cells respectively.
+ */
+extern void dt_reg_init(struct dt_reg *reg, u32 nr_address_cells,
+					    u32 nr_size_cells);
+
+/*
+ * dt_get_reg gets the @regidx'th reg tuple of @fdtnode's reg property
+ * and stores it in @reg. @reg must be initialized.
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_get_reg(int fdtnode, int regidx, struct dt_reg *reg);
+
+/**********************************************************************
+ * High-level accessors for required node types and properties
+ **********************************************************************/
+
+/*
+ * dt_get_bootargs gets the string pointer from /chosen/bootargs
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure, and @bootargs
+ *    will be set to NULL
+ */
+extern int dt_get_bootargs(const char **bootargs);
+
+/*
+ * dt_get_default_console_node gets the node of the path stored in
+ * /chosen/stdout-path (or the deprecated /chosen/linux,stdout-path)
+ * returns
+ *  - the node (>= 0) on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_get_default_console_node(void);
+
+/*
+ * dt_get_initrd gets the physical address of the initrd and its
+ * size from /chosen
+ * returns
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure, and @initrd will be
+ *    set to NULL and @size set to zero
+ */
+extern int dt_get_initrd(const char **initrd, u32 *size);
+
+/*
+ * dt_get_memory_params gets the memory parameters from the /memory node(s)
+ * storing each memory region ("address size" tuple) in consecutive entries
+ * of @regs, up to @nr_regs
+ * returns
+ *  - number of memory regions found on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_get_memory_params(struct dt_pbus_reg *regs, int nr_regs);
+
+/*
+ * dt_for_each_cpu_node runs @func on each cpu node in the /cpus node
+ * passing it its fdt node, its reg property value, and @info
+ *  - zero on success
+ *  - a negative FDT_ERR_* value on failure
+ */
+extern int dt_for_each_cpu_node(void (*func)(int fdtnode, u64 regval,
+				void *info), void *info);
+
+#endif /* _DEVICETREE_H_ */

tests/kvm-unit-tests/lib/errata.h

@@ -0,0 +1,24 @@
+#ifndef _ERRATA_H_
+#define _ERRATA_H_
+
+#define _ERRATA(erratum) errata("ERRATA_" # erratum)
+#define ERRATA(erratum) _ERRATA(erratum)
+
+#define _ERRATA_RELAXED(erratum) errata_relaxed("ERRATA_" # erratum)
+#define ERRATA_RELAXED(erratum) _ERRATA_RELAXED(erratum)
+
+static inline bool errata(const char *erratum)
+{
+	char *s = getenv(erratum);
+
+	return s && (*s == '1' || *s == 'y' || *s == 'Y');
+}
+
+static inline bool errata_relaxed(const char *erratum)
+{
+	char *s = getenv(erratum);
+
+	return !(s && (*s == '0' || *s == 'n' || *s == 'N'));
+}
+
+#endif

tests/kvm-unit-tests/lib/kbuild.h

@@ -0,0 +1,8 @@
+#ifndef _KBUILD_H_
+#define _KBUILD_H_
+#define DEFINE(sym, val) \
+	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+#define OFFSET(sym, str, mem)	DEFINE(sym, offsetof(struct str, mem))
+#define COMMENT(x)		asm volatile("\n->#" x)
+#define BLANK()			asm volatile("\n->" : : )
+#endif

tests/kvm-unit-tests/lib/libcflat.h

@@ -0,0 +1,132 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __LIBCFLAT_H
+#define __LIBCFLAT_H
+
+#include <stdarg.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#define __unused __attribute__((__unused__))
+
+#define xstr(s...) xxstr(s)
+#define xxstr(s...) #s
+
+#define __ALIGN_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+#define __ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a) - 1)
+#define ALIGN(x, a)		__ALIGN((x), (a))
+#define IS_ALIGNED(x, a)	(((x) & ((typeof(x))(a) - 1)) == 0)
+
+#define SZ_4K			(1 << 12)
+#define SZ_64K			(1 << 16)
+#define SZ_2M			(1 << 21)
+#define SZ_1G			(1 << 30)
+
+#define MIN(a, b)		((a) < (b) ? (a) : (b))
+#define MAX(a, b)		((a) > (b) ? (a) : (b))
+
+typedef uint8_t		u8;
+typedef int8_t		s8;
+typedef uint16_t	u16;
+typedef int16_t		s16;
+typedef uint32_t	u32;
+typedef int32_t		s32;
+typedef uint64_t	u64;
+typedef int64_t		s64;
+typedef unsigned long	ulong;
+
+typedef _Bool		bool;
+#define false 0
+#define true  1
+
+#if __SIZEOF_LONG__ == 8
+#  define __PRI32_PREFIX
+#  define __PRI64_PREFIX	"l"
+#  define __PRIPTR_PREFIX	"l"
+#else
+#if defined(__U32_LONG_FMT__)
+#  define __PRI32_PREFIX        "l"
+#else
+#  define __PRI32_PREFIX
+#endif
+#  define __PRI64_PREFIX	"ll"
+#  define __PRIPTR_PREFIX
+#endif
+#define PRId32  __PRI32_PREFIX	"d"
+#define PRIu32  __PRI32_PREFIX	"u"
+#define PRIx32  __PRI32_PREFIX	"x"
+#define PRId64  __PRI64_PREFIX	"d"
+#define PRIu64  __PRI64_PREFIX	"u"
+#define PRIx64  __PRI64_PREFIX	"x"
+#define PRIxPTR __PRIPTR_PREFIX	"x"
+
+typedef u64			phys_addr_t;
+#define INVALID_PHYS_ADDR	(~(phys_addr_t)0)
+
+extern void puts(const char *s);
+extern void exit(int code);
+extern void abort(void);
+extern long atol(const char *ptr);
+extern char *getenv(const char *name);
+
+extern int printf(const char *fmt, ...)
+					__attribute__((format(printf, 1, 2)));
+extern int snprintf(char *buf, int size, const char *fmt, ...)
+					__attribute__((format(printf, 3, 4)));
+extern int vsnprintf(char *buf, int size, const char *fmt, va_list va)
+					__attribute__((format(printf, 3, 0)));
+extern int vprintf(const char *fmt, va_list va)
+					__attribute__((format(printf, 1, 0)));
+
+extern void report_prefix_push(const char *prefix);
+extern void report_prefix_pop(void);
+extern void report(const char *msg_fmt, bool pass, ...);
+extern void report_xfail(const char *msg_fmt, bool xfail, bool pass, ...);
+extern void report_abort(const char *msg_fmt, ...);
+extern void report_skip(const char *msg_fmt, ...);
+extern void report_info(const char *msg_fmt, ...);
+extern int report_summary(void);
+
+extern void dump_stack(void);
+extern void dump_frame_stack(const void *instruction, const void *frame);
+
+#define ARRAY_SIZE(_a) (sizeof(_a)/sizeof((_a)[0]))
+
+#define container_of(ptr, type, member) ({				\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);		\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+
+#define assert(cond)							\
+do {									\
+	if (!(cond)) {							\
+		printf("%s:%d: assert failed: %s\n",			\
+		       __FILE__, __LINE__, #cond);			\
+		dump_stack();						\
+		abort();						\
+	}								\
+} while (0)
+
+static inline bool is_power_of_2(unsigned long n)
+{
+	return n && !(n & (n - 1));
+}
+
+#endif

tests/kvm-unit-tests/lib/libfdt/Makefile.libfdt

@@ -0,0 +1,10 @@
+# Makefile.libfdt
+#
+# This is not a complete Makefile of itself.  Instead, it is designed to
+# be easily embeddable into other systems of Makefiles.
+#
+LIBFDT_soname = libfdt.$(SHAREDLIB_EXT).1
+LIBFDT_INCLUDES = fdt.h libfdt.h libfdt_env.h
+LIBFDT_VERSION = version.lds
+LIBFDT_SRCS = fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c fdt_empty_tree.c
+LIBFDT_OBJS = $(LIBFDT_SRCS:%.c=%.o)

tests/kvm-unit-tests/lib/libfdt/README

@@ -0,0 +1,4 @@
+
+The code in this directory is originally imported from the libfdt
+directory of git://git.jdl.com/software/dtc.git - version 1.4.0.
+

tests/kvm-unit-tests/lib/libfdt/fdt.c

@@ -0,0 +1,250 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+int fdt_check_header(const void *fdt)
+{
+	if (fdt_magic(fdt) == FDT_MAGIC) {
+		/* Complete tree */
+		if (fdt_version(fdt) < FDT_FIRST_SUPPORTED_VERSION)
+			return -FDT_ERR_BADVERSION;
+		if (fdt_last_comp_version(fdt) > FDT_LAST_SUPPORTED_VERSION)
+			return -FDT_ERR_BADVERSION;
+	} else if (fdt_magic(fdt) == FDT_SW_MAGIC) {
+		/* Unfinished sequential-write blob */
+		if (fdt_size_dt_struct(fdt) == 0)
+			return -FDT_ERR_BADSTATE;
+	} else {
+		return -FDT_ERR_BADMAGIC;
+	}
+
+	return 0;
+}
+
+const void *fdt_offset_ptr(const void *fdt, int offset, unsigned int len)
+{
+	const char *p;
+
+	if (fdt_version(fdt) >= 0x11)
+		if (((offset + len) < offset)
+		    || ((offset + len) > fdt_size_dt_struct(fdt)))
+			return NULL;
+
+	p = _fdt_offset_ptr(fdt, offset);
+
+	if (p + len < p)
+		return NULL;
+	return p;
+}
+
+uint32_t fdt_next_tag(const void *fdt, int startoffset, int *nextoffset)
+{
+	const fdt32_t *tagp, *lenp;
+	uint32_t tag;
+	int offset = startoffset;
+	const char *p;
+
+	*nextoffset = -FDT_ERR_TRUNCATED;
+	tagp = fdt_offset_ptr(fdt, offset, FDT_TAGSIZE);
+	if (!tagp)
+		return FDT_END; /* premature end */
+	tag = fdt32_to_cpu(*tagp);
+	offset += FDT_TAGSIZE;
+
+	*nextoffset = -FDT_ERR_BADSTRUCTURE;
+	switch (tag) {
+	case FDT_BEGIN_NODE:
+		/* skip name */
+		do {
+			p = fdt_offset_ptr(fdt, offset++, 1);
+		} while (p && (*p != '\0'));
+		if (!p)
+			return FDT_END; /* premature end */
+		break;
+
+	case FDT_PROP:
+		lenp = fdt_offset_ptr(fdt, offset, sizeof(*lenp));
+		if (!lenp)
+			return FDT_END; /* premature end */
+		/* skip-name offset, length and value */
+		offset += sizeof(struct fdt_property) - FDT_TAGSIZE
+			+ fdt32_to_cpu(*lenp);
+		break;
+
+	case FDT_END:
+	case FDT_END_NODE:
+	case FDT_NOP:
+		break;
+
+	default:
+		return FDT_END;
+	}
+
+	if (!fdt_offset_ptr(fdt, startoffset, offset - startoffset))
+		return FDT_END; /* premature end */
+
+	*nextoffset = FDT_TAGALIGN(offset);
+	return tag;
+}
+
+int _fdt_check_node_offset(const void *fdt, int offset)
+{
+	if ((offset < 0) || (offset % FDT_TAGSIZE)
+	    || (fdt_next_tag(fdt, offset, &offset) != FDT_BEGIN_NODE))
+		return -FDT_ERR_BADOFFSET;
+
+	return offset;
+}
+
+int _fdt_check_prop_offset(const void *fdt, int offset)
+{
+	if ((offset < 0) || (offset % FDT_TAGSIZE)
+	    || (fdt_next_tag(fdt, offset, &offset) != FDT_PROP))
+		return -FDT_ERR_BADOFFSET;
+
+	return offset;
+}
+
+int fdt_next_node(const void *fdt, int offset, int *depth)
+{
+	int nextoffset = 0;
+	uint32_t tag;
+
+	if (offset >= 0)
+		if ((nextoffset = _fdt_check_node_offset(fdt, offset)) < 0)
+			return nextoffset;
+
+	do {
+		offset = nextoffset;
+		tag = fdt_next_tag(fdt, offset, &nextoffset);
+
+		switch (tag) {
+		case FDT_PROP:
+		case FDT_NOP:
+			break;
+
+		case FDT_BEGIN_NODE:
+			if (depth)
+				(*depth)++;
+			break;
+
+		case FDT_END_NODE:
+			if (depth && ((--(*depth)) < 0))
+				return nextoffset;
+			break;
+
+		case FDT_END:
+			if ((nextoffset >= 0)
+			    || ((nextoffset == -FDT_ERR_TRUNCATED) && !depth))
+				return -FDT_ERR_NOTFOUND;
+			else
+				return nextoffset;
+		}
+	} while (tag != FDT_BEGIN_NODE);
+
+	return offset;
+}
+
+int fdt_first_subnode(const void *fdt, int offset)
+{
+	int depth = 0;
+
+	offset = fdt_next_node(fdt, offset, &depth);
+	if (offset < 0 || depth != 1)
+		return -FDT_ERR_NOTFOUND;
+
+	return offset;
+}
+
+int fdt_next_subnode(const void *fdt, int offset)
+{
+	int depth = 1;
+
+	/*
+	 * With respect to the parent, the depth of the next subnode will be
+	 * the same as the last.
+	 */
+	do {
+		offset = fdt_next_node(fdt, offset, &depth);
+		if (offset < 0 || depth < 1)
+			return -FDT_ERR_NOTFOUND;
+	} while (depth > 1);
+
+	return offset;
+}
+
+const char *_fdt_find_string(const char *strtab, int tabsize, const char *s)
+{
+	int len = strlen(s) + 1;
+	const char *last = strtab + tabsize - len;
+	const char *p;
+
+	for (p = strtab; p <= last; p++)
+		if (memcmp(p, s, len) == 0)
+			return p;
+	return NULL;
+}
+
+int fdt_move(const void *fdt, void *buf, int bufsize)
+{
+	FDT_CHECK_HEADER(fdt);
+
+	if (fdt_totalsize(fdt) > bufsize)
+		return -FDT_ERR_NOSPACE;
+
+	memmove(buf, fdt, fdt_totalsize(fdt));
+	return 0;
+}

tests/kvm-unit-tests/lib/libfdt/fdt.h

@@ -0,0 +1,111 @@
+#ifndef _FDT_H
+#define _FDT_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ * Copyright 2012 Kim Phillips, Freescale Semiconductor.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __ASSEMBLY__
+
+struct fdt_header {
+	fdt32_t magic;			 /* magic word FDT_MAGIC */
+	fdt32_t totalsize;		 /* total size of DT block */
+	fdt32_t off_dt_struct;		 /* offset to structure */
+	fdt32_t off_dt_strings;		 /* offset to strings */
+	fdt32_t off_mem_rsvmap;		 /* offset to memory reserve map */
+	fdt32_t version;		 /* format version */
+	fdt32_t last_comp_version;	 /* last compatible version */
+
+	/* version 2 fields below */
+	fdt32_t boot_cpuid_phys;	 /* Which physical CPU id we're
+					    booting on */
+	/* version 3 fields below */
+	fdt32_t size_dt_strings;	 /* size of the strings block */
+
+	/* version 17 fields below */
+	fdt32_t size_dt_struct;		 /* size of the structure block */
+};
+
+struct fdt_reserve_entry {
+	fdt64_t address;
+	fdt64_t size;
+};
+
+struct fdt_node_header {
+	fdt32_t tag;
+	char name[0];
+};
+
+struct fdt_property {
+	fdt32_t tag;
+	fdt32_t len;
+	fdt32_t nameoff;
+	char data[0];
+};
+
+#endif /* !__ASSEMBLY */
+
+#define FDT_MAGIC	0xd00dfeed	/* 4: version, 4: total size */
+#define FDT_TAGSIZE	sizeof(fdt32_t)
+
+#define FDT_BEGIN_NODE	0x1		/* Start node: full name */
+#define FDT_END_NODE	0x2		/* End node */
+#define FDT_PROP	0x3		/* Property: name off,
+					   size, content */
+#define FDT_NOP		0x4		/* nop */
+#define FDT_END		0x9
+
+#define FDT_V1_SIZE	(7*sizeof(fdt32_t))
+#define FDT_V2_SIZE	(FDT_V1_SIZE + sizeof(fdt32_t))
+#define FDT_V3_SIZE	(FDT_V2_SIZE + sizeof(fdt32_t))
+#define FDT_V16_SIZE	FDT_V3_SIZE
+#define FDT_V17_SIZE	(FDT_V16_SIZE + sizeof(fdt32_t))
+
+#endif /* _FDT_H */

tests/kvm-unit-tests/lib/libfdt/fdt_empty_tree.c

@@ -0,0 +1,84 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2012 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+int fdt_create_empty_tree(void *buf, int bufsize)
+{
+	int err;
+
+	err = fdt_create(buf, bufsize);
+	if (err)
+		return err;
+
+	err = fdt_finish_reservemap(buf);
+	if (err)
+		return err;
+
+	err = fdt_begin_node(buf, "");
+	if (err)
+		return err;
+
+	err =  fdt_end_node(buf);
+	if (err)
+		return err;
+
+	err = fdt_finish(buf);
+	if (err)
+		return err;
+
+	return fdt_open_into(buf, buf, bufsize);
+}
+

tests/kvm-unit-tests/lib/libfdt/fdt_ro.c

@@ -0,0 +1,573 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+static int _fdt_nodename_eq(const void *fdt, int offset,
+			    const char *s, int len)
+{
+	const char *p = fdt_offset_ptr(fdt, offset + FDT_TAGSIZE, len+1);
+
+	if (! p)
+		/* short match */
+		return 0;
+
+	if (memcmp(p, s, len) != 0)
+		return 0;
+
+	if (p[len] == '\0')
+		return 1;
+	else if (!memchr(s, '@', len) && (p[len] == '@'))
+		return 1;
+	else
+		return 0;
+}
+
+const char *fdt_string(const void *fdt, int stroffset)
+{
+	return (const char *)fdt + fdt_off_dt_strings(fdt) + stroffset;
+}
+
+static int _fdt_string_eq(const void *fdt, int stroffset,
+			  const char *s, int len)
+{
+	const char *p = fdt_string(fdt, stroffset);
+
+	return (strlen(p) == len) && (memcmp(p, s, len) == 0);
+}
+
+int fdt_get_mem_rsv(const void *fdt, int n, uint64_t *address, uint64_t *size)
+{
+	FDT_CHECK_HEADER(fdt);
+	*address = fdt64_to_cpu(_fdt_mem_rsv(fdt, n)->address);
+	*size = fdt64_to_cpu(_fdt_mem_rsv(fdt, n)->size);
+	return 0;
+}
+
+int fdt_num_mem_rsv(const void *fdt)
+{
+	int i = 0;
+
+	while (fdt64_to_cpu(_fdt_mem_rsv(fdt, i)->size) != 0)
+		i++;
+	return i;
+}
+
+static int _nextprop(const void *fdt, int offset)
+{
+	uint32_t tag;
+	int nextoffset;
+
+	do {
+		tag = fdt_next_tag(fdt, offset, &nextoffset);
+
+		switch (tag) {
+		case FDT_END:
+			if (nextoffset >= 0)
+				return -FDT_ERR_BADSTRUCTURE;
+			else
+				return nextoffset;
+
+		case FDT_PROP:
+			return offset;
+		}
+		offset = nextoffset;
+	} while (tag == FDT_NOP);
+
+	return -FDT_ERR_NOTFOUND;
+}
+
+int fdt_subnode_offset_namelen(const void *fdt, int offset,
+			       const char *name, int namelen)
+{
+	int depth;
+
+	FDT_CHECK_HEADER(fdt);
+
+	for (depth = 0;
+	     (offset >= 0) && (depth >= 0);
+	     offset = fdt_next_node(fdt, offset, &depth))
+		if ((depth == 1)
+		    && _fdt_nodename_eq(fdt, offset, name, namelen))
+			return offset;
+
+	if (depth < 0)
+		return -FDT_ERR_NOTFOUND;
+	return offset; /* error */
+}
+
+int fdt_subnode_offset(const void *fdt, int parentoffset,
+		       const char *name)
+{
+	return fdt_subnode_offset_namelen(fdt, parentoffset, name, strlen(name));
+}
+
+int fdt_path_offset(const void *fdt, const char *path)
+{
+	const char *end = path + strlen(path);
+	const char *p = path;
+	int offset = 0;
+
+	FDT_CHECK_HEADER(fdt);
+
+	/* see if we have an alias */
+	if (*path != '/') {
+		const char *q = strchr(path, '/');
+
+		if (!q)
+			q = end;
+
+		p = fdt_get_alias_namelen(fdt, p, q - p);
+		if (!p)
+			return -FDT_ERR_BADPATH;
+		offset = fdt_path_offset(fdt, p);
+
+		p = q;
+	}
+
+	while (*p) {
+		const char *q;
+
+		while (*p == '/')
+			p++;
+		if (! *p)
+			return offset;
+		q = strchr(p, '/');
+		if (! q)
+			q = end;
+
+		offset = fdt_subnode_offset_namelen(fdt, offset, p, q-p);
+		if (offset < 0)
+			return offset;
+
+		p = q;
+	}
+
+	return offset;
+}
+
+const char *fdt_get_name(const void *fdt, int nodeoffset, int *len)
+{
+	const struct fdt_node_header *nh = _fdt_offset_ptr(fdt, nodeoffset);
+	int err;
+
+	if (((err = fdt_check_header(fdt)) != 0)
+	    || ((err = _fdt_check_node_offset(fdt, nodeoffset)) < 0))
+			goto fail;
+
+	if (len)
+		*len = strlen(nh->name);
+
+	return nh->name;
+
+ fail:
+	if (len)
+		*len = err;
+	return NULL;
+}
+
+int fdt_first_property_offset(const void *fdt, int nodeoffset)
+{
+	int offset;
+
+	if ((offset = _fdt_check_node_offset(fdt, nodeoffset)) < 0)
+		return offset;
+
+	return _nextprop(fdt, offset);
+}
+
+int fdt_next_property_offset(const void *fdt, int offset)
+{
+	if ((offset = _fdt_check_prop_offset(fdt, offset)) < 0)
+		return offset;
+
+	return _nextprop(fdt, offset);
+}
+
+const struct fdt_property *fdt_get_property_by_offset(const void *fdt,
+						      int offset,
+						      int *lenp)
+{
+	int err;
+	const struct fdt_property *prop;
+
+	if ((err = _fdt_check_prop_offset(fdt, offset)) < 0) {
+		if (lenp)
+			*lenp = err;
+		return NULL;
+	}
+
+	prop = _fdt_offset_ptr(fdt, offset);
+
+	if (lenp)
+		*lenp = fdt32_to_cpu(prop->len);
+
+	return prop;
+}
+
+const struct fdt_property *fdt_get_property_namelen(const void *fdt,
+						    int offset,
+						    const char *name,
+						    int namelen, int *lenp)
+{
+	for (offset = fdt_first_property_offset(fdt, offset);
+	     (offset >= 0);
+	     (offset = fdt_next_property_offset(fdt, offset))) {
+		const struct fdt_property *prop;
+
+		if (!(prop = fdt_get_property_by_offset(fdt, offset, lenp))) {
+			offset = -FDT_ERR_INTERNAL;
+			break;
+		}
+		if (_fdt_string_eq(fdt, fdt32_to_cpu(prop->nameoff),
+				   name, namelen))
+			return prop;
+	}
+
+	if (lenp)
+		*lenp = offset;
+	return NULL;
+}
+
+const struct fdt_property *fdt_get_property(const void *fdt,
+					    int nodeoffset,
+					    const char *name, int *lenp)
+{
+	return fdt_get_property_namelen(fdt, nodeoffset, name,
+					strlen(name), lenp);
+}
+
+const void *fdt_getprop_namelen(const void *fdt, int nodeoffset,
+				const char *name, int namelen, int *lenp)
+{
+	const struct fdt_property *prop;
+
+	prop = fdt_get_property_namelen(fdt, nodeoffset, name, namelen, lenp);
+	if (! prop)
+		return NULL;
+
+	return prop->data;
+}
+
+const void *fdt_getprop_by_offset(const void *fdt, int offset,
+				  const char **namep, int *lenp)
+{
+	const struct fdt_property *prop;
+
+	prop = fdt_get_property_by_offset(fdt, offset, lenp);
+	if (!prop)
+		return NULL;
+	if (namep)
+		*namep = fdt_string(fdt, fdt32_to_cpu(prop->nameoff));
+	return prop->data;
+}
+
+const void *fdt_getprop(const void *fdt, int nodeoffset,
+			const char *name, int *lenp)
+{
+	return fdt_getprop_namelen(fdt, nodeoffset, name, strlen(name), lenp);
+}
+
+uint32_t fdt_get_phandle(const void *fdt, int nodeoffset)
+{
+	const fdt32_t *php;
+	int len;
+
+	/* FIXME: This is a bit sub-optimal, since we potentially scan
+	 * over all the properties twice. */
+	php = fdt_getprop(fdt, nodeoffset, "phandle", &len);
+	if (!php || (len != sizeof(*php))) {
+		php = fdt_getprop(fdt, nodeoffset, "linux,phandle", &len);
+		if (!php || (len != sizeof(*php)))
+			return 0;
+	}
+
+	return fdt32_to_cpu(*php);
+}
+
+const char *fdt_get_alias_namelen(const void *fdt,
+				  const char *name, int namelen)
+{
+	int aliasoffset;
+
+	aliasoffset = fdt_path_offset(fdt, "/aliases");
+	if (aliasoffset < 0)
+		return NULL;
+
+	return fdt_getprop_namelen(fdt, aliasoffset, name, namelen, NULL);
+}
+
+const char *fdt_get_alias(const void *fdt, const char *name)
+{
+	return fdt_get_alias_namelen(fdt, name, strlen(name));
+}
+
+int fdt_get_path(const void *fdt, int nodeoffset, char *buf, int buflen)
+{
+	int pdepth = 0, p = 0;
+	int offset, depth, namelen;
+	const char *name;
+
+	FDT_CHECK_HEADER(fdt);
+
+	if (buflen < 2)
+		return -FDT_ERR_NOSPACE;
+
+	for (offset = 0, depth = 0;
+	     (offset >= 0) && (offset <= nodeoffset);
+	     offset = fdt_next_node(fdt, offset, &depth)) {
+		while (pdepth > depth) {
+			do {
+				p--;
+			} while (buf[p-1] != '/');
+			pdepth--;
+		}
+
+		if (pdepth >= depth) {
+			name = fdt_get_name(fdt, offset, &namelen);
+			if (!name)
+				return namelen;
+			if ((p + namelen + 1) <= buflen) {
+				memcpy(buf + p, name, namelen);
+				p += namelen;
+				buf[p++] = '/';
+				pdepth++;
+			}
+		}
+
+		if (offset == nodeoffset) {
+			if (pdepth < (depth + 1))
+				return -FDT_ERR_NOSPACE;
+
+			if (p > 1) /* special case so that root path is "/", not "" */
+				p--;
+			buf[p] = '\0';
+			return 0;
+		}
+	}
+
+	if ((offset == -FDT_ERR_NOTFOUND) || (offset >= 0))
+		return -FDT_ERR_BADOFFSET;
+	else if (offset == -FDT_ERR_BADOFFSET)
+		return -FDT_ERR_BADSTRUCTURE;
+
+	return offset; /* error from fdt_next_node() */
+}
+
+int fdt_supernode_atdepth_offset(const void *fdt, int nodeoffset,
+				 int supernodedepth, int *nodedepth)
+{
+	int offset, depth;
+	int supernodeoffset = -FDT_ERR_INTERNAL;
+
+	FDT_CHECK_HEADER(fdt);
+
+	if (supernodedepth < 0)
+		return -FDT_ERR_NOTFOUND;
+
+	for (offset = 0, depth = 0;
+	     (offset >= 0) && (offset <= nodeoffset);
+	     offset = fdt_next_node(fdt, offset, &depth)) {
+		if (depth == supernodedepth)
+			supernodeoffset = offset;
+
+		if (offset == nodeoffset) {
+			if (nodedepth)
+				*nodedepth = depth;
+
+			if (supernodedepth > depth)
+				return -FDT_ERR_NOTFOUND;
+			else
+				return supernodeoffset;
+		}
+	}
+
+	if ((offset == -FDT_ERR_NOTFOUND) || (offset >= 0))
+		return -FDT_ERR_BADOFFSET;
+	else if (offset == -FDT_ERR_BADOFFSET)
+		return -FDT_ERR_BADSTRUCTURE;
+
+	return offset; /* error from fdt_next_node() */
+}
+
+int fdt_node_depth(const void *fdt, int nodeoffset)
+{
+	int nodedepth;
+	int err;
+
+	err = fdt_supernode_atdepth_offset(fdt, nodeoffset, 0, &nodedepth);
+	if (err)
+		return (err < 0) ? err : -FDT_ERR_INTERNAL;
+	return nodedepth;
+}
+
+int fdt_parent_offset(const void *fdt, int nodeoffset)
+{
+	int nodedepth = fdt_node_depth(fdt, nodeoffset);
+
+	if (nodedepth < 0)
+		return nodedepth;
+	return fdt_supernode_atdepth_offset(fdt, nodeoffset,
+					    nodedepth - 1, NULL);
+}
+
+int fdt_node_offset_by_prop_value(const void *fdt, int startoffset,
+				  const char *propname,
+				  const void *propval, int proplen)
+{
+	int offset;
+	const void *val;
+	int len;
+
+	FDT_CHECK_HEADER(fdt);
+
+	/* FIXME: The algorithm here is pretty horrible: we scan each
+	 * property of a node in fdt_getprop(), then if that didn't
+	 * find what we want, we scan over them again making our way
+	 * to the next node.  Still it's the easiest to implement
+	 * approach; performance can come later. */
+	for (offset = fdt_next_node(fdt, startoffset, NULL);
+	     offset >= 0;
+	     offset = fdt_next_node(fdt, offset, NULL)) {
+		val = fdt_getprop(fdt, offset, propname, &len);
+		if (val && (len == proplen)
+		    && (memcmp(val, propval, len) == 0))
+			return offset;
+	}
+
+	return offset; /* error from fdt_next_node() */
+}
+
+int fdt_node_offset_by_phandle(const void *fdt, uint32_t phandle)
+{
+	int offset;
+
+	if ((phandle == 0) || (phandle == -1))
+		return -FDT_ERR_BADPHANDLE;
+
+	FDT_CHECK_HEADER(fdt);
+
+	/* FIXME: The algorithm here is pretty horrible: we
+	 * potentially scan each property of a node in
+	 * fdt_get_phandle(), then if that didn't find what
+	 * we want, we scan over them again making our way to the next
+	 * node.  Still it's the easiest to implement approach;
+	 * performance can come later. */
+	for (offset = fdt_next_node(fdt, -1, NULL);
+	     offset >= 0;
+	     offset = fdt_next_node(fdt, offset, NULL)) {
+		if (fdt_get_phandle(fdt, offset) == phandle)
+			return offset;
+	}
+
+	return offset; /* error from fdt_next_node() */
+}
+
+int fdt_stringlist_contains(const char *strlist, int listlen, const char *str)
+{
+	int len = strlen(str);
+	const char *p;
+
+	while (listlen >= len) {
+		if (memcmp(str, strlist, len+1) == 0)
+			return 1;
+		p = memchr(strlist, '\0', listlen);
+		if (!p)
+			return 0; /* malformed strlist.. */
+		listlen -= (p-strlist) + 1;
+		strlist = p + 1;
+	}
+	return 0;
+}
+
+int fdt_node_check_compatible(const void *fdt, int nodeoffset,
+			      const char *compatible)
+{
+	const void *prop;
+	int len;
+
+	prop = fdt_getprop(fdt, nodeoffset, "compatible", &len);
+	if (!prop)
+		return len;
+	if (fdt_stringlist_contains(prop, len, compatible))
+		return 0;
+	else
+		return 1;
+}
+
+int fdt_node_offset_by_compatible(const void *fdt, int startoffset,
+				  const char *compatible)
+{
+	int offset, err;
+
+	FDT_CHECK_HEADER(fdt);
+
+	/* FIXME: The algorithm here is pretty horrible: we scan each
+	 * property of a node in fdt_node_check_compatible(), then if
+	 * that didn't find what we want, we scan over them again
+	 * making our way to the next node.  Still it's the easiest to
+	 * implement approach; performance can come later. */
+	for (offset = fdt_next_node(fdt, startoffset, NULL);
+	     offset >= 0;
+	     offset = fdt_next_node(fdt, offset, NULL)) {
+		err = fdt_node_check_compatible(fdt, offset, compatible);
+		if ((err < 0) && (err != -FDT_ERR_NOTFOUND))
+			return err;
+		else if (err == 0)
+			return offset;
+	}
+
+	return offset; /* error from fdt_next_node() */
+}

tests/kvm-unit-tests/lib/libfdt/fdt_rw.c

@@ -0,0 +1,492 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+static int _fdt_blocks_misordered(const void *fdt,
+			      int mem_rsv_size, int struct_size)
+{
+	return (fdt_off_mem_rsvmap(fdt) < FDT_ALIGN(sizeof(struct fdt_header), 8))
+		|| (fdt_off_dt_struct(fdt) <
+		    (fdt_off_mem_rsvmap(fdt) + mem_rsv_size))
+		|| (fdt_off_dt_strings(fdt) <
+		    (fdt_off_dt_struct(fdt) + struct_size))
+		|| (fdt_totalsize(fdt) <
+		    (fdt_off_dt_strings(fdt) + fdt_size_dt_strings(fdt)));
+}
+
+static int _fdt_rw_check_header(void *fdt)
+{
+	FDT_CHECK_HEADER(fdt);
+
+	if (fdt_version(fdt) < 17)
+		return -FDT_ERR_BADVERSION;
+	if (_fdt_blocks_misordered(fdt, sizeof(struct fdt_reserve_entry),
+				   fdt_size_dt_struct(fdt)))
+		return -FDT_ERR_BADLAYOUT;
+	if (fdt_version(fdt) > 17)
+		fdt_set_version(fdt, 17);
+
+	return 0;
+}
+
+#define FDT_RW_CHECK_HEADER(fdt) \
+	{ \
+		int err; \
+		if ((err = _fdt_rw_check_header(fdt)) != 0) \
+			return err; \
+	}
+
+static inline int _fdt_data_size(void *fdt)
+{
+	return fdt_off_dt_strings(fdt) + fdt_size_dt_strings(fdt);
+}
+
+static int _fdt_splice(void *fdt, void *splicepoint, int oldlen, int newlen)
+{
+	char *p = splicepoint;
+	char *end = (char *)fdt + _fdt_data_size(fdt);
+
+	if (((p + oldlen) < p) || ((p + oldlen) > end))
+		return -FDT_ERR_BADOFFSET;
+	if ((end - oldlen + newlen) > ((char *)fdt + fdt_totalsize(fdt)))
+		return -FDT_ERR_NOSPACE;
+	memmove(p + newlen, p + oldlen, end - p - oldlen);
+	return 0;
+}
+
+static int _fdt_splice_mem_rsv(void *fdt, struct fdt_reserve_entry *p,
+			       int oldn, int newn)
+{
+	int delta = (newn - oldn) * sizeof(*p);
+	int err;
+	err = _fdt_splice(fdt, p, oldn * sizeof(*p), newn * sizeof(*p));
+	if (err)
+		return err;
+	fdt_set_off_dt_struct(fdt, fdt_off_dt_struct(fdt) + delta);
+	fdt_set_off_dt_strings(fdt, fdt_off_dt_strings(fdt) + delta);
+	return 0;
+}
+
+static int _fdt_splice_struct(void *fdt, void *p,
+			      int oldlen, int newlen)
+{
+	int delta = newlen - oldlen;
+	int err;
+
+	if ((err = _fdt_splice(fdt, p, oldlen, newlen)))
+		return err;
+
+	fdt_set_size_dt_struct(fdt, fdt_size_dt_struct(fdt) + delta);
+	fdt_set_off_dt_strings(fdt, fdt_off_dt_strings(fdt) + delta);
+	return 0;
+}
+
+static int _fdt_splice_string(void *fdt, int newlen)
+{
+	void *p = (char *)fdt
+		+ fdt_off_dt_strings(fdt) + fdt_size_dt_strings(fdt);
+	int err;
+
+	if ((err = _fdt_splice(fdt, p, 0, newlen)))
+		return err;
+
+	fdt_set_size_dt_strings(fdt, fdt_size_dt_strings(fdt) + newlen);
+	return 0;
+}
+
+static int _fdt_find_add_string(void *fdt, const char *s)
+{
+	char *strtab = (char *)fdt + fdt_off_dt_strings(fdt);
+	const char *p;
+	char *new;
+	int len = strlen(s) + 1;
+	int err;
+
+	p = _fdt_find_string(strtab, fdt_size_dt_strings(fdt), s);
+	if (p)
+		/* found it */
+		return (p - strtab);
+
+	new = strtab + fdt_size_dt_strings(fdt);
+	err = _fdt_splice_string(fdt, len);
+	if (err)
+		return err;
+
+	memcpy(new, s, len);
+	return (new - strtab);
+}
+
+int fdt_add_mem_rsv(void *fdt, uint64_t address, uint64_t size)
+{
+	struct fdt_reserve_entry *re;
+	int err;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	re = _fdt_mem_rsv_w(fdt, fdt_num_mem_rsv(fdt));
+	err = _fdt_splice_mem_rsv(fdt, re, 0, 1);
+	if (err)
+		return err;
+
+	re->address = cpu_to_fdt64(address);
+	re->size = cpu_to_fdt64(size);
+	return 0;
+}
+
+int fdt_del_mem_rsv(void *fdt, int n)
+{
+	struct fdt_reserve_entry *re = _fdt_mem_rsv_w(fdt, n);
+	int err;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	if (n >= fdt_num_mem_rsv(fdt))
+		return -FDT_ERR_NOTFOUND;
+
+	err = _fdt_splice_mem_rsv(fdt, re, 1, 0);
+	if (err)
+		return err;
+	return 0;
+}
+
+static int _fdt_resize_property(void *fdt, int nodeoffset, const char *name,
+				int len, struct fdt_property **prop)
+{
+	int oldlen;
+	int err;
+
+	*prop = fdt_get_property_w(fdt, nodeoffset, name, &oldlen);
+	if (! (*prop))
+		return oldlen;
+
+	if ((err = _fdt_splice_struct(fdt, (*prop)->data, FDT_TAGALIGN(oldlen),
+				      FDT_TAGALIGN(len))))
+		return err;
+
+	(*prop)->len = cpu_to_fdt32(len);
+	return 0;
+}
+
+static int _fdt_add_property(void *fdt, int nodeoffset, const char *name,
+			     int len, struct fdt_property **prop)
+{
+	int proplen;
+	int nextoffset;
+	int namestroff;
+	int err;
+
+	if ((nextoffset = _fdt_check_node_offset(fdt, nodeoffset)) < 0)
+		return nextoffset;
+
+	namestroff = _fdt_find_add_string(fdt, name);
+	if (namestroff < 0)
+		return namestroff;
+
+	*prop = _fdt_offset_ptr_w(fdt, nextoffset);
+	proplen = sizeof(**prop) + FDT_TAGALIGN(len);
+
+	err = _fdt_splice_struct(fdt, *prop, 0, proplen);
+	if (err)
+		return err;
+
+	(*prop)->tag = cpu_to_fdt32(FDT_PROP);
+	(*prop)->nameoff = cpu_to_fdt32(namestroff);
+	(*prop)->len = cpu_to_fdt32(len);
+	return 0;
+}
+
+int fdt_set_name(void *fdt, int nodeoffset, const char *name)
+{
+	char *namep;
+	int oldlen, newlen;
+	int err;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	namep = (char *)(uintptr_t)fdt_get_name(fdt, nodeoffset, &oldlen);
+	if (!namep)
+		return oldlen;
+
+	newlen = strlen(name);
+
+	err = _fdt_splice_struct(fdt, namep, FDT_TAGALIGN(oldlen+1),
+				 FDT_TAGALIGN(newlen+1));
+	if (err)
+		return err;
+
+	memcpy(namep, name, newlen+1);
+	return 0;
+}
+
+int fdt_setprop(void *fdt, int nodeoffset, const char *name,
+		const void *val, int len)
+{
+	struct fdt_property *prop;
+	int err;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	err = _fdt_resize_property(fdt, nodeoffset, name, len, &prop);
+	if (err == -FDT_ERR_NOTFOUND)
+		err = _fdt_add_property(fdt, nodeoffset, name, len, &prop);
+	if (err)
+		return err;
+
+	memcpy(prop->data, val, len);
+	return 0;
+}
+
+int fdt_appendprop(void *fdt, int nodeoffset, const char *name,
+		   const void *val, int len)
+{
+	struct fdt_property *prop;
+	int err, oldlen, newlen;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	prop = fdt_get_property_w(fdt, nodeoffset, name, &oldlen);
+	if (prop) {
+		newlen = len + oldlen;
+		err = _fdt_splice_struct(fdt, prop->data,
+					 FDT_TAGALIGN(oldlen),
+					 FDT_TAGALIGN(newlen));
+		if (err)
+			return err;
+		prop->len = cpu_to_fdt32(newlen);
+		memcpy(prop->data + oldlen, val, len);
+	} else {
+		err = _fdt_add_property(fdt, nodeoffset, name, len, &prop);
+		if (err)
+			return err;
+		memcpy(prop->data, val, len);
+	}
+	return 0;
+}
+
+int fdt_delprop(void *fdt, int nodeoffset, const char *name)
+{
+	struct fdt_property *prop;
+	int len, proplen;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	prop = fdt_get_property_w(fdt, nodeoffset, name, &len);
+	if (! prop)
+		return len;
+
+	proplen = sizeof(*prop) + FDT_TAGALIGN(len);
+	return _fdt_splice_struct(fdt, prop, proplen, 0);
+}
+
+int fdt_add_subnode_namelen(void *fdt, int parentoffset,
+			    const char *name, int namelen)
+{
+	struct fdt_node_header *nh;
+	int offset, nextoffset;
+	int nodelen;
+	int err;
+	uint32_t tag;
+	fdt32_t *endtag;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	offset = fdt_subnode_offset_namelen(fdt, parentoffset, name, namelen);
+	if (offset >= 0)
+		return -FDT_ERR_EXISTS;
+	else if (offset != -FDT_ERR_NOTFOUND)
+		return offset;
+
+	/* Try to place the new node after the parent's properties */
+	fdt_next_tag(fdt, parentoffset, &nextoffset); /* skip the BEGIN_NODE */
+	do {
+		offset = nextoffset;
+		tag = fdt_next_tag(fdt, offset, &nextoffset);
+	} while ((tag == FDT_PROP) || (tag == FDT_NOP));
+
+	nh = _fdt_offset_ptr_w(fdt, offset);
+	nodelen = sizeof(*nh) + FDT_TAGALIGN(namelen+1) + FDT_TAGSIZE;
+
+	err = _fdt_splice_struct(fdt, nh, 0, nodelen);
+	if (err)
+		return err;
+
+	nh->tag = cpu_to_fdt32(FDT_BEGIN_NODE);
+	memset(nh->name, 0, FDT_TAGALIGN(namelen+1));
+	memcpy(nh->name, name, namelen);
+	endtag = (fdt32_t *)((char *)nh + nodelen - FDT_TAGSIZE);
+	*endtag = cpu_to_fdt32(FDT_END_NODE);
+
+	return offset;
+}
+
+int fdt_add_subnode(void *fdt, int parentoffset, const char *name)
+{
+	return fdt_add_subnode_namelen(fdt, parentoffset, name, strlen(name));
+}
+
+int fdt_del_node(void *fdt, int nodeoffset)
+{
+	int endoffset;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	endoffset = _fdt_node_end_offset(fdt, nodeoffset);
+	if (endoffset < 0)
+		return endoffset;
+
+	return _fdt_splice_struct(fdt, _fdt_offset_ptr_w(fdt, nodeoffset),
+				  endoffset - nodeoffset, 0);
+}
+
+static void _fdt_packblocks(const char *old, char *new,
+			    int mem_rsv_size, int struct_size)
+{
+	int mem_rsv_off, struct_off, strings_off;
+
+	mem_rsv_off = FDT_ALIGN(sizeof(struct fdt_header), 8);
+	struct_off = mem_rsv_off + mem_rsv_size;
+	strings_off = struct_off + struct_size;
+
+	memmove(new + mem_rsv_off, old + fdt_off_mem_rsvmap(old), mem_rsv_size);
+	fdt_set_off_mem_rsvmap(new, mem_rsv_off);
+
+	memmove(new + struct_off, old + fdt_off_dt_struct(old), struct_size);
+	fdt_set_off_dt_struct(new, struct_off);
+	fdt_set_size_dt_struct(new, struct_size);
+
+	memmove(new + strings_off, old + fdt_off_dt_strings(old),
+		fdt_size_dt_strings(old));
+	fdt_set_off_dt_strings(new, strings_off);
+	fdt_set_size_dt_strings(new, fdt_size_dt_strings(old));
+}
+
+int fdt_open_into(const void *fdt, void *buf, int bufsize)
+{
+	int err;
+	int mem_rsv_size, struct_size;
+	int newsize;
+	const char *fdtstart = fdt;
+	const char *fdtend = fdtstart + fdt_totalsize(fdt);
+	char *tmp;
+
+	FDT_CHECK_HEADER(fdt);
+
+	mem_rsv_size = (fdt_num_mem_rsv(fdt)+1)
+		* sizeof(struct fdt_reserve_entry);
+
+	if (fdt_version(fdt) >= 17) {
+		struct_size = fdt_size_dt_struct(fdt);
+	} else {
+		struct_size = 0;
+		while (fdt_next_tag(fdt, struct_size, &struct_size) != FDT_END)
+			;
+		if (struct_size < 0)
+			return struct_size;
+	}
+
+	if (!_fdt_blocks_misordered(fdt, mem_rsv_size, struct_size)) {
+		/* no further work necessary */
+		err = fdt_move(fdt, buf, bufsize);
+		if (err)
+			return err;
+		fdt_set_version(buf, 17);
+		fdt_set_size_dt_struct(buf, struct_size);
+		fdt_set_totalsize(buf, bufsize);
+		return 0;
+	}
+
+	/* Need to reorder */
+	newsize = FDT_ALIGN(sizeof(struct fdt_header), 8) + mem_rsv_size
+		+ struct_size + fdt_size_dt_strings(fdt);
+
+	if (bufsize < newsize)
+		return -FDT_ERR_NOSPACE;
+
+	/* First attempt to build converted tree at beginning of buffer */
+	tmp = buf;
+	/* But if that overlaps with the old tree... */
+	if (((tmp + newsize) > fdtstart) && (tmp < fdtend)) {
+		/* Try right after the old tree instead */
+		tmp = (char *)(uintptr_t)fdtend;
+		if ((tmp + newsize) > ((char *)buf + bufsize))
+			return -FDT_ERR_NOSPACE;
+	}
+
+	_fdt_packblocks(fdt, tmp, mem_rsv_size, struct_size);
+	memmove(buf, tmp, newsize);
+
+	fdt_set_magic(buf, FDT_MAGIC);
+	fdt_set_totalsize(buf, bufsize);
+	fdt_set_version(buf, 17);
+	fdt_set_last_comp_version(buf, 16);
+	fdt_set_boot_cpuid_phys(buf, fdt_boot_cpuid_phys(fdt));
+
+	return 0;
+}
+
+int fdt_pack(void *fdt)
+{
+	int mem_rsv_size;
+
+	FDT_RW_CHECK_HEADER(fdt);
+
+	mem_rsv_size = (fdt_num_mem_rsv(fdt)+1)
+		* sizeof(struct fdt_reserve_entry);
+	_fdt_packblocks(fdt, fdt, mem_rsv_size, fdt_size_dt_struct(fdt));
+	fdt_set_totalsize(fdt, _fdt_data_size(fdt));
+
+	return 0;
+}

tests/kvm-unit-tests/lib/libfdt/fdt_strerror.c

@@ -0,0 +1,96 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+struct fdt_errtabent {
+	const char *str;
+};
+
+#define FDT_ERRTABENT(val) \
+	[(val)] = { .str = #val, }
+
+static struct fdt_errtabent fdt_errtable[] = {
+	FDT_ERRTABENT(FDT_ERR_NOTFOUND),
+	FDT_ERRTABENT(FDT_ERR_EXISTS),
+	FDT_ERRTABENT(FDT_ERR_NOSPACE),
+
+	FDT_ERRTABENT(FDT_ERR_BADOFFSET),
+	FDT_ERRTABENT(FDT_ERR_BADPATH),
+	FDT_ERRTABENT(FDT_ERR_BADSTATE),
+
+	FDT_ERRTABENT(FDT_ERR_TRUNCATED),
+	FDT_ERRTABENT(FDT_ERR_BADMAGIC),
+	FDT_ERRTABENT(FDT_ERR_BADVERSION),
+	FDT_ERRTABENT(FDT_ERR_BADSTRUCTURE),
+	FDT_ERRTABENT(FDT_ERR_BADLAYOUT),
+};
+#define FDT_ERRTABSIZE	(sizeof(fdt_errtable) / sizeof(fdt_errtable[0]))
+
+const char *fdt_strerror(int errval)
+{
+	if (errval > 0)
+		return "<valid offset/length>";
+	else if (errval == 0)
+		return "<no error>";
+	else if (errval > -FDT_ERRTABSIZE) {
+		const char *s = fdt_errtable[-errval].str;
+
+		if (s)
+			return s;
+	}
+
+	return "<unknown error>";
+}

