xnu-2782.30.5.tar.gz

[apple/xnu.git] / bsd / man / man2 / searchfs.2

.\" Copyright (c) 2003 Apple Computer, Inc. All rights reserved.
.\" 
.\" The contents of this file constitute Original Code as defined in and
.\" are subject to the Apple Public Source License Version 1.1 (the
.\" "License").  You may not use this file except in compliance with the
.\" License.  Please obtain a copy of the License at
.\" http://www.apple.com/publicsource and read it before using this file.
.\" 
.\" This Original Code and all software distributed under the License are
.\" distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, EITHER
.\" EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
.\" INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
.\" FITNESS FOR A PARTICULAR PURPOSE OR NON-INFRINGEMENT.  Please see the
.\" License for the specific language governing rights and limitations
.\" under the License.
.\" 
.\"     @(#)searchfs.2
.
.Dd October 13, 2008
.Dt SEARCHFS 2
.Os Darwin
.Sh NAME
.Nm searchfs
.Nd search a volume quickly
.Sh SYNOPSIS
.Fd #include <sys/attr.h>
.Fd #include <unistd.h>
.Ft int
.Fn searchfs "const char* path" "struct fssearchblock* searchBlock" "unsigned int* numMatches" "unsigned int scriptCode" "unsigned int options" "struct searchstate* state"
.
.Sh DESCRIPTION
The
.Fn searchfs
function searches the volume (that is, mounted file system) specified by  
.Fa path 
for file system objects matching the criteria specified by 
.Fa searchBlock , 
.Fa scriptCode , 
and 
.Fa options .
The 
.Fa numMatches 
parameter returns the number of matching file system objects found.
The function also returns attributes of those file system objects in a buffer 
specified by 
.Fa searchBlock .
The 
.Fa searchState 
parameter allows you search the volume using multiple calls to 
.Fn searchfs ,
resuming the search where it left off.
The routine will only return objects to which you have access (that is, you 
have execute permissions on the directories leading to this object from the root).
.Pp
.
.\" path parameter
.
The
.Fa path 
parameter must reference a valid file system object on the volume to be searched. 
Typically the path is to the volume's root directory.
The entire volume is always searched.
All directories listed in the path name leading to this object must be 
searchable.
.Pp
.
.\" searchBlock parameter
.
The
.Fa searchBlock
parameter is a pointer to an 
.Vt fssearchblock 
structure, as defined by
.Aq Pa sys/attr.h
(shown below).
You are responsible for filling out all fields of this structure before calling the function. 
.Bd -literal
struct fssearchblock {
    struct attrlist *   returnattrs;
    void *              returnbuffer;
    size_t              returnbuffersize;
    unsigned int        maxmatches;
    struct timeval      timelimit;
    void *              searchparams1;
    size_t              sizeofsearchparams1;
    void *              searchparams2;
    size_t              sizeofsearchparams2;
    struct attrlist     searchattrs;
};
.Ed
.Pp
.
For information about the 
.Vt attrlist 
structure, see the discussion of 
.Xr getattrlist 2 .
.Pp
.
.\" searchBlock elements
.
The fields of the 
.Vt fssearchblock
structure are defined as follows.
.Bl -tag -width sizeofsearchparams1
.
.It returnattrs
.Fn searchfs 
can return arbitrary attributes of the file system objects that meet the designated
search criteria passed in via 
.Vt searchparams1 
and 
.Vt searchparams2.  
This field must point to an 
.Vt attrlist 
structure that specifies the attributes that you want returned. 
To request an attribute you must set the corresponding bit in the appropriate 
.Vt attrgroup_t 
field of the 
.Vt attrlist 
structure.
You are responsible for filling out all fields of this structure before calling the function. 
You must not request volume attributes.
.
.It returnbuffer
.Fn searchfs 
places attributes of the matching file system objects into this returned attributes buffer. 
The attributes for any given object are grouped together and 
packed in exactly the same way as they would be returned from 
.Xr getdirentriesattr 2 .
The initial contents of this buffer are ignored.
.
.It returnbuffersize
