Add support for NSO parsing + decompression.

Makefile

@@ -13,7 +13,7 @@ all:
 .c.o:
 	$(CC) $(INCLUDE) -c $(CFLAGS) -o $@ $<
 
-hactool: sha.o aes.o extkeys.o rsa.o npdm.o bktr.o kip.o packages.o pki.o pfs0.o hfs0.o nca0_romfs.o romfs.o utils.o nax0.o nca.o xci.o main.o filepath.o ConvertUTF.o cJSON.o
+hactool: sha.o aes.o extkeys.o rsa.o npdm.o bktr.o kip.o packages.o pki.o pfs0.o hfs0.o nca0_romfs.o romfs.o utils.o nax0.o nso.o lz4.o nca.o xci.o main.o filepath.o ConvertUTF.o cJSON.o
 	$(CC) -o $@ $^ $(LDFLAGS) -L $(LIBDIR)
 
 aes.o: aes.h types.h
@@ -28,6 +28,8 @@ hfs0.o: hfs0.h types.h
 
 kip.o: kip.h types.h
 
+lz4.o: lz4.h
+
 main.o: main.c pki.h types.h
 
 packages.o: packages.h aes.h kip.h types.h
@@ -42,6 +44,8 @@ nca.o: nca.h aes.h sha.h rsa.h bktr.h filepath.h types.h
 