tests/kvm-unit-tests/lib/libfdt/fdt_sw.c

@@ -0,0 +1,256 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+static int _fdt_sw_check_header(void *fdt)
+{
+	if (fdt_magic(fdt) != FDT_SW_MAGIC)
+		return -FDT_ERR_BADMAGIC;
+	/* FIXME: should check more details about the header state */
+	return 0;
+}
+
+#define FDT_SW_CHECK_HEADER(fdt) \
+	{ \
+		int err; \
+		if ((err = _fdt_sw_check_header(fdt)) != 0) \
+			return err; \
+	}
+
+static void *_fdt_grab_space(void *fdt, size_t len)
+{
+	int offset = fdt_size_dt_struct(fdt);
+	int spaceleft;
+
+	spaceleft = fdt_totalsize(fdt) - fdt_off_dt_struct(fdt)
+		- fdt_size_dt_strings(fdt);
+
+	if ((offset + len < offset) || (offset + len > spaceleft))
+		return NULL;
+
+	fdt_set_size_dt_struct(fdt, offset + len);
+	return _fdt_offset_ptr_w(fdt, offset);
+}
+
+int fdt_create(void *buf, int bufsize)
+{
+	void *fdt = buf;
+
+	if (bufsize < sizeof(struct fdt_header))
+		return -FDT_ERR_NOSPACE;
+
+	memset(buf, 0, bufsize);
+
+	fdt_set_magic(fdt, FDT_SW_MAGIC);
+	fdt_set_version(fdt, FDT_LAST_SUPPORTED_VERSION);
+	fdt_set_last_comp_version(fdt, FDT_FIRST_SUPPORTED_VERSION);
+	fdt_set_totalsize(fdt,  bufsize);
+
+	fdt_set_off_mem_rsvmap(fdt, FDT_ALIGN(sizeof(struct fdt_header),
+					      sizeof(struct fdt_reserve_entry)));
+	fdt_set_off_dt_struct(fdt, fdt_off_mem_rsvmap(fdt));
+	fdt_set_off_dt_strings(fdt, bufsize);
+
+	return 0;
+}
+
+int fdt_add_reservemap_entry(void *fdt, uint64_t addr, uint64_t size)
+{
+	struct fdt_reserve_entry *re;
+	int offset;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	if (fdt_size_dt_struct(fdt))
+		return -FDT_ERR_BADSTATE;
+
+	offset = fdt_off_dt_struct(fdt);
+	if ((offset + sizeof(*re)) > fdt_totalsize(fdt))
+		return -FDT_ERR_NOSPACE;
+
+	re = (struct fdt_reserve_entry *)((char *)fdt + offset);
+	re->address = cpu_to_fdt64(addr);
+	re->size = cpu_to_fdt64(size);
+
+	fdt_set_off_dt_struct(fdt, offset + sizeof(*re));
+
+	return 0;
+}
+
+int fdt_finish_reservemap(void *fdt)
+{
+	return fdt_add_reservemap_entry(fdt, 0, 0);
+}
+
+int fdt_begin_node(void *fdt, const char *name)
+{
+	struct fdt_node_header *nh;
+	int namelen = strlen(name) + 1;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	nh = _fdt_grab_space(fdt, sizeof(*nh) + FDT_TAGALIGN(namelen));
+	if (! nh)
+		return -FDT_ERR_NOSPACE;
+
+	nh->tag = cpu_to_fdt32(FDT_BEGIN_NODE);
+	memcpy(nh->name, name, namelen);
+	return 0;
+}
+
+int fdt_end_node(void *fdt)
+{
+	fdt32_t *en;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	en = _fdt_grab_space(fdt, FDT_TAGSIZE);
+	if (! en)
+		return -FDT_ERR_NOSPACE;
+
+	*en = cpu_to_fdt32(FDT_END_NODE);
+	return 0;
+}
+
+static int _fdt_find_add_string(void *fdt, const char *s)
+{
+	char *strtab = (char *)fdt + fdt_totalsize(fdt);
+	const char *p;
+	int strtabsize = fdt_size_dt_strings(fdt);
+	int len = strlen(s) + 1;
+	int struct_top, offset;
+
+	p = _fdt_find_string(strtab - strtabsize, strtabsize, s);
+	if (p)
+		return p - strtab;
+
+	/* Add it */
+	offset = -strtabsize - len;
+	struct_top = fdt_off_dt_struct(fdt) + fdt_size_dt_struct(fdt);
+	if (fdt_totalsize(fdt) + offset < struct_top)
+		return 0; /* no more room :( */
+
+	memcpy(strtab + offset, s, len);
+	fdt_set_size_dt_strings(fdt, strtabsize + len);
+	return offset;
+}
+
+int fdt_property(void *fdt, const char *name, const void *val, int len)
+{
+	struct fdt_property *prop;
+	int nameoff;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	nameoff = _fdt_find_add_string(fdt, name);
+	if (nameoff == 0)
+		return -FDT_ERR_NOSPACE;
+
+	prop = _fdt_grab_space(fdt, sizeof(*prop) + FDT_TAGALIGN(len));
+	if (! prop)
+		return -FDT_ERR_NOSPACE;
+
+	prop->tag = cpu_to_fdt32(FDT_PROP);
+	prop->nameoff = cpu_to_fdt32(nameoff);
+	prop->len = cpu_to_fdt32(len);
+	memcpy(prop->data, val, len);
+	return 0;
+}
+
+int fdt_finish(void *fdt)
+{
+	char *p = (char *)fdt;
+	fdt32_t *end;
+	int oldstroffset, newstroffset;
+	uint32_t tag;
+	int offset, nextoffset;
+
+	FDT_SW_CHECK_HEADER(fdt);
+
+	/* Add terminator */
+	end = _fdt_grab_space(fdt, sizeof(*end));
+	if (! end)
+		return -FDT_ERR_NOSPACE;
+	*end = cpu_to_fdt32(FDT_END);
+
+	/* Relocate the string table */
+	oldstroffset = fdt_totalsize(fdt) - fdt_size_dt_strings(fdt);
+	newstroffset = fdt_off_dt_struct(fdt) + fdt_size_dt_struct(fdt);
+	memmove(p + newstroffset, p + oldstroffset, fdt_size_dt_strings(fdt));
+	fdt_set_off_dt_strings(fdt, newstroffset);
+
+	/* Walk the structure, correcting string offsets */
+	offset = 0;
+	while ((tag = fdt_next_tag(fdt, offset, &nextoffset)) != FDT_END) {
+		if (tag == FDT_PROP) {
+			struct fdt_property *prop =
+				_fdt_offset_ptr_w(fdt, offset);
+			int nameoff;
+
+			nameoff = fdt32_to_cpu(prop->nameoff);
+			nameoff += fdt_size_dt_strings(fdt);
+			prop->nameoff = cpu_to_fdt32(nameoff);
+		}
+		offset = nextoffset;
+	}
+	if (nextoffset < 0)
+		return nextoffset;
+
+	/* Finally, adjust the header */
+	fdt_set_totalsize(fdt, newstroffset + fdt_size_dt_strings(fdt));
+	fdt_set_magic(fdt, FDT_MAGIC);
+	return 0;
+}

tests/kvm-unit-tests/lib/libfdt/fdt_wip.c

@@ -0,0 +1,118 @@
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "libfdt_env.h"
+
+#include <fdt.h>
+#include <libfdt.h>
+
+#include "libfdt_internal.h"
+
+int fdt_setprop_inplace(void *fdt, int nodeoffset, const char *name,
+			const void *val, int len)
+{
+	void *propval;
+	int proplen;
+
+	propval = fdt_getprop_w(fdt, nodeoffset, name, &proplen);
+	if (! propval)
+		return proplen;
+
+	if (proplen != len)
+		return -FDT_ERR_NOSPACE;
+
+	memcpy(propval, val, len);
+	return 0;
+}
+
+static void _fdt_nop_region(void *start, int len)
+{
+	fdt32_t *p;
+
+	for (p = start; (char *)p < ((char *)start + len); p++)
+		*p = cpu_to_fdt32(FDT_NOP);
+}
+
+int fdt_nop_property(void *fdt, int nodeoffset, const char *name)
+{
+	struct fdt_property *prop;
+	int len;
+
+	prop = fdt_get_property_w(fdt, nodeoffset, name, &len);
+	if (! prop)
+		return len;
+
+	_fdt_nop_region(prop, len + sizeof(*prop));
+
+	return 0;
+}
+
+int _fdt_node_end_offset(void *fdt, int offset)
+{
+	int depth = 0;
+
+	while ((offset >= 0) && (depth >= 0))
+		offset = fdt_next_node(fdt, offset, &depth);
+
+	return offset;
+}
+
+int fdt_nop_node(void *fdt, int nodeoffset)
+{
+	int endoffset;
+
+	endoffset = _fdt_node_end_offset(fdt, nodeoffset);
+	if (endoffset < 0)
+		return endoffset;
+
+	_fdt_nop_region(fdt_offset_ptr_w(fdt, nodeoffset, 0),
+			endoffset - nodeoffset);
+	return 0;
+}

tests/kvm-unit-tests/lib/libfdt/libfdt.h

@@ -0,0 +1,1514 @@
+#ifndef _LIBFDT_H
+#define _LIBFDT_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <libfdt_env.h>
+#include <fdt.h>
+
+#define FDT_FIRST_SUPPORTED_VERSION	0x10
+#define FDT_LAST_SUPPORTED_VERSION	0x11
+
+/* Error codes: informative error codes */
+#define FDT_ERR_NOTFOUND	1
+	/* FDT_ERR_NOTFOUND: The requested node or property does not exist */
+#define FDT_ERR_EXISTS		2
+	/* FDT_ERR_EXISTS: Attemped to create a node or property which
+	 * already exists */
+#define FDT_ERR_NOSPACE		3
+	/* FDT_ERR_NOSPACE: Operation needed to expand the device
+	 * tree, but its buffer did not have sufficient space to
+	 * contain the expanded tree. Use fdt_open_into() to move the
+	 * device tree to a buffer with more space. */
+
+/* Error codes: codes for bad parameters */
+#define FDT_ERR_BADOFFSET	4
+	/* FDT_ERR_BADOFFSET: Function was passed a structure block
+	 * offset which is out-of-bounds, or which points to an
+	 * unsuitable part of the structure for the operation. */
+#define FDT_ERR_BADPATH		5
+	/* FDT_ERR_BADPATH: Function was passed a badly formatted path
+	 * (e.g. missing a leading / for a function which requires an
+	 * absolute path) */
+#define FDT_ERR_BADPHANDLE	6
+	/* FDT_ERR_BADPHANDLE: Function was passed an invalid phandle
+	 * value.  phandle values of 0 and -1 are not permitted. */
+#define FDT_ERR_BADSTATE	7
+	/* FDT_ERR_BADSTATE: Function was passed an incomplete device
+	 * tree created by the sequential-write functions, which is
+	 * not sufficiently complete for the requested operation. */
+
+/* Error codes: codes for bad device tree blobs */
+#define FDT_ERR_TRUNCATED	8
+	/* FDT_ERR_TRUNCATED: Structure block of the given device tree
+	 * ends without an FDT_END tag. */
+#define FDT_ERR_BADMAGIC	9
+	/* FDT_ERR_BADMAGIC: Given "device tree" appears not to be a
+	 * device tree at all - it is missing the flattened device
+	 * tree magic number. */
+#define FDT_ERR_BADVERSION	10
+	/* FDT_ERR_BADVERSION: Given device tree has a version which
+	 * can't be handled by the requested operation.  For
+	 * read-write functions, this may mean that fdt_open_into() is
+	 * required to convert the tree to the expected version. */
+#define FDT_ERR_BADSTRUCTURE	11
+	/* FDT_ERR_BADSTRUCTURE: Given device tree has a corrupt
+	 * structure block or other serious error (e.g. misnested
+	 * nodes, or subnodes preceding properties). */
+#define FDT_ERR_BADLAYOUT	12
+	/* FDT_ERR_BADLAYOUT: For read-write functions, the given
+	 * device tree has it's sub-blocks in an order that the
+	 * function can't handle (memory reserve map, then structure,
+	 * then strings).  Use fdt_open_into() to reorganize the tree
+	 * into a form suitable for the read-write operations. */
+
+/* "Can't happen" error indicating a bug in libfdt */
+#define FDT_ERR_INTERNAL	13
+	/* FDT_ERR_INTERNAL: libfdt has failed an internal assertion.
+	 * Should never be returned, if it is, it indicates a bug in
+	 * libfdt itself. */
+
+#define FDT_ERR_MAX		13
+
+/**********************************************************************/
+/* Low-level functions (you probably don't need these)                */
+/**********************************************************************/
+
+const void *fdt_offset_ptr(const void *fdt, int offset, unsigned int checklen);
+static inline void *fdt_offset_ptr_w(void *fdt, int offset, int checklen)
+{
+	return (void *)(uintptr_t)fdt_offset_ptr(fdt, offset, checklen);
+}
+
+uint32_t fdt_next_tag(const void *fdt, int offset, int *nextoffset);
+
+/**********************************************************************/
+/* Traversal functions                                                */
+/**********************************************************************/
+
+int fdt_next_node(const void *fdt, int offset, int *depth);
+
+/**
+ * fdt_first_subnode() - get offset of first direct subnode
+ *
+ * @fdt:	FDT blob
+ * @offset:	Offset of node to check
+ * @return offset of first subnode, or -FDT_ERR_NOTFOUND if there is none
+ */
+int fdt_first_subnode(const void *fdt, int offset);
+
+/**
+ * fdt_next_subnode() - get offset of next direct subnode
+ *
+ * After first calling fdt_first_subnode(), call this function repeatedly to
+ * get direct subnodes of a parent node.
+ *
+ * @fdt:	FDT blob
+ * @offset:	Offset of previous subnode
+ * @return offset of next subnode, or -FDT_ERR_NOTFOUND if there are no more
+ * subnodes
+ */
+int fdt_next_subnode(const void *fdt, int offset);
+
+/**********************************************************************/
+/* General functions                                                  */
+/**********************************************************************/
+
+#define fdt_get_header(fdt, field) \
+	(fdt32_to_cpu(((const struct fdt_header *)(fdt))->field))
+#define fdt_magic(fdt) 			(fdt_get_header(fdt, magic))
+#define fdt_totalsize(fdt)		(fdt_get_header(fdt, totalsize))
+#define fdt_off_dt_struct(fdt)		(fdt_get_header(fdt, off_dt_struct))
+#define fdt_off_dt_strings(fdt)		(fdt_get_header(fdt, off_dt_strings))
+#define fdt_off_mem_rsvmap(fdt)		(fdt_get_header(fdt, off_mem_rsvmap))
+#define fdt_version(fdt)		(fdt_get_header(fdt, version))
+#define fdt_last_comp_version(fdt) 	(fdt_get_header(fdt, last_comp_version))
+#define fdt_boot_cpuid_phys(fdt) 	(fdt_get_header(fdt, boot_cpuid_phys))
+#define fdt_size_dt_strings(fdt) 	(fdt_get_header(fdt, size_dt_strings))
+#define fdt_size_dt_struct(fdt)		(fdt_get_header(fdt, size_dt_struct))
+
+#define __fdt_set_hdr(name) \
+	static inline void fdt_set_##name(void *fdt, uint32_t val) \
+	{ \
+		struct fdt_header *fdth = (struct fdt_header*)fdt; \
+		fdth->name = cpu_to_fdt32(val); \
+	}
+__fdt_set_hdr(magic);
+__fdt_set_hdr(totalsize);
+__fdt_set_hdr(off_dt_struct);
+__fdt_set_hdr(off_dt_strings);
+__fdt_set_hdr(off_mem_rsvmap);
+__fdt_set_hdr(version);
+__fdt_set_hdr(last_comp_version);
+__fdt_set_hdr(boot_cpuid_phys);
+__fdt_set_hdr(size_dt_strings);
+__fdt_set_hdr(size_dt_struct);
+#undef __fdt_set_hdr
+
+/**
+ * fdt_check_header - sanity check a device tree or possible device tree
+ * @fdt: pointer to data which might be a flattened device tree
+ *
+ * fdt_check_header() checks that the given buffer contains what
+ * appears to be a flattened device tree with sane information in its
+ * header.
+ *
+ * returns:
+ *     0, if the buffer appears to contain a valid device tree
+ *     -FDT_ERR_BADMAGIC,
+ *     -FDT_ERR_BADVERSION,
+ *     -FDT_ERR_BADSTATE, standard meanings, as above
+ */
+int fdt_check_header(const void *fdt);
+
+/**
+ * fdt_move - move a device tree around in memory
+ * @fdt: pointer to the device tree to move
+ * @buf: pointer to memory where the device is to be moved
+ * @bufsize: size of the memory space at buf
+ *
+ * fdt_move() relocates, if possible, the device tree blob located at
+ * fdt to the buffer at buf of size bufsize.  The buffer may overlap
+ * with the existing device tree blob at fdt.  Therefore,
+ *     fdt_move(fdt, fdt, fdt_totalsize(fdt))
+ * should always succeed.
+ *
+ * returns:
+ *     0, on success
+ *     -FDT_ERR_NOSPACE, bufsize is insufficient to contain the device tree
+ *     -FDT_ERR_BADMAGIC,
+ *     -FDT_ERR_BADVERSION,
+ *     -FDT_ERR_BADSTATE, standard meanings
+ */
+int fdt_move(const void *fdt, void *buf, int bufsize);
+
+/**********************************************************************/
+/* Read-only functions                                                */
+/**********************************************************************/
+
+/**
+ * fdt_string - retrieve a string from the strings block of a device tree
+ * @fdt: pointer to the device tree blob
+ * @stroffset: offset of the string within the strings block (native endian)
+ *
+ * fdt_string() retrieves a pointer to a single string from the
+ * strings block of the device tree blob at fdt.
+ *
+ * returns:
+ *     a pointer to the string, on success
+ *     NULL, if stroffset is out of bounds
+ */
+const char *fdt_string(const void *fdt, int stroffset);
+
+/**
+ * fdt_num_mem_rsv - retrieve the number of memory reserve map entries
+ * @fdt: pointer to the device tree blob
+ *
+ * Returns the number of entries in the device tree blob's memory
+ * reservation map.  This does not include the terminating 0,0 entry
+ * or any other (0,0) entries reserved for expansion.
+ *
+ * returns:
+ *     the number of entries
+ */
+int fdt_num_mem_rsv(const void *fdt);
+
+/**
+ * fdt_get_mem_rsv - retrieve one memory reserve map entry
+ * @fdt: pointer to the device tree blob
+ * @address, @size: pointers to 64-bit variables
+ *
+ * On success, *address and *size will contain the address and size of
+ * the n-th reserve map entry from the device tree blob, in
+ * native-endian format.
+ *
+ * returns:
+ *     0, on success
+ *     -FDT_ERR_BADMAGIC,
+ *     -FDT_ERR_BADVERSION,
+ *     -FDT_ERR_BADSTATE, standard meanings
+ */
+int fdt_get_mem_rsv(const void *fdt, int n, uint64_t *address, uint64_t *size);
+
+/**
+ * fdt_subnode_offset_namelen - find a subnode based on substring
+ * @fdt: pointer to the device tree blob
+ * @parentoffset: structure block offset of a node
+ * @name: name of the subnode to locate
+ * @namelen: number of characters of name to consider
+ *
+ * Identical to fdt_subnode_offset(), but only examine the first
+ * namelen characters of name for matching the subnode name.  This is
+ * useful for finding subnodes based on a portion of a larger string,
+ * such as a full path.
+ */
+int fdt_subnode_offset_namelen(const void *fdt, int parentoffset,
+			       const char *name, int namelen);
+/**
+ * fdt_subnode_offset - find a subnode of a given node
+ * @fdt: pointer to the device tree blob
+ * @parentoffset: structure block offset of a node
+ * @name: name of the subnode to locate
+ *
+ * fdt_subnode_offset() finds a subnode of the node at structure block
+ * offset parentoffset with the given name.  name may include a unit
+ * address, in which case fdt_subnode_offset() will find the subnode
+ * with that unit address, or the unit address may be omitted, in
+ * which case fdt_subnode_offset() will find an arbitrary subnode
+ * whose name excluding unit address matches the given name.
+ *
+ * returns:
+ *	structure block offset of the requested subnode (>=0), on success
+ *	-FDT_ERR_NOTFOUND, if the requested subnode does not exist
+ *	-FDT_ERR_BADOFFSET, if parentoffset did not point to an FDT_BEGIN_NODE tag
+ *      -FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings.
+ */
+int fdt_subnode_offset(const void *fdt, int parentoffset, const char *name);
+
+/**
+ * fdt_path_offset - find a tree node by its full path
+ * @fdt: pointer to the device tree blob
+ * @path: full path of the node to locate
+ *
+ * fdt_path_offset() finds a node of a given path in the device tree.
+ * Each path component may omit the unit address portion, but the
+ * results of this are undefined if any such path component is
+ * ambiguous (that is if there are multiple nodes at the relevant
+ * level matching the given component, differentiated only by unit
+ * address).
+ *
+ * returns:
+ *	structure block offset of the node with the requested path (>=0), on success
+ *	-FDT_ERR_BADPATH, given path does not begin with '/' or is invalid
+ *	-FDT_ERR_NOTFOUND, if the requested node does not exist
+ *      -FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings.
+ */
+int fdt_path_offset(const void *fdt, const char *path);
+
+/**
+ * fdt_get_name - retrieve the name of a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: structure block offset of the starting node
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_get_name() retrieves the name (including unit address) of the
+ * device tree node at structure block offset nodeoffset.  If lenp is
+ * non-NULL, the length of this name is also returned, in the integer
+ * pointed to by lenp.
+ *
+ * returns:
+ *	pointer to the node's name, on success
+ *		If lenp is non-NULL, *lenp contains the length of that name (>=0)
+ *	NULL, on error
+ *		if lenp is non-NULL *lenp contains an error code (<0):
+ *		-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *		-FDT_ERR_BADMAGIC,
+ *		-FDT_ERR_BADVERSION,
+ *		-FDT_ERR_BADSTATE, standard meanings
+ */
+const char *fdt_get_name(const void *fdt, int nodeoffset, int *lenp);
+
+/**
+ * fdt_first_property_offset - find the offset of a node's first property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: structure block offset of a node
+ *
+ * fdt_first_property_offset() finds the first property of the node at
+ * the given structure block offset.
+ *
+ * returns:
+ *	structure block offset of the property (>=0), on success
+ *	-FDT_ERR_NOTFOUND, if the requested node has no properties
+ *	-FDT_ERR_BADOFFSET, if nodeoffset did not point to an FDT_BEGIN_NODE tag
+ *      -FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings.
+ */
+int fdt_first_property_offset(const void *fdt, int nodeoffset);
+
+/**
+ * fdt_next_property_offset - step through a node's properties
+ * @fdt: pointer to the device tree blob
+ * @offset: structure block offset of a property
+ *
+ * fdt_next_property_offset() finds the property immediately after the
+ * one at the given structure block offset.  This will be a property
+ * of the same node as the given property.
+ *
+ * returns:
+ *	structure block offset of the next property (>=0), on success
+ *	-FDT_ERR_NOTFOUND, if the given property is the last in its node
+ *	-FDT_ERR_BADOFFSET, if nodeoffset did not point to an FDT_PROP tag
+ *      -FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings.
+ */
+int fdt_next_property_offset(const void *fdt, int offset);
+
+/**
+ * fdt_get_property_by_offset - retrieve the property at a given offset
+ * @fdt: pointer to the device tree blob
+ * @offset: offset of the property to retrieve
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_get_property_by_offset() retrieves a pointer to the
+ * fdt_property structure within the device tree blob at the given
+ * offset.  If lenp is non-NULL, the length of the property value is
+ * also returned, in the integer pointed to by lenp.
+ *
+ * returns:
+ *	pointer to the structure representing the property
+ *		if lenp is non-NULL, *lenp contains the length of the property
+ *		value (>=0)
+ *	NULL, on error
+ *		if lenp is non-NULL, *lenp contains an error code (<0):
+ *		-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_PROP tag
+ *		-FDT_ERR_BADMAGIC,
+ *		-FDT_ERR_BADVERSION,
+ *		-FDT_ERR_BADSTATE,
+ *		-FDT_ERR_BADSTRUCTURE,
+ *		-FDT_ERR_TRUNCATED, standard meanings
+ */
+const struct fdt_property *fdt_get_property_by_offset(const void *fdt,
+						      int offset,
+						      int *lenp);
+
+/**
+ * fdt_get_property_namelen - find a property based on substring
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to find
+ * @name: name of the property to find
+ * @namelen: number of characters of name to consider
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * Identical to fdt_get_property_namelen(), but only examine the first
+ * namelen characters of name for matching the property name.
+ */
+const struct fdt_property *fdt_get_property_namelen(const void *fdt,
+						    int nodeoffset,
+						    const char *name,
+						    int namelen, int *lenp);
+
+/**
+ * fdt_get_property - find a given property in a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to find
+ * @name: name of the property to find
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_get_property() retrieves a pointer to the fdt_property
+ * structure within the device tree blob corresponding to the property
+ * named 'name' of the node at offset nodeoffset.  If lenp is
+ * non-NULL, the length of the property value is also returned, in the
+ * integer pointed to by lenp.
+ *
+ * returns:
+ *	pointer to the structure representing the property
+ *		if lenp is non-NULL, *lenp contains the length of the property
+ *		value (>=0)
+ *	NULL, on error
+ *		if lenp is non-NULL, *lenp contains an error code (<0):
+ *		-FDT_ERR_NOTFOUND, node does not have named property
+ *		-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *		-FDT_ERR_BADMAGIC,
+ *		-FDT_ERR_BADVERSION,
+ *		-FDT_ERR_BADSTATE,
+ *		-FDT_ERR_BADSTRUCTURE,
+ *		-FDT_ERR_TRUNCATED, standard meanings
+ */
+const struct fdt_property *fdt_get_property(const void *fdt, int nodeoffset,
+					    const char *name, int *lenp);
+static inline struct fdt_property *fdt_get_property_w(void *fdt, int nodeoffset,
+						      const char *name,
+						      int *lenp)
+{
+	return (struct fdt_property *)(uintptr_t)
+		fdt_get_property(fdt, nodeoffset, name, lenp);
+}
+
+/**
+ * fdt_getprop_by_offset - retrieve the value of a property at a given offset
+ * @fdt: pointer to the device tree blob
+ * @ffset: offset of the property to read
+ * @namep: pointer to a string variable (will be overwritten) or NULL
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_getprop_by_offset() retrieves a pointer to the value of the
+ * property at structure block offset 'offset' (this will be a pointer
+ * to within the device blob itself, not a copy of the value).  If
+ * lenp is non-NULL, the length of the property value is also
+ * returned, in the integer pointed to by lenp.  If namep is non-NULL,
+ * the property's namne will also be returned in the char * pointed to
+ * by namep (this will be a pointer to within the device tree's string
+ * block, not a new copy of the name).
+ *
+ * returns:
+ *	pointer to the property's value
+ *		if lenp is non-NULL, *lenp contains the length of the property
+ *		value (>=0)
+ *		if namep is non-NULL *namep contiains a pointer to the property
+ *		name.
+ *	NULL, on error
+ *		if lenp is non-NULL, *lenp contains an error code (<0):
+ *		-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_PROP tag
+ *		-FDT_ERR_BADMAGIC,
+ *		-FDT_ERR_BADVERSION,
+ *		-FDT_ERR_BADSTATE,
+ *		-FDT_ERR_BADSTRUCTURE,
+ *		-FDT_ERR_TRUNCATED, standard meanings
+ */
+const void *fdt_getprop_by_offset(const void *fdt, int offset,
+				  const char **namep, int *lenp);
+
+/**
+ * fdt_getprop_namelen - get property value based on substring
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to find
+ * @name: name of the property to find
+ * @namelen: number of characters of name to consider
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * Identical to fdt_getprop(), but only examine the first namelen
+ * characters of name for matching the property name.
+ */
+const void *fdt_getprop_namelen(const void *fdt, int nodeoffset,
+				const char *name, int namelen, int *lenp);
+
+/**
+ * fdt_getprop - retrieve the value of a given property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to find
+ * @name: name of the property to find
+ * @lenp: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_getprop() retrieves a pointer to the value of the property
+ * named 'name' of the node at offset nodeoffset (this will be a
+ * pointer to within the device blob itself, not a copy of the value).
+ * If lenp is non-NULL, the length of the property value is also
+ * returned, in the integer pointed to by lenp.
+ *
+ * returns:
+ *	pointer to the property's value
+ *		if lenp is non-NULL, *lenp contains the length of the property
+ *		value (>=0)
+ *	NULL, on error
+ *		if lenp is non-NULL, *lenp contains an error code (<0):
+ *		-FDT_ERR_NOTFOUND, node does not have named property
+ *		-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *		-FDT_ERR_BADMAGIC,
+ *		-FDT_ERR_BADVERSION,
+ *		-FDT_ERR_BADSTATE,
+ *		-FDT_ERR_BADSTRUCTURE,
+ *		-FDT_ERR_TRUNCATED, standard meanings
+ */
+const void *fdt_getprop(const void *fdt, int nodeoffset,
+			const char *name, int *lenp);
+static inline void *fdt_getprop_w(void *fdt, int nodeoffset,
+				  const char *name, int *lenp)
+{
+	return (void *)(uintptr_t)fdt_getprop(fdt, nodeoffset, name, lenp);
+}
+
+/**
+ * fdt_get_phandle - retrieve the phandle of a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: structure block offset of the node
+ *
+ * fdt_get_phandle() retrieves the phandle of the device tree node at
+ * structure block offset nodeoffset.
+ *
+ * returns:
+ *	the phandle of the node at nodeoffset, on success (!= 0, != -1)
+ *	0, if the node has no phandle, or another error occurs
+ */
+uint32_t fdt_get_phandle(const void *fdt, int nodeoffset);
+
+/**
+ * fdt_get_alias_namelen - get alias based on substring
+ * @fdt: pointer to the device tree blob
+ * @name: name of the alias th look up
+ * @namelen: number of characters of name to consider
+ *
+ * Identical to fdt_get_alias(), but only examine the first namelen
+ * characters of name for matching the alias name.
+ */
+const char *fdt_get_alias_namelen(const void *fdt,
+				  const char *name, int namelen);
+
+/**
+ * fdt_get_alias - retreive the path referenced by a given alias
+ * @fdt: pointer to the device tree blob
+ * @name: name of the alias th look up
+ *
+ * fdt_get_alias() retrieves the value of a given alias.  That is, the
+ * value of the property named 'name' in the node /aliases.
+ *
+ * returns:
+ *	a pointer to the expansion of the alias named 'name', if it exists
+ *	NULL, if the given alias or the /aliases node does not exist
+ */
+const char *fdt_get_alias(const void *fdt, const char *name);
+
+/**
+ * fdt_get_path - determine the full path of a node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose path to find
+ * @buf: character buffer to contain the returned path (will be overwritten)
+ * @buflen: size of the character buffer at buf
+ *
+ * fdt_get_path() computes the full path of the node at offset
+ * nodeoffset, and records that path in the buffer at buf.
+ *
+ * NOTE: This function is expensive, as it must scan the device tree
+ * structure from the start to nodeoffset.
+ *
+ * returns:
+ *	0, on success
+ *		buf contains the absolute path of the node at
+ *		nodeoffset, as a NUL-terminated string.
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_NOSPACE, the path of the given node is longer than (bufsize-1)
+ *		characters and will not fit in the given buffer.
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_get_path(const void *fdt, int nodeoffset, char *buf, int buflen);
+
+/**
+ * fdt_supernode_atdepth_offset - find a specific ancestor of a node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose parent to find
+ * @supernodedepth: depth of the ancestor to find
+ * @nodedepth: pointer to an integer variable (will be overwritten) or NULL
+ *
+ * fdt_supernode_atdepth_offset() finds an ancestor of the given node
+ * at a specific depth from the root (where the root itself has depth
+ * 0, its immediate subnodes depth 1 and so forth).  So
+ *	fdt_supernode_atdepth_offset(fdt, nodeoffset, 0, NULL);
+ * will always return 0, the offset of the root node.  If the node at
+ * nodeoffset has depth D, then:
+ *	fdt_supernode_atdepth_offset(fdt, nodeoffset, D, NULL);
+ * will return nodeoffset itself.
+ *
+ * NOTE: This function is expensive, as it must scan the device tree
+ * structure from the start to nodeoffset.
+ *
+ * returns:
+
+ *	structure block offset of the node at node offset's ancestor
+ *		of depth supernodedepth (>=0), on success
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+*	-FDT_ERR_NOTFOUND, supernodedepth was greater than the depth of nodeoffset
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_supernode_atdepth_offset(const void *fdt, int nodeoffset,
+				 int supernodedepth, int *nodedepth);
+
+/**
+ * fdt_node_depth - find the depth of a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose parent to find
+ *
+ * fdt_node_depth() finds the depth of a given node.  The root node
+ * has depth 0, its immediate subnodes depth 1 and so forth.
+ *
+ * NOTE: This function is expensive, as it must scan the device tree
+ * structure from the start to nodeoffset.
+ *
+ * returns:
+ *	depth of the node at nodeoffset (>=0), on success
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_node_depth(const void *fdt, int nodeoffset);
+
+/**
+ * fdt_parent_offset - find the parent of a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose parent to find
+ *
+ * fdt_parent_offset() locates the parent node of a given node (that
+ * is, it finds the offset of the node which contains the node at
+ * nodeoffset as a subnode).
+ *
+ * NOTE: This function is expensive, as it must scan the device tree
+ * structure from the start to nodeoffset, *twice*.
+ *
+ * returns:
+ *	structure block offset of the parent of the node at nodeoffset
+ *		(>=0), on success
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_parent_offset(const void *fdt, int nodeoffset);
+
+/**
+ * fdt_node_offset_by_prop_value - find nodes with a given property value
+ * @fdt: pointer to the device tree blob
+ * @startoffset: only find nodes after this offset
+ * @propname: property name to check
+ * @propval: property value to search for
+ * @proplen: length of the value in propval
+ *
+ * fdt_node_offset_by_prop_value() returns the offset of the first
+ * node after startoffset, which has a property named propname whose
+ * value is of length proplen and has value equal to propval; or if
+ * startoffset is -1, the very first such node in the tree.
+ *
+ * To iterate through all nodes matching the criterion, the following
+ * idiom can be used:
+ *	offset = fdt_node_offset_by_prop_value(fdt, -1, propname,
+ *					       propval, proplen);
+ *	while (offset != -FDT_ERR_NOTFOUND) {
+ *		// other code here
+ *		offset = fdt_node_offset_by_prop_value(fdt, offset, propname,
+ *						       propval, proplen);
+ *	}
+ *
+ * Note the -1 in the first call to the function, if 0 is used here
+ * instead, the function will never locate the root node, even if it
+ * matches the criterion.
+ *
+ * returns:
+ *	structure block offset of the located node (>= 0, >startoffset),
+ *		 on success
+ *	-FDT_ERR_NOTFOUND, no node matching the criterion exists in the
+ *		tree after startoffset
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_node_offset_by_prop_value(const void *fdt, int startoffset,
+				  const char *propname,
+				  const void *propval, int proplen);
+
+/**
+ * fdt_node_offset_by_phandle - find the node with a given phandle
+ * @fdt: pointer to the device tree blob
+ * @phandle: phandle value
+ *
+ * fdt_node_offset_by_phandle() returns the offset of the node
+ * which has the given phandle value.  If there is more than one node
+ * in the tree with the given phandle (an invalid tree), results are
+ * undefined.
+ *
+ * returns:
+ *	structure block offset of the located node (>= 0), on success
+ *	-FDT_ERR_NOTFOUND, no node with that phandle exists
+ *	-FDT_ERR_BADPHANDLE, given phandle value was invalid (0 or -1)
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_node_offset_by_phandle(const void *fdt, uint32_t phandle);
+
+/**
+ * fdt_node_check_compatible: check a node's compatible property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of a tree node
+ * @compatible: string to match against
+ *
+ *
+ * fdt_node_check_compatible() returns 0 if the given node contains a
+ * 'compatible' property with the given string as one of its elements,
+ * it returns non-zero otherwise, or on error.
+ *
+ * returns:
+ *	0, if the node has a 'compatible' property listing the given string
+ *	1, if the node has a 'compatible' property, but it does not list
+ *		the given string
+ *	-FDT_ERR_NOTFOUND, if the given node has no 'compatible' property
+ * 	-FDT_ERR_BADOFFSET, if nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_node_check_compatible(const void *fdt, int nodeoffset,
+			      const char *compatible);
+
+/**
+ * fdt_node_offset_by_compatible - find nodes with a given 'compatible' value
+ * @fdt: pointer to the device tree blob
+ * @startoffset: only find nodes after this offset
+ * @compatible: 'compatible' string to match against
+ *
+ * fdt_node_offset_by_compatible() returns the offset of the first
+ * node after startoffset, which has a 'compatible' property which
+ * lists the given compatible string; or if startoffset is -1, the
+ * very first such node in the tree.
+ *
+ * To iterate through all nodes matching the criterion, the following
+ * idiom can be used:
+ *	offset = fdt_node_offset_by_compatible(fdt, -1, compatible);
+ *	while (offset != -FDT_ERR_NOTFOUND) {
+ *		// other code here
+ *		offset = fdt_node_offset_by_compatible(fdt, offset, compatible);
+ *	}
+ *
+ * Note the -1 in the first call to the function, if 0 is used here
+ * instead, the function will never locate the root node, even if it
+ * matches the criterion.
+ *
+ * returns:
+ *	structure block offset of the located node (>= 0, >startoffset),
+ *		 on success
+ *	-FDT_ERR_NOTFOUND, no node matching the criterion exists in the
+ *		tree after startoffset
+ * 	-FDT_ERR_BADOFFSET, nodeoffset does not refer to a BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE, standard meanings
+ */
+int fdt_node_offset_by_compatible(const void *fdt, int startoffset,
+				  const char *compatible);
+
+/**
+ * fdt_stringlist_contains - check a string list property for a string
+ * @strlist: Property containing a list of strings to check
+ * @listlen: Length of property
+ * @str: String to search for
+ *
+ * This is a utility function provided for convenience. The list contains
+ * one or more strings, each terminated by \0, as is found in a device tree
+ * "compatible" property.
+ *
+ * @return: 1 if the string is found in the list, 0 not found, or invalid list
+ */
+int fdt_stringlist_contains(const char *strlist, int listlen, const char *str);
+
+/**********************************************************************/
+/* Write-in-place functions                                           */
+/**********************************************************************/
+
+/**
+ * fdt_setprop_inplace - change a property's value, but not its size
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: pointer to data to replace the property value with
+ * @len: length of the property value
+ *
+ * fdt_setprop_inplace() replaces the value of a given property with
+ * the data in val, of length len.  This function cannot change the
+ * size of a property, and so will only work if len is equal to the
+ * current length of the property.
+ *
+ * This function will alter only the bytes in the blob which contain
+ * the given property value, and will not alter or move any other part
+ * of the tree.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, if len is not equal to the property's current length
+ *	-FDT_ERR_NOTFOUND, node does not have the named property
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_setprop_inplace(void *fdt, int nodeoffset, const char *name,
+			const void *val, int len);
+
+/**
+ * fdt_setprop_inplace_u32 - change the value of a 32-bit integer property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 32-bit integer value to replace the property with
+ *
+ * fdt_setprop_inplace_u32() replaces the value of a given property
+ * with the 32-bit integer value in val, converting val to big-endian
+ * if necessary.  This function cannot change the size of a property,
+ * and so will only work if the property already exists and has length
+ * 4.
+ *
+ * This function will alter only the bytes in the blob which contain
+ * the given property value, and will not alter or move any other part
+ * of the tree.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, if the property's length is not equal to 4
+ *	-FDT_ERR_NOTFOUND, node does not have the named property
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_setprop_inplace_u32(void *fdt, int nodeoffset,
+					  const char *name, uint32_t val)
+{
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_setprop_inplace(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_setprop_inplace_u64 - change the value of a 64-bit integer property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 64-bit integer value to replace the property with
+ *
+ * fdt_setprop_inplace_u64() replaces the value of a given property
+ * with the 64-bit integer value in val, converting val to big-endian
+ * if necessary.  This function cannot change the size of a property,
+ * and so will only work if the property already exists and has length
+ * 8.
+ *
+ * This function will alter only the bytes in the blob which contain
+ * the given property value, and will not alter or move any other part
+ * of the tree.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, if the property's length is not equal to 8
+ *	-FDT_ERR_NOTFOUND, node does not have the named property
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_setprop_inplace_u64(void *fdt, int nodeoffset,
+					  const char *name, uint64_t val)
+{
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_setprop_inplace(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_setprop_inplace_cell - change the value of a single-cell property
+ *
+ * This is an alternative name for fdt_setprop_inplace_u32()
+ */
+static inline int fdt_setprop_inplace_cell(void *fdt, int nodeoffset,
+					   const char *name, uint32_t val)
+{
+	return fdt_setprop_inplace_u32(fdt, nodeoffset, name, val);
+}
+
+/**
+ * fdt_nop_property - replace a property with nop tags
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to nop
+ * @name: name of the property to nop
+ *
+ * fdt_nop_property() will replace a given property's representation
+ * in the blob with FDT_NOP tags, effectively removing it from the
+ * tree.
+ *
+ * This function will alter only the bytes in the blob which contain
+ * the property, and will not alter or move any other part of the
+ * tree.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOTFOUND, node does not have the named property
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_nop_property(void *fdt, int nodeoffset, const char *name);
+
+/**
+ * fdt_nop_node - replace a node (subtree) with nop tags
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node to nop
+ *
+ * fdt_nop_node() will replace a given node's representation in the
+ * blob, including all its subnodes, if any, with FDT_NOP tags,
+ * effectively removing it from the tree.
+ *
+ * This function will alter only the bytes in the blob which contain
+ * the node and its properties and subnodes, and will not alter or
+ * move any other part of the tree.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_nop_node(void *fdt, int nodeoffset);
+
+/**********************************************************************/
+/* Sequential write functions                                         */
+/**********************************************************************/
+
+int fdt_create(void *buf, int bufsize);
+int fdt_add_reservemap_entry(void *fdt, uint64_t addr, uint64_t size);
+int fdt_finish_reservemap(void *fdt);
+int fdt_begin_node(void *fdt, const char *name);
+int fdt_property(void *fdt, const char *name, const void *val, int len);
+static inline int fdt_property_u32(void *fdt, const char *name, uint32_t val)
+{
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_property(fdt, name, &tmp, sizeof(tmp));
+}
+static inline int fdt_property_u64(void *fdt, const char *name, uint64_t val)
+{
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_property(fdt, name, &tmp, sizeof(tmp));
+}
+static inline int fdt_property_cell(void *fdt, const char *name, uint32_t val)
+{
+	return fdt_property_u32(fdt, name, val);
+}
+#define fdt_property_string(fdt, name, str) \
+	fdt_property(fdt, name, str, strlen(str)+1)
+int fdt_end_node(void *fdt);
+int fdt_finish(void *fdt);
+
+/**********************************************************************/
+/* Read-write functions                                               */
+/**********************************************************************/
+
+int fdt_create_empty_tree(void *buf, int bufsize);
+int fdt_open_into(const void *fdt, void *buf, int bufsize);
+int fdt_pack(void *fdt);
+
+/**
+ * fdt_add_mem_rsv - add one memory reserve map entry
+ * @fdt: pointer to the device tree blob
+ * @address, @size: 64-bit values (native endian)
+ *
+ * Adds a reserve map entry to the given blob reserving a region at
+ * address address of length size.
+ *
+ * This function will insert data into the reserve map and will
+ * therefore change the indexes of some entries in the table.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new reservation entry
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_add_mem_rsv(void *fdt, uint64_t address, uint64_t size);
+
+/**
+ * fdt_del_mem_rsv - remove a memory reserve map entry
+ * @fdt: pointer to the device tree blob
+ * @n: entry to remove
+ *
+ * fdt_del_mem_rsv() removes the n-th memory reserve map entry from
+ * the blob.
+ *
+ * This function will delete data from the reservation table and will
+ * therefore change the indexes of some entries in the table.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOTFOUND, there is no entry of the given index (i.e. there
+ *		are less than n+1 reserve map entries)
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_del_mem_rsv(void *fdt, int n);
+
+/**
+ * fdt_set_name - change the name of a given node
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: structure block offset of a node
+ * @name: name to give the node
+ *
+ * fdt_set_name() replaces the name (including unit address, if any)
+ * of the given node with the given string.  NOTE: this function can't
+ * efficiently check if the new name is unique amongst the given
+ * node's siblings; results are undefined if this function is invoked
+ * with a name equal to one of the given node's siblings.
+ *
+ * This function may insert or delete data from the blob, and will
+ * therefore change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob
+ *		to contain the new name
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE, standard meanings
+ */
+int fdt_set_name(void *fdt, int nodeoffset, const char *name);
+
+/**
+ * fdt_setprop - create or change a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: pointer to data to set the property value to
+ * @len: length of the property value
+ *
+ * fdt_setprop() sets the value of the named property in the given
+ * node to the given value and length, creating the property if it
+ * does not already exist.
+ *
+ * This function may insert or delete data from the blob, and will
+ * therefore change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_setprop(void *fdt, int nodeoffset, const char *name,
+		const void *val, int len);
+
+/**
+ * fdt_setprop_u32 - set a property to a 32-bit integer
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 32-bit integer value for the property (native endian)
+ *
+ * fdt_setprop_u32() sets the value of the named property in the given
+ * node to the given 32-bit integer value (converting to big-endian if
+ * necessary), or creates a new property with that value if it does
+ * not already exist.
+ *
+ * This function may insert or delete data from the blob, and will
+ * therefore change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_setprop_u32(void *fdt, int nodeoffset, const char *name,
+				  uint32_t val)
+{
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_setprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_setprop_u64 - set a property to a 64-bit integer
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 64-bit integer value for the property (native endian)
+ *
+ * fdt_setprop_u64() sets the value of the named property in the given
+ * node to the given 64-bit integer value (converting to big-endian if
+ * necessary), or creates a new property with that value if it does
+ * not already exist.
+ *
+ * This function may insert or delete data from the blob, and will
+ * therefore change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_setprop_u64(void *fdt, int nodeoffset, const char *name,
+				  uint64_t val)
+{
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_setprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_setprop_cell - set a property to a single cell value
+ *
+ * This is an alternative name for fdt_setprop_u32()
+ */
+static inline int fdt_setprop_cell(void *fdt, int nodeoffset, const char *name,
+				   uint32_t val)
+{
+	return fdt_setprop_u32(fdt, nodeoffset, name, val);
+}
+
+/**
+ * fdt_setprop_string - set a property to a string value
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @str: string value for the property
+ *
+ * fdt_setprop_string() sets the value of the named property in the
+ * given node to the given string value (using the length of the
+ * string to determine the new length of the property), or creates a
+ * new property with that value if it does not already exist.
+ *
+ * This function may insert or delete data from the blob, and will
+ * therefore change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+#define fdt_setprop_string(fdt, nodeoffset, name, str) \
+	fdt_setprop((fdt), (nodeoffset), (name), (str), strlen(str)+1)
+
+/**
+ * fdt_appendprop - append to or create a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to append to
+ * @val: pointer to data to append to the property value
+ * @len: length of the data to append to the property value
+ *
+ * fdt_appendprop() appends the value to the named property in the
+ * given node, creating the property if it does not already exist.
+ *
+ * This function may insert data into the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_appendprop(void *fdt, int nodeoffset, const char *name,
+		   const void *val, int len);
+
+/**
+ * fdt_appendprop_u32 - append a 32-bit integer value to a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 32-bit integer value to append to the property (native endian)
+ *
+ * fdt_appendprop_u32() appends the given 32-bit integer value
+ * (converting to big-endian if necessary) to the value of the named
+ * property in the given node, or creates a new property with that
+ * value if it does not already exist.
+ *
+ * This function may insert data into the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_appendprop_u32(void *fdt, int nodeoffset,
+				     const char *name, uint32_t val)
+{
+	fdt32_t tmp = cpu_to_fdt32(val);
+	return fdt_appendprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_appendprop_u64 - append a 64-bit integer value to a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @val: 64-bit integer value to append to the property (native endian)
+ *
+ * fdt_appendprop_u64() appends the given 64-bit integer value
+ * (converting to big-endian if necessary) to the value of the named
+ * property in the given node, or creates a new property with that
+ * value if it does not already exist.
+ *
+ * This function may insert data into the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+static inline int fdt_appendprop_u64(void *fdt, int nodeoffset,
+				     const char *name, uint64_t val)
+{
+	fdt64_t tmp = cpu_to_fdt64(val);
+	return fdt_appendprop(fdt, nodeoffset, name, &tmp, sizeof(tmp));
+}
+
+/**
+ * fdt_appendprop_cell - append a single cell value to a property
+ *
+ * This is an alternative name for fdt_appendprop_u32()
+ */
+static inline int fdt_appendprop_cell(void *fdt, int nodeoffset,
+				      const char *name, uint32_t val)
+{
+	return fdt_appendprop_u32(fdt, nodeoffset, name, val);
+}
+
+/**
+ * fdt_appendprop_string - append a string to a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to change
+ * @name: name of the property to change
+ * @str: string value to append to the property
+ *
+ * fdt_appendprop_string() appends the given string to the value of
+ * the named property in the given node, or creates a new property
+ * with that value if it does not already exist.
+ *
+ * This function may insert data into the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOSPACE, there is insufficient free space in the blob to
+ *		contain the new property value
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+#define fdt_appendprop_string(fdt, nodeoffset, name, str) \
+	fdt_appendprop((fdt), (nodeoffset), (name), (str), strlen(str)+1)
+
+/**
+ * fdt_delprop - delete a property
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node whose property to nop
+ * @name: name of the property to nop
+ *
+ * fdt_del_property() will delete the given property.
+ *
+ * This function will delete data from the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_NOTFOUND, node does not have the named property
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_delprop(void *fdt, int nodeoffset, const char *name);
+
+/**
+ * fdt_add_subnode_namelen - creates a new node based on substring
+ * @fdt: pointer to the device tree blob
+ * @parentoffset: structure block offset of a node
+ * @name: name of the subnode to locate
+ * @namelen: number of characters of name to consider
+ *
+ * Identical to fdt_add_subnode(), but use only the first namelen
+ * characters of name as the name of the new node.  This is useful for
+ * creating subnodes based on a portion of a larger string, such as a
+ * full path.
+ */
+int fdt_add_subnode_namelen(void *fdt, int parentoffset,
+			    const char *name, int namelen);
+
+/**
+ * fdt_add_subnode - creates a new node
+ * @fdt: pointer to the device tree blob
+ * @parentoffset: structure block offset of a node
+ * @name: name of the subnode to locate
+ *
+ * fdt_add_subnode() creates a new node as a subnode of the node at
+ * structure block offset parentoffset, with the given name (which
+ * should include the unit address, if any).
+ *
+ * This function will insert data into the blob, and will therefore
+ * change the offsets of some existing nodes.
+
+ * returns:
+ *	structure block offset of the created nodeequested subnode (>=0), on success
+ *	-FDT_ERR_NOTFOUND, if the requested subnode does not exist
+ *	-FDT_ERR_BADOFFSET, if parentoffset did not point to an FDT_BEGIN_NODE tag
+ *	-FDT_ERR_EXISTS, if the node at parentoffset already has a subnode of
+ *		the given name
+ *	-FDT_ERR_NOSPACE, if there is insufficient free space in the
+ *		blob to contain the new node
+ *	-FDT_ERR_NOSPACE
+ *	-FDT_ERR_BADLAYOUT
+ *      -FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings.
+ */
+int fdt_add_subnode(void *fdt, int parentoffset, const char *name);
+
+/**
+ * fdt_del_node - delete a node (subtree)
+ * @fdt: pointer to the device tree blob
+ * @nodeoffset: offset of the node to nop
+ *
+ * fdt_del_node() will remove the given node, including all its
+ * subnodes if any, from the blob.
+ *
+ * This function will delete data from the blob, and will therefore
+ * change the offsets of some existing nodes.
+ *
+ * returns:
+ *	0, on success
+ *	-FDT_ERR_BADOFFSET, nodeoffset did not point to FDT_BEGIN_NODE tag
+ *	-FDT_ERR_BADLAYOUT,
+ *	-FDT_ERR_BADMAGIC,
+ *	-FDT_ERR_BADVERSION,
+ *	-FDT_ERR_BADSTATE,
+ *	-FDT_ERR_BADSTRUCTURE,
+ *	-FDT_ERR_TRUNCATED, standard meanings
+ */
+int fdt_del_node(void *fdt, int nodeoffset);
+
+/**********************************************************************/
+/* Debugging / informational functions                                */
+/**********************************************************************/
+
+const char *fdt_strerror(int errval);
+
+#endif /* _LIBFDT_H */

