[00/16] 2.6.32.51-longterm review

[00/16] 2.6.32.51-longterm review

[Greg KH]

This is the start of the longterm review cycle for the 2.6.32.51 release.
There are 16 patches in this series, all will be posted as a response
to this one.  If anyone has any issues with these being applied, please
let us know.  If anyone is a maintainer of the proper subsystem, and
wants to add a Signed-off-by: line to the patch, please respond with it.

Responses should be made by December 19, 2011, 18:00:00 UTC
Anything received after that time might be too late.

The whole patch series can be found in one patch at:
	kernel.org/pub/linux/kernel/v2.6/longterm-review/patch-2.6.32.51-rc1.gz
and the diffstat can be found below.

thanks,

greg k-h


 Makefile                                 |    2 +-
 arch/arm/mach-davinci/board-dm646x-evm.c |    6 +-
 arch/x86/oprofile/backtrace.c            |   46 +++++++++++++++++++--
 arch/x86/oprofile/nmi_int.c              |    8 ++--
 drivers/oprofile/buffer_sync.c           |   21 +++++-----
 drivers/usb/class/cdc-acm.c              |   10 +++++
 fs/ext4/inode.c                          |    2 +-
 fs/hfs/btree.c                           |   20 +++++++--
 fs/jbd/journal.c                         |    8 ++++
 fs/jbd2/journal.c                        |    8 ++++
 include/linux/log2.h                     |    1 -
 kernel/taskstats.c                       |    1 +
 mm/percpu.c                              |   32 +++++++++------
 mm/util.c                                |   13 ++++++
 net/xfrm/xfrm_algo.c                     |    4 +-
 sound/pci/hda/patch_realtek.c            |    2 +
 sound/pci/sis7019.c                      |   64 ++++++++++++++++++++++++-----
 17 files changed, 193 insertions(+), 55 deletions(-)

[01/16] ALSA: sis7019 - give slow codecs more time to reset

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: David Dillow <dave@thedillows.org>

commit fc084e0b930d546872ab23667052499f7daf0fed upstream.

There are some AC97 codec and board combinations that have been observed
to take a very long time to respond after the cold reset has completed.
In one case, more than 350 ms was required. To allow users to have sound
on those platforms, we'll wait up to 500ms for the codec to become
ready.

As a board may have multiple codecs, with some faster than others to
reset, we add a module parameter to inform the driver which codecs
should be present.

Reported-by: KotCzarny <tjosko@yahoo.com>
Signed-off-by: David Dillow <dave@thedillows.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 sound/pci/sis7019.c |   64 +++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 53 insertions(+), 11 deletions(-)

--- a/sound/pci/sis7019.c
+++ b/sound/pci/sis7019.c
@@ -40,6 +40,7 @@ MODULE_SUPPORTED_DEVICE("{{SiS,SiS7019 A
 static int index = SNDRV_DEFAULT_IDX1;	/* Index 0-MAX */
 static char *id = SNDRV_DEFAULT_STR1;	/* ID for this card */
 static int enable = 1;
+static int codecs = 1;
 
 module_param(index, int, 0444);
 MODULE_PARM_DESC(index, "Index value for SiS7019 Audio Accelerator.");
@@ -47,6 +48,8 @@ module_param(id, charp, 0444);
 MODULE_PARM_DESC(id, "ID string for SiS7019 Audio Accelerator.");
 module_param(enable, bool, 0444);
 MODULE_PARM_DESC(enable, "Enable SiS7019 Audio Accelerator.");
+module_param(codecs, int, 0444);
+MODULE_PARM_DESC(codecs, "Set bit to indicate that codec number is expected to be present (default 1)");
 
 static struct pci_device_id snd_sis7019_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SI, 0x7019) },
@@ -139,6 +142,9 @@ struct sis7019 {
 	dma_addr_t silence_dma_addr;
 };
 
+/* These values are also used by the module param 'codecs' to indicate
+ * which codecs should be present.
+ */
 #define SIS_PRIMARY_CODEC_PRESENT	0x0001
 #define SIS_SECONDARY_CODEC_PRESENT	0x0002
 #define SIS_TERTIARY_CODEC_PRESENT	0x0004
@@ -1075,6 +1081,7 @@ static int sis_chip_init(struct sis7019
 {
 	unsigned long io = sis->ioport;
 	void __iomem *ioaddr = sis->ioaddr;
+	unsigned long timeout;
 	u16 status;
 	int count;
 	int i;
@@ -1101,21 +1108,45 @@ static int sis_chip_init(struct sis7019
 	while ((inw(io + SIS_AC97_STATUS) & SIS_AC97_STATUS_BUSY) && --count)
 		udelay(1);
 
-	/* Now that we've finished the reset, find out what's attached.
+	/* Command complete, we can let go of the semaphore now.
 	 */
-	status = inl(io + SIS_AC97_STATUS);
-	if (status & SIS_AC97_STATUS_CODEC_READY)
-		sis->codecs_present |= SIS_PRIMARY_CODEC_PRESENT;
-	if (status & SIS_AC97_STATUS_CODEC2_READY)
-		sis->codecs_present |= SIS_SECONDARY_CODEC_PRESENT;
-	if (status & SIS_AC97_STATUS_CODEC3_READY)
-		sis->codecs_present |= SIS_TERTIARY_CODEC_PRESENT;
+	outl(SIS_AC97_SEMA_RELEASE, io + SIS_AC97_SEMA);
+	if (!count)
+		return -EIO;
+
+	/* Now that we've finished the reset, find out what's attached.
+	 * There are some codec/board combinations that take an extremely
+	 * long time to come up. 350+ ms has been observed in the field,
+	 * so we'll give them up to 500ms.
+	 */
+	sis->codecs_present = 0;
+	timeout = msecs_to_jiffies(500) + jiffies;
+	while (time_before_eq(jiffies, timeout)) {
+		status = inl(io + SIS_AC97_STATUS);
+		if (status & SIS_AC97_STATUS_CODEC_READY)
+			sis->codecs_present |= SIS_PRIMARY_CODEC_PRESENT;
+		if (status & SIS_AC97_STATUS_CODEC2_READY)
+			sis->codecs_present |= SIS_SECONDARY_CODEC_PRESENT;
+		if (status & SIS_AC97_STATUS_CODEC3_READY)
+			sis->codecs_present |= SIS_TERTIARY_CODEC_PRESENT;
+
+		if (sis->codecs_present == codecs)
+			break;
 
