* [PATCH 1/5] ppc/pnv: Add a PNOR model
2019-10-21 13:12 [PATCH 0/5] ppc/pnv: Add PNOR support Cédric Le Goater
@ 2019-10-21 13:12 ` Cédric Le Goater
2019-10-27 17:46 ` David Gibson
2019-10-21 13:12 ` [PATCH 2/5] ipmi: Add support to customize OEM functions Cédric Le Goater
` (4 subsequent siblings)
5 siblings, 1 reply; 18+ messages in thread
From: Cédric Le Goater @ 2019-10-21 13:12 UTC (permalink / raw)
To: David Gibson
Cc: qemu-devel, Greg Kurz, Cédric Le Goater, qemu-ppc,
Joel Stanley, Marty E . Plummer, Cédric Le Goater
From: Cédric Le Goater <clg@fr.ibm.com>
On a POWERPC PowerNV system, the host firmware is stored in a PNOR
flash chip which contents is mapped on the LPC bus. This model adds a
simple dummy device to map the contents of a block device in the host
address space.
Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
include/hw/ppc/pnv.h | 3 +
include/hw/ppc/pnv_pnor.h | 25 +++++++
hw/ppc/pnv.c | 14 ++++
hw/ppc/pnv_pnor.c | 135 ++++++++++++++++++++++++++++++++++++++
hw/ppc/Makefile.objs | 4 +-
5 files changed, 180 insertions(+), 1 deletion(-)
create mode 100644 include/hw/ppc/pnv_pnor.h
create mode 100644 hw/ppc/pnv_pnor.c
diff --git a/include/hw/ppc/pnv.h b/include/hw/ppc/pnv.h
index 5e01a9f3df95..e2f20f2b0bc4 100644
--- a/include/hw/ppc/pnv.h
+++ b/include/hw/ppc/pnv.h
@@ -24,6 +24,7 @@
#include "hw/sysbus.h"
#include "hw/ipmi/ipmi.h"
#include "hw/ppc/pnv_lpc.h"
+#include "hw/ppc/pnv_pnor.h"
#include "hw/ppc/pnv_psi.h"
#include "hw/ppc/pnv_occ.h"
#include "hw/ppc/pnv_homer.h"
@@ -173,6 +174,8 @@ typedef struct PnvMachineState {
IPMIBmc *bmc;
Notifier powerdown_notifier;
+
+ PnvPnor *pnor;
} PnvMachineState;
static inline bool pnv_chip_is_power9(const PnvChip *chip)
diff --git a/include/hw/ppc/pnv_pnor.h b/include/hw/ppc/pnv_pnor.h
new file mode 100644
index 000000000000..dec811695c8d
--- /dev/null
+++ b/include/hw/ppc/pnv_pnor.h
@@ -0,0 +1,25 @@
+/*
+ * QEMU PowerNV PNOR simple model
+ *
+ * Copyright (c) 2019, IBM Corporation.
+ *
+ * This code is licensed under the GPL version 2 or later. See the
+ * COPYING file in the top-level directory.
+ */
+#ifndef _PPC_PNV_PNOR_H
+#define _PPC_PNV_PNOR_H
+
+#define TYPE_PNV_PNOR "pnv-pnor"
+#define PNV_PNOR(obj) OBJECT_CHECK(PnvPnor, (obj), TYPE_PNV_PNOR)
+
+typedef struct PnvPnor {
+ SysBusDevice parent_obj;
+
+ BlockBackend *blk;
+
+ uint8_t *storage;
+ uint32_t size;
+ MemoryRegion mmio;
+} PnvPnor;
+
+#endif /* _PPC_PNV_PNOR_H */
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 1a22dfd46031..b74528eba42a 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -44,6 +44,7 @@
#include "hw/ppc/xics.h"
#include "hw/qdev-properties.h"
#include "hw/ppc/pnv_xscom.h"
+#include "hw/ppc/pnv_pnor.h"
#include "hw/isa/isa.h"
#include "hw/boards.h"
@@ -633,6 +634,8 @@ static void pnv_init(MachineState *machine)
long fw_size;
int i;
char *chip_typename;
+ DriveInfo *pnor = drive_get(IF_MTD, 0, 0);
+ DeviceState *dev;
/* allocate RAM */
if (machine->ram_size < (1 * GiB)) {
@@ -644,6 +647,17 @@ static void pnv_init(MachineState *machine)
machine->ram_size);
memory_region_add_subregion(get_system_memory(), 0, ram);
+ /*
+ * Create our simple PNOR device
+ */
+ dev = qdev_create(NULL, TYPE_PNV_PNOR);
+ if (pnor) {
+ qdev_prop_set_drive(dev, "drive", blk_by_legacy_dinfo(pnor),
+ &error_abort);
+ }
+ qdev_init_nofail(dev);
+ pnv->pnor = PNV_PNOR(dev);
+
/* load skiboot firmware */
if (bios_name == NULL) {
bios_name = FW_FILE_NAME;
diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c
new file mode 100644
index 000000000000..bfb1e92b0392
--- /dev/null
+++ b/hw/ppc/pnv_pnor.c
@@ -0,0 +1,135 @@
+/*
+ * QEMU PowerNV PNOR simple model
+ *
+ * Copyright (c) 2015-2019, IBM Corporation.
+ *
+ * This code is licensed under the GPL version 2 or later. See the
+ * COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/log.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/blockdev.h"
+#include "hw/loader.h"
+#include "hw/ppc/pnv_pnor.h"
+#include "hw/qdev-properties.h"
+
+static uint64_t pnv_pnor_read(void *opaque, hwaddr addr, unsigned size)
+{
+ PnvPnor *s = PNV_PNOR(opaque);
+ uint64_t ret = 0;
+ int i;
+
+ for (i = 0; i < size; i++) {
+ ret |= (uint64_t) s->storage[addr + i] << (8 * (size - i - 1));
+ }
+
+ return ret;
+}
+
+static void pnv_pnor_update(PnvPnor *s, int offset, int size)
+{
+ int offset_end;
+
+ if (s->blk) {
+ return;
+ }
+
+ offset_end = offset + size;
+ offset = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE);
+ offset_end = QEMU_ALIGN_UP(offset_end, BDRV_SECTOR_SIZE);
+
+ blk_pwrite(s->blk, offset, s->storage + offset,
+ offset_end - offset, 0);
+}
+
+static void pnv_pnor_write(void *opaque, hwaddr addr, uint64_t data,
+ unsigned size)
+{
+ PnvPnor *s = PNV_PNOR(opaque);
+ int i;
+
+ for (i = 0; i < size; i++) {
+ s->storage[addr + i] = (data >> (8 * (size - i - 1))) & 0xFF;
+ }
+ pnv_pnor_update(s, addr, size);
+}
+
+/*
+ * TODO: Check endianness: skiboot is BIG, Aspeed AHB is LITTLE, flash
+ * is BIG.
+ */
+static const MemoryRegionOps pnv_pnor_ops = {
+ .read = pnv_pnor_read,
+ .write = pnv_pnor_write,
+ .endianness = DEVICE_BIG_ENDIAN,
+ .valid = {
+ .min_access_size = 1,
+ .max_access_size = 4,
+ },
+};
+
+static void pnv_pnor_realize(DeviceState *dev, Error **errp)
+{
+ PnvPnor *s = PNV_PNOR(dev);
+ int ret;
+
+ if (s->blk) {
+ uint64_t perm = BLK_PERM_CONSISTENT_READ |
+ (blk_is_read_only(s->blk) ? 0 : BLK_PERM_WRITE);
+ ret = blk_set_perm(s->blk, perm, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ return;
+ }
+
+ s->size = blk_getlength(s->blk);
+ if (s->size <= 0) {
+ error_setg(errp, "failed to get flash size");
+ return;
+ }
+
+ s->storage = blk_blockalign(s->blk, s->size);
+
+ if (blk_pread(s->blk, 0, s->storage, s->size) != s->size) {
+ error_setg(errp, "failed to read the initial flash content");
+ return;
+ }
+ } else {
+ s->storage = blk_blockalign(NULL, s->size);
+ memset(s->storage, 0xFF, s->size);
+ }
+
+ memory_region_init_io(&s->mmio, OBJECT(s), &pnv_pnor_ops, s,
+ TYPE_PNV_PNOR, s->size);
+}
+
+static Property pnv_pnor_properties[] = {
+ DEFINE_PROP_UINT32("size", PnvPnor, size, 128 << 20),
+ DEFINE_PROP_DRIVE("drive", PnvPnor, blk),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pnv_pnor_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+
+ dc->realize = pnv_pnor_realize;
+ dc->props = pnv_pnor_properties;
+}
+
+static const TypeInfo pnv_pnor_info = {
+ .name = TYPE_PNV_PNOR,
+ .parent = TYPE_SYS_BUS_DEVICE,
+ .instance_size = sizeof(PnvPnor),
+ .class_init = pnv_pnor_class_init,
+};
+
+static void pnv_pnor_register_types(void)
+{
+ type_register_static(&pnv_pnor_info);
+}
+
+type_init(pnv_pnor_register_types)
diff --git a/hw/ppc/Makefile.objs b/hw/ppc/Makefile.objs
index 580bb4f0dd4c..101e9fc59185 100644
--- a/hw/ppc/Makefile.objs
+++ b/hw/ppc/Makefile.objs
@@ -9,7 +9,9 @@ obj-$(CONFIG_PSERIES) += spapr_tpm_proxy.o
obj-$(CONFIG_SPAPR_RNG) += spapr_rng.o
# IBM PowerNV
obj-$(CONFIG_POWERNV) += pnv.o pnv_xscom.o pnv_core.o pnv_lpc.o pnv_psi.o pnv_occ.o pnv_bmc.o
-obj-$(CONFIG_POWERNV) += pnv_homer.o
+obj-$(CONFIG_POWERNV) += pnv_homer.o pnv_pnor.o
+
+
ifeq ($(CONFIG_PCI)$(CONFIG_PSERIES)$(CONFIG_LINUX), yyy)
obj-y += spapr_pci_vfio.o spapr_pci_nvlink2.o
endif
--
2.21.0
^ permalink raw reply related [flat|nested] 18+ messages in thread* [PATCH 4/5] libxz: Add XZ Embedded library for PPC
2019-10-21 13:12 [PATCH 0/5] ppc/pnv: Add PNOR support Cédric Le Goater
` (2 preceding siblings ...)
2019-10-21 13:12 ` [PATCH 3/5] ppc/pnv: Add HIOMAP commands Cédric Le Goater
@ 2019-10-21 13:12 ` Cédric Le Goater
2019-10-21 13:12 ` [PATCH 5/5] ppc/pnv: Read the PNOR partition table Cédric Le Goater
2019-10-21 21:17 ` [PATCH 0/5] ppc/pnv: Add PNOR support no-reply
5 siblings, 0 replies; 18+ messages in thread
From: Cédric Le Goater @ 2019-10-21 13:12 UTC (permalink / raw)
To: David Gibson
Cc: qemu-devel, Greg Kurz, qemu-ppc, Joel Stanley, Marty E . Plummer,
Cédric Le Goater
version 20130513 from https://tukaani.org/xz/embedded.html
Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
libxz/xz.h | 304 ++++++++++
libxz/xz_config.h | 124 ++++
libxz/xz_lzma2.h | 204 +++++++
libxz/xz_private.h | 156 +++++
libxz/xz_stream.h | 62 ++
libxz/xz_crc32.c | 59 ++
libxz/xz_dec_lzma2.c | 1171 ++++++++++++++++++++++++++++++++++++++
libxz/xz_dec_stream.c | 847 +++++++++++++++++++++++++++
libxz/Makefile.objs | 1 +
target/ppc/Makefile.objs | 1 +
10 files changed, 2929 insertions(+)
create mode 100644 libxz/xz.h
create mode 100644 libxz/xz_config.h
create mode 100644 libxz/xz_lzma2.h
create mode 100644 libxz/xz_private.h
create mode 100644 libxz/xz_stream.h
create mode 100644 libxz/xz_crc32.c
create mode 100644 libxz/xz_dec_lzma2.c
create mode 100644 libxz/xz_dec_stream.c
create mode 100644 libxz/Makefile.objs
diff --git a/libxz/xz.h b/libxz/xz.h
new file mode 100644
index 000000000000..75df73e39e53
--- /dev/null
+++ b/libxz/xz.h
@@ -0,0 +1,304 @@
+/*
+ * XZ decompressor
+ *
+ * Authors: Lasse Collin <lasse.collin@tukaani.org>
+ * Igor Pavlov <http://7-zip.org/>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_H
+#define XZ_H
+
+#ifdef __KERNEL__
+ #include <linux/stddef.h>
+ #include <linux/types.h>
+#else
+ #include <stddef.h>
+ #include <stdint.h>
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* In Linux, this is used to make extern functions static when needed. */
+#ifndef XZ_EXTERN
+ #define XZ_EXTERN extern
+#endif
+
+/**
+ * enum xz_mode - Operation mode
+ *
+ * @XZ_SINGLE: Single-call mode. This uses less RAM than
+ * than multi-call modes, because the LZMA2
+ * dictionary doesn't need to be allocated as
+ * part of the decoder state. All required data
+ * structures are allocated at initialization,
+ * so xz_dec_run() cannot return XZ_MEM_ERROR.
+ * @XZ_PREALLOC: Multi-call mode with preallocated LZMA2
+ * dictionary buffer. All data structures are
+ * allocated at initialization, so xz_dec_run()
+ * cannot return XZ_MEM_ERROR.
+ * @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is
+ * allocated once the required size has been
+ * parsed from the stream headers. If the
+ * allocation fails, xz_dec_run() will return
+ * XZ_MEM_ERROR.
+ *
+ * It is possible to enable support only for a subset of the above
+ * modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC,
+ * or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled
+ * with support for all operation modes, but the preboot code may
+ * be built with fewer features to minimize code size.
+ */
+enum xz_mode {
+ XZ_SINGLE,
+ XZ_PREALLOC,
+ XZ_DYNALLOC
+};
+
+/**
+ * enum xz_ret - Return codes
+ * @XZ_OK: Everything is OK so far. More input or more
+ * output space is required to continue. This
+ * return code is possible only in multi-call mode
+ * (XZ_PREALLOC or XZ_DYNALLOC).
+ * @XZ_STREAM_END: Operation finished successfully.
+ * @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding
+ * is still possible in multi-call mode by simply
+ * calling xz_dec_run() again.
+ * Note that this return value is used only if
+ * XZ_DEC_ANY_CHECK was defined at build time,
+ * which is not used in the kernel. Unsupported
+ * check types return XZ_OPTIONS_ERROR if
+ * XZ_DEC_ANY_CHECK was not defined at build time.
+ * @XZ_MEM_ERROR: Allocating memory failed. This return code is
+ * possible only if the decoder was initialized
+ * with XZ_DYNALLOC. The amount of memory that was
+ * tried to be allocated was no more than the
+ * dict_max argument given to xz_dec_init().
+ * @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than
+ * allowed by the dict_max argument given to
+ * xz_dec_init(). This return value is possible
+ * only in multi-call mode (XZ_PREALLOC or
+ * XZ_DYNALLOC); the single-call mode (XZ_SINGLE)
+ * ignores the dict_max argument.
+ * @XZ_FORMAT_ERROR: File format was not recognized (wrong magic
+ * bytes).
+ * @XZ_OPTIONS_ERROR: This implementation doesn't support the requested
+ * compression options. In the decoder this means
+ * that the header CRC32 matches, but the header
+ * itself specifies something that we don't support.
+ * @XZ_DATA_ERROR: Compressed data is corrupt.
+ * @XZ_BUF_ERROR: Cannot make any progress. Details are slightly
+ * different between multi-call and single-call
+ * mode; more information below.
+ *
+ * In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls
+ * to XZ code cannot consume any input and cannot produce any new output.