tests/kvm-unit-tests/lib/libfdt/libfdt_env.h

@@ -0,0 +1,111 @@
+#ifndef _LIBFDT_ENV_H
+#define _LIBFDT_ENV_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ * Copyright 2012 Kim Phillips, Freescale Semiconductor.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#ifdef __CHECKER__
+#define __force __attribute__((force))
+#define __bitwise __attribute__((bitwise))
+#else
+#define __force
+#define __bitwise
+#endif
+
+typedef uint16_t __bitwise fdt16_t;
+typedef uint32_t __bitwise fdt32_t;
+typedef uint64_t __bitwise fdt64_t;
+
+#define EXTRACT_BYTE(x, n)	((unsigned long long)((uint8_t *)&x)[n])
+#define CPU_TO_FDT16(x) ((EXTRACT_BYTE(x, 0) << 8) | EXTRACT_BYTE(x, 1))
+#define CPU_TO_FDT32(x) ((EXTRACT_BYTE(x, 0) << 24) | (EXTRACT_BYTE(x, 1) << 16) | \
+			 (EXTRACT_BYTE(x, 2) << 8) | EXTRACT_BYTE(x, 3))
+#define CPU_TO_FDT64(x) ((EXTRACT_BYTE(x, 0) << 56) | (EXTRACT_BYTE(x, 1) << 48) | \
+			 (EXTRACT_BYTE(x, 2) << 40) | (EXTRACT_BYTE(x, 3) << 32) | \
+			 (EXTRACT_BYTE(x, 4) << 24) | (EXTRACT_BYTE(x, 5) << 16) | \
+			 (EXTRACT_BYTE(x, 6) << 8) | EXTRACT_BYTE(x, 7))
+
+static inline uint16_t fdt16_to_cpu(fdt16_t x)
+{
+	return (__force uint16_t)CPU_TO_FDT16(x);
+}
+static inline fdt16_t cpu_to_fdt16(uint16_t x)
+{
+	return (__force fdt16_t)CPU_TO_FDT16(x);
+}
+
+static inline uint32_t fdt32_to_cpu(fdt32_t x)
+{
+	return (__force uint32_t)CPU_TO_FDT32(x);
+}
+static inline fdt32_t cpu_to_fdt32(uint32_t x)
+{
+	return (__force fdt32_t)CPU_TO_FDT32(x);
+}
+
+static inline uint64_t fdt64_to_cpu(fdt64_t x)
+{
+	return (__force uint64_t)CPU_TO_FDT64(x);
+}
+static inline fdt64_t cpu_to_fdt64(uint64_t x)
+{
+	return (__force fdt64_t)CPU_TO_FDT64(x);
+}
+#undef CPU_TO_FDT64
+#undef CPU_TO_FDT32
+#undef CPU_TO_FDT16
+#undef EXTRACT_BYTE
+
+#endif /* _LIBFDT_ENV_H */

tests/kvm-unit-tests/lib/libfdt/libfdt_internal.h

@@ -0,0 +1,95 @@
+#ifndef _LIBFDT_INTERNAL_H
+#define _LIBFDT_INTERNAL_H
+/*
+ * libfdt - Flat Device Tree manipulation
+ * Copyright (C) 2006 David Gibson, IBM Corporation.
+ *
+ * libfdt is dual licensed: you can use it either under the terms of
+ * the GPL, or the BSD license, at your option.
+ *
+ *  a) This library 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.
+ *
+ *     This library is distributed in the hope that it will be useful,
+ *     but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *     GNU General Public License for more details.
+ *
+ *     You should have received a copy of the GNU General Public
+ *     License along with this library; if not, write to the Free
+ *     Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ *     MA 02110-1301 USA
+ *
+ * Alternatively,
+ *
+ *  b) Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *     1. Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *     2. Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ *     THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+ *     CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ *     INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *     MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *     DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
+ *     CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *     SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *     NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ *     LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ *     HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ *     OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ *     EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <fdt.h>
+
+#define FDT_ALIGN(x, a)		(((x) + (a) - 1) & ~((a) - 1))
+#define FDT_TAGALIGN(x)		(FDT_ALIGN((x), FDT_TAGSIZE))
+
+#define FDT_CHECK_HEADER(fdt) \
+	{ \
+		int err; \
+		if ((err = fdt_check_header(fdt)) != 0) \
+			return err; \
+	}
+
+int _fdt_check_node_offset(const void *fdt, int offset);
+int _fdt_check_prop_offset(const void *fdt, int offset);
+const char *_fdt_find_string(const char *strtab, int tabsize, const char *s);
+int _fdt_node_end_offset(void *fdt, int nodeoffset);
+
+static inline const void *_fdt_offset_ptr(const void *fdt, int offset)
+{
+	return (const char *)fdt + fdt_off_dt_struct(fdt) + offset;
+}
+
+static inline void *_fdt_offset_ptr_w(void *fdt, int offset)
+{
+	return (void *)(uintptr_t)_fdt_offset_ptr(fdt, offset);
+}
+
+static inline const struct fdt_reserve_entry *_fdt_mem_rsv(const void *fdt, int n)
+{
+	const struct fdt_reserve_entry *rsv_table =
+		(const struct fdt_reserve_entry *)
+		((const char *)fdt + fdt_off_mem_rsvmap(fdt));
+
+	return rsv_table + n;
+}
+static inline struct fdt_reserve_entry *_fdt_mem_rsv_w(void *fdt, int n)
+{
+	return (void *)(uintptr_t)_fdt_mem_rsv(fdt, n);
+}
+
+#define FDT_SW_MAGIC		(~FDT_MAGIC)
+
+#endif /* _LIBFDT_INTERNAL_H */

tests/kvm-unit-tests/lib/libfdt/version.lds

@@ -0,0 +1,60 @@
+LIBFDT_1.2 {
+	global:
+		fdt_next_node;
+		fdt_check_header;
+		fdt_move;
+		fdt_string;
+		fdt_num_mem_rsv;
+		fdt_get_mem_rsv;
+		fdt_subnode_offset_namelen;
+		fdt_subnode_offset;
+		fdt_path_offset;
+		fdt_get_name;
+		fdt_get_property_namelen;
+		fdt_get_property;
+		fdt_getprop_namelen;
+		fdt_getprop;
+		fdt_get_phandle;
+		fdt_get_alias_namelen;
+		fdt_get_alias;
+		fdt_get_path;
+		fdt_supernode_atdepth_offset;
+		fdt_node_depth;
+		fdt_parent_offset;
+		fdt_node_offset_by_prop_value;
+		fdt_node_offset_by_phandle;
+		fdt_node_check_compatible;
+		fdt_node_offset_by_compatible;
+		fdt_setprop_inplace;
+		fdt_nop_property;
+		fdt_nop_node;
+		fdt_create;
+		fdt_add_reservemap_entry;
+		fdt_finish_reservemap;
+		fdt_begin_node;
+		fdt_property;
+		fdt_end_node;
+		fdt_finish;
+		fdt_open_into;
+		fdt_pack;
+		fdt_add_mem_rsv;
+		fdt_del_mem_rsv;
+		fdt_set_name;
+		fdt_setprop;
+		fdt_delprop;
+		fdt_add_subnode_namelen;
+		fdt_add_subnode;
+		fdt_del_node;
+		fdt_strerror;
+		fdt_offset_ptr;
+		fdt_next_tag;
+		fdt_appendprop;
+		fdt_create_empty_tree;
+		fdt_first_property_offset;
+		fdt_get_property_by_offset;
+		fdt_getprop_by_offset;
+		fdt_next_property_offset;
+
+	local:
+		*;
+};

tests/kvm-unit-tests/lib/linux/const.h

@@ -0,0 +1,27 @@
+/* const.h: Macros for dealing with constants.  */
+
+#ifndef _LINUX_CONST_H
+#define _LINUX_CONST_H
+
+/* Some constant macros are used in both assembler and
+ * C code.  Therefore we cannot annotate them always with
+ * 'UL' and other type specifiers unilaterally.  We
+ * use the following macros to deal with this.
+ *
+ * Similarly, _AT() will cast an expression with a type in C, but
+ * leave it unchanged in asm.
+ */
+
+#ifdef __ASSEMBLY__
+#define _AC(X,Y)	X
+#define _AT(T,X)	X
+#else
+#define __AC(X,Y)	(X##Y)
+#define _AC(X,Y)	__AC(X,Y)
+#define _AT(T,X)	((T)(X))
+#endif
+
+#define _BITUL(x)	(_AC(1,UL) << (x))
+#define _BITULL(x)	(_AC(1,ULL) << (x))
+
+#endif /* !(_LINUX_CONST_H) */