-	/* All done, let go of the semaphore, and check for errors
+		msleep(1);
+	}
+
+	/* All done, check for errors.
 	 */
-	outl(SIS_AC97_SEMA_RELEASE, io + SIS_AC97_SEMA);
-	if (!sis->codecs_present || !count)
+	if (!sis->codecs_present) {
+		printk(KERN_ERR "sis7019: could not find any codecs\n");
 		return -EIO;
+	}
+
+	if (sis->codecs_present != codecs) {
+		printk(KERN_WARNING "sis7019: missing codecs, found %0x, expected %0x\n",
+		       sis->codecs_present, codecs);
+	}
 
 	/* Let the hardware know that the audio driver is alive,
 	 * and enable PCM slots on the AC-link for L/R playback (3 & 4) and
@@ -1387,6 +1418,17 @@ static int __devinit snd_sis7019_probe(s
 	if (!enable)
 		goto error_out;
 
+	/* The user can specify which codecs should be present so that we
+	 * can wait for them to show up if they are slow to recover from
+	 * the AC97 cold reset. We default to a single codec, the primary.
+	 *
+	 * We assume that SIS_PRIMARY_*_PRESENT matches bits 0-2.
+	 */
+	codecs &= SIS_PRIMARY_CODEC_PRESENT | SIS_SECONDARY_CODEC_PRESENT |
+		  SIS_TERTIARY_CODEC_PRESENT;
+	if (!codecs)
+		codecs = SIS_PRIMARY_CODEC_PRESENT;
+
 	rc = snd_card_create(index, id, THIS_MODULE, sizeof(*sis), &card);
 	if (rc < 0)
 		goto error_out;

[02/16] ALSA: hda/realtek - Fix Oops in alc_mux_select()

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <tiwai@suse.de>

commit cce4aa378a049f4275416ee6302dd24f37b289df upstream.

When no imux is available (e.g. a single capture source),
alc_auto_init_input_src() may trigger an Oops due to the access to -1.
Add a proper zero-check to avoid it.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 sound/pci/hda/patch_realtek.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -432,6 +432,8 @@ static int alc_mux_enum_put(struct snd_k
 	imux = &spec->input_mux[mux_idx];
 	if (!imux->num_items && mux_idx > 0)
 		imux = &spec->input_mux[0];
+	if (!imux->num_items)
+		return 0;
 
 	type = get_wcaps_type(get_wcaps(codec, nid));
 	if (type == AC_WID_AUD_MIX) {

[03/16] ARM: davinci: dm646x evm: wrong register used in setup_vpif_input_channel_mode

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Hans Verkuil <hans.verkuil@cisco.com>

commit 83713fc9373be2e943f82e9d36213708c6b0050e upstream.

The function setup_vpif_input_channel_mode() used the VSCLKDIS register
instead of VIDCLKCTL. This meant that when in HD mode videoport channel 0
used a different clock from channel 1.

Clearly a copy-and-paste error.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Manjunath Hadli <manjunath.hadli@ti.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/arm/mach-davinci/board-dm646x-evm.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -502,7 +502,7 @@ static int setup_vpif_input_channel_mode
 	int val;
 	u32 value;
 
-	if (!vpif_vsclkdis_reg || !cpld_client)
+	if (!vpif_vidclkctl_reg || !cpld_client)
 		return -ENXIO;
 
 	val = i2c_smbus_read_byte(cpld_client);
@@ -510,7 +510,7 @@ static int setup_vpif_input_channel_mode
 		return val;
 
 	spin_lock_irqsave(&vpif_reg_lock, flags);
-	value = __raw_readl(vpif_vsclkdis_reg);
+	value = __raw_readl(vpif_vidclkctl_reg);
 	if (mux_mode) {
 		val &= VPIF_INPUT_TWO_CHANNEL;
 		value |= VIDCH1CLK;
@@ -518,7 +518,7 @@ static int setup_vpif_input_channel_mode
 		val |= VPIF_INPUT_ONE_CHANNEL;
 		value &= ~VIDCH1CLK;
 	}
-	__raw_writel(value, vpif_vsclkdis_reg);
+	__raw_writel(value, vpif_vidclkctl_reg);
 	spin_unlock_irqrestore(&vpif_reg_lock, flags);
 
 	err = i2c_smbus_write_byte(cpld_client, val);

[04/16] oprofile: Free potentially owned tasks in case of errors

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Robert Richter <robert.richter@amd.com>

commit 6ac6519b93065625119a347be1cbcc1b89edb773 upstream.

After registering the task free notifier we possibly have tasks in our
dying_tasks list. Free them after unregistering the notifier in case
of an error.

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/oprofile/buffer_sync.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -140,6 +140,13 @@ static struct notifier_block module_load
 	.notifier_call = module_load_notify,
 };
 
+static void free_all_tasks(void)
+{
+	/* make sure we don't leak task structs */
+	process_task_mortuary();
+	process_task_mortuary();
+}
+
 int sync_start(void)
 {
 	int err;
@@ -173,6 +180,7 @@ out3:
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 out2:
 	task_handoff_unregister(&task_free_nb);
+	free_all_tasks();
 out1:
 	free_cpumask_var(marked_cpus);
 	goto out;
@@ -191,10 +199,7 @@ void sync_stop(void)
 	mutex_unlock(&buffer_mutex);
 	flush_scheduled_work();
 
-	/* make sure we don't leak task structs */
-	process_task_mortuary();
-	process_task_mortuary();
-
+	free_all_tasks();
 	free_cpumask_var(marked_cpus);
 }
 

[05/16] oprofile: Fix locking dependency in sync_start()

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Robert Richter <robert.richter@amd.com>

commit 130c5ce716c9bfd1c2a2ec840a746eb7ff9ce1e6 upstream.

This fixes the A->B/B->A locking dependency, see the warning below.