 npdm.o: npdm.c cJSON.h types.h
 
+nso.o: nso.h types.h
+
 romfs.o: ivfc.h types.h
 
 nca0_romfs.o: nca0_romfs.h ivfc.h types.h

lz4.h

@@ -0,0 +1,569 @@
+/*
+ *  LZ4 - Fast LZ compression algorithm
+ *  Header File
+ *  Copyright (C) 2011-2017, Yann Collet.
+
+   BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+   Redistribution and use in source and binary forms, with or without
+   modification, are permitted provided that the following conditions are
+   met:
+
+       * Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+       * Redistributions in binary form must reproduce the above
+   copyright notice, this list of conditions and the following disclaimer
+   in the documentation and/or other materials provided with the
+   distribution.
+
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+   You can contact the author at :
+    - LZ4 homepage : http://www.lz4.org
+    - LZ4 source repository : https://github.com/lz4/lz4
+*/
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+#ifndef LZ4_H_2983827168210
+#define LZ4_H_2983827168210
+
+/* --- Dependency --- */
+#include <stddef.h>   /* size_t */
+
+
+/**
+  Introduction
+
+  LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core,
+  scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
+  multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
+
+  The LZ4 compression library provides in-memory compression and decompression functions.
+  Compression can be done in:
+    - a single step (described as Simple Functions)
+    - a single step, reusing a context (described in Advanced Functions)
+    - unbounded multiple steps (described as Streaming compression)
+
+  lz4.h provides block compression functions. It gives full buffer control to user.
+  Decompressing an lz4-compressed block also requires metadata (such as compressed size).
+  Each application is free to encode such metadata in whichever way it wants.
+
+  An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md),
+  take care of encoding standard metadata alongside LZ4-compressed blocks.
+  If your application requires interoperability, it's recommended to use it.
+  A library is provided to take care of it, see lz4frame.h.
+*/
+
+/*^***************************************************************
+*  Export parameters
+*****************************************************************/
+/*
+*  LZ4_DLL_EXPORT :
+*  Enable exporting of functions when building a Windows DLL
+*  LZ4LIB_VISIBILITY :
+*  Control library symbols visibility.
+*/
+#ifndef LZ4LIB_VISIBILITY
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default")))
+#  else
+#    define LZ4LIB_VISIBILITY
+#  endif
+#endif
+#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1)
+#  define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY
+#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1)
+#  define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+#  define LZ4LIB_API LZ4LIB_VISIBILITY
+#endif
+
+/*------   Version   ------*/
+#define LZ4_VERSION_MAJOR    1    /* for breaking interface changes  */
+#define LZ4_VERSION_MINOR    8    /* for new (non-breaking) interface capabilities */
+#define LZ4_VERSION_RELEASE  2    /* for tweaks, bug-fixes, or development */
+
+#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
+
+#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
+#define LZ4_QUOTE(str) #str
+#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
+#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
+
+LZ4LIB_API int LZ4_versionNumber (void);  /**< library version number; useful to check dll version */
+LZ4LIB_API const char* LZ4_versionString (void);   /**< library version string; unseful to check dll version */
+
+
+/*-************************************
+*  Tuning parameter
+**************************************/
+/*!
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio
+ * Reduced memory usage may improve speed, thanks to cache effect
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
+ */
+#ifndef LZ4_MEMORY_USAGE
+# define LZ4_MEMORY_USAGE 14
+#endif
+
+/*-************************************
+*  Simple Functions
+**************************************/
+/*! LZ4_compress_default() :
+    Compresses 'srcSize' bytes from buffer 'src'
+    into already allocated 'dst' buffer of size 'dstCapacity'.
+    Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
+    It also runs faster, so it's a recommended setting.
+    If the function cannot compress 'src' into a more limited 'dst' budget,
+    compression stops *immediately*, and the function result is zero.
+    Note : as a consequence, 'dst' content is not valid.
+    Note 2 : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
+        srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
+        dstCapacity : size of buffer 'dst' (which must be already allocated)
+        return  : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
+                  or 0 if compression fails */
+LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
+
+/*! LZ4_decompress_safe() :
+    compressedSize : is the exact complete size of the compressed block.
+    dstCapacity : is the size of destination buffer, which must be already allocated.
+    return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
+             If destination buffer is not large enough, decoding will stop and output an error code (negative value).
+             If the source stream is detected malformed, the function will stop decoding and return a negative result.
+             This function is protected against malicious data packets.
+*/
+LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
+
+
+/*-************************************
+*  Advanced Functions
+**************************************/
+#define LZ4_MAX_INPUT_SIZE        0x7E000000   /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize)  ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
+
+/*!
+LZ4_compressBound() :
+    Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
+    This function is primarily useful for memory allocation purposes (destination buffer size).
