3.14.62-stable review

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Imre Deak <[email protected]>

commit fd0fe6acf1dd88aabfbf383f7e4c16315387a7b7 upstream.

After Damien's D3 fix I started to get runtime suspend residency for the first time and that revealed a breakage on the set_caching IOCTL path that accesses the HW but doesn't take an RPM ref. Fix this up.

---
 drivers/gpu/drm/i915/i915_gem.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -3655,6 +3655,7 @@ unlock:
 int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_caching *args = data;
 	struct drm_i915_gem_object *obj;
 	enum i915_cache_level level;

@@ -3674,9 +3675,11 @@ int i915_gem_set_caching_ioctl(struct dr
 		return -EINVAL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto rpm_put;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {

@@ -3689,6 +3692,9 @@ int i915_gem_set_caching_ioctl(struct dr
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+rpm_put:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Takashi Iwai <[email protected]>

commit 13d5e5d4725c64ec06040d636832e78453f477b7 upstream.

The commit [7f0973e973cd: ALSA: seq: Fix lockdep warnings due to double mutex locks] split the management of two linked lists (source and destination) into two individual calls for avoiding the AB/BA deadlock. However, this may leave the possible double deletion of one of two lists when the counterpart is being deleted concurrently. It ends up with a list corruption, as revealed by syzkaller fuzzer.

This patch fixes it by checking the list emptiness and skipping the deletion and the following process.

---
 sound/core/seq/seq_ports.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

@@ -540,19 +540,22 @@ static void delete_and_unsubscribe_port(
 					bool is_src, bool ack)
 {
 	struct snd_seq_port_subs_info *grp;
+	struct list_head *list;
+	bool empty;
 
 	grp = is_src ? &port->c_src : &port->c_dest;
+	list = is_src ? &subs->src_list : &subs->dest_list;
 	down_write(&grp->list_mutex);
 	write_lock_irq(&grp->list_lock);
-	if (is_src)
-		list_del(&subs->src_list);
-	else
-		list_del(&subs->dest_list);
+	empty = list_empty(list);
+	if (!empty)
+		list_del_init(list);
 	grp->exclusive = 0;
 	write_unlock_irq(&grp->list_lock);
 	up_write(&grp->list_mutex);
 
-	unsubscribe_port(client, port, grp, &subs->info, ack);
+	if (!empty)
+		unsubscribe_port(client, port, grp, &subs->info, ack);
 }
 
 /* connect two ports */

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Tony Lindgren <[email protected]>

commit b241d31ef2f6a289d33dcaa004714b26e06f476f upstream.

Otherwise rmmod omap2430; rmmod phy-twl4030-usb; modprobe omap2430 will try to use a non-existing phy and oops:

Unable to handle kernel paging request at virtual address b6f7c1f0

...
[<c048a284>] (devm_usb_get_phy_by_node) from [<bf0758ac>] (omap2430_musb_init+0x44/0x2b4 [omap2430]) [<bf0758ac>] (omap2430_musb_init [omap2430]) from [<bf055ec0>] (musb_init_controller+0x194/0x878 [musb_hdrc])

---
 drivers/phy/phy-twl4030-usb.c |    1 +
 1 file changed, 1 insertion(+)

@@ -777,6 +777,7 @@ static int twl4030_usb_remove(struct pla
 	struct twl4030_usb *twl = platform_get_drvdata(pdev);
 	int val;
 
+	usb_remove_phy(&twl->phy);
 	pm_runtime_get_sync(twl->dev);
 	cancel_delayed_work(&twl->id_workaround_work);
 	device_remove_file(twl->dev, &dev_attr_vbus);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Peter Hurley <[email protected]>

commit ee9159ddce14bc1dec9435ae4e3bd3153e783706 upstream.

The N_X25 line discipline may access the previous line discipline's closed and already-freed private data on open [1].

The tty->disc_data field _never_ refers to valid data on entry to the line discipline's open() method. Rather, the ldisc is expected to initialize that field for its own use for the lifetime of the instance (ie. from open() to close() only).

[1]

    [  634.336761] ==================================================================
    [  634.338226] BUG: KASAN: use-after-free in x25_asy_open_tty+0x13d/0x490 at addr ffff8800a743efd0
    [  634.339558] Read of size 4 by task syzkaller_execu/8981
    [  634.340359] =============================================================================
    [  634.341598] BUG kmalloc-512 (Not tainted): kasan: bad access detected
    ...
    [  634.405018] Call Trace:
    [  634.405277] dump_stack (lib/dump_stack.c:52)
    [  634.405775] print_trailer (mm/slub.c:655)
    [  634.406361] object_err (mm/slub.c:662)
    [  634.406824] kasan_report_error (mm/kasan/report.c:138 mm/kasan/report.c:236)
    [  634.409581] __asan_report_load4_noabort (mm/kasan/report.c:279)
    [  634.411355] x25_asy_open_tty (drivers/net/wan/x25_asy.c:559 (discriminator 1))
    [  634.413997] tty_ldisc_open.isra.2 (drivers/tty/tty_ldisc.c:447)
    [  634.414549] tty_set_ldisc (drivers/tty/tty_ldisc.c:567)
    [  634.415057] tty_ioctl (drivers/tty/tty_io.c:2646 drivers/tty/tty_io.c:2879)
    [  634.423524] do_vfs_ioctl (fs/ioctl.c:43 fs/ioctl.c:607)
    [  634.427491] SyS_ioctl (fs/ioctl.c:622 fs/ioctl.c:613)
    [  634.427945] entry_SYSCALL_64_fastpath (arch/x86/entry/entry_64.S:188)

---
 drivers/net/wan/x25_asy.c |    6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

@@ -545,16 +545,12 @@ static void x25_asy_receive_buf(struct t
 
 static int x25_asy_open_tty(struct tty_struct *tty)
 {
-	struct x25_asy *sl = tty->disc_data;
+	struct x25_asy *sl;
 	int err;
 
 	if (tty->ops->write == NULL)
 		return -EOPNOTSUPP;
 
-	/* First make sure we're not already connected. */
-	if (sl && sl->magic == X25_ASY_MAGIC)
-		return -EEXIST;
-
 	/* OK.  Find a free X.25 channel to use. */
 	sl = x25_asy_alloc();
 	if (sl == NULL)

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Peter Hurley <[email protected]>

commit f4f9edcf9b5289ed96113e79fa65a7bf27ecb096 upstream.

As the function documentation for tty_ldisc_ref_wait() notes, it is only callable from a tty file_operations routine; otherwise there is no guarantee the ref won't be NULL.

The key difference with the VT's paste_selection() is that is an ioctl, where __speakup_paste_selection() is completely async kworker, kicked off from interrupt context.

tty (ab)usage to match vt")

---
 drivers/staging/speakup/selection.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -140,7 +140,9 @@ static void __speakup_paste_selection(st
 	struct tty_ldisc *ld;
 	DECLARE_WAITQUEUE(wait, current);
 
-	ld = tty_ldisc_ref_wait(tty);
+	ld = tty_ldisc_ref(tty);
+	if (!ld)
+		goto tty_unref;
 	tty_buffer_lock_exclusive(&vc->port);
 
 	add_wait_queue(&vc->paste_wait, &wait);

@@ -160,6 +162,7 @@ static void __speakup_paste_selection(st
 
 	tty_buffer_unlock_exclusive(&vc->port);
 	tty_ldisc_deref(ld);
+tty_unref:
 	tty_kref_put(tty);
 }
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Herton R. Krzesinski <[email protected]>

commit 2831c89f42dcde440cfdccb9fee9f42d54bbc1ef upstream.

This change fixes a bug for a corner case where we have the the last release from a pty master/slave coming from a previously opened /dev/tty file. When this happens, the tty->driver_data can be stale, due to all ptmx or pts/N files having already been closed before (and thus the inode related to these files, which tty->driver_data points to, being already freed/destroyed).

The fix here is to keep a reference on the opened master ptmx inode. We maintain the inode referenced until the final pty_unix98_shutdown, and only pass this inode to devpts_kill_index.

---
 drivers/tty/pty.c |   18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

@@ -617,7 +617,14 @@ static void pty_unix98_remove(struct tty
 /* this is called once with whichever end is closed last */
 static void pty_unix98_shutdown(struct tty_struct *tty)
 {
-	devpts_kill_index(tty->driver_data, tty->index);
+	struct inode *ptmx_inode;
+
+	if (tty->driver->subtype == PTY_TYPE_MASTER)
+		ptmx_inode = tty->driver_data;
+	else
+		ptmx_inode = tty->link->driver_data;
+	devpts_kill_index(ptmx_inode, tty->index);
+	iput(ptmx_inode); /* drop reference we acquired at ptmx_open */
 }
 
 static const struct tty_operations ptm_unix98_ops = {

@@ -708,6 +715,15 @@ static int ptmx_open(struct inode *inode
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
 	tty->driver_data = inode;
 
+	/*
+	 * In the case where all references to ptmx inode are dropped and we
+	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
+	 * is closed/released before /dev/tty), we must make sure that the inode
+	 * is still valid when we call the final pty_unix98_shutdown, thus we
+	 * hold an additional reference to the ptmx inode
+	 */
+	ihold(inode);
+
 	tty_add_file(tty, filp);
 
 	slave_inode = devpts_pty_new(inode,

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Soeren Grunewald <[email protected]>

commit 899f0c1c7dbcc487fdc8756a49ff70b1d5d75f89 upstream.

The internal clock of the master chip, which is usually 125MHz, is only half (62.5MHz) for the slave chips. So we have to adjust the uartclk for all the slave ports. Therefor we add a new function to determine if a slave chip is present and update pci_xr17v35x_setup accordingly.

---
 drivers/tty/serial/8250/8250_pci.c |   22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

@@ -1613,6 +1613,9 @@ static int pci_eg20t_init(struct pci_dev
 #endif
 }
 
+#define PCI_DEVICE_ID_EXAR_XR17V4358	0x4358
+#define PCI_DEVICE_ID_EXAR_XR17V8358	0x8358
+
 static int
 pci_xr17c154_setup(struct serial_private *priv,
 		  const struct pciserial_board *board,

@@ -1622,6 +1625,15 @@ pci_xr17c154_setup(struct serial_private
 	return pci_default_setup(priv, board, port, idx);
 }
 
+static inline int
+xr17v35x_has_slave(struct serial_private *priv)
+{
+	const int dev_id = priv->dev->device;
+
+	return ((dev_id == PCI_DEVICE_ID_EXAR_XR17V4358) ||
+	        (dev_id == PCI_DEVICE_ID_EXAR_XR17V8358));
+}
+
 static int
 pci_xr17v35x_setup(struct serial_private *priv,
 		  const struct pciserial_board *board,

@@ -1636,6 +1648,13 @@ pci_xr17v35x_setup(struct serial_private
 	port->port.flags |= UPF_EXAR_EFR;
 
 	/*
+	 * Setup the uart clock for the devices on expansion slot to
+	 * half the clock speed of the main chip (which is 125MHz)
+	 */
+	if (xr17v35x_has_slave(priv) && idx >= 8)
+		port->port.uartclk = (7812500 * 16 / 2);
+
+	/*
 	 * Setup Multipurpose Input/Output pins.
 	 */
 	if (idx == 0) {

@@ -1772,9 +1791,6 @@ pci_wch_ch353_setup(struct serial_privat
 #define PCI_DEVICE_ID_SUNIX_1999	0x1999
 
 
-#define PCI_DEVICE_ID_EXAR_XR17V4358	0x4358
-#define PCI_DEVICE_ID_EXAR_XR17V8358	0x8358
-
 /* Unknown vendors/cards - this should not be in linux/pci_ids.h */
 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1584	0x1584
 #define PCI_SUBDEVICE_ID_UNKNOWN_0x1588	0x1588

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Greg Kroah-Hartman <[email protected]>

In Linus's tree, the iovec code has been reworked massively, but in older kernels the AIO layer should be checking this before passing the request on to other layers.

Many thanks to Ben Hawkes of Google Project Zero for pointing out the issue.

---
 fs/aio.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

@@ -1375,11 +1375,16 @@ static ssize_t aio_setup_single_vector(s
 				       unsigned long *nr_segs,
 				       struct iovec *iovec)
 {
-	if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
+	size_t len = kiocb->ki_nbytes;
+
+	if (len > MAX_RW_COUNT)
+		len = MAX_RW_COUNT;
+
+	if (unlikely(!access_ok(!rw, buf, len)))
 		return -EFAULT;
 
 	iovec->iov_base = buf;
-	iovec->iov_len = kiocb->ki_nbytes;
+	iovec->iov_len = len;
 	*nr_segs = 1;
 	return 0;
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Insu Yun <[email protected]>

commit 46901760b46064964b41015d00c140c83aa05bcf upstream.

Since sizeof(ext_new_group_data) > sizeof(ext_new_flex_group_data), integer overflow could be happened.
Therefore, need to fix integer overflow sanitization.

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

@@ -186,7 +186,7 @@ static struct ext4_new_flex_group_data *
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data))
+	if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
 		goto out2;
 	flex_gd->count = flexbg_size;
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Filipe Manana <[email protected]>

commit 0c0fe3b0fa45082cd752553fdb3a4b42503a118e upstream.