The function task_exit_notify() is called with (task_exit_notifier)
.rwsem set and then calls sync_buffer() which locks buffer_mutex. In
sync_start() the buffer_mutex was set to prevent notifier functions to
be started before sync_start() is finished. But when registering the
notifier, (task_exit_notifier).rwsem is locked too, but now in
different order than in sync_buffer(). In theory this causes a locking
dependency, what does not occur in practice since task_exit_notify()
is always called after the notifier is registered which means the lock
is already released.

However, after checking the notifier functions it turned out the
buffer_mutex in sync_start() is unnecessary. This is because
sync_buffer() may be called from the notifiers even if sync_start()
did not finish yet, the buffers are already allocated but empty. No
need to protect this with the mutex.

So we fix this theoretical locking dependency by removing buffer_mutex
in sync_start(). This is similar to the implementation before commit:

 750d857 oprofile: fix crash when accessing freed task structs

which introduced the locking dependency.

Lockdep warning:

oprofiled/4447 is trying to acquire lock:
 (buffer_mutex){+.+...}, at: [<ffffffffa0000e55>] sync_buffer+0x31/0x3ec [oprofile]

but task is already holding lock:
 ((task_exit_notifier).rwsem){++++..}, at: [<ffffffff81058026>] __blocking_notifier_call_chain+0x39/0x67

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 ((task_exit_notifier).rwsem){++++..}:
       [<ffffffff8106557f>] lock_acquire+0xf8/0x11e
       [<ffffffff81463a2b>] down_write+0x44/0x67
       [<ffffffff810581c0>] blocking_notifier_chain_register+0x52/0x8b
       [<ffffffff8105a6ac>] profile_event_register+0x2d/0x2f
       [<ffffffffa00013c1>] sync_start+0x47/0xc6 [oprofile]
       [<ffffffffa00001bb>] oprofile_setup+0x60/0xa5 [oprofile]
       [<ffffffffa00014e3>] event_buffer_open+0x59/0x8c [oprofile]
       [<ffffffff810cd3b9>] __dentry_open+0x1eb/0x308
       [<ffffffff810cd59d>] nameidata_to_filp+0x60/0x67
       [<ffffffff810daad6>] do_last+0x5be/0x6b2
       [<ffffffff810dbc33>] path_openat+0xc7/0x360
       [<ffffffff810dbfc5>] do_filp_open+0x3d/0x8c
       [<ffffffff810ccfd2>] do_sys_open+0x110/0x1a9
       [<ffffffff810cd09e>] sys_open+0x20/0x22
       [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b

-> #0 (buffer_mutex){+.+...}:
       [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711
       [<ffffffff8106557f>] lock_acquire+0xf8/0x11e
       [<ffffffff814634f0>] mutex_lock_nested+0x63/0x309
       [<ffffffffa0000e55>] sync_buffer+0x31/0x3ec [oprofile]
       [<ffffffffa0001226>] task_exit_notify+0x16/0x1a [oprofile]
       [<ffffffff81467b96>] notifier_call_chain+0x37/0x63
       [<ffffffff8105803d>] __blocking_notifier_call_chain+0x50/0x67
       [<ffffffff81058068>] blocking_notifier_call_chain+0x14/0x16
       [<ffffffff8105a718>] profile_task_exit+0x1a/0x1c
       [<ffffffff81039e8f>] do_exit+0x2a/0x6fc
       [<ffffffff8103a5e4>] do_group_exit+0x83/0xae
       [<ffffffff8103a626>] sys_exit_group+0x17/0x1b
       [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b

other info that might help us debug this:

1 lock held by oprofiled/4447:
 #0:  ((task_exit_notifier).rwsem){++++..}, at: [<ffffffff81058026>] __blocking_notifier_call_chain+0x39/0x67

stack backtrace:
Pid: 4447, comm: oprofiled Not tainted 2.6.39-00007-gcf4d8d4 #10
Call Trace:
 [<ffffffff81063193>] print_circular_bug+0xae/0xbc
 [<ffffffff81064dfb>] __lock_acquire+0x1085/0x1711
 [<ffffffffa0000e55>] ? sync_buffer+0x31/0x3ec [oprofile]
 [<ffffffff8106557f>] lock_acquire+0xf8/0x11e
 [<ffffffffa0000e55>] ? sync_buffer+0x31/0x3ec [oprofile]
 [<ffffffff81062627>] ? mark_lock+0x42f/0x552
 [<ffffffffa0000e55>] ? sync_buffer+0x31/0x3ec [oprofile]
 [<ffffffff814634f0>] mutex_lock_nested+0x63/0x309
 [<ffffffffa0000e55>] ? sync_buffer+0x31/0x3ec [oprofile]
 [<ffffffffa0000e55>] sync_buffer+0x31/0x3ec [oprofile]
 [<ffffffff81058026>] ? __blocking_notifier_call_chain+0x39/0x67
 [<ffffffff81058026>] ? __blocking_notifier_call_chain+0x39/0x67
 [<ffffffffa0001226>] task_exit_notify+0x16/0x1a [oprofile]
 [<ffffffff81467b96>] notifier_call_chain+0x37/0x63
 [<ffffffff8105803d>] __blocking_notifier_call_chain+0x50/0x67
 [<ffffffff81058068>] blocking_notifier_call_chain+0x14/0x16
 [<ffffffff8105a718>] profile_task_exit+0x1a/0x1c
 [<ffffffff81039e8f>] do_exit+0x2a/0x6fc
 [<ffffffff81465031>] ? retint_swapgs+0xe/0x13
 [<ffffffff8103a5e4>] do_group_exit+0x83/0xae
 [<ffffffff8103a626>] sys_exit_group+0x17/0x1b
 [<ffffffff8146ad4b>] system_call_fastpath+0x16/0x1b

Reported-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Carl Love <carll@us.ibm.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/oprofile/buffer_sync.c |    8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -154,8 +154,6 @@ int sync_start(void)
 	if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&buffer_mutex);
-
 	err = task_handoff_register(&task_free_nb);
 	if (err)
 		goto out1;
@@ -172,7 +170,6 @@ int sync_start(void)
 	start_cpu_work();
 
 out:
-	mutex_unlock(&buffer_mutex);
 	return err;
 out4:
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
@@ -189,14 +186,13 @@ out1:
 
 void sync_stop(void)
 {
-	/* flush buffers */
-	mutex_lock(&buffer_mutex);
 	end_cpu_work();
 	unregister_module_notifier(&module_load_nb);
 	profile_event_unregister(PROFILE_MUNMAP, &munmap_nb);
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
-	mutex_unlock(&buffer_mutex);
+	barrier();			/* do all of the above first */
+
 	flush_scheduled_work();
 
 	free_all_tasks();

[06/16] percpu: fix chunk range calculation

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Tejun Heo <tj@kernel.org>

commit a855b84c3d8c73220d4d3cd392a7bee7c83de70e upstream.

