15 Oct, 2010

1 commit

  • All file_operations should get a .llseek operation so we can make
    nonseekable_open the default for future file operations without a
    .llseek pointer.

    The three cases that we can automatically detect are no_llseek, seq_lseek
    and default_llseek. For cases where we can we can automatically prove that
    the file offset is always ignored, we use noop_llseek, which maintains
    the current behavior of not returning an error from a seek.

    New drivers should normally not use noop_llseek but instead use no_llseek
    and call nonseekable_open at open time. Existing drivers can be converted
    to do the same when the maintainer knows for certain that no user code
    relies on calling seek on the device file.

    The generated code is often incorrectly indented and right now contains
    comments that clarify for each added line why a specific variant was
    chosen. In the version that gets submitted upstream, the comments will
    be gone and I will manually fix the indentation, because there does not
    seem to be a way to do that using coccinelle.

    Some amount of new code is currently sitting in linux-next that should get
    the same modifications, which I will do at the end of the merge window.

    Many thanks to Julia Lawall for helping me learn to write a semantic
    patch that does all this.

    ===== begin semantic patch =====
    // This adds an llseek= method to all file operations,
    // as a preparation for making no_llseek the default.
    //
    // The rules are
    // - use no_llseek explicitly if we do nonseekable_open
    // - use seq_lseek for sequential files
    // - use default_llseek if we know we access f_pos
    // - use noop_llseek if we know we don't access f_pos,
    // but we still want to allow users to call lseek
    //
    @ open1 exists @
    identifier nested_open;
    @@
    nested_open(...)
    {

    }

    @ open exists@
    identifier open_f;
    identifier i, f;
    identifier open1.nested_open;
    @@
    int open_f(struct inode *i, struct file *f)
    {

    }

    @ read disable optional_qualifier exists @
    identifier read_f;
    identifier f, p, s, off;
    type ssize_t, size_t, loff_t;
    expression E;
    identifier func;
    @@
    ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
    {

    }

    @ read_no_fpos disable optional_qualifier exists @
    identifier read_f;
    identifier f, p, s, off;
    type ssize_t, size_t, loff_t;
    @@
    ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
    {
    ... when != off
    }

    @ write @
    identifier write_f;
    identifier f, p, s, off;
    type ssize_t, size_t, loff_t;
    expression E;
    identifier func;
    @@
    ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
    {

    }

    @ write_no_fpos @
    identifier write_f;
    identifier f, p, s, off;
    type ssize_t, size_t, loff_t;
    @@
    ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
    {
    ... when != off
    }

    @ fops0 @
    identifier fops;
    @@
    struct file_operations fops = {
    ...
    };

    @ has_llseek depends on fops0 @
    identifier fops0.fops;
    identifier llseek_f;
    @@
    struct file_operations fops = {
    ...
    .llseek = llseek_f,
    ...
    };

    @ has_read depends on fops0 @
    identifier fops0.fops;
    identifier read_f;
    @@
    struct file_operations fops = {
    ...
    .read = read_f,
    ...
    };

    @ has_write depends on fops0 @
    identifier fops0.fops;
    identifier write_f;
    @@
    struct file_operations fops = {
    ...
    .write = write_f,
    ...
    };

    @ has_open depends on fops0 @
    identifier fops0.fops;
    identifier open_f;
    @@
    struct file_operations fops = {
    ...
    .open = open_f,
    ...
    };

    // use no_llseek if we call nonseekable_open
    ////////////////////////////////////////////
    @ nonseekable1 depends on !has_llseek && has_open @
    identifier fops0.fops;
    identifier nso ~= "nonseekable_open";
    @@
    struct file_operations fops = {
    ... .open = nso, ...
    +.llseek = no_llseek, /* nonseekable */
    };

    @ nonseekable2 depends on !has_llseek @
    identifier fops0.fops;
    identifier open.open_f;
    @@
    struct file_operations fops = {
    ... .open = open_f, ...
    +.llseek = no_llseek, /* open uses nonseekable */
    };

    // use seq_lseek for sequential files
    /////////////////////////////////////
    @ seq depends on !has_llseek @
    identifier fops0.fops;
    identifier sr ~= "seq_read";
    @@
    struct file_operations fops = {
    ... .read = sr, ...
    +.llseek = seq_lseek, /* we have seq_read */
    };

    // use default_llseek if there is a readdir
    ///////////////////////////////////////////
    @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier readdir_e;
    @@
    // any other fop is used that changes pos
    struct file_operations fops = {
    ... .readdir = readdir_e, ...
    +.llseek = default_llseek, /* readdir is present */
    };

