Re: [Libguestfs] [PATCH] Report last-modified time of hive root and nodes

The infrastructure for modified-time reporting has been essentially unused. These changes report the registry time by treating the time fields as Windows filetime fields stored in little-Endian (which means they can be treated as a single 64-bit little-Endian integer). Some of the code changes necessary include: * Exposing the hive_h structure in the hivex header file (via generator.ml)

* Adding an additional argument to the node_start function, which should cause no complications since the change is specific to the C API.

Signed-off-by: Alex Nelson <ajnelson(a)cs.ucsc.edu&gt; --- generator/generator.ml | 44 ++++++++++++++++- lib/hivex.c | 124 +++++++++++++++++++++++++++++++----------------- xml/hivexml.c | 11 ++++- 3 files changed, 132 insertions(+), 47 deletions(-) diff --git a/generator/generator.ml b/generator/generator.ml index 31478cd..f1aa799 100755 --- a/generator/generator.ml +++ b/generator/generator.ml @@ -695,6 +695,46 @@ extern \"C\" { /* NOTE: This API is documented in the man page hivex(3). */ /* Hive handle. */ +struct hive_h { + char *filename; + int fd; + size_t size; + int msglvl; + int writable; + + /* Registry file, memory mapped if read-only, or malloc'd if writing. */ + union { + char *addr; + struct ntreg_header *hdr; + }; + + /* Use a bitmap to store which file offsets are valid (point to a + * used block). We only need to store 1 bit per 32 bits of the file + * (because blocks are 4-byte aligned). We found that the average + * block size in a registry file is ~50 bytes. So roughly 1 in 12 + * bits in the bitmap will be set, making it likely a more efficient + * structure than a hash table. + */ + char *bitmap; +#define BITMAP_SET(bitmap,off) (bitmap[(off)>>5] |= 1 << (((off)>>2)&7)) +#define BITMAP_CLR(bitmap,off) (bitmap[(off)>>5] &= ~ (1 << (((off)>>2)&7))) +#define BITMAP_TST(bitmap,off) (bitmap[(off)>>5] & (1 << (((off)>>2)&7))) +#define IS_VALID_BLOCK(h,off) \ + (((off) & 3) == 0 && \ + (off) >= 0x1000 && \ + (off) < (h)->size && \ + BITMAP_TST((h)->bitmap,(off))) + + /* Fields from the header, extracted from little-endianness hell. */ + size_t rootoffs; /* Root key offset (always an nk-block). */ + size_t endpages; /* Offset of end of pages. */ + char *last_modified; /* mtime of base block. */ + + /* For writing. */ + size_t endblocks; /* Offset to next block allocation (0 + if not allocated anything yet). */ +}; + typedef struct hive_h hive_h; /* Nodes and values. */ @@ -761,7 +801,7 @@ typedef struct hive_set_value hive_set_value; * languages make it much simpler to iterate over a tree. */ struct hivex_visitor { - int (*node_start) (hive_h *, void *opaque, hive_node_h, const char *name); + int (*node_start) (hive_h *, void *opaque, hive_node_h, const char *name, const char *last_modified); int (*node_end) (hive_h *, void *opaque, hive_node_h, const char *name); int (*value_string) (hive_h *, void *opaque, hive_node_h, hive_value_h, hive_type t, size_t len, const char *key, const char *str); int (*value_multiple_strings) (hive_h *, void *opaque, hive_node_h, hive_value_h, hive_type t, size_t len, const char *key, char **argv); @@ -1110,7 +1150,7 @@ terminates immediately. If you don't need a callback function at all, set the function pointer to NULL. struct hivex_visitor { - int (*node_start) (hive_h *, void *opaque, hive_node_h, const char *name); + int (*node_start) (hive_h *, void *opaque, hive_node_h, const char *name, const char *last_modified); int (*node_end) (hive_h *, void *opaque, hive_node_h, const char *name); int (*value_string) (hive_h *, void *opaque, hive_node_h, hive_value_h, hive_type t, size_t len, const char *key, const char *str); diff --git a/lib/hivex.c b/lib/hivex.c index fedbb6c..474249f 100644 --- a/lib/hivex.c +++ b/lib/hivex.c @@ -33,6 +33,7 @@ #include <sys/mman.h> #include <sys/stat.h> #include <assert.h> +#include <time.h> #include "c-ctype.h" #include "full-read.h" @@ -60,51 +61,12 @@ static char *windows_utf16_to_utf8 (/* const */ char *input, size_t len); static size_t utf16_string_len_in_bytes_max (const char *str, size_t len); -struct hive_h { - char *filename; - int fd; - size_t size; - int msglvl; - int writable; - - /* Registry