Percpu allocator recorded the cpus which map to the first and last
units in pcpu_first/last_unit_cpu respectively and used them to
determine the address range of a chunk - e.g. it assumed that the
first unit has the lowest address in a chunk while the last unit has
the highest address.

This simply isn't true.  Groups in a chunk can have arbitrary positive
or negative offsets from the previous one and there is no guarantee
that the first unit occupies the lowest offset while the last one the
highest.

Fix it by actually comparing unit offsets to determine cpus occupying
the lowest and highest offsets.  Also, rename pcu_first/last_unit_cpu
to pcpu_low/high_unit_cpu to avoid confusion.

The chunk address range is used to flush cache on vmalloc area
map/unmap and decide whether a given address is in the first chunk by
per_cpu_ptr_to_phys() and the bug was discovered by invalid
per_cpu_ptr_to_phys() translation for crash_note.

Kudos to Dave Young for tracking down the problem.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: WANG Cong <xiyou.wangcong@gmail.com>
Reported-by: Dave Young <dyoung@redhat.com>
Tested-by: Dave Young <dyoung@redhat.com>
LKML-Reference: <4EC21F67.10905@redhat.com>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 mm/percpu.c |   32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -110,9 +110,9 @@ static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
 
 /* the address of the first chunk which starts with the kernel static area */
 void *pcpu_base_addr __read_mostly;
@@ -746,8 +746,8 @@ static void pcpu_pre_unmap_flush(struct
 				 int page_start, int page_end)
 {
 	flush_cache_vunmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
@@ -809,8 +809,8 @@ static void pcpu_post_unmap_tlb_flush(st
 				      int page_start, int page_end)
 {
 	flush_tlb_kernel_range(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static int __pcpu_map_pages(unsigned long addr, struct page **pages,
@@ -887,8 +887,8 @@ static void pcpu_post_map_flush(struct p
 				int page_start, int page_end)
 {
 	flush_cache_vmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 /**
@@ -1680,7 +1680,9 @@ int __init pcpu_setup_first_chunk(const
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
-	pcpu_first_unit_cpu = NR_CPUS;
+
+	pcpu_low_unit_cpu = NR_CPUS;
+	pcpu_high_unit_cpu = NR_CPUS;
 
 	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
 		const struct pcpu_group_info *gi = &ai->groups[group];
@@ -1700,9 +1702,13 @@ int __init pcpu_setup_first_chunk(const
 			unit_map[cpu] = unit + i;
 			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
 
-			if (pcpu_first_unit_cpu == NR_CPUS)
-				pcpu_first_unit_cpu = cpu;
-			pcpu_last_unit_cpu = cpu;
+			/* determine low/high unit_cpu */
+			if (pcpu_low_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+				pcpu_low_unit_cpu = cpu;
+			if (pcpu_high_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+				pcpu_high_unit_cpu = cpu;
 		}
 	}
 	pcpu_nr_units = unit;

[07/16] xfrm: Fix key lengths for rfc3686(ctr(aes))

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Tushar Gohad <tgohad@mvista.com>

commit 4203223a1aed862b4445fdcd260d6139603a51d9 upstream.

Fix the min and max bit lengths for AES-CTR (RFC3686) keys.
The number of bits in key spec is the key length (128/256)
plus 32 bits of nonce.

This change takes care of the "Invalid key length" errors
reported by setkey when specifying 288 bit keys for aes-ctr.

Signed-off-by: Tushar Gohad <tgohad@mvista.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Calvin Owens <jcalvinowens@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/xfrm/xfrm_algo.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -411,8 +411,8 @@ static struct xfrm_algo_desc ealg_list[]
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AESCTR,
 		.sadb_alg_ivlen	= 8,
-		.sadb_alg_minbits = 128,
-		.sadb_alg_maxbits = 256
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 288
 	}
 },
 };

[07/16] xfrm: Fix key lengths for rfc3686(ctr(aes))

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Tushar Gohad <tgohad@mvista.com>

commit 4203223a1aed862b4445fdcd260d6139603a51d9 upstream.

Fix the min and max bit lengths for AES-CTR (RFC3686) keys.
The number of bits in key spec is the key length (128/256)
plus 32 bits of nonce.

This change takes care of the "Invalid key length" errors
reported by setkey when specifying 288 bit keys for aes-ctr.

Signed-off-by: Tushar Gohad <tgohad@mvista.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Calvin Owens <jcalvinowens@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/xfrm/xfrm_algo.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/xfrm/xfrm_algo.c
+++ b/net/xfrm/xfrm_algo.c
@@ -411,8 +411,8 @@ static struct xfrm_algo_desc ealg_list[]
 	.desc = {
 		.sadb_alg_id = SADB_X_EALG_AESCTR,
 		.sadb_alg_ivlen	= 8,
-		.sadb_alg_minbits = 128,
-		.sadb_alg_maxbits = 256
+		.sadb_alg_minbits = 160,
+		.sadb_alg_maxbits = 288
 	}
 },
 };

[08/16] linux/log2.h: Fix rounddown_pow_of_two(1)

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 13c07b0286d340275f2d97adf085cecda37ede37 upstream.

Exactly like roundup_pow_of_two(1), the rounddown version was buggy for
the case of a compile-time constant '1' argument.  Probably because it
originated from the same code, sharing history with the roundup version
from before the bugfix (for that one, see commit 1a06a52ee1b0: "Fix
roundup_pow_of_two(1)").

However, unlike the roundup version, the fix for rounddown is to just
remove the broken special case entirely.  It's simply not needed - the
generic code

    1UL << ilog2(n)

does the right thing for the constant '1' argment too.  The only reason
roundup needed that special case was because rounding up does so by
subtracting one from the argument (and then adding one to the result)
causing the obvious problems with "ilog2(0)".