    // use default_llseek if at least one of read/write touches f_pos
    /////////////////////////////////////////////////////////////////
    @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier read.read_f;
    @@
    // read fops use offset
    struct file_operations fops = {
    ... .read = read_f, ...
    +.llseek = default_llseek, /* read accesses f_pos */
    };

    @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier write.write_f;
    @@
    // write fops use offset
    struct file_operations fops = {
    ... .write = write_f, ...
    + .llseek = default_llseek, /* write accesses f_pos */
    };

    // Use noop_llseek if neither read nor write accesses f_pos
    ///////////////////////////////////////////////////////////

    @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier read_no_fpos.read_f;
    identifier write_no_fpos.write_f;
    @@
    // write fops use offset
    struct file_operations fops = {
    ...
    .write = write_f,
    .read = read_f,
    ...
    +.llseek = noop_llseek, /* read and write both use no f_pos */
    };

    @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier write_no_fpos.write_f;
    @@
    struct file_operations fops = {
    ... .write = write_f, ...
    +.llseek = noop_llseek, /* write uses no f_pos */
    };

    @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    identifier read_no_fpos.read_f;
    @@
    struct file_operations fops = {
    ... .read = read_f, ...
    +.llseek = noop_llseek, /* read uses no f_pos */
    };

    @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
    identifier fops0.fops;
    @@
    struct file_operations fops = {
    ...
    +.llseek = noop_llseek, /* no read or write fn */
    };
    ===== End semantic patch =====

    Signed-off-by: Arnd Bergmann
    Cc: Julia Lawall
    Cc: Christoph Hellwig

    Arnd Bergmann
     

12 May, 2010

3 commits


20 Apr, 2010

1 commit


30 Mar, 2010

1 commit

  • …it slab.h inclusion from percpu.h

    percpu.h is included by sched.h and module.h and thus ends up being
    included when building most .c files. percpu.h includes slab.h which
    in turn includes gfp.h making everything defined by the two files
    universally available and complicating inclusion dependencies.

    percpu.h -> slab.h dependency is about to be removed. Prepare for
    this change by updating users of gfp and slab facilities include those
    headers directly instead of assuming availability. As this conversion
    needs to touch large number of source files, the following script is
    used as the basis of conversion.

    http://userweb.kernel.org/~tj/misc/slabh-sweep.py

    The script does the followings.

    * Scan files for gfp and slab usages and update includes such that
    only the necessary includes are there. ie. if only gfp is used,
    gfp.h, if slab is used, slab.h.

    * When the script inserts a new include, it looks at the include
    blocks and try to put the new include such that its order conforms
    to its surrounding. It's put in the include block which contains
    core kernel includes, in the same order that the rest are ordered -
    alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
    doesn't seem to be any matching order.

    * If the script can't find a place to put a new include (mostly
    because the file doesn't have fitting include block), it prints out
    an error message indicating which .h file needs to be added to the
    file.

    The conversion was done in the following steps.

    1. The initial automatic conversion of all .c files updated slightly
    over 4000 files, deleting around 700 includes and adding ~480 gfp.h
    and ~3000 slab.h inclusions. The script emitted errors for ~400
    files.

    2. Each error was manually checked. Some didn't need the inclusion,
    some needed manual addition while adding it to implementation .h or
    embedding .c file was more appropriate for others. This step added
    inclusions to around 150 files.

    3. The script was run again and the output was compared to the edits
    from #2 to make sure no file was left behind.

    4. Several build tests were done and a couple of problems were fixed.
    e.g. lib/decompress_*.c used malloc/free() wrappers around slab
    APIs requiring slab.h to be added manually.

    5. The script was run on all .h files but without automatically
    editing them as sprinkling gfp.h and slab.h inclusions around .h
    files could easily lead to inclusion dependency hell. Most gfp.h
    inclusion directives were ignored as stuff from gfp.h was usually
    wildly available and often used in preprocessor macros. Each
    slab.h inclusion directive was examined and added manually as
    necessary.

    6. percpu.h was updated not to include slab.h.

    7. Build test were done on the following configurations and failures
    were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
    distributed build env didn't work with gcov compiles) and a few
    more options had to be turned off depending on archs to make things
    build (like ipr on powerpc/64 which failed due to missing writeq).

    * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
    * powerpc and powerpc64 SMP allmodconfig
    * sparc and sparc64 SMP allmodconfig
    * ia64 SMP allmodconfig
    * s390 SMP allmodconfig
    * alpha SMP allmodconfig
    * um on x86_64 SMP allmodconfig

    8. percpu.h modifications were reverted so that it could be applied as
    a separate patch and serve as bisection point.