tests/kvm-unit-tests/lib/linux/pci_regs.h

@@ -0,0 +1,949 @@
+/*
+ *	pci_regs.h
+ *
+ *	PCI standard defines
+ *	Copyright 1994, Drew Eckhardt
+ *	Copyright 1997--1999 Martin Mares <mj@ucw.cz>
+ *
+ *	For more information, please consult the following manuals (look at
+ *	http://www.pcisig.com/ for how to get them):
+ *
+ *	PCI BIOS Specification
+ *	PCI Local Bus Specification
+ *	PCI to PCI Bridge Specification
+ *	PCI System Design Guide
+ *
+ *	For HyperTransport information, please consult the following manuals
+ *	from http://www.hypertransport.org
+ *
+ *	The HyperTransport I/O Link Specification
+ */
+
+#ifndef LINUX_PCI_REGS_H
+#define LINUX_PCI_REGS_H
+
+/*
+ * Under PCI, each device has 256 bytes of configuration address space,
+ * of which the first 64 bytes are standardized as follows:
+ */
+#define PCI_STD_HEADER_SIZEOF	64
+#define PCI_VENDOR_ID		0x00	/* 16 bits */
+#define PCI_DEVICE_ID		0x02	/* 16 bits */
+#define PCI_COMMAND		0x04	/* 16 bits */
+#define  PCI_COMMAND_IO		0x1	/* Enable response in I/O space */
+#define  PCI_COMMAND_MEMORY	0x2	/* Enable response in Memory space */
+#define  PCI_COMMAND_MASTER	0x4	/* Enable bus mastering */
+#define  PCI_COMMAND_SPECIAL	0x8	/* Enable response to special cycles */
+#define  PCI_COMMAND_INVALIDATE	0x10	/* Use memory write and invalidate */
+#define  PCI_COMMAND_VGA_PALETTE 0x20	/* Enable palette snooping */
+#define  PCI_COMMAND_PARITY	0x40	/* Enable parity checking */
+#define  PCI_COMMAND_WAIT	0x80	/* Enable address/data stepping */
+#define  PCI_COMMAND_SERR	0x100	/* Enable SERR */
+#define  PCI_COMMAND_FAST_BACK	0x200	/* Enable back-to-back writes */
+#define  PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */
+
+#define PCI_STATUS		0x06	/* 16 bits */
+#define  PCI_STATUS_INTERRUPT	0x08	/* Interrupt status */
+#define  PCI_STATUS_CAP_LIST	0x10	/* Support Capability List */
+#define  PCI_STATUS_66MHZ	0x20	/* Support 66 MHz PCI 2.1 bus */
+#define  PCI_STATUS_UDF		0x40	/* Support User Definable Features [obsolete] */
+#define  PCI_STATUS_FAST_BACK	0x80	/* Accept fast-back to back */
+#define  PCI_STATUS_PARITY	0x100	/* Detected parity error */
+#define  PCI_STATUS_DEVSEL_MASK	0x600	/* DEVSEL timing */
+#define  PCI_STATUS_DEVSEL_FAST		0x000
+#define  PCI_STATUS_DEVSEL_MEDIUM	0x200
+#define  PCI_STATUS_DEVSEL_SLOW		0x400
+#define  PCI_STATUS_SIG_TARGET_ABORT	0x800 /* Set on target abort */
+#define  PCI_STATUS_REC_TARGET_ABORT	0x1000 /* Master ack of " */
+#define  PCI_STATUS_REC_MASTER_ABORT	0x2000 /* Set on master abort */
+#define  PCI_STATUS_SIG_SYSTEM_ERROR	0x4000 /* Set when we drive SERR */
+#define  PCI_STATUS_DETECTED_PARITY	0x8000 /* Set on parity error */
+
+#define PCI_CLASS_REVISION	0x08	/* High 24 bits are class, low 8 revision */
+#define PCI_REVISION_ID		0x08	/* Revision ID */
+#define PCI_CLASS_PROG		0x09	/* Reg. Level Programming Interface */
+#define PCI_CLASS_DEVICE	0x0a	/* Device class */
+
+#define PCI_CACHE_LINE_SIZE	0x0c	/* 8 bits */
+#define PCI_LATENCY_TIMER	0x0d	/* 8 bits */
+#define PCI_HEADER_TYPE		0x0e	/* 8 bits */
+#define  PCI_HEADER_TYPE_NORMAL		0
+#define  PCI_HEADER_TYPE_BRIDGE		1
+#define  PCI_HEADER_TYPE_CARDBUS	2
+
+#define PCI_BIST		0x0f	/* 8 bits */
+#define  PCI_BIST_CODE_MASK	0x0f	/* Return result */
+#define  PCI_BIST_START		0x40	/* 1 to start BIST, 2 secs or less */
+#define  PCI_BIST_CAPABLE	0x80	/* 1 if BIST capable */
+
+/*
+ * Base addresses specify locations in memory or I/O space.
+ * Decoded size can be determined by writing a value of
+ * 0xffffffff to the register, and reading it back.  Only
+ * 1 bits are decoded.
+ */
+#define PCI_BASE_ADDRESS_0	0x10	/* 32 bits */
+#define PCI_BASE_ADDRESS_1	0x14	/* 32 bits [htype 0,1 only] */
+#define PCI_BASE_ADDRESS_2	0x18	/* 32 bits [htype 0 only] */
+#define PCI_BASE_ADDRESS_3	0x1c	/* 32 bits */
+#define PCI_BASE_ADDRESS_4	0x20	/* 32 bits */
+#define PCI_BASE_ADDRESS_5	0x24	/* 32 bits */
+#define  PCI_BASE_ADDRESS_SPACE		0x01	/* 0 = memory, 1 = I/O */
+#define  PCI_BASE_ADDRESS_SPACE_IO	0x01
+#define  PCI_BASE_ADDRESS_SPACE_MEMORY	0x00
+#define  PCI_BASE_ADDRESS_MEM_TYPE_MASK	0x06
+#define  PCI_BASE_ADDRESS_MEM_TYPE_32	0x00	/* 32 bit address */
+#define  PCI_BASE_ADDRESS_MEM_TYPE_1M	0x02	/* Below 1M [obsolete] */
+#define  PCI_BASE_ADDRESS_MEM_TYPE_64	0x04	/* 64 bit address */
+#define  PCI_BASE_ADDRESS_MEM_PREFETCH	0x08	/* prefetchable? */
+#define  PCI_BASE_ADDRESS_MEM_MASK	(~0x0fUL)
+#define  PCI_BASE_ADDRESS_IO_MASK	(~0x03UL)
+/* bit 1 is reserved if address_space = 1 */
+
+/* Header type 0 (normal devices) */
+#define PCI_CARDBUS_CIS		0x28
+#define PCI_SUBSYSTEM_VENDOR_ID	0x2c
+#define PCI_SUBSYSTEM_ID	0x2e
+#define PCI_ROM_ADDRESS		0x30	/* Bits 31..11 are address, 10..1 reserved */
+#define  PCI_ROM_ADDRESS_ENABLE	0x01
+#define PCI_ROM_ADDRESS_MASK	(~0x7ffUL)
+
+#define PCI_CAPABILITY_LIST	0x34	/* Offset of first capability list entry */
+
+/* 0x35-0x3b are reserved */
+#define PCI_INTERRUPT_LINE	0x3c	/* 8 bits */
+#define PCI_INTERRUPT_PIN	0x3d	/* 8 bits */
+#define PCI_MIN_GNT		0x3e	/* 8 bits */
+#define PCI_MAX_LAT		0x3f	/* 8 bits */
+
+/* Header type 1 (PCI-to-PCI bridges) */
+#define PCI_PRIMARY_BUS		0x18	/* Primary bus number */
+#define PCI_SECONDARY_BUS	0x19	/* Secondary bus number */
+#define PCI_SUBORDINATE_BUS	0x1a	/* Highest bus number behind the bridge */
+#define PCI_SEC_LATENCY_TIMER	0x1b	/* Latency timer for secondary interface */
+#define PCI_IO_BASE		0x1c	/* I/O range behind the bridge */
+#define PCI_IO_LIMIT		0x1d
+#define  PCI_IO_RANGE_TYPE_MASK	0x0fUL	/* I/O bridging type */
+#define  PCI_IO_RANGE_TYPE_16	0x00
+#define  PCI_IO_RANGE_TYPE_32	0x01
+#define  PCI_IO_RANGE_MASK	(~0x0fUL) /* Standard 4K I/O windows */
+#define  PCI_IO_1K_RANGE_MASK	(~0x03UL) /* Intel 1K I/O windows */
+#define PCI_SEC_STATUS		0x1e	/* Secondary status register, only bit 14 used */
+#define PCI_MEMORY_BASE		0x20	/* Memory range behind */
+#define PCI_MEMORY_LIMIT	0x22
+#define  PCI_MEMORY_RANGE_TYPE_MASK 0x0fUL
+#define  PCI_MEMORY_RANGE_MASK	(~0x0fUL)
+#define PCI_PREF_MEMORY_BASE	0x24	/* Prefetchable memory range behind */
+#define PCI_PREF_MEMORY_LIMIT	0x26
+#define  PCI_PREF_RANGE_TYPE_MASK 0x0fUL
+#define  PCI_PREF_RANGE_TYPE_32	0x00
+#define  PCI_PREF_RANGE_TYPE_64	0x01
+#define  PCI_PREF_RANGE_MASK	(~0x0fUL)
+#define PCI_PREF_BASE_UPPER32	0x28	/* Upper half of prefetchable memory range */
+#define PCI_PREF_LIMIT_UPPER32	0x2c
+#define PCI_IO_BASE_UPPER16	0x30	/* Upper half of I/O addresses */
+#define PCI_IO_LIMIT_UPPER16	0x32
+/* 0x34 same as for htype 0 */
+/* 0x35-0x3b is reserved */
+#define PCI_ROM_ADDRESS1	0x38	/* Same as PCI_ROM_ADDRESS, but for htype 1 */
+/* 0x3c-0x3d are same as for htype 0 */
+#define PCI_BRIDGE_CONTROL	0x3e
+#define  PCI_BRIDGE_CTL_PARITY	0x01	/* Enable parity detection on secondary interface */
+#define  PCI_BRIDGE_CTL_SERR	0x02	/* The same for SERR forwarding */
+#define  PCI_BRIDGE_CTL_ISA	0x04	/* Enable ISA mode */
+#define  PCI_BRIDGE_CTL_VGA	0x08	/* Forward VGA addresses */
+#define  PCI_BRIDGE_CTL_MASTER_ABORT	0x20  /* Report master aborts */
+#define  PCI_BRIDGE_CTL_BUS_RESET	0x40	/* Secondary bus reset */
+#define  PCI_BRIDGE_CTL_FAST_BACK	0x80	/* Fast Back2Back enabled on secondary interface */
+
+/* Header type 2 (CardBus bridges) */
+#define PCI_CB_CAPABILITY_LIST	0x14
+/* 0x15 reserved */
+#define PCI_CB_SEC_STATUS	0x16	/* Secondary status */
+#define PCI_CB_PRIMARY_BUS	0x18	/* PCI bus number */
+#define PCI_CB_CARD_BUS		0x19	/* CardBus bus number */
+#define PCI_CB_SUBORDINATE_BUS	0x1a	/* Subordinate bus number */
+#define PCI_CB_LATENCY_TIMER	0x1b	/* CardBus latency timer */
+#define PCI_CB_MEMORY_BASE_0	0x1c
+#define PCI_CB_MEMORY_LIMIT_0	0x20
+#define PCI_CB_MEMORY_BASE_1	0x24
+#define PCI_CB_MEMORY_LIMIT_1	0x28
+#define PCI_CB_IO_BASE_0	0x2c
+#define PCI_CB_IO_BASE_0_HI	0x2e
+#define PCI_CB_IO_LIMIT_0	0x30
+#define PCI_CB_IO_LIMIT_0_HI	0x32
+#define PCI_CB_IO_BASE_1	0x34
+#define PCI_CB_IO_BASE_1_HI	0x36
+#define PCI_CB_IO_LIMIT_1	0x38
+#define PCI_CB_IO_LIMIT_1_HI	0x3a
+#define  PCI_CB_IO_RANGE_MASK	(~0x03UL)
+/* 0x3c-0x3d are same as for htype 0 */
+#define PCI_CB_BRIDGE_CONTROL	0x3e
+#define  PCI_CB_BRIDGE_CTL_PARITY	0x01	/* Similar to standard bridge control register */
+#define  PCI_CB_BRIDGE_CTL_SERR		0x02
+#define  PCI_CB_BRIDGE_CTL_ISA		0x04
+#define  PCI_CB_BRIDGE_CTL_VGA		0x08
+#define  PCI_CB_BRIDGE_CTL_MASTER_ABORT	0x20
+#define  PCI_CB_BRIDGE_CTL_CB_RESET	0x40	/* CardBus reset */
+#define  PCI_CB_BRIDGE_CTL_16BIT_INT	0x80	/* Enable interrupt for 16-bit cards */
+#define  PCI_CB_BRIDGE_CTL_PREFETCH_MEM0 0x100	/* Prefetch enable for both memory regions */
+#define  PCI_CB_BRIDGE_CTL_PREFETCH_MEM1 0x200
+#define  PCI_CB_BRIDGE_CTL_POST_WRITES	0x400
+#define PCI_CB_SUBSYSTEM_VENDOR_ID	0x40
+#define PCI_CB_SUBSYSTEM_ID		0x42
+#define PCI_CB_LEGACY_MODE_BASE		0x44	/* 16-bit PC Card legacy mode base address (ExCa) */
+/* 0x48-0x7f reserved */
+
+/* Capability lists */
+
+#define PCI_CAP_LIST_ID		0	/* Capability ID */
+#define  PCI_CAP_ID_PM		0x01	/* Power Management */
+#define  PCI_CAP_ID_AGP		0x02	/* Accelerated Graphics Port */
+#define  PCI_CAP_ID_VPD		0x03	/* Vital Product Data */
+#define  PCI_CAP_ID_SLOTID	0x04	/* Slot Identification */
+#define  PCI_CAP_ID_MSI		0x05	/* Message Signalled Interrupts */
+#define  PCI_CAP_ID_CHSWP	0x06	/* CompactPCI HotSwap */
+#define  PCI_CAP_ID_PCIX	0x07	/* PCI-X */
+#define  PCI_CAP_ID_HT		0x08	/* HyperTransport */
+#define  PCI_CAP_ID_VNDR	0x09	/* Vendor-Specific */
+#define  PCI_CAP_ID_DBG		0x0A	/* Debug port */
+#define  PCI_CAP_ID_CCRC	0x0B	/* CompactPCI Central Resource Control */
+#define  PCI_CAP_ID_SHPC	0x0C	/* PCI Standard Hot-Plug Controller */
+#define  PCI_CAP_ID_SSVID	0x0D	/* Bridge subsystem vendor/device ID */
+#define  PCI_CAP_ID_AGP3	0x0E	/* AGP Target PCI-PCI bridge */
+#define  PCI_CAP_ID_SECDEV	0x0F	/* Secure Device */
+#define  PCI_CAP_ID_EXP		0x10	/* PCI Express */
+#define  PCI_CAP_ID_MSIX	0x11	/* MSI-X */
+#define  PCI_CAP_ID_SATA	0x12	/* SATA Data/Index Conf. */
+#define  PCI_CAP_ID_AF		0x13	/* PCI Advanced Features */
+#define  PCI_CAP_ID_EA		0x14	/* PCI Enhanced Allocation */
+#define  PCI_CAP_ID_MAX		PCI_CAP_ID_EA
+#define PCI_CAP_LIST_NEXT	1	/* Next capability in the list */
+#define PCI_CAP_FLAGS		2	/* Capability defined flags (16 bits) */
+#define PCI_CAP_SIZEOF		4
+
+/* Power Management Registers */
+
+#define PCI_PM_PMC		2	/* PM Capabilities Register */
+#define  PCI_PM_CAP_VER_MASK	0x0007	/* Version */
+#define  PCI_PM_CAP_PME_CLOCK	0x0008	/* PME clock required */
+#define  PCI_PM_CAP_RESERVED    0x0010  /* Reserved field */
+#define  PCI_PM_CAP_DSI		0x0020	/* Device specific initialization */
+#define  PCI_PM_CAP_AUX_POWER	0x01C0	/* Auxiliary power support mask */
+#define  PCI_PM_CAP_D1		0x0200	/* D1 power state support */
+#define  PCI_PM_CAP_D2		0x0400	/* D2 power state support */
+#define  PCI_PM_CAP_PME		0x0800	/* PME pin supported */
+#define  PCI_PM_CAP_PME_MASK	0xF800	/* PME Mask of all supported states */
+#define  PCI_PM_CAP_PME_D0	0x0800	/* PME# from D0 */
+#define  PCI_PM_CAP_PME_D1	0x1000	/* PME# from D1 */
+#define  PCI_PM_CAP_PME_D2	0x2000	/* PME# from D2 */
+#define  PCI_PM_CAP_PME_D3	0x4000	/* PME# from D3 (hot) */
+#define  PCI_PM_CAP_PME_D3cold	0x8000	/* PME# from D3 (cold) */
+#define  PCI_PM_CAP_PME_SHIFT	11	/* Start of the PME Mask in PMC */
+#define PCI_PM_CTRL		4	/* PM control and status register */
+#define  PCI_PM_CTRL_STATE_MASK	0x0003	/* Current power state (D0 to D3) */
+#define  PCI_PM_CTRL_NO_SOFT_RESET	0x0008	/* No reset for D3hot->D0 */
+#define  PCI_PM_CTRL_PME_ENABLE	0x0100	/* PME pin enable */
+#define  PCI_PM_CTRL_DATA_SEL_MASK	0x1e00	/* Data select (??) */
+#define  PCI_PM_CTRL_DATA_SCALE_MASK	0x6000	/* Data scale (??) */
+#define  PCI_PM_CTRL_PME_STATUS	0x8000	/* PME pin status */
+#define PCI_PM_PPB_EXTENSIONS	6	/* PPB support extensions (??) */
+#define  PCI_PM_PPB_B2_B3	0x40	/* Stop clock when in D3hot (??) */
+#define  PCI_PM_BPCC_ENABLE	0x80	/* Bus power/clock control enable (??) */
+#define PCI_PM_DATA_REGISTER	7	/* (??) */
+#define PCI_PM_SIZEOF		8
+
+/* AGP registers */
+
+#define PCI_AGP_VERSION		2	/* BCD version number */
+#define PCI_AGP_RFU		3	/* Rest of capability flags */
+#define PCI_AGP_STATUS		4	/* Status register */
+#define  PCI_AGP_STATUS_RQ_MASK	0xff000000	/* Maximum number of requests - 1 */
+#define  PCI_AGP_STATUS_SBA	0x0200	/* Sideband addressing supported */
+#define  PCI_AGP_STATUS_64BIT	0x0020	/* 64-bit addressing supported */
+#define  PCI_AGP_STATUS_FW	0x0010	/* FW transfers supported */
+#define  PCI_AGP_STATUS_RATE4	0x0004	/* 4x transfer rate supported */
+#define  PCI_AGP_STATUS_RATE2	0x0002	/* 2x transfer rate supported */
+#define  PCI_AGP_STATUS_RATE1	0x0001	/* 1x transfer rate supported */
+#define PCI_AGP_COMMAND		8	/* Control register */
+#define  PCI_AGP_COMMAND_RQ_MASK 0xff000000  /* Master: Maximum number of requests */
+#define  PCI_AGP_COMMAND_SBA	0x0200	/* Sideband addressing enabled */
+#define  PCI_AGP_COMMAND_AGP	0x0100	/* Allow processing of AGP transactions */
+#define  PCI_AGP_COMMAND_64BIT	0x0020	/* Allow processing of 64-bit addresses */
+#define  PCI_AGP_COMMAND_FW	0x0010	/* Force FW transfers */
+#define  PCI_AGP_COMMAND_RATE4	0x0004	/* Use 4x rate */
+#define  PCI_AGP_COMMAND_RATE2	0x0002	/* Use 2x rate */
+#define  PCI_AGP_COMMAND_RATE1	0x0001	/* Use 1x rate */
+#define PCI_AGP_SIZEOF		12
+
+/* Vital Product Data */
+
+#define PCI_VPD_ADDR		2	/* Address to access (15 bits!) */
+#define  PCI_VPD_ADDR_MASK	0x7fff	/* Address mask */
+#define  PCI_VPD_ADDR_F		0x8000	/* Write 0, 1 indicates completion */
+#define PCI_VPD_DATA		4	/* 32-bits of data returned here */
+#define PCI_CAP_VPD_SIZEOF	8
+
+/* Slot Identification */
+
+#define PCI_SID_ESR		2	/* Expansion Slot Register */
+#define  PCI_SID_ESR_NSLOTS	0x1f	/* Number of expansion slots available */
+#define  PCI_SID_ESR_FIC	0x20	/* First In Chassis Flag */
+#define PCI_SID_CHASSIS_NR	3	/* Chassis Number */
+
+/* Message Signalled Interrupts registers */
+
+#define PCI_MSI_FLAGS		2	/* Message Control */
+#define  PCI_MSI_FLAGS_ENABLE	0x0001	/* MSI feature enabled */
+#define  PCI_MSI_FLAGS_QMASK	0x000e	/* Maximum queue size available */
+#define  PCI_MSI_FLAGS_QSIZE	0x0070	/* Message queue size configured */
+#define  PCI_MSI_FLAGS_64BIT	0x0080	/* 64-bit addresses allowed */
+#define  PCI_MSI_FLAGS_MASKBIT	0x0100	/* Per-vector masking capable */
+#define PCI_MSI_RFU		3	/* Rest of capability flags */
+#define PCI_MSI_ADDRESS_LO	4	/* Lower 32 bits */
+#define PCI_MSI_ADDRESS_HI	8	/* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */
+#define PCI_MSI_DATA_32		8	/* 16 bits of data for 32-bit devices */
+#define PCI_MSI_MASK_32		12	/* Mask bits register for 32-bit devices */
+#define PCI_MSI_PENDING_32	16	/* Pending intrs for 32-bit devices */
+#define PCI_MSI_DATA_64		12	/* 16 bits of data for 64-bit devices */
+#define PCI_MSI_MASK_64		16	/* Mask bits register for 64-bit devices */
+#define PCI_MSI_PENDING_64	20	/* Pending intrs for 64-bit devices */
+
+/* MSI-X registers */
+#define PCI_MSIX_FLAGS		2	/* Message Control */
+#define  PCI_MSIX_FLAGS_QSIZE	0x07FF	/* Table size */
+#define  PCI_MSIX_FLAGS_MASKALL	0x4000	/* Mask all vectors for this function */
+#define  PCI_MSIX_FLAGS_ENABLE	0x8000	/* MSI-X enable */
+#define PCI_MSIX_TABLE		4	/* Table offset */
+#define  PCI_MSIX_TABLE_BIR	0x00000007 /* BAR index */
+#define  PCI_MSIX_TABLE_OFFSET	0xfffffff8 /* Offset into specified BAR */
+#define PCI_MSIX_PBA		8	/* Pending Bit Array offset */
+#define  PCI_MSIX_PBA_BIR	0x00000007 /* BAR index */
+#define  PCI_MSIX_PBA_OFFSET	0xfffffff8 /* Offset into specified BAR */
+#define PCI_MSIX_FLAGS_BIRMASK	PCI_MSIX_PBA_BIR /* deprecated */
+#define PCI_CAP_MSIX_SIZEOF	12	/* size of MSIX registers */
+
+/* MSI-X Table entry format */
+#define PCI_MSIX_ENTRY_SIZE		16
+#define  PCI_MSIX_ENTRY_LOWER_ADDR	0
+#define  PCI_MSIX_ENTRY_UPPER_ADDR	4
+#define  PCI_MSIX_ENTRY_DATA		8
+#define  PCI_MSIX_ENTRY_VECTOR_CTRL	12
+#define   PCI_MSIX_ENTRY_CTRL_MASKBIT	1
+
+/* CompactPCI Hotswap Register */
+
+#define PCI_CHSWP_CSR		2	/* Control and Status Register */
+#define  PCI_CHSWP_DHA		0x01	/* Device Hiding Arm */
+#define  PCI_CHSWP_EIM		0x02	/* ENUM# Signal Mask */
+#define  PCI_CHSWP_PIE		0x04	/* Pending Insert or Extract */
+#define  PCI_CHSWP_LOO		0x08	/* LED On / Off */
+#define  PCI_CHSWP_PI		0x30	/* Programming Interface */
+#define  PCI_CHSWP_EXT		0x40	/* ENUM# status - extraction */
+#define  PCI_CHSWP_INS		0x80	/* ENUM# status - insertion */
+
+/* PCI Advanced Feature registers */
+
+#define PCI_AF_LENGTH		2
+#define PCI_AF_CAP		3
+#define  PCI_AF_CAP_TP		0x01
+#define  PCI_AF_CAP_FLR		0x02
+#define PCI_AF_CTRL		4
+#define  PCI_AF_CTRL_FLR	0x01
+#define PCI_AF_STATUS		5
+#define  PCI_AF_STATUS_TP	0x01
+#define PCI_CAP_AF_SIZEOF	6	/* size of AF registers */
+
+/* PCI Enhanced Allocation registers */
+
+#define PCI_EA_NUM_ENT		2	/* Number of Capability Entries */
+#define  PCI_EA_NUM_ENT_MASK	0x3f	/* Num Entries Mask */
+#define PCI_EA_FIRST_ENT	4	/* First EA Entry in List */
+#define PCI_EA_FIRST_ENT_BRIDGE	8	/* First EA Entry for Bridges */
+#define  PCI_EA_ES		0x00000007 /* Entry Size */
+#define  PCI_EA_BEI		0x000000f0 /* BAR Equivalent Indicator */
+/* 0-5 map to BARs 0-5 respectively */
+#define   PCI_EA_BEI_BAR0		0
+#define   PCI_EA_BEI_BAR5		5
+#define   PCI_EA_BEI_BRIDGE		6	/* Resource behind bridge */
+#define   PCI_EA_BEI_ENI		7	/* Equivalent Not Indicated */
+#define   PCI_EA_BEI_ROM		8	/* Expansion ROM */
+/* 9-14 map to VF BARs 0-5 respectively */
+#define   PCI_EA_BEI_VF_BAR0		9
+#define   PCI_EA_BEI_VF_BAR5		14
+#define   PCI_EA_BEI_RESERVED		15	/* Reserved - Treat like ENI */
+#define  PCI_EA_PP		0x0000ff00	/* Primary Properties */
+#define  PCI_EA_SP		0x00ff0000	/* Secondary Properties */
+#define   PCI_EA_P_MEM			0x00	/* Non-Prefetch Memory */
+#define   PCI_EA_P_MEM_PREFETCH		0x01	/* Prefetchable Memory */
+#define   PCI_EA_P_IO			0x02	/* I/O Space */
+#define   PCI_EA_P_VF_MEM_PREFETCH	0x03	/* VF Prefetchable Memory */
+#define   PCI_EA_P_VF_MEM		0x04	/* VF Non-Prefetch Memory */
+#define   PCI_EA_P_BRIDGE_MEM		0x05	/* Bridge Non-Prefetch Memory */
+#define   PCI_EA_P_BRIDGE_MEM_PREFETCH	0x06	/* Bridge Prefetchable Memory */
+#define   PCI_EA_P_BRIDGE_IO		0x07	/* Bridge I/O Space */
+/* 0x08-0xfc reserved */
+#define   PCI_EA_P_MEM_RESERVED		0xfd	/* Reserved Memory */
+#define   PCI_EA_P_IO_RESERVED		0xfe	/* Reserved I/O Space */
+#define   PCI_EA_P_UNAVAILABLE		0xff	/* Entry Unavailable */
+#define  PCI_EA_WRITABLE	0x40000000	/* Writable: 1 = RW, 0 = HwInit */
+#define  PCI_EA_ENABLE		0x80000000	/* Enable for this entry */
+#define PCI_EA_BASE		4		/* Base Address Offset */
+#define PCI_EA_MAX_OFFSET	8		/* MaxOffset (resource length) */
+/* bit 0 is reserved */
+#define  PCI_EA_IS_64		0x00000002	/* 64-bit field flag */
+#define  PCI_EA_FIELD_MASK	0xfffffffc	/* For Base & Max Offset */
+
+/* PCI-X registers (Type 0 (non-bridge) devices) */
+
+#define PCI_X_CMD		2	/* Modes & Features */
+#define  PCI_X_CMD_DPERR_E	0x0001	/* Data Parity Error Recovery Enable */
+#define  PCI_X_CMD_ERO		0x0002	/* Enable Relaxed Ordering */
+#define  PCI_X_CMD_READ_512	0x0000	/* 512 byte maximum read byte count */
+#define  PCI_X_CMD_READ_1K	0x0004	/* 1Kbyte maximum read byte count */
+#define  PCI_X_CMD_READ_2K	0x0008	/* 2Kbyte maximum read byte count */
+#define  PCI_X_CMD_READ_4K	0x000c	/* 4Kbyte maximum read byte count */
+#define  PCI_X_CMD_MAX_READ	0x000c	/* Max Memory Read Byte Count */
+				/* Max # of outstanding split transactions */
+#define  PCI_X_CMD_SPLIT_1	0x0000	/* Max 1 */
+#define  PCI_X_CMD_SPLIT_2	0x0010	/* Max 2 */
+#define  PCI_X_CMD_SPLIT_3	0x0020	/* Max 3 */
+#define  PCI_X_CMD_SPLIT_4	0x0030	/* Max 4 */
+#define  PCI_X_CMD_SPLIT_8	0x0040	/* Max 8 */
+#define  PCI_X_CMD_SPLIT_12	0x0050	/* Max 12 */
+#define  PCI_X_CMD_SPLIT_16	0x0060	/* Max 16 */
+#define  PCI_X_CMD_SPLIT_32	0x0070	/* Max 32 */
+#define  PCI_X_CMD_MAX_SPLIT	0x0070	/* Max Outstanding Split Transactions */
+#define  PCI_X_CMD_VERSION(x)	(((x) >> 12) & 3) /* Version */
+#define PCI_X_STATUS		4	/* PCI-X capabilities */
+#define  PCI_X_STATUS_DEVFN	0x000000ff	/* A copy of devfn */
+#define  PCI_X_STATUS_BUS	0x0000ff00	/* A copy of bus nr */
+#define  PCI_X_STATUS_64BIT	0x00010000	/* 64-bit device */
+#define  PCI_X_STATUS_133MHZ	0x00020000	/* 133 MHz capable */
+#define  PCI_X_STATUS_SPL_DISC	0x00040000	/* Split Completion Discarded */
+#define  PCI_X_STATUS_UNX_SPL	0x00080000	/* Unexpected Split Completion */
+#define  PCI_X_STATUS_COMPLEX	0x00100000	/* Device Complexity */
+#define  PCI_X_STATUS_MAX_READ	0x00600000	/* Designed Max Memory Read Count */
+#define  PCI_X_STATUS_MAX_SPLIT	0x03800000	/* Designed Max Outstanding Split Transactions */
+#define  PCI_X_STATUS_MAX_CUM	0x1c000000	/* Designed Max Cumulative Read Size */
+#define  PCI_X_STATUS_SPL_ERR	0x20000000	/* Rcvd Split Completion Error Msg */
+#define  PCI_X_STATUS_266MHZ	0x40000000	/* 266 MHz capable */
+#define  PCI_X_STATUS_533MHZ	0x80000000	/* 533 MHz capable */
+#define PCI_X_ECC_CSR		8	/* ECC control and status */
+#define PCI_CAP_PCIX_SIZEOF_V0	8	/* size of registers for Version 0 */
+#define PCI_CAP_PCIX_SIZEOF_V1	24	/* size for Version 1 */
+#define PCI_CAP_PCIX_SIZEOF_V2	PCI_CAP_PCIX_SIZEOF_V1	/* Same for v2 */
+
+/* PCI-X registers (Type 1 (bridge) devices) */
+
+#define PCI_X_BRIDGE_SSTATUS	2	/* Secondary Status */
+#define  PCI_X_SSTATUS_64BIT	0x0001	/* Secondary AD interface is 64 bits */
+#define  PCI_X_SSTATUS_133MHZ	0x0002	/* 133 MHz capable */
+#define  PCI_X_SSTATUS_FREQ	0x03c0	/* Secondary Bus Mode and Frequency */
+#define  PCI_X_SSTATUS_VERS	0x3000	/* PCI-X Capability Version */
+#define  PCI_X_SSTATUS_V1	0x1000	/* Mode 2, not Mode 1 */
+#define  PCI_X_SSTATUS_V2	0x2000	/* Mode 1 or Modes 1 and 2 */
+#define  PCI_X_SSTATUS_266MHZ	0x4000	/* 266 MHz capable */
+#define  PCI_X_SSTATUS_533MHZ	0x8000	/* 533 MHz capable */
+#define PCI_X_BRIDGE_STATUS	4	/* Bridge Status */
+
+/* PCI Bridge Subsystem ID registers */
+
+#define PCI_SSVID_VENDOR_ID     4	/* PCI Bridge subsystem vendor ID */
+#define PCI_SSVID_DEVICE_ID     6	/* PCI Bridge subsystem device ID */
+
+/* PCI Express capability registers */
+
+#define PCI_EXP_FLAGS		2	/* Capabilities register */
+#define PCI_EXP_FLAGS_VERS	0x000f	/* Capability version */
+#define PCI_EXP_FLAGS_TYPE	0x00f0	/* Device/Port type */
+#define  PCI_EXP_TYPE_ENDPOINT	0x0	/* Express Endpoint */
+#define  PCI_EXP_TYPE_LEG_END	0x1	/* Legacy Endpoint */
+#define  PCI_EXP_TYPE_ROOT_PORT 0x4	/* Root Port */
+#define  PCI_EXP_TYPE_UPSTREAM	0x5	/* Upstream Port */
+#define  PCI_EXP_TYPE_DOWNSTREAM 0x6	/* Downstream Port */
+#define  PCI_EXP_TYPE_PCI_BRIDGE 0x7	/* PCIe to PCI/PCI-X Bridge */
+#define  PCI_EXP_TYPE_PCIE_BRIDGE 0x8	/* PCI/PCI-X to PCIe Bridge */
+#define  PCI_EXP_TYPE_RC_END	0x9	/* Root Complex Integrated Endpoint */
+#define  PCI_EXP_TYPE_RC_EC	0xa	/* Root Complex Event Collector */
+#define PCI_EXP_FLAGS_SLOT	0x0100	/* Slot implemented */
+#define PCI_EXP_FLAGS_IRQ	0x3e00	/* Interrupt message number */
+#define PCI_EXP_DEVCAP		4	/* Device capabilities */
+#define  PCI_EXP_DEVCAP_PAYLOAD	0x00000007 /* Max_Payload_Size */
+#define  PCI_EXP_DEVCAP_PHANTOM	0x00000018 /* Phantom functions */
+#define  PCI_EXP_DEVCAP_EXT_TAG	0x00000020 /* Extended tags */
+#define  PCI_EXP_DEVCAP_L0S	0x000001c0 /* L0s Acceptable Latency */
+#define  PCI_EXP_DEVCAP_L1	0x00000e00 /* L1 Acceptable Latency */
+#define  PCI_EXP_DEVCAP_ATN_BUT	0x00001000 /* Attention Button Present */
+#define  PCI_EXP_DEVCAP_ATN_IND	0x00002000 /* Attention Indicator Present */
+#define  PCI_EXP_DEVCAP_PWR_IND	0x00004000 /* Power Indicator Present */
+#define  PCI_EXP_DEVCAP_RBER	0x00008000 /* Role-Based Error Reporting */
+#define  PCI_EXP_DEVCAP_PWR_VAL	0x03fc0000 /* Slot Power Limit Value */
+#define  PCI_EXP_DEVCAP_PWR_SCL	0x0c000000 /* Slot Power Limit Scale */
+#define  PCI_EXP_DEVCAP_FLR     0x10000000 /* Function Level Reset */
+#define PCI_EXP_DEVCTL		8	/* Device Control */
+#define  PCI_EXP_DEVCTL_CERE	0x0001	/* Correctable Error Reporting En. */
+#define  PCI_EXP_DEVCTL_NFERE	0x0002	/* Non-Fatal Error Reporting Enable */
+#define  PCI_EXP_DEVCTL_FERE	0x0004	/* Fatal Error Reporting Enable */
+#define  PCI_EXP_DEVCTL_URRE	0x0008	/* Unsupported Request Reporting En. */
+#define  PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */
+#define  PCI_EXP_DEVCTL_PAYLOAD	0x00e0	/* Max_Payload_Size */
+#define  PCI_EXP_DEVCTL_EXT_TAG	0x0100	/* Extended Tag Field Enable */
+#define  PCI_EXP_DEVCTL_PHANTOM	0x0200	/* Phantom Functions Enable */
+#define  PCI_EXP_DEVCTL_AUX_PME	0x0400	/* Auxiliary Power PM Enable */
+#define  PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800  /* Enable No Snoop */
+#define  PCI_EXP_DEVCTL_READRQ	0x7000	/* Max_Read_Request_Size */
+#define  PCI_EXP_DEVCTL_READRQ_128B  0x0000 /* 128 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_256B  0x1000 /* 256 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_512B  0x2000 /* 512 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_1024B 0x3000 /* 1024 Bytes */
+#define  PCI_EXP_DEVCTL_BCR_FLR 0x8000  /* Bridge Configuration Retry / FLR */
+#define PCI_EXP_DEVSTA		10	/* Device Status */
+#define  PCI_EXP_DEVSTA_CED	0x0001	/* Correctable Error Detected */
+#define  PCI_EXP_DEVSTA_NFED	0x0002	/* Non-Fatal Error Detected */
+#define  PCI_EXP_DEVSTA_FED	0x0004	/* Fatal Error Detected */
+#define  PCI_EXP_DEVSTA_URD	0x0008	/* Unsupported Request Detected */
+#define  PCI_EXP_DEVSTA_AUXPD	0x0010	/* AUX Power Detected */
+#define  PCI_EXP_DEVSTA_TRPND	0x0020	/* Transactions Pending */
+#define PCI_EXP_LNKCAP		12	/* Link Capabilities */
+#define  PCI_EXP_LNKCAP_SLS	0x0000000f /* Supported Link Speeds */
+#define  PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */
+#define  PCI_EXP_LNKCAP_SLS_5_0GB 0x00000002 /* LNKCAP2 SLS Vector bit 1 */
+#define  PCI_EXP_LNKCAP_MLW	0x000003f0 /* Maximum Link Width */
+#define  PCI_EXP_LNKCAP_ASPMS	0x00000c00 /* ASPM Support */
+#define  PCI_EXP_LNKCAP_L0SEL	0x00007000 /* L0s Exit Latency */
+#define  PCI_EXP_LNKCAP_L1EL	0x00038000 /* L1 Exit Latency */
+#define  PCI_EXP_LNKCAP_CLKPM	0x00040000 /* Clock Power Management */
+#define  PCI_EXP_LNKCAP_SDERC	0x00080000 /* Surprise Down Error Reporting Capable */
+#define  PCI_EXP_LNKCAP_DLLLARC	0x00100000 /* Data Link Layer Link Active Reporting Capable */
+#define  PCI_EXP_LNKCAP_LBNC	0x00200000 /* Link Bandwidth Notification Capability */
+#define  PCI_EXP_LNKCAP_PN	0xff000000 /* Port Number */
+#define PCI_EXP_LNKCTL		16	/* Link Control */
+#define  PCI_EXP_LNKCTL_ASPMC	0x0003	/* ASPM Control */
+#define  PCI_EXP_LNKCTL_ASPM_L0S 0x0001	/* L0s Enable */
+#define  PCI_EXP_LNKCTL_ASPM_L1  0x0002	/* L1 Enable */
+#define  PCI_EXP_LNKCTL_RCB	0x0008	/* Read Completion Boundary */
+#define  PCI_EXP_LNKCTL_LD	0x0010	/* Link Disable */
+#define  PCI_EXP_LNKCTL_RL	0x0020	/* Retrain Link */
+#define  PCI_EXP_LNKCTL_CCC	0x0040	/* Common Clock Configuration */
+#define  PCI_EXP_LNKCTL_ES	0x0080	/* Extended Synch */
+#define  PCI_EXP_LNKCTL_CLKREQ_EN 0x0100 /* Enable clkreq */
+#define  PCI_EXP_LNKCTL_HAWD	0x0200	/* Hardware Autonomous Width Disable */
+#define  PCI_EXP_LNKCTL_LBMIE	0x0400	/* Link Bandwidth Management Interrupt Enable */
+#define  PCI_EXP_LNKCTL_LABIE	0x0800	/* Link Autonomous Bandwidth Interrupt Enable */
+#define PCI_EXP_LNKSTA		18	/* Link Status */
+#define  PCI_EXP_LNKSTA_CLS	0x000f	/* Current Link Speed */
+#define  PCI_EXP_LNKSTA_CLS_2_5GB 0x0001 /* Current Link Speed 2.5GT/s */
+#define  PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */
+#define  PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */
+#define  PCI_EXP_LNKSTA_NLW	0x03f0	/* Negotiated Link Width */
+#define  PCI_EXP_LNKSTA_NLW_X1	0x0010	/* Current Link Width x1 */
+#define  PCI_EXP_LNKSTA_NLW_X2	0x0020	/* Current Link Width x2 */
+#define  PCI_EXP_LNKSTA_NLW_X4	0x0040	/* Current Link Width x4 */
+#define  PCI_EXP_LNKSTA_NLW_X8	0x0080	/* Current Link Width x8 */
+#define  PCI_EXP_LNKSTA_NLW_SHIFT 4	/* start of NLW mask in link status */
+#define  PCI_EXP_LNKSTA_LT	0x0800	/* Link Training */
+#define  PCI_EXP_LNKSTA_SLC	0x1000	/* Slot Clock Configuration */
+#define  PCI_EXP_LNKSTA_DLLLA	0x2000	/* Data Link Layer Link Active */
+#define  PCI_EXP_LNKSTA_LBMS	0x4000	/* Link Bandwidth Management Status */
+#define  PCI_EXP_LNKSTA_LABS	0x8000	/* Link Autonomous Bandwidth Status */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1	20	/* v1 endpoints end here */
+#define PCI_EXP_SLTCAP		20	/* Slot Capabilities */
+#define  PCI_EXP_SLTCAP_ABP	0x00000001 /* Attention Button Present */
+#define  PCI_EXP_SLTCAP_PCP	0x00000002 /* Power Controller Present */
+#define  PCI_EXP_SLTCAP_MRLSP	0x00000004 /* MRL Sensor Present */
+#define  PCI_EXP_SLTCAP_AIP	0x00000008 /* Attention Indicator Present */
+#define  PCI_EXP_SLTCAP_PIP	0x00000010 /* Power Indicator Present */
+#define  PCI_EXP_SLTCAP_HPS	0x00000020 /* Hot-Plug Surprise */
+#define  PCI_EXP_SLTCAP_HPC	0x00000040 /* Hot-Plug Capable */
+#define  PCI_EXP_SLTCAP_SPLV	0x00007f80 /* Slot Power Limit Value */
+#define  PCI_EXP_SLTCAP_SPLS	0x00018000 /* Slot Power Limit Scale */
+#define  PCI_EXP_SLTCAP_EIP	0x00020000 /* Electromechanical Interlock Present */
+#define  PCI_EXP_SLTCAP_NCCS	0x00040000 /* No Command Completed Support */
+#define  PCI_EXP_SLTCAP_PSN	0xfff80000 /* Physical Slot Number */
+#define PCI_EXP_SLTCTL		24	/* Slot Control */
+#define  PCI_EXP_SLTCTL_ABPE	0x0001	/* Attention Button Pressed Enable */
+#define  PCI_EXP_SLTCTL_PFDE	0x0002	/* Power Fault Detected Enable */
+#define  PCI_EXP_SLTCTL_MRLSCE	0x0004	/* MRL Sensor Changed Enable */
+#define  PCI_EXP_SLTCTL_PDCE	0x0008	/* Presence Detect Changed Enable */
+#define  PCI_EXP_SLTCTL_CCIE	0x0010	/* Command Completed Interrupt Enable */
+#define  PCI_EXP_SLTCTL_HPIE	0x0020	/* Hot-Plug Interrupt Enable */
+#define  PCI_EXP_SLTCTL_AIC	0x00c0	/* Attention Indicator Control */
+#define  PCI_EXP_SLTCTL_ATTN_IND_ON    0x0040 /* Attention Indicator on */
+#define  PCI_EXP_SLTCTL_ATTN_IND_BLINK 0x0080 /* Attention Indicator blinking */
+#define  PCI_EXP_SLTCTL_ATTN_IND_OFF   0x00c0 /* Attention Indicator off */
+#define  PCI_EXP_SLTCTL_PIC	0x0300	/* Power Indicator Control */
+#define  PCI_EXP_SLTCTL_PWR_IND_ON     0x0100 /* Power Indicator on */
+#define  PCI_EXP_SLTCTL_PWR_IND_BLINK  0x0200 /* Power Indicator blinking */
+#define  PCI_EXP_SLTCTL_PWR_IND_OFF    0x0300 /* Power Indicator off */
+#define  PCI_EXP_SLTCTL_PCC	0x0400	/* Power Controller Control */
+#define  PCI_EXP_SLTCTL_PWR_ON         0x0000 /* Power On */
+#define  PCI_EXP_SLTCTL_PWR_OFF        0x0400 /* Power Off */
+#define  PCI_EXP_SLTCTL_EIC	0x0800	/* Electromechanical Interlock Control */
+#define  PCI_EXP_SLTCTL_DLLSCE	0x1000	/* Data Link Layer State Changed Enable */
+#define PCI_EXP_SLTSTA		26	/* Slot Status */
+#define  PCI_EXP_SLTSTA_ABP	0x0001	/* Attention Button Pressed */
+#define  PCI_EXP_SLTSTA_PFD	0x0002	/* Power Fault Detected */
+#define  PCI_EXP_SLTSTA_MRLSC	0x0004	/* MRL Sensor Changed */
+#define  PCI_EXP_SLTSTA_PDC	0x0008	/* Presence Detect Changed */
+#define  PCI_EXP_SLTSTA_CC	0x0010	/* Command Completed */
+#define  PCI_EXP_SLTSTA_MRLSS	0x0020	/* MRL Sensor State */
+#define  PCI_EXP_SLTSTA_PDS	0x0040	/* Presence Detect State */
+#define  PCI_EXP_SLTSTA_EIS	0x0080	/* Electromechanical Interlock Status */
+#define  PCI_EXP_SLTSTA_DLLSC	0x0100	/* Data Link Layer State Changed */
+#define PCI_EXP_RTCTL		28	/* Root Control */
+#define  PCI_EXP_RTCTL_SECEE	0x0001	/* System Error on Correctable Error */
+#define  PCI_EXP_RTCTL_SENFEE	0x0002	/* System Error on Non-Fatal Error */
+#define  PCI_EXP_RTCTL_SEFEE	0x0004	/* System Error on Fatal Error */
+#define  PCI_EXP_RTCTL_PMEIE	0x0008	/* PME Interrupt Enable */
+#define  PCI_EXP_RTCTL_CRSSVE	0x0010	/* CRS Software Visibility Enable */
+#define PCI_EXP_RTCAP		30	/* Root Capabilities */
+#define  PCI_EXP_RTCAP_CRSVIS	0x0001	/* CRS Software Visibility capability */
+#define PCI_EXP_RTSTA		32	/* Root Status */
+#define PCI_EXP_RTSTA_PME	0x00010000 /* PME status */
+#define PCI_EXP_RTSTA_PENDING	0x00020000 /* PME pending */
+/*
+ * The Device Capabilities 2, Device Status 2, Device Control 2,
+ * Link Capabilities 2, Link Status 2, Link Control 2,
+ * Slot Capabilities 2, Slot Status 2, and Slot Control 2 registers
+ * are only present on devices with PCIe Capability version 2.
+ * Use pcie_capability_read_word() and similar interfaces to use them
+ * safely.
+ */
+#define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
+#define  PCI_EXP_DEVCAP2_ARI		0x00000020 /* Alternative Routing-ID */
+#define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
+#define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
+#define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
+#define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
+#define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
+#define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
+#define  PCI_EXP_DEVCTL2_ARI		0x0020	/* Alternative Routing-ID */
+#define  PCI_EXP_DEVCTL2_IDO_REQ_EN	0x0100	/* Allow IDO for requests */
+#define  PCI_EXP_DEVCTL2_IDO_CMP_EN	0x0200	/* Allow IDO for completions */
+#define  PCI_EXP_DEVCTL2_LTR_EN		0x0400	/* Enable LTR mechanism */
+#define  PCI_EXP_DEVCTL2_OBFF_MSGA_EN	0x2000	/* Enable OBFF Message type A */
+#define  PCI_EXP_DEVCTL2_OBFF_MSGB_EN	0x4000	/* Enable OBFF Message type B */
+#define  PCI_EXP_DEVCTL2_OBFF_WAKE_EN	0x6000	/* OBFF using WAKE# signaling */
+#define PCI_EXP_DEVSTA2		42	/* Device Status 2 */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	44	/* v2 endpoints end here */
+#define PCI_EXP_LNKCAP2		44	/* Link Capabilities 2 */
+#define  PCI_EXP_LNKCAP2_SLS_2_5GB	0x00000002 /* Supported Speed 2.5GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_5_0GB	0x00000004 /* Supported Speed 5.0GT/s */
+#define  PCI_EXP_LNKCAP2_SLS_8_0GB	0x00000008 /* Supported Speed 8.0GT/s */
+#define  PCI_EXP_LNKCAP2_CROSSLINK	0x00000100 /* Crosslink supported */
+#define PCI_EXP_LNKCTL2		48	/* Link Control 2 */
+#define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
+#define PCI_EXP_SLTCAP2		52	/* Slot Capabilities 2 */
+#define PCI_EXP_SLTCTL2		56	/* Slot Control 2 */
+#define PCI_EXP_SLTSTA2		58	/* Slot Status 2 */
+
+/* Extended Capabilities (PCI-X 2.0 and Express) */
+#define PCI_EXT_CAP_ID(header)		(header & 0x0000ffff)
+#define PCI_EXT_CAP_VER(header)		((header >> 16) & 0xf)
+#define PCI_EXT_CAP_NEXT(header)	((header >> 20) & 0xffc)
+
+#define PCI_EXT_CAP_ID_ERR	0x01	/* Advanced Error Reporting */
+#define PCI_EXT_CAP_ID_VC	0x02	/* Virtual Channel Capability */
+#define PCI_EXT_CAP_ID_DSN	0x03	/* Device Serial Number */
+#define PCI_EXT_CAP_ID_PWR	0x04	/* Power Budgeting */
+#define PCI_EXT_CAP_ID_RCLD	0x05	/* Root Complex Link Declaration */
+#define PCI_EXT_CAP_ID_RCILC	0x06	/* Root Complex Internal Link Control */
+#define PCI_EXT_CAP_ID_RCEC	0x07	/* Root Complex Event Collector */
+#define PCI_EXT_CAP_ID_MFVC	0x08	/* Multi-Function VC Capability */
+#define PCI_EXT_CAP_ID_VC9	0x09	/* same as _VC */
+#define PCI_EXT_CAP_ID_RCRB	0x0A	/* Root Complex RB? */
+#define PCI_EXT_CAP_ID_VNDR	0x0B	/* Vendor-Specific */
+#define PCI_EXT_CAP_ID_CAC	0x0C	/* Config Access - obsolete */
+#define PCI_EXT_CAP_ID_ACS	0x0D	/* Access Control Services */
+#define PCI_EXT_CAP_ID_ARI	0x0E	/* Alternate Routing ID */
+#define PCI_EXT_CAP_ID_ATS	0x0F	/* Address Translation Services */
+#define PCI_EXT_CAP_ID_SRIOV	0x10	/* Single Root I/O Virtualization */
+#define PCI_EXT_CAP_ID_MRIOV	0x11	/* Multi Root I/O Virtualization */
+#define PCI_EXT_CAP_ID_MCAST	0x12	/* Multicast */
+#define PCI_EXT_CAP_ID_PRI	0x13	/* Page Request Interface */
+#define PCI_EXT_CAP_ID_AMD_XXX	0x14	/* Reserved for AMD */
+#define PCI_EXT_CAP_ID_REBAR	0x15	/* Resizable BAR */
+#define PCI_EXT_CAP_ID_DPA	0x16	/* Dynamic Power Allocation */
+#define PCI_EXT_CAP_ID_TPH	0x17	/* TPH Requester */
+#define PCI_EXT_CAP_ID_LTR	0x18	/* Latency Tolerance Reporting */
+#define PCI_EXT_CAP_ID_SECPCI	0x19	/* Secondary PCIe Capability */
+#define PCI_EXT_CAP_ID_PMUX	0x1A	/* Protocol Multiplexing */
+#define PCI_EXT_CAP_ID_PASID	0x1B	/* Process Address Space ID */
+#define PCI_EXT_CAP_ID_MAX	PCI_EXT_CAP_ID_PASID
+
+#define PCI_EXT_CAP_DSN_SIZEOF	12
+#define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40
+
+/* Advanced Error Reporting */
+#define PCI_ERR_UNCOR_STATUS	4	/* Uncorrectable Error Status */
+#define  PCI_ERR_UNC_UND	0x00000001	/* Undefined */
+#define  PCI_ERR_UNC_DLP	0x00000010	/* Data Link Protocol */
+#define  PCI_ERR_UNC_SURPDN	0x00000020	/* Surprise Down */
+#define  PCI_ERR_UNC_POISON_TLP	0x00001000	/* Poisoned TLP */
+#define  PCI_ERR_UNC_FCP	0x00002000	/* Flow Control Protocol */
+#define  PCI_ERR_UNC_COMP_TIME	0x00004000	/* Completion Timeout */
+#define  PCI_ERR_UNC_COMP_ABORT	0x00008000	/* Completer Abort */
+#define  PCI_ERR_UNC_UNX_COMP	0x00010000	/* Unexpected Completion */
+#define  PCI_ERR_UNC_RX_OVER	0x00020000	/* Receiver Overflow */
+#define  PCI_ERR_UNC_MALF_TLP	0x00040000	/* Malformed TLP */
+#define  PCI_ERR_UNC_ECRC	0x00080000	/* ECRC Error Status */
+#define  PCI_ERR_UNC_UNSUP	0x00100000	/* Unsupported Request */
+#define  PCI_ERR_UNC_ACSV	0x00200000	/* ACS Violation */
+#define  PCI_ERR_UNC_INTN	0x00400000	/* internal error */
+#define  PCI_ERR_UNC_MCBTLP	0x00800000	/* MC blocked TLP */
+#define  PCI_ERR_UNC_ATOMEG	0x01000000	/* Atomic egress blocked */
+#define  PCI_ERR_UNC_TLPPRE	0x02000000	/* TLP prefix blocked */
+#define PCI_ERR_UNCOR_MASK	8	/* Uncorrectable Error Mask */
+	/* Same bits as above */
+#define PCI_ERR_UNCOR_SEVER	12	/* Uncorrectable Error Severity */
+	/* Same bits as above */
+#define PCI_ERR_COR_STATUS	16	/* Correctable Error Status */
+#define  PCI_ERR_COR_RCVR	0x00000001	/* Receiver Error Status */
+#define  PCI_ERR_COR_BAD_TLP	0x00000040	/* Bad TLP Status */
+#define  PCI_ERR_COR_BAD_DLLP	0x00000080	/* Bad DLLP Status */
+#define  PCI_ERR_COR_REP_ROLL	0x00000100	/* REPLAY_NUM Rollover */
+#define  PCI_ERR_COR_REP_TIMER	0x00001000	/* Replay Timer Timeout */
+#define  PCI_ERR_COR_ADV_NFAT	0x00002000	/* Advisory Non-Fatal */
+#define  PCI_ERR_COR_INTERNAL	0x00004000	/* Corrected Internal */
+#define  PCI_ERR_COR_LOG_OVER	0x00008000	/* Header Log Overflow */
+#define PCI_ERR_COR_MASK	20	/* Correctable Error Mask */
+	/* Same bits as above */
+#define PCI_ERR_CAP		24	/* Advanced Error Capabilities */
+#define  PCI_ERR_CAP_FEP(x)	((x) & 31)	/* First Error Pointer */
+#define  PCI_ERR_CAP_ECRC_GENC	0x00000020	/* ECRC Generation Capable */
+#define  PCI_ERR_CAP_ECRC_GENE	0x00000040	/* ECRC Generation Enable */
+#define  PCI_ERR_CAP_ECRC_CHKC	0x00000080	/* ECRC Check Capable */
+#define  PCI_ERR_CAP_ECRC_CHKE	0x00000100	/* ECRC Check Enable */
+#define PCI_ERR_HEADER_LOG	28	/* Header Log Register (16 bytes) */
+#define PCI_ERR_ROOT_COMMAND	44	/* Root Error Command */
+/* Correctable Err Reporting Enable */
+#define PCI_ERR_ROOT_CMD_COR_EN		0x00000001
+/* Non-fatal Err Reporting Enable */
+#define PCI_ERR_ROOT_CMD_NONFATAL_EN	0x00000002
+/* Fatal Err Reporting Enable */
+#define PCI_ERR_ROOT_CMD_FATAL_EN	0x00000004
+#define PCI_ERR_ROOT_STATUS	48
+#define PCI_ERR_ROOT_COR_RCV		0x00000001	/* ERR_COR Received */
+/* Multi ERR_COR Received */
+#define PCI_ERR_ROOT_MULTI_COR_RCV	0x00000002
+/* ERR_FATAL/NONFATAL Received */
+#define PCI_ERR_ROOT_UNCOR_RCV		0x00000004
+/* Multi ERR_FATAL/NONFATAL Received */
+#define PCI_ERR_ROOT_MULTI_UNCOR_RCV	0x00000008
+#define PCI_ERR_ROOT_FIRST_FATAL	0x00000010	/* First Fatal */
+#define PCI_ERR_ROOT_NONFATAL_RCV	0x00000020	/* Non-Fatal Received */
+#define PCI_ERR_ROOT_FATAL_RCV		0x00000040	/* Fatal Received */
+#define PCI_ERR_ROOT_ERR_SRC	52	/* Error Source Identification */
+
+/* Virtual Channel */
+#define PCI_VC_PORT_CAP1	4
+#define  PCI_VC_CAP1_EVCC	0x00000007	/* extended VC count */
+#define  PCI_VC_CAP1_LPEVCC	0x00000070	/* low prio extended VC count */
+#define  PCI_VC_CAP1_ARB_SIZE	0x00000c00
+#define PCI_VC_PORT_CAP2	8
+#define  PCI_VC_CAP2_32_PHASE		0x00000002
+#define  PCI_VC_CAP2_64_PHASE		0x00000004
+#define  PCI_VC_CAP2_128_PHASE		0x00000008
+#define  PCI_VC_CAP2_ARB_OFF		0xff000000
+#define PCI_VC_PORT_CTRL	12
+#define  PCI_VC_PORT_CTRL_LOAD_TABLE	0x00000001
+#define PCI_VC_PORT_STATUS	14
+#define  PCI_VC_PORT_STATUS_TABLE	0x00000001
+#define PCI_VC_RES_CAP		16
+#define  PCI_VC_RES_CAP_32_PHASE	0x00000002
+#define  PCI_VC_RES_CAP_64_PHASE	0x00000004
+#define  PCI_VC_RES_CAP_128_PHASE	0x00000008
+#define  PCI_VC_RES_CAP_128_PHASE_TB	0x00000010
+#define  PCI_VC_RES_CAP_256_PHASE	0x00000020
+#define  PCI_VC_RES_CAP_ARB_OFF		0xff000000
+#define PCI_VC_RES_CTRL		20
+#define  PCI_VC_RES_CTRL_LOAD_TABLE	0x00010000
+#define  PCI_VC_RES_CTRL_ARB_SELECT	0x000e0000
+#define  PCI_VC_RES_CTRL_ID		0x07000000
+#define  PCI_VC_RES_CTRL_ENABLE		0x80000000
+#define PCI_VC_RES_STATUS	26
+#define  PCI_VC_RES_STATUS_TABLE	0x00000001
+#define  PCI_VC_RES_STATUS_NEGO		0x00000002
+#define PCI_CAP_VC_BASE_SIZEOF		0x10
+#define PCI_CAP_VC_PER_VC_SIZEOF	0x0C
+
+/* Power Budgeting */
+#define PCI_PWR_DSR		4	/* Data Select Register */
+#define PCI_PWR_DATA		8	/* Data Register */
+#define  PCI_PWR_DATA_BASE(x)	((x) & 0xff)	    /* Base Power */
+#define  PCI_PWR_DATA_SCALE(x)	(((x) >> 8) & 3)    /* Data Scale */
+#define  PCI_PWR_DATA_PM_SUB(x)	(((x) >> 10) & 7)   /* PM Sub State */
+#define  PCI_PWR_DATA_PM_STATE(x) (((x) >> 13) & 3) /* PM State */
+#define  PCI_PWR_DATA_TYPE(x)	(((x) >> 15) & 7)   /* Type */
+#define  PCI_PWR_DATA_RAIL(x)	(((x) >> 18) & 7)   /* Power Rail */
+#define PCI_PWR_CAP		12	/* Capability */
+#define  PCI_PWR_CAP_BUDGET(x)	((x) & 1)	/* Included in system budget */
+#define PCI_EXT_CAP_PWR_SIZEOF	16
+
+/* Vendor-Specific (VSEC, PCI_EXT_CAP_ID_VNDR) */
+#define PCI_VNDR_HEADER		4	/* Vendor-Specific Header */
+#define  PCI_VNDR_HEADER_ID(x)	((x) & 0xffff)
+#define  PCI_VNDR_HEADER_REV(x)	(((x) >> 16) & 0xf)
+#define  PCI_VNDR_HEADER_LEN(x)	(((x) >> 20) & 0xfff)
+
+/*
+ * HyperTransport sub capability types
+ *
+ * Unfortunately there are both 3 bit and 5 bit capability types defined
+ * in the HT spec, catering for that is a little messy. You probably don't
+ * want to use these directly, just use pci_find_ht_capability() and it
+ * will do the right thing for you.
+ */
+#define HT_3BIT_CAP_MASK	0xE0
+#define HT_CAPTYPE_SLAVE	0x00	/* Slave/Primary link configuration */
+#define HT_CAPTYPE_HOST		0x20	/* Host/Secondary link configuration */
+
+#define HT_5BIT_CAP_MASK	0xF8
+#define HT_CAPTYPE_IRQ		0x80	/* IRQ Configuration */
+#define HT_CAPTYPE_REMAPPING_40	0xA0	/* 40 bit address remapping */
+#define HT_CAPTYPE_REMAPPING_64 0xA2	/* 64 bit address remapping */
+#define HT_CAPTYPE_UNITID_CLUMP	0x90	/* Unit ID clumping */
+#define HT_CAPTYPE_EXTCONF	0x98	/* Extended Configuration Space Access */
+#define HT_CAPTYPE_MSI_MAPPING	0xA8	/* MSI Mapping Capability */
+#define  HT_MSI_FLAGS		0x02		/* Offset to flags */
+#define  HT_MSI_FLAGS_ENABLE	0x1		/* Mapping enable */
+#define  HT_MSI_FLAGS_FIXED	0x2		/* Fixed mapping only */
+#define  HT_MSI_FIXED_ADDR	0x00000000FEE00000ULL	/* Fixed addr */
+#define  HT_MSI_ADDR_LO		0x04		/* Offset to low addr bits */
+#define  HT_MSI_ADDR_LO_MASK	0xFFF00000	/* Low address bit mask */
+#define  HT_MSI_ADDR_HI		0x08		/* Offset to high addr bits */
+#define HT_CAPTYPE_DIRECT_ROUTE	0xB0	/* Direct routing configuration */
+#define HT_CAPTYPE_VCSET	0xB8	/* Virtual Channel configuration */
+#define HT_CAPTYPE_ERROR_RETRY	0xC0	/* Retry on error configuration */
+#define HT_CAPTYPE_GEN3		0xD0	/* Generation 3 HyperTransport configuration */
+#define HT_CAPTYPE_PM		0xE0	/* HyperTransport power management configuration */
+#define HT_CAP_SIZEOF_LONG	28	/* slave & primary */
+#define HT_CAP_SIZEOF_SHORT	24	/* host & secondary */
+
+/* Alternative Routing-ID Interpretation */
+#define PCI_ARI_CAP		0x04	/* ARI Capability Register */
+#define  PCI_ARI_CAP_MFVC	0x0001	/* MFVC Function Groups Capability */
+#define  PCI_ARI_CAP_ACS	0x0002	/* ACS Function Groups Capability */
+#define  PCI_ARI_CAP_NFN(x)	(((x) >> 8) & 0xff) /* Next Function Number */
+#define PCI_ARI_CTRL		0x06	/* ARI Control Register */
+#define  PCI_ARI_CTRL_MFVC	0x0001	/* MFVC Function Groups Enable */
+#define  PCI_ARI_CTRL_ACS	0x0002	/* ACS Function Groups Enable */
+#define  PCI_ARI_CTRL_FG(x)	(((x) >> 4) & 7) /* Function Group */
+#define PCI_EXT_CAP_ARI_SIZEOF	8
+
+/* Address Translation Service */
+#define PCI_ATS_CAP		0x04	/* ATS Capability Register */
+#define  PCI_ATS_CAP_QDEP(x)	((x) & 0x1f)	/* Invalidate Queue Depth */
+#define  PCI_ATS_MAX_QDEP	32	/* Max Invalidate Queue Depth */
+#define PCI_ATS_CTRL		0x06	/* ATS Control Register */
+#define  PCI_ATS_CTRL_ENABLE	0x8000	/* ATS Enable */
+#define  PCI_ATS_CTRL_STU(x)	((x) & 0x1f)	/* Smallest Translation Unit */
+#define  PCI_ATS_MIN_STU	12	/* shift of minimum STU block */
+#define PCI_EXT_CAP_ATS_SIZEOF	8
+
+/* Page Request Interface */
+#define PCI_PRI_CTRL		0x04	/* PRI control register */
+#define  PCI_PRI_CTRL_ENABLE	0x01	/* Enable */
+#define  PCI_PRI_CTRL_RESET	0x02	/* Reset */
+#define PCI_PRI_STATUS		0x06	/* PRI status register */
+#define  PCI_PRI_STATUS_RF	0x001	/* Response Failure */
+#define  PCI_PRI_STATUS_UPRGI	0x002	/* Unexpected PRG index */
+#define  PCI_PRI_STATUS_STOPPED	0x100	/* PRI Stopped */
+#define PCI_PRI_MAX_REQ		0x08	/* PRI max reqs supported */
+#define PCI_PRI_ALLOC_REQ	0x0c	/* PRI max reqs allowed */
+#define PCI_EXT_CAP_PRI_SIZEOF	16
+
+/* Process Address Space ID */
+#define PCI_PASID_CAP		0x04    /* PASID feature register */
+#define  PCI_PASID_CAP_EXEC	0x02	/* Exec permissions Supported */
+#define  PCI_PASID_CAP_PRIV	0x04	/* Privilege Mode Supported */
+#define PCI_PASID_CTRL		0x06    /* PASID control register */
+#define  PCI_PASID_CTRL_ENABLE	0x01	/* Enable bit */
+#define  PCI_PASID_CTRL_EXEC	0x02	/* Exec permissions Enable */
+#define  PCI_PASID_CTRL_PRIV	0x04	/* Privilege Mode Enable */
+#define PCI_EXT_CAP_PASID_SIZEOF	8
+
+/* Single Root I/O Virtualization */
+#define PCI_SRIOV_CAP		0x04	/* SR-IOV Capabilities */
+#define  PCI_SRIOV_CAP_VFM	0x01	/* VF Migration Capable */
+#define  PCI_SRIOV_CAP_INTR(x)	((x) >> 21) /* Interrupt Message Number */
+#define PCI_SRIOV_CTRL		0x08	/* SR-IOV Control */
+#define  PCI_SRIOV_CTRL_VFE	0x01	/* VF Enable */
+#define  PCI_SRIOV_CTRL_VFM	0x02	/* VF Migration Enable */
+#define  PCI_SRIOV_CTRL_INTR	0x04	/* VF Migration Interrupt Enable */
+#define  PCI_SRIOV_CTRL_MSE	0x08	/* VF Memory Space Enable */
+#define  PCI_SRIOV_CTRL_ARI	0x10	/* ARI Capable Hierarchy */
+#define PCI_SRIOV_STATUS	0x0a	/* SR-IOV Status */
+#define  PCI_SRIOV_STATUS_VFM	0x01	/* VF Migration Status */
+#define PCI_SRIOV_INITIAL_VF	0x0c	/* Initial VFs */
+#define PCI_SRIOV_TOTAL_VF	0x0e	/* Total VFs */
+#define PCI_SRIOV_NUM_VF	0x10	/* Number of VFs */
+#define PCI_SRIOV_FUNC_LINK	0x12	/* Function Dependency Link */
+#define PCI_SRIOV_VF_OFFSET	0x14	/* First VF Offset */
+#define PCI_SRIOV_VF_STRIDE	0x16	/* Following VF Stride */
+#define PCI_SRIOV_VF_DID	0x1a	/* VF Device ID */
+#define PCI_SRIOV_SUP_PGSIZE	0x1c	/* Supported Page Sizes */
+#define PCI_SRIOV_SYS_PGSIZE	0x20	/* System Page Size */
+#define PCI_SRIOV_BAR		0x24	/* VF BAR0 */
+#define  PCI_SRIOV_NUM_BARS	6	/* Number of VF BARs */
+#define PCI_SRIOV_VFM		0x3c	/* VF Migration State Array Offset*/
+#define  PCI_SRIOV_VFM_BIR(x)	((x) & 7)	/* State BIR */
+#define  PCI_SRIOV_VFM_OFFSET(x) ((x) & ~7)	/* State Offset */
+#define  PCI_SRIOV_VFM_UA	0x0	/* Inactive.Unavailable */
+#define  PCI_SRIOV_VFM_MI	0x1	/* Dormant.MigrateIn */
+#define  PCI_SRIOV_VFM_MO	0x2	/* Active.MigrateOut */
+#define  PCI_SRIOV_VFM_AV	0x3	/* Active.Available */
+#define PCI_EXT_CAP_SRIOV_SIZEOF 64
+
+#define PCI_LTR_MAX_SNOOP_LAT	0x4
+#define PCI_LTR_MAX_NOSNOOP_LAT	0x6
+#define  PCI_LTR_VALUE_MASK	0x000003ff
+#define  PCI_LTR_SCALE_MASK	0x00001c00
+#define  PCI_LTR_SCALE_SHIFT	10
+#define PCI_EXT_CAP_LTR_SIZEOF	8
+
+/* Access Control Service */
+#define PCI_ACS_CAP		0x04	/* ACS Capability Register */
+#define  PCI_ACS_SV		0x01	/* Source Validation */
+#define  PCI_ACS_TB		0x02	/* Translation Blocking */
+#define  PCI_ACS_RR		0x04	/* P2P Request Redirect */
+#define  PCI_ACS_CR		0x08	/* P2P Completion Redirect */
+#define  PCI_ACS_UF		0x10	/* Upstream Forwarding */
+#define  PCI_ACS_EC		0x20	/* P2P Egress Control */
+#define  PCI_ACS_DT		0x40	/* Direct Translated P2P */
+#define PCI_ACS_EGRESS_BITS	0x05	/* ACS Egress Control Vector Size */
+#define PCI_ACS_CTRL		0x06	/* ACS Control Register */
+#define PCI_ACS_EGRESS_CTL_V	0x08	/* ACS Egress Control Vector */
+
+#define PCI_VSEC_HDR		4	/* extended cap - vendor-specific */
+#define  PCI_VSEC_HDR_LEN_SHIFT	20	/* shift for length field */
+
+/* SATA capability */
+#define PCI_SATA_REGS		4	/* SATA REGs specifier */
+#define  PCI_SATA_REGS_MASK	0xF	/* location - BAR#/inline */
+#define  PCI_SATA_REGS_INLINE	0xF	/* REGS in config space */
+#define PCI_SATA_SIZEOF_SHORT	8
+#define PCI_SATA_SIZEOF_LONG	16
+
+/* Resizable BARs */
+#define PCI_REBAR_CTRL		8	/* control register */
+#define  PCI_REBAR_CTRL_NBAR_MASK	(7 << 5)	/* mask for # bars */
+#define  PCI_REBAR_CTRL_NBAR_SHIFT	5	/* shift for # bars */
+
+/* Dynamic Power Allocation */
+#define PCI_DPA_CAP		4	/* capability register */
+#define  PCI_DPA_CAP_SUBSTATE_MASK	0x1F	/* # substates - 1 */
+#define PCI_DPA_BASE_SIZEOF	16	/* size with 0 substates */
+
+/* TPH Requester */
+#define PCI_TPH_CAP		4	/* capability register */
+#define  PCI_TPH_CAP_LOC_MASK	0x600	/* location mask */
+#define   PCI_TPH_LOC_NONE	0x000	/* no location */
+#define   PCI_TPH_LOC_CAP	0x200	/* in capability */
+#define   PCI_TPH_LOC_MSIX	0x400	/* in MSI-X */
+#define PCI_TPH_CAP_ST_MASK	0x07FF0000	/* st table mask */
+#define PCI_TPH_CAP_ST_SHIFT	16	/* st table shift */
+#define PCI_TPH_BASE_SIZEOF	12	/* size with no st table */
+
+#endif /* LINUX_PCI_REGS_H */

tests/kvm-unit-tests/lib/linux/psci.h

@@ -0,0 +1,108 @@
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <anup.patel@linaro.org>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE			0x84000000
+#define PSCI_0_2_FN(n)				(PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT				0x40000000
+#define PSCI_0_2_FN64_BASE			\
+					(PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n)			(PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION		PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND			PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF			PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON			PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO		PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE			PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE		PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU		PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF			PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET		PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND		PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON			PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO		PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE			PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
+
+#define PSCI_1_0_FN_PSCI_FEATURES		PSCI_0_2_FN(10)
+#define PSCI_1_0_FN_SYSTEM_SUSPEND		PSCI_0_2_FN(14)
+
+#define PSCI_1_0_FN64_SYSTEM_SUSPEND		PSCI_0_2_FN64(14)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT		0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT		16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK		\
+				(0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT		24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK		\
+				(0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI extended power state encoding for CPU_SUSPEND function */
+#define PSCI_1_0_EXT_POWER_STATE_ID_MASK	0xfffffff
+#define PSCI_1_0_EXT_POWER_STATE_ID_SHIFT	0
+#define PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT	30
+#define PSCI_1_0_EXT_POWER_STATE_TYPE_MASK	\
+				(0x1 << PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON		0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF		1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING	2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE			0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE		1
+#define PSCI_0_2_TOS_MP				2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT		16
+#define PSCI_VERSION_MINOR_MASK			\
+		((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK			~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver)			\
+		(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver)			\
+		((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI features decoding (>=1.0) */
+#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT	1
+#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK	\
+			(0x1 << PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS			0
+#define PSCI_RET_NOT_SUPPORTED			-1
+#define PSCI_RET_INVALID_PARAMS			-2
+#define PSCI_RET_DENIED				-3
+#define PSCI_RET_ALREADY_ON			-4
+#define PSCI_RET_ON_PENDING			-5
+#define PSCI_RET_INTERNAL_FAILURE		-6
+#define PSCI_RET_NOT_PRESENT			-7
+#define PSCI_RET_DISABLED			-8
+#define PSCI_RET_INVALID_ADDRESS		-9
+
+#endif /* _UAPI_LINUX_PSCI_H */

tests/kvm-unit-tests/lib/pci-edu.c

@@ -0,0 +1,73 @@
+/*
+ * Edu PCI device.
+ *
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * Authors:
+ *   Peter Xu <peterx@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or
+ * later.
+ */
+
+#include "pci-edu.h"
+#include "asm/barrier.h"
+
+/* Return true if alive */
+static inline bool edu_check_alive(struct pci_edu_dev *dev)
+{
+	static uint32_t live_count = 1;
+	uint32_t value;
+
+	edu_reg_writel(dev, EDU_REG_ALIVE, live_count++);
+	value = edu_reg_readl(dev, EDU_REG_ALIVE);
+	return (live_count - 1 == ~value);
+}
+
+bool edu_init(struct pci_edu_dev *dev)
+{
+	pcidevaddr_t dev_addr;
+
+	dev_addr = pci_find_dev(PCI_VENDOR_ID_QEMU, PCI_DEVICE_ID_EDU);
+	if (dev_addr == PCIDEVADDR_INVALID)
+		return false;
+
+	pci_dev_init(&dev->pci_dev, dev_addr);
+	pci_enable_defaults(&dev->pci_dev);
+	dev->reg_base = ioremap(dev->pci_dev.resource[EDU_BAR], PAGE_SIZE);
+	assert(edu_check_alive(dev));
+	return true;
+}
+
+void edu_dma(struct pci_edu_dev *dev, iova_t iova,
+	     size_t size, unsigned int dev_offset, bool from_device)
+{
+	uint64_t from, to;
+	uint32_t cmd = EDU_CMD_DMA_START;
+
+	assert(size <= EDU_DMA_SIZE_MAX);
+	assert(dev_offset < EDU_DMA_SIZE_MAX);
+
+	printf("edu device DMA start %s addr 0x%" PRIx64 " size 0x%lu off 0x%x\n",
+	       from_device ? "FROM" : "TO",
+	       iova, (ulong)size, dev_offset);
+
+	if (from_device) {
+		from = dev_offset + EDU_DMA_START;
+		to = iova;
+		cmd |= EDU_CMD_DMA_FROM;
+	} else {
+		from = iova;
+		to = EDU_DMA_START + dev_offset;
+		cmd |= EDU_CMD_DMA_TO;
+	}
+
+	edu_reg_writeq(dev, EDU_REG_DMA_SRC, from);
+	edu_reg_writeq(dev, EDU_REG_DMA_DST, to);
+	edu_reg_writeq(dev, EDU_REG_DMA_COUNT, size);
+	edu_reg_writel(dev, EDU_REG_DMA_CMD, cmd);
+
+	/* Wait until DMA finished */
+	while (edu_reg_readl(dev, EDU_REG_DMA_CMD) & EDU_CMD_DMA_START)
+		cpu_relax();
+}

tests/kvm-unit-tests/lib/pci-edu.h

@@ -0,0 +1,86 @@
+/*
+ * Edu PCI device header.
+ *
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * Authors:
+ *   Peter Xu <peterx@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or
+ * later.
+ *
+ * Edu device is a virtualized device in QEMU. Please refer to
+ * docs/specs/edu.txt in QEMU repository for EDU device manual.
+ */
+#ifndef __PCI_EDU_H__
+#define __PCI_EDU_H__
+
+#include "pci.h"
+#include "asm/io.h"
+
+#define  PCI_VENDOR_ID_QEMU              0x1234
+#define  PCI_DEVICE_ID_EDU               0x11e8
+
+/* The only bar used by EDU device */
+#define EDU_BAR                     0
+#define EDU_MAGIC                   0xed
+#define EDU_VERSION                 0x100
+#define EDU_DMA_BUF_SIZE            (1 << 20)
+#define EDU_INPUT_BUF_SIZE          256
+
+#define EDU_REG_ID                  0x0
+#define EDU_REG_ALIVE               0x4
+#define EDU_REG_FACTORIAL           0x8
+#define EDU_REG_STATUS              0x20
+#define EDU_REG_INTR_STATUS         0x24
+#define EDU_REG_INTR_RAISE          0x60
+#define EDU_REG_INTR_ACK            0x64
+#define EDU_REG_DMA_SRC             0x80
+#define EDU_REG_DMA_DST             0x88
+#define EDU_REG_DMA_COUNT           0x90
+#define EDU_REG_DMA_CMD             0x98
+
+#define EDU_CMD_DMA_START           0x01
+#define EDU_CMD_DMA_FROM            0x02
+#define EDU_CMD_DMA_TO              0x00
+
+#define EDU_STATUS_FACTORIAL        0x1
+#define EDU_STATUS_INT_ENABLE       0x80
+
+#define EDU_DMA_START               0x40000
+#define EDU_DMA_SIZE_MAX            4096
+
+struct pci_edu_dev {
+	struct pci_dev pci_dev;
+	volatile void *reg_base;
+};
+
+#define edu_reg(d, r) (volatile void *)((d)->reg_base + (r))
+
+static inline uint64_t edu_reg_readq(struct pci_edu_dev *dev, int reg)
+{
+	return __raw_readq(edu_reg(dev, reg));
+}
+
+static inline uint32_t edu_reg_readl(struct pci_edu_dev *dev, int reg)
+{
+	return __raw_readl(edu_reg(dev, reg));
+}
+
+static inline void edu_reg_writeq(struct pci_edu_dev *dev, int reg,
+				  uint64_t val)
+{
+	__raw_writeq(val, edu_reg(dev, reg));
+}
+
+static inline void edu_reg_writel(struct pci_edu_dev *dev, int reg,
+				  uint32_t val)
+{
+	__raw_writel(val, edu_reg(dev, reg));
+}
+
+bool edu_init(struct pci_edu_dev *dev);
+void edu_dma(struct pci_edu_dev *dev, iova_t iova,
+	     size_t size, unsigned int dev_offset, bool from_device);
+
+#endif

