linux-stable.git/fs/dlm/user.c, branch linux-3.16.y

dlm: avoid double-free on error path in dlm_device_{register,unregister}

2017-11-26T13:50:16+00:00

commit 55acdd926f6b21a5cdba23da98a48aedf19ac9c3 upstream.

Can be reproduced when running dlm_controld (tested on 4.4.x, 4.12.4):
 # seq 1 100 | xargs -P0 -n1 dlm_tool join
 # seq 1 100 | xargs -P0 -n1 dlm_tool leave

misc_register fails due to duplicate sysfs entry, which causes
dlm_device_register to free ls->ls_device.name.
In dlm_device_deregister the name was freed again, causing memory
corruption.

According to the comment in dlm_device_deregister the name should've been
set to NULL when registration fails,
so this patch does that.

sysfs: cannot create duplicate filename '/dev/char/10:1'
------------[ cut here ]------------
warning: cpu: 1 pid: 4450 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x56/0x70
modules linked in: msr rfcomm dlm ccm bnep dm_crypt uvcvideo
videobuf2_vmalloc videobuf2_memops videobuf2_v4l2 videobuf2_core videodev
btusb media btrtl btbcm btintel bluetooth ecdh_generic intel_rapl
x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm
snd_hda_codec_hdmi irqbypass crct10dif_pclmul crc32_pclmul
ghash_clmulni_intel thinkpad_acpi pcbc nvram snd_seq_midi
snd_seq_midi_event aesni_intel snd_hda_codec_realtek snd_hda_codec_generic
snd_rawmidi aes_x86_64 crypto_simd glue_helper snd_hda_intel snd_hda_codec
cryptd intel_cstate arc4 snd_hda_core snd_seq snd_seq_device snd_hwdep
iwldvm intel_rapl_perf mac80211 joydev input_leds iwlwifi serio_raw
cfg80211 snd_pcm shpchp snd_timer snd mac_hid mei_me lpc_ich mei soundcore
sunrpc parport_pc ppdev lp parport autofs4 i915 psmouse
 e1000e ahci libahci i2c_algo_bit sdhci_pci ptp drm_kms_helper sdhci
pps_core syscopyarea sysfillrect sysimgblt fb_sys_fops drm wmi video
cpu: 1 pid: 4450 comm: dlm_test.exe not tainted 4.12.4-041204-generic
hardware name: lenovo 232425u/232425u, bios g2et82ww (2.02 ) 09/11/2012
task: ffff96b0cbabe140 task.stack: ffffb199027d0000
rip: 0010:sysfs_warn_dup+0x56/0x70
rsp: 0018:ffffb199027d3c58 eflags: 00010282
rax: 0000000000000038 rbx: ffff96b0e2c49158 rcx: 0000000000000006
rdx: 0000000000000000 rsi: 0000000000000086 rdi: ffff96b15e24dcc0
rbp: ffffb199027d3c70 r08: 0000000000000001 r09: 0000000000000721
r10: ffffb199027d3c00 r11: 0000000000000721 r12: ffffb199027d3cd1
r13: ffff96b1592088f0 r14: 0000000000000001 r15: ffffffffffffffef
fs:  00007f78069c0700(0000) gs:ffff96b15e240000(0000)
knlgs:0000000000000000
cs:  0010 ds: 0000 es: 0000 cr0: 0000000080050033
cr2: 000000178625ed28 cr3: 0000000091d3e000 cr4: 00000000001406e0
call trace:
 sysfs_do_create_link_sd.isra.2+0x9e/0xb0
 sysfs_create_link+0x25/0x40
 device_add+0x5a9/0x640
 device_create_groups_vargs+0xe0/0xf0
 device_create_with_groups+0x3f/0x60
 ? snprintf+0x45/0x70
 misc_register+0x140/0x180
 device_write+0x6a8/0x790 [dlm]
 __vfs_write+0x37/0x160
 ? apparmor_file_permission+0x1a/0x20
 ? security_file_permission+0x3b/0xc0
 vfs_write+0xb5/0x1a0
 sys_write+0x55/0xc0
 ? sys_fcntl+0x5d/0xb0
 entry_syscall_64_fastpath+0x1e/0xa9
rip: 0033:0x7f78083454bd
rsp: 002b:00007f78069bbd30 eflags: 00000293 orig_rax: 0000000000000001
rax: ffffffffffffffda rbx: 0000000000000006 rcx: 00007f78083454bd
rdx: 000000000000009c rsi: 00007f78069bee00 rdi: 0000000000000005
rbp: 00007f77f8000a20 r08: 000000000000fcf0 r09: 0000000000000032
r10: 0000000000000024 r11: 0000000000000293 r12: 00007f78069bde00
r13: 00007f78069bee00 r14: 000000000000000a r15: 00007f78069bbd70
code: 85 c0 48 89 c3 74 12 b9 00 10 00 00 48 89 c2 31 f6 4c 89 ef e8 2c c8
ff ff 4c 89 e2 48 89 de 48 c7 c7 b0 8e 0c a8 e8 41 e8 ed ff <0f> ff 48 89
df e8 00 d5 f4 ff 5b 41 5c 41 5d 5d c3 66 0f 1f 84
---[ end trace 40412246357cc9e0 ]---