+ * This happens when there is no new input available, or the output buffer
+ * is full while at least one output byte is still pending. Assuming your
+ * code is not buggy, you can get this error only when decoding a compressed
+ * stream that is truncated or otherwise corrupt.
+ *
+ * In single-call mode, XZ_BUF_ERROR is returned only when the output buffer
+ * is too small or the compressed input is corrupt in a way that makes the
+ * decoder produce more output than the caller expected. When it is
+ * (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR
+ * is used instead of XZ_BUF_ERROR.
+ */
+enum xz_ret {
+ XZ_OK,
+ XZ_STREAM_END,
+ XZ_UNSUPPORTED_CHECK,
+ XZ_MEM_ERROR,
+ XZ_MEMLIMIT_ERROR,
+ XZ_FORMAT_ERROR,
+ XZ_OPTIONS_ERROR,
+ XZ_DATA_ERROR,
+ XZ_BUF_ERROR
+};
+
+/**
+ * struct xz_buf - Passing input and output buffers to XZ code
+ * @in: Beginning of the input buffer. This may be NULL if and only
+ * if in_pos is equal to in_size.
+ * @in_pos: Current position in the input buffer. This must not exceed
+ * in_size.
+ * @in_size: Size of the input buffer
+ * @out: Beginning of the output buffer. This may be NULL if and only
+ * if out_pos is equal to out_size.
+ * @out_pos: Current position in the output buffer. This must not exceed
+ * out_size.
+ * @out_size: Size of the output buffer
+ *
+ * Only the contents of the output buffer from out[out_pos] onward, and
+ * the variables in_pos and out_pos are modified by the XZ code.
+ */
+struct xz_buf {
+ const uint8_t *in;
+ size_t in_pos;
+ size_t in_size;
+
+ uint8_t *out;
+ size_t out_pos;
+ size_t out_size;
+};
+
+/**
+ * struct xz_dec - Opaque type to hold the XZ decoder state
+ */
+struct xz_dec;
+
+/**
+ * xz_dec_init() - Allocate and initialize a XZ decoder state
+ * @mode: Operation mode
+ * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for
+ * multi-call decoding. This is ignored in single-call mode
+ * (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes
+ * or 2^n + 2^(n-1) bytes (the latter sizes are less common
+ * in practice), so other values for dict_max don't make sense.
+ * In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB,
+ * 512 KiB, and 1 MiB are probably the only reasonable values,
+ * except for kernel and initramfs images where a bigger
+ * dictionary can be fine and useful.
+ *
+ * Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at
+ * once. The caller must provide enough output space or the decoding will
+ * fail. The output space is used as the dictionary buffer, which is why
+ * there is no need to allocate the dictionary as part of the decoder's
+ * internal state.
+ *
+ * Because the output buffer is used as the workspace, streams encoded using
+ * a big dictionary are not a problem in single-call mode. It is enough that
+ * the output buffer is big enough to hold the actual uncompressed data; it
+ * can be smaller than the dictionary size stored in the stream headers.
+ *
+ * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes
+ * of memory is preallocated for the LZMA2 dictionary. This way there is no
+ * risk that xz_dec_run() could run out of memory, since xz_dec_run() will
+ * never allocate any memory. Instead, if the preallocated dictionary is too
+ * small for decoding the given input stream, xz_dec_run() will return
+ * XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be
+ * decoded to avoid allocating excessive amount of memory for the dictionary.
+ *
+ * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC):
+ * dict_max specifies the maximum allowed dictionary size that xz_dec_run()
+ * may allocate once it has parsed the dictionary size from the stream
+ * headers. This way excessive allocations can be avoided while still
+ * limiting the maximum memory usage to a sane value to prevent running the
+ * system out of memory when decompressing streams from untrusted sources.
+ *
+ * On success, xz_dec_init() returns a pointer to struct xz_dec, which is
+ * ready to be used with xz_dec_run(). If memory allocation fails,
+ * xz_dec_init() returns NULL.
+ */
+XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max);
+
+/**
+ * xz_dec_run() - Run the XZ decoder
+ * @s: Decoder state allocated using xz_dec_init()
+ * @b: Input and output buffers
+ *
+ * The possible return values depend on build options and operation mode.
+ * See enum xz_ret for details.
+ *
+ * Note that if an error occurs in single-call mode (return value is not
+ * XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the
+ * contents of the output buffer from b->out[b->out_pos] onward are
+ * undefined. This is true even after XZ_BUF_ERROR, because with some filter
+ * chains, there may be a second pass over the output buffer, and this pass
+ * cannot be properly done if the output buffer is truncated. Thus, you
+ * cannot give the single-call decoder a too small buffer and then expect to
+ * get that amount valid data from the beginning of the stream. You must use
+ * the multi-call decoder if you don't want to uncompress the whole stream.
+ */
+XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b);
+
+/**
+ * xz_dec_reset() - Reset an already allocated decoder state
+ * @s: Decoder state allocated using xz_dec_init()
+ *
+ * This function can be used to reset the multi-call decoder state without
+ * freeing and reallocating memory with xz_dec_end() and xz_dec_init().
+ *
+ * In single-call mode, xz_dec_reset() is always called in the beginning of
+ * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in
+ * multi-call mode.
+ */
+XZ_EXTERN void xz_dec_reset(struct xz_dec *s);
+
+/**
+ * xz_dec_end() - Free the memory allocated for the decoder state
+ * @s: Decoder state allocated using xz_dec_init(). If s is NULL,
+ * this function does nothing.
+ */
+XZ_EXTERN void xz_dec_end(struct xz_dec *s);
+
+/*
+ * Standalone build (userspace build or in-kernel build for boot time use)
+ * needs a CRC32 implementation. For normal in-kernel use, kernel's own
+ * CRC32 module is used instead, and users of this module don't need to
+ * care about the functions below.
+ */
+#ifndef XZ_INTERNAL_CRC32
+ #ifdef __KERNEL__
+ #define XZ_INTERNAL_CRC32 0
+ #else
+ #define XZ_INTERNAL_CRC32 1
+ #endif
+#endif
+
+/*
+ * If CRC64 support has been enabled with XZ_USE_CRC64, a CRC64
+ * implementation is needed too.
+ */
+#ifndef XZ_USE_CRC64
+ #undef XZ_INTERNAL_CRC64
+ #define XZ_INTERNAL_CRC64 0
+#endif
+#ifndef XZ_INTERNAL_CRC64
+ #ifdef __KERNEL__
+ #error Using CRC64 in the kernel has not been implemented.
+ #else
+ #define XZ_INTERNAL_CRC64 1
+ #endif
+#endif
+
+#if XZ_INTERNAL_CRC32
+/*
+ * This must be called before any other xz_* function to initialize
+ * the CRC32 lookup table.
+ */
+XZ_EXTERN void xz_crc32_init(void);
+
+/*
+ * Update CRC32 value using the polynomial from IEEE-802.3. To start a new
+ * calculation, the third argument must be zero. To continue the calculation,
+ * the previously returned value is passed as the third argument.
+ */
+XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc);
+#endif
+
+#if XZ_INTERNAL_CRC64
+/*
+ * This must be called before any other xz_* function (except xz_crc32_init())
+ * to initialize the CRC64 lookup table.
+ */
+XZ_EXTERN void xz_crc64_init(void);
+
+/*
+ * Update CRC64 value using the polynomial from ECMA-182. To start a new
+ * calculation, the third argument must be zero. To continue the calculation,
+ * the previously returned value is passed as the third argument.
+ */
+XZ_EXTERN uint64_t xz_crc64(const uint8_t *buf, size_t size, uint64_t crc);
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/libxz/xz_config.h b/libxz/xz_config.h
new file mode 100644
index 000000000000..a380be02c143
--- /dev/null
+++ b/libxz/xz_config.h
@@ -0,0 +1,124 @@
+/*
+ * Private includes and definitions for userspace use of XZ Embedded
+ *
+ * Author: Lasse Collin <lasse.collin@tukaani.org>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_CONFIG_H
+#define XZ_CONFIG_H
+
+/* Uncomment to enable CRC64 support. */
+/* #define XZ_USE_CRC64 */
+
+/* Uncomment as needed to enable BCJ filter decoders. */
+/* #define XZ_DEC_X86 */
+/* #define XZ_DEC_POWERPC */
+/* #define XZ_DEC_IA64 */
+/* #define XZ_DEC_ARM */
+/* #define XZ_DEC_ARMTHUMB */
+/* #define XZ_DEC_SPARC */
+
+/*
+ * MSVC doesn't support modern C but XZ Embedded is mostly C89
+ * so these are enough.
+ */
+#ifdef _MSC_VER
+typedef unsigned char bool;
+ #define true 1
+ #define false 0
+ #define inline __inline
+#else
+ #include <stdbool.h>
+#endif
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "xz.h"
+
+#define kmalloc(size, flags) malloc(size)
+#define kfree(ptr) free(ptr)
+#define vmalloc(size) malloc(size)
+#define vfree(ptr) free(ptr)
+
+#define memeq(a, b, size) (memcmp(a, b, size) == 0)
+#define memzero(buf, size) memset(buf, 0, size)
+
+#ifndef min
+ #define min(x, y) ((x) < (y) ? (x) : (y))
+#endif
+#define min_t(type, x, y) min(x, y)
+
+/*
+ * Some functions have been marked with __always_inline to keep the
+ * performance reasonable even when the compiler is optimizing for
+ * small code size. You may be able to save a few bytes by #defining
+ * __always_inline to plain inline, but don't complain if the code
+ * becomes slow.
+ *
+ * NOTE: System headers on GNU/Linux may #define this macro already,
+ * so if you want to change it, you need to #undef it first.
+ */
+#ifndef __always_inline
+ #ifdef __GNUC__
+ #define __always_inline \
+ inline __attribute__((__always_inline__))
+ #else
+ #define __always_inline inline
+ #endif
+#endif
+
+/* Inline functions to access unaligned unsigned 32-bit integers */
+#ifndef get_unaligned_le32
+static inline uint32_t get_unaligned_le32(const uint8_t *buf)
+{
+ return (uint32_t)buf[0]
+ | ((uint32_t)buf[1] << 8)
+ | ((uint32_t)buf[2] << 16)
+ | ((uint32_t)buf[3] << 24);
+}
+#endif
+
+#ifndef get_unaligned_be32
+static inline uint32_t get_unaligned_be32(const uint8_t *buf)
+{
+ return (uint32_t)(buf[0] << 24)
+ | ((uint32_t)buf[1] << 16)
+ | ((uint32_t)buf[2] << 8)
+ | (uint32_t)buf[3];
+}
+#endif
+
+#ifndef put_unaligned_le32
+static inline void put_unaligned_le32(uint32_t val, uint8_t *buf)
+{
+ buf[0] = (uint8_t)val;
+ buf[1] = (uint8_t)(val >> 8);
+ buf[2] = (uint8_t)(val >> 16);
+ buf[3] = (uint8_t)(val >> 24);
+}
+#endif
+
+#ifndef put_unaligned_be32
+static inline void put_unaligned_be32(uint32_t val, uint8_t *buf)
+{
+ buf[0] = (uint8_t)(val >> 24);
+ buf[1] = (uint8_t)(val >> 16);
+ buf[2] = (uint8_t)(val >> 8);
+ buf[3] = (uint8_t)val;
+}
+#endif
+
+/*
+ * Use get_unaligned_le32() also for aligned access for simplicity. On
+ * little endian systems, #define get_le32(ptr) (*(const uint32_t *)(ptr))
+ * could save a few bytes in code size.
+ */
+#ifndef get_le32
+ #define get_le32 get_unaligned_le32
+#endif
+
+#endif
diff --git a/libxz/xz_lzma2.h b/libxz/xz_lzma2.h
new file mode 100644
index 000000000000..aa05d956319e
--- /dev/null
+++ b/libxz/xz_lzma2.h
@@ -0,0 +1,204 @@
+/*
+ * LZMA2 definitions
+ *
+ * Authors: Lasse Collin <lasse.collin@tukaani.org>
+ * Igor Pavlov <http://7-zip.org/>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_LZMA2_H
+#define XZ_LZMA2_H
+
+/* Range coder constants */
+#define RC_SHIFT_BITS 8
+#define RC_TOP_BITS 24
+#define RC_TOP_VALUE (1 << RC_TOP_BITS)
+#define RC_BIT_MODEL_TOTAL_BITS 11
+#define RC_BIT_MODEL_TOTAL (1 << RC_BIT_MODEL_TOTAL_BITS)
+#define RC_MOVE_BITS 5
+
+/*
+ * Maximum number of position states. A position state is the lowest pb
+ * number of bits of the current uncompressed offset. In some places there
+ * are different sets of probabilities for different position states.
+ */
+#define POS_STATES_MAX (1 << 4)
+
+/*
+ * This enum is used to track which LZMA symbols have occurred most recently
+ * and in which order. This information is used to predict the next symbol.
+ *
+ * Symbols:
+ * - Literal: One 8-bit byte
+ * - Match: Repeat a chunk of data at some distance
+ * - Long repeat: Multi-byte match at a recently seen distance
+ * - Short repeat: One-byte repeat at a recently seen distance
+ *
+ * The symbol names are in from STATE_oldest_older_previous. REP means
+ * either short or long repeated match, and NONLIT means any non-literal.
+ */
+enum lzma_state {
+ STATE_LIT_LIT,
+ STATE_MATCH_LIT_LIT,
+ STATE_REP_LIT_LIT,
+ STATE_SHORTREP_LIT_LIT,
+ STATE_MATCH_LIT,
+ STATE_REP_LIT,
+ STATE_SHORTREP_LIT,
+ STATE_LIT_MATCH,
+ STATE_LIT_LONGREP,
+ STATE_LIT_SHORTREP,
+ STATE_NONLIT_MATCH,
+ STATE_NONLIT_REP
+};
+
+/* Total number of states */
+#define STATES 12
+
+/* The lowest 7 states indicate that the previous state was a literal. */
+#define LIT_STATES 7
+
+/* Indicate that the latest symbol was a literal. */
+static inline void lzma_state_literal(enum lzma_state *state)
+{
+ if (*state <= STATE_SHORTREP_LIT_LIT)
+ *state = STATE_LIT_LIT;
+ else if (*state <= STATE_LIT_SHORTREP)
+ *state -= 3;
+ else
+ *state -= 6;
+}
+
+/* Indicate that the latest symbol was a match. */
+static inline void lzma_state_match(enum lzma_state *state)
+{
+ *state = *state < LIT_STATES ? STATE_LIT_MATCH : STATE_NONLIT_MATCH;
+}
+
+/* Indicate that the latest state was a long repeated match. */
+static inline void lzma_state_long_rep(enum lzma_state *state)
+{
+ *state = *state < LIT_STATES ? STATE_LIT_LONGREP : STATE_NONLIT_REP;
+}
+
+/* Indicate that the latest symbol was a short match. */
+static inline void lzma_state_short_rep(enum lzma_state *state)
+{
+ *state = *state < LIT_STATES ? STATE_LIT_SHORTREP : STATE_NONLIT_REP;
+}
+
+/* Test if the previous symbol was a literal. */
+static inline bool lzma_state_is_literal(enum lzma_state state)
+{
+ return state < LIT_STATES;
+}
+
+/* Each literal coder is divided in three sections:
+ * - 0x001-0x0FF: Without match byte
+ * - 0x101-0x1FF: With match byte; match bit is 0
+ * - 0x201-0x2FF: With match byte; match bit is 1
+ *
+ * Match byte is used when the previous LZMA symbol was something else than
+ * a literal (that is, it was some kind of match).
+ */
+#define LITERAL_CODER_SIZE 0x300
+
+/* Maximum number of literal coders */
+#define LITERAL_CODERS_MAX (1 << 4)
+
+/* Minimum length of a match is two bytes. */
+#define MATCH_LEN_MIN 2
+
+/* Match length is encoded with 4, 5, or 10 bits.