+    Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
+    Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
+        inputSize  : max supported value is LZ4_MAX_INPUT_SIZE
+        return : maximum output size in a "worst case" scenario
+              or 0, if input size is incorrect (too large or negative)
+*/
+LZ4LIB_API int LZ4_compressBound(int inputSize);
+
+/*!
+LZ4_compress_fast() :
+    Same as LZ4_compress_default(), but allows selection of "acceleration" factor.
+    The larger the acceleration value, the faster the algorithm, but also the lesser the compression.
+    It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed.
+    An acceleration value of "1" is the same as regular LZ4_compress_default()
+    Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c).
+*/
+LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+
+/*!
+LZ4_compress_fast_extState() :
+    Same compression function, just using an externally allocated memory space to store compression state.
+    Use LZ4_sizeofState() to know how much memory must be allocated,
+    and allocate it on 8-bytes boundaries (using malloc() typically).
+    Then, provide it as 'void* state' to compression function.
+*/
+LZ4LIB_API int LZ4_sizeofState(void);
+LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+
+/*!
+LZ4_compress_destSize() :
+    Reverse the logic : compresses as much data as possible from 'src' buffer
+    into already allocated buffer 'dst' of size 'targetDestSize'.
+    This function either compresses the entire 'src' content into 'dst' if it's large enough,
+    or fill 'dst' buffer completely with as much data as possible from 'src'.
+        *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'.
+                      New value is necessarily <= old value.
+        return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
+                 or 0 if compression fails
+*/
+LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
+
+
+/*!
+LZ4_decompress_fast() : **unsafe!**
+This function is a bit faster than LZ4_decompress_safe(),
+but doesn't provide any security guarantee.
+    originalSize : is the uncompressed size to regenerate
+                   Destination buffer must be already allocated, and its size must be >= 'originalSize' bytes.
+    return : number of bytes read from source buffer (== compressed size).
+             If the source stream is detected malformed, the function stops decoding and return a negative result.
+    note : This function respects memory boundaries for *properly formed* compressed data.
+           However, it does not provide any protection against malicious input.
+           It also doesn't know 'src' size, and implies it's >= compressed size.
+           Use this function in trusted environment **only**.
+*/
+LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
+
+/*!
+LZ4_decompress_safe_partial() :
+    This function decompress a compressed block of size 'srcSize' at position 'src'
+    into destination buffer 'dst' of size 'dstCapacity'.
+    The function will decompress a minimum of 'targetOutputSize' bytes, and stop after that.
+    However, it's not accurate, and may write more than 'targetOutputSize' (but always <= dstCapacity).
+   @return : the number of bytes decoded in the destination buffer (necessarily <= dstCapacity)
+        Note : this number can also be < targetOutputSize, if compressed block contains less data.
+            Therefore, always control how many bytes were decoded.
+            If source stream is detected malformed, function returns a negative result.
+            This function is protected against malicious data packets.
+*/
+LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity);
+
+
+/*-*********************************************
+*  Streaming Compression Functions
+***********************************************/
+typedef union LZ4_stream_u LZ4_stream_t;  /* incomplete type (defined later) */
+
+/*! LZ4_createStream() and LZ4_freeStream() :
+ *  LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure.
+ *  LZ4_freeStream() releases its memory.
+ */
+LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
+LZ4LIB_API int           LZ4_freeStream (LZ4_stream_t* streamPtr);
+
+/*! LZ4_resetStream() :
+ *  An LZ4_stream_t structure can be allocated once and re-used multiple times.
+ *  Use this function to start compressing a new stream.
+ */
+LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
+
+/*! LZ4_loadDict() :
+ *  Use this function to load a static dictionary into LZ4_stream_t.
+ *  Any previous data will be forgotten, only 'dictionary' will remain in memory.
+ *  Loading a size of 0 is allowed, and is the same as reset.
+ * @return : dictionary size, in bytes (necessarily <= 64 KB)
+ */
+LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
+
+/*! LZ4_compress_fast_continue() :
+ *  Compress 'src' content using data from previously compressed blocks, for better compression ratio.
+ *  'dst' buffer must be already allocated.
+ *  If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster.
+ *
+ *  Important : The previous 64KB of compressed data is assumed to remain present and unmodified in memory!
+ *
+ *  Special 1 : When input is a double-buffer, they can have any size, including < 64 KB.
+ *              Make sure that buffers are separated by at least one byte.
+ *              This way, each block only depends on previous block.
+ *  Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
+ *
+ * @return : size of compressed block
+ *           or 0 if there is an error (typically, cannot fit into 'dst').
+ *  After an error, the stream status is invalid, it can only be reset or freed.
+ */
+LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*! LZ4_saveDict() :
+ *  If last 64KB data cannot be guaranteed to remain available at its current memory location,
+ *  save it into a safer place (char* safeBuffer).
+ *  This is schematically equivalent to a memcpy() followed by LZ4_loadDict(),
+ *  but is much faster, because LZ4_saveDict() doesn't need to rebuild tables.
+ * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error.
+ */
+LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize);
+
+
+/*-**********************************************
+*  Streaming Decompression Functions
+*  Bufferless synchronous API
+************************************************/
+typedef union LZ4_streamDecode_u LZ4_streamDecode_t;   /* incomplete type (defined later) */
+
+/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
+ *  creation / destruction of streaming decompression tracking structure.
+ *  A tracking structure can be re-used multiple times sequentially. */
+LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
+LZ4LIB_API int                 LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
+
+/*! LZ4_setStreamDecode() :
+ *  An LZ4_streamDecode_t structure can be allocated once and re-used multiple times.
+ *  Use this function to start decompression of a new stream of blocks.
+ *  A dictionary can optionnally be set. Use NULL or size 0 for a reset order.
+ * @return : 1 if OK, 0 if error
+ */
+LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
+
+/*! LZ4_decompress_*_continue() :
+ *  These decoding functions allow decompression of consecutive blocks in "streaming" mode.
+ *  A block is an unsplittable entity, it must be presented entirely to a decompression function.
+ *  Decompression functions only accept one block at a time.
+ *  The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded.
+ *  If less than 64KB of data has been decoded all the data must be present.
+ *
+ *  Special : if application sets a ring buffer for decompression, it must respect one of the following conditions :
+ *  - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions)
+ *    In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB).
+ *  - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
+ *    maxBlockSize is implementation dependent. It's the maximum size of any single block.
+ *    In which case, encoding and decoding buffers do not need to be synchronized,
+ *    and encoding ring buffer can have any size, including small ones ( < 64 KB).
+ *  - _At least_ 64 KB + 8 bytes + maxBlockSize.
+ *    In which case, encoding and decoding buffers do not need to be synchronized,
+ *    and encoding ring buffer can have any size, including larger than decoding buffer.
+ *  Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer,
+ *  and indicate where it is saved using LZ4_setStreamDecode() before decompressing next block.
+*/
+LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
+LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
+
+
+/*! LZ4_decompress_*_usingDict() :
+ *  These decoding functions work the same as
+ *  a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue()
+ *  They are stand-alone, and don't need an LZ4_streamDecode_t structure.
+ */
+LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
+LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
+
+
+/*^**********************************************
+ * !!!!!!   STATIC LINKING ONLY   !!!!!!
+ ***********************************************/
+
+/*-************************************
+ *  Unstable declarations
+ **************************************
+ * Declarations in this section should be considered unstable.
+ * Use at your own peril, etc., etc.
+ * They may be removed in the future.
+ * Their signatures may change.
+ **************************************/
+
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+/*! LZ4_resetStream_fast() :
+ *  When an LZ4_stream_t is known to be in a internally coherent state,
+ *  it can often be prepared for a new compression with almost no work, only
+ *  sometimes falling back to the full, expensive reset that is always required
+ *  when the stream is in an indeterminate state (i.e., the reset performed by
+ *  LZ4_resetStream()).
+ *
+ *  LZ4_streams are guaranteed to be in a valid state when:
+ *  - returned from LZ4_createStream()
+ *  - reset by LZ4_resetStream()
+ *  - memset(stream, 0, sizeof(LZ4_stream_t))
+ *  - the stream was in a valid state and was reset by LZ4_resetStream_fast()
+ *  - the stream was in a valid state and was then used in any compression call
+ *    that returned success
+ *  - the stream was in an indeterminate state and was used in a compression
+ *    call that fully reset the state (LZ4_compress_fast_extState()) and that
+ *    returned success
+ */
+LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
+
+/*! LZ4_compress_fast_extState_fastReset() :
+ *  A variant of LZ4_compress_fast_extState().
+ *
+ *  Using this variant avoids an expensive initialization step. It is only safe
+ *  to call if the state buffer is known to be correctly initialized already
+ *  (see above comment on LZ4_resetStream_fast() for a definition of "correctly
+ *  initialized"). From a high level, the difference is that this function
+ *  initializes the provided state with a call to LZ4_resetStream_fast() while
+ *  LZ4_compress_fast_extState() starts with a call to LZ4_resetStream().
+ */
+LZ4LIB_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*! LZ4_attach_dictionary() :
+ *  This is an experimental API that allows for the efficient use of a
+ *  static dictionary many times.
+ *
+ *  Rather than re-loading the dictionary buffer into a working context before
+ *  each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
+ *  working LZ4_stream_t, this function introduces a no-copy setup mechanism,
+ *  in which the working stream references the dictionary stream in-place.
+ *
+ *  Several assumptions are made about the state of the dictionary stream.
+ *  Currently, only streams which have been prepared by LZ4_loadDict() should
+ *  be expected to work.
+ *
+ *  Alternatively, the provided dictionary stream pointer may be NULL, in which
+ *  case any existing dictionary stream is unset.
+ *
+ *  If a dictionary is provided, it replaces any pre-existing stream history.
+ *  The dictionary contents are the only history that can be referenced and
+ *  logically immediately precede the data compressed in the first subsequent