While doing some tests I ran into an hang on an extent buffer's rwlock that produced the following trace:

[39389.800012] NMI watchdog: BUG: soft lockup - CPU#15 stuck for 22s! [fdm-stress:32166]
[39389.800016] NMI watchdog: BUG: soft lockup - CPU#14 stuck for 22s! [fdm-stress:32165]
[39389.800016] Modules linked in: btrfs dm_mod ppdev xor sha256_generic hmac raid6_pq drbg ansi_cprng aesni_intel i2c_piix4 acpi_cpufreq aes_x86_64 ablk_helper tpm_tis parport_pc i2c_core sg cryptd evdev psmouse lrw tpm parport gf128mul serio_raw pcspkr glue_helper processor button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel scsi_mod e1000 virtio floppy [last unloaded: btrfs]
[39389.800016] irq event stamp: 0
[39389.800016] hardirqs last  enabled at (0): [<          (null)>]           (null)
[39389.800016] hardirqs last disabled at (0): [<ffffffff8104e58d>] copy_process+0x638/0x1a35
[39389.800016] softirqs last  enabled at (0): [<ffffffff8104e58d>] copy_process+0x638/0x1a35
[39389.800016] softirqs last disabled at (0): [<          (null)>]           (null)
[39389.800016] CPU: 14 PID: 32165 Comm: fdm-stress Not tainted 4.4.0-rc6-btrfs-next-18+ #1
[39389.800016] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014
[39389.800016] task: ffff880175b1ca40 ti: ffff8800a185c000 task.ti: ffff8800a185c000
[39389.800016] RIP: 0010:[<ffffffff810902af>]  [<ffffffff810902af>] queued_spin_lock_slowpath+0x57/0x158
[39389.800016] RSP: 0018:ffff8800a185fb80  EFLAGS: 00000202
[39389.800016] RAX: 0000000000000101 RBX: ffff8801710c4e9c RCX: 0000000000000101
[39389.800016] RDX: 0000000000000100 RSI: 0000000000000001 RDI: 0000000000000001
[39389.800016] RBP: ffff8800a185fb98 R08: 0000000000000001 R09: 0000000000000000
[39389.800016] R10: ffff8800a185fb68 R11: 6db6db6db6db6db7 R12: ffff8801710c4e98
[39389.800016] R13: ffff880175b1ca40 R14: ffff8800a185fc10 R15: ffff880175b1ca40
[39389.800016] FS:  00007f6d37fff700(0000) GS:ffff8802be9c0000(0000) knlGS:0000000000000000
[39389.800016] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[39389.800016] CR2: 00007f6d300019b8 CR3: 0000000037c93000 CR4: 00000000001406e0
[39389.800016] Stack:
[39389.800016]  ffff8801710c4e98 ffff8801710c4e98 ffff880175b1ca40 ffff8800a185fbb0
[39389.800016]  ffffffff81091e11 ffff8801710c4e98 ffff8800a185fbc8 ffffffff81091895
[39389.800016]  ffff8801710c4e98 ffff8800a185fbe8 ffffffff81486c5c ffffffffa067288c
[39389.800016] Call Trace:
[39389.800016]  [<ffffffff81091e11>] queued_read_lock_slowpath+0x46/0x60
[39389.800016]  [<ffffffff81091895>] do_raw_read_lock+0x3e/0x41
[39389.800016]  [<ffffffff81486c5c>] _raw_read_lock+0x3d/0x44
[39389.800016]  [<ffffffffa067288c>] ? btrfs_tree_read_lock+0x54/0x125 [btrfs]
[39389.800016]  [<ffffffffa067288c>] btrfs_tree_read_lock+0x54/0x125 [btrfs]
[39389.800016]  [<ffffffffa0622ced>] ? btrfs_find_item+0xa7/0xd2 [btrfs]
[39389.800016]  [<ffffffffa069363f>] btrfs_ref_to_path+0xd6/0x174 [btrfs]
[39389.800016]  [<ffffffffa0693730>] inode_to_path+0x53/0xa2 [btrfs]
[39389.800016]  [<ffffffffa0693e2e>] paths_from_inode+0x117/0x2ec [btrfs]
[39389.800016]  [<ffffffffa0670cff>] btrfs_ioctl+0xd5b/0x2793 [btrfs]
[39389.800016]  [<ffffffff8108a8b0>] ? arch_local_irq_save+0x9/0xc
[39389.800016]  [<ffffffff81276727>] ? __this_cpu_preempt_check+0x13/0x15
[39389.800016]  [<ffffffff8108a8b0>] ? arch_local_irq_save+0x9/0xc
[39389.800016]  [<ffffffff8118b3d4>] ? rcu_read_unlock+0x3e/0x5d
[39389.800016]  [<ffffffff811822f8>] do_vfs_ioctl+0x42b/0x4ea
[39389.800016]  [<ffffffff8118b4f3>] ? __fget_light+0x62/0x71
[39389.800016]  [<ffffffff8118240e>] SyS_ioctl+0x57/0x79
[39389.800016]  [<ffffffff814872d7>] entry_SYSCALL_64_fastpath+0x12/0x6f
[39389.800016] Code: b9 01 01 00 00 f7 c6 00 ff ff ff 75 32 83 fe 01 89 ca 89 f0 0f 45 d7 f0 0f b1 13 39 f0 74 04 89 c6 eb e2 ff ca 0f 84 fa 00 00 00 <8b> 03 84 c0 74 04 f3 90 eb f6 66 c7 03 01 00 e9 e6 00 00 00 e8
[39389.800012] Modules linked in: btrfs dm_mod ppdev xor sha256_generic hmac raid6_pq drbg ansi_cprng aesni_intel i2c_piix4 acpi_cpufreq aes_x86_64 ablk_helper tpm_tis parport_pc i2c_core sg cryptd evdev psmouse lrw tpm parport gf128mul serio_raw pcspkr glue_helper processor button loop autofs4 ext4 crc16 mbcache jbd2 sd_mod sr_mod cdrom ata_generic virtio_scsi ata_piix libata virtio_pci virtio_ring crc32c_intel scsi_mod e1000 virtio floppy [last unloaded: btrfs]
[39389.800012] irq event stamp: 0
[39389.800012] hardirqs last  enabled at (0): [<          (null)>]           (null)
[39389.800012] hardirqs last disabled at (0): [<ffffffff8104e58d>] copy_process+0x638/0x1a35
[39389.800012] softirqs last  enabled at (0): [<ffffffff8104e58d>] copy_process+0x638/0x1a35
[39389.800012] softirqs last disabled at (0): [<          (null)>]           (null)
[39389.800012] CPU: 15 PID: 32166 Comm: fdm-stress Tainted: G             L  4.4.0-rc6-btrfs-next-18+ #1
[39389.800012] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS by qemu-project.org 04/01/2014
[39389.800012] task: ffff880179294380 ti: ffff880034a60000 task.ti: ffff880034a60000
[39389.800012] RIP: 0010:[<ffffffff81091e8d>]  [<ffffffff81091e8d>] queued_write_lock_slowpath+0x62/0x72
[39389.800012] RSP: 0018:ffff880034a639f0  EFLAGS: 00000206
[39389.800012] RAX: 0000000000000101 RBX: ffff8801710c4e98 RCX: 0000000000000000
[39389.800012] RDX: 00000000000000ff RSI: 0000000000000000 RDI: ffff8801710c4e9c
[39389.800012] RBP: ffff880034a639f8 R08: 0000000000000001 R09: 0000000000000000
[39389.800012] R10: ffff880034a639b0 R11: 0000000000001000 R12: ffff8801710c4e98
[39389.800012] R13: 0000000000000001 R14: ffff880172cbc000 R15: ffff8801710c4e00
[39389.800012] FS:  00007f6d377fe700(0000) GS:ffff8802be9e0000(0000) knlGS:0000000000000000
[39389.800012] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[39389.800012] CR2: 00007f6d3d3c1000 CR3: 0000000037c93000 CR4: 00000000001406e0
[39389.800012] Stack:
[39389.800012]  ffff8801710c4e98 ffff880034a63a10 ffffffff81091963 ffff8801710c4e98
[39389.800012]  ffff880034a63a30 ffffffff81486f1b ffffffffa0672cb3 ffff8801710c4e00
[39389.800012]  ffff880034a63a78 ffffffffa0672cb3 ffff8801710c4e00 ffff880034a63a58
[39389.800012] Call Trace:
[39389.800012]  [<ffffffff81091963>] do_raw_write_lock+0x72/0x8c
[39389.800012]  [<ffffffff81486f1b>] _raw_write_lock+0x3a/0x41
[39389.800012]  [<ffffffffa0672cb3>] ? btrfs_tree_lock+0x119/0x251 [btrfs]
[39389.800012]  [<ffffffffa0672cb3>] btrfs_tree_lock+0x119/0x251 [btrfs]
[39389.800012]  [<ffffffffa061aeba>] ? rcu_read_unlock+0x5b/0x5d [btrfs]
[39389.800012]  [<ffffffffa061ce13>] ? btrfs_root_node+0xda/0xe6 [btrfs]
[39389.800012]  [<ffffffffa061ce83>] btrfs_lock_root_node+0x22/0x42 [btrfs]
[39389.800012]  [<ffffffffa062046b>] btrfs_search_slot+0x1b8/0x758 [btrfs]
[39389.800012]  [<ffffffff810fc6b0>] ? time_hardirqs_on+0x15/0x28
[39389.800012]  [<ffffffffa06365db>] btrfs_lookup_inode+0x31/0x95 [btrfs]
[39389.800012]  [<ffffffff8108d62f>] ? trace_hardirqs_on+0xd/0xf
[39389.800012]  [<ffffffff8148482b>] ? mutex_lock_nested+0x397/0x3bc
[39389.800012]  [<ffffffffa068821b>] __btrfs_update_delayed_inode+0x59/0x1c0 [btrfs]
[39389.800012]  [<ffffffffa068858e>] __btrfs_commit_inode_delayed_items+0x194/0x5aa [btrfs]
[39389.800012]  [<ffffffff81486ab7>] ? _raw_spin_unlock+0x31/0x44
[39389.800012]  [<ffffffffa0688a48>] __btrfs_run_delayed_items+0xa4/0x15c [btrfs]
[39389.800012]  [<ffffffffa0688d62>] btrfs_run_delayed_items+0x11/0x13 [btrfs]
[39389.800012]  [<ffffffffa064048e>] btrfs_commit_transaction+0x234/0x96e [btrfs]
[39389.800012]  [<ffffffffa0618d10>] btrfs_sync_fs+0x145/0x1ad [btrfs]
[39389.800012]  [<ffffffffa0671176>] btrfs_ioctl+0x11d2/0x2793 [btrfs]
[39389.800012]  [<ffffffff8108a8b0>] ? arch_local_irq_save+0x9/0xc
[39389.800012]  [<ffffffff81140261>] ? __might_fault+0x4c/0xa7
[39389.800012]  [<ffffffff81140261>] ? __might_fault+0x4c/0xa7
[39389.800012]  [<ffffffff8108a8b0>] ? arch_local_irq_save+0x9/0xc
[39389.800012]  [<ffffffff8118b3d4>] ? rcu_read_unlock+0x3e/0x5d
[39389.800012]  [<ffffffff811822f8>] do_vfs_ioctl+0x42b/0x4ea
[39389.800012]  [<ffffffff8118b4f3>] ? __fget_light+0x62/0x71
[39389.800012]  [<ffffffff8118240e>] SyS_ioctl+0x57/0x79
[39389.800012]  [<ffffffff814872d7>] entry_SYSCALL_64_fastpath+0x12/0x6f
[39389.800012] Code: f0 0f b1 13 85 c0 75 ef eb 2a f3 90 8a 03 84 c0 75 f8 f0 0f b0 13 84 c0 75 f0 ba ff 00 00 00 eb 0a f0 0f b1 13 ff c8 74 0b f3 90 <8b> 03 83 f8 01 75 f7 eb ed c6 43 04 00 5b 5d c3 0f 1f 44 00 00

This happens because in the code path executed by the inode_paths ioctl we end up nesting two calls to read lock a leaf's rwlock when after the first call to read_lock() and before the second call to read_lock(), another task (running the delayed items as part of a transaction commit) has already called write_lock() against the leaf's rwlock. This situation is illustrated by the following diagram:

Task A Task B

  btrfs_ref_to_path()               btrfs_commit_transaction()
    read_lock(&eb->lock);

                                      btrfs_run_delayed_items()
                                        __btrfs_commit_inode_delayed_items()
                                          __btrfs_update_delayed_inode()
                                            btrfs_lookup_inode()

                                              write_lock(&eb->lock);
                                                --> task waits for lock

    read_lock(&eb->lock);
    --> makes this task hang
        forever (and task B too
	of course)

So fix this by avoiding doing the nested read lock, which is easily avoidable. This issue does not happen if task B calls write_lock() after task A does the second call to read_lock(), however there does not seem to exist anything in the documentation that mentions what is the expected behaviour for recursive locking of rwlocks (leaving the idea that doing so is not a good usage of rwlocks).

Also, as a side effect necessary for this fix, make sure we do not needlessly read lock extent buffers when the input path has skip_locking set (used when called from send).

---
 fs/btrfs/backref.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

@@ -1264,7 +1264,8 @@ char *btrfs_ref_to_path(struct btrfs_roo
 			read_extent_buffer(eb, dest + bytes_left,
 					   name_off, name_len);
 		if (eb != eb_in) {
-			btrfs_tree_read_unlock_blocking(eb);
+			if (!path->skip_locking)
+				btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
 		}
 		ret = inode_ref_info(parent, 0, fs_root, path, &found_key);

@@ -1283,9 +1284,10 @@ char *btrfs_ref_to_path(struct btrfs_roo
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			atomic_inc(&eb->refs);
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			if (!path->skip_locking)
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->nodes[0] = NULL;
+			path->locks[0] = 0;
 		}
 		btrfs_release_path(path);
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Peter Feiner <[email protected]>

commit 956959f6b7a982b2e789a7a8fa1de437074a5eb9 upstream.

The -i flag was incorrectly listed as a short flag for --no-inherit. It should have only been listed as a short flag for --input.

This documentation error has existed since the --input flag was introduced in 6810fc915f7a89d8134edb3996dbbf8eac386c26 (perf trace: Add option to analyze events in a file versus live).