+ *
+ * Length Bits
+ * 2-9 4 = Choice=0 + 3 bits
+ * 10-17 5 = Choice=1 + Choice2=0 + 3 bits
+ * 18-273 10 = Choice=1 + Choice2=1 + 8 bits
+ */
+#define LEN_LOW_BITS 3
+#define LEN_LOW_SYMBOLS (1 << LEN_LOW_BITS)
+#define LEN_MID_BITS 3
+#define LEN_MID_SYMBOLS (1 << LEN_MID_BITS)
+#define LEN_HIGH_BITS 8
+#define LEN_HIGH_SYMBOLS (1 << LEN_HIGH_BITS)
+#define LEN_SYMBOLS (LEN_LOW_SYMBOLS + LEN_MID_SYMBOLS + LEN_HIGH_SYMBOLS)
+
+/*
+ * Maximum length of a match is 273 which is a result of the encoding
+ * described above.
+ */
+#define MATCH_LEN_MAX (MATCH_LEN_MIN + LEN_SYMBOLS - 1)
+
+/*
+ * Different sets of probabilities are used for match distances that have
+ * very short match length: Lengths of 2, 3, and 4 bytes have a separate
+ * set of probabilities for each length. The matches with longer length
+ * use a shared set of probabilities.
+ */
+#define DIST_STATES 4
+
+/*
+ * Get the index of the appropriate probability array for decoding
+ * the distance slot.
+ */
+static inline uint32_t lzma_get_dist_state(uint32_t len)
+{
+ return len < DIST_STATES + MATCH_LEN_MIN
+ ? len - MATCH_LEN_MIN : DIST_STATES - 1;
+}
+
+/*
+ * The highest two bits of a 32-bit match distance are encoded using six bits.
+ * This six-bit value is called a distance slot. This way encoding a 32-bit
+ * value takes 6-36 bits, larger values taking more bits.
+ */
+#define DIST_SLOT_BITS 6
+#define DIST_SLOTS (1 << DIST_SLOT_BITS)
+
+/* Match distances up to 127 are fully encoded using probabilities. Since
+ * the highest two bits (distance slot) are always encoded using six bits,
+ * the distances 0-3 don't need any additional bits to encode, since the
+ * distance slot itself is the same as the actual distance. DIST_MODEL_START
+ * indicates the first distance slot where at least one additional bit is
+ * needed.
+ */
+#define DIST_MODEL_START 4
+
+/*
+ * Match distances greater than 127 are encoded in three pieces:
+ * - distance slot: the highest two bits
+ * - direct bits: 2-26 bits below the highest two bits
+ * - alignment bits: four lowest bits
+ *
+ * Direct bits don't use any probabilities.
+ *
+ * The distance slot value of 14 is for distances 128-191.
+ */
+#define DIST_MODEL_END 14
+
+/* Distance slots that indicate a distance <= 127. */
+#define FULL_DISTANCES_BITS (DIST_MODEL_END / 2)
+#define FULL_DISTANCES (1 << FULL_DISTANCES_BITS)
+
+/*
+ * For match distances greater than 127, only the highest two bits and the
+ * lowest four bits (alignment) is encoded using probabilities.
+ */
+#define ALIGN_BITS 4
+#define ALIGN_SIZE (1 << ALIGN_BITS)
+#define ALIGN_MASK (ALIGN_SIZE - 1)
+
+/* Total number of all probability variables */
+#define PROBS_TOTAL (1846 + LITERAL_CODERS_MAX * LITERAL_CODER_SIZE)
+
+/*
+ * LZMA remembers the four most recent match distances. Reusing these
+ * distances tends to take less space than re-encoding the actual
+ * distance value.
+ */
+#define REPS 4
+
+#endif
diff --git a/libxz/xz_private.h b/libxz/xz_private.h
new file mode 100644
index 000000000000..49c366554086
--- /dev/null
+++ b/libxz/xz_private.h
@@ -0,0 +1,156 @@
+/*
+ * Private includes and definitions
+ *
+ * Author: Lasse Collin <lasse.collin@tukaani.org>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_PRIVATE_H
+#define XZ_PRIVATE_H
+
+#ifdef __KERNEL__
+ #include <linux/xz.h>
+ #include <linux/kernel.h>
+ #include <asm/unaligned.h>
+ /* XZ_PREBOOT may be defined only via decompress_unxz.c. */
+ #ifndef XZ_PREBOOT
+ #include <linux/slab.h>
+ #include <linux/vmalloc.h>
+ #include <linux/string.h>
+ #ifdef CONFIG_XZ_DEC_X86
+ #define XZ_DEC_X86
+ #endif
+ #ifdef CONFIG_XZ_DEC_POWERPC
+ #define XZ_DEC_POWERPC
+ #endif
+ #ifdef CONFIG_XZ_DEC_IA64
+ #define XZ_DEC_IA64
+ #endif
+ #ifdef CONFIG_XZ_DEC_ARM
+ #define XZ_DEC_ARM
+ #endif
+ #ifdef CONFIG_XZ_DEC_ARMTHUMB
+ #define XZ_DEC_ARMTHUMB
+ #endif
+ #ifdef CONFIG_XZ_DEC_SPARC
+ #define XZ_DEC_SPARC
+ #endif
+ #define memeq(a, b, size) (memcmp(a, b, size) == 0)
+ #define memzero(buf, size) memset(buf, 0, size)
+ #endif
+ #define get_le32(p) le32_to_cpup((const uint32_t *)(p))
+#else
+ /*
+ * For userspace builds, use a separate header to define the required
+ * macros and functions. This makes it easier to adapt the code into
+ * different environments and avoids clutter in the Linux kernel tree.
+ */
+ #include "xz_config.h"
+#endif
+
+/* If no specific decoding mode is requested, enable support for all modes. */
+#if !defined(XZ_DEC_SINGLE) && !defined(XZ_DEC_PREALLOC) \
+ && !defined(XZ_DEC_DYNALLOC)
+ #define XZ_DEC_SINGLE
+ #define XZ_DEC_PREALLOC
+ #define XZ_DEC_DYNALLOC
+#endif
+
+/*
+ * The DEC_IS_foo(mode) macros are used in "if" statements. If only some
+ * of the supported modes are enabled, these macros will evaluate to true or
+ * false at compile time and thus allow the compiler to omit unneeded code.
+ */
+#ifdef XZ_DEC_SINGLE
+ #define DEC_IS_SINGLE(mode) ((mode) == XZ_SINGLE)
+#else
+ #define DEC_IS_SINGLE(mode) (false)
+#endif
+
+#ifdef XZ_DEC_PREALLOC
+ #define DEC_IS_PREALLOC(mode) ((mode) == XZ_PREALLOC)
+#else
+ #define DEC_IS_PREALLOC(mode) (false)
+#endif
+
+#ifdef XZ_DEC_DYNALLOC
+ #define DEC_IS_DYNALLOC(mode) ((mode) == XZ_DYNALLOC)
+#else
+ #define DEC_IS_DYNALLOC(mode) (false)
+#endif
+
+#if !defined(XZ_DEC_SINGLE)
+ #define DEC_IS_MULTI(mode) (true)
+#elif defined(XZ_DEC_PREALLOC) || defined(XZ_DEC_DYNALLOC)
+ #define DEC_IS_MULTI(mode) ((mode) != XZ_SINGLE)
+#else
+ #define DEC_IS_MULTI(mode) (false)
+#endif
+
+/*
+ * If any of the BCJ filter decoders are wanted, define XZ_DEC_BCJ.
+ * XZ_DEC_BCJ is used to enable generic support for BCJ decoders.
+ */
+#ifndef XZ_DEC_BCJ
+ #if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \
+ || defined(XZ_DEC_IA64) || defined(XZ_DEC_ARM) \
+ || defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \
+ || defined(XZ_DEC_SPARC)
+ #define XZ_DEC_BCJ
+ #endif
+#endif
+
+/*
+ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
+ * before calling xz_dec_lzma2_run().
+ */
+XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode,
+ uint32_t dict_max);
+
+/*
+ * Decode the LZMA2 properties (one byte) and reset the decoder. Return
+ * XZ_OK on success, XZ_MEMLIMIT_ERROR if the preallocated dictionary is not
+ * big enough, and XZ_OPTIONS_ERROR if props indicates something that this
+ * decoder doesn't support.
+ */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s,
+ uint8_t props);
+
+/* Decode raw LZMA2 stream from b->in to b->out. */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
+ struct xz_buf *b);
+
+/* Free the memory allocated for the LZMA2 decoder. */
+XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s);
+
+#ifdef XZ_DEC_BCJ
+/*
+ * Allocate memory for BCJ decoders. xz_dec_bcj_reset() must be used before
+ * calling xz_dec_bcj_run().
+ */
+XZ_EXTERN struct xz_dec_bcj *xz_dec_bcj_create(bool single_call);
+
+/*
+ * Decode the Filter ID of a BCJ filter. This implementation doesn't
+ * support custom start offsets, so no decoding of Filter Properties
+ * is needed. Returns XZ_OK if the given Filter ID is supported.
+ * Otherwise XZ_OPTIONS_ERROR is returned.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id);
+
+/*
+ * Decode raw BCJ + LZMA2 stream. This must be used only if there actually is
+ * a BCJ filter in the chain. If the chain has only LZMA2, xz_dec_lzma2_run()
+ * must be called directly.
+ */
+XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
+ struct xz_dec_lzma2 *lzma2,
+ struct xz_buf *b);
+
+/* Free the memory allocated for the BCJ filters. */
+#define xz_dec_bcj_end(s) kfree(s)
+#endif
+
+#endif
diff --git a/libxz/xz_stream.h b/libxz/xz_stream.h
new file mode 100644
index 000000000000..54fda5389497
--- /dev/null
+++ b/libxz/xz_stream.h
@@ -0,0 +1,62 @@
+/*
+ * Definitions for handling the .xz file format
+ *
+ * Author: Lasse Collin <lasse.collin@tukaani.org>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#ifndef XZ_STREAM_H
+#define XZ_STREAM_H
+
+#if defined(__KERNEL__) && !XZ_INTERNAL_CRC32
+ #include <linux/crc32.h>
+ #undef crc32
+ #define xz_crc32(buf, size, crc) \
+ (~crc32_le(~(uint32_t)(crc), buf, size))
+#endif
+
+/*
+ * See the .xz file format specification at
+ * http://tukaani.org/xz/xz-file-format.txt
+ * to understand the container format.
+ */
+
+#define STREAM_HEADER_SIZE 12
+
+#define HEADER_MAGIC "\3757zXZ"
+#define HEADER_MAGIC_SIZE 6
+
+#define FOOTER_MAGIC "YZ"
+#define FOOTER_MAGIC_SIZE 2
+
+/*
+ * Variable-length integer can hold a 63-bit unsigned integer or a special
+ * value indicating that the value is unknown.
+ *
+ * Experimental: vli_type can be defined to uint32_t to save a few bytes
+ * in code size (no effect on speed). Doing so limits the uncompressed and
+ * compressed size of the file to less than 256 MiB and may also weaken
+ * error detection slightly.
+ */
+typedef uint64_t vli_type;
+
+#define VLI_MAX ((vli_type)-1 / 2)
+#define VLI_UNKNOWN ((vli_type)-1)
+
+/* Maximum encoded size of a VLI */
+#define VLI_BYTES_MAX (sizeof(vli_type) * 8 / 7)
+
+/* Integrity Check types */
+enum xz_check {
+ XZ_CHECK_NONE = 0,
+ XZ_CHECK_CRC32 = 1,
+ XZ_CHECK_CRC64 = 4,
+ XZ_CHECK_SHA256 = 10
+};
+
+/* Maximum possible Check ID */
+#define XZ_CHECK_MAX 15
+
+#endif
diff --git a/libxz/xz_crc32.c b/libxz/xz_crc32.c
new file mode 100644
index 000000000000..34532d14fd4c
--- /dev/null
+++ b/libxz/xz_crc32.c
@@ -0,0 +1,59 @@
+/*
+ * CRC32 using the polynomial from IEEE-802.3
+ *
+ * Authors: Lasse Collin <lasse.collin@tukaani.org>
+ * Igor Pavlov <http://7-zip.org/>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+/*
+ * This is not the fastest implementation, but it is pretty compact.
+ * The fastest versions of xz_crc32() on modern CPUs without hardware
+ * accelerated CRC instruction are 3-5 times as fast as this version,
+ * but they are bigger and use more memory for the lookup table.
+ */
+
+#include "xz_private.h"
+
+/*
+ * STATIC_RW_DATA is used in the pre-boot environment on some architectures.
+ * See <linux/decompress/mm.h> for details.
+ */
+#ifndef STATIC_RW_DATA
+# define STATIC_RW_DATA static
+#endif
+
+STATIC_RW_DATA uint32_t xz_crc32_table[256];
+
+XZ_EXTERN void xz_crc32_init(void)
+{
+ const uint32_t poly = 0xEDB88320;
+
+ uint32_t i;
+ uint32_t j;
+ uint32_t r;
+
+ for (i = 0; i < 256; ++i) {
+ r = i;
+ for (j = 0; j < 8; ++j)
+ r = (r >> 1) ^ (poly & ~((r & 1) - 1));
+
+ xz_crc32_table[i] = r;
+ }
+
+ return;
+}
+
+XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc)
+{
+ crc = ~crc;
+
+ while (size != 0) {
+ crc = xz_crc32_table[*buf++ ^ (crc & 0xFF)] ^ (crc >> 8);
+ --size;
+ }
+
+ return ~crc;
+}
diff --git a/libxz/xz_dec_lzma2.c b/libxz/xz_dec_lzma2.c
new file mode 100644
index 000000000000..e9fb006c87fe
--- /dev/null
+++ b/libxz/xz_dec_lzma2.c
@@ -0,0 +1,1171 @@
+/*
+ * LZMA2 decoder
+ *
+ * Authors: Lasse Collin <lasse.collin@tukaani.org>
+ * Igor Pavlov <http://7-zip.org/>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#include "xz_private.h"
+#include "xz_lzma2.h"
+
+/*
+ * Range decoder initialization eats the first five bytes of each LZMA chunk.
+ */
+#define RC_INIT_BYTES 5
+
+/*
+ * Minimum number of usable input buffer to safely decode one LZMA symbol.
+ * The worst case is that we decode 22 bits using probabilities and 26
+ * direct bits. This may decode at maximum of 20 bytes of input. However,
+ * lzma_main() does an extra normalization before returning, thus we
+ * need to put 21 here.
+ */
+#define LZMA_IN_REQUIRED 21
+
+/*
+ * Dictionary (history buffer)
+ *
+ * These are always true:
+ * start <= pos <= full <= end
+ * pos <= limit <= end
+ *
+ * In multi-call mode, also these are true:
+ * end == size
+ * size <= size_max
+ * allocated <= size
+ *
+ * Most of these variables are size_t to support single-call mode,
+ * in which the dictionary variables address the actual output
+ * buffer directly.
+ */
+struct dictionary {
+ /* Beginning of the history buffer */
+ uint8_t *buf;
+
+ /* Old position in buf (before decoding more data) */
+ size_t start;
+
+ /* Position in buf */
+ size_t pos;
+
+ /*
+ * How full dictionary is. This is used to detect corrupt input that
+ * would read beyond the beginning of the uncompressed stream.
+ */
+ size_t full;
+
+ /* Write limit; we don't write to buf[limit] or later bytes. */
+ size_t limit;
+
+ /*
+ * End of the dictionary buffer. In multi-call mode, this is
+ * the same as the dictionary size. In single-call mode, this
+ * indicates the size of the output buffer.
+ */
+ size_t end;
+
+ /*
+ * Size of the dictionary as specified in Block Header. This is used
+ * together with "full" to detect corrupt input that would make us
+ * read beyond the beginning of the uncompressed stream.
+ */
+ uint32_t size;
+
+ /*
+ * Maximum allowed dictionary size in multi-call mode.
+ * This is ignored in single-call mode.