dlm: 59f24629-ae39-44e2-9030-397ebc2eda26: leaving the lockspace group...
bug: unable to handle kernel null pointer dereference at 0000000000000001
ip: [] kmem_cache_alloc+0x7a/0x140
pgd 0
oops: 0000 [#1] smp
modules linked in: dlm 8021q garp mrp stp llc openvswitch nf_defrag_ipv6
nf_conntrack libcrc32c iptable_filter dm_multipath crc32_pclmul dm_mod
aesni_intel psmouse aes_x86_64 sg ablk_helper cryptd lrw gf128mul
glue_helper i2c_piix4 nls_utf8 tpm_tis tpm isofs nfsd auth_rpcgss
oid_registry nfs_acl lockd grace sunrpc xen_wdt ip_tables x_tables autofs4
hid_generic usbhid hid sr_mod cdrom sd_mod ata_generic pata_acpi 8139too
serio_raw ata_piix 8139cp mii uhci_hcd ehci_pci ehci_hcd libata
scsi_dh_rdac scsi_dh_hp_sw scsi_dh_emc scsi_dh_alua scsi_mod ipv6
cpu: 0 pid: 394 comm: systemd-udevd tainted: g w 4.4.0+0 #1
hardware name: xen hvm domu, bios 4.7.2-2.2 05/11/2017
task: ffff880002410000 ti: ffff88000243c000 task.ti: ffff88000243c000
rip: e030:[] []
kmem_cache_alloc+0x7a/0x140
rsp: e02b:ffff88000243fd90 eflags: 00010202
rax: 0000000000000000 rbx: ffff8800029864d0 rcx: 000000000007b36c
rdx: 000000000007b36b rsi: 00000000024000c0 rdi: ffff880036801c00
rbp: ffff88000243fdc0 r08: 0000000000018880 r09: 0000000000000054
r10: 000000000000004a r11: ffff880034ace6c0 r12: 00000000024000c0
r13: ffff880036801c00 r14: 0000000000000001 r15: ffffffff8118dcc2
fs: 00007f0ab77548c0(0000) gs:ffff880036e00000(0000) knlgs:0000000000000000
cs: e033 ds: 0000 es: 0000 cr0: 0000000080050033
cr2: 0000000000000001 cr3: 000000000332d000 cr4: 0000000000040660
stack:
ffffffff8118dc90 ffff8800029864d0 0000000000000000 ffff88003430b0b0
ffff880034b78320 ffff88003430b0b0 ffff88000243fdf8 ffffffff8118dcc2
ffff8800349c6700 ffff8800029864d0 000000000000000b 00007f0ab7754b90
call trace:
[] ? anon_vma_fork+0x60/0x140
[] anon_vma_fork+0x92/0x140
[] copy_process+0xcae/0x1a80
[] _do_fork+0x8b/0x2d0
[] sys_clone+0x19/0x20
[] entry_syscall_64_fastpath+0x12/0x71
] code: f6 75 1c 4c 89 fa 44 89 e6 4c 89 ef e8 a7 e4 00 00 41 f7 c4 00 80
00 00 49 89 c6 74 47 eb 32 49 63 45 20 48 8d 4a 01 4d 8b 45 00 <49> 8b 1c
06 4c 89 f0 65 49 0f c7 08 0f 94 c0 84 c0 74 ac 49 63
rip [] kmem_cache_alloc+0x7a/0x140
rsp 
cr2: 0000000000000001
--[ end trace 70cb9fd1b164a0e8 ]--