But rounddown doesn't do any of that, since ilog2() naturally truncates
(ie "rounds down") to the right rounded down value.  And without the
ilog2(0) case, there's no reason for the special case that had the wrong
value.

tl;dr: rounddown_pow_of_two(1) should be 1, not 0.

Acked-by: Dmitry Torokhov <dtor@vmware.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/linux/log2.h |    1 -
 1 file changed, 1 deletion(-)

--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -185,7 +185,6 @@ unsigned long __rounddown_pow_of_two(uns
 #define rounddown_pow_of_two(n)			\
 (						\
 	__builtin_constant_p(n) ? (		\
-		(n == 1) ? 0 :			\
 		(1UL << ilog2(n))) :		\
 	__rounddown_pow_of_two(n)		\
  )

[09/16] jbd/jbd2: validate sb->s_first in journal_get_superblock()

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 2378 bytes --]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Eryu Guan <guaneryu@gmail.com>

commit 8762202dd0d6e46854f786bdb6fb3780a1625efe upstream.

I hit a J_ASSERT(blocknr != 0) failure in cleanup_journal_tail() when
mounting a fsfuzzed ext3 image. It turns out that the corrupted ext3
image has s_first = 0 in journal superblock, and the 0 is passed to
journal->j_head in journal_reset(), then to blocknr in
cleanup_journal_tail(), in the end the J_ASSERT failed.

So validate s_first after reading journal superblock from disk in
journal_get_superblock() to ensure s_first is valid.

The following script could reproduce it:

fstype=ext3
blocksize=1024
img=$fstype.img
offset=0
found=0
magic="c0 3b 39 98"

dd if=/dev/zero of=$img bs=1M count=8
mkfs -t $fstype -b $blocksize -F $img
filesize=`stat -c %s $img`
while [ $offset -lt $filesize ]
do
        if od -j $offset -N 4 -t x1 $img | grep -i "$magic";then
                echo "Found journal: $offset"
                found=1
                break
        fi
        offset=`echo "$offset+$blocksize" | bc`
done

if [ $found -ne 1 ];then
        echo "Magic \"$magic\" not found"
        exit 1
fi

dd if=/dev/zero of=$img seek=$(($offset+23)) conv=notrunc bs=1 count=1

mkdir -p ./mnt
mount -o loop $img ./mnt

Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: Moritz Mühlenhoff <jmm@inutil.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/jbd/journal.c  |    8 ++++++++
 fs/jbd2/journal.c |    8 ++++++++
 2 files changed, 16 insertions(+)

--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -1070,6 +1070,14 @@ static int journal_get_superblock(journa
 		goto out;
 	}
 
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
+		goto out;
+	}
+
 	return 0;
 
 out:
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1183,6 +1183,14 @@ static int journal_get_superblock(journa
 		goto out;
 	}
 
+	if (be32_to_cpu(sb->s_first) == 0 ||
+	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+		printk(KERN_WARNING
+			"JBD2: Invalid start block of journal: %u\n",
+			be32_to_cpu(sb->s_first));
+		goto out;
+	}
+
 	return 0;
 
 out:

[10/16] Make TASKSTATS require root access

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 1228 bytes --]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 1a51410abe7d0ee4b1d112780f46df87d3621043 upstream.

Ok, this isn't optimal, since it means that 'iotop' needs admin
capabilities, and we may have to work on this some more.  But at the
same time it is very much not acceptable to let anybody just read
anybody elses IO statistics quite at this level.

Use of the GENL_ADMIN_PERM suggested by Johannes Berg as an alternative
to checking the capabilities by hand.

Reported-by: Vasiliy Kulikov <segoon@openwall.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Moritz Mühlenhoff <jmm@inutil.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/taskstats.c |    1 +
 1 file changed, 1 insertion(+)

--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -592,6 +592,7 @@ static struct genl_ops taskstats_ops = {
 	.cmd		= TASKSTATS_CMD_GET,
 	.doit		= taskstats_user_cmd,
 	.policy		= taskstats_cmd_get_policy,
+	.flags		= GENL_ADMIN_PERM,
 };
 
 static struct genl_ops cgroupstats_ops = {

[11/16] hfs: fix hfs_find_init() sb->ext_tree NULL ptr oops

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 3188 bytes --]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Phillip Lougher <plougher@redhat.com>

commit 434a964daa14b9db083ce20404a4a2add54d037a upstream.

Clement Lecigne reports a filesystem which causes a kernel oops in
hfs_find_init() trying to dereference sb->ext_tree which is NULL.

This proves to be because the filesystem has a corrupted MDB extent
record, where the extents file does not fit into the first three extents
in the file record (the first blocks).

In hfs_get_block() when looking up the blocks for the extent file
(HFS_EXT_CNID), it fails the first blocks special case, and falls
through to the extent code (which ultimately calls hfs_find_init())
which is in the process of being initialised.

Hfs avoids this scenario by always having the extents b-tree fitting
into the first blocks (the extents B-tree can't have overflow extents).

The fix is to check at mount time that the B-tree fits into first
blocks, i.e.  fail if HFS_I(inode)->alloc_blocks >=
HFS_I(inode)->first_blocks

Note, the existing commit 47f365eb57573 ("hfs: fix oops on mount with
corrupted btree extent records") becomes subsumed into this as a special
case, but only for the extents B-tree (HFS_EXT_CNID), it is perfectly
acceptable for the catalog B-Tree file to grow beyond three extents,
with the remaining extent descriptors in the extents overfow.