tests/kvm-unit-tests/lib/pci-host-generic.c

@@ -0,0 +1,320 @@
+/*
+ * Generic PCI host controller as described in PCI Bus Binding to Open Firmware
+ *
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "devicetree.h"
+#include "alloc.h"
+#include "pci.h"
+#include "asm/pci.h"
+#include "asm/io.h"
+#include "pci-host-generic.h"
+#include <linux/pci_regs.h>
+
+static struct pci_host_bridge *pci_host_bridge;
+
+static int of_flags_to_pci_type(u32 of_flags)
+{
+	static int type_map[] = {
+		[1] = PCI_BASE_ADDRESS_SPACE_IO,
+		[2] = PCI_BASE_ADDRESS_MEM_TYPE_32,
+		[3] = PCI_BASE_ADDRESS_MEM_TYPE_64
+	};
+	int idx = (of_flags >> 24) & 0x03;
+	int res;
+
+	assert(idx > 0);
+	res = type_map[idx];
+
+	if (of_flags & 0x40000000)
+		res |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+	return res;
+}
+
+static int pci_bar_type(u32 bar)
+{
+	if (bar & PCI_BASE_ADDRESS_SPACE)
+		return PCI_BASE_ADDRESS_SPACE_IO;
+	else
+		return bar & (PCI_BASE_ADDRESS_MEM_TYPE_MASK |
+			      PCI_BASE_ADDRESS_MEM_PREFETCH);
+}
+
+/*
+ * Probe DT for a generic PCI host controller
+ * See kernel Documentation/devicetree/bindings/pci/host-generic-pci.txt
+ * and function gen_pci_probe() in drivers/pci/host/pci-host-generic.c
+ */
+static struct pci_host_bridge *pci_dt_probe(void)
+{
+	struct pci_host_bridge *host;
+	const void *fdt = dt_fdt();
+	const struct fdt_property *prop;
+	struct dt_pbus_reg base;
+	struct dt_device dt_dev;
+	struct dt_bus dt_bus;
+	struct pci_addr_space *as;
+	fdt32_t *data;
+	u32 bus, bus_max;
+	u32 nac, nsc, nac_root, nsc_root;
+	int nr_range_cells, nr_addr_spaces;
+	int ret, node, len, i;
+
+	if (!dt_available()) {
+		printf("No device tree found\n");
+		return NULL;
+	}
+
+	dt_bus_init_defaults(&dt_bus);
+	dt_device_init(&dt_dev, &dt_bus, NULL);
+
+	node = fdt_path_offset(fdt, "/");
+	assert(node >= 0);
+
+	ret = dt_get_nr_cells(node, &nac_root, &nsc_root);
+	assert(ret == 0);
+	assert(nac_root == 1 || nac_root == 2);
+
+	node = fdt_node_offset_by_compatible(fdt, node,
+					     "pci-host-ecam-generic");
+	if (node == -FDT_ERR_NOTFOUND) {
+		printf("No PCIe ECAM compatible controller found\n");
+		return NULL;
+	}
+	assert(node >= 0);
+
+	prop = fdt_get_property(fdt, node, "device_type", &len);
+	assert(prop && len == 4 && !strcmp((char *)prop->data, "pci"));
+
+	dt_device_bind_node(&dt_dev, node);
+	ret = dt_pbus_get_base(&dt_dev, &base);
+	assert(ret == 0);
+
+	prop = fdt_get_property(fdt, node, "bus-range", &len);
+	if (prop == NULL) {
+		assert(len == -FDT_ERR_NOTFOUND);
+		bus		= 0x00;
+		bus_max		= 0xff;
+	} else {
+		data		= (fdt32_t *)prop->data;
+		bus		= fdt32_to_cpu(data[0]);
+		bus_max		= fdt32_to_cpu(data[1]);
+		assert(bus <= bus_max);
+	}
+	assert(bus_max < base.size / (1 << PCI_ECAM_BUS_SHIFT));
+
+	ret = dt_get_nr_cells(node, &nac, &nsc);
+	assert(ret == 0);
+	assert(nac == 3 && nsc == 2);
+
+	prop = fdt_get_property(fdt, node, "ranges", &len);
+	assert(prop != NULL);
+
+	nr_range_cells = nac + nsc + nac_root;
+	nr_addr_spaces = (len / 4) / nr_range_cells;
+	assert(nr_addr_spaces);
+
+	host = malloc(sizeof(*host) +
+		      sizeof(host->addr_space[0]) * nr_addr_spaces);
+	assert(host != NULL);
+
+	host->start		= base.addr;
+	host->size		= base.size;
+	host->bus		= bus;
+	host->bus_max		= bus_max;
+	host->nr_addr_spaces	= nr_addr_spaces;
+
+	data = (fdt32_t *)prop->data;
+	as = &host->addr_space[0];
+
+	for (i = 0; i < nr_addr_spaces; i++) {
+		/*
+		 * The PCI binding encodes the PCI address with three
+		 * cells as follows:
+		 *
+		 * phys.hi  cell: npt000ss bbbbbbbb dddddfff rrrrrrrr
+		 * phys.mid cell: hhhhhhhh hhhhhhhh hhhhhhhh hhhhhhhh
+		 * phys.lo  cell: llllllll llllllll llllllll llllllll
+		 *
+		 * PCI device bus address and flags are encoded into phys.high
+		 * PCI 64 bit address is encoded into phys.mid and phys.low
+		 */
+		as->type = of_flags_to_pci_type(fdt32_to_cpu(data[0]));
+		as->pci_start = ((u64)fdt32_to_cpu(data[1]) << 32) |
+				fdt32_to_cpu(data[2]);
+
+		if (nr_range_cells == 6) {
+			as->start = fdt32_to_cpu(data[3]);
+			as->size  = ((u64)fdt32_to_cpu(data[4]) << 32) |
+				    fdt32_to_cpu(data[5]);
+		} else {
+			as->start = ((u64)fdt32_to_cpu(data[3]) << 32) |
+				    fdt32_to_cpu(data[4]);
+			as->size  = ((u64)fdt32_to_cpu(data[5]) << 32) |
+				    fdt32_to_cpu(data[6]);
+		}
+
+		data += nr_range_cells;
+		as++;
+	}
+
+	return host;
+}
+
+static bool pci_alloc_resource(struct pci_dev *dev, int bar_num, u64 *addr)
+{
+	struct pci_host_bridge *host = pci_host_bridge;
+	struct pci_addr_space *as = &host->addr_space[0];
+	u32 bar;
+	u64 size, pci_addr;
+	int type, i;
+
+	*addr = INVALID_PHYS_ADDR;
+
+	size = pci_bar_size(dev, bar_num);
+	if (!size)
+		return false;
+
+	bar = pci_bar_get(dev, bar_num);
+	type = pci_bar_type(bar);
+	if (type & PCI_BASE_ADDRESS_MEM_TYPE_MASK)
+		type &= ~PCI_BASE_ADDRESS_MEM_PREFETCH;
+
+	for (i = 0; i < host->nr_addr_spaces; i++) {
+		if (as->type == type)
+			break;
+		as++;
+	}
+
+	if (i >= host->nr_addr_spaces) {
+		printf("%s: warning: can't satisfy request for ", __func__);
+		pci_dev_print_id(dev);
+		printf(" ");
+		pci_bar_print(dev, bar_num);
+		printf("\n");
+		return false;
+	}
+
+	pci_addr = ALIGN(as->pci_start + as->allocated, size);
+	size += pci_addr - (as->pci_start + as->allocated);
+	assert(as->allocated + size <= as->size);
+	*addr = pci_addr;
+	as->allocated += size;
+
+	return true;
+}
+
+bool pci_probe(void)
+{
+	struct pci_dev pci_dev;
+	pcidevaddr_t dev;
+	u8 header;
+	u32 cmd;
+	int i;
+
+	assert(!pci_host_bridge);
+	pci_host_bridge = pci_dt_probe();
+	if (!pci_host_bridge)
+		return false;
+
+	for (dev = 0; dev < PCI_DEVFN_MAX; dev++) {
+		if (!pci_dev_exists(dev))
+			continue;
+
+		pci_dev_init(&pci_dev, dev);
+
+		/* We are only interested in normal PCI devices */
+		header = pci_config_readb(dev, PCI_HEADER_TYPE);
+		if ((header & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_NORMAL)
+			continue;
+
+		cmd = PCI_COMMAND_SERR | PCI_COMMAND_PARITY;
+
+		for (i = 0; i < PCI_BAR_NUM; i++) {
+			u64 addr;
+
+			if (pci_alloc_resource(&pci_dev, i, &addr)) {
+				pci_bar_set_addr(&pci_dev, i, addr);
+
+				if (pci_bar_is_memory(&pci_dev, i))
+					cmd |= PCI_COMMAND_MEMORY;
+				else
+					cmd |= PCI_COMMAND_IO;
+			}
+
+			if (pci_bar_is64(&pci_dev, i))
+				i++;
+		}
+
+		pci_config_writew(dev, PCI_COMMAND, cmd);
+	}
+
+	return true;
+}
+
+/*
+ * This function is to be called from pci_translate_addr() to provide
+ * mapping between this host bridge's PCI busses address and CPU physical
+ * address.
+ */
+phys_addr_t pci_host_bridge_get_paddr(u64 pci_addr)
+{
+	struct pci_host_bridge *host = pci_host_bridge;
+	struct pci_addr_space *as = &host->addr_space[0];
+	int i;
+
+	for (i = 0; i < host->nr_addr_spaces; i++) {
+		if (pci_addr >= as->pci_start &&
+		    pci_addr < as->pci_start + as->size)
+			return as->start + (pci_addr - as->pci_start);
+		as++;
+	}
+
+	return INVALID_PHYS_ADDR;
+}
+
+static void __iomem *pci_get_dev_conf(struct pci_host_bridge *host, int devfn)
+{
+	return (void __iomem *)(unsigned long)
+		host->start + (devfn << PCI_ECAM_DEVFN_SHIFT);
+}
+
+u8 pci_config_readb(pcidevaddr_t dev, u8 off)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	return readb(conf + off);
+}
+
+u16 pci_config_readw(pcidevaddr_t dev, u8 off)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	return readw(conf + off);
+}
+
+u32 pci_config_readl(pcidevaddr_t dev, u8 off)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	return readl(conf + off);
+}
+
+void pci_config_writeb(pcidevaddr_t dev, u8 off, u8 val)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	writeb(val, conf + off);
+}
+
+void pci_config_writew(pcidevaddr_t dev, u8 off, u16 val)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	writew(val, conf + off);
+}
+
+void pci_config_writel(pcidevaddr_t dev, u8 off, u32 val)
+{
+	void __iomem *conf = pci_get_dev_conf(pci_host_bridge, dev);
+	writel(val, conf + off);
+}

tests/kvm-unit-tests/lib/pci-host-generic.h

@@ -0,0 +1,46 @@
+#ifndef PCI_HOST_GENERIC_H
+#define PCI_HOST_GENERIC_H
+/*
+ * PCI host bridge supporting structures and constants
+ *
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+struct pci_addr_space {
+	phys_addr_t		pci_start;
+	phys_addr_t		start;
+	phys_addr_t		size;
+	phys_addr_t		allocated;
+	int			type;
+};
+
+struct pci_host_bridge {
+	phys_addr_t		start;
+	phys_addr_t		size;
+	int			bus;
+	int			bus_max;
+	int			nr_addr_spaces;
+	struct pci_addr_space	addr_space[];
+};
+
+/*
+ * The following constants are derived from Linux, see this source:
+ *
+ *         drivers/pci/host/pci-host-generic.c
+ *                 struct gen_pci_cfg_bus_ops::bus_shift
+ *                 int gen_pci_parse_map_cfg_windows(struct gen_pci *pci)
+ *
+ * Documentation/devicetree/bindings/pci/host-generic-pci.txt describes
+ * ECAM Configuration Space is be memory-mapped by concatenating the various
+ * components to form an offset:
+ *
+ *	cfg_offset(bus, device, function, register) =
+ *		   bus << 20 | device << 15 | function << 12 | register
+ */
+#define PCI_ECAM_BUS_SHIFT	20
+#define PCI_ECAM_DEVFN_SHIFT	12
+
+#endif

tests/kvm-unit-tests/lib/pci-testdev.c

@@ -0,0 +1,194 @@
+/*
+ * QEMU "pci-testdev" PCI test device
+ *
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "pci.h"
+#include "asm/io.h"
+
+struct pci_testdev_ops {
+	u8 (*io_readb)(const volatile void *addr);
+	u16 (*io_readw)(const volatile void *addr);
+	u32 (*io_readl)(const volatile void *addr);
+	void (*io_writeb)(u8 value, volatile void *addr);
+	void (*io_writew)(u16 value, volatile void *addr);
+	void (*io_writel)(u32 value, volatile void *addr);
+};
+
+static u8 pio_readb(const volatile void *addr)
+{
+	return inb((unsigned long)addr);
+}
+
+static u16 pio_readw(const volatile void *addr)
+{
+	return inw((unsigned long)addr);
+}
+
+static u32 pio_readl(const volatile void *addr)
+{
+	return inl((unsigned long)addr);
+}
+
+static void pio_writeb(u8 value, volatile void *addr)
+{
+	outb(value, (unsigned long)addr);
+}
+
+static void pio_writew(u16 value, volatile void *addr)
+{
+	outw(value, (unsigned long)addr);
+}
+
+static void pio_writel(u32 value, volatile void *addr)
+{
+	outl(value, (unsigned long)addr);
+}
+
+static struct pci_testdev_ops pci_testdev_io_ops = {
+	.io_readb	= pio_readb,
+	.io_readw	= pio_readw,
+	.io_readl	= pio_readl,
+	.io_writeb	= pio_writeb,
+	.io_writew	= pio_writew,
+	.io_writel	= pio_writel
+};
+
+static u8 mmio_readb(const volatile void *addr)
+{
+	return *(const volatile u8 __force *)addr;
+}
+
+static u16 mmio_readw(const volatile void *addr)
+{
+	return *(const volatile u16 __force *)addr;
+}
+
+static u32 mmio_readl(const volatile void *addr)
+{
+	return *(const volatile u32 __force *)addr;
+}
+
+static void mmio_writeb(u8 value, volatile void *addr)
+{
+	*(volatile u8 __force *)addr = value;
+}
+
+static void mmio_writew(u16 value, volatile void *addr)
+{
+	*(volatile u16 __force *)addr = value;
+}
+
+static void mmio_writel(u32 value, volatile void *addr)
+{
+	*(volatile u32 __force *)addr = value;
+}
+
+static struct pci_testdev_ops pci_testdev_mem_ops = {
+	.io_readb	= mmio_readb,
+	.io_readw	= mmio_readw,
+	.io_readl	= mmio_readl,
+	.io_writeb	= mmio_writeb,
+	.io_writew	= mmio_writew,
+	.io_writel	= mmio_writel
+};
+
+static bool pci_testdev_one(struct pci_test_dev_hdr *test,
+			    int test_nr,
+			    struct pci_testdev_ops *ops)
+{
+	u8 width;
+	u32 count, sig, off;
+	const int nr_writes = 16;
+	int i;
+
+	ops->io_writeb(test_nr, &test->test);
+	count = ops->io_readl(&test->count);
+	if (count != 0)
+		return false;
+
+	width = ops->io_readb(&test->width);
+	if (width != 1 && width != 2 && width != 4)
+		return false;
+
+	sig = ops->io_readl(&test->data);
+	off = ops->io_readl(&test->offset);
+
+	for (i = 0; i < nr_writes; i++) {
+		switch (width) {
+		case 1: ops->io_writeb(sig, (void *)test + off); break;
+		case 2: ops->io_writew(sig, (void *)test + off); break;
+		case 4: ops->io_writel(sig, (void *)test + off); break;
+		}
+	}
+
+	count = ops->io_readl(&test->count);
+	if (!count)
+		return true;
+
+	return (int)count == nr_writes;
+}
+
+void pci_testdev_print(struct pci_test_dev_hdr *test,
+		       struct pci_testdev_ops *ops)
+{
+	bool io = (ops == &pci_testdev_io_ops);
+	int i;
+
+	printf("pci-testdev %3s: ", io ? "io" : "mem");
+	for (i = 0;; ++i) {
+		char c = ops->io_readb(&test->name[i]);
+		if (!c)
+			break;
+		printf("%c", c);
+	}
+	printf("\n");
+}
+
+static int pci_testdev_all(struct pci_test_dev_hdr *test,
+			   struct pci_testdev_ops *ops)
+{
+	int i;
+
+	for (i = 0;; i++) {
+		if (!pci_testdev_one(test, i, ops))
+			break;
+		pci_testdev_print(test, ops);
+	}
+
+	return i;
+}
+
+int pci_testdev(void)
+{
+	struct pci_dev pci_dev;
+	pcidevaddr_t dev;
+	phys_addr_t addr;
+	void __iomem *mem, *io;
+	int nr_tests = 0;
+	bool ret;
+
+	dev = pci_find_dev(PCI_VENDOR_ID_REDHAT, PCI_DEVICE_ID_REDHAT_TEST);
+	if (dev == PCIDEVADDR_INVALID) {
+		printf("'pci-testdev' device is not found, "
+		       "check QEMU '-device pci-testdev' parameter\n");
+		return -1;
+	}
+	pci_dev_init(&pci_dev, dev);
+
+	ret = pci_bar_is_valid(&pci_dev, 0) && pci_bar_is_valid(&pci_dev, 1);
+	assert(ret);
+
+	addr = pci_bar_get_addr(&pci_dev, 0);
+	mem = ioremap(addr, PAGE_SIZE);
+
+	addr = pci_bar_get_addr(&pci_dev, 1);
+	io = (void *)(unsigned long)addr;
+
+	nr_tests += pci_testdev_all(mem, &pci_testdev_mem_ops);
+	nr_tests += pci_testdev_all(io, &pci_testdev_io_ops);
+
+	return nr_tests;
+}

tests/kvm-unit-tests/lib/pci.c

@@ -0,0 +1,374 @@
+/*
+ * Copyright (C) 2013, Red Hat Inc, Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include <linux/pci_regs.h>
+#include "pci.h"
+#include "asm/pci.h"
+
+void pci_cap_walk(struct pci_dev *dev, pci_cap_handler_t handler)
+{
+	uint8_t cap_offset;
+	uint8_t cap_id;
+	int count = 0;
+
+	cap_offset = pci_config_readb(dev->bdf, PCI_CAPABILITY_LIST);
+	while (cap_offset) {
+		cap_id = pci_config_readb(dev->bdf, cap_offset);
+		assert(cap_id < PCI_CAP_ID_MAX + 1);
+		handler(dev, cap_offset, cap_id);
+		cap_offset = pci_config_readb(dev->bdf, cap_offset + 1);
+		/* Avoid dead loop during cap walk */
+		assert(++count <= 255);
+	}
+}
+
+void pci_msi_set_enable(struct pci_dev *dev, bool enabled)
+{
+	uint16_t msi_control;
+	uint16_t offset;
+
+	offset = dev->msi_offset;
+	msi_control = pci_config_readw(dev->bdf, offset + PCI_MSI_FLAGS);
+
+	if (enabled)
+		msi_control |= PCI_MSI_FLAGS_ENABLE;
+	else
+		msi_control &= ~PCI_MSI_FLAGS_ENABLE;
+
+	pci_config_writew(dev->bdf, offset + PCI_MSI_FLAGS, msi_control);
+}
+
+bool pci_setup_msi(struct pci_dev *dev, uint64_t msi_addr, uint32_t msi_data)
+{
+	uint16_t msi_control;
+	uint16_t offset;
+	pcidevaddr_t addr;
+
+	assert(dev);
+
+	if (!dev->msi_offset) {
+		printf("MSI: dev 0x%x does not support MSI.\n", dev->bdf);
+		return false;
+	}
+
+	addr = dev->bdf;
+	offset = dev->msi_offset;
+	msi_control = pci_config_readw(addr, offset + PCI_MSI_FLAGS);
+	pci_config_writel(addr, offset + PCI_MSI_ADDRESS_LO,
+			  msi_addr & 0xffffffff);
+
+	if (msi_control & PCI_MSI_FLAGS_64BIT) {
+		pci_config_writel(addr, offset + PCI_MSI_ADDRESS_HI,
+				  (uint32_t)(msi_addr >> 32));
+		pci_config_writel(addr, offset + PCI_MSI_DATA_64, msi_data);
+	} else {
+		pci_config_writel(addr, offset + PCI_MSI_DATA_32, msi_data);
+	}
+
+	pci_msi_set_enable(dev, true);
+
+	return true;
+}
+
+void pci_cmd_set_clr(struct pci_dev *dev, uint16_t set, uint16_t clr)
+{
+	uint16_t val = pci_config_readw(dev->bdf, PCI_COMMAND);
+
+	/* No overlap is allowed */
+	assert((set & clr) == 0);
+	val |= set;
+	val &= ~clr;
+
+	pci_config_writew(dev->bdf, PCI_COMMAND, val);
+}
+
+bool pci_dev_exists(pcidevaddr_t dev)
+{
+	return (pci_config_readw(dev, PCI_VENDOR_ID) != 0xffff &&
+		pci_config_readw(dev, PCI_DEVICE_ID) != 0xffff);
+}
+
+/* Scan bus look for a specific device. Only bus 0 scanned for now. */
+pcidevaddr_t pci_find_dev(uint16_t vendor_id, uint16_t device_id)
+{
+	pcidevaddr_t dev;
+
+	for (dev = 0; dev < PCI_DEVFN_MAX; ++dev) {
+		if (pci_config_readw(dev, PCI_VENDOR_ID) == vendor_id &&
+		    pci_config_readw(dev, PCI_DEVICE_ID) == device_id)
+			return dev;
+	}
+
+	return PCIDEVADDR_INVALID;
+}
+
+uint32_t pci_bar_mask(uint32_t bar)
+{
+	return (bar & PCI_BASE_ADDRESS_SPACE_IO) ?
+		PCI_BASE_ADDRESS_IO_MASK : PCI_BASE_ADDRESS_MEM_MASK;
+}
+
+uint32_t pci_bar_get(struct pci_dev *dev, int bar_num)
+{
+	return pci_config_readl(dev->bdf, PCI_BASE_ADDRESS_0 +
+				bar_num * 4);
+}
+
+static phys_addr_t __pci_bar_get_addr(struct pci_dev *dev, int bar_num)
+{
+	uint32_t bar = pci_bar_get(dev, bar_num);
+	uint32_t mask = pci_bar_mask(bar);
+	uint64_t addr = bar & mask;
+	phys_addr_t phys_addr;
+
+	if (pci_bar_is64(dev, bar_num))
+		addr |= (uint64_t)pci_bar_get(dev, bar_num + 1) << 32;
+
+	phys_addr = pci_translate_addr(dev->bdf, addr);
+	assert(phys_addr != INVALID_PHYS_ADDR);
+
+	return phys_addr;
+}
+
+phys_addr_t pci_bar_get_addr(struct pci_dev *dev, int bar_num)
+{
+	return dev->resource[bar_num];
+}
+
+void pci_bar_set_addr(struct pci_dev *dev, int bar_num, phys_addr_t addr)
+{
+	int off = PCI_BASE_ADDRESS_0 + bar_num * 4;
+
+	pci_config_writel(dev->bdf, off, (uint32_t)addr);
+	dev->resource[bar_num] = addr;
+
+	if (pci_bar_is64(dev, bar_num)) {
+		assert(bar_num + 1 < PCI_BAR_NUM);
+		pci_config_writel(dev->bdf, off + 4, (uint32_t)(addr >> 32));
+		dev->resource[bar_num + 1] = dev->resource[bar_num];
+	}
+}
+
+/*
+ * To determine the amount of address space needed by a PCI device,
+ * one must save the original value of the BAR, write a value of
+ * all 1's to the register, and then read it back. The amount of
+ * memory can be then determined by masking the information bits,
+ * performing a bitwise NOT, and incrementing the value by 1.
+ *
+ * The following pci_bar_size_helper() and pci_bar_size() functions
+ * implement the algorithm.
+ */
+static uint32_t pci_bar_size_helper(struct pci_dev *dev, int bar_num)
+{
+	int off = PCI_BASE_ADDRESS_0 + bar_num * 4;
+	uint16_t bdf = dev->bdf;
+	uint32_t bar, val;
+
+	bar = pci_config_readl(bdf, off);
+	pci_config_writel(bdf, off, ~0u);
+	val = pci_config_readl(bdf, off);
+	pci_config_writel(bdf, off, bar);
+
+	return val;
+}
+
+phys_addr_t pci_bar_size(struct pci_dev *dev, int bar_num)
+{
+	uint32_t bar, size;
+
+	size = pci_bar_size_helper(dev, bar_num);
+	if (!size)
+		return 0;
+
+	bar = pci_bar_get(dev, bar_num);
+	size &= pci_bar_mask(bar);
+
+	if (pci_bar_is64(dev, bar_num)) {
+		phys_addr_t size64 = pci_bar_size_helper(dev, bar_num + 1);
+		size64 = (size64 << 32) | size;
+
+		return ~size64 + 1;
+	} else {
+		return ~size + 1;
+	}
+}
+
+bool pci_bar_is_memory(struct pci_dev *dev, int bar_num)
+{
+	uint32_t bar = pci_bar_get(dev, bar_num);
+
+	return !(bar & PCI_BASE_ADDRESS_SPACE_IO);
+}
+
+bool pci_bar_is_valid(struct pci_dev *dev, int bar_num)
+{
+	return dev->resource[bar_num] != INVALID_PHYS_ADDR;
+}
+
+bool pci_bar_is64(struct pci_dev *dev, int bar_num)
+{
+	uint32_t bar = pci_bar_get(dev, bar_num);
+
+	if (bar & PCI_BASE_ADDRESS_SPACE_IO)
+		return false;
+
+	return (bar & PCI_BASE_ADDRESS_MEM_TYPE_MASK) ==
+		      PCI_BASE_ADDRESS_MEM_TYPE_64;
+}
+
+void pci_bar_print(struct pci_dev *dev, int bar_num)
+{
+	phys_addr_t size, start, end;
+	uint32_t bar;
+
+	if (!pci_bar_is_valid(dev, bar_num))
+		return;
+
+	bar = pci_bar_get(dev, bar_num);
+	size = pci_bar_size(dev, bar_num);
+	start = pci_bar_get_addr(dev, bar_num);
+	end = start + size - 1;
+
+	if (pci_bar_is64(dev, bar_num)) {
+		printf("BAR#%d,%d [%" PRIx64 "-%" PRIx64 " ",
+		       bar_num, bar_num + 1, start, end);
+	} else {
+		printf("BAR#%d [%02x-%02x ",
+		       bar_num, (uint32_t)start, (uint32_t)end);
+	}
+
+	if (bar & PCI_BASE_ADDRESS_SPACE_IO) {
+		printf("PIO");
+	} else {
+		printf("MEM");
+		switch (bar & PCI_BASE_ADDRESS_MEM_TYPE_MASK) {
+		case PCI_BASE_ADDRESS_MEM_TYPE_32:
+			printf("32");
+			break;
+		case PCI_BASE_ADDRESS_MEM_TYPE_1M:
+			printf("1M");
+			break;
+		case PCI_BASE_ADDRESS_MEM_TYPE_64:
+			printf("64");
+			break;
+		default:
+			assert(0);
+		}
+	}
+
+	if (bar & PCI_BASE_ADDRESS_MEM_PREFETCH)
+		printf("/p");
+
+	printf("]");
+}
+
+void pci_dev_print_id(struct pci_dev *dev)
+{
+	pcidevaddr_t bdf = dev->bdf;
+
+	printf("00.%02x.%1x %04x:%04x", bdf / 8, bdf % 8,
+		pci_config_readw(bdf, PCI_VENDOR_ID),
+		pci_config_readw(bdf, PCI_DEVICE_ID));
+}
+
+static void pci_cap_print(struct pci_dev *dev, int cap_offset, int cap_id)
+{
+	switch (cap_id) {
+	case PCI_CAP_ID_MSI: {
+		uint16_t control = pci_config_readw(dev->bdf, cap_offset + PCI_MSI_FLAGS);
+		printf("\tMSI,%s-bit capability ", control & PCI_MSI_FLAGS_64BIT ? "64" : "32");
+		break;
+	}
+	default:
+		printf("\tcapability 0x%02x ", cap_id);
+		break;
+	}
+	printf("at offset 0x%02x\n", cap_offset);
+}
+
+void pci_dev_print(struct pci_dev *dev)
+{
+	pcidevaddr_t bdf = dev->bdf;
+	uint8_t header = pci_config_readb(bdf, PCI_HEADER_TYPE);
+	uint8_t progif = pci_config_readb(bdf, PCI_CLASS_PROG);
+	uint8_t subclass = pci_config_readb(bdf, PCI_CLASS_DEVICE);
+	uint8_t class = pci_config_readb(bdf, PCI_CLASS_DEVICE + 1);
+	int i;
+
+	pci_dev_print_id(dev);
+	printf(" type %02x progif %02x class %02x subclass %02x\n",
+	       header, progif, class, subclass);
+
+	pci_cap_walk(dev, pci_cap_print);
+
+	if ((header & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_NORMAL)
+		return;
+
+	for (i = 0; i < PCI_BAR_NUM; i++) {
+		if (pci_bar_is_valid(dev, i)) {
+			printf("\t");
+			pci_bar_print(dev, i);
+			printf("\n");
+		}
+		if (pci_bar_is64(dev, i))
+			i++;
+	}
+}
+
+void pci_print(void)
+{
+	pcidevaddr_t devfn;
+	struct pci_dev pci_dev;
+
+	for (devfn = 0; devfn < PCI_DEVFN_MAX; ++devfn) {
+		if (pci_dev_exists(devfn)) {
+			pci_dev_init(&pci_dev, devfn);
+			pci_dev_print(&pci_dev);
+		}
+	}
+}
+
+void pci_dev_init(struct pci_dev *dev, pcidevaddr_t bdf)
+{
+	int i;
+
+	memset(dev, 0, sizeof(*dev));
+	dev->bdf = bdf;
+
+	for (i = 0; i < PCI_BAR_NUM; i++) {
+		if (pci_bar_size(dev, i)) {
+			dev->resource[i] = __pci_bar_get_addr(dev, i);
+			if (pci_bar_is64(dev, i)) {
+				assert(i + 1 < PCI_BAR_NUM);
+				dev->resource[i + 1] = dev->resource[i];
+				i++;
+			}
+		} else {
+			dev->resource[i] = INVALID_PHYS_ADDR;
+		}
+	}
+}
+
+uint8_t pci_intx_line(struct pci_dev *dev)
+{
+	return pci_config_readb(dev->bdf, PCI_INTERRUPT_LINE);
+}
+
+static void pci_cap_setup(struct pci_dev *dev, int cap_offset, int cap_id)
+{
+	switch (cap_id) {
+	case PCI_CAP_ID_MSI:
+		dev->msi_offset = cap_offset;
+		break;
+	}
+}
+
+void pci_enable_defaults(struct pci_dev *dev)
+{
+	/* Enable device DMA operations */
+	pci_cmd_set_clr(dev, PCI_COMMAND_MASTER, 0);
+	pci_cap_walk(dev, pci_cap_setup);
+}

tests/kvm-unit-tests/lib/pci.h

@@ -0,0 +1,102 @@
+#ifndef PCI_H
+#define PCI_H
+/*
+ * API for scanning a PCI bus for a given device, as well to access
+ * BAR registers.
+ *
+ * Copyright (C) 2013, Red Hat Inc, Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+typedef uint16_t pcidevaddr_t;
+enum {
+	PCIDEVADDR_INVALID = 0xffff,
+};
+
+#define PCI_BAR_NUM                     6
+#define PCI_DEVFN_MAX                   256
+
+#define PCI_BDF_GET_DEVFN(x)            ((x) & 0xff)
+#define PCI_BDF_GET_BUS(x)              (((x) >> 8) & 0xff)
+
+struct pci_dev {
+	uint16_t bdf;
+	uint16_t msi_offset;
+	phys_addr_t resource[PCI_BAR_NUM];
+};
+
+extern void pci_dev_init(struct pci_dev *dev, pcidevaddr_t bdf);
+extern void pci_cmd_set_clr(struct pci_dev *dev, uint16_t set, uint16_t clr);
+typedef void (*pci_cap_handler_t)(struct pci_dev *dev, int cap_offset, int cap_id);
+extern void pci_cap_walk(struct pci_dev *dev, pci_cap_handler_t handler);
+extern void pci_enable_defaults(struct pci_dev *dev);
+extern bool pci_setup_msi(struct pci_dev *dev, uint64_t msi_addr,
+			  uint32_t msi_data);
+
+typedef phys_addr_t iova_t;
+
+extern bool pci_probe(void);
+extern void pci_print(void);
+extern bool pci_dev_exists(pcidevaddr_t dev);
+extern pcidevaddr_t pci_find_dev(uint16_t vendor_id, uint16_t device_id);
+
+/*
+ * @bar_num in all BAR access functions below is the index of the 32-bit
+ * register starting from the PCI_BASE_ADDRESS_0 offset.
+ *
+ * In cases where the BAR size is 64-bit, a caller should still provide
+ * @bar_num in terms of 32-bit words. For example, if a device has a 64-bit
+ * BAR#0 and a 32-bit BAR#1, then caller should provide 2 to address BAR#1,
+ * not 1.
+ *
+ * It is expected the caller is aware of the device BAR layout and never
+ * tries to address the middle of a 64-bit register.
+ */
+extern phys_addr_t pci_bar_get_addr(struct pci_dev *dev, int bar_num);
+extern void pci_bar_set_addr(struct pci_dev *dev, int bar_num, phys_addr_t addr);
+extern phys_addr_t pci_bar_size(struct pci_dev *dev, int bar_num);
+extern uint32_t pci_bar_get(struct pci_dev *dev, int bar_num);
+extern uint32_t pci_bar_mask(uint32_t bar);
+extern bool pci_bar_is64(struct pci_dev *dev, int bar_num);
+extern bool pci_bar_is_memory(struct pci_dev *dev, int bar_num);
+extern bool pci_bar_is_valid(struct pci_dev *dev, int bar_num);
+extern void pci_bar_print(struct pci_dev *dev, int bar_num);
+extern void pci_dev_print_id(struct pci_dev *dev);
+extern void pci_dev_print(struct pci_dev *dev);
+extern uint8_t pci_intx_line(struct pci_dev *dev);
+void pci_msi_set_enable(struct pci_dev *dev, bool enabled);
+
+extern int pci_testdev(void);
+
+/*
+ * pci-testdev is a driver for the pci-testdev qemu pci device. The
+ * device enables testing mmio and portio exits, and measuring their
+ * speed.
+ */
+#define PCI_VENDOR_ID_REDHAT		0x1b36
+#define PCI_DEVICE_ID_REDHAT_TEST	0x0005
+
+/*
+ * pci-testdev supports at least three types of tests (via mmio and
+ * portio BARs): no-eventfd, wildcard-eventfd and datamatch-eventfd
+ */
+#define PCI_TESTDEV_BAR_MEM		0
+#define PCI_TESTDEV_BAR_IO		1
+#define PCI_TESTDEV_NUM_BARS		2
+#define PCI_TESTDEV_NUM_TESTS		3
+
+struct pci_test_dev_hdr {
+	uint8_t  test;
+	uint8_t  width;
+	uint8_t  pad0[2];
+	uint32_t offset;
+	uint32_t data;
+	uint32_t count;
+	uint8_t  name[];
+};
+
+#define  PCI_HEADER_TYPE_MASK		0x7f
+
+#endif /* PCI_H */

tests/kvm-unit-tests/lib/printf.c

@@ -0,0 +1,261 @@
+#include "libcflat.h"
+
+#define BUFSZ 2000
+
+typedef struct pstream {
+    char *buffer;
+    int remain;
+    int added;
+} pstream_t;
+
+typedef struct strprops {
+    char pad;
+    int npad;
+} strprops_t;
+
+static void addchar(pstream_t *p, char c)
+{
+    if (p->remain) {
+	*p->buffer++ = c;
+	--p->remain;
+    }
+    ++p->added;
+}
+
+void print_str(pstream_t *p, const char *s, strprops_t props)
+{
+    const char *s_orig = s;
+    int npad = props.npad;
+
+    if (npad > 0) {
+	npad -= strlen(s_orig);
+	while (npad > 0) {
+	    addchar(p, props.pad);
+	    --npad;
+	}
+    }
+
+    while (*s)
+	addchar(p, *s++);
+
+    if (npad < 0) {
+	props.pad = ' '; /* ignore '0' flag with '-' flag */
+	npad += strlen(s_orig);
+	while (npad < 0) {
+	    addchar(p, props.pad);
+	    ++npad;
+	}
+    }
+}
+
+static char digits[16] = "0123456789abcdef";
+
+void print_int(pstream_t *ps, long long n, int base, strprops_t props)
+{
+    char buf[sizeof(long) * 3 + 2], *p = buf;
+    int s = 0, i;
+
+    if (n < 0) {
+	n = -n;
+	s = 1;
+    }
+
+    while (n) {
+	*p++ = digits[n % base];
+	n /= base;
+    }
+
+    if (s)
+	*p++ = '-';
+
+    if (p == buf)
+	*p++ = '0';
+
+    for (i = 0; i < (p - buf) / 2; ++i) {
+	char tmp;
+
+	tmp = buf[i];
+	buf[i] = p[-1-i];
+	p[-1-i] = tmp;
+    }
+
+    *p = 0;
+
+    print_str(ps, buf, props);
+}
+
+void print_unsigned(pstream_t *ps, unsigned long long n, int base,
+		    strprops_t props)
+{
+    char buf[sizeof(long) * 3 + 1], *p = buf;
+    int i;
+
+    while (n) {
+	*p++ = digits[n % base];
+	n /= base;
+    }
+
+    if (p == buf)
+	*p++ = '0';
+
+    for (i = 0; i < (p - buf) / 2; ++i) {
+	char tmp;
+
+	tmp = buf[i];
+	buf[i] = p[-1-i];
+	p[-1-i] = tmp;
+    }
+
+    *p = 0;
+
+    print_str(ps, buf, props);
+}
+
+static int fmtnum(const char **fmt)
+{
+    const char *f = *fmt;
+    int len = 0, num;
+
+    if (*f == '-')
+	++f, ++len;
+
+    while (*f >= '0' && *f <= '9')
+	++f, ++len;
+
+    num = atol(*fmt);
+    *fmt += len;
+    return num;
+}
+
+int vsnprintf(char *buf, int size, const char *fmt, va_list va)
+{
+    pstream_t s;
+
+    s.buffer = buf;
+    s.remain = size - 1;
+    s.added = 0;
+    while (*fmt) {
+	char f = *fmt++;
+	int nlong = 0;
+	strprops_t props;
+	memset(&props, 0, sizeof(props));
+	props.pad = ' ';
+
+	if (f != '%') {
+	    addchar(&s, f);
+	    continue;
+	}
+    morefmt:
+	f = *fmt++;
+	switch (f) {
+	case '%':
+	    addchar(&s, '%');
+	    break;
+	case 'c':
+            addchar(&s, va_arg(va, int));
+	    break;
+	case '\0':
+	    --fmt;
+	    break;
+	case '0':
+	    props.pad = '0';
+	    ++fmt;
+	    /* fall through */
+	case '1'...'9':
+	case '-':
+	    --fmt;
+	    props.npad = fmtnum(&fmt);
+	    goto morefmt;
+	case 'l':
+	    ++nlong;
+	    goto morefmt;
+	case 'd':
+	    switch (nlong) {
+	    case 0:
+		print_int(&s, va_arg(va, int), 10, props);
+		break;
+	    case 1:
+		print_int(&s, va_arg(va, long), 10, props);
+		break;
+	    default:
+		print_int(&s, va_arg(va, long long), 10, props);
+		break;
+	    }
+	    break;
+	case 'u':
+	    switch (nlong) {
+	    case 0:
+		print_unsigned(&s, va_arg(va, unsigned), 10, props);
+		break;
+	    case 1:
+		print_unsigned(&s, va_arg(va, unsigned long), 10, props);
+		break;
+	    default:
+		print_unsigned(&s, va_arg(va, unsigned long long), 10, props);
+		break;
+	    }
+	    break;
+	case 'x':
+	    switch (nlong) {
+	    case 0:
+		print_unsigned(&s, va_arg(va, unsigned), 16, props);
+		break;
+	    case 1:
+		print_unsigned(&s, va_arg(va, unsigned long), 16, props);
+		break;
+	    default:
+		print_unsigned(&s, va_arg(va, unsigned long long), 16, props);
+		break;
+	    }
+	    break;
+	case 'p':
+	    print_str(&s, "0x", props);
+	    print_unsigned(&s, (unsigned long)va_arg(va, void *), 16, props);
+	    break;
+	case 's':
+	    print_str(&s, va_arg(va, const char *), props);
+	    break;
+	default:
+	    addchar(&s, f);
+	    break;
+	}
+    }
+    *s.buffer = 0;
+    ++s.added;
+    return s.added;
+}
+
+
+int snprintf(char *buf, int size, const char *fmt, ...)
+{
+    va_list va;
+    int r;
+
+    va_start(va, fmt);
+    r = vsnprintf(buf, size, fmt, va);
+    va_end(va);
+    return r;
+}
+
+int vprintf(const char *fmt, va_list va)
+{
+    char buf[BUFSZ];
+    int r;
+
+    r = vsnprintf(buf, sizeof(buf), fmt, va);
+    puts(buf);
+    return r;
+}
+
+int printf(const char *fmt, ...)
+{
+    va_list va;
+    char buf[BUFSZ];
+    int r;
+
+    va_start(va, fmt);
+    r = vsnprintf(buf, sizeof buf, fmt, va);
+    va_end(va);
+    puts(buf);
+    return r;
+}

tests/kvm-unit-tests/lib/report.c

@@ -0,0 +1,145 @@
+/*
+ * Test result reporting
+ *
+ * Copyright (c) Siemens AG, 2014
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ *  Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+#include "libcflat.h"
+#include "asm/spinlock.h"
+
+static unsigned int tests, failures, xfailures, skipped;
+static char prefixes[256];
+static struct spinlock lock;
+
+void report_prefix_push(const char *prefix)
+{
+	spin_lock(&lock);
+	strcat(prefixes, prefix);
+	strcat(prefixes, ": ");
+	spin_unlock(&lock);
+}
+
+void report_prefix_pop(void)
+{
+	char *p, *q;
+
+	spin_lock(&lock);
+
+	if (!*prefixes)
+		return;
+
+	for (p = prefixes, q = strstr(p, ": ") + 2;
+			*q;
+			p = q, q = strstr(p, ": ") + 2)
+		;
+	*p = '\0';
+
+	spin_unlock(&lock);
+}
+
+static void va_report(const char *msg_fmt,
+		bool pass, bool xfail, bool skip, va_list va)
+{
+	char *prefix = skip ? "SKIP"
+	                    : xfail ? (pass ? "XPASS" : "XFAIL")
+	                            : (pass ? "PASS"  : "FAIL");
+
+	spin_lock(&lock);
+
+	tests++;
+	printf("%s: ", prefix);
+	puts(prefixes);
+	vprintf(msg_fmt, va);
+	puts("\n");
+	if (skip)
+		skipped++;
+	else if (xfail && !pass)
+		xfailures++;
+	else if (xfail || !pass)
+		failures++;
+
+	spin_unlock(&lock);
+}
+
+void report(const char *msg_fmt, bool pass, ...)
+{
+	va_list va;
+	va_start(va, pass);
+	va_report(msg_fmt, pass, false, false, va);
+	va_end(va);
+}
+
+void report_xfail(const char *msg_fmt, bool xfail, bool pass, ...)
+{
+	va_list va;
+	va_start(va, pass);
+	va_report(msg_fmt, pass, xfail, false, va);
+	va_end(va);
+}
+
+void report_skip(const char *msg_fmt, ...)
+{
+	va_list va;
+	va_start(va, msg_fmt);
+	va_report(msg_fmt, false, false, true, va);
+	va_end(va);
+}
+
+void report_info(const char *msg_fmt, ...)
+{
+	va_list va;
+
+	spin_lock(&lock);
+	puts("INFO: ");
+	puts(prefixes);
+	va_start(va, msg_fmt);
+	vprintf(msg_fmt, va);
+	va_end(va);
+	puts("\n");
+	spin_unlock(&lock);
+}
+
+int report_summary(void)
+{
+	spin_lock(&lock);
+
+	printf("SUMMARY: %d tests", tests);
+	if (failures)
+		printf(", %d unexpected failures", failures);
+	if (xfailures)
+		printf(", %d expected failures", xfailures);
+	if (skipped)
+		printf(", %d skipped", skipped);
+	printf("\n");
+
+	if (tests == skipped)
+		/* Blame AUTOTOOLS for using 77 for skipped test and QEMU for
+		 * mangling error codes in a way that gets 77 if we ... */
+		return 77 >> 1;
+
+	return failures > 0 ? 1 : 0;
+
+	spin_unlock(&lock);
+}
+
+void report_abort(const char *msg_fmt, ...)
+{
+	va_list va;
+
+	spin_lock(&lock);
+	puts("ABORT: ");
+	puts(prefixes);
+	va_start(va, msg_fmt);
+	vprintf(msg_fmt, va);
+	va_end(va);
+	puts("\n");
+	spin_unlock(&lock);
+	report_summary();
+	abort();
+}

tests/kvm-unit-tests/lib/setjmp.h

@@ -0,0 +1,12 @@
+#ifndef LIBCFLAT_SETJMP_H
+#define LIBCFLAT_SETJMP_H 1
+
+typedef struct jmp_buf_tag {
+	long int regs[8];
+} jmp_buf[1];
+
+extern int setjmp (struct jmp_buf_tag env[1]);
+extern void longjmp (struct jmp_buf_tag env[1], int val)
+     __attribute__ ((__noreturn__));
+
+#endif /* setjmp.h  */

tests/kvm-unit-tests/lib/stack.c

@@ -0,0 +1,96 @@
+#include <libcflat.h>
+#include <stack.h>
+
+#define MAX_DEPTH 20
+
+static void print_stack(const void **return_addrs, int depth,
+			bool top_is_return_address)
+{
+	int i = 0;
+
+	printf("\tSTACK:");
+
+	/* @addr indicates a non-return address, as expected by the stack
+	 * pretty printer script. */
+	if (depth > 0 && !top_is_return_address) {
+		printf(" @%lx", (unsigned long) return_addrs[0]);
+		i++;
+	}
+
+	for (; i < depth; i++) {
+		printf(" %lx", (unsigned long) return_addrs[i]);
+	}
+	printf("\n");
+}
+
+void dump_stack(void)
+{
+	const void *return_addrs[MAX_DEPTH];
+	int depth;
+
+	depth = backtrace(return_addrs, MAX_DEPTH);
+	print_stack(&return_addrs[1], depth ? depth - 1 : 0, true);
+}
+
+void dump_frame_stack(const void *instruction, const void *frame)
+{
+	const void *return_addrs[MAX_DEPTH];
+	int depth;
+
+	return_addrs[0] = instruction;
+	depth = backtrace_frame(frame, &return_addrs[1], MAX_DEPTH - 1);
+	print_stack(return_addrs, depth + 1, false);
+}
+
+#ifndef HAVE_ARCH_BACKTRACE
+int backtrace(const void **return_addrs, int max_depth)
+{
+	static int walking;
+	int depth = 0;
+	void *addr;
+
+	if (walking) {
+		printf("RECURSIVE STACK WALK!!!\n");
+		return 0;
+	}
+	walking = 1;
+
+	/* __builtin_return_address requires a compile-time constant argument */
+#define GET_RETURN_ADDRESS(i)						\
+	if (max_depth == i)						\
+		goto done;						\
+	addr = __builtin_return_address(i);				\
+	if (!addr)							\
+		goto done;						\
+	return_addrs[i] = __builtin_extract_return_addr(addr);		\
+	depth = i + 1;							\
+
+	GET_RETURN_ADDRESS(0)
+	GET_RETURN_ADDRESS(1)
+	GET_RETURN_ADDRESS(2)
+	GET_RETURN_ADDRESS(3)
+	GET_RETURN_ADDRESS(4)
+	GET_RETURN_ADDRESS(5)
+	GET_RETURN_ADDRESS(6)
+	GET_RETURN_ADDRESS(7)
+	GET_RETURN_ADDRESS(8)
+	GET_RETURN_ADDRESS(9)
+	GET_RETURN_ADDRESS(10)
+	GET_RETURN_ADDRESS(11)
+	GET_RETURN_ADDRESS(12)
+	GET_RETURN_ADDRESS(13)
+	GET_RETURN_ADDRESS(14)
+	GET_RETURN_ADDRESS(15)
+	GET_RETURN_ADDRESS(16)
+	GET_RETURN_ADDRESS(17)
+	GET_RETURN_ADDRESS(18)
+	GET_RETURN_ADDRESS(19)
+	GET_RETURN_ADDRESS(20)
+
+#undef GET_RETURN_ADDRESS
+
+done:
+	walking = 0;
+	return depth;
+}
+#endif  /* HAVE_ARCH_BACKTRACE */

tests/kvm-unit-tests/lib/stack.h

@@ -0,0 +1,21 @@
+#ifndef _STACK_H_
+#define _STACK_H_
+
+#include <libcflat.h>
+#include <asm/stack.h>
+
+#ifdef HAVE_ARCH_BACKTRACE_FRAME
+extern int backtrace_frame(const void *frame, const void **return_addrs,
+			   int max_depth);
+#else
+static inline int
+backtrace_frame(const void *frame __unused, const void **return_addrs __unused,
+		int max_depth __unused)
+{
+	return 0;
+}
+#endif
+
+extern int backtrace(const void **return_addrs, int max_depth);
+
+#endif

tests/kvm-unit-tests/lib/string.c

@@ -0,0 +1,175 @@
+#include "libcflat.h"
+
+unsigned long strlen(const char *buf)
+{
+    unsigned long len = 0;
+
+    while (*buf++)
+	++len;
+    return len;
+}
+
+char *strcat(char *dest, const char *src)
+{
+    char *p = dest;
+
+    while (*p)
+	++p;
+    while ((*p++ = *src++) != 0)
+	;
+    return dest;
+}
+
+char *strcpy(char *dest, const char *src)
+{
+    *dest = 0;
+    return strcat(dest, src);
+}
+
+int strncmp(const char *a, const char *b, size_t n)
+{
+    for (; n--; ++a, ++b)
+        if (*a != *b || *a == '\0')
+            return *a - *b;
+
+    return 0;
+}
+
+int strcmp(const char *a, const char *b)
+{
+    return strncmp(a, b, SIZE_MAX);
+}
+
+char *strchr(const char *s, int c)
+{
+    while (*s != (char)c)
+	if (*s++ == '\0')
+	    return NULL;
+    return (char *)s;
+}
+
+char *strstr(const char *s1, const char *s2)
+{
+    size_t l1, l2;
+
+    l2 = strlen(s2);
+    if (!l2)
+	return (char *)s1;
+    l1 = strlen(s1);
+    while (l1 >= l2) {
+	l1--;
+	if (!memcmp(s1, s2, l2))
+	    return (char *)s1;
+	s1++;
+    }
+    return NULL;
+}
+
+void *memset(void *s, int c, size_t n)
+{
+    size_t i;
+    char *a = s;
+
+    for (i = 0; i < n; ++i)
+        a[i] = c;
+
+    return s;
+}
+
+void *memcpy(void *dest, const void *src, size_t n)
+{
+    size_t i;
+    char *a = dest;
+    const char *b = src;
+
+    for (i = 0; i < n; ++i)
+        a[i] = b[i];
+
+    return dest;
+}
+
+int memcmp(const void *s1, const void *s2, size_t n)
+{
+    const unsigned char *a = s1, *b = s2;
+    int ret = 0;
+
+    while (n--) {
+	ret = *a - *b;
+	if (ret)
+	    break;
+	++a, ++b;
+    }
+    return ret;
+}
+
+void *memmove(void *dest, const void *src, size_t n)
+{
+    const unsigned char *s = src;
+    unsigned char *d = dest;
+
+    if (d <= s) {
+	while (n--)
+	    *d++ = *s++;
+    } else {
+	d += n, s += n;
+	while (n--)
+	    *--d = *--s;
+    }
+    return dest;
+}
+
+void *memchr(const void *s, int c, size_t n)
+{
+    const unsigned char *str = s, chr = (unsigned char)c;
+
+    while (n--)
+	if (*str++ == chr)
+	    return (void *)(str - 1);
+    return NULL;
+}
+
+long atol(const char *ptr)
+{
+    long acc = 0;
+    const char *s = ptr;
+    int neg, c;
+
+    while (*s == ' ' || *s == '\t')
+        s++;
+    if (*s == '-'){
+        neg = 1;
+        s++;
+    } else {
+        neg = 0;
+        if (*s == '+')
+            s++;
+    }
+
+    while (*s) {
+        if (*s < '0' || *s > '9')
+            break;
+        c = *s - '0';
+        acc = acc * 10 + c;
+        s++;
+    }
+
+    if (neg)
+        acc = -acc;
+
+    return acc;
+}
+
+extern char **environ;
+
+char *getenv(const char *name)
+{
+    char **envp = environ, *delim;
+
+    while (*envp) {
+        delim = strchr(*envp, '=');
+        if (delim && strncmp(name, *envp, delim - *envp) == 0)
+            return delim + 1;
+        ++envp;
+    }
+    return NULL;
+}