Set this field to the size, in bytes, of the buffer pointed to by 
.Fa returnbuffer .
.
.It maxmatches
Specifies the maximum number of matches that you want this call to 
.Fn searchfs 
to return.
.
.It timelimit
Specifies the maximum time that you want this call to 
.Fn searchfs 
to run.
.Pp
.
If you're implementing a volume format, you should impose your own internal 
limit on the duration of this call to prevent a malicious user program 
from monopolizing kernel resources.
.Pp
.
.It searchparams1
Specifies the lower bound of the search criteria. 
This is discussed in detail below. 
You must place attribute values into the buffer in the same 
way as they would be returned by 
.Xr getattrlist 2 ,
where the 
.Fa searchattrs
field determines the exact layout of the attribute values.
.
.It sizeofsearchparams1
Set this field to the size, in bytes, of the buffer pointed to by 
.Fa searchparams1 .
.
.It searchparams2
Specifies the upper bound of the search criteria. 
This is discussed in detail below. 
You must place attribute values into the buffer in the same 
way as they would be returned by 
.Xr getattrlist 2 ,
where the 
.Fa searchattrs
field determines the exact layout of the attribute values.
.
.It sizeofsearchparams2
Set this field to the size, in bytes, of the buffer pointed to by 
.Fa searchparams2 .
.
.It searchattrs
Specifies the attributes that you want you use for your search criteria. 
You are responsible for filling out all fields of this structure before calling the function. 
To search for an attribute you must set the corresponding bit in the appropriate 
.Vt attrgroup_t 
field of the 
.Vt attrlist 
structure, and place the appropriate values into the 
.Fa searchparam1 
and 
.Fa searchparam2 
buffers.
The attributes specified here determine the format of those buffers. 
This is discussed in detail below. 
.
.El
.Pp
.
.\" numMatches parameter
.
The 
.Fa numMatches 
parameter points to an 
.Vt unsigned int 
variable. 
The initial value of this variable is ignored.
On return, this variable contains the number of matching file system objects found.
The is always less than or equal to the 
.Fa maxmatches 
field of the 
.Fa searchBlock 
parameter.
The attributes for the matching objects have been placed into the returned attributes buffer.
.Pp
.
.\" scriptCode parameter
.
The 
.Fa scriptCode 
parameter is currently ignored. 
You should always pass in the value 0x08000103, which corresponds to the 
UTF-8 text encoding value defined by 
.Aq Pa CarbonCore/TextCommon.h .
.Pp
.
.\" options parameter
.
The
.Fa options
parameter is a bit set that controls the behaviour of
.Fn searchfs .
The following option bits are defined.
.
.Bl -tag -width SRCHFS_MATCHPARTIALNAMES
.
.It SRCHFS_START
If this bit is set, 
.Fn searchfs 
will ignore the 
.Fa state 
parameter and start a new search. 
Otherwise 
.Fn searchfs 
assumes that 
.Fa searchstate 
is valid and attempts to resume a previous search based on that state.
.
.It SRCHFS_MATCHPARTIALNAMES
If this bit is set, 
.Fn searchfs 
will consider substrings to be successful matches when evaluating the 
.Dv ATTR_CMN_NAME
attribute.
.
.It SRCHFS_MATCHDIRS
If this bit is set, 
.Fn searchfs 
will search for directories that match the search criteria.
To get meaningful results you must specify either this bit or 
.Dv SRCHFS_MATCHFILES , 
or both.
.
.It SRCHFS_MATCHFILES
If this bit is set, 
.Fn searchfs 
will search for files that match the search criteria.
To get meaningful results you must specify either this bit or 
.Dv SRCHFS_MATCHDIRS , 
or both.
.
.It SRCHFS_SKIPLINKS
If this bit is set, 
.Fn searchfs 
will only return one reference for a hard linked file, rather than a reference 
for each hard link to the file.
.Pp
This option is not recommended for general development.
Its primary client is the 
.Xr quotacheck 2 
utility.  Note that not all filesystems that support 
.Fn searchfs 
support this option and may return EINVAL if it is requested.
.Pp
.
This option is privileged (the caller's effective UID must be 0) and cannot 
be used if you request the 
.Dv ATTR_CMN_NAME 
or 
.Dv ATTR_CMN_PAROBJID 
attributes.
.Pp
Introduced with Darwin 7.0 (Mac OS X version 10.3).
.
.It SRCHFS_SKIPINVISIBLE
If this bit is set, 
