unxz: update from XZ embedded git

function                                             old     new   delta
rc_reset                                               -      21     +21
unpack_xz_stream                                    2342    2357     +15
lzma_reset                                           102      64     -38
lzma_len                                             506     443     -63
xz_dec_lzma2_run                                    1438    1374     -64
xz_dec_reset                                          73       -     -73
lzma_main                                           2517    2183    -334
------------------------------------------------------------------------------
(add/remove: 1/1 grow/shrink: 1/4 up/down: 36/-572)          Total: -536 bytes

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

4 files changed, 253 insertions, 144 deletions

diff --git a/archival/libunarchive/unxz/xz.h b/archival/libunarchive/unxz/xz.h
index eb82706..c6c071c 100644
--- a/archival/libunarchive/unxz/xz.h
+++ b/archival/libunarchive/unxz/xz.h
@@ -30,9 +30,42 @@
 #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.
+ *                          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
@@ -42,8 +75,17 @@
  *                          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_MEMLIMIT_ERROR:      Not enough memory was preallocated at decoder
- *                          initialization 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
@@ -72,6 +114,7 @@ enum xz_ret {
 	XZ_OK,
 	XZ_STREAM_END,
 	XZ_UNSUPPORTED_CHECK,
+	XZ_MEM_ERROR,
 	XZ_MEMLIMIT_ERROR,
 	XZ_FORMAT_ERROR,
 	XZ_OPTIONS_ERROR,
@@ -112,61 +155,67 @@ 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, or special value of zero to indicate
- *              single-call decoding mode.
- *
- * If dict_max > 0, the decoder is initialized to work in multi-call mode.
- * dict_max number of 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.
- *
- * LZMA2 dictionary is always 2^n bytes or 2^n + 2^(n-1) bytes (the latter
- * sizes are less common in practice). In the kernel, dictionary sizes of
- * 64 KiB, 128 KiB, 256 KiB, 512 KiB, and 1 MiB are probably the only
- * reasonable values.
- *
- * If dict_max == 0, the decoder is initialized to work in single-call mode.
- * In single-call mode, 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.
+ *              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. It is enough that the
- * output buffer is big enough to hold the actual uncompressed data; it
+ * 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(). On error, xz_dec_init() returns NULL.
+ * ready to be used with xz_dec_run(). If memory allocation fails,
+ * xz_dec_init() returns NULL.
  */
-XZ_EXTERN struct xz_dec * XZ_FUNC xz_dec_init(uint32_t dict_max);
+XZ_EXTERN struct xz_dec * XZ_FUNC 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
  *
- * In multi-call mode, this function may return any of the values listed in
- * enum xz_ret.
- *
- * In single-call mode, this function never returns XZ_OK. 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.
- *
- * NOTE: In single-call mode, the contents of the output buffer are undefined
- * also after XZ_BUF_ERROR. This is 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.
+ * The possible return values depend on build options and operation mode.
+ * See enum xz_ret for details.
+ *
+ * NOTE: 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_FUNC xz_dec_run(struct xz_dec *s, struct xz_buf *b);
 
diff --git a/archival/libunarchive/unxz/xz_dec_lzma2.c b/archival/libunarchive/unxz/xz_dec_lzma2.c
index 37de6fc..da71cb4 100644
--- a/archival/libunarchive/unxz/xz_dec_lzma2.c
+++ b/archival/libunarchive/unxz/xz_dec_lzma2.c
@@ -34,7 +34,8 @@
  *
  * In multi-call mode, also these are true:
  *    end == size
- *    size <= allocated
+ *    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
@@ -74,11 +75,20 @@ struct dictionary {
 	uint32_t size;
 
 	/*
-	 * Amount of memory allocated for the dictionary. A special
-	 * value of zero indicates that we are in single-call mode,
-	 * where the output buffer works as the dictionary.
+	 * 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 */
@@ -120,31 +130,31 @@ struct lzma_len_dec {
 };
 
 struct lzma_dec {
-	/*
-	 * 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 */
-
-	/* Types of the most recently seen LZMA symbols */
-	enum lzma_state state;
-
 	/* 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];
 
@@ -201,49 +211,59 @@ struct lzma_dec {
 	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 {
-	/* LZMA2 */
-	struct {
-		/* 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;
-	} 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
@@ -253,10 +273,6 @@ struct xz_dec_lzma2 {
 		uint32_t size;
 		uint8_t buf[3 * LZMA_IN_REQUIRED];
 	} temp;
-
-	struct dictionary dict;
-	struct rc_dec rc;
-	struct lzma_dec lzma;
 };
 
 /**************
@@ -269,7 +285,7 @@ struct xz_dec_lzma2 {
  */
 static void XZ_FUNC dict_reset(struct dictionary *dict, struct xz_buf *b)
 {
-	if (dict->allocated == 0) {
+	if (DEC_IS_SINGLE(dict->mode)) {
 		dict->buf = b->out + b->out_pos;
 		dict->end = b->out_size - b->out_pos;
 	}
@@ -379,7 +395,7 @@ static void XZ_FUNC dict_uncompressed(
 		if (dict->full < dict->pos)
 			dict->full = dict->pos;
 
-		if (dict->allocated != 0) {
+		if (DEC_IS_MULTI(dict->mode)) {
 			if (dict->pos == dict->end)
 				dict->pos = 0;
 
@@ -404,7 +420,7 @@ static uint32_t XZ_FUNC dict_flush(struct dictionary *dict, struct xz_buf *b)
 {
 	size_t copy_size = dict->pos - dict->start;
 