tests/kvm-unit-tests/lib/string.h

@@ -0,0 +1,17 @@
+#ifndef __STRING_H
+#define __STRING_H
+
+extern unsigned long strlen(const char *buf);
+extern char *strcat(char *dest, const char *src);
+extern char *strcpy(char *dest, const char *src);
+extern int strcmp(const char *a, const char *b);
+extern int strncmp(const char *a, const char *b, size_t n);
+extern char *strchr(const char *s, int c);
+extern char *strstr(const char *haystack, const char *needle);
+extern void *memset(void *s, int c, size_t n);
+extern void *memcpy(void *dest, const void *src, size_t n);
+extern int memcmp(const void *s1, const void *s2, size_t n);
+extern void *memmove(void *dest, const void *src, size_t n);
+extern void *memchr(const void *s, int c, size_t n);
+
+#endif /* _STRING_H */

tests/kvm-unit-tests/lib/util.c

@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2016, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include <libcflat.h>
+
+int parse_keyval(char *s, long *val)
+{
+	char *p;
+
+	p = strchr(s, '=');
+	if (!p)
+		return -1;
+
+	*val = atol(p+1);
+	return p - s;
+}

tests/kvm-unit-tests/lib/util.h

@@ -0,0 +1,23 @@
+#ifndef _UTIL_H_
+#define _UTIL_H_
+/*
+ * Collection of utility functions to share between unit tests.
+ *
+ * Copyright (C) 2016, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+/*
+ * parse_keyval extracts the integer from a string formatted as
+ * string=integer. This is useful for passing expected values to
+ * the unit test on the command line, i.e. it helps parse QEMU
+ * command lines that include something like -append var1=1 var2=2
+ * @s is the input string, likely a command line parameter, and
+ * @val is a pointer to where the integer will be stored.
+ *
+ * Returns the offset of the '=', or -1 if no keyval pair is found.
+ */
+extern int parse_keyval(char *s, long *val);
+
+#endif

tests/kvm-unit-tests/lib/virtio-mmio.c

@@ -0,0 +1,177 @@
+/*
+ * virtqueue support adapted from the Linux kernel.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "devicetree.h"
+#include "alloc.h"
+#include "asm/page.h"
+#include "asm/io.h"
+#include "virtio.h"
+#include "virtio-mmio.h"
+
+static void vm_get(struct virtio_device *vdev, unsigned offset,
+		   void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u8 *p = buf;
+	unsigned i;
+
+	for (i = 0; i < len; ++i)
+		p[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static void vm_set(struct virtio_device *vdev, unsigned offset,
+		   const void *buf, unsigned len)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	const u8 *p = buf;
+	unsigned i;
+
+	for (i = 0; i < len; ++i)
+		writeb(p[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+}
+
+static bool vm_notify(struct virtqueue *vq)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
+	writel(vq->index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	return true;
+}
+
+static struct virtqueue *vm_setup_vq(struct virtio_device *vdev,
+				     unsigned index,
+				     void (*callback)(struct virtqueue *vq),
+				     const char *name)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	struct vring_virtqueue *vq;
+	void *queue;
+	unsigned num = VIRTIO_MMIO_QUEUE_NUM_MIN;
+
+	vq = calloc(1, sizeof(*vq));
+	queue = memalign(PAGE_SIZE, VIRTIO_MMIO_QUEUE_SIZE_MIN);
+	assert(vq && queue);
+
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+
+	assert(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX) >= num);
+
+	if (readl(vm_dev->base + VIRTIO_MMIO_QUEUE_PFN) != 0) {
+		printf("%s: virtqueue %d already setup! base=%p\n",
+				__func__, index, vm_dev->base);
+		return NULL;
+	}
+
+	writel(num, vm_dev->base + VIRTIO_MMIO_QUEUE_NUM);
+	writel(VIRTIO_MMIO_VRING_ALIGN,
+			vm_dev->base + VIRTIO_MMIO_QUEUE_ALIGN);
+	writel(virt_to_pfn(queue), vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
+
+	vring_init_virtqueue(vq, index, num, VIRTIO_MMIO_VRING_ALIGN,
+			     vdev, queue, vm_notify, callback, name);
+
+	return &vq->vq;
+}
+
+static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+		       struct virtqueue *vqs[], vq_callback_t *callbacks[],
+		       const char *names[])
+{
+	unsigned i;
+
+	for (i = 0; i < nvqs; ++i) {
+		vqs[i] = vm_setup_vq(vdev, i,
+				     callbacks ? callbacks[i] : NULL,
+				     names ? names[i] : "");
+		if (vqs[i] == NULL)
+			return -1;
+	}
+
+	return 0;
+}
+
+static const struct virtio_config_ops vm_config_ops = {
+	.get = vm_get,
+	.set = vm_set,
+	.find_vqs = vm_find_vqs,
+};
+
+static void vm_device_init(struct virtio_mmio_device *vm_dev)
+{
+	vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID);
+	vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
+	vm_dev->vdev.config = &vm_config_ops;
+
+	writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
+}
+
+/******************************************************
+ * virtio-mmio device tree support
+ ******************************************************/
+
+struct vm_dt_info {
+	u32 devid;
+	void *base;
+};
+
+static int vm_dt_match(const struct dt_device *dev, int fdtnode)
+{
+	struct vm_dt_info *info = (struct vm_dt_info *)dev->info;
+	struct dt_pbus_reg base;
+	u32 magic;
+	int ret;
+
+	dt_device_bind_node((struct dt_device *)dev, fdtnode);
+
+	ret = dt_pbus_get_base(dev, &base);
+	assert(ret == 0);
+	info->base = ioremap(base.addr, base.size);
+
+	magic = readl(info->base + VIRTIO_MMIO_MAGIC_VALUE);
+	if (magic != ('v' | 'i' << 8 | 'r' << 16 | 't' << 24))
+		return false;
+
+	return readl(info->base + VIRTIO_MMIO_DEVICE_ID) == info->devid;
+}
+
+static struct virtio_device *virtio_mmio_dt_bind(u32 devid)
+{
+	struct virtio_mmio_device *vm_dev;
+	struct dt_device dt_dev;
+	struct dt_bus dt_bus;
+	struct vm_dt_info info;
+	int node;
+
+	if (!dt_available())
+		return NULL;
+
+	dt_bus_init_defaults(&dt_bus);
+	dt_bus.match = vm_dt_match;
+
+	info.devid = devid;
+
+	dt_device_init(&dt_dev, &dt_bus, &info);
+
+	node = dt_device_find_compatible(&dt_dev, "virtio,mmio");
+	assert(node >= 0 || node == -FDT_ERR_NOTFOUND);
+
+	if (node == -FDT_ERR_NOTFOUND)
+		return NULL;
+
+	vm_dev = calloc(1, sizeof(*vm_dev));
+	assert(vm_dev != NULL);
+
+	vm_dev->base = info.base;
+	vm_device_init(vm_dev);
+
+	return &vm_dev->vdev;
+}
+
+struct virtio_device *virtio_mmio_bind(u32 devid)
+{
+	return virtio_mmio_dt_bind(devid);
+}

tests/kvm-unit-tests/lib/virtio-mmio.h

@@ -0,0 +1,65 @@
+#ifndef _VIRTIO_MMIO_H_
+#define _VIRTIO_MMIO_H_
+/*
+ * A minimal implementation of virtio-mmio. Adapted from the Linux Kernel.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "asm/page.h"
+#include "virtio.h"
+
+#define VIRTIO_MMIO_MAGIC_VALUE		0x000
+#define VIRTIO_MMIO_VERSION		0x004
+#define VIRTIO_MMIO_DEVICE_ID		0x008
+#define VIRTIO_MMIO_VENDOR_ID		0x00c
+#define VIRTIO_MMIO_HOST_FEATURES	0x010
+#define VIRTIO_MMIO_HOST_FEATURES_SEL	0x014
+#define VIRTIO_MMIO_GUEST_FEATURES	0x020
+#define VIRTIO_MMIO_GUEST_FEATURES_SEL	0x024
+#define VIRTIO_MMIO_GUEST_PAGE_SIZE	0x028
+#define VIRTIO_MMIO_QUEUE_SEL		0x030
+#define VIRTIO_MMIO_QUEUE_NUM_MAX	0x034
+#define VIRTIO_MMIO_QUEUE_NUM		0x038
+#define VIRTIO_MMIO_QUEUE_ALIGN		0x03c
+#define VIRTIO_MMIO_QUEUE_PFN		0x040
+#define VIRTIO_MMIO_QUEUE_NOTIFY	0x050
+#define VIRTIO_MMIO_INTERRUPT_STATUS	0x060
+#define VIRTIO_MMIO_INTERRUPT_ACK	0x064
+#define VIRTIO_MMIO_STATUS		0x070
+#define VIRTIO_MMIO_CONFIG		0x100
+
+#define VIRTIO_MMIO_INT_VRING		(1 << 0)
+#define VIRTIO_MMIO_INT_CONFIG		(1 << 1)
+
+#define VIRTIO_MMIO_VRING_ALIGN		PAGE_SIZE
+
+/*
+ * The minimum queue size is 2*VIRTIO_MMIO_VRING_ALIGN, which
+ * means the largest queue num for the minimum queue size is 128, i.e.
+ * 2*VIRTIO_MMIO_VRING_ALIGN = vring_size(128, VIRTIO_MMIO_VRING_ALIGN),
+ * where vring_size is
+ *
+ * unsigned vring_size(unsigned num, unsigned long align)
+ * {
+ *     return ((sizeof(struct vring_desc) * num + sizeof(u16) * (3 + num)
+ *              + align - 1) & ~(align - 1))
+ *             + sizeof(u16) * 3 + sizeof(struct vring_used_elem) * num;
+ * }
+ */
+#define VIRTIO_MMIO_QUEUE_SIZE_MIN	(2*VIRTIO_MMIO_VRING_ALIGN)
+#define VIRTIO_MMIO_QUEUE_NUM_MIN	128
+
+#define to_virtio_mmio_device(vdev_ptr) \
+	container_of(vdev_ptr, struct virtio_mmio_device, vdev)
+
+struct virtio_mmio_device {
+	struct virtio_device vdev;
+	void *base;
+};
+
+extern struct virtio_device *virtio_mmio_bind(u32 devid);
+
+#endif /* _VIRTIO_MMIO_H_ */

tests/kvm-unit-tests/lib/virtio.c

@@ -0,0 +1,130 @@
+/*
+ * virtqueue support adapted from the Linux kernel.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "asm/io.h"
+#include "virtio.h"
+#include "virtio-mmio.h"
+
+void vring_init(struct vring *vr, unsigned int num, void *p,
+		       unsigned long align)
+{
+	vr->num = num;
+	vr->desc = p;
+	vr->avail = p + num*sizeof(struct vring_desc);
+	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(u16)
+		+ align-1) & ~(align - 1));
+}
+
+void vring_init_virtqueue(struct vring_virtqueue *vq, unsigned index,
+			  unsigned num, unsigned vring_align,
+			  struct virtio_device *vdev, void *pages,
+			  bool (*notify)(struct virtqueue *),
+			  void (*callback)(struct virtqueue *),
+			  const char *name)
+{
+	unsigned i;
+
+	vring_init(&vq->vring, num, pages, vring_align);
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.name = name;
+	vq->vq.num_free = num;
+	vq->vq.index = index;
+	vq->notify = notify;
+	vq->last_used_idx = 0;
+	vq->num_added = 0;
+	vq->free_head = 0;
+
+	for (i = 0; i < num-1; i++) {
+		vq->vring.desc[i].next = i+1;
+		vq->data[i] = NULL;
+	}
+	vq->data[i] = NULL;
+}
+
+int virtqueue_add_outbuf(struct virtqueue *_vq, char *buf, unsigned int len)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned avail;
+	int head;
+
+	assert(buf != NULL);
+	assert(len != 0);
+
+	if (!vq->vq.num_free)
+		return -1;
+
+	--vq->vq.num_free;
+
+	head = vq->free_head;
+
+	vq->vring.desc[head].flags = 0;
+	vq->vring.desc[head].addr = virt_to_phys(buf);
+	vq->vring.desc[head].len = len;
+
+	vq->free_head = vq->vring.desc[head].next;
+
+	vq->data[head] = buf;
+
+	avail = (vq->vring.avail->idx & (vq->vring.num-1));
+	vq->vring.avail->ring[avail] = head;
+	wmb();
+	vq->vring.avail->idx++;
+	vq->num_added++;
+
+	return 0;
+}
+
+bool virtqueue_kick(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	mb();
+	return vq->notify(_vq);
+}
+
+void detach_buf(struct vring_virtqueue *vq, unsigned head)
+{
+	unsigned i = head;
+
+	vq->data[head] = NULL;
+
+	while (vq->vring.desc[i].flags & VRING_DESC_F_NEXT) {
+		i = vq->vring.desc[i].next;
+		vq->vq.num_free++;
+	}
+
+	vq->vring.desc[i].next = vq->free_head;
+	vq->free_head = head;
+	vq->vq.num_free++;
+}
+
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 last_used;
+	unsigned i;
+	void *ret;
+
+	rmb();
+
+	last_used = (vq->last_used_idx & (vq->vring.num-1));
+	i = vq->vring.used->ring[last_used].id;
+	*len = vq->vring.used->ring[last_used].len;
+
+	ret = vq->data[i];
+	detach_buf(vq, i);
+
+	vq->last_used_idx++;
+
+	return ret;
+}
+
+struct virtio_device *virtio_bind(u32 devid)
+{
+	return virtio_mmio_bind(devid);
+}

tests/kvm-unit-tests/lib/virtio.h

@@ -0,0 +1,150 @@
+#ifndef _VIRTIO_H_
+#define _VIRTIO_H_
+/*
+ * A minimal implementation of virtio.
+ * Structures adapted from the Linux Kernel.
+ *
+ * Copyright (C) 2014, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+#define VIRTIO_ID_CONSOLE 3
+
+struct virtio_device_id {
+	u32 device;
+	u32 vendor;
+};
+
+struct virtio_device {
+	struct virtio_device_id id;
+	const struct virtio_config_ops *config;
+};
+
+struct virtqueue {
+	void (*callback)(struct virtqueue *vq);
+	const char *name;
+	struct virtio_device *vdev;
+	unsigned int index;
+	unsigned int num_free;
+	void *priv;
+};
+
+typedef void vq_callback_t(struct virtqueue *);
+struct virtio_config_ops {
+	void (*get)(struct virtio_device *vdev, unsigned offset,
+		    void *buf, unsigned len);
+	void (*set)(struct virtio_device *vdev, unsigned offset,
+		    const void *buf, unsigned len);
+	int (*find_vqs)(struct virtio_device *vdev, unsigned nvqs,
+			struct virtqueue *vqs[],
+			vq_callback_t *callbacks[],
+			const char *names[]);
+};
+
+static inline u8
+virtio_config_readb(struct virtio_device *vdev, unsigned offset)
+{
+	u8 val;
+	vdev->config->get(vdev, offset, &val, 1);
+	return val;
+}
+
+static inline u16
+virtio_config_readw(struct virtio_device *vdev, unsigned offset)
+{
+	u16 val;
+	vdev->config->get(vdev, offset, &val, 2);
+	return val;
+}
+
+static inline u32
+virtio_config_readl(struct virtio_device *vdev, unsigned offset)
+{
+	u32 val;
+	vdev->config->get(vdev, offset, &val, 4);
+	return val;
+}
+
+static inline void
+virtio_config_writeb(struct virtio_device *vdev, unsigned offset, u8 val)
+{
+	vdev->config->set(vdev, offset, &val, 1);
+}
+
+static inline void
+virtio_config_writew(struct virtio_device *vdev, unsigned offset, u16 val)
+{
+	vdev->config->set(vdev, offset, &val, 2);
+}
+
+static inline void
+virtio_config_writel(struct virtio_device *vdev, unsigned offset, u32 val)
+{
+	vdev->config->set(vdev, offset, &val, 4);
+}
+
+#define VRING_DESC_F_NEXT	1
+#define VRING_DESC_F_WRITE	2
+
+struct vring_desc {
+	u64 addr;
+	u32 len;
+	u16 flags;
+	u16 next;
+};
+
+struct vring_avail {
+	u16 flags;
+	u16 idx;
+	u16 ring[];
+};
+
+struct vring_used_elem {
+	u32 id;
+	u32 len;
+};
+
+struct vring_used {
+	u16 flags;
+	u16 idx;
+	struct vring_used_elem ring[];
+};
+
+struct vring {
+	unsigned int num;
+	struct vring_desc *desc;
+	struct vring_avail *avail;
+	struct vring_used *used;
+};
+
+struct vring_virtqueue {
+	struct virtqueue vq;
+	struct vring vring;
+	unsigned int free_head;
+	unsigned int num_added;
+	u16 last_used_idx;
+	bool (*notify)(struct virtqueue *vq);
+	void *data[];
+};
+
+#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+
+extern void vring_init(struct vring *vr, unsigned int num, void *p,
+		       unsigned long align);
+extern void vring_init_virtqueue(struct vring_virtqueue *vq, unsigned index,
+				 unsigned num, unsigned vring_align,
+				 struct virtio_device *vdev, void *pages,
+				 bool (*notify)(struct virtqueue *),
+				 void (*callback)(struct virtqueue *),
+				 const char *name);
+extern int virtqueue_add_outbuf(struct virtqueue *vq, char *buf,
+				unsigned int len);
+extern bool virtqueue_kick(struct virtqueue *vq);
+extern void detach_buf(struct vring_virtqueue *vq, unsigned head);
+extern void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len);
+
+extern struct virtio_device *virtio_bind(u32 devid);
+
+#endif /* _VIRTIO_H_ */

tests/kvm-unit-tests/lib/x86/acpi.c

@@ -0,0 +1,52 @@
+#include "libcflat.h"
+#include "acpi.h"
+
+void* find_acpi_table_addr(u32 sig)
+{
+    unsigned long addr;
+    struct rsdp_descriptor *rsdp;
+    struct rsdt_descriptor_rev1 *rsdt;
+    void *end;
+    int i;
+
+    /* FACS is special... */
+    if (sig == FACS_SIGNATURE) {
+        struct fadt_descriptor_rev1 *fadt;
+        fadt = find_acpi_table_addr(FACP_SIGNATURE);
+        if (!fadt) {
+            return NULL;
+        }
+        return (void*)(ulong)fadt->firmware_ctrl;
+    }
+
+    for(addr = 0xf0000; addr < 0x100000; addr += 16) {
+	rsdp = (void*)addr;
+	if (rsdp->signature == 0x2052545020445352LL)
+          break;
+    }
+    if (addr == 0x100000) {
+        printf("Can't find RSDP\n");
+        return 0;
+    }
+
+    if (sig == RSDP_SIGNATURE) {
+        return rsdp;
+    }
+
+    rsdt = (void*)(ulong)rsdp->rsdt_physical_address;
+    if (!rsdt || rsdt->signature != RSDT_SIGNATURE)
+        return 0;
+
+    if (sig == RSDT_SIGNATURE) {
+        return rsdt;
+    }
+
+    end = (void*)rsdt + rsdt->length;
+    for (i=0; (void*)&rsdt->table_offset_entry[i] < end; i++) {
+        struct acpi_table *t = (void*)(ulong)rsdt->table_offset_entry[i];
+        if (t && t->signature == sig) {
+            return t;
+        }
+    }
+   return NULL;
+}

tests/kvm-unit-tests/lib/x86/acpi.h

@@ -0,0 +1,104 @@
+#ifndef KVM_ACPI_H
+#define KVM_ACPI_H 1
+
+#include "libcflat.h"
+
+#define ACPI_SIGNATURE(c1, c2, c3, c4) \
+	((c1) | ((c2) << 8) | ((c3) << 16) | ((c4) << 24))
+
+#define RSDP_SIGNATURE ACPI_SIGNATURE('R','S','D','P')
+#define RSDT_SIGNATURE ACPI_SIGNATURE('R','S','D','T')
+#define FACP_SIGNATURE ACPI_SIGNATURE('F','A','C','P')
+#define FACS_SIGNATURE ACPI_SIGNATURE('F','A','C','S')
+
+struct rsdp_descriptor {        /* Root System Descriptor Pointer */
+    u64 signature;              /* ACPI signature, contains "RSD PTR " */
+    u8  checksum;               /* To make sum of struct == 0 */
+    u8  oem_id [6];             /* OEM identification */
+    u8  revision;               /* Must be 0 for 1.0, 2 for 2.0 */
+    u32 rsdt_physical_address;  /* 32-bit physical address of RSDT */
+    u32 length;                 /* XSDT Length in bytes including hdr */
+    u64 xsdt_physical_address;  /* 64-bit physical address of XSDT */
+    u8  extended_checksum;      /* Checksum of entire table */
+    u8  reserved [3];           /* Reserved field must be 0 */
+};
+
+#define ACPI_TABLE_HEADER_DEF   /* ACPI common table header */ \
+    u32 signature;          /* ACPI signature (4 ASCII characters) */ \
+    u32 length;                 /* Length of table, in bytes, including header */ \
+    u8  revision;               /* ACPI Specification minor version # */ \
+    u8  checksum;               /* To make sum of entire table == 0 */ \
+    u8  oem_id [6];             /* OEM identification */ \
+    u8  oem_table_id [8];       /* OEM table identification */ \
+    u32 oem_revision;           /* OEM revision number */ \
+    u8  asl_compiler_id [4];    /* ASL compiler vendor ID */ \
+    u32 asl_compiler_revision;  /* ASL compiler revision number */
+
+struct acpi_table {
+    ACPI_TABLE_HEADER_DEF
+    char data[0];
+};
+
+struct rsdt_descriptor_rev1 {
+    ACPI_TABLE_HEADER_DEF
+    u32 table_offset_entry[0];
+};
+
+struct fadt_descriptor_rev1
+{
+    ACPI_TABLE_HEADER_DEF     /* ACPI common table header */
+    u32 firmware_ctrl;          /* Physical address of FACS */
+    u32 dsdt;                   /* Physical address of DSDT */
+    u8  model;                  /* System Interrupt Model */
+    u8  reserved1;              /* Reserved */
+    u16 sci_int;                /* System vector of SCI interrupt */
+    u32 smi_cmd;                /* Port address of SMI command port */
+    u8  acpi_enable;            /* Value to write to smi_cmd to enable ACPI */
+    u8  acpi_disable;           /* Value to write to smi_cmd to disable ACPI */
+    u8  S4bios_req;             /* Value to write to SMI CMD to enter S4BIOS state */
+    u8  reserved2;              /* Reserved - must be zero */
+    u32 pm1a_evt_blk;           /* Port address of Power Mgt 1a acpi_event Reg Blk */
+    u32 pm1b_evt_blk;           /* Port address of Power Mgt 1b acpi_event Reg Blk */
+    u32 pm1a_cnt_blk;           /* Port address of Power Mgt 1a Control Reg Blk */
+    u32 pm1b_cnt_blk;           /* Port address of Power Mgt 1b Control Reg Blk */
+    u32 pm2_cnt_blk;            /* Port address of Power Mgt 2 Control Reg Blk */
+    u32 pm_tmr_blk;             /* Port address of Power Mgt Timer Ctrl Reg Blk */
+    u32 gpe0_blk;               /* Port addr of General Purpose acpi_event 0 Reg Blk */
+    u32 gpe1_blk;               /* Port addr of General Purpose acpi_event 1 Reg Blk */
+    u8  pm1_evt_len;            /* Byte length of ports at pm1_x_evt_blk */
+    u8  pm1_cnt_len;            /* Byte length of ports at pm1_x_cnt_blk */
+    u8  pm2_cnt_len;            /* Byte Length of ports at pm2_cnt_blk */
+    u8  pm_tmr_len;             /* Byte Length of ports at pm_tm_blk */
+    u8  gpe0_blk_len;           /* Byte Length of ports at gpe0_blk */
+    u8  gpe1_blk_len;           /* Byte Length of ports at gpe1_blk */
+    u8  gpe1_base;              /* Offset in gpe model where gpe1 events start */
+    u8  reserved3;              /* Reserved */
+    u16 plvl2_lat;              /* Worst case HW latency to enter/exit C2 state */
+    u16 plvl3_lat;              /* Worst case HW latency to enter/exit C3 state */
+    u16 flush_size;             /* Size of area read to flush caches */
+    u16 flush_stride;           /* Stride used in flushing caches */
+    u8  duty_offset;            /* Bit location of duty cycle field in p_cnt reg */
+    u8  duty_width;             /* Bit width of duty cycle field in p_cnt reg */
+    u8  day_alrm;               /* Index to day-of-month alarm in RTC CMOS RAM */
+    u8  mon_alrm;               /* Index to month-of-year alarm in RTC CMOS RAM */
+    u8  century;                /* Index to century in RTC CMOS RAM */
+    u8  reserved4;              /* Reserved */
+    u8  reserved4a;             /* Reserved */
+    u8  reserved4b;             /* Reserved */
+};
+
+struct facs_descriptor_rev1
+{
+    u32 signature;           /* ACPI Signature */
+    u32 length;                 /* Length of structure, in bytes */
+    u32 hardware_signature;     /* Hardware configuration signature */
+    u32 firmware_waking_vector; /* ACPI OS waking vector */
+    u32 global_lock;            /* Global Lock */
+    u32 S4bios_f        : 1;    /* Indicates if S4BIOS support is present */
+    u32 reserved1       : 31;   /* Must be 0 */
+    u8  reserved3 [40];         /* Reserved - must be zero */
+};
+
+void* find_acpi_table_addr(u32 sig);
+
+#endif

tests/kvm-unit-tests/lib/x86/apic-defs.h

@@ -0,0 +1,138 @@
+#ifndef _ASM_X86_APICDEF_H
+#define _ASM_X86_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define	APIC_DEFAULT_PHYS_BASE	0xfee00000
+#define APIC_BSP		(1UL << 8)
+#define APIC_EXTD		(1UL << 10)
+#define APIC_EN			(1UL << 11)
+
+#define	APIC_ID		0x20
+
+#define	APIC_LVR	0x30
+#define		APIC_LVR_MASK		0xFF00FF
+#define		GET_APIC_VERSION(x)	((x) & 0xFFu)
+#define		GET_APIC_MAXLVT(x)	(((x) >> 16) & 0xFFu)
+#ifdef CONFIG_X86_32
+#  define	APIC_INTEGRATED(x)	((x) & 0xF0u)
+#else
+#  define	APIC_INTEGRATED(x)	(1)
+#endif
+#define		APIC_XAPIC(x)		((x) >= 0x14)
+#define	APIC_TASKPRI	0x80
+#define		APIC_TPRI_MASK		0xFFu
+#define	APIC_ARBPRI	0x90
+#define		APIC_ARBPRI_MASK	0xFFu
+#define	APIC_PROCPRI	0xA0
+#define	APIC_EOI	0xB0
+#define		APIC_EIO_ACK		0x0
+#define	APIC_RRR	0xC0
+#define	APIC_LDR	0xD0
+#define		APIC_LDR_MASK		(0xFFu << 24)
+#define		GET_APIC_LOGICAL_ID(x)	(((x) >> 24) & 0xFFu)
+#define		SET_APIC_LOGICAL_ID(x)	(((x) << 24))
+#define		APIC_ALL_CPUS		0xFFu
+#define	APIC_DFR	0xE0
+#define		APIC_DFR_CLUSTER		0x0FFFFFFFul
+#define		APIC_DFR_FLAT			0xFFFFFFFFul
+#define	APIC_SPIV	0xF0
+#define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
+#define		APIC_SPIV_APIC_ENABLED		(1 << 8)
+#define	APIC_ISR	0x100
+#define	APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
+#define	APIC_TMR	0x180
+#define	APIC_IRR	0x200
+#define	APIC_ESR	0x280
+#define		APIC_ESR_SEND_CS	0x00001
+#define		APIC_ESR_RECV_CS	0x00002
+#define		APIC_ESR_SEND_ACC	0x00004
+#define		APIC_ESR_RECV_ACC	0x00008
+#define		APIC_ESR_SENDILL	0x00020
+#define		APIC_ESR_RECVILL	0x00040
+#define		APIC_ESR_ILLREGA	0x00080
+#define	APIC_ICR	0x300
+#define		APIC_DEST_SELF		0x40000
+#define		APIC_DEST_ALLINC	0x80000
+#define		APIC_DEST_ALLBUT	0xC0000
+#define		APIC_ICR_RR_MASK	0x30000
+#define		APIC_ICR_RR_INVALID	0x00000
+#define		APIC_ICR_RR_INPROG	0x10000
+#define		APIC_ICR_RR_VALID	0x20000
+#define		APIC_INT_LEVELTRIG	0x08000
+#define		APIC_INT_ASSERT		0x04000
+#define		APIC_ICR_BUSY		0x01000
+#define		APIC_DEST_LOGICAL	0x00800
+#define		APIC_DEST_PHYSICAL	0x00000
+#define		APIC_DM_FIXED		0x00000
+#define		APIC_DM_LOWEST		0x00100
+#define		APIC_DM_SMI		0x00200
+#define		APIC_DM_REMRD		0x00300
+#define		APIC_DM_NMI		0x00400
+#define		APIC_DM_INIT		0x00500
+#define		APIC_DM_STARTUP		0x00600
+#define		APIC_DM_EXTINT		0x00700
+#define		APIC_VECTOR_MASK	0x000FF
+#define	APIC_ICR2	0x310
+#define		GET_APIC_DEST_FIELD(x)	(((x) >> 24) & 0xFF)
+#define		SET_APIC_DEST_FIELD(x)	((x) << 24)
+#define	APIC_LVTT	0x320
+#define	APIC_LVTTHMR	0x330
+#define	APIC_LVTPC	0x340
+#define	APIC_LVT0	0x350
+#define		APIC_LVT_TIMER_BASE_MASK	(0x3 << 18)
+#define		GET_APIC_TIMER_BASE(x)		(((x) >> 18) & 0x3)
+#define		SET_APIC_TIMER_BASE(x)		(((x) << 18))
+#define		APIC_TIMER_BASE_CLKIN		0x0
+#define		APIC_TIMER_BASE_TMBASE		0x1
+#define		APIC_TIMER_BASE_DIV		0x2
+#define		APIC_LVT_TIMER_ONESHOT		(0 << 17)
+#define		APIC_LVT_TIMER_PERIODIC		(1 << 17)
+#define		APIC_LVT_TIMER_TSCDEADLINE	(2 << 17)
+#define		APIC_LVT_MASKED			(1 << 16)
+#define		APIC_LVT_LEVEL_TRIGGER		(1 << 15)
+#define		APIC_LVT_REMOTE_IRR		(1 << 14)
+#define		APIC_INPUT_POLARITY		(1 << 13)
+#define		APIC_SEND_PENDING		(1 << 12)
+#define		APIC_MODE_MASK			0x700
+#define		GET_APIC_DELIVERY_MODE(x)	(((x) >> 8) & 0x7)
+#define		SET_APIC_DELIVERY_MODE(x, y)	(((x) & ~0x700) | ((y) << 8))
+#define			APIC_MODE_FIXED		0x0
+#define			APIC_MODE_NMI		0x4
+#define			APIC_MODE_EXTINT	0x7
+#define	APIC_LVT1	0x360
+#define	APIC_LVTERR	0x370
+#define	APIC_TMICT	0x380
+#define	APIC_TMCCT	0x390
+#define	APIC_TDCR	0x3E0
+#define APIC_SELF_IPI	0x3F0
+#define		APIC_TDR_DIV_TMBASE	(1 << 2)
+#define		APIC_TDR_DIV_1		0xB
+#define		APIC_TDR_DIV_2		0x0
+#define		APIC_TDR_DIV_4		0x1
+#define		APIC_TDR_DIV_8		0x2
+#define		APIC_TDR_DIV_16		0x3
+#define		APIC_TDR_DIV_32		0x8
+#define		APIC_TDR_DIV_64		0x9
+#define		APIC_TDR_DIV_128	0xA
+#define	APIC_EILVT0     0x500
+#define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
+#define		APIC_EILVT_NR_AMD_10H	4
+#define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
+#define		APIC_EILVT_MSG_FIX	0x0
+#define		APIC_EILVT_MSG_SMI	0x2
+#define		APIC_EILVT_MSG_NMI	0x4
+#define		APIC_EILVT_MSG_EXT	0x7
+#define		APIC_EILVT_MASKED	(1 << 16)
+#define	APIC_EILVT1     0x510
+#define	APIC_EILVT2     0x520
+#define	APIC_EILVT3     0x530
+
+#define APIC_BASE_MSR	0x800
+
+#endif /* _ASM_X86_APICDEF_H */

tests/kvm-unit-tests/lib/x86/apic.c

@@ -0,0 +1,208 @@
+#include "libcflat.h"
+#include "apic.h"
+#include "msr.h"
+#include "processor.h"
+
+static void *g_apic = (void *)0xfee00000;
+static void *g_ioapic = (void *)0xfec00000;
+
+struct apic_ops {
+    u32 (*reg_read)(unsigned reg);
+    void (*reg_write)(unsigned reg, u32 val);
+    void (*icr_write)(u32 val, u32 dest);
+    u32 (*id)(void);
+};
+
+static void outb(unsigned char data, unsigned short port)
+{
+    asm volatile ("out %0, %1" : : "a"(data), "d"(port));
+}
+
+void eoi(void)
+{
+    apic_write(APIC_EOI, 0);
+}
+
+static u32 xapic_read(unsigned reg)
+{
+    return *(volatile u32 *)(g_apic + reg);
+}
+
+static void xapic_write(unsigned reg, u32 val)
+{
+    *(volatile u32 *)(g_apic + reg) = val;
+}
+
+static void xapic_icr_write(u32 val, u32 dest)
+{
+    while (xapic_read(APIC_ICR) & APIC_ICR_BUSY)
+        ;
+    xapic_write(APIC_ICR2, dest << 24);
+    xapic_write(APIC_ICR, val);
+}
+
+static uint32_t xapic_id(void)
+{
+    return xapic_read(APIC_ID) >> 24;
+}
+
+static const struct apic_ops xapic_ops = {
+    .reg_read = xapic_read,
+    .reg_write = xapic_write,
+    .icr_write = xapic_icr_write,
+    .id = xapic_id,
+};
+
+static const struct apic_ops *apic_ops = &xapic_ops;
+
+static u32 x2apic_read(unsigned reg)
+{
+    unsigned a, d;
+
+    asm volatile ("rdmsr" : "=a"(a), "=d"(d) : "c"(APIC_BASE_MSR + reg/16));
+    return a | (u64)d << 32;
+}
+
+static void x2apic_write(unsigned reg, u32 val)
+{
+    asm volatile ("wrmsr" : : "a"(val), "d"(0), "c"(APIC_BASE_MSR + reg/16));
+}
+
+static void x2apic_icr_write(u32 val, u32 dest)
+{
+    asm volatile ("wrmsr" : : "a"(val), "d"(dest),
+                  "c"(APIC_BASE_MSR + APIC_ICR/16));
+}
+
+static uint32_t x2apic_id(void)
+{
+    return x2apic_read(APIC_ID);
+}
+
+static const struct apic_ops x2apic_ops = {
+    .reg_read = x2apic_read,
+    .reg_write = x2apic_write,
+    .icr_write = x2apic_icr_write,
+    .id = x2apic_id,
+};
+
+u32 apic_read(unsigned reg)
+{
+    return apic_ops->reg_read(reg);
+}
+
+void apic_write(unsigned reg, u32 val)
+{
+    apic_ops->reg_write(reg, val);
+}
+
+bool apic_read_bit(unsigned reg, int n)
+{
+    reg += (n >> 5) << 4;
+    n &= 31;
+    return (apic_read(reg) & (1 << n)) != 0;
+}
+
+void apic_icr_write(u32 val, u32 dest)
+{
+    apic_ops->icr_write(val, dest);
+}
+
+uint32_t apic_id(void)
+{
+    return apic_ops->id();
+}
+
+uint8_t apic_get_tpr(void)
+{
+	unsigned long tpr;
+
+#ifdef __x86_64__
+	asm volatile ("mov %%cr8, %0" : "=r"(tpr));
+#else
+	tpr = apic_read(APIC_TASKPRI) >> 4;
+#endif
+	return tpr;
+}
+
+void apic_set_tpr(uint8_t tpr)
+{
+#ifdef __x86_64__
+	asm volatile ("mov %0, %%cr8" : : "r"((unsigned long) tpr));
+#else
+	apic_write(APIC_TASKPRI, tpr << 4);
+#endif
+}
+
+int enable_x2apic(void)
+{
+    unsigned a, b, c, d;
+
+    asm ("cpuid" : "=a"(a), "=b"(b), "=c"(c), "=d"(d) : "0"(1));
+
+    if (c & (1 << 21)) {
+        asm ("rdmsr" : "=a"(a), "=d"(d) : "c"(MSR_IA32_APICBASE));
+        a |= 1 << 10;
+        asm ("wrmsr" : : "a"(a), "d"(d), "c"(MSR_IA32_APICBASE));
+        apic_ops = &x2apic_ops;
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+void reset_apic(void)
+{
+    u64 disabled = rdmsr(MSR_IA32_APICBASE) & ~(APIC_EN | APIC_EXTD);
+    wrmsr(MSR_IA32_APICBASE, disabled);
+    apic_ops = &xapic_ops;
+    wrmsr(MSR_IA32_APICBASE, disabled | APIC_EN);
+}
+
+u32 ioapic_read_reg(unsigned reg)
+{
+    *(volatile u32 *)g_ioapic = reg;
+    return *(volatile u32 *)(g_ioapic + 0x10);
+}
+
+void ioapic_write_reg(unsigned reg, u32 value)
+{
+    *(volatile u32 *)g_ioapic = reg;
+    *(volatile u32 *)(g_ioapic + 0x10) = value;
+}
+
+void ioapic_write_redir(unsigned line, ioapic_redir_entry_t e)
+{
+    ioapic_write_reg(0x10 + line * 2 + 0, ((u32 *)&e)[0]);
+    ioapic_write_reg(0x10 + line * 2 + 1, ((u32 *)&e)[1]);
+}
+
+ioapic_redir_entry_t ioapic_read_redir(unsigned line)
+{
+    ioapic_redir_entry_t e;
+
+    ((u32 *)&e)[0] = ioapic_read_reg(0x10 + line * 2 + 0);
+    ((u32 *)&e)[1] = ioapic_read_reg(0x10 + line * 2 + 1);
+    return e;
+
+}
+
+void set_mask(unsigned line, int mask)
+{
+    ioapic_redir_entry_t e = ioapic_read_redir(line);
+
+    e.mask = mask;
+    ioapic_write_redir(line, e);
+}
+
+void enable_apic(void)
+{
+    printf("enabling apic\n");
+    xapic_write(0xf0, 0x1ff); /* spurious vector register */
+}
+
+void mask_pic_interrupts(void)
+{
+    outb(0xff, 0x21);
+    outb(0xff, 0xa1);
+}

tests/kvm-unit-tests/lib/x86/apic.h

@@ -0,0 +1,50 @@
+#ifndef CFLAT_APIC_H
+#define CFLAT_APIC_H
+
+#include <stdint.h>
+#include "apic-defs.h"
+
+typedef struct {
+    uint8_t vector;
+    uint8_t delivery_mode:3;
+    uint8_t dest_mode:1;
+    uint8_t delivery_status:1;
+    uint8_t polarity:1;
+    uint8_t remote_irr:1;
+    uint8_t trig_mode:1;
+    uint8_t mask:1;
+    uint8_t reserve:7;
+    uint8_t reserved[4];
+    uint8_t dest_id;
+} ioapic_redir_entry_t;
+
+typedef enum trigger_mode {
+	TRIGGER_EDGE = 0,
+	TRIGGER_LEVEL,
+	TRIGGER_MAX,
+} trigger_mode_t;
+
+void mask_pic_interrupts(void);
+
+void eoi(void);
+uint8_t apic_get_tpr(void);
+void apic_set_tpr(uint8_t tpr);
+
+void ioapic_write_redir(unsigned line, ioapic_redir_entry_t e);
+void ioapic_write_reg(unsigned reg, uint32_t value);
+ioapic_redir_entry_t ioapic_read_redir(unsigned line);
+uint32_t ioapic_read_reg(unsigned reg);
+
+void set_mask(unsigned line, int mask);
+
+void enable_apic(void);
+uint32_t apic_read(unsigned reg);
+bool apic_read_bit(unsigned reg, int n);
+void apic_write(unsigned reg, uint32_t val);
+void apic_icr_write(uint32_t val, uint32_t dest);
+uint32_t apic_id(void);
+
+int enable_x2apic(void);
+void reset_apic(void);
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/barrier.h

@@ -0,0 +1,27 @@
+#ifndef _ASM_X86_BARRIER_H_
+#define _ASM_X86_BARRIER_H_
+/*
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+#define mb()	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence":::"memory")
+
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+	asm volatile("rep; nop" ::: "memory");
+}
+
+static inline void cpu_relax(void)
+{
+	rep_nop();
+}
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/bitops.h

@@ -0,0 +1,14 @@
+#ifndef _ASMX86_BITOPS_H_
+#define _ASMX86_BITOPS_H_
+
+#ifndef _BITOPS_H_
+#error only <bitops.h> can be included directly
+#endif
+
+#ifdef __x86_64__
+#define BITS_PER_LONG	64
+#else
+#define BITS_PER_LONG	32
+#endif
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/io.h

@@ -0,0 +1,65 @@
+#ifndef _ASM_X86_IO_H_
+#define _ASM_X86_IO_H_
+
+#define __iomem
+
+#define inb inb
+static inline uint8_t inb(unsigned long port)
+{
+    unsigned char value;
+    asm volatile("inb %w1, %0" : "=a" (value) : "Nd" ((unsigned short)port));
+    return value;
+}
+
+#define inw inw
+static inline uint16_t inw(unsigned long port)
+{
+    unsigned short value;
+    asm volatile("inw %w1, %0" : "=a" (value) : "Nd" ((unsigned short)port));
+    return value;
+}
+
+#define inl inl
+static inline uint32_t inl(unsigned long port)
+{
+    unsigned int value;
+    asm volatile("inl %w1, %0" : "=a" (value) : "Nd" ((unsigned short)port));
+    return value;
+}
+
+#define outb outb
+static inline void outb(uint8_t value, unsigned long port)
+{
+    asm volatile("outb %b0, %w1" : : "a"(value), "Nd"((unsigned short)port));
+}
+
+#define outw outw
+static inline void outw(uint16_t value, unsigned long port)
+{
+    asm volatile("outw %w0, %w1" : : "a"(value), "Nd"((unsigned short)port));
+}
+
+#define outl outl
+static inline void outl(uint32_t value, unsigned long port)
+{
+    asm volatile("outl %0, %w1" : : "a"(value), "Nd"((unsigned short)port));
+}
+
+#define virt_to_phys virt_to_phys
+static inline unsigned long virt_to_phys(const void *virt)
+{
+    return (unsigned long)virt;
+}
+
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(unsigned long phys)
+{
+    return (void *)phys;
+}
+
+#define ioremap ioremap
+void __iomem *ioremap(phys_addr_t phys_addr, size_t size);
+
+#include <asm-generic/io.h>
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/page.h

@@ -0,0 +1,48 @@
+#ifndef _ASM_X86_PAGE_H_
+#define _ASM_X86_PAGE_H_
+/*
+ * Copyright (C) 2016, Red Hat Inc, Alexander Gordeev <agordeev@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+
+
+#include <linux/const.h>
+#include <bitops.h>
+
+#define PAGE_SHIFT	12
+#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#ifndef __ASSEMBLY__
+
+#ifdef __x86_64__
+#define LARGE_PAGE_SIZE	(512 * PAGE_SIZE)
+#else
+#define LARGE_PAGE_SIZE	(1024 * PAGE_SIZE)
+#endif
+
+#define PT_PRESENT_MASK		(1ull << 0)
+#define PT_WRITABLE_MASK	(1ull << 1)
+#define PT_USER_MASK		(1ull << 2)
+#define PT_ACCESSED_MASK	(1ull << 5)
+#define PT_DIRTY_MASK		(1ull << 6)
+#define PT_PAGE_SIZE_MASK	(1ull << 7)
+#define PT64_NX_MASK		(1ull << 63)
+#define PT_ADDR_MASK		GENMASK_ULL(51, 12)
+
+#ifdef __x86_64__
+#define	PAGE_LEVEL	4
+#define	PGDIR_WIDTH	9
+#define	PGDIR_MASK	511
+#else
+#define	PAGE_LEVEL	2
+#define	PGDIR_WIDTH	10
+#define	PGDIR_MASK	1023
+#endif
+
+#define PGDIR_BITS(lvl)        (((lvl) - 1) * PGDIR_WIDTH + PAGE_SHIFT)
+#define PGDIR_OFFSET(va, lvl)  (((va) >> PGDIR_BITS(lvl)) & PGDIR_MASK)
+
+#endif /* !__ASSEMBLY__ */
+#endif

tests/kvm-unit-tests/lib/x86/asm/pci.h

@@ -0,0 +1,59 @@
+#ifndef ASM_PCI_H
+#define ASM_PCI_H
+/*
+ * Copyright (C) 2013, Red Hat Inc, Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+#include "pci.h"
+#include "x86/asm/io.h"
+
+#define PCI_CONF1_ADDRESS(dev, reg)	((0x1 << 31) | (dev << 8) | reg)
+
+static inline uint8_t pci_config_readb(pcidevaddr_t dev, uint8_t reg)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    return inb(0xCFC);
+}
+
+static inline uint16_t pci_config_readw(pcidevaddr_t dev, uint8_t reg)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    return inw(0xCFC);
+}
+
+static inline uint32_t pci_config_readl(pcidevaddr_t dev, uint8_t reg)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    return inl(0xCFC);
+}
+
+static inline void pci_config_writeb(pcidevaddr_t dev, uint8_t reg,
+                                     uint8_t val)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    outb(val, 0xCFC);
+}
+
+static inline void pci_config_writew(pcidevaddr_t dev, uint8_t reg,
+                                     uint16_t val)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    outw(val, 0xCFC);
+}
+
+static inline void pci_config_writel(pcidevaddr_t dev, uint8_t reg,
+                                     uint32_t val)
+{
+    outl(PCI_CONF1_ADDRESS(dev, reg), 0xCF8);
+    outl(val, 0xCFC);
+}
+
+static inline
+phys_addr_t pci_translate_addr(pcidevaddr_t dev __unused, uint64_t addr)
+{
+    return addr;
+}
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/spinlock.h