This fixes CVE-2011-2203

Reported-by: Clement LECIGNE <clement.lecigne@netasq.com>
Signed-off-by: Phillip Lougher <plougher@redhat.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Moritz Mühlenhoff <jmm@inutil.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/hfs/btree.c |   20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -45,11 +45,26 @@ struct hfs_btree *hfs_btree_open(struct
 	case HFS_EXT_CNID:
 		hfs_inode_read_fork(tree->inode, mdb->drXTExtRec, mdb->drXTFlSize,
 				    mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz));
+		if (HFS_I(tree->inode)->alloc_blocks >
+					HFS_I(tree->inode)->first_blocks) {
+			printk(KERN_ERR "hfs: invalid btree extent records\n");
+			unlock_new_inode(tree->inode);
+			goto free_inode;
+		}
+
 		tree->inode->i_mapping->a_ops = &hfs_btree_aops;
 		break;
 	case HFS_CAT_CNID:
 		hfs_inode_read_fork(tree->inode, mdb->drCTExtRec, mdb->drCTFlSize,
 				    mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz));
+
+		if (!HFS_I(tree->inode)->first_blocks) {
+			printk(KERN_ERR "hfs: invalid btree extent records "
+								"(0 size).\n");
+			unlock_new_inode(tree->inode);
+			goto free_inode;
+		}
+
 		tree->inode->i_mapping->a_ops = &hfs_btree_aops;
 		break;
 	default:
@@ -58,11 +73,6 @@ struct hfs_btree *hfs_btree_open(struct
 	}
 	unlock_new_inode(tree->inode);
 
-	if (!HFS_I(tree->inode)->first_blocks) {
-		printk(KERN_ERR "hfs: invalid btree extent records (0 size).\n");
-		goto free_inode;
-	}
-
 	mapping = tree->inode->i_mapping;
 	page = read_mapping_page(mapping, 0, NULL);
 	if (IS_ERR(page))

[12/16] export __get_user_pages_fast() function

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------


From: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>

commit 45888a0c6edc305495b6bd72a30e66bc40b324c6 upstream.

Backport for stable kernel v2.6.32.y to v2.6.36.y.

Needed for next patch:

 oprofile, x86: Fix nmi-unsafe callgraph support

This function is used by KVM to pin process's page in the atomic context.

Define the 'weak' function to avoid other architecture not support it

Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 mm/util.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

--- a/mm/util.c
+++ b/mm/util.c
@@ -233,6 +233,19 @@ void arch_pick_mmap_layout(struct mm_str
 }
 #endif
 
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ * If the architecture not support this fucntion, simply return with no
+ * page pinned
+ */
+int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
+				 int nr_pages, int write, struct page **pages)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address

[13/16] [PATCH 2/3] oprofile, x86: Fix nmi-unsafe callgraph support

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Robert Richter <robert.richter@amd.com>

commit a0e3e70243f5b270bc3eca718f0a9fa5e6b8262e upstream.

Backport for stable kernel v2.6.32.y to v2.6.36.y.

Current oprofile's x86 callgraph support may trigger page faults
throwing the BUG_ON(in_nmi()) message below. This patch fixes this by
using the same nmi-safe copy-from-user code as in perf.

------------[ cut here ]------------
kernel BUG at .../arch/x86/kernel/traps.c:436!
invalid opcode: 0000 [#1] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:0a.0/0000:07:00.0/0000:08:04.0/net/eth0/broadcast
CPU 5
Modules linked in:

Pid: 8611, comm: opcontrol Not tainted 2.6.39-00007-gfe47ae7 #1 Advanced Micro Device Anaheim/Anaheim
RIP: 0010:[<ffffffff813e8e35>]  [<ffffffff813e8e35>] do_nmi+0x22/0x1ee
RSP: 0000:ffff88042fd47f28  EFLAGS: 00010002
RAX: ffff88042c0a7fd8 RBX: 0000000000000001 RCX: 00000000c0000101
RDX: 00000000ffff8804 RSI: ffffffffffffffff RDI: ffff88042fd47f58
RBP: ffff88042fd47f48 R08: 0000000000000004 R09: 0000000000001484
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88042fd47f58
R13: 0000000000000000 R14: ffff88042fd47d98 R15: 0000000000000020
FS:  00007fca25e56700(0000) GS:ffff88042fd40000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000074 CR3: 000000042d28b000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process opcontrol (pid: 8611, threadinfo ffff88042c0a6000, task ffff88042c532310)
Stack:
 0000000000000000 0000000000000001 ffff88042c0a7fd8 0000000000000000
 ffff88042fd47de8 ffffffff813e897a 0000000000000020 ffff88042fd47d98
 0000000000000000 ffff88042c0a7fd8 ffff88042fd47de8 0000000000000074
Call Trace:
 <NMI>
 [<ffffffff813e897a>] nmi+0x1a/0x20
 [<ffffffff813f08ab>] ? bad_to_user+0x25/0x771
 <<EOE>>
Code: ff 59 5b 41 5c 41 5d c9 c3 55 65 48 8b 04 25 88 b5 00 00 48 89 e5 41 55 41 54 49 89 fc 53 48 83 ec 08 f6 80 47 e0 ff ff 04 74 04 <0f> 0b eb fe 81 80 44 e0 ff ff 00 00 01 04 65 ff 04 25 c4 0f 01
RIP  [<ffffffff813e8e35>] do_nmi+0x22/0x1ee
 RSP <ffff88042fd47f28>
---[ end trace ed6752185092104b ]---
Kernel panic - not syncing: Fatal exception in interrupt
Pid: 8611, comm: opcontrol Tainted: G      D     2.6.39-00007-gfe47ae7 #1
Call Trace:
 <NMI>  [<ffffffff813e5e0a>] panic+0x8c/0x188
 [<ffffffff813e915c>] oops_end+0x81/0x8e
 [<ffffffff8100403d>] die+0x55/0x5e
 [<ffffffff813e8c45>] do_trap+0x11c/0x12b
 [<ffffffff810023c8>] do_invalid_op+0x91/0x9a
 [<ffffffff813e8e35>] ? do_nmi+0x22/0x1ee
 [<ffffffff8131e6fa>] ? oprofile_add_sample+0x83/0x95
 [<ffffffff81321670>] ? op_amd_check_ctrs+0x4f/0x2cf
 [<ffffffff813ee4d5>] invalid_op+0x15/0x20
 [<ffffffff813e8e35>] ? do_nmi+0x22/0x1ee
 [<ffffffff813e8e7a>] ? do_nmi+0x67/0x1ee
 [<ffffffff813e897a>] nmi+0x1a/0x20
 [<ffffffff813f08ab>] ? bad_to_user+0x25/0x771
 <<EOE>>

Cc: John Lumby <johnlumby@hotmail.com>
Cc: Maynard Johnson <maynardj@us.ibm.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/x86/oprofile/backtrace.c |   46 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 42 insertions(+), 4 deletions(-)