+ *  compression call.
+ *
+ *  The dictionary will only remain attached to the working stream through the
+ *  first compression call, at the end of which it is cleared. The dictionary
+ *  stream (and source buffer) must remain in-place / accessible / unchanged
+ *  through the completion of the first compression call on the stream.
+ */
+LZ4LIB_API void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream);
+
+#endif
+
+/*-************************************
+ *  Private definitions
+ **************************************
+ * Do not use these definitions.
+ * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
+ * Using these definitions will expose code to API and/or ABI break in future versions of the library.
+ **************************************/
+#define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
+#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */
+
+#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
+#include <stdint.h>
+
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
+    uint32_t hashTable[LZ4_HASH_SIZE_U32];
+    uint32_t currentOffset;
+    uint16_t initCheck;
+    uint16_t tableType;
+    const uint8_t* dictionary;
+    const LZ4_stream_t_internal* dictCtx;
+    uint32_t dictSize;
+};
+
+typedef struct {
+    const uint8_t* externalDict;
+    size_t extDictSize;
+    const uint8_t* prefixEnd;
+    size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+#else
+
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
+    unsigned int hashTable[LZ4_HASH_SIZE_U32];
+    unsigned int currentOffset;
+    unsigned short initCheck;
+    unsigned short tableType;
+    const unsigned char* dictionary;
+    const LZ4_stream_t_internal* dictCtx;
+    unsigned int dictSize;
+};
+
+typedef struct {
+    const unsigned char* externalDict;
+    size_t extDictSize;
+    const unsigned char* prefixEnd;
+    size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+#endif
+
+/*!
+ * LZ4_stream_t :
+ * information structure to track an LZ4 stream.
+ * init this structure before first use.
+ * note : only use in association with static linking !
+ *        this definition is not API/ABI safe,
+ *        it may change in a future version !
+ */
+#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4)
+#define LZ4_STREAMSIZE     (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+union LZ4_stream_u {
+    unsigned long long table[LZ4_STREAMSIZE_U64];
+    LZ4_stream_t_internal internal_donotuse;
+} ;  /* previously typedef'd to LZ4_stream_t */
+
+
+/*!
+ * LZ4_streamDecode_t :
+ * information structure to track an LZ4 stream during decompression.
+ * init this structure  using LZ4_setStreamDecode (or memset()) before first use
+ * note : only use in association with static linking !
+ *        this definition is not API/ABI safe,
+ *        and may change in a future version !
+ */
+#define LZ4_STREAMDECODESIZE_U64  4
+#define LZ4_STREAMDECODESIZE     (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
+union LZ4_streamDecode_u {
+    unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+    LZ4_streamDecode_t_internal internal_donotuse;
+} ;   /* previously typedef'd to LZ4_streamDecode_t */
+
+
+/*-************************************
+*  Obsolete Functions
+**************************************/
+
+/*! Deprecation warnings
+   Should deprecation warnings be a problem,
+   it is generally possible to disable them,
+   typically with -Wno-deprecated-declarations for gcc
+   or _CRT_SECURE_NO_WARNINGS in Visual.
+   Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */
+#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS
+#  define LZ4_DEPRECATED(message)   /* disable deprecation warnings */
+#else
+#  define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+#  if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
+#    define LZ4_DEPRECATED(message) [[deprecated(message)]]
+#  elif (LZ4_GCC_VERSION >= 405) || defined(__clang__)
+#    define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
+#  elif (LZ4_GCC_VERSION >= 301)
+#    define LZ4_DEPRECATED(message) __attribute__((deprecated))
+#  elif defined(_MSC_VER)
+#    define LZ4_DEPRECATED(message) __declspec(deprecated(message))
+#  else
+#    pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler")
+#    define LZ4_DEPRECATED(message)
+#  endif
+#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
+
+/* Obsolete compression functions */
+LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress               (const char* source, char* dest, int sourceSize);
+LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState               (void* state, const char* source, char* dest, int inputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue                (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
+LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue  (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
+
+/* Obsolete decompression functions */
+LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
+LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
+
+/* Obsolete streaming functions; degraded functionality; do not use!
+ *
+ * In order to perform streaming compression, these functions depended on data
+ * that is no longer tracked in the state. They have been preserved as well as
+ * possible: using them will still produce a correct output. However, they don't
+ * actually retain any history between compression calls. The compression ratio
+ * achieved will therefore be no better than compressing each chunk
+ * independently.
+ */
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int   LZ4_sizeofStreamState(void);
+LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API  int   LZ4_resetStreamState(void* state, char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API     char* LZ4_slideInputBuffer (void* state);
+
+/* Obsolete streaming decoding functions */
+LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
+LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
+
+#endif /* LZ4_H_2983827168210 */
+
+
+#if defined (__cplusplus)
+}
+#endif