+ */
+ uint32_t size_max;
+
+ /*
+ * Amount of memory currently allocated for the dictionary.
+ * This is used only with XZ_DYNALLOC. (With XZ_PREALLOC,
+ * size_max is always the same as the allocated size.)
+ */
+ uint32_t allocated;
+
+ /* Operation mode */
+ enum xz_mode mode;
+};
+
+/* Range decoder */
+struct rc_dec {
+ uint32_t range;
+ uint32_t code;
+
+ /*
+ * Number of initializing bytes remaining to be read
+ * by rc_read_init().
+ */
+ uint32_t init_bytes_left;
+
+ /*
+ * Buffer from which we read our input. It can be either
+ * temp.buf or the caller-provided input buffer.
+ */
+ const uint8_t *in;
+ size_t in_pos;
+ size_t in_limit;
+};
+
+/* Probabilities for a length decoder. */
+struct lzma_len_dec {
+ /* Probability of match length being at least 10 */
+ uint16_t choice;
+
+ /* Probability of match length being at least 18 */
+ uint16_t choice2;
+
+ /* Probabilities for match lengths 2-9 */
+ uint16_t low[POS_STATES_MAX][LEN_LOW_SYMBOLS];
+
+ /* Probabilities for match lengths 10-17 */
+ uint16_t mid[POS_STATES_MAX][LEN_MID_SYMBOLS];
+
+ /* Probabilities for match lengths 18-273 */
+ uint16_t high[LEN_HIGH_SYMBOLS];
+};
+
+struct lzma_dec {
+ /* Distances of latest four matches */
+ uint32_t rep0;
+ uint32_t rep1;
+ uint32_t rep2;
+ uint32_t rep3;
+
+ /* Types of the most recently seen LZMA symbols */
+ enum lzma_state state;
+
+ /*
+ * Length of a match. This is updated so that dict_repeat can
+ * be called again to finish repeating the whole match.
+ */
+ uint32_t len;
+
+ /*
+ * LZMA properties or related bit masks (number of literal
+ * context bits, a mask dervied from the number of literal
+ * position bits, and a mask dervied from the number
+ * position bits)
+ */
+ uint32_t lc;
+ uint32_t literal_pos_mask; /* (1 << lp) - 1 */
+ uint32_t pos_mask; /* (1 << pb) - 1 */
+
+ /* If 1, it's a match. Otherwise it's a single 8-bit literal. */
+ uint16_t is_match[STATES][POS_STATES_MAX];
+
+ /* If 1, it's a repeated match. The distance is one of rep0 .. rep3. */
+ uint16_t is_rep[STATES];
+
+ /*
+ * If 0, distance of a repeated match is rep0.
+ * Otherwise check is_rep1.
+ */
+ uint16_t is_rep0[STATES];
+
+ /*
+ * If 0, distance of a repeated match is rep1.
+ * Otherwise check is_rep2.
+ */
+ uint16_t is_rep1[STATES];
+
+ /* If 0, distance of a repeated match is rep2. Otherwise it is rep3. */
+ uint16_t is_rep2[STATES];
+
+ /*
+ * If 1, the repeated match has length of one byte. Otherwise
+ * the length is decoded from rep_len_decoder.
+ */
+ uint16_t is_rep0_long[STATES][POS_STATES_MAX];
+
+ /*
+ * Probability tree for the highest two bits of the match
+ * distance. There is a separate probability tree for match
+ * lengths of 2 (i.e. MATCH_LEN_MIN), 3, 4, and [5, 273].
+ */
+ uint16_t dist_slot[DIST_STATES][DIST_SLOTS];
+
+ /*
+ * Probility trees for additional bits for match distance
+ * when the distance is in the range [4, 127].
+ */
+ uint16_t dist_special[FULL_DISTANCES - DIST_MODEL_END];
+
+ /*
+ * Probability tree for the lowest four bits of a match
+ * distance that is equal to or greater than 128.
+ */
+ uint16_t dist_align[ALIGN_SIZE];
+
+ /* Length of a normal match */
+ struct lzma_len_dec match_len_dec;
+
+ /* Length of a repeated match */
+ struct lzma_len_dec rep_len_dec;
+
+ /* Probabilities of literals */
+ uint16_t literal[LITERAL_CODERS_MAX][LITERAL_CODER_SIZE];
+};
+
+struct lzma2_dec {
+ /* Position in xz_dec_lzma2_run(). */
+ enum lzma2_seq {
+ SEQ_CONTROL,
+ SEQ_UNCOMPRESSED_1,
+ SEQ_UNCOMPRESSED_2,
+ SEQ_COMPRESSED_0,
+ SEQ_COMPRESSED_1,
+ SEQ_PROPERTIES,
+ SEQ_LZMA_PREPARE,
+ SEQ_LZMA_RUN,
+ SEQ_COPY
+ } sequence;
+
+ /* Next position after decoding the compressed size of the chunk. */
+ enum lzma2_seq next_sequence;
+
+ /* Uncompressed size of LZMA chunk (2 MiB at maximum) */
+ uint32_t uncompressed;
+
+ /*
+ * Compressed size of LZMA chunk or compressed/uncompressed
+ * size of uncompressed chunk (64 KiB at maximum)
+ */
+ uint32_t compressed;
+
+ /*
+ * True if dictionary reset is needed. This is false before
+ * the first chunk (LZMA or uncompressed).
+ */
+ bool need_dict_reset;
+
+ /*
+ * True if new LZMA properties are needed. This is false
+ * before the first LZMA chunk.
+ */
+ bool need_props;
+};
+
+struct xz_dec_lzma2 {
+ /*
+ * The order below is important on x86 to reduce code size and
+ * it shouldn't hurt on other platforms. Everything up to and
+ * including lzma.pos_mask are in the first 128 bytes on x86-32,
+ * which allows using smaller instructions to access those
+ * variables. On x86-64, fewer variables fit into the first 128
+ * bytes, but this is still the best order without sacrificing
+ * the readability by splitting the structures.
+ */
+ struct rc_dec rc;
+ struct dictionary dict;
+ struct lzma2_dec lzma2;
+ struct lzma_dec lzma;
+
+ /*
+ * Temporary buffer which holds small number of input bytes between
+ * decoder calls. See lzma2_lzma() for details.
+ */
+ struct {
+ uint32_t size;
+ uint8_t buf[3 * LZMA_IN_REQUIRED];
+ } temp;
+};
+
+/**************
+ * Dictionary *
+ **************/
+
+/*
+ * Reset the dictionary state. When in single-call mode, set up the beginning
+ * of the dictionary to point to the actual output buffer.
+ */
+static void dict_reset(struct dictionary *dict, struct xz_buf *b)
+{
+ if (DEC_IS_SINGLE(dict->mode)) {
+ dict->buf = b->out + b->out_pos;
+ dict->end = b->out_size - b->out_pos;
+ }
+
+ dict->start = 0;
+ dict->pos = 0;
+ dict->limit = 0;
+ dict->full = 0;
+}
+
+/* Set dictionary write limit */
+static void dict_limit(struct dictionary *dict, size_t out_max)
+{
+ if (dict->end - dict->pos <= out_max)
+ dict->limit = dict->end;
+ else
+ dict->limit = dict->pos + out_max;
+}
+
+/* Return true if at least one byte can be written into the dictionary. */
+static inline bool dict_has_space(const struct dictionary *dict)
+{
+ return dict->pos < dict->limit;
+}
+
+/*
+ * Get a byte from the dictionary at the given distance. The distance is
+ * assumed to valid, or as a special case, zero when the dictionary is
+ * still empty. This special case is needed for single-call decoding to
+ * avoid writing a '\0' to the end of the destination buffer.
+ */
+static inline uint32_t dict_get(const struct dictionary *dict, uint32_t dist)
+{
+ size_t offset = dict->pos - dist - 1;
+
+ if (dist >= dict->pos)
+ offset += dict->end;
+
+ return dict->full > 0 ? dict->buf[offset] : 0;
+}
+
+/*
+ * Put one byte into the dictionary. It is assumed that there is space for it.
+ */
+static inline void dict_put(struct dictionary *dict, uint8_t byte)
+{
+ dict->buf[dict->pos++] = byte;
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+}
+
+/*
+ * Repeat given number of bytes from the given distance. If the distance is
+ * invalid, false is returned. On success, true is returned and *len is
+ * updated to indicate how many bytes were left to be repeated.
+ */
+static bool dict_repeat(struct dictionary *dict, uint32_t *len, uint32_t dist)
+{
+ size_t back;
+ uint32_t left;
+
+ if (dist >= dict->full || dist >= dict->size)
+ return false;
+
+ left = min_t(size_t, dict->limit - dict->pos, *len);
+ *len -= left;
+
+ back = dict->pos - dist - 1;
+ if (dist >= dict->pos)
+ back += dict->end;
+
+ do {
+ dict->buf[dict->pos++] = dict->buf[back++];
+ if (back == dict->end)
+ back = 0;
+ } while (--left > 0);
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+
+ return true;
+}
+
+/* Copy uncompressed data as is from input to dictionary and output buffers. */
+static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b,
+ uint32_t *left)
+{
+ size_t copy_size;
+
+ while (*left > 0 && b->in_pos < b->in_size
+ && b->out_pos < b->out_size) {
+ copy_size = min(b->in_size - b->in_pos,
+ b->out_size - b->out_pos);
+ if (copy_size > dict->end - dict->pos)
+ copy_size = dict->end - dict->pos;
+ if (copy_size > *left)
+ copy_size = *left;
+
+ *left -= copy_size;
+
+ memcpy(dict->buf + dict->pos, b->in + b->in_pos, copy_size);
+ dict->pos += copy_size;
+
+ if (dict->full < dict->pos)
+ dict->full = dict->pos;
+
+ if (DEC_IS_MULTI(dict->mode)) {
+ if (dict->pos == dict->end)
+ dict->pos = 0;
+
+ memcpy(b->out + b->out_pos, b->in + b->in_pos,
+ copy_size);
+ }
+
+ dict->start = dict->pos;
+
+ b->out_pos += copy_size;
+ b->in_pos += copy_size;
+ }
+}
+
+/*
+ * Flush pending data from dictionary to b->out. It is assumed that there is
+ * enough space in b->out. This is guaranteed because caller uses dict_limit()
+ * before decoding data into the dictionary.
+ */
+static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b)
+{
+ size_t copy_size = dict->pos - dict->start;
+
+ if (DEC_IS_MULTI(dict->mode)) {
+ if (dict->pos == dict->end)
+ dict->pos = 0;
+
+ memcpy(b->out + b->out_pos, dict->buf + dict->start,
+ copy_size);
+ }
+
+ dict->start = dict->pos;
+ b->out_pos += copy_size;
+ return copy_size;
+}
+
+/*****************
+ * Range decoder *
+ *****************/
+
+/* Reset the range decoder. */
+static void rc_reset(struct rc_dec *rc)
+{
+ rc->range = (uint32_t)-1;
+ rc->code = 0;
+ rc->init_bytes_left = RC_INIT_BYTES;
+}
+
+/*
+ * Read the first five initial bytes into rc->code if they haven't been
+ * read already. (Yes, the first byte gets completely ignored.)
+ */
+static bool rc_read_init(struct rc_dec *rc, struct xz_buf *b)
+{
+ while (rc->init_bytes_left > 0) {
+ if (b->in_pos == b->in_size)
+ return false;
+
+ rc->code = (rc->code << 8) + b->in[b->in_pos++];
+ --rc->init_bytes_left;
+ }
+
+ return true;
+}
+
+/* Return true if there may not be enough input for the next decoding loop. */
+static inline bool rc_limit_exceeded(const struct rc_dec *rc)
+{
+ return rc->in_pos > rc->in_limit;
+}
+
+/*
+ * Return true if it is possible (from point of view of range decoder) that
+ * we have reached the end of the LZMA chunk.
+ */
+static inline bool rc_is_finished(const struct rc_dec *rc)
+{
+ return rc->code == 0;
+}
+
+/* Read the next input byte if needed. */
+static __always_inline void rc_normalize(struct rc_dec *rc)
+{
+ if (rc->range < RC_TOP_VALUE) {
+ rc->range <<= RC_SHIFT_BITS;
+ rc->code = (rc->code << RC_SHIFT_BITS) + rc->in[rc->in_pos++];
+ }
+}
+
+/*
+ * Decode one bit. In some versions, this function has been splitted in three
+ * functions so that the compiler is supposed to be able to more easily avoid
+ * an extra branch. In this particular version of the LZMA decoder, this
+ * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3
+ * on x86). Using a non-splitted version results in nicer looking code too.
+ *
+ * NOTE: This must return an int. Do not make it return a bool or the speed
+ * of the code generated by GCC 3.x decreases 10-15 %. (GCC 4.3 doesn't care,
+ * and it generates 10-20 % faster code than GCC 3.x from this file anyway.)