    Given the fact that I had only a couple of failures from tests on step
    6, I'm fairly confident about the coverage of this conversion patch.
    If there is a breakage, it's likely to be something in one of the arch
    headers which should be easily discoverable easily on most builds of
    the specific arch.

    Signed-off-by: Tejun Heo <tj@kernel.org>
    Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
    Cc: Ingo Molnar <mingo@redhat.com>
    Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>

    Tejun Heo
     

25 Mar, 2010

5 commits


23 Mar, 2010

1 commit

  • Commit 8ccb92ad (netfilter: xt_recent: fix false match) fixed supposedly
    false matches in rules using a zero hit_count. As it turns out there is
    nothing false about these matches and people are actually using entries
    with a hit_count of zero to make rules dependant on addresses inserted
    manually through /proc.

    Since this slipped past the eyes of three reviewers, instead of
    reverting the commit in question, this patch explicitly checks
    for a hit_count of zero to make the intentions more clear.

    Reported-by: Thomas Jarosch
    Tested-by: Thomas Jarosch
    Cc: stable@kernel.org
    Signed-off-by: Patrick McHardy

    Patrick McHardy
     

18 Mar, 2010

2 commits


17 Mar, 2010

5 commits


23 Feb, 2010

2 commits

  • A rule with a zero hit_count will always match.

    Signed-off-by: Tim Gardner
    Cc: stable@kernel.org
    Signed-off-by: Patrick McHardy

    Tim Gardner
     
  • e->index overflows e->stamps[] every ip_pkt_list_tot packets.

    Consider the case when ip_pkt_list_tot==1; the first packet received is stored
    in e->stamps[0] and e->index is initialized to 1. The next received packet
    timestamp is then stored at e->stamps[1] in recent_entry_update(),
    a buffer overflow because the maximum e->stamps[] index is 0.

    Signed-off-by: Tim Gardner
    Cc: stable@kernel.org
    Signed-off-by: Patrick McHardy

    Tim Gardner
     

15 Feb, 2010

1 commit


18 Jan, 2010

1 commit


04 Jan, 2010

1 commit


16 Dec, 2009

1 commit

  • Makes use of skip_spaces() defined in lib/string.c for removing leading
    spaces from strings all over the tree.

    It decreases lib.a code size by 47 bytes and reuses the function tree-wide:
    text data bss dec hex filename
    64688 584 592 65864 10148 (TOTALS-BEFORE)
    64641 584 592 65817 10119 (TOTALS-AFTER)

    Also, while at it, if we see (*str && isspace(*str)), we can be sure to
    remove the first condition (*str) as the second one (isspace(*str)) also
    evaluates to 0 whenever *str == 0, making it redundant. In other words,
    "a char equals zero is never a space".

    Julia Lawall tried the semantic patch (http://coccinelle.lip6.fr) below,
    and found occurrences of this pattern on 3 more files:
    drivers/leds/led-class.c
    drivers/leds/ledtrig-timer.c
    drivers/video/output.c

    @@
    expression str;
    @@

    ( // ignore skip_spaces cases
    while (*str && isspace(*str)) { \(str++;\|++str;\) }
    |
    - *str &&
    isspace(*str)
    )

    Signed-off-by: André Goddard Rosa
    Cc: Julia Lawall
    Cc: Martin Schwidefsky
    Cc: Jeff Dike
    Cc: Ingo Molnar
    Cc: Thomas Gleixner
    Cc: "H. Peter Anvin"
    Cc: Richard Purdie
    Cc: Neil Brown
    Cc: Kyle McMartin
    Cc: Henrique de Moraes Holschuh
    Cc: David Howells
    Cc:
    Cc: Samuel Ortiz
    Cc: Patrick McHardy
    Cc: Takashi Iwai
    Signed-off-by: Andrew Morton
    Signed-off-by: Linus Torvalds

    André Goddard Rosa
     

24 Apr, 2009

1 commit

  • Related-to: commit 325fb5b4d26038cba665dd0d8ee09555321061f0

    The compat path suffers from a similar problem. It only uses a __be32
    when all of the recent code uses, and expects, an nf_inet_addr
    everywhere. As a result, addresses stored by xt_recents were
    filled with whatever other stuff was on the stack following the be32.

    Signed-off-by: Jan Engelhardt

    With a minor compile fix from Roman.