.Fn searchfs 
will not match any invisible file system objects (that is, objects whose 
.Dv ATTR_CMN_FNDRINFO 
attribute has bit 6 set in the ninth byte) or any objects within 
invisible directories.
.Pp
Introduced with Darwin 7.0 (Mac OS X version 10.3).
.
.It SRCHFS_SKIPPACKAGES
If this bit is set, 
.Fn searchfs 
will not match any file system objects that are inside a package. 
A package is defined as a directory whose extension matches one 
of the extensions that are configured into the kernel by Launch Services.
.Pp
Introduced with Darwin 7.0 (Mac OS X version 10.3).
.
.It SRCHFS_SKIPINAPPROPRIATE
If this bit is set, 
.Fn searchfs 
will not match any file system objects that are within an inappropriate directory. 
The current list of inappropriate directories contains one item: /System.
.Pp
Introduced with Darwin 7.0 (Mac OS X version 10.3).
.
.It SRCHFS_NEGATEPARAMS
If this bit is set, 
.Fn searchfs 
will return all the file system objects that do not match the search criteria.
.Pp
Introduced with Darwin 7.0 (Mac OS X version 10.3).
.
.El
.Pp
.
.\" state parameter
.
The 
.Fa state 
parameter is a pointer to an opaque data structure that 
.Fn searchfs 
uses to maintain the state of a search between successive calls. 
In your first call to 
.Fn searchfs ,
you specify the 
.Dv SRCHFS_START 
flag in the 
.Fa options 
parameter. 
This tells 
.Fn searchfs 
that the search state is invalid and that it should start a new search. 
When this call completes, it may have only returned partial results;
in that case, it will have updated the structure pointed to by 
.Fa state .
If you call 
.Fn searchfs 
again, this time without specifying the 
.Dv SRCHFS_START 
flag in the 
.Fa options 
parameter, it will resume the search where it left off, using the search state 
that it previously stored in the state structure.
You do not need to explicitly dispose of this state.
.Pp
.
The 
.Fn searchfs 
function returns significant errors in the followings cases.
.
.Bl -bullet
.
.It
If it has found as many objects as you requested in the 
.Fa maxmatches 
field of the 
.Fa searchBlock 
parameter, it will return 
.Dv EAGAIN . 
.
.It
If there is not enough space in the returned attributes buffer for the first match, 
it will return 
.Dv ENOBUFS .
You should allocate a larger returned attributes buffer and try again.
.Fa numMatches 
will be zero in this case.
.
.It
If the timeout expires it will return 
.Dv EAGAIN .
.
.It
If you attempt to resume a search (that is, 
.Dv SRCHFS_START 
is not specified in the 
.Fa options 
parameter) and the catalog has changed since the last search, 
the function will return 
.Dv EBUSY . 
You must start your search again from the beginning.
.
.El
.Pp
.
If 
.Fn searchfs
returns 
.Dv EAGAIN ,
the value in 
.Fa numMatches 
may be greater than zero. 
This is known as a partial result. 
You should be sure to process these matches before calling 
.Fn searchfs 
again.
.
.Sh SEARCH CRITERIA
.
You specify the search criteria using a combination of the 
.Fa searchattrs , 
.Fa searchparams1 ,
.Fa sizeofsearchparams1, 
.Fa searchparams2 ,
and
.Fa sizeofsearchparams2 
fields of the 
.Fa searchBlock 
parameter, and various flags in the 
.Fa options 
parameter. 
The 
.Fa searchattrs 
field determines the attributes considered when comparing a file system object to 
the search criteria.
You can specify that an attribute should be considered by setting the corresponding 
bit in the appropriate 
.Vt attrgroup_t 
field of the 
.Vt attrlist 
structure. 
See the discussion of 
.Xr getattrlist 2 
for a detailed description of this structure. 
.Pp
.
The 
.Fa searchparams1 ,
.Fa sizeofsearchparams1 , 
.Fa searchparams2 ,
and
.Fa sizeofsearchparams2 
fields specify the attribute values that must be matched. 
The format of each of these buffers is determined by the attributes that you're searching for. 
The values are packed in exactly the same way as they would be returned from 
.Xr getattrlist 2 ,
including the leading
.Vt u_int32_t
length value.  Note that the size of these buffers must be bounded by SEARCHFS_MAX_SEARCHPARMS bytes, 
which is defined in <sys/attr.h>.  
.Pp
.
The attribute values in the first and second search buffers form a lower and upper bound for 