+ */
+static __always_inline int rc_bit(struct rc_dec *rc, uint16_t *prob)
+{
+ uint32_t bound;
+ int bit;
+
+ rc_normalize(rc);
+ bound = (rc->range >> RC_BIT_MODEL_TOTAL_BITS) * *prob;
+ if (rc->code < bound) {
+ rc->range = bound;
+ *prob += (RC_BIT_MODEL_TOTAL - *prob) >> RC_MOVE_BITS;
+ bit = 0;
+ } else {
+ rc->range -= bound;
+ rc->code -= bound;
+ *prob -= *prob >> RC_MOVE_BITS;
+ bit = 1;
+ }
+
+ return bit;
+}
+
+/* Decode a bittree starting from the most significant bit. */
+static __always_inline uint32_t rc_bittree(struct rc_dec *rc,
+ uint16_t *probs, uint32_t limit)
+{
+ uint32_t symbol = 1;
+
+ do {
+ if (rc_bit(rc, &probs[symbol]))
+ symbol = (symbol << 1) + 1;
+ else
+ symbol <<= 1;
+ } while (symbol < limit);
+
+ return symbol;
+}
+
+/* Decode a bittree starting from the least significant bit. */
+static __always_inline void rc_bittree_reverse(struct rc_dec *rc,
+ uint16_t *probs,
+ uint32_t *dest, uint32_t limit)
+{
+ uint32_t symbol = 1;
+ uint32_t i = 0;
+
+ do {
+ if (rc_bit(rc, &probs[symbol])) {
+ symbol = (symbol << 1) + 1;
+ *dest += 1 << i;
+ } else {
+ symbol <<= 1;
+ }
+ } while (++i < limit);
+}
+
+/* Decode direct bits (fixed fifty-fifty probability) */
+static inline void rc_direct(struct rc_dec *rc, uint32_t *dest, uint32_t limit)
+{
+ uint32_t mask;
+
+ do {
+ rc_normalize(rc);
+ rc->range >>= 1;
+ rc->code -= rc->range;
+ mask = (uint32_t)0 - (rc->code >> 31);
+ rc->code += rc->range & mask;
+ *dest = (*dest << 1) + (mask + 1);
+ } while (--limit > 0);
+}
+
+/********
+ * LZMA *
+ ********/
+
+/* Get pointer to literal coder probability array. */
+static uint16_t *lzma_literal_probs(struct xz_dec_lzma2 *s)
+{
+ uint32_t prev_byte = dict_get(&s->dict, 0);
+ uint32_t low = prev_byte >> (8 - s->lzma.lc);
+ uint32_t high = (s->dict.pos & s->lzma.literal_pos_mask) << s->lzma.lc;
+ return s->lzma.literal[low + high];
+}
+
+/* Decode a literal (one 8-bit byte) */
+static void lzma_literal(struct xz_dec_lzma2 *s)
+{
+ uint16_t *probs;
+ uint32_t symbol;
+ uint32_t match_byte;
+ uint32_t match_bit;
+ uint32_t offset;
+ uint32_t i;
+
+ probs = lzma_literal_probs(s);
+
+ if (lzma_state_is_literal(s->lzma.state)) {
+ symbol = rc_bittree(&s->rc, probs, 0x100);
+ } else {
+ symbol = 1;
+ match_byte = dict_get(&s->dict, s->lzma.rep0) << 1;
+ offset = 0x100;
+
+ do {
+ match_bit = match_byte & offset;
+ match_byte <<= 1;
+ i = offset + match_bit + symbol;
+
+ if (rc_bit(&s->rc, &probs[i])) {
+ symbol = (symbol << 1) + 1;
+ offset &= match_bit;
+ } else {
+ symbol <<= 1;
+ offset &= ~match_bit;
+ }
+ } while (symbol < 0x100);
+ }
+
+ dict_put(&s->dict, (uint8_t)symbol);
+ lzma_state_literal(&s->lzma.state);
+}
+
+/* Decode the length of the match into s->lzma.len. */
+static void lzma_len(struct xz_dec_lzma2 *s, struct lzma_len_dec *l,
+ uint32_t pos_state)
+{
+ uint16_t *probs;
+ uint32_t limit;
+
+ if (!rc_bit(&s->rc, &l->choice)) {
+ probs = l->low[pos_state];
+ limit = LEN_LOW_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN;
+ } else {
+ if (!rc_bit(&s->rc, &l->choice2)) {
+ probs = l->mid[pos_state];
+ limit = LEN_MID_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS;
+ } else {
+ probs = l->high;
+ limit = LEN_HIGH_SYMBOLS;
+ s->lzma.len = MATCH_LEN_MIN + LEN_LOW_SYMBOLS
+ + LEN_MID_SYMBOLS;
+ }
+ }
+
+ s->lzma.len += rc_bittree(&s->rc, probs, limit) - limit;
+}
+
+/* Decode a match. The distance will be stored in s->lzma.rep0. */
+static void lzma_match(struct xz_dec_lzma2 *s, uint32_t pos_state)
+{
+ uint16_t *probs;
+ uint32_t dist_slot;
+ uint32_t limit;
+
+ lzma_state_match(&s->lzma.state);
+
+ s->lzma.rep3 = s->lzma.rep2;
+ s->lzma.rep2 = s->lzma.rep1;
+ s->lzma.rep1 = s->lzma.rep0;
+
+ lzma_len(s, &s->lzma.match_len_dec, pos_state);
+
+ probs = s->lzma.dist_slot[lzma_get_dist_state(s->lzma.len)];
+ dist_slot = rc_bittree(&s->rc, probs, DIST_SLOTS) - DIST_SLOTS;
+
+ if (dist_slot < DIST_MODEL_START) {
+ s->lzma.rep0 = dist_slot;
+ } else {
+ limit = (dist_slot >> 1) - 1;
+ s->lzma.rep0 = 2 + (dist_slot & 1);
+
+ if (dist_slot < DIST_MODEL_END) {
+ s->lzma.rep0 <<= limit;
+ probs = s->lzma.dist_special + s->lzma.rep0
+ - dist_slot - 1;
+ rc_bittree_reverse(&s->rc, probs,
+ &s->lzma.rep0, limit);
+ } else {
+ rc_direct(&s->rc, &s->lzma.rep0, limit - ALIGN_BITS);
+ s->lzma.rep0 <<= ALIGN_BITS;
+ rc_bittree_reverse(&s->rc, s->lzma.dist_align,
+ &s->lzma.rep0, ALIGN_BITS);
+ }
+ }
+}
+
+/*
+ * Decode a repeated match. The distance is one of the four most recently
+ * seen matches. The distance will be stored in s->lzma.rep0.
+ */
+static void lzma_rep_match(struct xz_dec_lzma2 *s, uint32_t pos_state)
+{
+ uint32_t tmp;
+
+ if (!rc_bit(&s->rc, &s->lzma.is_rep0[s->lzma.state])) {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep0_long[
+ s->lzma.state][pos_state])) {
+ lzma_state_short_rep(&s->lzma.state);
+ s->lzma.len = 1;
+ return;
+ }
+ } else {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep1[s->lzma.state])) {
+ tmp = s->lzma.rep1;
+ } else {
+ if (!rc_bit(&s->rc, &s->lzma.is_rep2[s->lzma.state])) {
+ tmp = s->lzma.rep2;
+ } else {
+ tmp = s->lzma.rep3;
+ s->lzma.rep3 = s->lzma.rep2;
+ }
+
+ s->lzma.rep2 = s->lzma.rep1;
+ }
+
+ s->lzma.rep1 = s->lzma.rep0;
+ s->lzma.rep0 = tmp;
+ }
+
+ lzma_state_long_rep(&s->lzma.state);
+ lzma_len(s, &s->lzma.rep_len_dec, pos_state);
+}
+
+/* LZMA decoder core */
+static bool lzma_main(struct xz_dec_lzma2 *s)
+{
+ uint32_t pos_state;
+
+ /*
+ * If the dictionary was reached during the previous call, try to
+ * finish the possibly pending repeat in the dictionary.
+ */
+ if (dict_has_space(&s->dict) && s->lzma.len > 0)
+ dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0);
+
+ /*
+ * Decode more LZMA symbols. One iteration may consume up to
+ * LZMA_IN_REQUIRED - 1 bytes.
+ */
+ while (dict_has_space(&s->dict) && !rc_limit_exceeded(&s->rc)) {
+ pos_state = s->dict.pos & s->lzma.pos_mask;
+
+ if (!rc_bit(&s->rc, &s->lzma.is_match[
+ s->lzma.state][pos_state])) {
+ lzma_literal(s);
+ } else {
+ if (rc_bit(&s->rc, &s->lzma.is_rep[s->lzma.state]))
+ lzma_rep_match(s, pos_state);
+ else
+ lzma_match(s, pos_state);
+
+ if (!dict_repeat(&s->dict, &s->lzma.len, s->lzma.rep0))
+ return false;
+ }
+ }
+
+ /*
+ * Having the range decoder always normalized when we are outside
+ * this function makes it easier to correctly handle end of the chunk.
+ */
+ rc_normalize(&s->rc);
+
+ return true;
+}
+
+/*
+ * Reset the LZMA decoder and range decoder state. Dictionary is nore reset
+ * here, because LZMA state may be reset without resetting the dictionary.
+ */
+static void lzma_reset(struct xz_dec_lzma2 *s)
+{
+ uint16_t *probs;
+ size_t i;
+
+ s->lzma.state = STATE_LIT_LIT;
+ s->lzma.rep0 = 0;
+ s->lzma.rep1 = 0;
+ s->lzma.rep2 = 0;
+ s->lzma.rep3 = 0;
+
+ /*
+ * All probabilities are initialized to the same value. This hack
+ * makes the code smaller by avoiding a separate loop for each
+ * probability array.
+ *
+ * This could be optimized so that only that part of literal
+ * probabilities that are actually required. In the common case
+ * we would write 12 KiB less.
+ */
+ probs = s->lzma.is_match[0];
+ for (i = 0; i < PROBS_TOTAL; ++i)
+ probs[i] = RC_BIT_MODEL_TOTAL / 2;
+
+ rc_reset(&s->rc);
+}
+
+/*
+ * Decode and validate LZMA properties (lc/lp/pb) and calculate the bit masks
+ * from the decoded lp and pb values. On success, the LZMA decoder state is
+ * reset and true is returned.
+ */
+static bool lzma_props(struct xz_dec_lzma2 *s, uint8_t props)
+{
+ if (props > (4 * 5 + 4) * 9 + 8)
+ return false;
+
+ s->lzma.pos_mask = 0;
+ while (props >= 9 * 5) {
+ props -= 9 * 5;
+ ++s->lzma.pos_mask;
+ }
+
+ s->lzma.pos_mask = (1 << s->lzma.pos_mask) - 1;
+
+ s->lzma.literal_pos_mask = 0;
+ while (props >= 9) {
+ props -= 9;
+ ++s->lzma.literal_pos_mask;
+ }
+
+ s->lzma.lc = props;
+
+ if (s->lzma.lc + s->lzma.literal_pos_mask > 4)
+ return false;
+
+ s->lzma.literal_pos_mask = (1 << s->lzma.literal_pos_mask) - 1;
+
+ lzma_reset(s);
+
+ return true;
+}
+
+/*********
+ * LZMA2 *
+ *********/
+
+/*
+ * The LZMA decoder assumes that if the input limit (s->rc.in_limit) hasn't
+ * been exceeded, it is safe to read up to LZMA_IN_REQUIRED bytes. This
+ * wrapper function takes care of making the LZMA decoder's assumption safe.
+ *
+ * As long as there is plenty of input left to be decoded in the current LZMA
+ * chunk, we decode directly from the caller-supplied input buffer until
+ * there's LZMA_IN_REQUIRED bytes left. Those remaining bytes are copied into
+ * s->temp.buf, which (hopefully) gets filled on the next call to this
+ * function. We decode a few bytes from the temporary buffer so that we can
+ * continue decoding from the caller-supplied input buffer again.
+ */
+static bool lzma2_lzma(struct xz_dec_lzma2 *s, struct xz_buf *b)
+{
+ size_t in_avail;
+ uint32_t tmp;
+
+ in_avail = b->in_size - b->in_pos;
+ if (s->temp.size > 0 || s->lzma2.compressed == 0) {
+ tmp = 2 * LZMA_IN_REQUIRED - s->temp.size;
+ if (tmp > s->lzma2.compressed - s->temp.size)
+ tmp = s->lzma2.compressed - s->temp.size;
+ if (tmp > in_avail)
+ tmp = in_avail;
+
+ memcpy(s->temp.buf + s->temp.size, b->in + b->in_pos, tmp);
+
+ if (s->temp.size + tmp == s->lzma2.compressed) {
+ memzero(s->temp.buf + s->temp.size + tmp,
+ sizeof(s->temp.buf)
+ - s->temp.size - tmp);
+ s->rc.in_limit = s->temp.size + tmp;
+ } else if (s->temp.size + tmp < LZMA_IN_REQUIRED) {
+ s->temp.size += tmp;
+ b->in_pos += tmp;
+ return true;
+ } else {
+ s->rc.in_limit = s->temp.size + tmp - LZMA_IN_REQUIRED;
+ }
+
+ s->rc.in = s->temp.buf;
+ s->rc.in_pos = 0;
+
+ if (!lzma_main(s) || s->rc.in_pos > s->temp.size + tmp)
+ return false;
+
+ s->lzma2.compressed -= s->rc.in_pos;
+
+ if (s->rc.in_pos < s->temp.size) {
+ s->temp.size -= s->rc.in_pos;
+ memmove(s->temp.buf, s->temp.buf + s->rc.in_pos,
+ s->temp.size);
+ return true;
+ }
+
+ b->in_pos += s->rc.in_pos - s->temp.size;
+ s->temp.size = 0;
+ }
+
+ in_avail = b->in_size - b->in_pos;
+ if (in_avail >= LZMA_IN_REQUIRED) {
+ s->rc.in = b->in;
+ s->rc.in_pos = b->in_pos;
+
+ if (in_avail >= s->lzma2.compressed + LZMA_IN_REQUIRED)
+ s->rc.in_limit = b->in_pos + s->lzma2.compressed;
+ else
+ s->rc.in_limit = b->in_size - LZMA_IN_REQUIRED;
+
+ if (!lzma_main(s))
+ return false;
+
+ in_avail = s->rc.in_pos - b->in_pos;
+ if (in_avail > s->lzma2.compressed)
+ return false;
+
+ s->lzma2.compressed -= in_avail;
+ b->in_pos = s->rc.in_pos;
+ }
+
+ in_avail = b->in_size - b->in_pos;
+ if (in_avail < LZMA_IN_REQUIRED) {
+ if (in_avail > s->lzma2.compressed)
+ in_avail = s->lzma2.compressed;
+
+ memcpy(s->temp.buf, b->in + b->in_pos, in_avail);
+ s->temp.size = in_avail;
+ b->in_pos += in_avail;
+ }
+
+ return true;
+}
+
+/*
+ * Take care of the LZMA2 control layer, and forward the job of actual LZMA
+ * decoding or copying of uncompressed chunks to other functions.
+ */
+XZ_EXTERN enum xz_ret xz_dec_lzma2_run(struct xz_dec_lzma2 *s,
+ struct xz_buf *b)
+{
+ uint32_t tmp;
+
+ while (b->in_pos < b->in_size || s->lzma2.sequence == SEQ_LZMA_RUN) {
+ switch (s->lzma2.sequence) {
+ case SEQ_CONTROL:
+ /*
+ * LZMA2 control byte
+ *
+ * Exact values:
+ * 0x00 End marker
+ * 0x01 Dictionary reset followed by
+ * an uncompressed chunk
+ * 0x02 Uncompressed chunk (no dictionary reset)
+ *
+ * Highest three bits (s->control & 0xE0):
+ * 0xE0 Dictionary reset, new properties and state
+ * reset, followed by LZMA compressed chunk
+ * 0xC0 New properties and state reset, followed
+ * by LZMA compressed chunk (no dictionary
+ * reset)
+ * 0xA0 State reset using old properties,
+ * followed by LZMA compressed chunk (no
+ * dictionary reset)
+ * 0x80 LZMA chunk (no dictionary or state reset)
+ *
+ * For LZMA compressed chunks, the lowest five bits
+ * (s->control & 1F) are the highest bits of the
+ * uncompressed size (bits 16-20).
+ *
+ * A new LZMA2 stream must begin with a dictionary
+ * reset. The first LZMA chunk must set new
+ * properties and reset the LZMA state.
+ *
+ * Values that don't match anything described above
+ * are invalid and we return XZ_DATA_ERROR.
+ */
+ tmp = b->in[b->in_pos++];
+
+ if (tmp == 0x00)
+ return XZ_STREAM_END;
+
+ if (tmp >= 0xE0 || tmp == 0x01) {
+ s->lzma2.need_props = true;
+ s->lzma2.need_dict_reset = false;
+ dict_reset(&s->dict, b);
+ } else if (s->lzma2.need_dict_reset) {
+ return XZ_DATA_ERROR;
+ }
+
+ if (tmp >= 0x80) {
+ s->lzma2.uncompressed = (tmp & 0x1F) << 16;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_1;
+
+ if (tmp >= 0xC0) {
+ /*
+ * When there are new properties,
+ * state reset is done at
+ * SEQ_PROPERTIES.
+ */
+ s->lzma2.need_props = false;
+ s->lzma2.next_sequence
+ = SEQ_PROPERTIES;
+
+ } else if (s->lzma2.need_props) {
+ return XZ_DATA_ERROR;
+
+ } else {
+ s->lzma2.next_sequence
+ = SEQ_LZMA_PREPARE;
+ if (tmp >= 0xA0)
+ lzma_reset(s);
+ }
+ } else {
+ if (tmp > 0x02)
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ s->lzma2.next_sequence = SEQ_COPY;
+ }
+
+ break;
+
+ case SEQ_UNCOMPRESSED_1:
+ s->lzma2.uncompressed
+ += (uint32_t)b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_UNCOMPRESSED_2;
+ break;
+
+ case SEQ_UNCOMPRESSED_2:
+ s->lzma2.uncompressed
+ += (uint32_t)b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = SEQ_COMPRESSED_0;
+ break;
+
+ case SEQ_COMPRESSED_0:
+ s->lzma2.compressed
+ = (uint32_t)b->in[b->in_pos++] << 8;
+ s->lzma2.sequence = SEQ_COMPRESSED_1;
+ break;
+
+ case SEQ_COMPRESSED_1:
+ s->lzma2.compressed
+ += (uint32_t)b->in[b->in_pos++] + 1;
+ s->lzma2.sequence = s->lzma2.next_sequence;
+ break;
+
+ case SEQ_PROPERTIES:
+ if (!lzma_props(s, b->in[b->in_pos++]))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.sequence = SEQ_LZMA_PREPARE;
+
+ case SEQ_LZMA_PREPARE:
+ if (s->lzma2.compressed < RC_INIT_BYTES)
+ return XZ_DATA_ERROR;
+
+ if (!rc_read_init(&s->rc, b))
+ return XZ_OK;
+
+ s->lzma2.compressed -= RC_INIT_BYTES;
+ s->lzma2.sequence = SEQ_LZMA_RUN;
+
+ case SEQ_LZMA_RUN:
+ /*
+ * Set dictionary limit to indicate how much we want
+ * to be encoded at maximum. Decode new data into the
+ * dictionary. Flush the new data from dictionary to
+ * b->out. Check if we finished decoding this chunk.