@@ -0,0 +1,11 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+struct spinlock {
+    int v;
+};
+
+void spin_lock(struct spinlock *lock);
+void spin_unlock(struct spinlock *lock);
+
+#endif

tests/kvm-unit-tests/lib/x86/asm/stack.h

@@ -0,0 +1,11 @@
+#ifndef _X86ASM_STACK_H_
+#define _X86ASM_STACK_H_
+
+#ifndef _STACK_H_
+#error Do not directly include <asm/stack.h>. Just use <stack.h>.
+#endif
+
+#define HAVE_ARCH_BACKTRACE_FRAME
+#define HAVE_ARCH_BACKTRACE
+
+#endif

tests/kvm-unit-tests/lib/x86/atomic.c

@@ -0,0 +1,37 @@
+#include <libcflat.h>
+#include "atomic.h"
+
+#ifdef __i386__
+
+u64 atomic64_cmpxchg(atomic64_t *v, u64 old, u64 new)
+{
+        u32 low = new;
+        u32 high = new >> 32;
+
+        asm volatile("lock cmpxchg8b %1\n"
+                     : "+A" (old),
+                       "+m" (*(volatile long long *)&v->counter)
+                     : "b" (low), "c" (high)
+                     : "memory"
+                     );
+
+        return old;
+}
+
+#else
+
+u64 atomic64_cmpxchg(atomic64_t *v, u64 old, u64 new)
+{
+        u64 ret;
+        u64 _old = old;
+        u64 _new = new;
+
+        asm volatile("lock cmpxchgq %2,%1"
+                     : "=a" (ret), "+m" (*(volatile long *)&v->counter)
+                     : "r" (_new), "0" (_old)
+                     : "memory"
+                     );
+        return ret;
+}
+
+#endif

tests/kvm-unit-tests/lib/x86/atomic.h

@@ -0,0 +1,166 @@
+#ifndef __ATOMIC_H
+#define __ATOMIC_H
+
+#include "asm-generic/atomic.h"
+
+typedef struct {
+	volatile int counter;
+} atomic_t;
+
+#ifdef __i386__
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return v->counter;
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile("lock incl %0"
+		     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+	asm volatile("lock decl %0"
+		     : "+m" (v->counter));
+}
+
+typedef struct {
+	u64 __attribute__((aligned(8))) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(val)	{ (val) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @ptr:      pointer to type atomic64_t
+ *
+ * Atomically reads the value of @ptr and returns it.
+ */
+static inline u64 atomic64_read(atomic64_t *ptr)
+{
+	u64 res;
+
+	/*
+	 * Note, we inline this atomic64_t primitive because
+	 * it only clobbers EAX/EDX and leaves the others
+	 * untouched. We also (somewhat subtly) rely on the
+	 * fact that cmpxchg8b returns the current 64-bit value
+	 * of the memory location we are touching:
+	 */
+	asm volatile("mov %%ebx, %%eax\n\t"
+                     "mov %%ecx, %%edx\n\t"
+                     "lock cmpxchg8b %1\n"
+                     : "=&A" (res)
+                     : "m" (*ptr)
+                     );
+	return res;
+}
+
+u64 atomic64_cmpxchg(atomic64_t *v, u64 old, u64 new);
+
+#elif defined(__x86_64__)
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return v->counter;
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile("lock incl %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+	asm volatile("lock decl %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+typedef struct {
+	long long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i)	{ (i) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+static inline long atomic64_read(const atomic64_t *v)
+{
+	return v->counter;
+}
+
+u64 atomic64_cmpxchg(atomic64_t *v, u64 old, u64 new);
+
+#endif
+
+#endif

tests/kvm-unit-tests/lib/x86/desc.c

@@ -0,0 +1,407 @@
+#include "libcflat.h"
+#include "desc.h"
+#include "processor.h"
+#include <setjmp.h>
+
+void set_idt_entry(int vec, void *addr, int dpl)
+{
+    idt_entry_t *e = &boot_idt[vec];
+    memset(e, 0, sizeof *e);
+    e->offset0 = (unsigned long)addr;
+    e->selector = read_cs();
+    e->ist = 0;
+    e->type = 14;
+    e->dpl = dpl;
+    e->p = 1;
+    e->offset1 = (unsigned long)addr >> 16;
+#ifdef __x86_64__
+    e->offset2 = (unsigned long)addr >> 32;
+#endif
+}
+
+void set_idt_dpl(int vec, u16 dpl)
+{
+    idt_entry_t *e = &boot_idt[vec];
+    e->dpl = dpl;
+}
+
+void set_idt_sel(int vec, u16 sel)
+{
+    idt_entry_t *e = &boot_idt[vec];
+    e->selector = sel;
+}
+
+struct ex_record {
+    unsigned long rip;
+    unsigned long handler;
+};
+
+extern struct ex_record exception_table_start, exception_table_end;
+
+static const char* exception_mnemonic(int vector)
+{
+	switch(vector) {
+	case 0: return "#DE";
+	case 1: return "#DB";
+	case 2: return "#NMI";
+	case 3: return "#BP";
+	case 4: return "#OF";
+	case 5: return "#BR";
+	case 6: return "#UD";
+	case 7: return "#NM";
+	case 8: return "#DF";
+	case 10: return "#TS";
+	case 11: return "#NP";
+	case 12: return "#SS";
+	case 13: return "#GP";
+	case 14: return "#PF";
+	case 16: return "#MF";
+	case 17: return "#AC";
+	case 18: return "#MC";
+	case 19: return "#XM";
+	default: return "#??";
+	}
+}
+
+static void unhandled_exception(struct ex_regs *regs, bool cpu)
+{
+	printf("Unhandled %sexception %ld %s at ip %016lx\n",
+	       cpu ? "cpu " : "", regs->vector,
+	       exception_mnemonic(regs->vector), regs->rip);
+	if (regs->vector == 14)
+		printf("PF at 0x%lx addr 0x%lx\n", regs->rip, read_cr2());
+
+	printf("error_code=%04lx      rflags=%08lx      cs=%08lx\n"
+	       "rax=%016lx rcx=%016lx rdx=%016lx rbx=%016lx\n"
+	       "rbp=%016lx rsi=%016lx rdi=%016lx\n"
+#ifdef __x86_64__
+	       " r8=%016lx  r9=%016lx r10=%016lx r11=%016lx\n"
+	       "r12=%016lx r13=%016lx r14=%016lx r15=%016lx\n"
+#endif
+	       "cr0=%016lx cr2=%016lx cr3=%016lx cr4=%016lx\n"
+#ifdef __x86_64__
+	       "cr8=%016lx\n"
+#endif
+	       ,
+	       regs->error_code, regs->rflags, regs->cs,
+	       regs->rax, regs->rcx, regs->rdx, regs->rbx,
+	       regs->rbp, regs->rsi, regs->rdi,
+#ifdef __x86_64__
+	       regs->r8, regs->r9, regs->r10, regs->r11,
+	       regs->r12, regs->r13, regs->r14, regs->r15,
+#endif
+	       read_cr0(), read_cr2(), read_cr3(), read_cr4()
+#ifdef __x86_64__
+	       , read_cr8()
+#endif
+	);
+	dump_frame_stack((void*) regs->rip, (void*) regs->rbp);
+	abort();
+}
+
+static void check_exception_table(struct ex_regs *regs)
+{
+    struct ex_record *ex;
+    unsigned ex_val;
+
+    ex_val = regs->vector | (regs->error_code << 16) |
+		(((regs->rflags >> 16) & 1) << 8);
+    asm("mov %0, %%gs:4" : : "r"(ex_val));
+
+    for (ex = &exception_table_start; ex != &exception_table_end; ++ex) {
+        if (ex->rip == regs->rip) {
+            regs->rip = ex->handler;
+            return;
+        }
+    }
+    unhandled_exception(regs, false);
+}
+
+static void (*exception_handlers[32])(struct ex_regs *regs);
+
+
+void handle_exception(u8 v, void (*func)(struct ex_regs *regs))
+{
+	if (v < 32)
+		exception_handlers[v] = func;
+}
+
+#ifndef __x86_64__
+__attribute__((regparm(1)))
+#endif
+void do_handle_exception(struct ex_regs *regs)
+{
+	if (regs->vector < 32 && exception_handlers[regs->vector]) {
+		exception_handlers[regs->vector](regs);
+		return;
+	}
+	unhandled_exception(regs, true);
+}
+
+#define EX(NAME, N) extern char NAME##_fault;	\
+	asm (".pushsection .text \n\t"		\
+	     #NAME"_fault: \n\t"		\
+	     "push"W" $0 \n\t"			\
+	     "push"W" $"#N" \n\t"		\
+	     "jmp __handle_exception \n\t"	\
+	     ".popsection")
+
+#define EX_E(NAME, N) extern char NAME##_fault;	\
+	asm (".pushsection .text \n\t"		\
+	     #NAME"_fault: \n\t"		\
+	     "push"W" $"#N" \n\t"		\
+	     "jmp __handle_exception \n\t"	\
+	     ".popsection")
+
+EX(de, 0);
+EX(db, 1);
+EX(nmi, 2);
+EX(bp, 3);
+EX(of, 4);
+EX(br, 5);
+EX(ud, 6);
+EX(nm, 7);
+EX_E(df, 8);
+EX_E(ts, 10);
+EX_E(np, 11);
+EX_E(ss, 12);
+EX_E(gp, 13);
+EX_E(pf, 14);
+EX(mf, 16);
+EX_E(ac, 17);
+EX(mc, 18);
+EX(xm, 19);
+
+asm (".pushsection .text \n\t"
+     "__handle_exception: \n\t"
+#ifdef __x86_64__
+     "push %r15; push %r14; push %r13; push %r12 \n\t"
+     "push %r11; push %r10; push %r9; push %r8 \n\t"
+#endif
+     "push %"R "di; push %"R "si; push %"R "bp; sub $"S", %"R "sp \n\t"
+     "push %"R "bx; push %"R "dx; push %"R "cx; push %"R "ax \n\t"
+#ifdef __x86_64__
+     "mov %"R "sp, %"R "di \n\t"
+#else
+     "mov %"R "sp, %"R "ax \n\t"
+#endif
+     "call do_handle_exception \n\t"
+     "pop %"R "ax; pop %"R "cx; pop %"R "dx; pop %"R "bx \n\t"
+     "add $"S", %"R "sp; pop %"R "bp; pop %"R "si; pop %"R "di \n\t"
+#ifdef __x86_64__
+     "pop %r8; pop %r9; pop %r10; pop %r11 \n\t"
+     "pop %r12; pop %r13; pop %r14; pop %r15 \n\t"
+#endif
+     "add $"S", %"R "sp \n\t"
+     "add $"S", %"R "sp \n\t"
+     "iret"W" \n\t"
+     ".popsection");
+
+static void *idt_handlers[32] = {
+	[0] = &de_fault,
+	[1] = &db_fault,
+	[2] = &nmi_fault,
+	[3] = &bp_fault,
+	[4] = &of_fault,
+	[5] = &br_fault,
+	[6] = &ud_fault,
+	[7] = &nm_fault,
+	[8] = &df_fault,
+	[10] = &ts_fault,
+	[11] = &np_fault,
+	[12] = &ss_fault,
+	[13] = &gp_fault,
+	[14] = &pf_fault,
+	[16] = &mf_fault,
+	[17] = &ac_fault,
+	[18] = &mc_fault,
+	[19] = &xm_fault,
+};
+
+void setup_idt(void)
+{
+    int i;
+    static bool idt_initialized = false;
+
+    if (idt_initialized) {
+        return;
+    }
+    idt_initialized = true;
+    for (i = 0; i < 32; i++)
+	    if (idt_handlers[i])
+		    set_idt_entry(i, idt_handlers[i], 0);
+    handle_exception(0, check_exception_table);
+    handle_exception(6, check_exception_table);
+    handle_exception(13, check_exception_table);
+}
+
+unsigned exception_vector(void)
+{
+    unsigned char vector;
+
+    asm("movb %%gs:4, %0" : "=q"(vector));
+    return vector;
+}
+
+unsigned exception_error_code(void)
+{
+    unsigned short error_code;
+
+    asm("mov %%gs:6, %0" : "=rm"(error_code));
+    return error_code;
+}
+
+bool exception_rflags_rf(void)
+{
+    unsigned char rf_flag;
+
+    asm("movb %%gs:5, %b0" : "=q"(rf_flag));
+    return rf_flag & 1;
+}
+
+static char intr_alt_stack[4096];
+
+#ifndef __x86_64__
+/*
+ * GDT, with 6 entries:
+ * 0x00 - NULL descriptor
+ * 0x08 - Code segment (ring 0)
+ * 0x10 - Data segment (ring 0)
+ * 0x18 - Not present code segment (ring 0)
+ * 0x20 - Code segment (ring 3)
+ * 0x28 - Data segment (ring 3)
+ * 0x30 - Interrupt task
+ * 0x38 to 0x78 - Free to use for test cases
+ * 0x80 - Primary task (CPU 0)
+ */
+
+void set_gdt_entry(int sel, u32 base,  u32 limit, u8 access, u8 gran)
+{
+	int num = sel >> 3;
+
+	/* Setup the descriptor base address */
+	gdt32[num].base_low = (base & 0xFFFF);
+	gdt32[num].base_middle = (base >> 16) & 0xFF;
+	gdt32[num].base_high = (base >> 24) & 0xFF;
+
+	/* Setup the descriptor limits */
+	gdt32[num].limit_low = (limit & 0xFFFF);
+	gdt32[num].granularity = ((limit >> 16) & 0x0F);
+
+	/* Finally, set up the granularity and access flags */
+	gdt32[num].granularity |= (gran & 0xF0);
+	gdt32[num].access = access;
+}
+
+void set_gdt_task_gate(u16 sel, u16 tss_sel)
+{
+    set_gdt_entry(sel, tss_sel, 0, 0x85, 0); // task, present
+}
+
+void set_idt_task_gate(int vec, u16 sel)
+{
+    idt_entry_t *e = &boot_idt[vec];
+
+    memset(e, 0, sizeof *e);
+
+    e->selector = sel;
+    e->ist = 0;
+    e->type = 5;
+    e->dpl = 0;
+    e->p = 1;
+}
+
+/*
+ * 0 - main task
+ * 1 - interrupt task
+ */
+
+tss32_t tss_intr;
+
+void setup_tss32(void)
+{
+	u16 desc_size = sizeof(tss32_t);
+
+	tss.cr3 = read_cr3();
+	tss_intr.cr3 = read_cr3();
+	tss_intr.ss0 = tss_intr.ss1 = tss_intr.ss2 = 0x10;
+	tss_intr.esp = tss_intr.esp0 = tss_intr.esp1 = tss_intr.esp2 =
+		(u32)intr_alt_stack + 4096;
+	tss_intr.cs = 0x08;
+	tss_intr.ds = tss_intr.es = tss_intr.fs = tss_intr.gs = tss_intr.ss = 0x10;
+	tss_intr.iomap_base = (u16)desc_size;
+	set_gdt_entry(TSS_INTR, (u32)&tss_intr, desc_size - 1, 0x89, 0x0f);
+}
+
+void set_intr_task_gate(int e, void *fn)
+{
+	tss_intr.eip = (u32)fn;
+	set_idt_task_gate(e, TSS_INTR);
+}
+
+void setup_alt_stack(void)
+{
+	setup_tss32();
+}
+
+void set_intr_alt_stack(int e, void *fn)
+{
+	set_intr_task_gate(e, fn);
+}
+
+void print_current_tss_info(void)
+{
+	u16 tr = str();
+
+	if (tr != TSS_MAIN && tr != TSS_INTR)
+		printf("Unknown TSS %x\n", tr);
+	else
+		printf("TR=%x (%s) Main TSS back link %x. Intr TSS back link %x\n",
+		       tr, tr ? "interrupt" : "main", tss.prev, tss_intr.prev);
+}
+#else
+void set_intr_alt_stack(int e, void *addr)
+{
+	set_idt_entry(e, addr, 0);
+	boot_idt[e].ist = 1;
+}
+
+void setup_alt_stack(void)
+{
+	tss.ist1 = (u64)intr_alt_stack + 4096;
+}
+#endif
+
+static bool exception;
+static jmp_buf *exception_jmpbuf;
+
+static void exception_handler_longjmp(void)
+{
+	longjmp(*exception_jmpbuf, 1);
+}
+
+static void exception_handler(struct ex_regs *regs)
+{
+	/* longjmp must happen after iret, so do not do it now.  */
+	exception = true;
+	regs->rip = (unsigned long)&exception_handler_longjmp;
+}
+
+bool test_for_exception(unsigned int ex, void (*trigger_func)(void *data),
+			void *data)
+{
+	jmp_buf jmpbuf;
+	int ret;
+
+	handle_exception(ex, exception_handler);
+	ret = set_exception_jmpbuf(jmpbuf);
+	if (ret == 0)
+		trigger_func(data);
+	handle_exception(ex, NULL);
+	return ret;
+}
+
+void __set_exception_jmpbuf(jmp_buf *addr)
+{
+	exception_jmpbuf = addr;
+}

tests/kvm-unit-tests/lib/x86/desc.h

@@ -0,0 +1,164 @@
+#ifndef __IDT_TEST__
+#define __IDT_TEST__
+
+#include <setjmp.h>
+
+void setup_idt(void);
+void setup_alt_stack(void);
+
+struct ex_regs {
+    unsigned long rax, rcx, rdx, rbx;
+    unsigned long dummy, rbp, rsi, rdi;
+#ifdef __x86_64__
+    unsigned long r8, r9, r10, r11;
+    unsigned long r12, r13, r14, r15;
+#endif
+    unsigned long vector;
+    unsigned long error_code;
+    unsigned long rip;
+    unsigned long cs;
+    unsigned long rflags;
+};
+
+typedef struct {
+	u16 prev;
+	u16 res1;
+	u32 esp0;
+	u16 ss0;
+	u16 res2;
+	u32 esp1;
+	u16 ss1;
+	u16 res3;
+	u32 esp2;
+	u16 ss2;
+	u16 res4;
+	u32 cr3;
+	u32 eip;
+	u32 eflags;
+	u32 eax, ecx, edx, ebx, esp, ebp, esi, edi;
+	u16 es;
+	u16 res5;
+	u16 cs;
+	u16 res6;
+	u16 ss;
+	u16 res7;
+	u16 ds;
+	u16 res8;
+	u16 fs;
+	u16 res9;
+	u16 gs;
+	u16 res10;
+	u16 ldt;
+	u16 res11;
+	u16 t:1;
+	u16 res12:15;
+	u16 iomap_base;
+} tss32_t;
+
+typedef struct  __attribute__((packed)) {
+	u32 res1;
+	u64 rsp0;
+	u64 rsp1;
+	u64 rsp2;
+	u64 res2;
+	u64 ist1;
+	u64 ist2;
+	u64 ist3;
+	u64 ist4;
+	u64 ist5;
+	u64 ist6;
+	u64 ist7;
+	u64 res3;
+	u16 res4;
+	u16 iomap_base;
+} tss64_t;
+
+#define ASM_TRY(catch)                                  \
+    "movl $0, %%gs:4 \n\t"                              \
+    ".pushsection .data.ex \n\t"                        \
+    ".quad 1111f, " catch "\n\t"                        \
+    ".popsection \n\t"                                  \
+    "1111:"
+
+#define DB_VECTOR   1
+#define BP_VECTOR   3
+#define UD_VECTOR   6
+#define GP_VECTOR   13
+
+#define KERNEL_CS 0x08
+#define KERNEL_DS 0x10
+#define NP_SEL 0x18
+#define USER_CS 0x23
+#define USER_DS 0x2b
+#ifdef __x86_64__
+#define KERNEL_CS64 KERNEL_CS
+#define KERNEL_DS64 KERNEL_DS
+#define KERNEL_CS32 0x30
+#define KERNEL_DS32 0x38
+#define KERNEL_CS16 0x40
+#define KERNEL_DS16 0x48
+#else
+#define KERNEL_CS32 KERNEL_CS
+#define KERNEL_DS32 KERNEL_DS
+#endif
+#define TSS_INTR 0x50
+#define FIRST_SPARE_SEL 0x58
+#define TSS_MAIN 0x80
+
+typedef struct {
+    unsigned short offset0;
+    unsigned short selector;
+    unsigned short ist : 3;
+    unsigned short : 5;
+    unsigned short type : 4;
+    unsigned short : 1;
+    unsigned short dpl : 2;
+    unsigned short p : 1;
+    unsigned short offset1;
+#ifdef __x86_64__
+    unsigned offset2;
+    unsigned reserved;
+#endif
+} idt_entry_t;
+
+typedef struct {
+	u16 limit_low;
+	u16 base_low;
+	u8 base_middle;
+	u8 access;
+	u8 granularity;
+	u8 base_high;
+} gdt_entry_t;
+
+extern idt_entry_t boot_idt[256];
+
+#ifndef __x86_64__
+extern gdt_entry_t gdt32[];
+extern tss32_t tss;
+extern tss32_t tss_intr;
+void set_gdt_task_gate(u16 tss_sel, u16 sel);
+void set_idt_task_gate(int vec, u16 sel);
+void set_intr_task_gate(int vec, void *fn);
+void setup_tss32(void);
+#else
+extern tss64_t tss;
+#endif
+
+unsigned exception_vector(void);
+unsigned exception_error_code(void);
+bool exception_rflags_rf(void);
+void set_idt_entry(int vec, void *addr, int dpl);
+void set_idt_sel(int vec, u16 sel);
+void set_idt_dpl(int vec, u16 dpl);
+void set_gdt_entry(int sel, u32 base,  u32 limit, u8 access, u8 gran);
+void set_intr_alt_stack(int e, void *fn);
+void print_current_tss_info(void);
+void handle_exception(u8 v, void (*func)(struct ex_regs *regs));
+
+bool test_for_exception(unsigned int ex, void (*trigger_func)(void *data),
+			void *data);
+void __set_exception_jmpbuf(jmp_buf *addr);
+#define set_exception_jmpbuf(jmpbuf) \
+	(setjmp(jmpbuf) ? : (__set_exception_jmpbuf(&(jmpbuf)), 0))
+
+#endif

tests/kvm-unit-tests/lib/x86/fake-apic.h

@@ -0,0 +1,14 @@
+#ifndef SILLY_APIC_H
+#define SILLY_APIC_H
+
+#define APIC_BASE 0x1000
+#define APIC_SIZE 0x100
+
+#define APIC_REG_NCPU        0x00
+#define APIC_REG_ID          0x04
+#define APIC_REG_SIPI_ADDR   0x08
+#define APIC_REG_SEND_SIPI   0x0c
+#define APIC_REG_IPI_VECTOR  0x10
+#define APIC_REG_SEND_IPI    0x14
+
+#endif

tests/kvm-unit-tests/lib/x86/fwcfg.c

@@ -0,0 +1,45 @@
+#include "fwcfg.h"
+#include "smp.h"
+
+static struct spinlock lock;
+
+uint64_t fwcfg_get_u(uint16_t index, int bytes)
+{
+    uint64_t r = 0;
+    uint8_t b;
+    int i;
+
+    spin_lock(&lock);
+    asm volatile ("out %0, %1" : : "a"(index), "d"((uint16_t)BIOS_CFG_IOPORT));
+    for (i = 0; i < bytes; ++i) {
+        asm volatile ("in %1, %0" : "=a"(b) : "d"((uint16_t)(BIOS_CFG_IOPORT + 1)));
+        r |= (uint64_t)b << (i * 8);
+    }
+    spin_unlock(&lock);
+    return r;
+}
+
+uint8_t fwcfg_get_u8(unsigned index)
+{
+    return fwcfg_get_u(index, 1);
+}
+
+uint16_t fwcfg_get_u16(unsigned index)
+{
+    return fwcfg_get_u(index, 2);
+}
+
+uint32_t fwcfg_get_u32(unsigned index)
+{
+    return fwcfg_get_u(index, 4);
+}
+
+uint64_t fwcfg_get_u64(unsigned index)
+{
+    return fwcfg_get_u(index, 8);
+}
+
+unsigned fwcfg_get_nb_cpus(void)
+{
+    return fwcfg_get_u16(FW_CFG_NB_CPUS);
+}

tests/kvm-unit-tests/lib/x86/fwcfg.h

@@ -0,0 +1,44 @@
+#ifndef FWCFG_H
+#define FWCFG_H
+
+#include <stdint.h>
+
+#define FW_CFG_SIGNATURE        0x00
+#define FW_CFG_ID               0x01
+#define FW_CFG_UUID             0x02
+#define FW_CFG_RAM_SIZE         0x03
+#define FW_CFG_NOGRAPHIC        0x04
+#define FW_CFG_NB_CPUS          0x05
+#define FW_CFG_MACHINE_ID       0x06
+#define FW_CFG_KERNEL_ADDR      0x07
+#define FW_CFG_KERNEL_SIZE      0x08
+#define FW_CFG_KERNEL_CMDLINE   0x09
+#define FW_CFG_INITRD_ADDR      0x0a
+#define FW_CFG_INITRD_SIZE      0x0b
+#define FW_CFG_BOOT_DEVICE      0x0c
+#define FW_CFG_NUMA             0x0d
+#define FW_CFG_BOOT_MENU        0x0e
+#define FW_CFG_MAX_CPUS         0x0f
+#define FW_CFG_MAX_ENTRY        0x10
+
+#define FW_CFG_WRITE_CHANNEL    0x4000
+#define FW_CFG_ARCH_LOCAL       0x8000
+#define FW_CFG_ENTRY_MASK       ~(FW_CFG_WRITE_CHANNEL | FW_CFG_ARCH_LOCAL)
+
+#define FW_CFG_INVALID          0xffff
+
+#define BIOS_CFG_IOPORT 0x510
+
+#define FW_CFG_ACPI_TABLES (FW_CFG_ARCH_LOCAL + 0)
+#define FW_CFG_SMBIOS_ENTRIES (FW_CFG_ARCH_LOCAL + 1)
+#define FW_CFG_IRQ0_OVERRIDE (FW_CFG_ARCH_LOCAL + 2)
+
+uint8_t fwcfg_get_u8(unsigned index);
+uint16_t fwcfg_get_u16(unsigned index);
+uint32_t fwcfg_get_u32(unsigned index);
+uint64_t fwcfg_get_u64(unsigned index);
+
+unsigned fwcfg_get_nb_cpus(void);
+
+#endif
+

tests/kvm-unit-tests/lib/x86/intel-iommu.c

@@ -0,0 +1,372 @@
+/*
+ * Intel IOMMU APIs
+ *
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * Authors:
+ *   Peter Xu <peterx@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or
+ * later.
+ */
+
+#include "intel-iommu.h"
+#include "libcflat.h"
+#include "pci.h"
+#include "atomic.h"
+
+/*
+ * VT-d in QEMU currently only support 39 bits address width, which is
+ * 3-level translation.
+ */
+#define VTD_PAGE_LEVEL      3
+#define VTD_CE_AW_39BIT     0x1
+
+typedef uint64_t vtd_pte_t;
+
+struct vtd_root_entry {
+	/* Quad 1 */
+	uint64_t present:1;
+	uint64_t __reserved:11;
+	uint64_t context_table_p:52;
+	/* Quad 2 */
+	uint64_t __reserved_2;
+} __attribute__ ((packed));
+typedef struct vtd_root_entry vtd_re_t;
+
+struct vtd_context_entry {
+	/* Quad 1 */
+	uint64_t present:1;
+	uint64_t disable_fault_report:1;
+	uint64_t trans_type:2;
+	uint64_t __reserved:8;
+	uint64_t slptptr:52;
+	/* Quad 2 */
+	uint64_t addr_width:3;
+	uint64_t __ignore:4;
+	uint64_t __reserved_2:1;
+	uint64_t domain_id:16;
+	uint64_t __reserved_3:40;
+} __attribute__ ((packed));
+typedef struct vtd_context_entry vtd_ce_t;
+
+struct vtd_irte {
+	uint32_t present:1;
+	uint32_t fault_disable:1;    /* Fault Processing Disable */
+	uint32_t dest_mode:1;        /* Destination Mode */
+	uint32_t redir_hint:1;       /* Redirection Hint */
+	uint32_t trigger_mode:1;     /* Trigger Mode */
+	uint32_t delivery_mode:3;    /* Delivery Mode */
+	uint32_t __avail:4;          /* Available spaces for software */
+	uint32_t __reserved_0:3;     /* Reserved 0 */
+	uint32_t irte_mode:1;        /* IRTE Mode */
+	uint32_t vector:8;           /* Interrupt Vector */
+	uint32_t __reserved_1:8;     /* Reserved 1 */
+	uint32_t dest_id;            /* Destination ID */
+	uint16_t source_id:16;       /* Source-ID */
+	uint64_t sid_q:2;            /* Source-ID Qualifier */
+	uint64_t sid_vtype:2;        /* Source-ID Validation Type */
+	uint64_t __reserved_2:44;    /* Reserved 2 */
+} __attribute__ ((packed));
+typedef struct vtd_irte vtd_irte_t;
+
+#define VTD_RTA_MASK  (PAGE_MASK)
+#define VTD_IRTA_MASK (PAGE_MASK)
+
+void *vtd_reg_base;
+
+static uint64_t vtd_root_table(void)
+{
+	/* No extend root table support yet */
+	return vtd_readq(DMAR_RTADDR_REG) & VTD_RTA_MASK;
+}
+
+static uint64_t vtd_ir_table(void)
+{
+	return vtd_readq(DMAR_IRTA_REG) & VTD_IRTA_MASK;
+}
+
+static void vtd_gcmd_or(uint32_t cmd)
+{
+	uint32_t status;
+
+	/* We only allow set one bit for each time */
+	assert(is_power_of_2(cmd));
+
+	status = vtd_readl(DMAR_GSTS_REG);
+	vtd_writel(DMAR_GCMD_REG, status | cmd);
+
+	if (cmd & VTD_GCMD_ONE_SHOT_BITS) {
+		/* One-shot bits are taking effect immediately */
+		return;
+	}
+
+	/* Make sure IOMMU handled our command request */
+	while (!(vtd_readl(DMAR_GSTS_REG) & cmd))
+		cpu_relax();
+}
+
+static void vtd_dump_init_info(void)
+{
+	uint32_t version;
+
+	version = vtd_readl(DMAR_VER_REG);
+
+	/* Major version >= 1 */
+	assert(((version >> 3) & 0xf) >= 1);
+
+	printf("VT-d version:   0x%x\n", version);
+	printf("     cap:       0x%016lx\n", vtd_readq(DMAR_CAP_REG));
+	printf("     ecap:      0x%016lx\n", vtd_readq(DMAR_ECAP_REG));
+}
+
+static void vtd_setup_root_table(void)
+{
+	void *root = alloc_page();
+
+	memset(root, 0, PAGE_SIZE);
+	vtd_writeq(DMAR_RTADDR_REG, virt_to_phys(root));
+	vtd_gcmd_or(VTD_GCMD_ROOT);
+	printf("DMAR table address: 0x%016lx\n", vtd_root_table());
+}
+
+static void vtd_setup_ir_table(void)
+{
+	void *root = alloc_page();
+
+	memset(root, 0, PAGE_SIZE);
+	/* 0xf stands for table size (2^(0xf+1) == 65536) */
+	vtd_writeq(DMAR_IRTA_REG, virt_to_phys(root) | 0xf);
+	vtd_gcmd_or(VTD_GCMD_IR_TABLE);
+	printf("IR table address: 0x%016lx\n", vtd_ir_table());
+}
+
+static void vtd_install_pte(vtd_pte_t *root, iova_t iova,
+			    phys_addr_t pa, int level_target)
+{
+	int level;
+	unsigned int offset;
+	void *page;
+
+	for (level = VTD_PAGE_LEVEL; level > level_target; level--) {
+		offset = PGDIR_OFFSET(iova, level);
+		if (!(root[offset] & VTD_PTE_RW)) {
+			page = alloc_page();
+			memset(page, 0, PAGE_SIZE);
+			root[offset] = virt_to_phys(page) | VTD_PTE_RW;
+		}
+		root = (uint64_t *)(phys_to_virt(root[offset] &
+						 VTD_PTE_ADDR));
+	}
+
+	offset = PGDIR_OFFSET(iova, level);
+	root[offset] = pa | VTD_PTE_RW;
+	if (level != 1) {
+		/* This is huge page */
+		root[offset] |= VTD_PTE_HUGE;
+	}
+}
+
+/**
+ * vtd_map_range: setup IO address mapping for specific memory range
+ *
+ * @sid: source ID of the device to setup
+ * @iova: start IO virtual address
+ * @pa: start physical address
+ * @size: size of the mapping area
+ */
+void vtd_map_range(uint16_t sid, iova_t iova, phys_addr_t pa, size_t size)
+{
+	uint8_t bus_n, devfn;
+	void *slptptr;
+	vtd_ce_t *ce;
+	vtd_re_t *re = phys_to_virt(vtd_root_table());
+
+	assert(IS_ALIGNED(iova, SZ_4K));
+	assert(IS_ALIGNED(pa, SZ_4K));
+	assert(IS_ALIGNED(size, SZ_4K));
+
+	bus_n = PCI_BDF_GET_BUS(sid);
+	devfn = PCI_BDF_GET_DEVFN(sid);
+
+	/* Point to the correct root entry */
+	re += bus_n;
+
+	if (!re->present) {
+		ce = alloc_page();
+		memset(ce, 0, PAGE_SIZE);
+		memset(re, 0, sizeof(*re));
+		re->context_table_p = virt_to_phys(ce) >> VTD_PAGE_SHIFT;
+		re->present = 1;
+		printf("allocated vt-d root entry for PCI bus %d\n",
+		       bus_n);
+	} else
+		ce = phys_to_virt(re->context_table_p << VTD_PAGE_SHIFT);
+
+	/* Point to the correct context entry */
+	ce += devfn;
+
+	if (!ce->present) {
+		slptptr = alloc_page();
+		memset(slptptr, 0, PAGE_SIZE);
+		memset(ce, 0, sizeof(*ce));
+		/* To make it simple, domain ID is the same as SID */
+		ce->domain_id = sid;
+		/* We only test 39 bits width case (3-level paging) */
+		ce->addr_width = VTD_CE_AW_39BIT;
+		ce->slptptr = virt_to_phys(slptptr) >> VTD_PAGE_SHIFT;
+		ce->trans_type = VTD_CONTEXT_TT_MULTI_LEVEL;
+		ce->present = 1;
+		/* No error reporting yet */
+		ce->disable_fault_report = 1;
+		printf("allocated vt-d context entry for devfn 0x%x\n",
+		       devfn);
+	} else
+		slptptr = phys_to_virt(ce->slptptr << VTD_PAGE_SHIFT);
+
+	while (size) {
+		/* TODO: currently we only map 4K pages (level = 1) */
+		printf("map 4K page IOVA 0x%lx to 0x%lx (sid=0x%04x)\n",
+		       iova, pa, sid);
+		vtd_install_pte(slptptr, iova, pa, 1);
+		size -= VTD_PAGE_SIZE;
+		iova += VTD_PAGE_SIZE;
+		pa += VTD_PAGE_SIZE;
+	}
+}
+
+static uint16_t vtd_intr_index_alloc(void)
+{
+	static volatile int index_ctr = 0;
+	int ctr;
+
+	assert(index_ctr < 65535);
+	ctr = atomic_inc_fetch(&index_ctr);
+	printf("INTR: alloc IRTE index %d\n", ctr);
+	return ctr;
+}
+
+static void vtd_setup_irte(struct pci_dev *dev, vtd_irte_t *irte,
+			   int vector, int dest_id, trigger_mode_t trigger)
+{
+	assert(sizeof(vtd_irte_t) == 16);
+	memset(irte, 0, sizeof(*irte));
+	irte->fault_disable = 1;
+	irte->dest_mode = 0;	 /* physical */
+	irte->trigger_mode = trigger;
+	irte->delivery_mode = 0; /* fixed */
+	irte->irte_mode = 0;	 /* remapped */
+	irte->vector = vector;
+	irte->dest_id = dest_id;
+	irte->source_id = dev->bdf;
+	irte->sid_q = 0;
+	irte->sid_vtype = 1;     /* full-sid verify */
+	irte->present = 1;
+}
+
+struct vtd_msi_addr {
+	uint32_t __dont_care:2;
+	uint32_t handle_15:1;	 /* handle[15] */
+	uint32_t shv:1;
+	uint32_t interrupt_format:1;
+	uint32_t handle_0_14:15; /* handle[0:14] */
+	uint32_t head:12;	 /* 0xfee */
+	uint32_t addr_hi;	 /* not used except with x2apic */
+} __attribute__ ((packed));
+typedef struct vtd_msi_addr vtd_msi_addr_t;
+
+struct vtd_msi_data {
+	uint16_t __reserved;
+	uint16_t subhandle;
+} __attribute__ ((packed));
+typedef struct vtd_msi_data vtd_msi_data_t;
+
+struct vtd_ioapic_entry {
+	uint64_t vector:8;
+	uint64_t __zeros:3;
+	uint64_t index_15:1;
+	uint64_t delivery_status:1;
+	uint64_t polarity:1;
+	uint64_t remote_irr:1;
+	uint64_t trigger_mode:1;
+	uint64_t mask:1;
+	uint64_t __zeros_2:31;
+	uint64_t interrupt_format:1;
+	uint64_t index_0_14:15;
+} __attribute__ ((packed));
+typedef struct vtd_ioapic_entry vtd_ioapic_entry_t;
+
+/**
+ * vtd_setup_msi - setup MSI message for a device
+ *
+ * @dev: PCI device to setup MSI
+ * @vector: interrupt vector
+ * @dest_id: destination processor
+ */
+bool vtd_setup_msi(struct pci_dev *dev, int vector, int dest_id)
+{
+	vtd_msi_data_t msi_data = {};
+	vtd_msi_addr_t msi_addr = {};
+	vtd_irte_t *irte = phys_to_virt(vtd_ir_table());
+	uint16_t index = vtd_intr_index_alloc();
+
+	assert(sizeof(vtd_msi_addr_t) == 8);
+	assert(sizeof(vtd_msi_data_t) == 4);
+
+	/* Use edge irq as default */
+	vtd_setup_irte(dev, irte + index, vector,
+		       dest_id, TRIGGER_EDGE);
+
+	msi_addr.handle_15 = index >> 15 & 1;
+	msi_addr.shv = 0;
+	msi_addr.interrupt_format = 1;
+	msi_addr.handle_0_14 = index & 0x7fff;
+	msi_addr.head = 0xfee;
+	msi_data.subhandle = 0;
+
+	printf("%s: msi_addr=0x%" PRIx64 ", msi_data=0x%x\n", __func__,
+		*(uint64_t *)&msi_addr, *(uint32_t *)&msi_data);
+
+	return pci_setup_msi(dev, *(uint64_t *)&msi_addr,
+			     *(uint32_t *)&msi_data);
+}
+
+void vtd_setup_ioapic_irq(struct pci_dev *dev, int vector,
+			  int dest_id, trigger_mode_t trigger)
+{
+	vtd_ioapic_entry_t entry = {};
+	vtd_irte_t *irte = phys_to_virt(vtd_ir_table());
+	ioapic_redir_entry_t *entry_2 = (ioapic_redir_entry_t *)&entry;
+	uint16_t index = vtd_intr_index_alloc();
+	uint8_t line;
+
+	assert(dev);
+	assert(sizeof(vtd_ioapic_entry_t) == 8);
+
+	vtd_setup_irte(dev, irte + index, vector,
+		       dest_id, trigger);
+
+	entry.vector = vector;
+	entry.trigger_mode = trigger;
+	entry.index_15 = (index >> 15) & 1;
+	entry.interrupt_format = 1;
+	entry.index_0_14 = index & 0x7fff;
+
+	line = pci_intx_line(dev);
+	ioapic_write_redir(line, *entry_2);
+}
+
+void vtd_init(void)
+{
+	setup_vm();
+	smp_init();
+
+	vtd_reg_base = ioremap(Q35_HOST_BRIDGE_IOMMU_ADDR, PAGE_SIZE);
+
+	vtd_dump_init_info();
+	vtd_gcmd_or(VTD_GCMD_QI); /* Enable QI */
+	vtd_setup_root_table();
+	vtd_setup_ir_table();
+	vtd_gcmd_or(VTD_GCMD_DMAR); /* Enable DMAR */
+	vtd_gcmd_or(VTD_GCMD_IR);   /* Enable IR */
+}

tests/kvm-unit-tests/lib/x86/intel-iommu.h

@@ -0,0 +1,149 @@
+/*
+ * Intel IOMMU header
+ *
+ * Copyright (C) 2016 Red Hat, Inc.
+ *
+ * Authors:
+ *   Peter Xu <peterx@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or
+ * later.
+ *
+ * (From include/linux/intel-iommu.h)
+ */
+
+#ifndef __INTEL_IOMMU_H__
+#define __INTEL_IOMMU_H__
+
+#include "libcflat.h"
+#include "vm.h"
+#include "isr.h"
+#include "smp.h"
+#include "desc.h"
+#include "pci.h"
+#include "asm/io.h"
+#include "apic.h"
+
+#define Q35_HOST_BRIDGE_IOMMU_ADDR  0xfed90000ULL
+#define VTD_PAGE_SHIFT              PAGE_SHIFT
+#define VTD_PAGE_SIZE               PAGE_SIZE
+
+/*
+ * Intel IOMMU register specification
+ */
+#define DMAR_VER_REG            0x0  /* Arch version supported by this IOMMU */
+#define DMAR_CAP_REG            0x8  /* Hardware supported capabilities */
+#define DMAR_CAP_REG_HI         0xc  /* High 32-bit of DMAR_CAP_REG */
+#define DMAR_ECAP_REG           0x10 /* Extended capabilities supported */
+#define DMAR_ECAP_REG_HI        0X14
+#define DMAR_GCMD_REG           0x18 /* Global command */
+#define DMAR_GSTS_REG           0x1c /* Global status */
+#define DMAR_RTADDR_REG         0x20 /* Root entry table */
+#define DMAR_RTADDR_REG_HI      0X24
+#define DMAR_CCMD_REG           0x28 /* Context command */
+#define DMAR_CCMD_REG_HI        0x2c
+#define DMAR_FSTS_REG           0x34 /* Fault status */
+#define DMAR_FECTL_REG          0x38 /* Fault control */
+#define DMAR_FEDATA_REG         0x3c /* Fault event interrupt data */
+#define DMAR_FEADDR_REG         0x40 /* Fault event interrupt addr */
+#define DMAR_FEUADDR_REG        0x44 /* Upper address */
+#define DMAR_AFLOG_REG          0x58 /* Advanced fault control */
+#define DMAR_AFLOG_REG_HI       0X5c
+#define DMAR_PMEN_REG           0x64 /* Enable protected memory region */
+#define DMAR_PLMBASE_REG        0x68 /* PMRR low addr */
+#define DMAR_PLMLIMIT_REG       0x6c /* PMRR low limit */
+#define DMAR_PHMBASE_REG        0x70 /* PMRR high base addr */
+#define DMAR_PHMBASE_REG_HI     0X74
+#define DMAR_PHMLIMIT_REG       0x78 /* PMRR high limit */
+#define DMAR_PHMLIMIT_REG_HI    0x7c
+#define DMAR_IQH_REG            0x80 /* Invalidation queue head */
+#define DMAR_IQH_REG_HI         0X84
+#define DMAR_IQT_REG            0x88 /* Invalidation queue tail */
+#define DMAR_IQT_REG_HI         0X8c
+#define DMAR_IQA_REG            0x90 /* Invalidation queue addr */
+#define DMAR_IQA_REG_HI         0x94
+#define DMAR_ICS_REG            0x9c /* Invalidation complete status */
+#define DMAR_IRTA_REG           0xb8 /* Interrupt remapping table addr */
+#define DMAR_IRTA_REG_HI        0xbc
+#define DMAR_IECTL_REG          0xa0 /* Invalidation event control */
+#define DMAR_IEDATA_REG         0xa4 /* Invalidation event data */
+#define DMAR_IEADDR_REG         0xa8 /* Invalidation event address */
+#define DMAR_IEUADDR_REG        0xac /* Invalidation event address */
+#define DMAR_PQH_REG            0xc0 /* Page request queue head */
+#define DMAR_PQH_REG_HI         0xc4
+#define DMAR_PQT_REG            0xc8 /* Page request queue tail*/
+#define DMAR_PQT_REG_HI         0xcc
+#define DMAR_PQA_REG            0xd0 /* Page request queue address */
+#define DMAR_PQA_REG_HI         0xd4
+#define DMAR_PRS_REG            0xdc /* Page request status */
+#define DMAR_PECTL_REG          0xe0 /* Page request event control */
+#define DMAR_PEDATA_REG         0xe4 /* Page request event data */
+#define DMAR_PEADDR_REG         0xe8 /* Page request event address */
+#define DMAR_PEUADDR_REG        0xec /* Page event upper address */
+#define DMAR_MTRRCAP_REG        0x100 /* MTRR capability */
+#define DMAR_MTRRCAP_REG_HI     0x104
+#define DMAR_MTRRDEF_REG        0x108 /* MTRR default type */
+#define DMAR_MTRRDEF_REG_HI     0x10c
+
+#define VTD_GCMD_IR_TABLE       0x1000000
+#define VTD_GCMD_IR             0x2000000
+#define VTD_GCMD_QI             0x4000000
+#define VTD_GCMD_WBF            0x8000000  /* Write Buffer Flush */
+#define VTD_GCMD_SFL            0x20000000 /* Set Fault Log */
+#define VTD_GCMD_ROOT           0x40000000
+#define VTD_GCMD_DMAR           0x80000000
+#define VTD_GCMD_ONE_SHOT_BITS  (VTD_GCMD_IR_TABLE | VTD_GCMD_WBF | \
+				 VTD_GCMD_SFL | VTD_GCMD_ROOT)
+
+/* Supported Adjusted Guest Address Widths */
+#define VTD_CAP_SAGAW_SHIFT         8
+/* 39-bit AGAW, 3-level page-table */
+#define VTD_CAP_SAGAW_39bit         (0x2ULL << VTD_CAP_SAGAW_SHIFT)
+/* 48-bit AGAW, 4-level page-table */
+#define VTD_CAP_SAGAW_48bit         (0x4ULL << VTD_CAP_SAGAW_SHIFT)
+#define VTD_CAP_SAGAW               VTD_CAP_SAGAW_39bit
+
+/* Both 1G/2M huge pages */
+#define VTD_CAP_SLLPS               ((1ULL << 34) | (1ULL << 35))
+
+#define VTD_CONTEXT_TT_MULTI_LEVEL  0
+#define VTD_CONTEXT_TT_DEV_IOTLB    1
+#define VTD_CONTEXT_TT_PASS_THROUGH 2
+
+#define VTD_PTE_R                   (1 << 0)
+#define VTD_PTE_W                   (1 << 1)
+#define VTD_PTE_RW                  (VTD_PTE_R | VTD_PTE_W)
+#define VTD_PTE_ADDR                GENMASK_ULL(63, 12)
+#define VTD_PTE_HUGE                (1 << 7)
+
+extern void *vtd_reg_base;
+#define vtd_reg(reg) ({ assert(vtd_reg_base); \
+			(volatile void *)(vtd_reg_base + reg); })
+
+static inline void vtd_writel(unsigned int reg, uint32_t value)
+{
+	__raw_writel(value, vtd_reg(reg));
+}
+
+static inline void vtd_writeq(unsigned int reg, uint64_t value)
+{
+	__raw_writeq(value, vtd_reg(reg));
+}
+
+static inline uint32_t vtd_readl(unsigned int reg)
+{
+	return __raw_readl(vtd_reg(reg));
+}
+
+static inline uint64_t vtd_readq(unsigned int reg)
+{
+	return __raw_readq(vtd_reg(reg));
+}
+
+void vtd_init(void);
+void vtd_map_range(uint16_t sid, phys_addr_t iova, phys_addr_t pa, size_t size);
+bool vtd_setup_msi(struct pci_dev *dev, int vector, int dest_id);
+void vtd_setup_ioapic_irq(struct pci_dev *dev, int vector,
+			  int dest_id, trigger_mode_t trigger);
+
+#endif

tests/kvm-unit-tests/lib/x86/io.c

@@ -0,0 +1,99 @@
+#include "libcflat.h"
+#include "vm.h"
+#include "smp.h"
+#include "asm/io.h"
+#include "asm/page.h"
+#ifndef USE_SERIAL
+#define USE_SERIAL
+#endif
+
+static struct spinlock lock;
+static int serial_iobase = 0x3f8;
+static int serial_inited = 0;
+
+static void serial_outb(char ch)
+{
+        u8 lsr;
+
+        do {
+                lsr = inb(serial_iobase + 0x05);
+        } while (!(lsr & 0x20));
+
+        outb(ch, serial_iobase + 0x00);
+}
+
+static void serial_init(void)
+{
+        u8 lcr;
+
+        /* set DLAB */
+        lcr = inb(serial_iobase + 0x03);
+        lcr |= 0x80;
+        outb(lcr, serial_iobase + 0x03);
+
+        /* set baud rate to 115200 */
+        outb(0x01, serial_iobase + 0x00);
+        outb(0x00, serial_iobase + 0x01);
+
+        /* clear DLAB */
+        lcr = inb(serial_iobase + 0x03);
+        lcr &= ~0x80;
+        outb(lcr, serial_iobase + 0x03);
+}
+
+static void print_serial(const char *buf)
+{
+	unsigned long len = strlen(buf);
+#ifdef USE_SERIAL
+        unsigned long i;
+        if (!serial_inited) {
+            serial_init();
+            serial_inited = 1;
+        }
+
+        for (i = 0; i < len; i++) {
+            serial_outb(buf[i]);
+        }
+#else
+        asm volatile ("rep/outsb" : "+S"(buf), "+c"(len) : "d"(0xf1));
+#endif
+}
+
+void puts(const char *s)
+{
+	spin_lock(&lock);
+	print_serial(s);
+	spin_unlock(&lock);
+}
+
+void exit(int code)
+{
+#ifdef USE_SERIAL
+        static const char shutdown_str[8] = "Shutdown";
+        int i;
+
+        /* test device exit (with status) */
+        outl(code, 0xf4);
+
+        /* if that failed, try the Bochs poweroff port */
+        for (i = 0; i < 8; i++) {
+                outb(shutdown_str[i], 0x8900);
+        }
+#else
+        asm volatile("out %0, %1" : : "a"(code), "d"((short)0xf4));
+#endif
+}
+
+void __iomem *ioremap(phys_addr_t phys_addr, size_t size)
+{
+	phys_addr_t base = phys_addr & PAGE_MASK;
+	phys_addr_t offset = phys_addr - base;
+
+	/*
+	 * The kernel sets PTEs for an ioremap() with page cache disabled,
+	 * but we do not do that right now. It would make sense that I/O
+	 * mappings would be uncached - and may help us find bugs when we
+	 * properly map that way.
+	 */
+	return vmap(phys_addr, size) + offset;
+}