main.c

@@ -12,6 +12,7 @@
 #include "nax0.h"
 #include "extkeys.h"
 #include "packages.h"
+#include "nso.h"
 
 static char *prog_name = "hactool";
 
@@ -619,6 +620,20 @@ int main(int argc, char **argv) {
             }
             break;
         }
+        case FILETYPE_NSO0: {
+            nso0_ctx_t nso0_ctx;
+            memset(&nso0_ctx, 0, sizeof(nso0_ctx));
+            nso0_ctx.file = tool_ctx.file;
+            nso0_ctx.tool_ctx = &tool_ctx;
+            nso0_process(&nso0_ctx);
+            if (nso0_ctx.header) {
+                free(nso0_ctx.header);
+            }
+            if (nso0_ctx.uncompressed_header) {
+                free(nso0_ctx.uncompressed_header);
+            }
+            break;
+        }
         case FILETYPE_XCI: {
             xci_ctx_t xci_ctx;
             memset(&xci_ctx, 0, sizeof(xci_ctx));

nso.c

@@ -0,0 +1,126 @@
+#include <string.h>
+#include "nso.h"
+#include "lz4.h"
+#include "sha.h"
+
+void *nso_uncompress(nso0_ctx_t *ctx) {
+    /* Make new header with correct sizes, fixed flags. */
+    nso0_header_t new_header = *ctx->header;
+    for (unsigned int i = 0; i < 3; i++) {
+        new_header.segments[i].file_off = new_header.segments[i].dst_off + sizeof(nso0_header_t);
+        new_header.compressed_sizes[i] = new_header.segments[i].decomp_size;
+    }
+    /* Clear module offset/size. */
+    new_header.segments[0].align_or_total_size = 0x100;
+    new_header.segments[1].align_or_total_size = 0;
+    /* Clear compression flags. */
+    new_header.flags &= 0xF8;
+    
+    uint64_t size = nso_get_size(&new_header);
+    nso0_header_t *new_nso = calloc(1, size);
+    if (new_nso == NULL) {
+        fprintf(stderr, "Failed to allocate uncompressed NSO0!\n");
+        exit(EXIT_FAILURE);
+    }
+    *((nso0_header_t *)new_nso) = new_header;
+    
+    for (unsigned int segment = 0; segment < 3; segment++) {
+        char *src = (char *)ctx->header + ctx->header->segments[segment].file_off;
+        char *dst = (char *)new_nso + new_header.segments[segment].file_off;
+        if ((ctx->header->flags >> segment) & 1) {
+            if (LZ4_decompress_safe(src, dst, ctx->header->compressed_sizes[segment], new_header.segments[segment].decomp_size) != (int)new_header.segments[segment].decomp_size) {
+                fprintf(stderr, "Error: Failed to decompress NSO0 segment %u!\n", segment);
+                exit(EXIT_FAILURE);
+            }
+        } else {
+            memcpy(dst, src, new_header.segments[segment].decomp_size);
+        }
+        if ((ctx->tool_ctx->action & ACTION_VERIFY) && ((ctx->header->flags >> (segment + 3)) & 1)) {
+            unsigned char calc_hash[0x20];
+            sha256_hash_buffer(calc_hash, dst, new_header.segments[segment].decomp_size);
+            if (memcmp(calc_hash, new_header.section_hashes[segment], sizeof(calc_hash)) == 0) {
+                ctx->segment_validities[segment] = VALIDITY_VALID;
+            } else {
+                ctx->segment_validities[segment] = VALIDITY_INVALID;
+            }
+        }
+    }
+        
+    return new_nso;
+}
+
+void nso0_process(nso0_ctx_t *ctx) {
+    /* Read *just* safe amount. */
+    nso0_header_t raw_header; 
+    fseeko64(ctx->file, 0, SEEK_SET);
+    if (fread(&raw_header, 1, sizeof(raw_header), ctx->file) != sizeof(raw_header)) {
+        fprintf(stderr, "Failed to read NSO0 header!\n");
+        exit(EXIT_FAILURE);
+    }
+    
+    if (raw_header.magic != MAGIC_NSO0) {
+        printf("Error: NSO0 is corrupt!\n");
+        exit(EXIT_FAILURE);
+    }
+