+ * In case the dictionary got full but we didn't fill
+ * the output buffer yet, we may run this loop
+ * multiple times without changing s->lzma2.sequence.
+ */
+ dict_limit(&s->dict, min_t(size_t,
+ b->out_size - b->out_pos,
+ s->lzma2.uncompressed));
+ if (!lzma2_lzma(s, b))
+ return XZ_DATA_ERROR;
+
+ s->lzma2.uncompressed -= dict_flush(&s->dict, b);
+
+ if (s->lzma2.uncompressed == 0) {
+ if (s->lzma2.compressed > 0 || s->lzma.len > 0
+ || !rc_is_finished(&s->rc))
+ return XZ_DATA_ERROR;
+
+ rc_reset(&s->rc);
+ s->lzma2.sequence = SEQ_CONTROL;
+
+ } else if (b->out_pos == b->out_size
+ || (b->in_pos == b->in_size
+ && s->temp.size
+ < s->lzma2.compressed)) {
+ return XZ_OK;
+ }
+
+ break;
+
+ case SEQ_COPY:
+ dict_uncompressed(&s->dict, b, &s->lzma2.compressed);
+ if (s->lzma2.compressed > 0)
+ return XZ_OK;
+
+ s->lzma2.sequence = SEQ_CONTROL;
+ break;
+ }
+ }
+
+ return XZ_OK;
+}
+
+XZ_EXTERN struct xz_dec_lzma2 *xz_dec_lzma2_create(enum xz_mode mode,
+ uint32_t dict_max)
+{
+ struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return NULL;
+
+ s->dict.mode = mode;
+ s->dict.size_max = dict_max;
+
+ if (DEC_IS_PREALLOC(mode)) {
+ s->dict.buf = vmalloc(dict_max);
+ if (s->dict.buf == NULL) {
+ kfree(s);
+ return NULL;
+ }
+ } else if (DEC_IS_DYNALLOC(mode)) {
+ s->dict.buf = NULL;
+ s->dict.allocated = 0;
+ }
+
+ return s;
+}
+
+XZ_EXTERN enum xz_ret xz_dec_lzma2_reset(struct xz_dec_lzma2 *s, uint8_t props)
+{
+ /* This limits dictionary size to 3 GiB to keep parsing simpler. */
+ if (props > 39)
+ return XZ_OPTIONS_ERROR;
+
+ s->dict.size = 2 + (props & 1);
+ s->dict.size <<= (props >> 1) + 11;
+
+ if (DEC_IS_MULTI(s->dict.mode)) {
+ if (s->dict.size > s->dict.size_max)
+ return XZ_MEMLIMIT_ERROR;
+
+ s->dict.end = s->dict.size;
+
+ if (DEC_IS_DYNALLOC(s->dict.mode)) {
+ if (s->dict.allocated < s->dict.size) {
+ vfree(s->dict.buf);
+ s->dict.buf = vmalloc(s->dict.size);
+ if (s->dict.buf == NULL) {
+ s->dict.allocated = 0;
+ return XZ_MEM_ERROR;
+ }
+ }
+ }
+ }
+
+ s->lzma.len = 0;
+
+ s->lzma2.sequence = SEQ_CONTROL;
+ s->lzma2.need_dict_reset = true;
+
+ s->temp.size = 0;
+
+ return XZ_OK;
+}
+
+XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s)
+{
+ if (DEC_IS_MULTI(s->dict.mode))
+ vfree(s->dict.buf);
+
+ kfree(s);
+}
diff --git a/libxz/xz_dec_stream.c b/libxz/xz_dec_stream.c
new file mode 100644
index 000000000000..bb9517a985df
--- /dev/null
+++ b/libxz/xz_dec_stream.c
@@ -0,0 +1,847 @@
+/*
+ * .xz Stream decoder
+ *
+ * Author: Lasse Collin <lasse.collin@tukaani.org>
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#include "xz_private.h"
+#include "xz_stream.h"
+
+#ifdef XZ_USE_CRC64
+# define IS_CRC64(check_type) ((check_type) == XZ_CHECK_CRC64)
+#else
+# define IS_CRC64(check_type) false
+#endif
+
+/* Hash used to validate the Index field */
+struct xz_dec_hash {
+ vli_type unpadded;
+ vli_type uncompressed;
+ uint32_t crc32;
+};
+
+struct xz_dec {
+ /* Position in dec_main() */
+ enum {
+ SEQ_STREAM_HEADER,
+ SEQ_BLOCK_START,
+ SEQ_BLOCK_HEADER,
+ SEQ_BLOCK_UNCOMPRESS,
+ SEQ_BLOCK_PADDING,
+ SEQ_BLOCK_CHECK,
+ SEQ_INDEX,
+ SEQ_INDEX_PADDING,
+ SEQ_INDEX_CRC32,
+ SEQ_STREAM_FOOTER
+ } sequence;
+
+ /* Position in variable-length integers and Check fields */
+ uint32_t pos;
+
+ /* Variable-length integer decoded by dec_vli() */
+ vli_type vli;
+
+ /* Saved in_pos and out_pos */
+ size_t in_start;
+ size_t out_start;
+
+#ifdef XZ_USE_CRC64
+ /* CRC32 or CRC64 value in Block or CRC32 value in Index */
+ uint64_t crc;
+#else
+ /* CRC32 value in Block or Index */
+ uint32_t crc;
+#endif
+
+ /* Type of the integrity check calculated from uncompressed data */
+ enum xz_check check_type;
+
+ /* Operation mode */
+ enum xz_mode mode;
+
+ /*
+ * True if the next call to xz_dec_run() is allowed to return
+ * XZ_BUF_ERROR.
+ */
+ bool allow_buf_error;
+
+ /* Information stored in Block Header */
+ struct {
+ /*
+ * Value stored in the Compressed Size field, or
+ * VLI_UNKNOWN if Compressed Size is not present.
+ */
+ vli_type compressed;
+
+ /*
+ * Value stored in the Uncompressed Size field, or
+ * VLI_UNKNOWN if Uncompressed Size is not present.
+ */
+ vli_type uncompressed;
+
+ /* Size of the Block Header field */
+ uint32_t size;
+ } block_header;
+
+ /* Information collected when decoding Blocks */
+ struct {
+ /* Observed compressed size of the current Block */
+ vli_type compressed;
+
+ /* Observed uncompressed size of the current Block */
+ vli_type uncompressed;
+
+ /* Number of Blocks decoded so far */
+ vli_type count;
+
+ /*
+ * Hash calculated from the Block sizes. This is used to
+ * validate the Index field.
+ */
+ struct xz_dec_hash hash;
+ } block;
+
+ /* Variables needed when verifying the Index field */
+ struct {
+ /* Position in dec_index() */
+ enum {
+ SEQ_INDEX_COUNT,
+ SEQ_INDEX_UNPADDED,
+ SEQ_INDEX_UNCOMPRESSED
+ } sequence;
+
+ /* Size of the Index in bytes */
+ vli_type size;
+
+ /* Number of Records (matches block.count in valid files) */
+ vli_type count;
+
+ /*
+ * Hash calculated from the Records (matches block.hash in
+ * valid files).
+ */
+ struct xz_dec_hash hash;
+ } index;
+
+ /*
+ * Temporary buffer needed to hold Stream Header, Block Header,
+ * and Stream Footer. The Block Header is the biggest (1 KiB)
+ * so we reserve space according to that. buf[] has to be aligned
+ * to a multiple of four bytes; the size_t variables before it
+ * should guarantee this.
+ */
+ struct {
+ size_t pos;
+ size_t size;
+ uint8_t buf[1024];
+ } temp;
+
+ struct xz_dec_lzma2 *lzma2;
+
+#ifdef XZ_DEC_BCJ
+ struct xz_dec_bcj *bcj;
+ bool bcj_active;
+#endif
+};
+
+#ifdef XZ_DEC_ANY_CHECK
+/* Sizes of the Check field with different Check IDs */
+static const uint8_t check_sizes[16] = {
+ 0,
+ 4, 4, 4,
+ 8, 8, 8,
+ 16, 16, 16,
+ 32, 32, 32,
+ 64, 64, 64
+};
+#endif
+
+/*
+ * Fill s->temp by copying data starting from b->in[b->in_pos]. Caller
+ * must have set s->temp.pos to indicate how much data we are supposed
+ * to copy into s->temp.buf. Return true once s->temp.pos has reached
+ * s->temp.size.
+ */
+static bool fill_temp(struct xz_dec *s, struct xz_buf *b)
+{
+ size_t copy_size = min_t(size_t,
+ b->in_size - b->in_pos, s->temp.size - s->temp.pos);
+
+ memcpy(s->temp.buf + s->temp.pos, b->in + b->in_pos, copy_size);
+ b->in_pos += copy_size;
+ s->temp.pos += copy_size;
+
+ if (s->temp.pos == s->temp.size) {
+ s->temp.pos = 0;
+ return true;
+ }
+
+ return false;
+}
+
+/* Decode a variable-length integer (little-endian base-128 encoding) */
+static enum xz_ret dec_vli(struct xz_dec *s, const uint8_t *in,
+ size_t *in_pos, size_t in_size)
+{
+ uint8_t byte;
+
+ if (s->pos == 0)
+ s->vli = 0;
+
+ while (*in_pos < in_size) {
+ byte = in[*in_pos];
+ ++*in_pos;
+
+ s->vli |= (vli_type)(byte & 0x7F) << s->pos;
+
+ if ((byte & 0x80) == 0) {
+ /* Don't allow non-minimal encodings. */
+ if (byte == 0 && s->pos != 0)
+ return XZ_DATA_ERROR;
+
+ s->pos = 0;
+ return XZ_STREAM_END;
+ }
+
+ s->pos += 7;
+ if (s->pos == 7 * VLI_BYTES_MAX)
+ return XZ_DATA_ERROR;
+ }
+
+ return XZ_OK;
+}
+
+/*
+ * Decode the Compressed Data field from a Block. Update and validate
+ * the observed compressed and uncompressed sizes of the Block so that
+ * they don't exceed the values possibly stored in the Block Header
+ * (validation assumes that no integer overflow occurs, since vli_type
+ * is normally uint64_t). Update the CRC32 or CRC64 value if presence of
+ * the CRC32 or CRC64 field was indicated in Stream Header.
+ *
+ * Once the decoding is finished, validate that the observed sizes match
+ * the sizes possibly stored in the Block Header. Update the hash and
+ * Block count, which are later used to validate the Index field.
+ */
+static enum xz_ret dec_block(struct xz_dec *s, struct xz_buf *b)
+{
+ enum xz_ret ret;
+
+ s->in_start = b->in_pos;
+ s->out_start = b->out_pos;
+
+#ifdef XZ_DEC_BCJ
+ if (s->bcj_active)
+ ret = xz_dec_bcj_run(s->bcj, s->lzma2, b);
+ else
+#endif
+ ret = xz_dec_lzma2_run(s->lzma2, b);
+
+ s->block.compressed += b->in_pos - s->in_start;
+ s->block.uncompressed += b->out_pos - s->out_start;
+
+ /*
+ * There is no need to separately check for VLI_UNKNOWN, since
+ * the observed sizes are always smaller than VLI_UNKNOWN.
+ */
+ if (s->block.compressed > s->block_header.compressed
+ || s->block.uncompressed
+ > s->block_header.uncompressed)
+ return XZ_DATA_ERROR;
+
+ if (s->check_type == XZ_CHECK_CRC32)
+ s->crc = xz_crc32(b->out + s->out_start,
+ b->out_pos - s->out_start, s->crc);
+#ifdef XZ_USE_CRC64
+ else if (s->check_type == XZ_CHECK_CRC64)
+ s->crc = xz_crc64(b->out + s->out_start,
+ b->out_pos - s->out_start, s->crc);
+#endif
+
+ if (ret == XZ_STREAM_END) {
+ if (s->block_header.compressed != VLI_UNKNOWN
+ && s->block_header.compressed
+ != s->block.compressed)
+ return XZ_DATA_ERROR;
+
+ if (s->block_header.uncompressed != VLI_UNKNOWN
+ && s->block_header.uncompressed
+ != s->block.uncompressed)
+ return XZ_DATA_ERROR;
+
+ s->block.hash.unpadded += s->block_header.size
+ + s->block.compressed;
+
+#ifdef XZ_DEC_ANY_CHECK
+ s->block.hash.unpadded += check_sizes[s->check_type];
+#else
+ if (s->check_type == XZ_CHECK_CRC32)
+ s->block.hash.unpadded += 4;
+ else if (IS_CRC64(s->check_type))
+ s->block.hash.unpadded += 8;
+#endif
+
+ s->block.hash.uncompressed += s->block.uncompressed;
+ s->block.hash.crc32 = xz_crc32(
+ (const uint8_t *)&s->block.hash,
+ sizeof(s->block.hash), s->block.hash.crc32);
+
+ ++s->block.count;
+ }
+
+ return ret;
+}
+
+/* Update the Index size and the CRC32 value. */
+static void index_update(struct xz_dec *s, const struct xz_buf *b)
+{
+ size_t in_used = b->in_pos - s->in_start;
+ s->index.size += in_used;
+ s->crc = xz_crc32(b->in + s->in_start, in_used, s->crc);
+}
+
+/*
+ * Decode the Number of Records, Unpadded Size, and Uncompressed Size
+ * fields from the Index field. That is, Index Padding and CRC32 are not
+ * decoded by this function.
+ *
+ * This can return XZ_OK (more input needed), XZ_STREAM_END (everything
+ * successfully decoded), or XZ_DATA_ERROR (input is corrupt).
+ */
+static enum xz_ret dec_index(struct xz_dec *s, struct xz_buf *b)
+{
+ enum xz_ret ret;
+
+ do {
+ ret = dec_vli(s, b->in, &b->in_pos, b->in_size);
+ if (ret != XZ_STREAM_END) {
+ index_update(s, b);
+ return ret;
+ }
+
+ switch (s->index.sequence) {
+ case SEQ_INDEX_COUNT:
+ s->index.count = s->vli;
+
+ /*
+ * Validate that the Number of Records field
+ * indicates the same number of Records as
+ * there were Blocks in the Stream.
+ */
+ if (s->index.count != s->block.count)
+ return XZ_DATA_ERROR;
+
+ s->index.sequence = SEQ_INDEX_UNPADDED;
+ break;
+
+ case SEQ_INDEX_UNPADDED:
+ s->index.hash.unpadded += s->vli;
+ s->index.sequence = SEQ_INDEX_UNCOMPRESSED;
+ break;
+
+ case SEQ_INDEX_UNCOMPRESSED:
+ s->index.hash.uncompressed += s->vli;
+ s->index.hash.crc32 = xz_crc32(
+ (const uint8_t *)&s->index.hash,
+ sizeof(s->index.hash),
+ s->index.hash.crc32);
+ --s->index.count;
+ s->index.sequence = SEQ_INDEX_UNPADDED;
+ break;
+ }
+ } while (s->index.count > 0);
+
+ return XZ_STREAM_END;
+}
+
+/*
+ * Validate that the next four or eight input bytes match the value
+ * of s->crc. s->pos must be zero when starting to validate the first byte.
+ * The "bits" argument allows using the same code for both CRC32 and CRC64.