Signed-off-by: Edwin Török 
Signed-off-by: David Teigland 
Signed-off-by: Ben Hutchings

dlm: remove signal blocking

2013-08-12T20:22:43+00:00

The signal blocking was incorrect and unnecessary
so just remove it.

Signed-off-by: David Teigland

dlm: check the write size from user

2013-02-04T21:31:22+00:00

Return EINVAL from write if the size is larger than
allowed.  Do this before allocating kernel memory for
the bogus size, which could lead to OOM.

Reported-by: Sasha Levin 
Tested-by: Jana Saout 
Signed-off-by: David Teigland

dlm: check the maximum size of a request from user

2012-09-10T14:50:27+00:00

device_write only checks whether the request size is big enough, but it doesn't
check if the size is too big.

At that point, it also tries to allocate as much memory as the user has requested
even if it's too much. This can lead to OOM killer kicking in, or memory corruption
if (count + 1) overflows.

Signed-off-by: Sasha Levin 
Signed-off-by: David Teigland

dlm: add recovery callbacks

2012-01-04T14:56:31+00:00

These new callbacks notify the dlm user about lock recovery.
GFS2, and possibly others, need to be aware of when the dlm
will be doing lock recovery for a failed lockspace member.

In the past, this coordination has been done between dlm and
file system daemons in userspace, which then direct their
kernel counterparts.  These callbacks allow the same
coordination directly, and more simply.

Signed-off-by: David Teigland

dlm: use workqueue for callbacks

2011-07-15T17:30:43+00:00

Instead of creating our own kthread (dlm_astd) to deliver
callbacks for all lockspaces, use a per-lockspace workqueue
to deliver the callbacks.  This eliminates complications and
slowdowns from many lockspaces sharing the same thread.

Signed-off-by: David Teigland

dlm: Remove superfluous call to recalc_sigpending()

2011-03-28T15:20:17+00:00

recalc_sigpending() is called within sigprocmask(), so there is no
need call it again after sigprocmask() has returned.

Signed-off-by: Matt Fleming 
Signed-off-by: David Teigland

dlm: record full callback state

2011-03-10T16:40:00+00:00

Change how callbacks are recorded for locks.  Previously, information
about multiple callbacks was combined into a couple of variables that
indicated what the end result should be.  In some situations, we
could not tell from this combined state what the exact sequence of
callbacks were, and would end up either delivering the callbacks in
the wrong order, or suppress redundant callbacks incorrectly.  This
new approach records all the data for each callback, leaving no
uncertainty about what needs to be delivered.

Signed-off-by: David Teigland

llseek: automatically add .llseek fop

2010-10-15T13:53:27+00:00

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(...)
{
<+...
nonseekable_open(...)
...+>
}

@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}

@ 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)
{
<+...
(
   *off = E
|
   *off += E
|
   func(..., off, ...)
|
   E = *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)
{
<+...
(
  *off = E
|
  *off += E
|
  func(..., off, ...)
|
  E = *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

dlm: fix ast ordering for user locks

2010-04-30T19:52:51+00:00

Commit 7fe2b3190b8b299409f13cf3a6f85c2bd371f8bb fixed possible
misordering of completion asts (casts) and blocking asts (basts)
for kernel locks.  This patch does the same for locks taken by
user space applications.

Signed-off-by: David Teigland