the search, respectively.
These have different meanings depending on the type of attribute.
.
.Bl -bullet
.
.It
For string attributes (specifically 
.Dv ATTR_CMN_NAME ,
the object name), the value in the first search 
buffer is significant and the value in the second search buffer is ignored.
The string comparison is either an exact match or a substring match depending on 
the 
.Dv SRCHFS_MATCHPARTIALNAMES 
flag in the 
.Fa options 
parameter.
.
.It
For structured attributes (specifically 
.Dv ATTR_CMN_FNDRINFO ,
the Finder information), the value from the 
file system object is masked (logical AND) with the value in the second search buffer and then 
compared, byte for byte, against the value in the first search buffer.
If it is equal, the object is a match.
.
.It
For scalar attributes (all other attributes, for example, 
.Dv ATTR_CMN_MODTIME ,
the modification date), the values in the first and second search 
buffers are literally a lower and upper bound. 
An object matches the criteria if its value is greater than or equal to the value in 
the first buffer and less than or equal to the value in the second. 
.
.El
.
.Sh RETURN VALUES
Upon successful completion, a value of 0 is returned.
This means that the entire volume has been searched and all matches returned.
Otherwise, a value of -1 is returned and
.Va errno
is set to indicate the error.
.Pp
.
See the discussion of the 
.Dv EAGAIN ,
.Dv ENOBUFS ,
and
.Dv EBUSY 
error codes above.
.
.Sh COMPATIBILITY
Not all volumes support 
.Fn searchfs .
You can test whether a volume supports 
.Fn searchfs 
by using 
.Xr getattrlist 2 
to get the volume capabilities attribute 
.Dv ATTR_VOL_CAPABILITIES ,
and then testing the 
.Dv VOL_CAP_INT_SEARCHFS 
flag.
.Pp
.
The 
.Fn searchfs 
function has been undocumented for more than two years. 
In that time a number of volume format implementations have been created without 
a proper specification for the behaviour of this routine. 
You may encounter volume format implementations with slightly different 
behaviour than what is described here. 
Your program is expected to be tolerant of this variant behaviour.
.Pp
.
If you're implementing a volume format that supports 
.Fn searchfs ,
you should be careful to support the behaviour specified by this document.
.Pp
.
A bug in systems prior to Darwin 7.0 (Mac OS X version 10.3) makes searching for the 
.Dv ATTR_CMN_BKUPTIME 
attribute tricky. 
The bug causes the attribute to consume two items in the search attribute buffers, the 
first in the proper place and the second between 
.Dv ATTR_CMN_FNDRINFO
and 
.Dv ATTR_CMN_OWNERID .
.
.Sh ERRORS
.Fn searchfs
will fail if:
.Bl -tag -width Er
.
.It Bq Er ENOTSUP
The volume does not support
.Fn searchfs .
.
.It Bq Er ENOTDIR
A component of the path prefix is not a directory.
.
.It Bq Er ENAMETOOLONG
A component of a path name exceeded 
.Dv NAME_MAX
characters, or an entire path name exceeded 
.Dv PATH_MAX
characters.
.
.It Bq Er ENOENT
The file system object does not exist.
.
.It Bq Er EACCES
Search permission is denied for a component of the path prefix.
.
.It Bq Er ELOOP
Too many symbolic links were encountered in translating the pathname.
.
.It Bq Er EFAULT
One of the pointer parameters points to an invalid address.
.
.It Bq Er EINVAL
The 
.Fa options 
parameter contains an invalid flag or sizeofsearchparams1/2 is greater than
SEARCHFS_MAX_SEARCHPARMS (see attr.h).  Additionally, filesystems that do
not support SRCHFS_SKIPLINKS may return EINVAL if this search option
is requested.
.
.It Bq Er EAGAIN
The search terminated with partial results, either because 
.Fa numMatches 
has hit the limit specified by 
.Fa maxmatches 
or because the timeout expired.
Process the matches returned so far and then call 
.Fn searchfs 
again to look for more.
.Pp
.
.It Bq Er ENOBUFS
The returned attributes buffer is too small for the first match.
You should allocate a larger returned attributes buffer and try again.
.Fa numMatches 
will be zero in this case.
.
.It Bq Er EBUSY
The search could not be resumed because the volume has changed.
.
.It Bq Er EIO
An I/O error occurred while reading from or writing to the file system.
.El
.Pp
.
.Sh CAVEATS