---
 tools/perf/Documentation/perf-trace.txt |    1 -
 1 file changed, 1 deletion(-)

@@ -59,7 +59,6 @@ OPTIONS
 --verbose=::
         Verbosity level.
 
--i::
 --no-inherit::
 	Child tasks do not inherit counters.
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Nicholas Bellinger <[email protected]>

commit ca82c2bded29b38d36140bfa1e76a7bbfcade390 upstream.

This patch addresses a case where iscsi_target_do_tx_login_io() fails sending the last login response PDU, after the RX/TX threads have already been started.

The case centers around iscsi_target_rx_thread() not invoking allow_signal(SIGINT) before the send_sig(SIGINT, ...) occurs from the failure path, resulting in RX thread hanging indefinately on iscsi_conn->rx_login_comp.

Note this bug is a regression introduced by:

commit e54198657b65625085834847ab6271087323ffea
Author: Nicholas Bellinger <[email protected]>
Date: Wed Jul 22 23:14:19 2015 -0700

iscsi-target: Fix iscsit_start_kthreads failure OOPs

To address this bug, complete ->rx_login_complete for good measure in the failure path, and immediately return from RX thread context if connection state did not actually reach full feature phase (TARG_CONN_STATE_LOGGED_IN).

---
 drivers/target/iscsi/iscsi_target.c      |   13 ++++++++++++-
 drivers/target/iscsi/iscsi_target_nego.c |    1 +
 2 files changed, 13 insertions(+), 1 deletion(-)

@@ -4027,6 +4027,17 @@ reject:
 	return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 }
 
+static bool iscsi_target_check_conn_state(struct iscsi_conn *conn)
+{
+	bool ret;
+
+	spin_lock_bh(&conn->state_lock);
+	ret = (conn->conn_state != TARG_CONN_STATE_LOGGED_IN);
+	spin_unlock_bh(&conn->state_lock);
+
+	return ret;
+}
+
 int iscsi_target_rx_thread(void *arg)
 {
 	int ret, rc;

@@ -4044,7 +4055,7 @@ int iscsi_target_rx_thread(void *arg)
 	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
 	 */
 	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
-	if (rc < 0)
+	if (rc < 0 || iscsi_target_check_conn_state(conn))
 		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {

@@ -393,6 +393,7 @@ err:
 	if (login->login_complete) {
 		if (conn->rx_thread && conn->rx_thread_active) {
 			send_sig(SIGINT, conn->rx_thread, 1);
+			complete(&conn->rx_login_comp);
 			kthread_stop(conn->rx_thread);
 		}
 		if (conn->tx_thread && conn->tx_thread_active) {

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Bart Van Assche <[email protected]>

commit b49493f99690c8eaacfbc635bafaad629ea2c036 upstream.

Avoid that kmemleak reports the following memory leak if a SCSI LLD calls scsi_host_alloc() and scsi_host_put() but neither scsi_host_add() nor scsi_host_remove(). The following shell command triggers that scenario:

for ((i=0; i<2; i++)); do
srp_daemon -oac |
while read line; do
echo $line >/sys/class/infiniband_srp/srp-mlx4_0-1/add_target
done
done

unreferenced object 0xffff88021b24a220 (size 8):
comm "srp_daemon", pid 56421, jiffies 4295006762 (age 4240.750s) hex dump (first 8 bytes):

    68 6f 73 74 35 38 00 a5                          host58..
  backtrace:
    [<ffffffff8151014a>] kmemleak_alloc+0x7a/0xc0
    [<ffffffff81165c1e>] __kmalloc_track_caller+0xfe/0x160
    [<ffffffff81260d2b>] kvasprintf+0x5b/0x90
    [<ffffffff81260e2d>] kvasprintf_const+0x8d/0xb0
    [<ffffffff81254b0c>] kobject_set_name_vargs+0x3c/0xa0
    [<ffffffff81337e3c>] dev_set_name+0x3c/0x40
    [<ffffffff81355757>] scsi_host_alloc+0x327/0x4b0
    [<ffffffffa03edc8e>] srp_create_target+0x4e/0x8a0 [ib_srp]
    [<ffffffff8133778b>] dev_attr_store+0x1b/0x20
    [<ffffffff811f27fa>] sysfs_kf_write+0x4a/0x60
    [<ffffffff811f1e8e>] kernfs_fop_write+0x14e/0x180
    [<ffffffff81176eef>] __vfs_write+0x2f/0xf0
    [<ffffffff811771e4>] vfs_write+0xa4/0x100
    [<ffffffff81177c64>] SyS_write+0x54/0xc0
    [<ffffffff8151b257>] entry_SYSCALL_64_fastpath+0x12/0x6f

---
 drivers/scsi/hosts.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -308,6 +308,17 @@ static void scsi_host_dev_release(struct
 		kfree(queuedata);
 	}
 
+	if (shost->shost_state == SHOST_CREATED) {
+		/*
+		 * Free the shost_dev device name here if scsi_host_alloc()
+		 * and scsi_host_put() have been called but neither
+		 * scsi_host_add() nor scsi_host_remove() has been called.
+		 * This avoids that the memory allocated for the shost_dev
+		 * name is leaked.
+		 */
+		kfree(dev_name(&shost->shost_dev));
+	}
+
 	scsi_destroy_command_freelist(shost);
 	if (shost->bqt)
 		blk_free_tags(shost->bqt);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Nicholas Bellinger <[email protected]>

commit 26a99c19f810b2593410899a5b304b21b47428a6 upstream.

This patch is a iscsi-target specific bug-fix for a dead-lock that can occur during explicit struct se_node_acl->acl_group se_session deletion via configfs rmdir(2), when iscsi-target time2retain timer is still active.

It changes iscsi-target to obtain se_portal_group->session_lock internally using spin_in_locked() to check for the specific se_node_acl configfs shutdown rmdir(2) case.

Note this patch is intended for stable, and the subsequent v4.5-rc patch converts target_core_tpg.c to use proper se_sess->sess_kref reference counting for both se_node_acl deletion + se_node_acl->queue_depth se_session restart.

---
 drivers/target/iscsi/iscsi_target_configfs.c |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

@@ -1876,7 +1876,8 @@ static void lio_tpg_release_fabric_acl(
 }
 
 /*
- * Called with spin_lock_bh(struct se_portal_group->session_lock) held..
+ * Called with spin_lock_irq(struct se_portal_group->session_lock) held
+ * or not held.
  *
  * Also, this function calls iscsit_inc_session_usage_count() on the
  * struct iscsi_session in question.

@@ -1884,19 +1885,32 @@ static void lio_tpg_release_fabric_acl(
 static int lio_tpg_shutdown_session(struct se_session *se_sess)
 {
 	struct iscsi_session *sess = se_sess->fabric_sess_ptr;
+	struct se_portal_group *se_tpg = se_sess->se_tpg;
+	bool local_lock = false;
+
+	if (!spin_is_locked(&se_tpg->session_lock)) {
+		spin_lock_irq(&se_tpg->session_lock);
+		local_lock = true;
+	}
 
 	spin_lock(&sess->conn_lock);
 	if (atomic_read(&sess->session_fall_back_to_erl0) ||
 	    atomic_read(&sess->session_logout) ||
 	    (sess->time2retain_timer_flags & ISCSI_TF_EXPIRED)) {
 		spin_unlock(&sess->conn_lock);
+		if (local_lock)
+			spin_unlock_irq(&sess->conn_lock);
 		return 0;
 	}
 	atomic_set(&sess->session_reinstatement, 1);
 	spin_unlock(&sess->conn_lock);
 
 	iscsit_stop_time2retain_timer(sess);
+	spin_unlock_irq(&se_tpg->session_lock);
+
 	iscsit_stop_session(sess, 1, 1);
+	if (!local_lock)
+		spin_lock_irq(&se_tpg->session_lock);
 
 	return 1;
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Kirill A. Shutemov <[email protected]>

commit 461c7fa126794157484dca48e88effa4963e3af3 upstream.

Reduced testcase:

    #include <fcntl.h>
    #include <unistd.h>
    #include <sys/mman.h>
    #include <numaif.h>

    #define SIZE 0x2000

    int main()
    {
        int fd;
        void *p;

        fd = open("/dev/sg0", O_RDWR);
        p = mmap(NULL, SIZE, PROT_EXEC, MAP_PRIVATE | MAP_LOCKED, fd, 0);
        mbind(p, SIZE, 0, NULL, 0, MPOL_MF_MOVE);
        return 0;
    }

We shouldn't try to migrate pages in sg VMA as we don't have a way to update Sg_scatter_hold::pages accordingly from mm core.

Let's mark the VMA as VM_IO to indicate to mm core that the VMA is not migratable.

---
 drivers/scsi/sg.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1258,7 +1258,7 @@ sg_mmap(struct file *filp, struct vm_are
 	}
 
 	sfp->mmap_called = 1;
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_private_data = sfp;
 	vma->vm_ops = &sg_mmap_vm_ops;
 	return 0;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Hannes Reinecke <[email protected]>

commit d2d06d4fe0f2cc2df9b17fefec96e6e1a1271d91 upstream.

If MODE SELECT returns with sense '05/91/36' (command lock violation) it should always be retried without counting the number of retries. During an HBA upgrade or similar circumstances one might see a flood of MODE SELECT command from various HBAs, which will easily trigger the sense code and exceed the retry count.

---
 drivers/scsi/device_handler/scsi_dh_rdac.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -569,7 +569,7 @@ static int mode_select_handle_sense(stru
 			/*
 			 * Command Lock contention
 			 */
-			err = SCSI_DH_RETRY;
+			err = SCSI_DH_IMM_RETRY;
 		break;
 	default:
 		break;

@@ -619,6 +619,8 @@ retry:
 		err = mode_select_handle_sense(sdev, h->sense);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
+		if (err == SCSI_DH_IMM_RETRY)
+			goto retry;
 	}
 	if (err == SCSI_DH_OK) {
 		h->state = RDAC_STATE_ACTIVE;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lars-Peter Clausen <[email protected]>

commit 785171fd6cd7dcd7ada5a733b6a2d44ec566c3a0 upstream.

While the datasheet for the AD7785 lists 0xXB as the product ID the actual product ID is 0xX3.

Fix the product ID otherwise the driver will reject the device due to non matching IDs.

---
 drivers/iio/adc/ad7793.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -101,7 +101,7 @@
 #define AD7795_CH_AIN1M_AIN1M	8 /* AIN1(-) - AIN1(-) */
 
 /* ID Register Bit Designations (AD7793_REG_ID) */
-#define AD7785_ID		0xB
+#define AD7785_ID		0x3
 #define AD7792_ID		0xA
 #define AD7793_ID		0xB
 #define AD7794_ID		0xF

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vladimir Zapolskiy <[email protected]>

commit 01bb70ae0b98d266fa3e860482c7ce22fa482a6e upstream.

If common clock framework is configured, the driver generates a warning, which is fixed by this change:

    root@devkit3250:~# cat /sys/bus/iio/devices/iio\:device0/in_voltage0_raw
    ------------[ cut here ]------------
    WARNING: CPU: 0 PID: 724 at drivers/clk/clk.c:727 clk_core_enable+0x2c/0xa4()
    Modules linked in: sc16is7xx snd_soc_uda1380
    CPU: 0 PID: 724 Comm: cat Not tainted 4.3.0-rc2+ #198
    Hardware name: LPC32XX SoC (Flattened Device Tree)
    Backtrace:
    [<>] (dump_backtrace) from [<>] (show_stack+0x18/0x1c)
    [<>] (show_stack) from [<>] (dump_stack+0x20/0x28)
    [<>] (dump_stack) from [<>] (warn_slowpath_common+0x90/0xb8)
    [<>] (warn_slowpath_common) from [<>] (warn_slowpath_null+0x24/0x2c)
    [<>] (warn_slowpath_null) from [<>] (clk_core_enable+0x2c/0xa4)
    [<>] (clk_core_enable) from [<>] (clk_enable+0x24/0x38)
    [<>] (clk_enable) from [<>] (lpc32xx_read_raw+0x38/0x80)
    [<>] (lpc32xx_read_raw) from [<>] (iio_read_channel_info+0x70/0x94)
    [<>] (iio_read_channel_info) from [<>] (dev_attr_show+0x28/0x4c)
    [<>] (dev_attr_show) from [<>] (sysfs_kf_seq_show+0x8c/0xf0)
    [<>] (sysfs_kf_seq_show) from [<>] (kernfs_seq_show+0x2c/0x30)
    [<>] (kernfs_seq_show) from [<>] (seq_read+0x1c8/0x440)
    [<>] (seq_read) from [<>] (kernfs_fop_read+0x38/0x170)
    [<>] (kernfs_fop_read) from [<>] (do_readv_writev+0x16c/0x238)
    [<>] (do_readv_writev) from [<>] (vfs_readv+0x50/0x58)
    [<>] (vfs_readv) from [<>] (default_file_splice_read+0x1a4/0x308)
    [<>] (default_file_splice_read) from [<>] (do_splice_to+0x78/0x84)
    [<>] (do_splice_to) from [<>] (splice_direct_to_actor+0xc8/0x1cc)
    [<>] (splice_direct_to_actor) from [<>] (do_splice_direct+0xa0/0xb8)
    [<>] (do_splice_direct) from [<>] (do_sendfile+0x1a8/0x30c)
    [<>] (do_sendfile) from [<>] (SyS_sendfile64+0x104/0x10c)
    [<>] (SyS_sendfile64) from [<>] (ret_fast_syscall+0x0/0x38)

---
 drivers/staging/iio/adc/lpc32xx_adc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -76,7 +76,7 @@ static int lpc32xx_read_raw(struct iio_d
 
 	if (mask == IIO_CHAN_INFO_RAW) {
 		mutex_lock(&indio_dev->mlock);
-		clk_enable(info->clk);
+		clk_prepare_enable(info->clk);
 		/* Measurement setup */
 		__raw_writel(AD_INTERNAL | (chan->address) | AD_REFp | AD_REFm,
 			LPC32XX_ADC_SELECT(info->adc_base));

@@ -84,7 +84,7 @@ static int lpc32xx_read_raw(struct iio_d
 		__raw_writel(AD_PDN_CTRL | AD_STROBE,
 			LPC32XX_ADC_CTRL(info->adc_base));
 		wait_for_completion(&info->completion); /* set by ISR */
-		clk_disable(info->clk);
+		clk_disable_unprepare(info->clk);
 		*val = info->value;
 		mutex_unlock(&indio_dev->mlock);
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Hennerich <[email protected]>

commit 03fe472ef33b7f31fbd11d300dbb3fdab9c00fd4 upstream.

i2c_master_send() returns the number of bytes transferred on success while the ad5064 driver expects that the write() callback returns 0 on success. Fix that by translating any non negative return value of i2c_master_send() to 0.