+ */
+static enum xz_ret crc_validate(struct xz_dec *s, struct xz_buf *b,
+ uint32_t bits)
+{
+ do {
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ if (((s->crc >> s->pos) & 0xFF) != b->in[b->in_pos++])
+ return XZ_DATA_ERROR;
+
+ s->pos += 8;
+
+ } while (s->pos < bits);
+
+ s->crc = 0;
+ s->pos = 0;
+
+ return XZ_STREAM_END;
+}
+
+#ifdef XZ_DEC_ANY_CHECK
+/*
+ * Skip over the Check field when the Check ID is not supported.
+ * Returns true once the whole Check field has been skipped over.
+ */
+static bool check_skip(struct xz_dec *s, struct xz_buf *b)
+{
+ while (s->pos < check_sizes[s->check_type]) {
+ if (b->in_pos == b->in_size)
+ return false;
+
+ ++b->in_pos;
+ ++s->pos;
+ }
+
+ s->pos = 0;
+
+ return true;
+}
+#endif
+
+/* Decode the Stream Header field (the first 12 bytes of the .xz Stream). */
+static enum xz_ret dec_stream_header(struct xz_dec *s)
+{
+ if (!memeq(s->temp.buf, HEADER_MAGIC, HEADER_MAGIC_SIZE))
+ return XZ_FORMAT_ERROR;
+
+ if (xz_crc32(s->temp.buf + HEADER_MAGIC_SIZE, 2, 0)
+ != get_le32(s->temp.buf + HEADER_MAGIC_SIZE + 2))
+ return XZ_DATA_ERROR;
+
+ if (s->temp.buf[HEADER_MAGIC_SIZE] != 0)
+ return XZ_OPTIONS_ERROR;
+
+ /*
+ * Of integrity checks, we support none (Check ID = 0),
+ * CRC32 (Check ID = 1), and optionally CRC64 (Check ID = 4).
+ * However, if XZ_DEC_ANY_CHECK is defined, we will accept other
+ * check types too, but then the check won't be verified and
+ * a warning (XZ_UNSUPPORTED_CHECK) will be given.
+ */
+ s->check_type = s->temp.buf[HEADER_MAGIC_SIZE + 1];
+
+#ifdef XZ_DEC_ANY_CHECK
+ if (s->check_type > XZ_CHECK_MAX)
+ return XZ_OPTIONS_ERROR;
+
+ if (s->check_type > XZ_CHECK_CRC32 && !IS_CRC64(s->check_type))
+ return XZ_UNSUPPORTED_CHECK;
+#else
+ if (s->check_type > XZ_CHECK_CRC32 && !IS_CRC64(s->check_type))
+ return XZ_OPTIONS_ERROR;
+#endif
+
+ return XZ_OK;
+}
+
+/* Decode the Stream Footer field (the last 12 bytes of the .xz Stream) */
+static enum xz_ret dec_stream_footer(struct xz_dec *s)
+{
+ if (!memeq(s->temp.buf + 10, FOOTER_MAGIC, FOOTER_MAGIC_SIZE))
+ return XZ_DATA_ERROR;
+
+ if (xz_crc32(s->temp.buf + 4, 6, 0) != get_le32(s->temp.buf))
+ return XZ_DATA_ERROR;
+
+ /*
+ * Validate Backward Size. Note that we never added the size of the
+ * Index CRC32 field to s->index.size, thus we use s->index.size / 4
+ * instead of s->index.size / 4 - 1.
+ */
+ if ((s->index.size >> 2) != get_le32(s->temp.buf + 4))
+ return XZ_DATA_ERROR;
+
+ if (s->temp.buf[8] != 0 || s->temp.buf[9] != s->check_type)
+ return XZ_DATA_ERROR;
+
+ /*
+ * Use XZ_STREAM_END instead of XZ_OK to be more convenient
+ * for the caller.
+ */
+ return XZ_STREAM_END;
+}
+
+/* Decode the Block Header and initialize the filter chain. */
+static enum xz_ret dec_block_header(struct xz_dec *s)
+{
+ enum xz_ret ret;
+
+ /*
+ * Validate the CRC32. We know that the temp buffer is at least
+ * eight bytes so this is safe.
+ */
+ s->temp.size -= 4;
+ if (xz_crc32(s->temp.buf, s->temp.size, 0)
+ != get_le32(s->temp.buf + s->temp.size))
+ return XZ_DATA_ERROR;
+
+ s->temp.pos = 2;
+
+ /*
+ * Catch unsupported Block Flags. We support only one or two filters
+ * in the chain, so we catch that with the same test.
+ */
+#ifdef XZ_DEC_BCJ
+ if (s->temp.buf[1] & 0x3E)
+#else
+ if (s->temp.buf[1] & 0x3F)
+#endif
+ return XZ_OPTIONS_ERROR;
+
+ /* Compressed Size */
+ if (s->temp.buf[1] & 0x40) {
+ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
+ != XZ_STREAM_END)
+ return XZ_DATA_ERROR;
+
+ s->block_header.compressed = s->vli;
+ } else {
+ s->block_header.compressed = VLI_UNKNOWN;
+ }
+
+ /* Uncompressed Size */
+ if (s->temp.buf[1] & 0x80) {
+ if (dec_vli(s, s->temp.buf, &s->temp.pos, s->temp.size)
+ != XZ_STREAM_END)
+ return XZ_DATA_ERROR;
+
+ s->block_header.uncompressed = s->vli;
+ } else {
+ s->block_header.uncompressed = VLI_UNKNOWN;
+ }
+
+#ifdef XZ_DEC_BCJ
+ /* If there are two filters, the first one must be a BCJ filter. */
+ s->bcj_active = s->temp.buf[1] & 0x01;
+ if (s->bcj_active) {
+ if (s->temp.size - s->temp.pos < 2)
+ return XZ_OPTIONS_ERROR;
+
+ ret = xz_dec_bcj_reset(s->bcj, s->temp.buf[s->temp.pos++]);
+ if (ret != XZ_OK)
+ return ret;
+
+ /*
+ * We don't support custom start offset,
+ * so Size of Properties must be zero.
+ */
+ if (s->temp.buf[s->temp.pos++] != 0x00)
+ return XZ_OPTIONS_ERROR;
+ }
+#endif
+
+ /* Valid Filter Flags always take at least two bytes. */
+ if (s->temp.size - s->temp.pos < 2)
+ return XZ_DATA_ERROR;
+
+ /* Filter ID = LZMA2 */
+ if (s->temp.buf[s->temp.pos++] != 0x21)
+ return XZ_OPTIONS_ERROR;
+
+ /* Size of Properties = 1-byte Filter Properties */
+ if (s->temp.buf[s->temp.pos++] != 0x01)
+ return XZ_OPTIONS_ERROR;
+
+ /* Filter Properties contains LZMA2 dictionary size. */
+ if (s->temp.size - s->temp.pos < 1)
+ return XZ_DATA_ERROR;
+
+ ret = xz_dec_lzma2_reset(s->lzma2, s->temp.buf[s->temp.pos++]);
+ if (ret != XZ_OK)
+ return ret;
+
+ /* The rest must be Header Padding. */
+ while (s->temp.pos < s->temp.size)
+ if (s->temp.buf[s->temp.pos++] != 0x00)
+ return XZ_OPTIONS_ERROR;
+
+ s->temp.pos = 0;
+ s->block.compressed = 0;
+ s->block.uncompressed = 0;
+
+ return XZ_OK;
+}
+
+static enum xz_ret dec_main(struct xz_dec *s, struct xz_buf *b)
+{
+ enum xz_ret ret;
+
+ /*
+ * Store the start position for the case when we are in the middle
+ * of the Index field.
+ */
+ s->in_start = b->in_pos;
+
+ while (true) {
+ switch (s->sequence) {
+ case SEQ_STREAM_HEADER:
+ /*
+ * Stream Header is copied to s->temp, and then
+ * decoded from there. This way if the caller
+ * gives us only little input at a time, we can
+ * still keep the Stream Header decoding code
+ * simple. Similar approach is used in many places
+ * in this file.
+ */
+ if (!fill_temp(s, b))
+ return XZ_OK;
+
+ /*
+ * If dec_stream_header() returns
+ * XZ_UNSUPPORTED_CHECK, it is still possible
+ * to continue decoding if working in multi-call
+ * mode. Thus, update s->sequence before calling
+ * dec_stream_header().
+ */
+ s->sequence = SEQ_BLOCK_START;
+
+ ret = dec_stream_header(s);
+ if (ret != XZ_OK)
+ return ret;
+
+ case SEQ_BLOCK_START:
+ /* We need one byte of input to continue. */
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ /* See if this is the beginning of the Index field. */
+ if (b->in[b->in_pos] == 0) {
+ s->in_start = b->in_pos++;
+ s->sequence = SEQ_INDEX;
+ break;
+ }
+
+ /*
+ * Calculate the size of the Block Header and
+ * prepare to decode it.
+ */
+ s->block_header.size
+ = ((uint32_t)b->in[b->in_pos] + 1) * 4;
+
+ s->temp.size = s->block_header.size;
+ s->temp.pos = 0;
+ s->sequence = SEQ_BLOCK_HEADER;
+
+ case SEQ_BLOCK_HEADER:
+ if (!fill_temp(s, b))
+ return XZ_OK;
+
+ ret = dec_block_header(s);
+ if (ret != XZ_OK)
+ return ret;
+
+ s->sequence = SEQ_BLOCK_UNCOMPRESS;
+
+ case SEQ_BLOCK_UNCOMPRESS:
+ ret = dec_block(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->sequence = SEQ_BLOCK_PADDING;
+
+ case SEQ_BLOCK_PADDING:
+ /*
+ * Size of Compressed Data + Block Padding
+ * must be a multiple of four. We don't need
+ * s->block.compressed for anything else
+ * anymore, so we use it here to test the size
+ * of the Block Padding field.
+ */
+ while (s->block.compressed & 3) {
+ if (b->in_pos == b->in_size)
+ return XZ_OK;
+
+ if (b->in[b->in_pos++] != 0)
+ return XZ_DATA_ERROR;
+
+ ++s->block.compressed;
+ }
+
+ s->sequence = SEQ_BLOCK_CHECK;
+
+ case SEQ_BLOCK_CHECK:
+ if (s->check_type == XZ_CHECK_CRC32) {
+ ret = crc_validate(s, b, 32);
+ if (ret != XZ_STREAM_END)
+ return ret;
+ }
+ else if (IS_CRC64(s->check_type)) {
+ ret = crc_validate(s, b, 64);
+ if (ret != XZ_STREAM_END)
+ return ret;
+ }
+#ifdef XZ_DEC_ANY_CHECK
+ else if (!check_skip(s, b)) {
+ return XZ_OK;
+ }
+#endif
+
+ s->sequence = SEQ_BLOCK_START;
+ break;
+
+ case SEQ_INDEX:
+ ret = dec_index(s, b);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->sequence = SEQ_INDEX_PADDING;
+
+ case SEQ_INDEX_PADDING:
+ while ((s->index.size + (b->in_pos - s->in_start))
+ & 3) {
+ if (b->in_pos == b->in_size) {
+ index_update(s, b);
+ return XZ_OK;
+ }
+
+ if (b->in[b->in_pos++] != 0)
+ return XZ_DATA_ERROR;
+ }
+
+ /* Finish the CRC32 value and Index size. */
+ index_update(s, b);
+
+ /* Compare the hashes to validate the Index field. */
+ if (!memeq(&s->block.hash, &s->index.hash,
+ sizeof(s->block.hash)))
+ return XZ_DATA_ERROR;
+
+ s->sequence = SEQ_INDEX_CRC32;
+
+ case SEQ_INDEX_CRC32:
+ ret = crc_validate(s, b, 32);
+ if (ret != XZ_STREAM_END)
+ return ret;
+
+ s->temp.size = STREAM_HEADER_SIZE;
+ s->sequence = SEQ_STREAM_FOOTER;
+
+ case SEQ_STREAM_FOOTER:
+ if (!fill_temp(s, b))
+ return XZ_OK;
+
+ return dec_stream_footer(s);
+ }
+ }
+
+ /* Never reached */
+}
+
+/*
+ * xz_dec_run() is a wrapper for dec_main() to handle some special cases in
+ * multi-call and single-call decoding.
+ *
+ * In multi-call mode, we must return XZ_BUF_ERROR when it seems clear that we
+ * are not going to make any progress anymore. This is to prevent the caller
+ * from calling us infinitely when the input file is truncated or otherwise
+ * corrupt. Since zlib-style API allows that the caller fills the input buffer
+ * only when the decoder doesn't produce any new output, we have to be careful
+ * to avoid returning XZ_BUF_ERROR too easily: XZ_BUF_ERROR is returned only
+ * after the second consecutive call to xz_dec_run() that makes no progress.
+ *
+ * In single-call mode, if we couldn't decode everything and no error
+ * occurred, either the input is truncated or the output buffer is too small.
+ * Since we know that the last input byte never produces any output, we know
+ * that if all the input was consumed and decoding wasn't finished, the file
+ * must be corrupt. Otherwise the output buffer has to be too small or the
+ * file is corrupt in a way that decoding it produces too big output.
+ *
+ * If single-call decoding fails, we reset b->in_pos and b->out_pos back to
+ * their original values. This is because with some filter chains there won't
+ * be any valid uncompressed data in the output buffer unless the decoding
+ * actually succeeds (that's the price to pay of using the output buffer as
+ * the workspace).
+ */
+XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b)
+{
+ size_t in_start;
+ size_t out_start;
+ enum xz_ret ret;
+
+ if (DEC_IS_SINGLE(s->mode))
+ xz_dec_reset(s);
+
+ in_start = b->in_pos;
+ out_start = b->out_pos;
+ ret = dec_main(s, b);
+
+ if (DEC_IS_SINGLE(s->mode)) {
+ if (ret == XZ_OK)
+ ret = b->in_pos == b->in_size
+ ? XZ_DATA_ERROR : XZ_BUF_ERROR;
+
+ if (ret != XZ_STREAM_END) {
+ b->in_pos = in_start;
+ b->out_pos = out_start;
+ }
+
+ } else if (ret == XZ_OK && in_start == b->in_pos
+ && out_start == b->out_pos) {
+ if (s->allow_buf_error)
+ ret = XZ_BUF_ERROR;
+
+ s->allow_buf_error = true;
+ } else {
+ s->allow_buf_error = false;
+ }
+
+ return ret;
+}
+
+XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max)
+{
+ struct xz_dec *s = kmalloc(sizeof(*s), GFP_KERNEL);
+ if (s == NULL)
+ return NULL;
+
+ s->mode = mode;
+
+#ifdef XZ_DEC_BCJ
+ s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode));
+ if (s->bcj == NULL)
+ goto error_bcj;
+#endif
+
+ s->lzma2 = xz_dec_lzma2_create(mode, dict_max);
+ if (s->lzma2 == NULL)
+ goto error_lzma2;
+
+ xz_dec_reset(s);
+ return s;
+
+error_lzma2:
+#ifdef XZ_DEC_BCJ
+ xz_dec_bcj_end(s->bcj);
+error_bcj:
+#endif
+ kfree(s);
+ return NULL;
+}
+
+XZ_EXTERN void xz_dec_reset(struct xz_dec *s)
+{
+ s->sequence = SEQ_STREAM_HEADER;
+ s->allow_buf_error = false;
+ s->pos = 0;
+ s->crc = 0;
+ memzero(&s->block, sizeof(s->block));
+ memzero(&s->index, sizeof(s->index));
+ s->temp.pos = 0;
+ s->temp.size = STREAM_HEADER_SIZE;
+}
+
+XZ_EXTERN void xz_dec_end(struct xz_dec *s)
+{
+ if (s != NULL) {
+ xz_dec_lzma2_end(s->lzma2);
+#ifdef XZ_DEC_BCJ
+ xz_dec_bcj_end(s->bcj);
+#endif
+ kfree(s);
+ }
+}
diff --git a/libxz/Makefile.objs b/libxz/Makefile.objs
new file mode 100644
index 000000000000..0fdd53400437
--- /dev/null
+++ b/libxz/Makefile.objs
@@ -0,0 +1 @@
+obj-y += xz_dec_stream.o xz_dec_lzma2.o xz_crc32.o
diff --git a/target/ppc/Makefile.objs b/target/ppc/Makefile.objs
index e8fa18ce13d1..ec2ad3e14dd5 100644
--- a/target/ppc/Makefile.objs
+++ b/target/ppc/Makefile.objs
@@ -18,3 +18,4 @@ obj-y += mem_helper.o
obj-y += ../../libdecnumber/
obj-$(CONFIG_USER_ONLY) += user_only_helper.o
obj-y += gdbstub.o
+obj-$(TARGET_PPC64) += ../../libxz/
--
2.21.0
^ permalink raw reply related [flat|nested] 18+ messages in thread* [PATCH 5/5] ppc/pnv: Read the PNOR partition table
2019-10-21 13:12 [PATCH 0/5] ppc/pnv: Add PNOR support Cédric Le Goater
` (3 preceding siblings ...)