The list of attributes that are valid as search criteria currently includes the 
following list of attributes.  Note that this list is substantially smaller than 
what is available via 
.Xr getattrlist 2
for a particular filesystem object.  In general, a filesystem that supports 
.Fn searchfs
will typically supply per-item attributes for matched objects that are also 
supported by the
.Xr getdirentries 2
system call.  This varies from filesystem to filesystem.

.Pp
.
.Bl -item -compact
.It 
ATTR_CMN_NAME
.It 
ATTR_CMN_OBJID
.It
ATTR_CMN_PAROBJID
.It
ATTR_CMN_CRTIME
.It
ATTR_CMN_MODTIME
.It
ATTR_CMN_CHGTIME
.It
ATTR_CMN_ACCTIME
.It
ATTR_CMN_BKUPTIME
.It
ATTR_CMN_FNDRINFO
.It
ATTR_CMN_BKUPTIME
.It
ATTR_CMN_OWNERID
.It
ATTR_CMN_GRPID
.It
ATTR_CMN_ACCESSMASK
.It
ATTR_CMN_FILEID
.It
ATTR_CMN_PARENTID
.Pp
.
.It
ATTR_DIR_ENTRYCOUNT
.Pp
.
.It
ATTR_FILE_DATALENGTH
.It
ATTR_FILE_DATAALLOCSIZE
.It
ATTR_FILE_RSRCLENGTH
.It
ATTR_FILE_RSRCALLOCSIZE
.El
.
.Sh EXAMPLES
.
The following code searches a volume for files of the specified type and creator.
.
.Bd -literal
#include <assert.h>
#include <stdio.h>
#include <stddef.h>
#include <string.h>
#include <sys/attr.h>
#include <sys/errno.h>
#include <unistd.h>
.Pp
.
typedef struct attrlist         attrlist_t;
typedef struct fssearchblock    fssearchblock_t;
typedef struct searchstate      searchstate_t;
.Pp
.
struct SearchAttrBuf {
    u_int32_t       length;
    char            finderInfo[32];
};
typedef struct SearchAttrBuf SearchAttrBuf;
.Pp
.
struct ResultAttrBuf {
    u_int32_t       length;
    attrreference_t name;
    fsobj_id_t      parObjID;
};
typedef struct ResultAttrBuf ResultAttrBuf;
.Pp
.
enum {
    kMatchesPerCall = 16
};
.Pp
.
static int SearchFSDemo(
    const char *volPath, 
    const char *type, 
    const char *creator
)
{
    int             err;
    fssearchblock_t searchBlock;
    SearchAttrBuf   lower;
    SearchAttrBuf   upper;
    static const unsigned char kAllOnes[4] = { 0xFF, 0xFF, 0xFF, 0xFF };
    unsigned int    matchCount;
    unsigned int    matchIndex;
    unsigned int    options;
    searchstate_t   state;
    ResultAttrBuf * thisEntry;
    attrlist_t      returnAttrList;
    char            resultAttrBuf[  kMatchesPerCall 
                                  * (sizeof(ResultAttrBuf) + 64)];
.Pp
.
    // resultAttrBuf is big enough for kMatchesPerCall entries, 
    // assuming that the average name length is less than 64.
.Pp
.
    assert(strlen(type)    == 4);
    assert(strlen(creator) == 4);
.Pp
    