---
 drivers/iio/dac/ad5064.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -598,10 +598,16 @@ static int ad5064_i2c_write(struct ad506
 	unsigned int addr, unsigned int val)
 {
 	struct i2c_client *i2c = to_i2c_client(st->dev);
+	int ret;
 
 	st->data.i2c[0] = (cmd << 4) | addr;
 	put_unaligned_be16(val, &st->data.i2c[1]);
-	return i2c_master_send(i2c, st->data.i2c, 3);
+
+	ret = i2c_master_send(i2c, st->data.i2c, 3);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int ad5064_i2c_probe(struct i2c_client *i2c,

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Carpenter <[email protected]>

commit 231bfe53c57e89857753c940192acba933cba56c upstream.

WARN_ON() only takes a condition argument. I have changed these to WARN() instead.

---
 drivers/iio/industrialio-buffer.c |    2 +-
 drivers/iio/industrialio-core.c   |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

@@ -830,7 +830,7 @@ int iio_scan_mask_set(struct iio_dev *in
 	if (trialmask == NULL)
 		return -ENOMEM;
 	if (!indio_dev->masklength) {
-		WARN_ON("Trying to set scanmask prior to registering buffer\n");
+		WARN(1, "Trying to set scanmask prior to registering buffer\n");
 		goto err_invalid_mask;
 	}
 	bitmap_copy(trialmask, buffer->scan_mask, indio_dev->masklength);

@@ -589,7 +589,7 @@ int __iio_device_attr_init(struct device
 			break;
 		case IIO_SEPARATE:
 			if (!chan->indexed) {
-				WARN_ON("Differential channels must be indexed\n");
+				WARN(1, "Differential channels must be indexed\n");
 				ret = -EINVAL;
 				goto error_free_full_postfix;
 			}

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vasily Averin <[email protected]>

commit 01b9b0b28626db4a47d7f48744d70abca9914ef1 upstream.

In some cases tmp_bug can be not filled in cifs_filldir and stay uninitialized, therefore its printk with "%s" modifier can leak content of kernelspace memory. If old content of this buffer does not contain '\0' access bejond end of allocated object can crash the host.

---
 fs/cifs/readdir.c |    1 +
 1 file changed, 1 insertion(+)

@@ -849,6 +849,7 @@ int cifs_readdir(struct file *file, stru
 		 * if buggy server returns . and .. late do we want to
 		 * check for that here?
 		 */
+		*tmp_buf = 0;
 		rc = cifs_filldir(current_entry, file, ctx,
 				  tmp_buf, max_len);
 		if (rc) {

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Vegard Nossum <[email protected]>

commit b0918d9f476a8434b055e362b83fa4fd1d462c3f upstream.

udf_next_aext() just follows extent pointers while extents are marked as indirect. This can loop forever for corrupted filesystem. Limit number the of indirect extents we are willing to follow in a row.

[JK: Updated changelog, limit, style]

---
 fs/udf/inode.c |   15 +++++++++++++++
 1 file changed, 15 insertions(+)

@@ -2062,14 +2062,29 @@ void udf_write_aext(struct inode *inode,
 		epos->offset += adsize;
 }
 
+/*
+ * Only 1 indirect extent in a row really makes sense but allow upto 16 in case
+ * someone does some weird stuff.
+ */
+#define UDF_MAX_INDIR_EXTS 16
+
 int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
 		     struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
 {
 	int8_t etype;
+	unsigned int indirections = 0;
 
 	while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
 	       (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
 		int block;
+
+		if (++indirections > UDF_MAX_INDIR_EXTS) {
+			udf_err(inode->i_sb,
+				"too many indirect extents in inode %lu\n",
+				inode->i_ino);
+			return -1;
+		}
+
 		epos->block = *eloc;
 		epos->offset = sizeof(struct allocExtDesc);
 		brelse(epos->bh);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Andrew Gabbasov <[email protected]>

commit ad402b265ecf6fa22d04043b41444cdfcdf4f52d upstream.

udf_CS0toUTF8 function stops the conversion when the output buffer length reaches UDF_NAME_LEN-2, which is correct maximum name length, but, when checking, it leaves the space for a single byte only, while multi-bytes output characters can take more space, causing buffer overflow.

Similar error exists in udf_CS0toNLS function, that restricts the output length to UDF_NAME_LEN, while actual maximum allowed length is UDF_NAME_LEN-2.

In these cases the output can override not only the current buffer length field, causing corruption of the name buffer itself, but also following allocation structures, causing kernel crash.

Adjust the output length checks in both functions to prevent buffer overruns in case of multi-bytes UTF8 or NLS characters.

---
 fs/udf/unicode.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -132,11 +132,15 @@ int udf_CS0toUTF8(struct ustr *utf_o, co
 		if (c < 0x80U)
 			utf_o->u_name[utf_o->u_len++] = (uint8_t)c;
 		else if (c < 0x800U) {
+			if (utf_o->u_len > (UDF_NAME_LEN - 4))
+				break;
 			utf_o->u_name[utf_o->u_len++] =
 						(uint8_t)(0xc0 | (c >> 6));
 			utf_o->u_name[utf_o->u_len++] =
 						(uint8_t)(0x80 | (c & 0x3f));
 		} else {
+			if (utf_o->u_len > (UDF_NAME_LEN - 5))
+				break;
 			utf_o->u_name[utf_o->u_len++] =
 						(uint8_t)(0xe0 | (c >> 12));
 			utf_o->u_name[utf_o->u_len++] =

@@ -281,7 +285,7 @@ static int udf_CS0toNLS(struct nls_table
 			c = (c << 8) | ocu[i++];
 
 		len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
-				    UDF_NAME_LEN - utf_o->u_len);
+				    UDF_NAME_LEN - 2 - utf_o->u_len);
 		/* Valid character? */
 		if (len >= 0)
 			utf_o->u_len += len;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Andrew Gabbasov <[email protected]>

commit bb00c898ad1ce40c4bb422a8207ae562e9aea7ae upstream.

If a name contains at least some characters with Unicode values exceeding single byte, the CS0 output should have 2 bytes per character. And if other input characters have single byte Unicode values, then the single input byte is converted to 2 output bytes, and the length of output becomes larger than the length of input. And if the input name is long enough, the output length may exceed the allocated buffer length.

All this means that conversion from UTF8 or NLS to CS0 requires checking of output length in order to stop when it exceeds the given output buffer size.

[JK: Make code return -ENAMETOOLONG instead of silently truncating the name]

---
 fs/udf/unicode.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

@@ -181,17 +181,22 @@ int udf_CS0toUTF8(struct ustr *utf_o, co
 static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length)
 {
 	unsigned c, i, max_val, utf_char;
-	int utf_cnt, u_len;
+	int utf_cnt, u_len, u_ch;
 
 	memset(ocu, 0, sizeof(dstring) * length);
 	ocu[0] = 8;
 	max_val = 0xffU;
+	u_ch = 1;
 
 try_again:
 	u_len = 0U;
 	utf_char = 0U;
 	utf_cnt = 0U;
 	for (i = 0U; i < utf->u_len; i++) {
+		/* Name didn't fit? */
+		if (u_len + 1 + u_ch >= length)
+			return 0;
+
 		c = (uint8_t)utf->u_name[i];
 
 		/* Complete a multi-byte UTF-8 character */

@@ -233,6 +238,7 @@ try_again:
 			if (max_val == 0xffU) {
 				max_val = 0xffffU;
 				ocu[0] = (uint8_t)0x10U;
+				u_ch = 2;
 				goto try_again;
 			}
 			goto error_out;

@@ -303,15 +309,19 @@ static int udf_NLStoCS0(struct nls_table
 	int len;
 	unsigned i, max_val;
 	uint16_t uni_char;
-	int u_len;
+	int u_len, u_ch;
 
 	memset(ocu, 0, sizeof(dstring) * length);
 	ocu[0] = 8;
 	max_val = 0xffU;
+	u_ch = 1;
 
 try_again:
 	u_len = 0U;
 	for (i = 0U; i < uni->u_len; i++) {
+		/* Name didn't fit? */
+		if (u_len + 1 + u_ch >= length)
+			return 0;
 		len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
 		if (!len)
 			continue;

@@ -324,6 +334,7 @@ try_again:
 		if (uni_char > max_val) {
 			max_val = 0xffffU;
 			ocu[0] = (uint8_t)0x10U;
+			u_ch = 2;
 			goto try_again;
 		}
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Helmut Klein <[email protected]>

commit 5442f0eadf2885453d5b2ed8c8592f32a3744f8e upstream.

The "reg" entry in the "poweroff" section of "kirkwood-ts219.dtsi" addressed the wrong uart (0 = console). This patch changes the address to select uart 1, which is the uart connected to the pic microcontroller, which can switch the device off.

---
 arch/arm/boot/dts/kirkwood-ts219.dtsi |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -47,7 +47,7 @@
 		};
 		poweroff@12100 {
 			compatible = "qnap,power-off";
-			reg = <0x12000 0x100>;
+			reg = <0x12100 0x100>;
 			clocks = <&gate_clk 7>;
 		};
 		spi@10600 {

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Anson Huang <[email protected]>

commit fa0708b320f6da4c1104fe56e01b7abf66fd16ad upstream.

In cpu_v7_do_suspend routine, r11 is used while it is NOT saved/restored, different compiler may have different usage of ARM general registers, so it may cause issues during calling cpu_v7_do_suspend.

We meet kernel fault occurs when using GCC 4.8.3, r11 contains valid value before calling into cpu_v7_do_suspend, but when returned from this routine, r11 is corrupted and lead to kernel fault. Doing save/restore for those corrupted registers is a must in assemble code.

---
 arch/arm/mm/proc-v7.S |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area)
 .equ	cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	stmia	r0!, {r4 - r5}

@@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	stmia	r0, {r5 - r11}
-	ldmfd	sp!, {r4 - r10, pc}
+	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
 ENTRY(cpu_v7_do_resume)

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Linus Walleij <[email protected]>

commit e972c37459c813190461dabfeaac228e00aae259 upstream.

Since the dawn of time the ICST code has only supported divide by one or hang in an eternal loop. Luckily we were always dividing by one because the reference frequency for the systems using the ICSTs is 24MHz and the [min,max] values for the PLL input if [10,320] MHz for ICST307 and [6,200] for ICST525, so the loop will always terminate immediately without assigning any divisor for the reference frequency.

But for the code to make sense, let's insert the missing i++

---
 arch/arm/common/icst.c |    1 +
 1 file changed, 1 insertion(+)

@@ -58,6 +58,7 @@ icst_hz_to_vco(const struct icst_params
 
 		if (f > p->vco_min && f <= p->vco_max)
 			break;
+		i++;
 	} while (i < 8);
 
 	if (i >= 8)

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Linus Walleij <[email protected]>

commit 5070fb14a0154f075c8b418e5bc58a620ae85a45 upstream.

When trying to set the ICST 307 clock to 25174000 Hz I ran into this arithmetic error: the icst_hz_to_vco() correctly figure out DIVIDE=2, RDW=100 and VDW=99 yielding a frequency of 25174000 Hz out of the VCO. (I replicated the icst_hz() function in a spreadsheet to verify this.)

However, when I called icst_hz() on these VCO settings it would instead return 4122709 Hz. This causes an error in the common clock driver for ICST as the common clock framework will call .round_rate() on the clock which will utilize icst_hz_to_vco() followed by icst_hz() suggesting the erroneous frequency, and then the clock gets set to this.

The error did not manifest in the old clock framework since this high frequency was only used by the CLCD, which calls clk_set_rate() without first calling clk_round_rate() and since the old clock framework would not call clk_round_rate() before setting the frequency, the correct values propagated into the VCO.

After some experimenting I figured out that it was due to a simple arithmetic overflow: the divisor for 24Mhz reference frequency as reference becomes 24000000*2*(99+8)=0x132212400 and the "1" in bit 32 overflows and is lost.

But introducing an explicit 64-by-32 bit do_div() and casting the divisor into (u64) we get the right frequency back, and the right frequency gets set.

Tested on the ARM Versatile.

---
 arch/arm/common/icst.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -16,7 +16,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-
+#include <asm/div64.h>
 #include <asm/hardware/icst.h>
 
 /*

@@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div);
 
 unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco)
 {
-	return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]);
+	u64 dividend = p->ref * 2 * (u64)(vco.v + 8);
+	u32 divisor = (vco.r + 2) * p->s2div[vco.s];
+
+	do_div(dividend, divisor);
+	return (unsigned long)dividend;
 }
 
 EXPORT_SYMBOL(icst_hz);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Naoya Horiguchi <[email protected]>

commit d96b339f453997f2f08c52da3f41423be48c978f upstream.