    Reported-and-tested-by: Roman Hoog Antink
    Signed-off-by: Patrick McHardy

    Jan Engelhardt
     

24 Feb, 2009

1 commit

  • Fix regression introduded by commit 079aa88 (netfilter: xt_recent: IPv6 support):

    From http://bugzilla.kernel.org/show_bug.cgi?id=12753:

    Problem Description:
    An uninitialized buffer causes IPv4 addresses added manually (via the +IP
    command to the proc interface) to never match any packets. Similarly, the -IP
    command fails to remove IPv4 addresses.

    Details:
    In the function recent_entry_lookup, the xt_recent module does comparisons of
    the entire nf_inet_addr union value, both for IPv4 and IPv6 addresses. For
    addresses initialized from actual packets the remaining 12 bytes not occupied
    by the IPv4 are zeroed so this works correctly. However when setting the
    nf_inet_addr addr variable in the recent_mt_proc_write function, only the IPv4
    bytes are initialized and the remaining 12 bytes contain garbage.

    Hence addresses added in this way never match any packets, unless these
    uninitialized 12 bytes happened to be zero by coincidence. Similarly, addresses
    cannot consistently be removed using the proc interface due to mismatch of the
    garbage bytes (although it will sometimes work to remove an address that was
    added manually).

    Reading the /proc/net/xt_recent/ entries hides this problem because this only
    uses the first 4 bytes when displaying IPv4 addresses.

    Steps to reproduce:
    $ iptables -I INPUT -m recent --rcheck -j LOG
    $ echo +169.254.156.239 > /proc/net/xt_recent/DEFAULT
    $ cat /proc/net/xt_recent/DEFAULT
    src=169.254.156.239 ttl: 0 last_seen: 119910 oldest_pkt: 1 119910

    [At this point no packets from 169.254.156.239 are being logged.]

    $ iptables -I INPUT -s 169.254.156.239 -m recent --set
    $ cat /proc/net/xt_recent/DEFAULT
    src=169.254.156.239 ttl: 0 last_seen: 119910 oldest_pkt: 1 119910
    src=169.254.156.239 ttl: 255 last_seen: 126184 oldest_pkt: 4 125434, 125684, 125934, 126184

    [At this point, adding the address via an iptables rule, packets are being
    logged correctly.]

    $ echo -169.254.156.239 > /proc/net/xt_recent/DEFAULT
    $ cat /proc/net/xt_recent/DEFAULT
    src=169.254.156.239 ttl: 0 last_seen: 119910 oldest_pkt: 1 119910
    src=169.254.156.239 ttl: 255 last_seen: 126992 oldest_pkt: 10 125434, 125684, 125934, 126184, 126434, 126684, 126934, 126991, 126991, 126992
    $ echo -169.254.156.239 > /proc/net/xt_recent/DEFAULT
    $ cat /proc/net/xt_recent/DEFAULT
    src=169.254.156.239 ttl: 0 last_seen: 119910 oldest_pkt: 1 119910
    src=169.254.156.239 ttl: 255 last_seen: 126992 oldest_pkt: 10 125434, 125684, 125934, 126184, 126434, 126684, 126934, 126991, 126991, 126992

    [Removing the address via /proc interface failed evidently.]

    Possible solutions:
    - initialize the addr variable in recent_mt_proc_write
    - compare only 4 bytes for IPv4 addresses in recent_entry_lookup

    Signed-off-by: Patrick McHardy

    Josef Drexler
     

20 Nov, 2008

1 commit


31 Oct, 2008

1 commit


30 Oct, 2008

1 commit


29 Oct, 2008

1 commit


20 Oct, 2008

1 commit

  • Fixes a crash in recent_seq_start:

    BUG: unable to handle kernel NULL pointer dereference at 0000000000000100
    IP: [] recent_seq_start+0x4c/0x90 [xt_recent]
    PGD 17d33c067 PUD 107afe067 PMD 0
    Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
    CPU 0
    Modules linked in: ipt_LOG xt_recent af_packet iptable_nat nf_nat nf_conntrack_ipv4 nf_conntrack nf_defrag_ipv4 xt_tcpudp iptable_filter ip_tables x_tables ext2 nls_utf8 fuse sr_mod cdrom [last unloaded: ntfs]
    Pid: 32373, comm: cat Not tainted 2.6.27-04ab591808565f968d4406f6435090ad671ebdab #6
    RIP: 0010:[] [] recent_seq_start+0x4c/0x90 [xt_recent]
    RSP: 0018:ffff88015fed7e28 EFLAGS: 00010246
    ...

    Signed-off-by: Alexey Dobriyan
    Signed-off-by: Patrick McHardy
    Signed-off-by: David S. Miller

    Alexey Dobriyan
     

08 Oct, 2008

6 commits