    memset(&searchBlock, 0, sizeof(searchBlock));
    searchBlock.searchattrs.bitmapcount = ATTR_BIT_MAP_COUNT;
    searchBlock.searchattrs.commonattr  = ATTR_CMN_FNDRINFO;
.Pp
    
    memset(&lower, 0, sizeof(lower));
    memset(&upper, 0, sizeof(upper));
    lower.length = sizeof(lower);
    upper.length = sizeof(upper);
    memcpy(&lower.finderInfo[0], type,     4);
    memcpy(&lower.finderInfo[4], creator,  4);
    memcpy(&upper.finderInfo[0], kAllOnes, 4);
    memcpy(&upper.finderInfo[4], kAllOnes, 4);
    searchBlock.searchparams1       = &lower;
    searchBlock.sizeofsearchparams1 = sizeof(lower);
    searchBlock.searchparams2       = &upper;
    searchBlock.sizeofsearchparams2 = sizeof(lower);
.Pp
    
    searchBlock.timelimit.tv_sec  = 0;
    searchBlock.timelimit.tv_usec = 100 * 1000;
.Pp
    
    searchBlock.maxmatches = kMatchesPerCall;
.Pp
    
    memset(&returnAttrList, 0, sizeof(returnAttrList));
    returnAttrList.bitmapcount = ATTR_BIT_MAP_COUNT;
    returnAttrList.commonattr  = ATTR_CMN_NAME | ATTR_CMN_PAROBJID;
.Pp
.
    searchBlock.returnattrs = &returnAttrList;
    searchBlock.returnbuffer = resultAttrBuf;
    searchBlock.returnbuffersize = sizeof(resultAttrBuf);
.Pp
    
    options = SRCHFS_START | SRCHFS_MATCHFILES;
.Pp
    
    do {
        err = searchfs(
            volPath, 
            &searchBlock, 
            &matchCount, 
            0x08000103, 
            options, 
            &state
        );
        if (err != 0) {
            err = errno;
        }
        if ( (err == 0) || (err == EAGAIN) ) {
            thisEntry = (ResultAttrBuf *) resultAttrBuf;
.Pp
            
            for (matchIndex = 0; matchIndex < matchCount; matchIndex++) {
                printf("%08x ", thisEntry->parObjID.fid_objno);
                printf(
                    "%s\en", 
                    ((char *) &thisEntry->name) 
                        + thisEntry->name.attr_dataoffset
                );
.
                // Advance to the next entry.
.
                ((char *) thisEntry) += thisEntry->length;
            }
        }
.Pp
        
        options &= ~SRCHFS_START;
    } while (err == EAGAIN);
.Pp
    
    return err;
}
.Ed
.
.Sh SEE ALSO
.
.Xr getattrlist 2
.
.Sh HISTORY
A
.Fn searchfs
function call appeared in Darwin 1.3.1 (Mac OS X version 10.0).
.