I saw the following BUG_ON triggered in a testcase where a process calls madvise(MADV_SOFT_OFFLINE) on thps, along with a background process that calls migratepages command repeatedly (doing ping-pong among different NUMA nodes) for the first process:

Soft offlining page 0x60000 at 0x700000600000
__get_any_page: 0x60000 free buddy page
page:ffffea0001800000 count:0 mapcount:-127 mapping: (null) index:0x1
flags: 0x1fffc0000000000()

   page dumped because: VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0)
   ------------[ cut here ]------------
   kernel BUG at /src/linux-dev/include/linux/mm.h:342!
   invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC
   Modules linked in: cfg80211 rfkill crc32c_intel serio_raw virtio_balloon i2c_piix4 virtio_blk virtio_net ata_generic pata_acpi
   CPU: 3 PID: 3035 Comm: test_alloc_gene Tainted: G           O    4.4.0-rc8-v4.4-rc8-160107-1501-00000-rc8+ #74
   Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
   task: ffff88007c63d5c0 ti: ffff88007c210000 task.ti: ffff88007c210000
   RIP: 0010:[<ffffffff8118998c>]  [<ffffffff8118998c>] put_page+0x5c/0x60
   RSP: 0018:ffff88007c213e00  EFLAGS: 00010246
   Call Trace:
     put_hwpoison_page+0x4e/0x80
     soft_offline_page+0x501/0x520
     SyS_madvise+0x6bc/0x6f0
     entry_SYSCALL_64_fastpath+0x12/0x6a
   Code: 8b fc ff ff 5b 5d c3 48 89 df e8 b0 fa ff ff 48 89 df 31 f6 e8 c6 7d ff ff 5b 5d c3 48 c7 c6 08 54 a2 81 48 89 df e8 a4 c5 01 00 <0f> 0b 66 90 66 66 66 66 90 55 48 89 e5 41 55 41 54 53 48 8b 47
   RIP  [<ffffffff8118998c>] put_page+0x5c/0x60
    RSP <ffff88007c213e00>

The root cause resides in get_any_page() which retries to get a refcount of the page to be soft-offlined. This function calls put_hwpoison_page(), expecting that the target page is putback to LRU list. But it can be also freed to buddy. So the second check need to care about such case.

---
 mm/memory-failure.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1509,7 +1509,7 @@ static int get_any_page(struct page *pag
 		 * Did it turn free?
 		 */
 		ret = __get_any_page(page, pfn, 0);
-		if (!PageLRU(page)) {
+		if (ret == 1 && !PageLRU(page)) {
 			/* Drop page reference which is from __get_any_page() */
 			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Kirill A. Shutemov <[email protected]>

commit 7162a1e87b3e380133dadc7909081bb70d0a7041 upstream.

Tetsuo Handa reported underflow of NR_MLOCK on munlock.

Testcase:

    #include <stdio.h>
    #include <stdlib.h>
    #include <sys/mman.h>

    #define BASE ((void *)0x400000000000)
    #define SIZE (1UL << 21)

    int main(int argc, char *argv[])
    {
        void *addr;

        system("grep Mlocked /proc/meminfo");
        addr = mmap(BASE, SIZE, PROT_READ | PROT_WRITE,
                MAP_ANONYMOUS | MAP_PRIVATE | MAP_LOCKED | MAP_FIXED,
                -1, 0);
        if (addr == MAP_FAILED)
            printf("mmap() failed\n"), exit(1);
        munmap(addr, SIZE);
        system("grep Mlocked /proc/meminfo");
        return 0;
    }

It happens on munlock_vma_page() due to unfortunate choice of nr_pages data type:

    __mod_zone_page_state(zone, NR_MLOCK, -nr_pages);

For unsigned int nr_pages, implicitly casted to long in __mod_zone_page_state(), it becomes something around UINT_MAX.

munlock_vma_page() usually called for THP as small pages go though pagevec.

Let's make nr_pages signed int.

Similar fixes in 6cdb18ad98a4 ("mm/vmstat: fix overflow in mod_zone_page_state()") used long' type, but int' here is OK for a count of the number of sub-pages in a huge page.

---
 mm/mlock.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -172,7 +172,7 @@ static void __munlock_isolation_failed(s
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int nr_pages;
+	int nr_pages;
 	struct zone *zone = page_zone(page);
 
 	/* For try_to_munlock() and to serialize with page migration */

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: CQ Tang <[email protected]>

commit fda3bec12d0979aae3f02ee645913d66fbc8a26e upstream.

This is a 32-bit register. Apparently harmless on real hardware, but causing justified warnings in simulation.

---
 drivers/iommu/dmar.c                |    2 +-
 drivers/iommu/intel_irq_remapping.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

@@ -986,7 +986,7 @@ void dmar_disable_qi(struct intel_iommu
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts =  dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts =  readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_QIES))
 		goto end;
 

@@ -489,7 +489,7 @@ static void iommu_disable_irq_remapping(
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
-	sts = dmar_readq(iommu->reg + DMAR_GSTS_REG);
+	sts = readl(iommu->reg + DMAR_GSTS_REG);
 	if (!(sts & DMA_GSTS_IRES))
 		goto end;
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Andrew Banman <[email protected]>

commit 5f0f2887f4de9508dcf438deab28f1de8070c271 upstream.

test_pages_in_a_zone() does not account for the possibility of missing sections in the given pfn range. pfn_valid_within always returns 1 when CONFIG_HOLES_IN_ZONE is not set, allowing invalid pfns from missing sections to pass the test, leading to a kernel oops.

Wrap an additional pfn loop with PAGES_PER_SECTION granularity to check for missing sections before proceeding into the zone-check code.

This also prevents a crash from offlining memory devices with missing sections. Despite this, it may be a good idea to keep the related patch '[PATCH 3/3] drivers: memory: prohibit offlining of memory blocks with missing sections' because missing sections in a memory block may lead to other problems not covered by the scope of this fix.

---
 mm/memory_hotplug.c |   31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

@@ -1220,23 +1220,30 @@ int is_mem_section_removable(unsigned lo
  */
 static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, sec_end_pfn;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
-	for (pfn = start_pfn;
+	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
 	     pfn < end_pfn;
-	     pfn += MAX_ORDER_NR_PAGES) {
-		i = 0;
-		/* This is just a CONFIG_HOLES_IN_ZONE check.*/
-		while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i))
-			i++;
-		if (i == MAX_ORDER_NR_PAGES)
+	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+		/* Make sure the memory section is present first */
+		if (!present_section_nr(pfn_to_section_nr(pfn)))
 			continue;
-		page = pfn_to_page(pfn + i);
-		if (zone && page_zone(page) != zone)
-			return 0;
-		zone = page_zone(page);
+		for (; pfn < sec_end_pfn && pfn < end_pfn;
+		     pfn += MAX_ORDER_NR_PAGES) {
+			i = 0;
+			/* This is just a CONFIG_HOLES_IN_ZONE check.*/
+			while ((i < MAX_ORDER_NR_PAGES) &&
+				!pfn_valid_within(pfn + i))
+				i++;
+			if (i == MAX_ORDER_NR_PAGES)
+				continue;
+			page = pfn_to_page(pfn + i);
+			if (zone && page_zone(page) != zone)
+				return 0;
+			zone = page_zone(page);
+		}
 	}
 	return 1;
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Mathias Nyman <[email protected]>

commit 5c82171167adb8e4ac77b91a42cd49fb211a81a0 upstream.

xhci driver frees data for all devices, both usb2 and and usb3 the first time usb_remove_hcd() is called, including td_list and and xhci_ring structures.

When usb_remove_hcd() is called a second time for the second xhci bus it will try to dequeue all pending urbs, and touches td_list which is already freed for that endpoint.

---
 drivers/usb/host/xhci.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -1523,7 +1523,9 @@ int xhci_urb_dequeue(struct usb_hcd *hcd
 		xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
 				"HW died, freeing TD.");
 		urb_priv = urb->hcpriv;
-		for (i = urb_priv->td_cnt; i < urb_priv->length; i++) {
+		for (i = urb_priv->td_cnt;
+		     i < urb_priv->length && xhci->devs[urb->dev->slot_id];
+		     i++) {
 			td = urb_priv->td[i];
 			if (!list_empty(&td->td_list))
 				list_del_init(&td->td_list);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Sudip Mukherjee <[email protected]>

commit 601f1db653217f205ffa5fb33514b4e1711e56d1 upstream.

The build of m32104ut_defconfig for m32r arch was failing for long long time with the error:

ERROR: "memory_start" [fs/udf/udf.ko] undefined!
ERROR: "memory_end" [fs/udf/udf.ko] undefined!
ERROR: "memory_end" [drivers/scsi/sg.ko] undefined!
ERROR: "memory_start" [drivers/scsi/sg.ko] undefined!
ERROR: "memory_end" [drivers/i2c/i2c-dev.ko] undefined!
ERROR: "memory_start" [drivers/i2c/i2c-dev.ko] undefined!

As done in other architectures export the symbols to fix the error.

---
 arch/m32r/kernel/setup.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -81,7 +81,10 @@ static struct resource code_resource = {
 };
 
 unsigned long memory_start;
+EXPORT_SYMBOL(memory_start);
+
 unsigned long memory_end;
+EXPORT_SYMBOL(memory_end);
 
 void __init setup_arch(char **);
 int get_cpuinfo(char *);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Daniel Mentz <[email protected]>

commit 0354aec19ce3d355c6213b0434064efc25c9b22c upstream.

dma-debug uses struct dma_debug_entry to keep track of dma coherent memory allocation requests. The virtual address is converted into a pfn and an offset. Previously, the offset was calculated using an incorrect bit mask. As a result, we saw incorrect error messages from dma-debug like the following:

"DMA-API: exceeded 7 overlapping mappings of cacheline 0x03e00000"

Cacheline 0x03e00000 does not exist on our platform.

---
 lib/dma-debug.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1440,7 +1440,7 @@ void debug_dma_alloc_coherent(struct dev
 	entry->type      = dma_debug_coherent;
 	entry->dev       = dev;
 	entry->pfn	 = page_to_pfn(virt_to_page(virt));
-	entry->offset	 = (size_t) virt & PAGE_MASK;
+	entry->offset	 = (size_t) virt & ~PAGE_MASK;
 	entry->size      = size;
 	entry->dev_addr  = dma_addr;
 	entry->direction = DMA_BIDIRECTIONAL;

@@ -1456,7 +1456,7 @@ void debug_dma_free_coherent(struct devi
 		.type           = dma_debug_coherent,
 		.dev            = dev,
 		.pfn		= page_to_pfn(virt_to_page(virt)),
-		.offset		= (size_t) virt & PAGE_MASK,
+		.offset		= (size_t) virt & ~PAGE_MASK,
 		.dev_addr       = addr,
 		.size           = size,
 		.direction      = DMA_BIDIRECTIONAL,

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Konstantin Khlebnikov <[email protected]>

commit 732042821cfa106b3c20b9780e4c60fee9d68900 upstream.

Helper radix_tree_iter_retry() resets next_index to the current index. In following radix_tree_next_slot current chunk size becomes zero. This isn't checked and it tries to dereference null pointer in slot.

Tagged iterator is fine because retry happens only at slot 0 where tag bitmask in iter->tags is filled with single bit.

---
 include/linux/radix-tree.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -341,7 +341,7 @@ void **radix_tree_iter_retry(struct radi
  * @iter:	pointer to radix tree iterator
  * Returns:	current chunk size
  */
-static __always_inline unsigned
+static __always_inline long
 radix_tree_chunk_size(struct radix_tree_iter *iter)
 {
 	return iter->next_index - iter->index;

@@ -375,9 +375,9 @@ radix_tree_next_slot(void **slot, struct
 			return slot + offset + 1;
 		}
 	} else {
-		unsigned size = radix_tree_chunk_size(iter) - 1;
+		long size = radix_tree_chunk_size(iter);
 
-		while (size--) {
+		while (--size > 0) {
 			slot++;
 			iter->index++;
 			if (likely(*slot))

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Thomas Gleixner <[email protected]>

commit fb75a4282d0d9a3c7c44d940582c2d226cf3acfb upstream.

If the proxy lock in the requeue loop acquires the rtmutex for a waiter then it acquired also refcount on the pi_state related to the futex, but the waiter side does not drop the reference count.

Add the missing free_pi_state() call.

---
 kernel/futex.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -2648,6 +2648,11 @@ static int futex_wait_requeue_pi(u32 __u
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			/*
+			 * Drop the reference to the pi state which
+			 * the requeue_pi() code acquired for us.
+			 */
+			free_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
 		}
 	} else {

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Jann Horn <[email protected]>

commit caaee6234d05a58c5b4d05e7bf766131b810a657 upstream.

By checking the effective credentials instead of the real UID / permitted capabilities, ensure that the calling process actually intended to use its credentials.

To ensure that all ptrace checks use the correct caller credentials (e.g. in case out-of-tree code or newly added code omits the PTRACE_MODE_*CREDS flag), use two new flags and require one of them to be set.

The problem was that when a privileged task had temporarily dropped its privileges, e.g. by calling setreuid(0, user_uid), with the intent to perform following syscalls with the credentials of a user, it still passed ptrace access checks that the user would not be able to pass.

While an attacker should not be able to convince the privileged task to perform a ptrace() syscall, this is a problem because the ptrace access check is reused for things in procfs.

In particular, the following somewhat interesting procfs entries only rely on ptrace access checks:

/proc/$pid/stat - uses the check for determining whether pointers
should be visible, useful for bypassing ASLR
/proc/$pid/maps - also useful for bypassing ASLR /proc/$pid/cwd - useful for gaining access to restricted
directories that contain files with lax permissions, e.g. in this scenario:
lrwxrwxrwx root root /proc/13020/cwd -> /root/foobar drwx------ root root /root
drwxr-xr-x root root /root/foobar
-rw-r--r-- root root /root/foobar/secret

Therefore, on a system where a root-owned mode 6755 binary changes its effective credentials as described and then dumps a user-specified file, this could be used by an attacker to reveal the memory layout of root's processes or reveal the contents of files he is not allowed to access (through /proc/$pid/cwd).