tests/kvm-unit-tests/lib/x86/isr.c

@@ -0,0 +1,124 @@
+#include "libcflat.h"
+#include "isr.h"
+#include "vm.h"
+#include "desc.h"
+
+extern char isr_entry_point[];
+
+asm (
+    "isr_entry_point: \n"
+#ifdef __x86_64__
+    "push %r15 \n\t"
+    "push %r14 \n\t"
+    "push %r13 \n\t"
+    "push %r12 \n\t"
+    "push %r11 \n\t"
+    "push %r10 \n\t"
+    "push %r9  \n\t"
+    "push %r8  \n\t"
+#endif
+    "push %"R "di \n\t"
+    "push %"R "si \n\t"
+    "push %"R "bp \n\t"
+    "push %"R "sp \n\t"
+    "push %"R "bx \n\t"
+    "push %"R "dx \n\t"
+    "push %"R "cx \n\t"
+    "push %"R "ax \n\t"
+#ifdef __x86_64__
+    "mov %rsp, %rdi \n\t"
+    "callq *8*16(%rsp) \n\t"
+#else
+    "push %esp \n\t"
+    "calll *4+4*8(%esp) \n\t"
+    "add $4, %esp \n\t"
+#endif
+    "pop %"R "ax \n\t"
+    "pop %"R "cx \n\t"
+    "pop %"R "dx \n\t"
+    "pop %"R "bx \n\t"
+    "pop %"R "bp \n\t"
+    "pop %"R "bp \n\t"
+    "pop %"R "si \n\t"
+    "pop %"R "di \n\t"
+#ifdef __x86_64__
+    "pop %r8  \n\t"
+    "pop %r9  \n\t"
+    "pop %r10 \n\t"
+    "pop %r11 \n\t"
+    "pop %r12 \n\t"
+    "pop %r13 \n\t"
+    "pop %r14 \n\t"
+    "pop %r15 \n\t"
+#endif
+    ".globl isr_iret_ip\n\t"
+#ifdef __x86_64__
+    "add $8, %rsp \n\t"
+    "isr_iret_ip: \n\t"
+    "iretq \n\t"
+#else
+    "add $4, %esp \n\t"
+    "isr_iret_ip: \n\t"
+    "iretl \n\t"
+#endif
+    );
+
+void handle_irq(unsigned vec, void (*func)(isr_regs_t *regs))
+{
+    u8 *thunk = vmalloc(50);
+
+    set_idt_entry(vec, thunk, 0);
+
+#ifdef __x86_64__
+    /* sub $8, %rsp */
+    *thunk++ = 0x48; *thunk++ = 0x83; *thunk++ = 0xec; *thunk++ = 0x08;
+    /* mov $func_low, %(rsp) */
+    *thunk++ = 0xc7; *thunk++ = 0x04; *thunk++ = 0x24;
+    *(u32 *)thunk = (ulong)func; thunk += 4;
+    /* mov $func_high, %(rsp+4) */
+    *thunk++ = 0xc7; *thunk++ = 0x44; *thunk++ = 0x24; *thunk++ = 0x04;
+    *(u32 *)thunk = (ulong)func >> 32; thunk += 4;
+    /* jmp isr_entry_point */
+    *thunk ++ = 0xe9;
+    *(u32 *)thunk = (ulong)isr_entry_point - (ulong)(thunk + 4);
+#else
+    /* push $func */
+    *thunk++ = 0x68;
+    *(u32 *)thunk = (ulong)func; thunk += 4;
+    /* jmp isr_entry_point */
+    *thunk++ = 0xe9;
+    *(u32 *)thunk = (ulong)isr_entry_point - (ulong)(thunk + 4);
+#endif
+}
+
+void handle_external_interrupt(int vector)
+{
+	idt_entry_t *idt = &boot_idt[vector];
+	unsigned long entry =
+		idt->offset0 | ((unsigned long)idt->offset1 << 16);
+#ifdef __x86_64__
+	unsigned long tmp;
+	entry |= ((unsigned long)idt->offset2 << 32);
+#endif
+
+	asm volatile(
+#ifdef __x86_64__
+		     "mov %%rsp, %[sp]\n\t"
+		     "and $0xfffffffffffffff0, %%rsp\n\t"
+		     "push $%c[ss]\n\t"
+		     "push %[sp]\n\t"
+#endif
+		     "pushf\n\t"
+		     "orl $0x200, (%%"R "sp)\n\t"
+		     "push $%c[cs]\n\t"
+		     "call *%[entry]\n\t"
+		     :
+#ifdef __x86_64__
+		     [sp]"=&r"(tmp)
+#endif
+		     :
+		     [entry]"r"(entry),
+		     [ss]"i"(KERNEL_DS),
+		     [cs]"i"(KERNEL_CS)
+		     );
+}

tests/kvm-unit-tests/lib/x86/isr.h

@@ -0,0 +1,14 @@
+#ifndef __ISR_TEST__
+#define __ISR_TEST__
+
+typedef struct {
+    ulong regs[sizeof(ulong)*2];
+    ulong func;
+    ulong rip;
+    ulong cs;
+    ulong rflags;
+} isr_regs_t;
+
+void handle_irq(unsigned vec, void (*func)(isr_regs_t *regs));
+void handle_external_interrupt(int vector);
+#endif

tests/kvm-unit-tests/lib/x86/msr.h

@@ -0,0 +1,412 @@
+#ifndef _ASM_X86_MSR_INDEX_H
+#define _ASM_X86_MSR_INDEX_H
+
+/* CPU model specific register (MSR) numbers */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER		0xc0000080 /* extended feature register */
+#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX		0xc0000103 /* Auxiliary TSC */
+
+/* EFER bits: */
+#define _EFER_SCE		0  /* SYSCALL/SYSRET */
+#define _EFER_LME		8  /* Long mode enable */
+#define _EFER_LMA		10 /* Long mode active (read-only) */
+#define _EFER_NX		11 /* No execute enable */
+#define _EFER_SVME		12 /* Enable virtualization */
+#define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
+#define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+
+#define EFER_SCE		(1<<_EFER_SCE)
+#define EFER_LME		(1<<_EFER_LME)
+#define EFER_LMA		(1<<_EFER_LMA)
+#define EFER_NX			(1<<_EFER_NX)
+#define EFER_SVME		(1<<_EFER_SVME)
+#define EFER_LMSLE		(1<<_EFER_LMSLE)
+#define EFER_FFXSR		(1<<_EFER_FFXSR)
+
+/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_PERFCTR0		0x000000c1
+#define MSR_IA32_PERFCTR1		0x000000c2
+#define MSR_FSB_FREQ			0x000000cd
+
+#define MSR_MTRRcap			0x000000fe
+#define MSR_IA32_BBL_CR_CTL		0x00000119
+
+#define MSR_IA32_SYSENTER_CS		0x00000174
+#define MSR_IA32_SYSENTER_ESP		0x00000175
+#define MSR_IA32_SYSENTER_EIP		0x00000176
+
+#define MSR_IA32_MCG_CAP		0x00000179
+#define MSR_IA32_MCG_STATUS		0x0000017a
+#define MSR_IA32_MCG_CTL		0x0000017b
+
+#define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_IA32_DS_AREA		0x00000600
+#define MSR_IA32_PERF_CAPABILITIES	0x00000345
+
+#define MSR_MTRRfix64K_00000		0x00000250
+#define MSR_MTRRfix16K_80000		0x00000258
+#define MSR_MTRRfix16K_A0000		0x00000259
+#define MSR_MTRRfix4K_C0000		0x00000268
+#define MSR_MTRRfix4K_C8000		0x00000269
+#define MSR_MTRRfix4K_D0000		0x0000026a
+#define MSR_MTRRfix4K_D8000		0x0000026b
+#define MSR_MTRRfix4K_E0000		0x0000026c
+#define MSR_MTRRfix4K_E8000		0x0000026d
+#define MSR_MTRRfix4K_F0000		0x0000026e
+#define MSR_MTRRfix4K_F8000		0x0000026f
+#define MSR_MTRRdefType			0x000002ff
+
+#define MSR_IA32_CR_PAT			0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR		0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
+#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
+#define MSR_IA32_LASTINTFROMIP		0x000001dd
+#define MSR_IA32_LASTINTTOIP		0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
+#define DEBUGCTLMSR_TR			(1UL <<  6)
+#define DEBUGCTLMSR_BTS			(1UL <<  7)
+#define DEBUGCTLMSR_BTINT		(1UL <<  8)
+#define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
+#define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+
+#define MSR_IA32_MC0_CTL		0x00000400
+#define MSR_IA32_MC0_STATUS		0x00000401
+#define MSR_IA32_MC0_ADDR		0x00000402
+#define MSR_IA32_MC0_MISC		0x00000403
+
+#define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
+#define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
+#define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
+#define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
+
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2		0x00000280
+#define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
+
+#define CMCI_EN			(1ULL << 30)
+#define CMCI_THRESHOLD_MASK		0xffffULL
+
+#define MSR_P6_PERFCTR0			0x000000c1
+#define MSR_P6_PERFCTR1			0x000000c2
+#define MSR_P6_EVNTSEL0			0x00000186
+#define MSR_P6_EVNTSEL1			0x00000187
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+   complete list. */
+
+#define MSR_AMD64_PATCH_LEVEL		0x0000008b
+#define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_PATCH_LOADER		0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
+#define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_DC_CFG		0xc0011022
+#define MSR_AMD64_IBSFETCHCTL		0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSOPCTL		0xc0011033
+#define MSR_AMD64_IBSOPRIP		0xc0011034
+#define MSR_AMD64_IBSOPDATA		0xc0011035
+#define MSR_AMD64_IBSOPDATA2		0xc0011036
+#define MSR_AMD64_IBSOPDATA3		0xc0011037
+#define MSR_AMD64_IBSDCLINAD		0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSCTL		0xc001103a
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
+#define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1			0xc001001a
+#define MSR_K8_TOP_MEM2			0xc001001d
+#define MSR_K8_SYSCFG			0xc0010010
+#define MSR_K8_INT_PENDING_MSG		0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
+#define MSR_K8_TSEG_ADDR		0xc0010112
+#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0			0xc0010000
+#define MSR_K7_PERFCTR0			0xc0010004
+#define MSR_K7_EVNTSEL1			0xc0010001
+#define MSR_K7_PERFCTR1			0xc0010005
+#define MSR_K7_EVNTSEL2			0xc0010002
+#define MSR_K7_PERFCTR2			0xc0010006
+#define MSR_K7_EVNTSEL3			0xc0010003
+#define MSR_K7_PERFCTR3			0xc0010007
+#define MSR_K7_CLK_CTL			0xc001001b
+#define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_FID_VID_CTL		0xc0010041
+#define MSR_K7_FID_VID_STATUS		0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_EFER			0xc0000080
+#define MSR_K6_STAR			0xc0000081
+#define MSR_K6_WHCR			0xc0000082
+#define MSR_K6_UWCCR			0xc0000085
+#define MSR_K6_EPMR			0xc0000086
+#define MSR_K6_PSOR			0xc0000087
+#define MSR_K6_PFIR			0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1			0x00000107
+#define MSR_IDT_FCR2			0x00000108
+#define MSR_IDT_FCR3			0x00000109
+#define MSR_IDT_FCR4			0x0000010a
+
+#define MSR_IDT_MCR0			0x00000110
+#define MSR_IDT_MCR1			0x00000111
+#define MSR_IDT_MCR2			0x00000112
+#define MSR_IDT_MCR3			0x00000113
+#define MSR_IDT_MCR4			0x00000114
+#define MSR_IDT_MCR5			0x00000115
+#define MSR_IDT_MCR6			0x00000116
+#define MSR_IDT_MCR7			0x00000117
+#define MSR_IDT_MCR_CTRL		0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR			0x00001107
+#define MSR_VIA_LONGHAUL		0x0000110a
+#define MSR_VIA_RNG			0x0000110b
+#define MSR_VIA_BCR2			0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL		0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
+#define MSR_TMTA_LRTI_READOUT		0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR		0x00000000
+#define MSR_IA32_P5_MC_TYPE		0x00000001
+#define MSR_IA32_TSC			0x00000010
+#define MSR_IA32_PLATFORM_ID		0x00000017
+#define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
+
+#define FEATURE_CONTROL_LOCKED				(1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
+
+#define MSR_IA32_APICBASE		0x0000001b
+#define MSR_IA32_APICBASE_BSP		(1<<8)
+#define MSR_IA32_APICBASE_ENABLE	(1<<11)
+#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
+
+#define MSR_IA32_UCODE_WRITE		0x00000079
+#define MSR_IA32_UCODE_REV		0x0000008b
+
+#define MSR_IA32_PERF_STATUS		0x00000198
+#define MSR_IA32_PERF_CTL		0x00000199
+
+#define MSR_IA32_MPERF			0x000000e7
+#define MSR_IA32_APERF			0x000000e8
+
+#define MSR_IA32_THERM_CONTROL		0x0000019a
+#define MSR_IA32_THERM_INTERRUPT	0x0000019b
+
+#define THERM_INT_LOW_ENABLE		(1 << 0)
+#define THERM_INT_HIGH_ENABLE		(1 << 1)
+
+#define MSR_IA32_THERM_STATUS		0x0000019c
+
+#define THERM_STATUS_PROCHOT		(1 << 0)
+
+#define MSR_THERM2_CTL			0x0000019d
+
+#define MSR_THERM2_CTL_TM_SELECT	(1ULL << 16)
+
+#define MSR_IA32_MISC_ENABLE		0x000001a0
+
+#define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
+
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
+#define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)
+#define MSR_IA32_MISC_ENABLE_EMON		(1ULL << 7)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL	(1ULL << 11)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL	(1ULL << 12)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP	(1ULL << 16)
+#define MSR_IA32_MISC_ENABLE_MWAIT		(1ULL << 18)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID	(1ULL << 22)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE	(1ULL << 23)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE		(1ULL << 34)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT		(1ULL << 2)
+#define MSR_IA32_MISC_ENABLE_TM1		(1ULL << 3)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE	(1ULL << 4)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE	(1ULL << 6)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK	(1ULL << 8)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE	(1ULL << 9)
+#define MSR_IA32_MISC_ENABLE_FERR		(1ULL << 10)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX	(1ULL << 10)
+#define MSR_IA32_MISC_ENABLE_TM2		(1ULL << 13)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE	(1ULL << 19)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK	(1ULL << 20)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT	(1ULL << 24)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE	(1ULL << 37)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE	(1ULL << 38)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE	(1ULL << 39)
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX		0x00000180
+#define MSR_IA32_MCG_EBX		0x00000181
+#define MSR_IA32_MCG_ECX		0x00000182
+#define MSR_IA32_MCG_EDX		0x00000183
+#define MSR_IA32_MCG_ESI		0x00000184
+#define MSR_IA32_MCG_EDI		0x00000185
+#define MSR_IA32_MCG_EBP		0x00000186
+#define MSR_IA32_MCG_ESP		0x00000187
+#define MSR_IA32_MCG_EFLAGS		0x00000188
+#define MSR_IA32_MCG_EIP		0x00000189
+#define MSR_IA32_MCG_RESERVED		0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0		0x00000300
+#define MSR_P4_BPU_PERFCTR1		0x00000301
+#define MSR_P4_BPU_PERFCTR2		0x00000302
+#define MSR_P4_BPU_PERFCTR3		0x00000303
+#define MSR_P4_MS_PERFCTR0		0x00000304
+#define MSR_P4_MS_PERFCTR1		0x00000305
+#define MSR_P4_MS_PERFCTR2		0x00000306
+#define MSR_P4_MS_PERFCTR3		0x00000307
+#define MSR_P4_FLAME_PERFCTR0		0x00000308
+#define MSR_P4_FLAME_PERFCTR1		0x00000309
+#define MSR_P4_FLAME_PERFCTR2		0x0000030a
+#define MSR_P4_FLAME_PERFCTR3		0x0000030b
+#define MSR_P4_IQ_PERFCTR0		0x0000030c
+#define MSR_P4_IQ_PERFCTR1		0x0000030d
+#define MSR_P4_IQ_PERFCTR2		0x0000030e
+#define MSR_P4_IQ_PERFCTR3		0x0000030f
+#define MSR_P4_IQ_PERFCTR4		0x00000310
+#define MSR_P4_IQ_PERFCTR5		0x00000311
+#define MSR_P4_BPU_CCCR0		0x00000360
+#define MSR_P4_BPU_CCCR1		0x00000361
+#define MSR_P4_BPU_CCCR2		0x00000362
+#define MSR_P4_BPU_CCCR3		0x00000363
+#define MSR_P4_MS_CCCR0			0x00000364
+#define MSR_P4_MS_CCCR1			0x00000365
+#define MSR_P4_MS_CCCR2			0x00000366
+#define MSR_P4_MS_CCCR3			0x00000367
+#define MSR_P4_FLAME_CCCR0		0x00000368
+#define MSR_P4_FLAME_CCCR1		0x00000369
+#define MSR_P4_FLAME_CCCR2		0x0000036a
+#define MSR_P4_FLAME_CCCR3		0x0000036b
+#define MSR_P4_IQ_CCCR0			0x0000036c
+#define MSR_P4_IQ_CCCR1			0x0000036d
+#define MSR_P4_IQ_CCCR2			0x0000036e
+#define MSR_P4_IQ_CCCR3			0x0000036f
+#define MSR_P4_IQ_CCCR4			0x00000370
+#define MSR_P4_IQ_CCCR5			0x00000371
+#define MSR_P4_ALF_ESCR0		0x000003ca
+#define MSR_P4_ALF_ESCR1		0x000003cb
+#define MSR_P4_BPU_ESCR0		0x000003b2
+#define MSR_P4_BPU_ESCR1		0x000003b3
+#define MSR_P4_BSU_ESCR0		0x000003a0
+#define MSR_P4_BSU_ESCR1		0x000003a1
+#define MSR_P4_CRU_ESCR0		0x000003b8
+#define MSR_P4_CRU_ESCR1		0x000003b9
+#define MSR_P4_CRU_ESCR2		0x000003cc
+#define MSR_P4_CRU_ESCR3		0x000003cd
+#define MSR_P4_CRU_ESCR4		0x000003e0
+#define MSR_P4_CRU_ESCR5		0x000003e1
+#define MSR_P4_DAC_ESCR0		0x000003a8
+#define MSR_P4_DAC_ESCR1		0x000003a9
+#define MSR_P4_FIRM_ESCR0		0x000003a4
+#define MSR_P4_FIRM_ESCR1		0x000003a5
+#define MSR_P4_FLAME_ESCR0		0x000003a6
+#define MSR_P4_FLAME_ESCR1		0x000003a7
+#define MSR_P4_FSB_ESCR0		0x000003a2
+#define MSR_P4_FSB_ESCR1		0x000003a3
+#define MSR_P4_IQ_ESCR0			0x000003ba
+#define MSR_P4_IQ_ESCR1			0x000003bb
+#define MSR_P4_IS_ESCR0			0x000003b4
+#define MSR_P4_IS_ESCR1			0x000003b5
+#define MSR_P4_ITLB_ESCR0		0x000003b6
+#define MSR_P4_ITLB_ESCR1		0x000003b7
+#define MSR_P4_IX_ESCR0			0x000003c8
+#define MSR_P4_IX_ESCR1			0x000003c9
+#define MSR_P4_MOB_ESCR0		0x000003aa
+#define MSR_P4_MOB_ESCR1		0x000003ab
+#define MSR_P4_MS_ESCR0			0x000003c0
+#define MSR_P4_MS_ESCR1			0x000003c1
+#define MSR_P4_PMH_ESCR0		0x000003ac
+#define MSR_P4_PMH_ESCR1		0x000003ad
+#define MSR_P4_RAT_ESCR0		0x000003bc
+#define MSR_P4_RAT_ESCR1		0x000003bd
+#define MSR_P4_SAAT_ESCR0		0x000003ae
+#define MSR_P4_SAAT_ESCR1		0x000003af
+#define MSR_P4_SSU_ESCR0		0x000003be
+#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0		0x000003c2
+#define MSR_P4_TBPU_ESCR1		0x000003c3
+#define MSR_P4_TC_ESCR0			0x000003c4
+#define MSR_P4_TC_ESCR1			0x000003c5
+#define MSR_P4_U2L_ESCR0		0x000003b0
+#define MSR_P4_U2L_ESCR1		0x000003b1
+
+#define MSR_P4_PEBS_MATRIX_VERT		0x000003f2
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0		0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+#define MSR_IA32_VMX_TRUE_PIN		0x0000048d
+#define MSR_IA32_VMX_TRUE_PROC		0x0000048e
+#define MSR_IA32_VMX_TRUE_EXIT		0x0000048f
+#define MSR_IA32_VMX_TRUE_ENTRY		0x00000490
+
+#define MSR_IA32_TSCDEADLINE		0x000006e0
+
+/* AMD-V MSRs */
+
+#define MSR_VM_CR                       0xc0010114
+#define MSR_VM_IGNNE                    0xc0010115
+#define MSR_VM_HSAVE_PA                 0xc0010117
+
+#endif /* _ASM_X86_MSR_INDEX_H */

tests/kvm-unit-tests/lib/x86/processor.h

@@ -0,0 +1,433 @@
+#ifndef LIBCFLAT_PROCESSOR_H
+#define LIBCFLAT_PROCESSOR_H
+
+#include "libcflat.h"
+#include "msr.h"
+#include <stdint.h>
+
+#ifdef __x86_64__
+#  define R "r"
+#  define W "q"
+#  define S "8"
+#else
+#  define R "e"
+#  define W "l"
+#  define S "4"
+#endif
+
+#define X86_CR0_PE     0x00000001
+#define X86_CR0_MP     0x00000002
+#define X86_CR0_TS     0x00000008
+#define X86_CR0_WP     0x00010000
+#define X86_CR0_AM     0x00040000
+#define X86_CR0_PG     0x80000000
+#define X86_CR4_TSD    0x00000004
+#define X86_CR4_DE     0x00000008
+#define X86_CR4_PSE    0x00000010
+#define X86_CR4_PAE    0x00000020
+#define X86_CR4_VMXE   0x00002000
+#define X86_CR4_PCIDE  0x00020000
+#define X86_CR4_SMAP   0x00200000
+#define X86_CR4_PKE    0x00400000
+
+#define X86_EFLAGS_CF  0x00000001
+#define X86_EFLAGS_PF  0x00000004
+#define X86_EFLAGS_AF  0x00000010
+#define X86_EFLAGS_ZF  0x00000040
+#define X86_EFLAGS_SF  0x00000080
+#define X86_EFLAGS_OF  0x00000800
+#define X86_EFLAGS_AC  0x00040000
+
+#define X86_IA32_EFER          0xc0000080
+#define X86_EFER_LMA           (1UL << 8)
+
+struct far_pointer32 {
+	u32 offset;
+	u16 selector;
+} __attribute__((packed));
+
+struct descriptor_table_ptr {
+    u16 limit;
+    ulong base;
+} __attribute__((packed));
+
+static inline void barrier(void)
+{
+    asm volatile ("" : : : "memory");
+}
+
+static inline void clac(void)
+{
+    asm volatile (".byte 0x0f, 0x01, 0xca" : : : "memory");
+}
+
+static inline void stac(void)
+{
+    asm volatile (".byte 0x0f, 0x01, 0xcb" : : : "memory");
+}
+
+static inline u16 read_cs(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%cs, %0" : "=mr"(val));
+    return val;
+}
+
+static inline u16 read_ds(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%ds, %0" : "=mr"(val));
+    return val;
+}
+
+static inline u16 read_es(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%es, %0" : "=mr"(val));
+    return val;
+}
+
+static inline u16 read_ss(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%ss, %0" : "=mr"(val));
+    return val;
+}
+
+static inline u16 read_fs(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%fs, %0" : "=mr"(val));
+    return val;
+}
+
+static inline u16 read_gs(void)
+{
+    unsigned val;
+
+    asm volatile ("mov %%gs, %0" : "=mr"(val));
+    return val;
+}
+
+static inline unsigned long read_rflags(void)
+{
+	unsigned long f;
+	asm volatile ("pushf; pop %0\n\t" : "=rm"(f));
+	return f;
+}
+
+static inline void write_ds(unsigned val)
+{
+    asm volatile ("mov %0, %%ds" : : "rm"(val) : "memory");
+}
+
+static inline void write_es(unsigned val)
+{
+    asm volatile ("mov %0, %%es" : : "rm"(val) : "memory");
+}
+
+static inline void write_ss(unsigned val)
+{
+    asm volatile ("mov %0, %%ss" : : "rm"(val) : "memory");
+}
+
+static inline void write_fs(unsigned val)
+{
+    asm volatile ("mov %0, %%fs" : : "rm"(val) : "memory");
+}
+
+static inline void write_gs(unsigned val)
+{
+    asm volatile ("mov %0, %%gs" : : "rm"(val) : "memory");
+}
+
+static inline void write_rflags(unsigned long f)
+{
+    asm volatile ("push %0; popf\n\t" : : "rm"(f));
+}
+
+static inline u64 rdmsr(u32 index)
+{
+    u32 a, d;
+    asm volatile ("rdmsr" : "=a"(a), "=d"(d) : "c"(index) : "memory");
+    return a | ((u64)d << 32);
+}
+
+static inline void wrmsr(u32 index, u64 val)
+{
+    u32 a = val, d = val >> 32;
+    asm volatile ("wrmsr" : : "a"(a), "d"(d), "c"(index) : "memory");
+}
+
+static inline uint64_t rdpmc(uint32_t index)
+{
+    uint32_t a, d;
+    asm volatile ("rdpmc" : "=a"(a), "=d"(d) : "c"(index));
+    return a | ((uint64_t)d << 32);
+}
+
+static inline void write_cr0(ulong val)
+{
+    asm volatile ("mov %0, %%cr0" : : "r"(val) : "memory");
+}
+
+static inline ulong read_cr0(void)
+{
+    ulong val;
+    asm volatile ("mov %%cr0, %0" : "=r"(val) : : "memory");
+    return val;
+}
+
+static inline void write_cr2(ulong val)
+{
+    asm volatile ("mov %0, %%cr2" : : "r"(val) : "memory");
+}
+
+static inline ulong read_cr2(void)
+{
+    ulong val;
+    asm volatile ("mov %%cr2, %0" : "=r"(val) : : "memory");
+    return val;
+}
+
+static inline void write_cr3(ulong val)
+{
+    asm volatile ("mov %0, %%cr3" : : "r"(val) : "memory");
+}
+
+static inline ulong read_cr3(void)
+{
+    ulong val;
+    asm volatile ("mov %%cr3, %0" : "=r"(val) : : "memory");
+    return val;
+}
+
+static inline void write_cr4(ulong val)
+{
+    asm volatile ("mov %0, %%cr4" : : "r"(val) : "memory");
+}
+
+static inline ulong read_cr4(void)
+{
+    ulong val;
+    asm volatile ("mov %%cr4, %0" : "=r"(val) : : "memory");
+    return val;
+}
+
+static inline void write_cr8(ulong val)
+{
+    asm volatile ("mov %0, %%cr8" : : "r"(val) : "memory");
+}
+
+static inline ulong read_cr8(void)
+{
+    ulong val;
+    asm volatile ("mov %%cr8, %0" : "=r"(val) : : "memory");
+    return val;
+}
+
+static inline void lgdt(const struct descriptor_table_ptr *ptr)
+{
+    asm volatile ("lgdt %0" : : "m"(*ptr));
+}
+
+static inline void sgdt(struct descriptor_table_ptr *ptr)
+{
+    asm volatile ("sgdt %0" : "=m"(*ptr));
+}
+
+static inline void lidt(const struct descriptor_table_ptr *ptr)
+{
+    asm volatile ("lidt %0" : : "m"(*ptr));
+}
+
+static inline void sidt(struct descriptor_table_ptr *ptr)
+{
+    asm volatile ("sidt %0" : "=m"(*ptr));
+}
+
+static inline void lldt(unsigned val)
+{
+    asm volatile ("lldt %0" : : "rm"(val));
+}
+
+static inline u16 sldt(void)
+{
+    u16 val;
+    asm volatile ("sldt %0" : "=rm"(val));
+    return val;
+}
+
+static inline void ltr(u16 val)
+{
+    asm volatile ("ltr %0" : : "rm"(val));
+}
+
+static inline u16 str(void)
+{
+    u16 val;
+    asm volatile ("str %0" : "=rm"(val));
+    return val;
+}
+
+static inline void write_dr6(ulong val)
+{
+    asm volatile ("mov %0, %%dr6" : : "r"(val) : "memory");
+}
+
+static inline ulong read_dr6(void)
+{
+    ulong val;
+    asm volatile ("mov %%dr6, %0" : "=r"(val));
+    return val;
+}
+
+static inline void write_dr7(ulong val)
+{
+    asm volatile ("mov %0, %%dr7" : : "r"(val) : "memory");
+}
+
+static inline ulong read_dr7(void)
+{
+    ulong val;
+    asm volatile ("mov %%dr7, %0" : "=r"(val));
+    return val;
+}
+
+struct cpuid { u32 a, b, c, d; };
+
+static inline struct cpuid raw_cpuid(u32 function, u32 index)
+{
+    struct cpuid r;
+    asm volatile ("cpuid"
+                  : "=a"(r.a), "=b"(r.b), "=c"(r.c), "=d"(r.d)
+                  : "0"(function), "2"(index));
+    return r;
+}
+
+static inline struct cpuid cpuid_indexed(u32 function, u32 index)
+{
+    u32 level = raw_cpuid(function & 0xf0000000, 0).a;
+    if (level < function)
+        return (struct cpuid) { 0, 0, 0, 0 };
+    return raw_cpuid(function, index);
+}
+
+static inline struct cpuid cpuid(u32 function)
+{
+    return cpuid_indexed(function, 0);
+}
+
+static inline u8 cpuid_maxphyaddr(void)
+{
+    if (raw_cpuid(0x80000000, 0).a < 0x80000008)
+        return 36;
+    return raw_cpuid(0x80000008, 0).a & 0xff;
+}
+
+
+static inline void pause(void)
+{
+    asm volatile ("pause");
+}
+
+static inline void cli(void)
+{
+    asm volatile ("cli");
+}
+
+static inline void sti(void)
+{
+    asm volatile ("sti");
+}
+
+static inline unsigned long long rdtsc()
+{
+	long long r;
+
+#ifdef __x86_64__
+	unsigned a, d;
+
+	asm volatile ("rdtsc" : "=a"(a), "=d"(d));
+	r = a | ((long long)d << 32);
+#else
+	asm volatile ("rdtsc" : "=A"(r));
+#endif
+	return r;
+}
+
+static inline unsigned long long rdtscp(u32 *aux)
+{
+       long long r;
+
+#ifdef __x86_64__
+       unsigned a, d;
+
+       asm volatile ("rdtscp" : "=a"(a), "=d"(d), "=c"(*aux));
+       r = a | ((long long)d << 32);
+#else
+       asm volatile ("rdtscp" : "=A"(r), "=c"(*aux));
+#endif
+       return r;
+}
+
+static inline void wrtsc(u64 tsc)
+{
+	unsigned a = tsc, d = tsc >> 32;
+
+	asm volatile("wrmsr" : : "a"(a), "d"(d), "c"(0x10));
+}
+
+static inline void irq_disable(void)
+{
+    asm volatile("cli");
+}
+
+/* Note that irq_enable() does not ensure an interrupt shadow due
+ * to the vagaries of compiler optimizations.  If you need the
+ * shadow, use a single asm with "sti" and the instruction after it.
+ */
+static inline void irq_enable(void)
+{
+    asm volatile("sti");
+}
+
+static inline void invlpg(volatile void *va)
+{
+	asm volatile("invlpg (%0)" ::"r" (va) : "memory");
+}
+
+static inline void safe_halt(void)
+{
+	asm volatile("sti; hlt");
+}
+
+static inline u32 read_pkru(void)
+{
+    unsigned int eax, edx;
+    unsigned int ecx = 0;
+    unsigned int pkru;
+
+    asm volatile(".byte 0x0f,0x01,0xee\n\t"
+                 : "=a" (eax), "=d" (edx)
+                 : "c" (ecx));
+    pkru = eax;
+    return pkru;
+}
+
+static inline void write_pkru(u32 pkru)
+{
+    unsigned int eax = pkru;
+    unsigned int ecx = 0;
+    unsigned int edx = 0;
+
+    asm volatile(".byte 0x0f,0x01,0xef\n\t"
+        : : "a" (eax), "c" (ecx), "d" (edx));
+}
+
+#endif

tests/kvm-unit-tests/lib/x86/setjmp32.S

@@ -0,0 +1,25 @@
+.globl setjmp
+setjmp:
+	mov (%esp), %ecx	// get return EIP
+	mov 4(%esp), %eax	// get jmp_buf
+	mov %ecx, (%eax)
+	mov %esp, 4(%eax)
+	mov %ebp, 8(%eax)
+	mov %ebx, 12(%eax)
+	mov %esi, 16(%eax)
+	mov %edi, 20(%eax)
+	xor %eax, %eax
+	ret
+
+.globl longjmp
+longjmp:
+	mov 8(%esp), %eax	// get return value
+	mov 4(%esp), %ecx	// get jmp_buf
+	mov 20(%ecx), %edi
+	mov 16(%ecx), %esi
+	mov 12(%ecx), %ebx
+	mov 8(%ecx), %ebp
+	mov 4(%ecx), %esp
+	mov (%ecx), %ecx	// get saved EIP
+	mov %ecx, (%esp)	// and store it on the stack
+	ret

tests/kvm-unit-tests/lib/x86/setjmp64.S

@@ -0,0 +1,27 @@
+.globl setjmp
+setjmp:
+	mov (%rsp), %rsi
+	mov %rsi, (%rdi)
+	mov %rsp, 0x8(%rdi)
+	mov %rbp, 0x10(%rdi)
+	mov %rbx, 0x18(%rdi)
+	mov %r12, 0x20(%rdi)
+	mov %r13, 0x28(%rdi)
+	mov %r14, 0x30(%rdi)
+	mov %r15, 0x38(%rdi)
+	xor %eax, %eax
+	ret
+
+.globl longjmp
+longjmp:
+	mov %esi, %eax
+	mov 0x38(%rdi), %r15
+	mov 0x30(%rdi), %r14
+	mov 0x28(%rdi), %r13
+	mov 0x20(%rdi), %r12
+	mov 0x18(%rdi), %rbx
+	mov 0x10(%rdi), %rbp
+	mov 0x8(%rdi), %rsp
+	mov (%rdi), %rsi
+	mov %rsi, (%rsp)
+	ret

tests/kvm-unit-tests/lib/x86/setup.c

@@ -0,0 +1,47 @@
+/*
+ * Initialize machine setup information
+ *
+ * Copyright (C) 2017, Red Hat Inc, Andrew Jones <drjones@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.
+ */
+#include "libcflat.h"
+
+#define MBI_MODS_COUNT	20
+#define MBI_MODS_ADDR	24
+#define MB_MOD_START	 0
+#define MB_MOD_END	 4
+
+#define ENV_SIZE 16384
+
+extern void setup_env(char *env, int size);
+
+char *initrd;
+u32 initrd_size;
+
+static char env[ENV_SIZE];
+
+void setup_get_initrd(u8 *bootinfo)
+{
+	u32 *mods_addr, *mod_start, *mod_end;
+
+	if (*((u32 *)&bootinfo[MBI_MODS_COUNT]) != 1)
+		return;
+
+	mods_addr = (u32 *)&bootinfo[MBI_MODS_ADDR];
+	mod_start = (u32 *)(ulong)(*mods_addr + MB_MOD_START);
+	mod_end = (u32 *)(ulong)(*mods_addr + MB_MOD_END);
+
+	initrd = (char *)(ulong)*mod_start;
+	initrd_size = *mod_end - *mod_start;
+}
+
+void setup_environ(void)
+{
+	if (initrd) {
+		/* environ is currently the only file in the initrd */
+		u32 size = MIN(initrd_size, ENV_SIZE);
+		memcpy(env, initrd, size);
+		setup_env(env, size);
+	}
+}

tests/kvm-unit-tests/lib/x86/smp.c

@@ -0,0 +1,125 @@
+
+#include <libcflat.h>
+#include "smp.h"
+#include "apic.h"
+#include "fwcfg.h"
+#include "desc.h"
+
+#define IPI_VECTOR 0x20
+
+typedef void (*ipi_function_type)(void *data);
+
+static struct spinlock ipi_lock;
+static volatile ipi_function_type ipi_function;
+static void *volatile ipi_data;
+static volatile int ipi_done;
+static volatile bool ipi_wait;
+static int _cpu_count;
+
+static __attribute__((used)) void ipi()
+{
+    void (*function)(void *data) = ipi_function;
+    void *data = ipi_data;
+    bool wait = ipi_wait;
+
+    if (!wait) {
+	ipi_done = 1;
+	apic_write(APIC_EOI, 0);
+    }
+    function(data);
+    if (wait) {
+	ipi_done = 1;
+	apic_write(APIC_EOI, 0);
+    }
+}
+
+asm (
+     "ipi_entry: \n"
+     "   call ipi \n"
+#ifndef __x86_64__
+     "   iret"
+#else
+     "   iretq"
+#endif
+     );
+
+void spin_lock(struct spinlock *lock)
+{
+    int v = 1;
+
+    do {
+	asm volatile ("xchg %1, %0" : "+m"(lock->v), "+r"(v));
+    } while (v);
+    asm volatile ("" : : : "memory");
+}
+
+void spin_unlock(struct spinlock *lock)
+{
+    asm volatile ("" : : : "memory");
+    lock->v = 0;
+}
+
+int cpu_count(void)
+{
+    return _cpu_count;
+}
+
+int smp_id(void)
+{
+    unsigned id;
+
+    asm ("mov %%gs:0, %0" : "=r"(id));
+    return id;
+}
+
+static void setup_smp_id(void *data)
+{
+    asm ("mov %0, %%gs:0" : : "r"(apic_id()) : "memory");
+}
+
+static void __on_cpu(int cpu, void (*function)(void *data), void *data,
+                     int wait)
+{
+    spin_lock(&ipi_lock);
+    if (cpu == smp_id())
+	function(data);
+    else {
+	ipi_done = 0;
+	ipi_function = function;
+	ipi_data = data;
+	ipi_wait = wait;
+	apic_icr_write(APIC_INT_ASSERT | APIC_DEST_PHYSICAL | APIC_DM_FIXED
+                       | IPI_VECTOR,
+                       cpu);
+	while (!ipi_done)
+	    ;
+    }
+    spin_unlock(&ipi_lock);
+}
+
+void on_cpu(int cpu, void (*function)(void *data), void *data)
+{
+    __on_cpu(cpu, function, data, 1);
+}
+
+void on_cpu_async(int cpu, void (*function)(void *data), void *data)
+{
+    __on_cpu(cpu, function, data, 0);
+}
+
+
+void smp_init(void)
+{
+    int i;
+    void ipi_entry(void);
+
+    _cpu_count = fwcfg_get_nb_cpus();
+
+    setup_idt();
+    set_idt_entry(IPI_VECTOR, ipi_entry, 0);
+
+    setup_smp_id(0);
+    for (i = 1; i < cpu_count(); ++i)
+        on_cpu(i, setup_smp_id, 0);
+
+}

tests/kvm-unit-tests/lib/x86/smp.h

@@ -0,0 +1,12 @@
+#ifndef __SMP_H
+#define __SMP_H
+#include <asm/spinlock.h>
+
+void smp_init(void);
+
+int cpu_count(void);
+int smp_id(void);
+void on_cpu(int cpu, void (*function)(void *data), void *data);
+void on_cpu_async(int cpu, void (*function)(void *data), void *data);
+
+#endif

tests/kvm-unit-tests/lib/x86/stack.c

@@ -0,0 +1,31 @@
+#include <libcflat.h>
+#include <stack.h>
+
+int backtrace_frame(const void *frame, const void **return_addrs, int max_depth)
+{
+	static int walking;
+	int depth = 0;
+	const unsigned long *bp = (unsigned long *) frame;
+
+	if (walking) {
+		printf("RECURSIVE STACK WALK!!!\n");
+		return 0;
+	}
+	walking = 1;
+
+	for (depth = 0; bp && depth < max_depth; depth++) {
+		return_addrs[depth] = (void *) bp[1];
+		if (return_addrs[depth] == 0)
+			break;
+		bp = (unsigned long *) bp[0];
+	}
+
+	walking = 0;
+	return depth;
+}
+
+int backtrace(const void **return_addrs, int max_depth)
+{
+	return backtrace_frame(__builtin_frame_address(0), return_addrs,
+			       max_depth);
+}

tests/kvm-unit-tests/lib/x86/vm.c

@@ -0,0 +1,224 @@
+#include "fwcfg.h"
+#include "vm.h"
+#include "libcflat.h"
+
+static void *free = 0;
+static void *vfree_top = 0;
+
+static void free_memory(void *mem, unsigned long size)
+{
+    while (size >= PAGE_SIZE) {
+	*(void **)mem = free;
+	free = mem;
+	mem += PAGE_SIZE;
+	size -= PAGE_SIZE;
+    }
+}
+
+void *alloc_page()
+{
+    void *p;
+
+    if (!free)
+	return 0;
+
+    p = free;
+    free = *(void **)free;
+
+    return p;
+}
+
+void free_page(void *page)
+{
+    *(void **)page = free;
+    free = page;
+}
+
+extern char edata;
+static unsigned long end_of_memory;
+
+unsigned long *install_pte(unsigned long *cr3,
+			   int pte_level,
+			   void *virt,
+			   unsigned long pte,
+			   unsigned long *pt_page)
+{
+    int level;
+    unsigned long *pt = cr3;
+    unsigned offset;
+
+    for (level = PAGE_LEVEL; level > pte_level; --level) {
+	offset = PGDIR_OFFSET((unsigned long)virt, level);
+	if (!(pt[offset] & PT_PRESENT_MASK)) {
+	    unsigned long *new_pt = pt_page;
+            if (!new_pt)
+                new_pt = alloc_page();
+            else
+                pt_page = 0;
+	    memset(new_pt, 0, PAGE_SIZE);
+	    pt[offset] = virt_to_phys(new_pt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
+	}
+	pt = phys_to_virt(pt[offset] & PT_ADDR_MASK);
+    }
+    offset = PGDIR_OFFSET((unsigned long)virt, level);
+    pt[offset] = pte;
+    return &pt[offset];
+}
+
+unsigned long *get_pte(unsigned long *cr3, void *virt)
+{
+    int level;
+    unsigned long *pt = cr3, pte;
+    unsigned offset;
+
+    for (level = PAGE_LEVEL; level > 1; --level) {
+	offset = ((unsigned long)virt >> (((level-1) * PGDIR_WIDTH) + 12)) & PGDIR_MASK;
+	pte = pt[offset];
+	if (!(pte & PT_PRESENT_MASK))
+	    return NULL;
+	if (level == 2 && (pte & PT_PAGE_SIZE_MASK))
+	    return &pt[offset];
+	pt = phys_to_virt(pte & PT_ADDR_MASK);
+    }
+    offset = ((unsigned long)virt >> (((level-1) * PGDIR_WIDTH) + 12)) & PGDIR_MASK;
+    return &pt[offset];
+}
+
+unsigned long *install_large_page(unsigned long *cr3,
+				  unsigned long phys,
+				  void *virt)
+{
+    return install_pte(cr3, 2, virt,
+		       phys | PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK | PT_PAGE_SIZE_MASK, 0);
+}
+
+unsigned long *install_page(unsigned long *cr3,
+			    unsigned long phys,
+			    void *virt)
+{
+    return install_pte(cr3, 1, virt, phys | PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK, 0);
+}
+
+
+static void setup_mmu_range(unsigned long *cr3, unsigned long start,
+			    unsigned long len)
+{
+	u64 max = (u64)len + (u64)start;
+	u64 phys = start;
+
+	while (phys + LARGE_PAGE_SIZE <= max) {
+		install_large_page(cr3, phys, (void *)(ulong)phys);
+		phys += LARGE_PAGE_SIZE;
+	}
+	while (phys + PAGE_SIZE <= max) {
+		install_page(cr3, phys, (void *)(ulong)phys);
+		phys += PAGE_SIZE;
+	}
+}
+
+static void setup_mmu(unsigned long len)
+{
+    unsigned long *cr3 = alloc_page();
+
+    memset(cr3, 0, PAGE_SIZE);
+
+#ifdef __x86_64__
+    if (len < (1ul << 32))
+        len = (1ul << 32);  /* map mmio 1:1 */
+
+    setup_mmu_range(cr3, 0, len);
+#else
+    if (len > (1ul << 31))
+	    len = (1ul << 31);
+
+    /* 0 - 2G memory, 2G-3G valloc area, 3G-4G mmio */
+    setup_mmu_range(cr3, 0, len);
+    setup_mmu_range(cr3, 3ul << 30, (1ul << 30));
+    vfree_top = (void*)(3ul << 30);
+#endif
+
+    write_cr3(virt_to_phys(cr3));
+#ifndef __x86_64__
+    write_cr4(X86_CR4_PSE);
+#endif
+    write_cr0(X86_CR0_PG |X86_CR0_PE | X86_CR0_WP);
+
+    printf("paging enabled\n");
+    printf("cr0 = %lx\n", read_cr0());
+    printf("cr3 = %lx\n", read_cr3());
+    printf("cr4 = %lx\n", read_cr4());
+}
+
+void setup_vm()
+{
+    assert(!end_of_memory);
+    end_of_memory = fwcfg_get_u64(FW_CFG_RAM_SIZE);
+    free_memory(&edata, end_of_memory - (unsigned long)&edata);
+    setup_mmu(end_of_memory);
+}
+
+void *vmalloc(unsigned long size)
+{
+    void *mem, *p;
+    unsigned pages;
+
+    size += sizeof(unsigned long);
+
+    size = (size + PAGE_SIZE - 1) & ~(PAGE_SIZE - 1);
+    vfree_top -= size;
+    mem = p = vfree_top;
+    pages = size / PAGE_SIZE;
+    while (pages--) {
+	install_page(phys_to_virt(read_cr3()), virt_to_phys(alloc_page()), p);
+	p += PAGE_SIZE;
+    }
+    *(unsigned long *)mem = size;
+    mem += sizeof(unsigned long);
+    return mem;
+}
+
+uint64_t virt_to_phys_cr3(void *mem)
+{
+    return (*get_pte(phys_to_virt(read_cr3()), mem) & PT_ADDR_MASK) + ((ulong)mem & (PAGE_SIZE - 1));
+}
+
+void vfree(void *mem)
+{
+    unsigned long size = ((unsigned long *)mem)[-1];
+
+    while (size) {
+	free_page(phys_to_virt(*get_pte(phys_to_virt(read_cr3()), mem) & PT_ADDR_MASK));
+	mem += PAGE_SIZE;
+	size -= PAGE_SIZE;
+    }
+}
+
+void *vmap(unsigned long long phys, unsigned long size)
+{
+    void *mem, *p;
+    unsigned pages;
+
+    size = (size + PAGE_SIZE - 1) & ~(PAGE_SIZE - 1);
+    vfree_top -= size;
+    phys &= ~(unsigned long long)(PAGE_SIZE - 1);
+
+    mem = p = vfree_top;
+    pages = size / PAGE_SIZE;
+    while (pages--) {
+	install_page(phys_to_virt(read_cr3()), phys, p);
+	phys += PAGE_SIZE;
+	p += PAGE_SIZE;
+    }
+    return mem;
+}
+
+void *alloc_vpages(ulong nr)
+{
+	vfree_top -= PAGE_SIZE * nr;
+	return vfree_top;
+}
+
+void *alloc_vpage(void)
+{
+    return alloc_vpages(1);
+}

tests/kvm-unit-tests/lib/x86/vm.h

@@ -0,0 +1,31 @@
+#ifndef VM_H
+#define VM_H
+
+#include "processor.h"
+#include "asm/page.h"
+#include "asm/io.h"
+
+void setup_vm();
+
+void *vmalloc(unsigned long size);
+void vfree(void *mem);
+void *vmap(unsigned long long phys, unsigned long size);
+void *alloc_vpage(void);
+void *alloc_vpages(ulong nr);
+uint64_t virt_to_phys_cr3(void *mem);
+
+unsigned long *get_pte(unsigned long *cr3, void *virt);
+unsigned long *install_pte(unsigned long *cr3,
+                           int pte_level,
+                           void *virt,
+                           unsigned long pte,
+                           unsigned long *pt_page);
+
+void *alloc_page();
+void free_page(void *page);
+
+unsigned long *install_large_page(unsigned long *cr3,unsigned long phys,
+                                  void *virt);
+unsigned long *install_page(unsigned long *cr3, unsigned long phys, void *virt);
+
+#endif

tests/kvm-unit-tests/run.js

@@ -0,0 +1,38 @@
+#!/usr/bin/env node
+"use strict";
+
+var V86 = require("../../build/libv86.js").V86;
+var fs = require("fs");
+
+function readfile(path)
+{
+    return new Uint8Array(fs.readFileSync(path)).buffer;
+}
+
+function Loader(path)
+{
+    this.buffer = readfile(path);
+    this.byteLength = this.buffer.byteLength;
+}
+
+Loader.prototype.load = function()
+{
+    this.onload && this.onload({});
+};
+
+var bios = readfile(__dirname + "/../../bios/seabios.bin");
+var vga_bios = readfile(__dirname + "/../../bios/vgabios.bin");
+
+var emulator = new V86({
+    bios: { buffer: bios },
+    vga_bios: { buffer: vga_bios },
+    multiboot: new Loader(process.argv[2]),
+    autostart: true,
+    memory_size: 256 * 1024 * 1024,
+});
+
+emulator.add_listener("serial0-output-char", function(chr)
+{
+    process.stdout.write(chr);
+});
+

tests/kvm-unit-tests/x86/Makefile

@@ -0,0 +1 @@
+include $(TEST_DIR)/Makefile.$(ARCH)