-	if (dict->allocated != 0) {
+	if (DEC_IS_MULTI(dict->mode)) {
 		if (dict->pos == dict->end)
 			dict->pos = 0;
 
@@ -422,7 +438,7 @@ static uint32_t XZ_FUNC dict_flush(struct dictionary *dict, struct xz_buf *b)
  *****************/
 
 /* Reset the range decoder. */
-static __always_inline void XZ_FUNC rc_reset(struct rc_dec *rc)
+static void XZ_FUNC rc_reset(struct rc_dec *rc)
 {
 	rc->range = (uint32_t)-1;
 	rc->code = 0;
@@ -1088,28 +1104,27 @@ XZ_EXTERN NOINLINE enum xz_ret XZ_FUNC xz_dec_lzma2_run(
 	return XZ_OK;
 }
 
-XZ_EXTERN struct xz_dec_lzma2 * XZ_FUNC xz_dec_lzma2_create(uint32_t dict_max)
+XZ_EXTERN struct xz_dec_lzma2 * XZ_FUNC xz_dec_lzma2_create(
+		enum xz_mode mode, uint32_t dict_max)
 {
-	struct xz_dec_lzma2 *s;
-
-	/* Maximum supported dictionary by this implementation is 3 GiB. */
-	if (dict_max > ((uint32_t)3 << 30))
-		return NULL;
-
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	struct xz_dec_lzma2 *s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (s == NULL)
 		return NULL;
 
-	if (dict_max > 0) {
+	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;
 	}
 
-	s->dict.allocated = dict_max;
-
 	return s;
 }
 
@@ -1123,18 +1138,23 @@ XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_lzma2_reset(
 	s->dict.size = 2 + (props & 1);
 	s->dict.size <<= (props >> 1) + 11;
 
-	if (s->dict.allocated > 0 && s->dict.allocated < s->dict.size) {
-#ifdef XZ_REALLOC_DICT_BUF
-		s->dict.buf = XZ_REALLOC_DICT_BUF(s->dict.buf, s->dict.size);
-			if (!s->dict.buf)
-				return XZ_MEMLIMIT_ERROR;
-		s->dict.allocated = s->dict.size;
-#else
-		return XZ_MEMLIMIT_ERROR;
-#endif
-	}
+	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;
+		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;
 
@@ -1148,7 +1168,7 @@ XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_lzma2_reset(
 
 XZ_EXTERN void XZ_FUNC xz_dec_lzma2_end(struct xz_dec_lzma2 *s)
 {
-	if (s->dict.allocated > 0)
+	if (DEC_IS_MULTI(s->dict.mode))
 		vfree(s->dict.buf);
 
 	kfree(s);
diff --git a/archival/libunarchive/unxz/xz_dec_stream.c b/archival/libunarchive/unxz/xz_dec_stream.c
index 21db283..bdcbf1b 100644
--- a/archival/libunarchive/unxz/xz_dec_stream.c
+++ b/archival/libunarchive/unxz/xz_dec_stream.c
@@ -48,8 +48,8 @@ struct xz_dec {
 	/* Type of the integrity check calculated from uncompressed data */
 	enum xz_check check_type;
 
-	/* True if we are operating in single-call mode. */
-	bool single_call;
+	/* Operation mode */
+	enum xz_mode mode;
 
 	/*
 	 * True if the next call to xz_dec_run() is allowed to return
@@ -737,14 +737,14 @@ XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_run(struct xz_dec *s, struct xz_buf *b)
 	size_t out_start;
 	enum xz_ret ret;
 
-	if (s->single_call)
+	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 (s->single_call) {
+	if (DEC_IS_SINGLE(s->mode)) {
 		if (ret == XZ_OK)
 			ret = b->in_pos == b->in_size
 					? XZ_DATA_ERROR : XZ_BUF_ERROR;
@@ -767,21 +767,22 @@ XZ_EXTERN enum xz_ret XZ_FUNC xz_dec_run(struct xz_dec *s, struct xz_buf *b)
 	return ret;
 }
 
-XZ_EXTERN struct xz_dec * XZ_FUNC xz_dec_init(uint32_t dict_max)
+XZ_EXTERN struct xz_dec * XZ_FUNC 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->single_call = dict_max == 0;
+	s->mode = mode;
 
 #ifdef XZ_DEC_BCJ
-	s->bcj = xz_dec_bcj_create(s->single_call);
+	s->bcj = xz_dec_bcj_create(DEC_IS_SINGLE(mode));
 	if (s->bcj == NULL)
 		goto error_bcj;
 #endif
 
-	s->lzma2 = xz_dec_lzma2_create(dict_max);
+	s->lzma2 = xz_dec_lzma2_create(mode, dict_max);
 	if (s->lzma2 == NULL)
 		goto error_lzma2;
 
diff --git a/archival/libunarchive/unxz/xz_private.h b/archival/libunarchive/unxz/xz_private.h
index f4e0b40..145649a 100644
--- a/archival/libunarchive/unxz/xz_private.h
+++ b/archival/libunarchive/unxz/xz_private.h
@@ -53,6 +53,45 @@
 #	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.
@@ -71,7 +110,7 @@
  * before calling xz_dec_lzma2_run().
  */
 XZ_EXTERN struct xz_dec_lzma2 * XZ_FUNC xz_dec_lzma2_create(
-		uint32_t dict_max);
+		enum xz_mode mode, uint32_t dict_max);
 
 /*
  * Decode the LZMA2 properties (one byte) and reset the decoder. Return