---
 fs/proc/array.c        |    2 +-
 fs/proc/base.c         |   20 ++++++++++----------
 fs/proc/namespaces.c   |    4 ++--
 include/linux/ptrace.h |   24 +++++++++++++++++++++++-
 kernel/events/core.c   |    2 +-
 kernel/futex.c         |    2 +-
 kernel/futex_compat.c  |    2 +-
 kernel/kcmp.c          |    4 ++--
 kernel/ptrace.c        |   39 +++++++++++++++++++++++++++++++--------
 mm/process_vm_access.c |    2 +-
 security/commoncap.c   |    7 ++++++-
 11 files changed, 79 insertions(+), 29 deletions(-)

@@ -391,7 +391,7 @@ static int do_task_stat(struct seq_file
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
-	permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+	permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
 	mm = get_task_mm(task);
 	if (mm) {
 		vsize = task_vsize(mm);

@@ -239,7 +239,7 @@ out:
 
 static int proc_pid_auxv(struct task_struct *task, char *buffer)
 {
-	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+	struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	int res = PTR_ERR(mm);
 	if (mm && !IS_ERR(mm)) {
 		unsigned int nwords = 0;

@@ -269,7 +269,7 @@ static int proc_pid_wchan(struct task_st
 	wchan = get_wchan(task);
 
 	if (lookup_symbol_name(wchan, symname) < 0)
-		if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 			return 0;
 		else
 			return sprintf(buffer, "%lu", wchan);

@@ -283,7 +283,7 @@ static int lock_trace(struct task_struct
 	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
 	if (err)
 		return err;
-	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
 		mutex_unlock(&task->signal->cred_guard_mutex);
 		return -EPERM;
 	}

@@ -557,7 +557,7 @@ static int proc_fd_access_allowed(struct
 	 */
 	task = get_proc_task(inode);
 	if (task) {
-		allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+		allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 		put_task_struct(task);
 	}
 	return allowed;

@@ -592,7 +592,7 @@ static bool has_pid_permissions(struct p
 		return true;
 	if (in_group_p(pid->pid_gid))
 		return true;
-	return ptrace_may_access(task, PTRACE_MODE_READ);
+	return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
 
 

@@ -707,7 +707,7 @@ static int __mem_open(struct inode *inod
 	if (!task)
 		return -ESRCH;
 
-	mm = mm_access(task, mode);
+	mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
 	put_task_struct(task);
 
 	if (IS_ERR(mm))

@@ -1760,7 +1760,7 @@ static int map_files_d_revalidate(struct
 	if (!task)
 		goto out_notask;
 
-	mm = mm_access(task, PTRACE_MODE_READ);
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (IS_ERR_OR_NULL(mm))
 		goto out;
 

@@ -1895,7 +1895,7 @@ static struct dentry *proc_map_files_loo
 		goto out;
 
 	result = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	result = -ENOENT;

@@ -1952,7 +1952,7 @@ proc_map_files_readdir(struct file *file
 		goto out;
 
 	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	ret = 0;

@@ -2431,7 +2431,7 @@ static int do_io_accounting(struct task_
 	if (result)
 		return result;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
 		result = -EACCES;
 		goto out_unlock;
 	}

@@ -119,7 +119,7 @@ static void *proc_ns_follow_link(struct
 	if (!task)
 		goto out;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops);

@@ -152,7 +152,7 @@ static int proc_ns_readlink(struct dentr
 	if (!task)
 		goto out;
 
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
 		goto out_put_task;
 
 	len = -ENOENT;

@@ -56,7 +56,29 @@ extern void exit_ptrace(struct task_stru
 #define PTRACE_MODE_READ	0x01
 #define PTRACE_MODE_ATTACH	0x02
 #define PTRACE_MODE_NOAUDIT	0x04
-/* Returns true on success, false on denial. */
+#define PTRACE_MODE_FSCREDS 0x08
+#define PTRACE_MODE_REALCREDS 0x10
+
+/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */
+#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS)
+#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS)
+#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS)
+#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS)
+
+/**
+ * ptrace_may_access - check whether the caller is permitted to access
+ * a target task.
+ * @task: target task
+ * @mode: selects type of access and caller credentials
+ *
+ * Returns true on success, false on denial.
+ *
+ * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must
+ * be set in @mode to specify whether the access was requested through
+ * a filesystem syscall (should use effective capabilities and fsuid
+ * of the caller) or through an explicit syscall such as
+ * process_vm_writev or ptrace (and should use the real credentials).
+ */
 extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
 static inline int ptrace_reparented(struct task_struct *child)

@@ -3096,7 +3096,7 @@ find_lively_task_by_vpid(pid_t vpid)
 
 	/* Reuse ptrace permission checks for now. */
 	err = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
 		goto errout;
 
 	return task;

@@ -2774,7 +2774,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pi
 	}
 
 	ret = -EPERM;
-	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
 		goto err_unlock;
 
 	head = p->robust_list;

@@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list,
 	}
 
 	ret = -EPERM;
-	if (!ptrace_may_access(p, PTRACE_MODE_READ))
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
 		goto err_unlock;
 
 	head = p->compat_robust_list;

@@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t
 			&task2->signal->cred_guard_mutex);
 	if (ret)
 		goto err;
-	if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
-	    !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
+	    !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) {
 		ret = -EPERM;
 		goto err_unlock;
 	}

@@ -225,6 +225,14 @@ static int ptrace_has_cap(struct user_na
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
+	int dumpable = 0;
+	kuid_t caller_uid;
+	kgid_t caller_gid;
+
+	if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
+		WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
+		return -EPERM;
+	}
 
 	/* May we inspect the given task?
 	 * This check is used both for attaching with ptrace

@@ -234,18 +242,33 @@ static int __ptrace_may_access(struct ta
 	 * because setting up the necessary parent/child relationship
 	 * or halting the specified task is impossible.
 	 */
-	int dumpable = 0;
+
 	/* Don't let security modules deny introspection */
 	if (same_thread_group(task, current))
 		return 0;
 	rcu_read_lock();
+	if (mode & PTRACE_MODE_FSCREDS) {
+		caller_uid = cred->fsuid;
+		caller_gid = cred->fsgid;
+	} else {
+		/*
+		 * Using the euid would make more sense here, but something
+		 * in userland might rely on the old behavior, and this
+		 * shouldn't be a security problem since
+		 * PTRACE_MODE_REALCREDS implies that the caller explicitly
+		 * used a syscall that requests access to another process
+		 * (and not a filesystem syscall to procfs).
+		 */
+		caller_uid = cred->uid;
+		caller_gid = cred->gid;
+	}
 	tcred = __task_cred(task);
-	if (uid_eq(cred->uid, tcred->euid) &&
-	    uid_eq(cred->uid, tcred->suid) &&
-	    uid_eq(cred->uid, tcred->uid)  &&
-	    gid_eq(cred->gid, tcred->egid) &&
-	    gid_eq(cred->gid, tcred->sgid) &&
-	    gid_eq(cred->gid, tcred->gid))
+	if (uid_eq(caller_uid, tcred->euid) &&
+	    uid_eq(caller_uid, tcred->suid) &&
+	    uid_eq(caller_uid, tcred->uid)  &&
+	    gid_eq(caller_gid, tcred->egid) &&
+	    gid_eq(caller_gid, tcred->sgid) &&
+	    gid_eq(caller_gid, tcred->gid))
 		goto ok;
 	if (ptrace_has_cap(tcred->user_ns, mode))
 		goto ok;

@@ -312,7 +335,7 @@ static int ptrace_attach(struct task_str
 		goto out;
 
 	task_lock(task);
-	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
 	task_unlock(task);
 	if (retval)
 		goto unlock_creds;

@@ -298,7 +298,7 @@ static ssize_t process_vm_rw_core(pid_t
 		goto free_proc_pages;
 	}
 
-	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS);
 	if (!mm || IS_ERR(mm)) {
 		rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
 		/*

@@ -142,12 +142,17 @@ int cap_ptrace_access_check(struct task_
 {
 	int ret = 0;
 	const struct cred *cred, *child_cred;
+	const kernel_cap_t *caller_caps;
 
 	rcu_read_lock();
 	cred = current_cred();
 	child_cred = __task_cred(child);
+	if (mode & PTRACE_MODE_FSCREDS)
+		caller_caps = &cred->cap_effective;
+	else
+		caller_caps = &cred->cap_permitted;
 	if (cred->user_ns == child_cred->user_ns &&
-	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+	    cap_issubset(child_cred->cap_permitted, *caller_caps))
 		goto out;
 	if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
 		goto out;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Steven Rostedt <[email protected]>

commit 32abc2ede536aae52978d6c0a8944eb1df14f460 upstream.

When a long value is read on 32 bit machines for 64 bit output, the parsing needs to change "%lu" into "%llu", as the value is read natively.

Unfortunately, if "%llu" is already there, the code will add another "l" to it and fail to parse it properly.

---
 tools/lib/traceevent/event-parse.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -4249,13 +4249,12 @@ static void pretty_print(struct trace_se
 				    sizeof(long) != 8) {
 					char *p;
 
-					ls = 2;
 					/* make %l into %ll */
-					p = strchr(format, 'l');
-					if (p)
+					if (ls == 1 && (p = strchr(format, 'l')))
 						memmove(p+1, p, strlen(p)+1);
 					else if (strcmp(format, "%p") == 0)
 						strcpy(format, "0x%llx");
+					ls = 2;
 				}
 				switch (ls) {
 				case -2:

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit b33c8ff4431a343561e2319f17c14286f2aa52e2 upstream.

In my randconfig tests, I came across a bug that involves several components:

* gcc-4.9 through at least 5.3
* CONFIG_GCOV_PROFILE_ALL enabling -fprofile-arcs for all files
* CONFIG_PROFILE_ALL_BRANCHES overriding every if()
* The optimized implementation of do_div() that tries to replace a library call with an division by multiplication
* code in drivers/media/dvb-frontends/zl10353.c doing

        u32 adc_clock = 450560; /* 45.056 MHz */
        if (state->config.adc_clock)
                adc_clock = state->config.adc_clock;
        do_div(value, adc_clock);

In this case, gcc fails to determine whether the divisor in do_div() is __builtin_constant_p(). In particular, it concludes that __builtin_constant_p(adc_clock) is false, while __builtin_constant_p(!!adc_clock) is true.

That in turn throws off the logic in do_div() that also uses __builtin_constant_p(), and instead of picking either the constant- optimized division, and the code in ilog2() that uses __builtin_constant_p() to figure out whether it knows the answer at compile time. The result is a link error from failing to find multiple symbols that should never have been called based on the __builtin_constant_p():

dvb-frontends/zl10353.c:138: undefined reference to ____ilog2_NaN' dvb-frontends/zl10353.c:138: undefined reference to __aeabi_uldivmod'
ERROR: "____ilog2_NaN" [drivers/media/dvb-frontends/zl10353.ko] undefined!
ERROR: "__aeabi_uldivmod" [drivers/media/dvb-frontends/zl10353.ko] undefined!

This patch avoids the problem by changing __trace_if() to check whether the condition is known at compile-time to be nonzero, rather than checking whether it is actually a constant.

I see this one link error in roughly one out of 1600 randconfig builds on ARM, and the patch fixes all known instances.

---
 include/linux/compiler.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -131,7 +131,7 @@ void ftrace_likely_update(struct ftrace_
  */
 #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
 #define __trace_if(cond) \
-	if (__builtin_constant_p((cond)) ? !!(cond) :			\
+	if (__builtin_constant_p(!!(cond)) ? !!(cond) :			\
 	({								\
 		int ______r;						\
 		static struct ftrace_branch_data			\

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: James Bottomley <[email protected]>

commit 00cd29b799e3449f0c68b1cc77cd4a5f95b42d17 upstream.

The starting node for a klist iteration is often passed in from somewhere way above the klist infrastructure, meaning there's no guarantee the node is still on the list. We've seen this in SCSI where we use bus_find_device() to iterate through a list of devices. In the face of heavy hotplug activity, the last device returned by bus_find_device() can be removed before the next call. This leads to

Dec  3 13:22:02 localhost kernel: WARNING: CPU: 2 PID: 28073 at include/linux/kref.h:47 klist_iter_init_node+0x3d/0x50()
Dec  3 13:22:02 localhost kernel: Modules linked in: scsi_debug x86_pkg_temp_thermal kvm_intel kvm irqbypass crc32c_intel joydev iTCO_wdt dcdbas ipmi_devintf acpi_power_meter iTCO_vendor_support ipmi_si imsghandler pcspkr wmi acpi_cpufreq tpm_tis tpm shpchp lpc_ich mfd_core nfsd nfs_acl lockd grace sunrpc tg3 ptp pps_core
Dec  3 13:22:02 localhost kernel: CPU: 2 PID: 28073 Comm: cat Not tainted 4.4.0-rc1+ #2
Dec  3 13:22:02 localhost kernel: Hardware name: Dell Inc. PowerEdge R320/08VT7V, BIOS 2.0.22 11/19/2013
Dec  3 13:22:02 localhost kernel: ffffffff81a20e77 ffff880613acfd18 ffffffff81321eef 0000000000000000
Dec  3 13:22:02 localhost kernel: ffff880613acfd50 ffffffff8107ca52 ffff88061176b198 0000000000000000
Dec  3 13:22:02 localhost kernel: ffffffff814542b0 ffff880610cfb100 ffff88061176b198 ffff880613acfd60
Dec  3 13:22:02 localhost kernel: Call Trace:
Dec  3 13:22:02 localhost kernel: [<ffffffff81321eef>] dump_stack+0x44/0x55
Dec  3 13:22:02 localhost kernel: [<ffffffff8107ca52>] warn_slowpath_common+0x82/0xc0
Dec  3 13:22:02 localhost kernel: [<ffffffff814542b0>] ? proc_scsi_show+0x20/0x20
Dec  3 13:22:02 localhost kernel: [<ffffffff8107cb4a>] warn_slowpath_null+0x1a/0x20
Dec  3 13:22:02 localhost kernel: [<ffffffff8167225d>] klist_iter_init_node+0x3d/0x50
Dec  3 13:22:02 localhost kernel: [<ffffffff81421d41>] bus_find_device+0x51/0xb0
Dec  3 13:22:02 localhost kernel: [<ffffffff814545ad>] scsi_seq_next+0x2d/0x40

[...]