file, memory mapped if read-only, or malloc'd if writing. */ - union { - char *addr; - struct ntreg_header *hdr; - }; - - /* Use a bitmap to store which file offsets are valid (point to a - * used block). We only need to store 1 bit per 32 bits of the file - * (because blocks are 4-byte aligned). We found that the average - * block size in a registry file is ~50 bytes. So roughly 1 in 12 - * bits in the bitmap will be set, making it likely a more efficient - * structure than a hash table. - */ - char *bitmap; -#define BITMAP_SET(bitmap,off) (bitmap[(off)>>5] |= 1 << (((off)>>2)&7)) -#define BITMAP_CLR(bitmap,off) (bitmap[(off)>>5] &= ~ (1 << (((off)>>2)&7))) -#define BITMAP_TST(bitmap,off) (bitmap[(off)>>5] & (1 << (((off)>>2)&7))) -#define IS_VALID_BLOCK(h,off) \ - (((off) & 3) == 0 && \ - (off) >= 0x1000 && \ - (off) < (h)->size && \ - BITMAP_TST((h)->bitmap,(off))) - - /* Fields from the header, extracted from little-endianness hell. */ - size_t rootoffs; /* Root key offset (always an nk-block). */ - size_t endpages; /* Offset of end of pages. */ - - /* For writing. */ - size_t endblocks; /* Offset to next block allocation (0 - if not allocated anything yet). */ -}; - /* NB. All fields are little endian. */ struct ntreg_header { char magic[4]; /* "regf" */ uint32_t sequence1; uint32_t sequence2; - char last_modified[8]; + uint64_t last_modified; uint32_t major_ver; /* 1 */ uint32_t minor_ver; /* 3 */ uint32_t unknown5; /* 0 */ @@ -173,7 +135,7 @@ struct ntreg_nk_record { int32_t seg_len; /* length (always -ve because used) */ char id[2]; /* "nk" */ uint16_t flags; - char timestamp[8]; + uint64_t timestamp; uint32_t unknown1; uint32_t parent; /* offset of owner/parent */ uint32_t nr_subkeys; /* number of subkeys */ @@ -265,7 +227,34 @@ header_checksum (const hive_h *h) return sum; } +#define WINDOWS_TICK 10000000LL +#define SEC_TO_UNIX_EPOCH 11644473600LL +/** + * Convert Windows filetime to ISO 8601 format. + * Source for filetime->time_t conversion: http://stackoverflow.com/questions/6161776/convert-windows-filetime-to-se... + * Source for time_t->char* conversion: Fiwalk version 0.6.14's fiwalk.cpp. + * @param windows_ticks Expected to not have any remaining Endian issues. + */ +int +filetime_to_8601 (char *buf, int bufsize, uint64_t windows_ticks) +{ + if (buf == NULL) { + fprintf (stderr, "filetime_to_8601: Received null output buffer, unable to proceed.\n"); + return -1; + } + uint64_t nanos = windows_ticks % WINDOWS_TICK; + time_t tt = (windows_ticks / WINDOWS_TICK - SEC_TO_UNIX_EPOCH); + struct tm time_tm; + if (gmtime_r (&tt, &time_tm) == NULL) { + fprintf (stderr, "filetime_to_8601: Error running gmtime_r on timestamp (decimal hundreds of ns: %" PRIu64 ").\n", windows_ticks); + return -1; + } + strftime(buf, bufsize, "%FT%TZ", &time_tm); + return 0; +} + #define HIVEX_OPEN_MSGLVL_MASK (HIVEX_OPEN_VERBOSE|HIVEX_OPEN_DEBUG) +#define TIMESTAMP_BUF_LEN 32 hive_h * hivex_open (const char *filename, int flags) @@ -359,6 +348,15 @@ hivex_open (const char *filename, int flags) goto error; } + /* Last-modified time. */ + h->last_modified = (char *) calloc(1 + TIMESTAMP_BUF_LEN, sizeof(char)); + int ft_rc = filetime_to_8601(h->last_modified, TIMESTAMP_BUF_LEN, le64toh ((uint64_t) h->hdr->last_modified)); + if (ft_rc) { + fprintf (stderr, "hivex: failed to parse time value\n"); + free(h->last_modified); + h->last_modified = NULL; + } + if (h->msglvl >= 2) { char *name = windows_utf16_to_utf8 (h->hdr->name, 64); @@ -367,6 +365,8 @@ hivex_open (const char *filename, int flags) " file version %" PRIu32 ".%" PRIu32 "\n" " sequence nos %" PRIu32 " %" PRIu32 "\n" " (sequences nos should match if hive was synched at shutdown)\n" + " last modified %s\n" + " (decimal, 100 ns) %" PRIu64 "\n" " original file name %s\n" " (only 32 chars are stored, name is probably truncated)\n" " root offset 0x%x + 0x1000\n" @@ -374,6 +374,8 @@ hivex_open (const char *filename, int flags) " checksum 0x%x (calculated 0x%x)\n", major_ver, le32toh (h->hdr->minor_ver), le32toh (h->hdr->sequence1), le32toh (h->hdr->sequence2), + h->last_modified, + le64toh (h->hdr->last_modified), name ? name : "(conversion failed)", le32toh (h->hdr->offset), le32toh (h->hdr->blocks), h->size, @@ -541,6 +543,10 @@ hivex_close (hive_h *h) if (h->msglvl >= 1) fprintf (stderr, "hivex_close\n"); + if (h->last_modified) { + free (h->last_modified); + h->last_modified = NULL; + } free (h->bitmap); if (!h->writable) munmap (h->addr, h->size); @@ -608,6 +614,33 @@ hivex_node_name (hive_h *h, hive_node_h node) return ret; } +/* Caller responsible for freeing returned char* if non-null. */ +char * +hivex_node_mtime (hive_h *h, hive_node_h node) +{ + int ft_rc; + if (!IS_VALID_BLOCK (h, node) || !BLOCK_ID_EQ (h, node, "nk")) { + errno = EINVAL; + return NULL; + } + + struct ntreg_nk_record *nk = (struct ntreg_nk_record *) (h->addr + node); + + char *ret = calloc (32 + 1, sizeof(char)); + if (ret == NULL) + return ret; + ft_rc = filetime_to_8601 (ret, 32, le64toh (nk->timestamp)); + if (h->msglvl >= 2) { + fprintf(stderr, "hivex_node_mtime: nk->timestamp: %" PRIu64 "\n", nk->timestamp); + fprintf(stderr, "hivex_node_mtime: ret: %s\n", ret); + } + if (ft_rc) { + free(ret); + ret = NULL; + } + return ret; +} + #if 0 /* I think the documentation for the sk and classname fields in the nk * record is wrong, or else the offset field is in the wrong place. @@ -1560,6 +1593,7 @@ hivex__visit_node (hive_h *h, hive_node_h node, { int skip_bad = flags & HIVEX_VISIT_SKIP_BAD; char *name = NULL; + char *last_modified = NULL; hive_value_h *values = NULL; hive_node_h *children = NULL; char *key = NULL; @@ -1584,8 +1618,11 @@ hivex__visit_node (hive_h *h, hive_node_h node, BITMAP_CLR (unvisited, node); name = hivex_node_name (h, node); + last_modified = hivex_node_mtime (h, node); + if (h->msglvl >= 2) + fprintf(stderr, "hivex__visit_node: last_modified: %s\n", last_modified ? last_modified : "NULL" ); if (!name) return skip_bad ? 0 : -1; - if (vtor->node_start && vtor->node_start (h, opaque, node, name) == -1) + if (vtor->node_start && vtor->node_start (h, opaque, node, name, last_modified) == -1) goto error; values = hivex_node_values (h, node); @@ -1764,6 +1801,7 @@ hivex__visit_node (hive_h *h, hive_node_h node, error: free (name); + free (last_modified); free (values); free (children); free (key); @@ -2264,7 +2302,7 @@ hivex_node_add_child (hive_h *h, hive_node_h parent, const char *name) nk->sk = htole32 (parent_sk_offset - 0x1000); /* Inherit parent timestamp. */ - memcpy (nk->timestamp, parent_nk->timestamp, sizeof (parent_nk->timestamp)); + nk->timestamp = parent_nk->timestamp; /* What I found out the hard way (not documented anywhere): the * subkeys in lh-records must be kept sorted. If you just add a diff --git a/xml/hivexml.c b/xml/hivexml.c index 90cb22b..b32eaa2 100644 --- a/xml/hivexml.c +++ b/xml/hivexml.c @@ -40,7 +40,7 @@ #endif /* Callback functions. */ -static int node_start (hive_h *, void *, hive_node_h, const char *name); +static int node_start (hive_h *, void *, hive_node_h, const char *name, const char *last_modified); static int node_end (hive_h *, void *, hive_node_h, const char *name); static int value_string (hive_h *, void *, hive_node_h, hive_value_h, hive_type t, size_t len, const char *key, const char *str); static int value_multiple_strings (hive_h *, void *, hive_node_h, hive_value_h, hive_type t, size_t len, const char *key, char **argv); @@ -123,6 +123,8 @@ main (int argc, char *argv[]) XML_CHECK (xmlTextWriterStartDocument, (writer, NULL, "utf-8", NULL)); XML_CHECK (xmlTextWriterStartElement, (writer, BAD_CAST "hive")); + if (h->last_modified) + XML_CHECK (xmlTextWriterWriteAttribute, (writer, BAD_CAST "mtime", BAD_CAST (h->last_modified))); if (hivex_visit (h, &visitor, sizeof visitor, writer, visit_flags) == -1) { perror (argv[optind]); @@ -142,11 +144,16 @@ main (int argc, char *argv[]) } static int -node_start (hive_h *h, void *writer_v, hive_node_h node, const char *name) +node_start (hive_h *h, void *writer_v, hive_node_h node, const char *name, const char *last_modified) { xmlTextWriterPtr writer = (xmlTextWriterPtr) writer_v; XML_CHECK (xmlTextWriterStartElement, (writer, BAD_CAST "node")); XML_CHECK (xmlTextWriterWriteAttribute, (writer, BAD_CAST "name", BAD_CAST name)); + if (last_modified) { + XML_CHECK (xmlTextWriterWriteAttribute, (writer, BAD_CAST "mtime", BAD_CAST last_modified)); + } else { + fprintf(stderr, "node_start: last_modified came across NULL.\n"); + } return 0; } -- 1.7.6