+    uint64_t size = nso_get_size(&raw_header);
+    ctx->header = malloc(size);
+    if (ctx->header == NULL) {
+        fprintf(stderr, "Failed to allocate NSO0!\n");
+        exit(EXIT_FAILURE);
+    }
+    
+    fseeko64(ctx->file, 0, SEEK_SET);
+    if (fread(ctx->header, 1, size, ctx->file) != size) {
+        fprintf(stderr, "Failed to read NSO0!\n");
+        exit(EXIT_FAILURE);
+    }
+    
+    ctx->uncompressed_header = nso_uncompress(ctx);
+    
+    if (ctx->tool_ctx->action & ACTION_INFO) {
+        nso0_print(ctx);
+    }
+    
+    if (ctx->tool_ctx->action & ACTION_EXTRACT) {
+        nso0_save(ctx);
+    }
+}
+
+void nso0_print(nso0_ctx_t *ctx) {
+    printf("NSO0:\n");
+    memdump(stdout, "    Build Id:                       ", ctx->header->build_id, 0x20);
+    printf("    Sections:\n");
+    if ((ctx->tool_ctx->action & ACTION_VERIFY) && ctx->segment_validities[0] != VALIDITY_UNCHECKED) {
+        printf("        .text   (%s):             %08"PRIx32"-%08"PRIx32"\n", GET_VALIDITY_STR(ctx->segment_validities[0]), ctx->header->segments[0].dst_off, ctx->header->segments[0].dst_off + align(ctx->header->segments[0].decomp_size, 0x1000));
+    } else {
+        printf("        .text:                      %08"PRIx32"-%08"PRIx32"\n", ctx->header->segments[0].dst_off, ctx->header->segments[0].dst_off + align(ctx->header->segments[0].decomp_size, 0x1000));
+    }
+    if ((ctx->tool_ctx->action & ACTION_VERIFY) && ctx->segment_validities[1] != VALIDITY_UNCHECKED) {
+        printf("        .rodata (%s):             %08"PRIx32"-%08"PRIx32"\n", GET_VALIDITY_STR(ctx->segment_validities[1]), ctx->header->segments[1].dst_off, ctx->header->segments[1].dst_off + align(ctx->header->segments[1].decomp_size, 0x1000));
+    } else {
+        printf("        .rodata:                    %08"PRIx32"-%08"PRIx32"\n", ctx->header->segments[1].dst_off, ctx->header->segments[1].dst_off + align(ctx->header->segments[1].decomp_size, 0x1000));
+    }
+    if ((ctx->tool_ctx->action & ACTION_VERIFY) && ctx->segment_validities[2] != VALIDITY_UNCHECKED) {
+        printf("        .rwdata (%s):             %08"PRIx32"-%08"PRIx32"\n", GET_VALIDITY_STR(ctx->segment_validities[2]), ctx->header->segments[2].dst_off, ctx->header->segments[2].dst_off + align(ctx->header->segments[2].decomp_size, 0x1000));
+    } else {
+        printf("        .rwdata:                    %08"PRIx32"-%08"PRIx32"\n", ctx->header->segments[2].dst_off, ctx->header->segments[2].dst_off + align(ctx->header->segments[2].decomp_size, 0x1000));
+    }
+    printf("        .bss:                       %08"PRIx32"-%08"PRIx32"\n", ctx->header->segments[2].dst_off + align(ctx->header->segments[2].decomp_size, 0x1000), ctx->header->segments[2].dst_off + align(ctx->header->segments[2].decomp_size, 0x1000) + align(ctx->header->segments[2].align_or_total_size, 0x1000));
+}
+
+void nso0_save(nso0_ctx_t *ctx) {
+    filepath_t *uncmp_path = &ctx->tool_ctx->settings.uncompressed_path;
+    if (ctx->tool_ctx->file_type == FILETYPE_NSO0 && uncmp_path->valid == VALIDITY_VALID) {     
+        FILE *f_uncmp = os_fopen(uncmp_path->os_path, OS_MODE_WRITE);
+        if (f_uncmp == NULL) {
+            fprintf(stderr, "Failed to open %s!\n", uncmp_path->char_path);
+            return;
+        }
+        if (fwrite(ctx->uncompressed_header, 1, nso_get_size(ctx->uncompressed_header), f_uncmp) != nso_get_size(ctx->uncompressed_header)) {
+            fprintf(stderr, "Failed to write uncompressed nso!\n");
+            exit(EXIT_FAILURE);
+        }
+        fclose(f_uncmp);
+    }
+}