And an eventual crash. It can actually occur in any hotplug system which has a device finder and a starting device.

We can fix this globally by making sure the starting node for klist_iter_init_node() is actually a member of the list before using it (and by starting from the beginning if it isn't).

---
 lib/klist.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *
 			  struct klist_node *n)
 {
 	i->i_klist = k;
-	i->i_cur = n;
-	if (n)
-		kref_get(&n->n_ref);
+	i->i_cur = NULL;
+	if (n && kref_get_unless_zero(&n->n_ref))
+		i->i_cur = n;
 }
 EXPORT_SYMBOL_GPL(klist_iter_init_node);
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Christoph Hellwig <[email protected]>

commit 40998193560dab6c3ce8d25f4fa58a23e252ef38 upstream.

When dropping a lock while iterating a list we must restart the search as other threads could have manipulated the list under us. Without this we can get stuck in an endless loop. This bug was introduced by

commit bc3f02a795d3b4faa99d37390174be2a75d091bd

Author: Dan Williams <[email protected]>
Date:   Tue Aug 28 22:12:10 2012 -0700

[SCSI] scsi_remove_target: fix softlockup regression on hot remove

Which was itself trying to fix a reported soft lockup issue

http://thread.gmane.org/gmane.linux.kernel/1348679

However, we believe even with this revert of the original patch, the soft lockup problem has been fixed by

commit f2495e228fce9f9cec84367547813cbb0d6db15a

Author: James Bottomley <[email protected]>
Date:   Tue Jan 21 07:01:41 2014 -0800

[SCSI] dual scan thread bug fix

Thanks go to Dan Williams <[email protected]> for tracking all this prior history down.

---
 drivers/scsi/scsi_sysfs.c |   16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

@@ -1123,31 +1123,23 @@ static void __scsi_remove_target(struct
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget, *last = NULL;
+	struct scsi_target *starget;
 	unsigned long flags;
 
-	/* remove targets being careful to lookup next entry before
-	 * deleting the last
-	 */
+restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
 		if (starget->state == STARGET_DEL)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
-			/* assuming new targets arrive at the end */
 			kref_get(&starget->reap_ref);
 			spin_unlock_irqrestore(shost->host_lock, flags);
-			if (last)
-				scsi_target_reap(last);
-			last = starget;
 			__scsi_remove_target(starget);
-			spin_lock_irqsave(shost->host_lock, flags);
+			scsi_target_reap(starget);
+			goto restart;
 		}
 	}
 	spin_unlock_irqrestore(shost->host_lock, flags);
-
-	if (last)
-		scsi_target_reap(last);
 }
 EXPORT_SYMBOL(scsi_remove_target);
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Peter Oberparleiter <[email protected]>

commit 863e02d0e173bb9d8cea6861be22820b25c076cc upstream.

Writing a number to /sys/bus/scsi/devices/<sdev>/queue_ramp_up_period returns the value of that number instead of the number of bytes written. This behavior can confuse programs expecting POSIX write() semantics. Fix this by returning the number of bytes written instead.

---
 drivers/scsi/scsi_sysfs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -882,7 +882,7 @@ sdev_store_queue_ramp_up_period(struct d
 		return -EINVAL;
 
 	sdev->queue_ramp_up_period = msecs_to_jiffies(period);
-	return period;
+	return count;
 }
 
 static struct device_attribute sdev_attr_queue_ramp_up_period =

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Ken Xue <[email protected]>

commit 4fd41a8552afc01054d9d9fc7f1a63c324867d27 upstream.

The routines in scsi_pm.c assume that if a runtime-PM callback is invoked for a SCSI device, it can only mean that the device's driver has asked the block layer to handle the runtime power management (by calling blk_pm_runtime_init(), which among other things sets q->dev).

However, this assumption turns out to be wrong for things like the ses driver. Normally ses devices are not allowed to do runtime PM, but userspace can override this setting. If this happens, the kernel gets a NULL pointer dereference when blk_post_runtime_resume() tries to use the uninitialized q->dev pointer.

This patch fixes the problem by checking q->dev in block layer before handle runtime PM. Since ses doesn't define any PM callbacks and call blk_pm_runtime_init(), the crash won't occur.

This fixes Bugzilla #101371.
https://bugzilla.kernel.org/show_bug.cgi?id=101371

More discussion can be found from below link.
http://marc.info/?l=linux-scsi&m=144163730531875&w=2

---
 block/blk-core.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -3164,6 +3164,9 @@ int blk_pre_runtime_suspend(struct reque
 {
 	int ret = 0;
 
+	if (!q->dev)
+		return ret;
+
 	spin_lock_irq(q->queue_lock);
 	if (q->nr_pending) {
 		ret = -EBUSY;

@@ -3191,6 +3194,9 @@ EXPORT_SYMBOL(blk_pre_runtime_suspend);
  */
 void blk_post_runtime_suspend(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_SUSPENDED;

@@ -3215,6 +3221,9 @@ EXPORT_SYMBOL(blk_post_runtime_suspend);
  */
 void blk_pre_runtime_resume(struct request_queue *q)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	q->rpm_status = RPM_RESUMING;
 	spin_unlock_irq(q->queue_lock);

@@ -3237,6 +3246,9 @@ EXPORT_SYMBOL(blk_pre_runtime_resume);
  */
 void blk_post_runtime_resume(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_ACTIVE;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Ken Xue <[email protected]>

commit 1c69d3b6eb73e466ecbb8edaf1bc7fd585b288da upstream.

This reverts commit 49718f0fb8c9 ("SCSI: Fix NULL pointer dereference in runtime PM")

The old commit may lead to a issue that blk_{pre|post}_runtime_suspend and blk_{pre|post}_runtime_resume may not be called in pairs.

Take sr device as example, when sr device goes to runtime suspend, blk_{pre|post}_runtime_suspend will be called since sr device defined pm->runtime_suspend. But blk_{pre|post}_runtime_resume will not be called since sr device doesn't have pm->runtime_resume. so, sr device can not resume correctly anymore.

More discussion can be found from below link.
http://marc.info/?l=linux-scsi&m=144163730531875&w=2

---
 drivers/scsi/scsi_pm.c |   20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

@@ -151,13 +151,13 @@ static int sdev_runtime_suspend(struct d
 	struct scsi_device *sdev = to_scsi_device(dev);
 	int err = 0;
 
-	if (pm && pm->runtime_suspend) {
-		err = blk_pre_runtime_suspend(sdev->request_queue);
-		if (err)
-			return err;
+	err = blk_pre_runtime_suspend(sdev->request_queue);
+	if (err)
+		return err;
+	if (pm && pm->runtime_suspend)
 		err = pm->runtime_suspend(dev);
-		blk_post_runtime_suspend(sdev->request_queue, err);
-	}
+	blk_post_runtime_suspend(sdev->request_queue, err);
+
 	return err;
 }
 

@@ -180,11 +180,11 @@ static int sdev_runtime_resume(struct de
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int err = 0;
 
-	if (pm && pm->runtime_resume) {
-		blk_pre_runtime_resume(sdev->request_queue);
+	blk_pre_runtime_resume(sdev->request_queue);
+	if (pm && pm->runtime_resume)
 		err = pm->runtime_resume(dev);
-		blk_post_runtime_resume(sdev->request_queue, err);
-	}
+	blk_post_runtime_resume(sdev->request_queue, err);
+
 	return err;
 }
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Alan Stern <[email protected]>

commit 13b4389143413a1f18127c07f72c74cad5b563e8 upstream.

Runtime suspend during driver probe and removal can cause problems. The driver's runtime_suspend or runtime_resume callbacks may invoked before the driver has finished binding to the device or after the driver has unbound from the device.

This problem shows up with the sd and sr drivers, and can cause disk or CD/DVD drives to become unusable as a result. The fix is simple. The drivers store a pointer to the scsi_disk or scsi_cd structure as their private device data when probing is finished, so we simply have to be sure to clear the private data during removal and test it during runtime suspend/resume.

This fixes <https://bugs.debian.org/801925>.

---
 drivers/scsi/sd.c |    7 +++++--
 drivers/scsi/sr.c |    4 ++++
 2 files changed, 9 insertions(+), 2 deletions(-)

@@ -3129,8 +3129,8 @@ static int sd_suspend_common(struct devi
 	struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
 	int ret = 0;
 
-	if (!sdkp)
-		return 0;	/* this can happen */
+	if (!sdkp)	/* E.g.: runtime suspend following sd_remove() */
+		return 0;
 
 	if (sdkp->WCE && sdkp->media_present) {
 		sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n");

@@ -3171,6 +3171,9 @@ static int sd_resume(struct device *dev)
 	struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev);
 	int ret = 0;
 
+	if (!sdkp)	/* E.g.: runtime resume at the start of sd_probe() */
+		return 0;
+
 	if (!sdkp->device->manage_start_stop)
 		goto done;
 

@@ -142,6 +142,9 @@ static int sr_runtime_suspend(struct dev
 {
 	struct scsi_cd *cd = dev_get_drvdata(dev);
 
+	if (!cd)	/* E.g.: runtime suspend following sr_remove() */
+		return 0;
+
 	if (cd->media_present)
 		return -EBUSY;
 	else

@@ -995,6 +998,7 @@ static int sr_remove(struct device *dev)
 
 	blk_queue_prep_rq(cd->device->request_queue, scsi_prep_fn);
 	del_gendisk(cd->disk);
+	dev_set_drvdata(dev, NULL);
 
 	mutex_lock(&sr_ref_mutex);
 	kref_put(&cd->kref, sr_kref_release);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Mika Westerberg <[email protected]>

commit 82c43310508eb19eb41fe7862e89afeb74030b84 upstream.

I have a Marvell 88SE9230 SATA Controller that has some sort of integrated console SCSI device attached to one of the ports.

ata14: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata14.00: ATAPI: MARVELL VIRTUALL, 1.09, max UDMA/66 ata14.00: configured for UDMA/66
scsi 13:0:0:0: Processor Marvell Console 1.01 PQ: 0 ANSI: 5

Sending it VPD INQUIRY command seem to always fail with following error:

ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 ata14.00: irq_stat 0x40000001
ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 2 dma 16640 in

            Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation)

ata14: hard resetting link

This has been minor annoyance (only error printed on dmesg) until commit 09e2b0b14690 ("scsi: rescan VPD attributes") added call to scsi_attach_vpd() in scsi_rescan_device(). The commit causes the system to splat out following errors continuously without ever reaching the UI:

ata14.00: configured for UDMA/66
ata14: EH complete
ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 ata14.00: irq_stat 0x40000001
ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 6 dma 16640 in

            Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation)
  ata14: hard resetting link
  ata14: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
  ata14.00: configured for UDMA/66
  ata14: EH complete
  ata14.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6
  ata14.00: irq_stat 0x40000001
  ata14.00: cmd a0/01:00:00:00:01/00:00:00:00:00/a0 tag 7 dma 16640 in
            Inquiry 12 01 00 00 ff 00res 00/00:00:00:00:00/00:00:00:00:00/00 Emask 0x3 (HSM violation)

Without in-depth understanding of SCSI layer and the Marvell controller, I suspect this happens because when the link goes down (because of an error) we schedule scsi_rescan_device() which again fails to read VPD data... ad infinitum.

Since VPD data cannot be read from the device anyway we prevent the SCSI layer from even trying by blacklisting the device. This gets away the error and the system starts up normally.

[mkp: Widened the match to all revisions of this device]

---
 drivers/scsi/scsi_devinfo.c |    1 +
 1 file changed, 1 insertion(+)

@@ -205,6 +205,7 @@ static struct {
 	{"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC},
 	{"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN},
+	{"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES},
 	{"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN},
 	{"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},
 	{"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36},

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: James Bottomley <[email protected]>

commit 90a88d6ef88edcfc4f644dddc7eef4ea41bccf8b upstream.