--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -11,6 +11,8 @@
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
+
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
@@ -47,6 +49,42 @@ static struct stacktrace_ops backtrace_o
 	.address = backtrace_address,
 };
 
+/* from arch/x86/kernel/cpu/perf_event.c: */
+
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
+
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
+
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
+
+		map = kmap_atomic(page, KM_USER0);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map, KM_USER0);
+		put_page(page);
+
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
+
 struct frame_head {
 	struct frame_head *bp;
 	unsigned long ret;
@@ -54,12 +92,12 @@ struct frame_head {
 
 static struct frame_head *dump_user_backtrace(struct frame_head *head)
 {
+	/* Also check accessibility of one struct frame_head beyond: */
 	struct frame_head bufhead[2];
+	unsigned long bytes;
 
-	/* Also check accessibility of one struct frame_head beyond */
-	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
-		return NULL;
-	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+	bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
+	if (bytes != sizeof(bufhead))
 		return NULL;
 
 	oprofile_add_trace(bufhead[0].ret);

Re: [13/16] [PATCH 2/3] oprofile, x86: Fix nmi-unsafe callgraph support

[Robert Richter]

On 16.12.11 12:49:46, Greg KH wrote:
> 2.6.32-longterm review patch.  If anyone has any objections, please let me know.

Looks like the [PATCH ...] should be stripped in the subject line.

Same with

 [14/16] [PATCH 3/3] oprofile, x86: Fix crash when unloading module (timer mode)

-Robert

-- 
Advanced Micro Devices, Inc.
Operating System Research Center

Re: [13/16] [PATCH 2/3] oprofile, x86: Fix nmi-unsafe callgraph support

[Greg KH]

On Sun, Dec 18, 2011 at 05:04:01PM +0100, Robert Richter wrote:
> On 16.12.11 12:49:46, Greg KH wrote:
> > 2.6.32-longterm review patch.  If anyone has any objections, please let me know.
> 
> Looks like the [PATCH ...] should be stripped in the subject line.
> 
> Same with
> 
>  [14/16] [PATCH 3/3] oprofile, x86: Fix crash when unloading module (timer mode)

oops, you are right, oh well, I messed that one up...

greg k-h

[14/16] [PATCH 3/3] oprofile, x86: Fix crash when unloading module (timer mode)

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Robert Richter <robert.richter@amd.com>

Based on 97f7f81 oprofile, x86: Fix crash when unloading module (nmi timer
mode) upstream.

Fix for stable kernels v2.6.28.y to v2.6.34.y. This patch is for .32.

Oprofile crashs while unlaoding modules and if in timer mode. Timer
mode is the fallback if the architectural initialization fails. The
pointer variable model is then used uninitialzied during exit causing
a NULL pointer dereference.

It can be triggered with kernel parameters oprofile.timer=1 nolapic
used. Happens esp. in virtual machine environments.

oprofile: using timer interrupt.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000028
IP: [<ffffffffa000251f>] op_nmi_exit+0x3d/0x4a [oprofile]
PGD 42ac5e067 PUD 42ac5d067 PMD 0
Oops: 0000 [#1] PREEMPT SMP
last sysfs file: /sys/module/oprofile/refcnt
CPU 0
Modules linked in: oprofile(-)
Pid: 2245, comm: modprobe Not tainted 2.6.32.21-oprofile-x86_64-debug-00038-gf4db115 #69 Anaheim
RIP: 0010:[<ffffffffa000251f>]  [<ffffffffa000251f>] op_nmi_exit+0x3d/0x4a [oprofile]
RSP: 0018:ffff88042d4f9ec8  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffffffffa0005590 RCX: ffff88042d4f9ea8
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000001
RBP: ffff88042d4f9ec8 R08: ffff88042d4f9ee8 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000080
R13: 00000000fffffff5 R14: 0000000000000001 R15: 00000000006101e0
FS:  00007fef6ac9c700(0000) GS:ffff880028200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000028 CR3: 000000042ac60000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process modprobe (pid: 2245, threadinfo ffff88042d4f8000, task ffff88042cd66040)
Stack:
 ffff88042d4f9ed8 ffffffffa0002096 ffff88042d4f9ee8 ffffffffa0003bbb
<0> ffff88042d4f9f78 ffffffff810748ad 656c69666f72706f 00007fff77a07800
<0> ffff88042d4f9f28 ffffffff81068414 000000000060f180 0000000000000000
Call Trace:
 [<ffffffffa0002096>] oprofile_arch_exit+0xe/0x10 [oprofile]
 [<ffffffffa0003bbb>] oprofile_exit+0x13/0x15 [oprofile]
 [<ffffffff810748ad>] sys_delete_module+0x1cd/0x244
 [<ffffffff81068414>] ? trace_hardirqs_on_caller+0x114/0x13f
 [<ffffffff8143ad47>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff8100b13b>] system_call_fastpath+0x16/0x1b
Code: 48 c7 c7 90 4e 00 a0 e8 e7 15 22 e1 48 c7 c7 e0 4e 00 a0 e8 bd 18 22 e1 48 c7 c7 70 4e 00 a0 e8 94 4e 41 e1 48 8b 05 d1 39 00 00 <48> 8b 40 28 48 85 c0 74 02 ff d0 c9 c3 55 48 89 e5 e8 cb 88 00
RIP  [<ffffffffa000251f>] op_nmi_exit+0x3d/0x4a [oprofile]
 RSP <ffff88042d4f9ec8>
CR2: 0000000000000028
---[ end trace 18b12420ceb19193 ]---

Signed-off-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/x86/oprofile/nmi_int.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -750,12 +750,12 @@ int __init op_nmi_init(struct oprofile_o
 
 void op_nmi_exit(void)
 {
-	if (using_nmi) {
-		exit_sysfs();
+	if (!using_nmi)
+		return;
+	exit_sysfs();
 #ifdef CONFIG_SMP
-		unregister_cpu_notifier(&oprofile_cpu_nb);
+	unregister_cpu_notifier(&oprofile_cpu_nb);
 #endif
-	}
 	if (model->exit)
 		model->exit();
 }

[15/16] ext4: avoid hangs in ext4_da_should_update_i_disksize()

[Greg KH]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Andrea Arcangeli <aarcange@redhat.com>

commit ea51d132dbf9b00063169c1159bee253d9649224 upstream.