2019-10-21 13:12 ` [PATCH 4/5] libxz: Add XZ Embedded library for PPC Cédric Le Goater
@ 2019-10-21 13:12 ` Cédric Le Goater
2019-10-21 21:17 ` [PATCH 0/5] ppc/pnv: Add PNOR support no-reply
5 siblings, 0 replies; 18+ messages in thread
From: Cédric Le Goater @ 2019-10-21 13:12 UTC (permalink / raw)
To: David Gibson
Cc: qemu-devel, Greg Kurz, Cédric Le Goater, qemu-ppc,
Joel Stanley, Marty E . Plummer, Cédric Le Goater
From: Cédric Le Goater <clg@fr.ibm.com>
This patch adds the logic to read the partition table of a PNOR file
and a routine to load the PAYLOAD (skiboot) partition in the machine
memory.
Code based on the libflash of skiboot:
https://github.com/open-power/skiboot/blob/master/libflash/
Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
include/hw/ppc/ffs.h | 150 ++++++++++++++++++++++++++++++++++++
include/hw/ppc/pnv_pnor.h | 6 ++
hw/ppc/pnv.c | 33 +++++---
hw/ppc/pnv_pnor.c | 156 ++++++++++++++++++++++++++++++++++++++
4 files changed, 334 insertions(+), 11 deletions(-)
create mode 100644 include/hw/ppc/ffs.h
diff --git a/include/hw/ppc/ffs.h b/include/hw/ppc/ffs.h
new file mode 100644
index 000000000000..15216cf2389b
--- /dev/null
+++ b/include/hw/ppc/ffs.h
@@ -0,0 +1,150 @@
+/*
+ * Copyright 2013-2014 IBM Corp.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ * implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+/*
+ * Copyright (c) International Business Machines Corp., 2012
+ *
+ * FSP Flash Structure
+ *
+ * This header defines the layout for the FSP Flash Structure.
+ */
+
+#ifndef FFS_H
+#define FFS_H
+
+#include <stdint.h>
+
+/* The version of this partition implementation */
+#define FFS_VERSION_1 1
+
+/* Magic number for the partition header (ASCII 'PART') */
+#define FFS_MAGIC 0x50415254
+
+/* The maximum length of the partition name */
+#define PART_NAME_MAX 15
+
+/*
+ * Sizes of the data structures
+ */
+#define FFS_HDR_SIZE sizeof(struct ffs_hdr)
+#define FFS_ENTRY_SIZE sizeof(struct ffs_entry)
+
+/*
+ * Sizes of the data structures w/o checksum
+ */
+#define FFS_HDR_SIZE_CSUM (FFS_HDR_SIZE - sizeof(uint32_t))
+#define FFS_ENTRY_SIZE_CSUM (FFS_ENTRY_SIZE - sizeof(uint32_t))
+
+/* pid of logical partitions/containers */
+#define FFS_PID_TOPLEVEL 0xFFFFFFFF
+
+/*
+ * Type of image contained w/in partition
+ */
+enum type {
+ FFS_TYPE_DATA = 1,
+ FFS_TYPE_LOGICAL = 2,
+ FFS_TYPE_PARTITION = 3,
+};
+
+/*
+ * Flag bit definitions
+ */
+#define FFS_FLAGS_PROTECTED 0x0001
+#define FFS_FLAGS_U_BOOT_ENV 0x0002
+
+/* Data integrity flags */
+#define FFS_ENRY_INTEG_ECC 0x8000
+
+/**
+ * struct ffs_entry_user - User data enties
+ *
+ * @chip: Chip Select (0,1)
+ * @compressType: Compression Indication/alg (0=not compressed)
+ * @dataInteg: Indicates Data Integrity mechanism
+ * @verCheck: Indicates Version check type
+ * @miscFlags: Misc Partition related Flags
+ * @freeMisc[2]: Unused Miscellaneious Info
+ * @freeUser[14]: Unused User Data
+ */
+struct ffs_entry_user {
+ uint8_t chip;
+ uint8_t compresstype;
+ uint16_t datainteg;
+ uint8_t vercheck;
+ uint8_t miscflags;
+ uint8_t freemisc[2];
+ uint32_t reserved[14];
+};
+
+/**
+ * struct ffs_entry - Partition entry
+ *
+ * @name: Opaque null terminated string
+ * @base: Starting offset of partition in flash (in hdr.block_size)
+ * @size: Partition size (in hdr.block_size)
+ * @pid: Parent partition entry (FFS_PID_TOPLEVEL for toplevel)
+ * @id: Partition entry ID [1..65536]
+ * @type: Describe type of partition
+ * @flags: Partition attributes (optional)
+ * @actual: Actual partition size (in bytes)
+ * @resvd: Reserved words for future use
+ * @user: User data (optional)
+ * @checksum: Partition entry checksum (includes all above)
+ */
+struct ffs_entry {
+ char name[PART_NAME_MAX + 1];
+ uint32_t base;
+ uint32_t size;
+ uint32_t pid;
+ uint32_t id;
+ uint32_t type;
+ uint32_t flags;
+ uint32_t actual;
+ uint32_t resvd[4];
+ struct ffs_entry_user user;
+ uint32_t checksum;
+} __attribute__ ((packed));
+
+/**
+ * struct ffs_hdr - FSP Flash Structure header
+ *
+ * @magic: Eye catcher/corruption detector
+ * @version: Version of the structure
+ * @size: Size of partition table (in block_size)
+ * @entry_size: Size of struct ffs_entry element (in bytes)
+ * @entry_count: Number of struct ffs_entry elements in @entries array
+ * @block_size: Size of block on device (in bytes)
+ * @block_count: Number of blocks on device
+ * @resvd: Reserved words for future use
+ * @checksum: Header checksum
+ * @entries: Pointer to array of partition entries
+ */
+struct ffs_hdr {
+ uint32_t magic;
+ uint32_t version;
+ uint32_t size;
+ uint32_t entry_size;
+ uint32_t entry_count;
+ uint32_t block_size;
+ uint32_t block_count;
+ uint32_t resvd[4];
+ uint32_t checksum;
+ struct ffs_entry entries[];
+} __attribute__ ((packed));
+
+
+#endif /* FFS_H */
diff --git a/include/hw/ppc/pnv_pnor.h b/include/hw/ppc/pnv_pnor.h
index c3dd28643cae..14ec06038f3e 100644
--- a/include/hw/ppc/pnv_pnor.h
+++ b/include/hw/ppc/pnv_pnor.h
@@ -25,6 +25,12 @@ typedef struct PnvPnor {
uint8_t *storage;
uint32_t size;
MemoryRegion mmio;
+
+ uint32_t skiboot_addr;
+ uint32_t skiboot_size;
} PnvPnor;
+extern int pnv_pnor_load_skiboot(PnvPnor *pnor, hwaddr addr, size_t max_size,
+ Error **errp);
+
#endif /* _PPC_PNV_PNOR_H */
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 7019273f1cdd..8cc792dee25d 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -637,6 +637,7 @@ static void pnv_init(MachineState *machine)
char *chip_typename;
DriveInfo *pnor = drive_get(IF_MTD, 0, 0);
DeviceState *dev;
+ bool load_skiboot_from_pnor = false;
/* allocate RAM */
if (machine->ram_size < (1 * GiB)) {
@@ -659,23 +660,33 @@ static void pnv_init(MachineState *machine)
qdev_init_nofail(dev);
pnv->pnor = PNV_PNOR(dev);
- /* load skiboot firmware */
+ /*
+ * Try to load skiboot from pnor if no 'bios' was provided on the
+ * command line. skiboot will load the kernel and initramfs from
+ * the PNOR.
+ */
if (bios_name == NULL) {
bios_name = FW_FILE_NAME;
+ load_skiboot_from_pnor = !!pnor;
}
- fw_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
- if (!fw_filename) {
- error_report("Could not find OPAL firmware '%s'", bios_name);
- exit(1);
- }
+ if (load_skiboot_from_pnor) {
+ pnv_pnor_load_skiboot(pnv->pnor, FW_LOAD_ADDR, FW_MAX_SIZE,
+ &error_fatal);
+ } else {
+ fw_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
+ if (!fw_filename) {
+ error_report("Could not find OPAL firmware '%s'", bios_name);
+ exit(1);
+ }
- fw_size = load_image_targphys(fw_filename, FW_LOAD_ADDR, FW_MAX_SIZE);
- if (fw_size < 0) {
- error_report("Could not load OPAL firmware '%s'", fw_filename);
- exit(1);
+ fw_size = load_image_targphys(fw_filename, FW_LOAD_ADDR, FW_MAX_SIZE);
+ if (fw_size < 0) {
+ error_report("Could not load OPAL firmware '%s'", fw_filename);
+ exit(1);
+ }
+ g_free(fw_filename);
}
- g_free(fw_filename);
/* load kernel */
if (machine->kernel_filename) {
diff --git a/hw/ppc/pnv_pnor.c b/hw/ppc/pnv_pnor.c
index bfb1e92b0392..c29bf7eea197 100644
--- a/hw/ppc/pnv_pnor.c
+++ b/hw/ppc/pnv_pnor.c
@@ -14,8 +14,161 @@
#include "sysemu/block-backend.h"
#include "sysemu/blockdev.h"
#include "hw/loader.h"
+#include "hw/ppc/ffs.h"
#include "hw/ppc/pnv_pnor.h"
#include "hw/qdev-properties.h"
+#include "libxz/xz.h"
+
+static uint32_t ffs_checksum(void *data, size_t size)
+{
+ uint32_t i, csum = 0;
+
+ for (i = csum = 0; i < (size / 4); i++) {
+ csum ^= ((uint32_t *)data)[i];
+ }
+ return csum;
+}
+
+static int ffs_check_convert_header(struct ffs_hdr *dst, struct ffs_hdr *src)
+{
+ dst->magic = be32_to_cpu(src->magic);
+ if (dst->magic != FFS_MAGIC) {
+ return -1;
+ }
+ dst->version = be32_to_cpu(src->version);
+ if (dst->version != FFS_VERSION_1) {
+ return -1;
+ }
+ if (ffs_checksum(src, FFS_HDR_SIZE) != 0) {
+ return -1;
+ }
+ dst->size = be32_to_cpu(src->size);
+ dst->entry_size = be32_to_cpu(src->entry_size);
+ dst->entry_count = be32_to_cpu(src->entry_count);
+ dst->block_size = be32_to_cpu(src->block_size);
+ dst->block_count = be32_to_cpu(src->block_count);
+
+ return 0;
+}
+
+static int ffs_check_convert_entry(struct ffs_entry *dst, struct ffs_entry *src)
+{
+ if (ffs_checksum(src, FFS_ENTRY_SIZE) != 0) {
+ return -1;
+ }
+
+ memcpy(dst->name, src->name, sizeof(dst->name));
+ dst->base = be32_to_cpu(src->base);
+ dst->size = be32_to_cpu(src->size);
+ dst->pid = be32_to_cpu(src->pid);
+ dst->id = be32_to_cpu(src->id);
+ dst->type = be32_to_cpu(src->type);
+ dst->flags = be32_to_cpu(src->flags);
+ dst->actual = be32_to_cpu(src->actual);
+ dst->user.datainteg = be16_to_cpu(src->user.datainteg);
+
+ return 0;
+}
+
+static int decompress(void *dst, size_t dst_size, void *src, size_t src_size,
+ Error **errp)
+{
+ struct xz_dec *s;
+ struct xz_buf b;
+ int ret = 0;
+
+ /* Initialize the xz library first */
+ xz_crc32_init();
+ s = xz_dec_init(XZ_SINGLE, 0);
+ if (!s) {
+ error_report("failed to initialize xz");
+ return -1;
+ }
+
+ b.in = src;
+ b.in_pos = 0;
+ b.in_size = src_size;
+ b.out = dst;
+ b.out_pos = 0;
+ b.out_size = dst_size;
+
+ /* Start decompressing */
+ ret = xz_dec_run(s, &b);
+ if (ret != XZ_STREAM_END) {
+ error_setg(errp, "failed to decompress : %d", ret);
+ ret = -1;
+ } else {
+ ret = 0;
+ }
+
+ /* Clean up memory */
+ xz_dec_end(s);
+ return ret;
+}
+
+int pnv_pnor_load_skiboot(PnvPnor *s, hwaddr addr, size_t max_size,
+ Error **errp)
+{
+ int rc;
+ void *buffer = g_malloc0(max_size);
+
+ rc = decompress(buffer, max_size, &s->storage[s->skiboot_addr],
+ s->skiboot_size, errp);
+ if (rc == 0) {
+ rom_add_blob_fixed("pnor.skiboot", buffer, max_size, addr);
+ }
+ g_free(buffer);
+ return rc;
+}
+
+#define SECUREBOOT_HEADER_MAGIC 0x17082011
+#define SECUREBOOT_HEADER_SIZE 4096
+
+static void pnv_pnor_find_skiboot(PnvPnor *s, Error **errp)
+{
+ uint8_t *storage = s->storage;
+ struct ffs_hdr hdr;
+ struct ffs_entry ent;
+ uint32_t magic;
+ uint32_t i;
+ int rc;
+
+ rc = ffs_check_convert_header(&hdr, (struct ffs_hdr *) storage);
+ if (rc) {
+ error_setg(errp, "bad header");
+ return;
+ }
+
+ for (i = 0; i < hdr.entry_count; i++) {
+ uint32_t esize = hdr.entry_size;
+ uint32_t offset = FFS_HDR_SIZE + i * esize;
+ struct ffs_entry *src_ent = (struct ffs_entry *)(storage + offset);
+
+ rc = ffs_check_convert_entry(&ent, src_ent);
+ if (rc) {
+ error_report("bad partition entry %d", i);
+ continue;
+ }
+
+ if (strcmp("PAYLOAD", ent.name)) {
+ continue;
+ }
+
+ s->skiboot_addr = ent.base * 0x1000,
+ s->skiboot_size = ent.size * 0x1000;
+
+ /* Check for secure boot header */
+ magic = be32_to_cpu(*(uint32_t *)&s->storage[s->skiboot_addr]);
+ if (magic == SECUREBOOT_HEADER_MAGIC) {
+ s->skiboot_addr += SECUREBOOT_HEADER_SIZE;
+ s->skiboot_size -= SECUREBOOT_HEADER_SIZE;
+ }
+
+ return;
+ }
+
+ error_setg(errp, "pnv_pnor: no skiboot partition !?");
+}
static uint64_t pnv_pnor_read(void *opaque, hwaddr addr, unsigned size)
{
@@ -97,6 +250,9 @@ static void pnv_pnor_realize(DeviceState *dev, Error **errp)
error_setg(errp, "failed to read the initial flash content");
return;
}
+
+ /* Read partitions to validate contents */
+ pnv_pnor_find_skiboot(s, errp);
} else {
s->storage = blk_blockalign(NULL, s->size);
memset(s->storage, 0xFF, s->size);
--
2.21.0
^ permalink raw reply related [flat|nested] 18+ messages in thread