nso.h

@@ -0,0 +1,52 @@
+#ifndef HACTOOL_NSO_H
+#define HACTOOL_NSO_H
+#include "types.h"
+#include "utils.h"
+#include "settings.h"
+
+#define MAGIC_NSO0 0x304F534E
+
+typedef struct {
+    uint32_t file_off;
+    uint32_t dst_off;
+    uint32_t decomp_size;
+    uint32_t align_or_total_size;
+} nso0_segment_t;
+
+typedef struct {
+    uint32_t magic;
+    uint32_t _0x4;
+    uint32_t _0x8;
+    uint32_t flags;
+    nso0_segment_t segments[3];
+    uint8_t build_id[0x20];
+    uint32_t compressed_sizes[3];
+    uint8_t _0x6C[0x24];
+    uint64_t dynstr_extents;
+    uint64_t dynsym_extents;
+    uint8_t section_hashes[3][0x20];
+    unsigned char data[];
+} nso0_header_t;
+
+typedef struct {
+    FILE *file;
+    hactool_ctx_t *tool_ctx;
+    nso0_header_t *header;
+    nso0_header_t *uncompressed_header;
+    validity_t segment_validities[3];
+} nso0_ctx_t;
+
+void nso0_process(nso0_ctx_t *ctx);
+void nso0_print(nso0_ctx_t *ctx);
+void nso0_save(nso0_ctx_t *ctx);
+
+static inline uint64_t nso_get_section_size(nso0_header_t *header, unsigned int segment) {
+    int is_compressed = (header->flags >> segment) & 1;
+    return is_compressed ? header->compressed_sizes[segment] : header->segments[segment].decomp_size;
+}
+
+static inline uint64_t nso_get_size(nso0_header_t *header) {
+    return header->segments[2].file_off + nso_get_section_size(header, 2);
+}
+
+#endif