If the pte mapping in generic_perform_write() is unmapped between
iov_iter_fault_in_readable() and iov_iter_copy_from_user_atomic(), the
"copied" parameter to ->end_write can be zero. ext4 couldn't cope with
it with delayed allocations enabled. This skips the i_disksize
enlargement logic if copied is zero and no new data was appeneded to
the inode.

 gdb> bt
 #0  0xffffffff811afe80 in ext4_da_should_update_i_disksize (file=0xffff88003f606a80, mapping=0xffff88001d3824e0, pos=0x1\
 08000, len=0x1000, copied=0x0, page=0xffffea0000d792e8, fsdata=0x0) at fs/ext4/inode.c:2467
 #1  ext4_da_write_end (file=0xffff88003f606a80, mapping=0xffff88001d3824e0, pos=0x108000, len=0x1000, copied=0x0, page=0\
 xffffea0000d792e8, fsdata=0x0) at fs/ext4/inode.c:2512
 #2  0xffffffff810d97f1 in generic_perform_write (iocb=<value optimized out>, iov=<value optimized out>, nr_segs=<value o\
 ptimized out>, pos=0x108000, ppos=0xffff88001e26be40, count=<value optimized out>, written=0x0) at mm/filemap.c:2440
 #3  generic_file_buffered_write (iocb=<value optimized out>, iov=<value optimized out>, nr_segs=<value optimized out>, p\
 os=0x108000, ppos=0xffff88001e26be40, count=<value optimized out>, written=0x0) at mm/filemap.c:2482
 #4  0xffffffff810db5d1 in __generic_file_aio_write (iocb=0xffff88001e26bde8, iov=0xffff88001e26bec8, nr_segs=0x1, ppos=0\
 xffff88001e26be40) at mm/filemap.c:2600
 #5  0xffffffff810db853 in generic_file_aio_write (iocb=0xffff88001e26bde8, iov=0xffff88001e26bec8, nr_segs=<value optimi\
 zed out>, pos=<value optimized out>) at mm/filemap.c:2632
 #6  0xffffffff811a71aa in ext4_file_write (iocb=0xffff88001e26bde8, iov=0xffff88001e26bec8, nr_segs=0x1, pos=0x108000) a\
 t fs/ext4/file.c:136
 #7  0xffffffff811375aa in do_sync_write (filp=0xffff88003f606a80, buf=<value optimized out>, len=<value optimized out>, \
 ppos=0xffff88001e26bf48) at fs/read_write.c:406
 #8  0xffffffff81137e56 in vfs_write (file=0xffff88003f606a80, buf=0x1ec2960 <Address 0x1ec2960 out of bounds>, count=0x4\
 000, pos=0xffff88001e26bf48) at fs/read_write.c:435
 #9  0xffffffff8113816c in sys_write (fd=<value optimized out>, buf=0x1ec2960 <Address 0x1ec2960 out of bounds>, count=0x\
 4000) at fs/read_write.c:487
 #10 <signal handler called>
 #11 0x00007f120077a390 in __brk_reservation_fn_dmi_alloc__ ()
 #12 0x0000000000000000 in ?? ()
 gdb> print offset
 $22 = 0xffffffffffffffff
 gdb> print idx
 $23 = 0xffffffff
 gdb> print inode->i_blkbits
 $24 = 0xc
 gdb> up
 #1  ext4_da_write_end (file=0xffff88003f606a80, mapping=0xffff88001d3824e0, pos=0x108000, len=0x1000, copied=0x0, page=0\
 xffffea0000d792e8, fsdata=0x0) at fs/ext4/inode.c:2512
 2512                    if (ext4_da_should_update_i_disksize(page, end)) {
 gdb> print start
 $25 = 0x0
 gdb> print end
 $26 = 0xffffffffffffffff
 gdb> print pos
 $27 = 0x108000
 gdb> print new_i_size
 $28 = 0x108000
 gdb> print ((struct ext4_inode_info *)((char *)inode-((int)(&((struct ext4_inode_info *)0)->vfs_inode))))->i_disksize
 $29 = 0xd9000
 gdb> down
 2467            for (i = 0; i < idx; i++)
 gdb> print i
 $30 = 0xd44acbee

This is 100% reproducible with some autonuma development code tuned in
a very aggressive manner (not normal way even for knumad) which does
"exotic" changes to the ptes. It wouldn't normally trigger but I don't
see why it can't happen normally if the page is added to swap cache in
between the two faults leading to "copied" being zero (which then
hangs in ext4). So it should be fixed. Especially possible with lumpy
reclaim (albeit disabled if compaction is enabled) as that would
ignore the young bits in the ptes.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ext4/inode.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3228,7 +3228,7 @@ static int ext4_da_write_end(struct file
 	 */
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
+	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
 		if (ext4_da_should_update_i_disksize(page, end)) {
 			down_write(&EXT4_I(inode)->i_data_sem);
 			if (new_i_size > EXT4_I(inode)->i_disksize) {

[16/16] USB: cdc-acm: add IDs for Motorola H24 HSPA USB module.

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 1510 bytes --]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Krzysztof Hałasa <khalasa@piap.pl>

commit 6abff5dc4d5a2c90e597137ce8987e7fd439259b upstream.

Add USB IDs for Motorola H24 HSPA USB module.

Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
Acked-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/class/cdc-acm.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1528,6 +1528,16 @@ static struct usb_device_id acm_ids[] =
 	},
 	{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
 	},
+	/* Motorola H24 HSPA module: */
+	{ USB_DEVICE(0x22b8, 0x2d91) }, /* modem                                */
+	{ USB_DEVICE(0x22b8, 0x2d92) }, /* modem           + diagnostics        */
+	{ USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port                      */
+	{ USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics        */
+	{ USB_DEVICE(0x22b8, 0x2d96) }, /* modem                         + NMEA */
+	{ USB_DEVICE(0x22b8, 0x2d97) }, /* modem           + diagnostics + NMEA */
+	{ USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port               + NMEA */
+	{ USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+
 	{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
 	.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
 					   data interface instead of