This softlockup is currently happening:

[  444.088002] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:1:29]
[  444.088002] Modules linked in: lpfc(-) qla2x00tgt(O) qla2xxx_scst(O) scst_vdisk(O) scsi_transport_fc libcrc32c scst(O) dlm configfs nfsd lockd grace nfs_acl auth_rpcgss sunrpc ed

d snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device dm_mod iTCO_wdt snd_hda_codec_realtek snd_hda_codec_generic gpio_ich iTCO_vendor_support ppdev snd_hda_intel snd_hda_codec snd_hda _core snd_hwdep tg3 snd_pcm snd_timer libphy lpc_ich parport_pc ptp acpi_cpufreq snd pps_core fjes parport i2c_i801 ehci_pci tpm_tis tpm sr_mod cdrom soundcore floppy hwmon sg 8250_ fintek pcspkr i915 drm_kms_helper uhci_hcd ehci_hcd drm fb_sys_fops sysimgblt sysfillrect syscopyarea i2c_algo_bit usbcore button video usb_common fan ata_generic ata_piix libata th ermal

[  444.088002] CPU: 1 PID: 29 Comm: kworker/1:1 Tainted: G           O    4.4.0-rc5-2.g1e923a3-default #1
[  444.088002] Hardware name: FUJITSU SIEMENS ESPRIMO E           /D2164-A1, BIOS 5.00 R1.10.2164.A1               05/08/2006
[  444.088002] Workqueue: fc_wq_4 fc_rport_final_delete [scsi_transport_fc]
[  444.088002] task: f6266ec0 ti: f6268000 task.ti: f6268000
[  444.088002] EIP: 0060:[<c07e7044>] EFLAGS: 00000286 CPU: 1
[  444.088002] EIP is at _raw_spin_unlock_irqrestore+0x14/0x20
[  444.088002] EAX: 00000286 EBX: f20d3800 ECX: 00000002 EDX: 00000286
[  444.088002] ESI: f50ba800 EDI: f2146848 EBP: f6269ec8 ESP: f6269ec8
[  444.088002]  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
[  444.088002] CR0: 8005003b CR2: 08f96600 CR3: 363ae000 CR4: 000006d0
[  444.088002] Stack:
[  444.088002]  f6269eec c066b0f7 00000286 f2146848 f50ba808 f50ba800 f50ba800 f2146a90
[  444.088002]  f2146848 f6269f08 f8f0a4ed f3141000 f2146800 f2146a90 f619fa00 00000040
[  444.088002]  f6269f40 c026cb25 00000001 166c6392 00000061 f6757140 f6136340 00000004
[  444.088002] Call Trace:
[  444.088002]  [<c066b0f7>] scsi_remove_target+0x167/0x1c0
[  444.088002]  [<f8f0a4ed>] fc_rport_final_delete+0x9d/0x1e0 [scsi_transport_fc]
[  444.088002]  [<c026cb25>] process_one_work+0x155/0x3e0
[  444.088002]  [<c026cde7>] worker_thread+0x37/0x490
[  444.088002]  [<c027214b>] kthread+0x9b/0xb0
[  444.088002]  [<c07e72c1>] ret_from_kernel_thread+0x21/0x40

What appears to be happening is that something has pinned the target so it can't go into STARGET_DEL via final release and the loop in scsi_remove_target spins endlessly until that happens.

The fix for this soft lockup is to not keep looping over a device that we've called remove on but which hasn't gone into DEL state. This patch will retain a simplistic memory of the last target and not keep looping over it.

---
 drivers/scsi/scsi_sysfs.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -1123,16 +1123,18 @@ static void __scsi_remove_target(struct
 void scsi_remove_target(struct device *dev)
 {
 	struct Scsi_Host *shost = dev_to_shost(dev->parent);
-	struct scsi_target *starget;
+	struct scsi_target *starget, *last_target = NULL;
 	unsigned long flags;
 
 restart:
 	spin_lock_irqsave(shost->host_lock, flags);
 	list_for_each_entry(starget, &shost->__targets, siblings) {
-		if (starget->state == STARGET_DEL)
+		if (starget->state == STARGET_DEL ||
+		    starget == last_target)
 			continue;
 		if (starget->dev.parent == dev || &starget->dev == dev) {
 			kref_get(&starget->reap_ref);
+			last_target = starget;
 			spin_unlock_irqrestore(shost->host_lock, flags);
 			__scsi_remove_target(starget);
 			scsi_target_reap(starget);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lars-Peter Clausen <[email protected]>

commit 5dcbe97bedd6ba4b0f574a96cc2e293d26f3d857 upstream.

The ad5629/ad5669 are the I2C variant of the ad5628/ad5668, which has a SPI interface. They are mostly identical with the exception that the shift factor is different. Currently the driver does not take care of this difference which leads to incorrect DAC output values.

Fix this by introducing a custom channel spec for the ad5629/ad5669 with the correct shift factor.

---
 drivers/iio/dac/ad5064.c |   83 ++++++++++++++++++++++++++++++++---------------
 1 file changed, 57 insertions(+), 26 deletions(-)

@@ -113,12 +113,16 @@ enum ad5064_type {
 	ID_AD5065,
 	ID_AD5628_1,
 	ID_AD5628_2,
+	ID_AD5629_1,
+	ID_AD5629_2,
 	ID_AD5648_1,
 	ID_AD5648_2,
 	ID_AD5666_1,
 	ID_AD5666_2,
 	ID_AD5668_1,
 	ID_AD5668_2,
+	ID_AD5669_1,
+	ID_AD5669_2,
 };
 
 static int ad5064_write(struct ad5064_state *st, unsigned int cmd,

@@ -291,7 +295,7 @@ static const struct iio_chan_spec_ext_in
 	{ },
 };
 
-#define AD5064_CHANNEL(chan, addr, bits) {			\
+#define AD5064_CHANNEL(chan, addr, bits, _shift) {		\
 	.type = IIO_VOLTAGE,					\
 	.indexed = 1,						\
 	.output = 1,						\

@@ -303,36 +307,39 @@ static const struct iio_chan_spec_ext_in
 		.sign = 'u',					\
 		.realbits = (bits),				\
 		.storagebits = 16,				\
-		.shift = 20 - bits,				\
+		.shift = (_shift),				\
 	},							\
 	.ext_info = ad5064_ext_info,				\
 }
 
-#define DECLARE_AD5064_CHANNELS(name, bits) \
+#define DECLARE_AD5064_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 1, bits), \
-	AD5064_CHANNEL(2, 2, bits), \
-	AD5064_CHANNEL(3, 3, bits), \
-	AD5064_CHANNEL(4, 4, bits), \
-	AD5064_CHANNEL(5, 5, bits), \
-	AD5064_CHANNEL(6, 6, bits), \
-	AD5064_CHANNEL(7, 7, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 1, bits, shift), \
+	AD5064_CHANNEL(2, 2, bits, shift), \
+	AD5064_CHANNEL(3, 3, bits, shift), \
+	AD5064_CHANNEL(4, 4, bits, shift), \
+	AD5064_CHANNEL(5, 5, bits, shift), \
+	AD5064_CHANNEL(6, 6, bits, shift), \
+	AD5064_CHANNEL(7, 7, bits, shift), \
 }
 
-#define DECLARE_AD5065_CHANNELS(name, bits) \
+#define DECLARE_AD5065_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 3, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 3, bits, shift), \
 }
 
-static DECLARE_AD5064_CHANNELS(ad5024_channels, 12);
-static DECLARE_AD5064_CHANNELS(ad5044_channels, 14);
-static DECLARE_AD5064_CHANNELS(ad5064_channels, 16);
+static DECLARE_AD5064_CHANNELS(ad5024_channels, 12, 8);
+static DECLARE_AD5064_CHANNELS(ad5044_channels, 14, 6);
+static DECLARE_AD5064_CHANNELS(ad5064_channels, 16, 4);
 
-static DECLARE_AD5065_CHANNELS(ad5025_channels, 12);
-static DECLARE_AD5065_CHANNELS(ad5045_channels, 14);
-static DECLARE_AD5065_CHANNELS(ad5065_channels, 16);
+static DECLARE_AD5065_CHANNELS(ad5025_channels, 12, 8);
+static DECLARE_AD5065_CHANNELS(ad5045_channels, 14, 6);
+static DECLARE_AD5065_CHANNELS(ad5065_channels, 16, 4);
+
+static DECLARE_AD5064_CHANNELS(ad5629_channels, 12, 4);
+static DECLARE_AD5064_CHANNELS(ad5669_channels, 16, 0);
 
 static const struct ad5064_chip_info ad5064_chip_info_tbl[] = {
 	[ID_AD5024] = {

@@ -382,6 +389,18 @@ static const struct ad5064_chip_info ad5
 		.channels = ad5024_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5629_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5629_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
 	[ID_AD5648_1] = {
 		.shared_vref = true,
 		.internal_vref = 2500000,

@@ -418,6 +437,18 @@ static const struct ad5064_chip_info ad5
 		.channels = ad5064_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5669_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5669_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
 };
 
 static inline unsigned int ad5064_num_vref(struct ad5064_state *st)

@@ -623,12 +654,12 @@ static int ad5064_i2c_remove(struct i2c_
 }
 
 static const struct i2c_device_id ad5064_i2c_ids[] = {
-	{"ad5629-1", ID_AD5628_1},
-	{"ad5629-2", ID_AD5628_2},
-	{"ad5629-3", ID_AD5628_2}, /* similar enough to ad5629-2 */
-	{"ad5669-1", ID_AD5668_1},
-	{"ad5669-2", ID_AD5668_2},
-	{"ad5669-3", ID_AD5668_2}, /* similar enough to ad5669-2 */
+	{"ad5629-1", ID_AD5629_1},
+	{"ad5629-2", ID_AD5629_2},
+	{"ad5629-3", ID_AD5629_2}, /* similar enough to ad5629-2 */
+	{"ad5669-1", ID_AD5669_1},
+	{"ad5669-2", ID_AD5669_2},
+	{"ad5669-3", ID_AD5669_2}, /* similar enough to ad5669-2 */
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, ad5064_i2c_ids);

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Lars-Peter Clausen <[email protected]>

commit d590faf9e8f8509a0a0aa79c38e87fcc6b913248 upstream.

The SPI tx and rx buffers are both supposed to be scan_bytes amount of bytes large and a common allocation is used to allocate both buffers. This puts the beginning of the tx buffer scan_bytes bytes after the rx buffer. The initialization of the tx buffer pointer is done adding scan_bytes to the beginning of the rx buffer, but since the rx buffer is of type __be16 this will actually add two times as much and the tx buffer ends up pointing after the allocated buffer.

Fix this by using scan_count, which is scan_bytes / 2, instead of scan_bytes when initializing the tx buffer pointer.

---
 drivers/iio/imu/adis_buffer.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev
 		return -ENOMEM;
 
 	rx = adis->buffer;
-	tx = rx + indio_dev->scan_bytes;
+	tx = rx + scan_count;
 
 	spi_message_init(&adis->msg);
 

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Yong Li <[email protected]>

commit 97a249e98a72d6b79fb7350a8dd56b147e9d5bdb upstream.

Without this change, the name entity for mcp4725 is missing in /sys/bus/iio/devices/iio\:device*/name

With this change, name is reported correctly

---
 drivers/iio/dac/mcp4725.c |    1 +
 1 file changed, 1 insertion(+)

@@ -301,6 +301,7 @@ static int mcp4725_probe(struct i2c_clie
 	data->client = client;
 
 	indio_dev->dev.parent = &client->dev;
+	indio_dev->name = id->name;
 	indio_dev->info = &mcp4725_info;
 	indio_dev->channels = &mcp4725_channel;
 	indio_dev->num_channels = 1;

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Anton Protopopov <[email protected]>

commit 4b550af519854421dfec9f7732cdddeb057134b2 upstream.

The setup_ntlmv2_rsp() function may return positive value ENOMEM instead of -ENOMEM in case of kmalloc failure.

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

@@ -710,7 +710,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, c
 
 	ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL);
 	if (!ses->auth_key.response) {
-		rc = ENOMEM;
+		rc = -ENOMEM;
 		ses->auth_key.len = 0;
 		goto setup_ntlmv2_rsp_ret;
 	}

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Andrew Elble <[email protected]>

commit 361cad3c89070aeb37560860ea8bfc092d545adc upstream.

We've seen this in a packet capture - I've intermixed what I think was going on. The fix here is to grab the so_lock sooner.

1964379 -> #1 open (for write) reply seqid=1
1964393 -> #2 open (for read) reply seqid=2

__nfs4_close(), state->n_wronly-- nfs4_state_set_mode_locked(), changes state->state = [R] state->flags is [RW]
state->state is [R], state->n_wronly == 0, state->n_rdonly == 1

1964398 -> #3 open (for write) call -> because close is already running 1964399 -> downgrade (to read) call seqid=2 (close of #1) 1964402 -> #3 open (for write) reply seqid=3

__update_open_stateid()
nfs_set_open_stateid_locked(), changes state->flags state->flags is [RW]
state->state is [R], state->n_wronly == 0, state->n_rdonly == 1 new sequence number is exposed now via nfs4_stateid_copy()

next step would be update_open_stateflags(), pending so_lock

1964403 -> downgrade reply seqid=2, fails with OLD_STATEID (close of #1)

nfs4_close_prepare() gets so_lock and recalcs flags -> send close

1964405 -> downgrade (to read) call seqid=3 (close of #1 retry)

__update_open_stateid() gets so_lock
* update_open_stateflags() updates state->n_wronly. nfs4_state_set_mode_locked() updates state->state

state->flags is [RW]
state->state is [RW], state->n_wronly == 1, state->n_rdonly == 1

* should have suppressed the preceding nfs4_close_prepare() from sending open_downgrade

1964406 -> write call
1964408 -> downgrade (to read) reply seqid=4 (close of #1 retry)

nfs_clear_open_stateid_locked()
state->flags is [R]
state->state is [RW], state->n_wronly == 1, state->n_rdonly == 1

1964409 -> write reply (fails, openmode)

---
 fs/nfs/nfs4proc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1169,6 +1169,7 @@ static void __update_open_stateid(struct
 	 * Protect the call to nfs4_state_set_mode_locked and
 	 * serialise the stateid update
 	 */
+	spin_lock(&state->owner->so_lock);
 	write_seqlock(&state->seqlock);
 	if (deleg_stateid != NULL) {
 		nfs4_stateid_copy(&state->stateid, deleg_stateid);

@@ -1177,7 +1178,6 @@ static void __update_open_stateid(struct
 	if (open_stateid != NULL)
 		nfs_set_open_stateid_locked(state, open_stateid, fmode);
 	write_sequnlock(&state->seqlock);
-	spin_lock(&state->owner->so_lock);
 	update_open_stateflags(state, fmode);
 	spin_unlock(&state->owner->so_lock);
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Herton R. Krzesinski <[email protected]>

commit 1f55c718c290616889c04946864a13ef30f64929 upstream.

Considering current pty code and multiple devpts instances, it's possible to umount a devpts file system while a program still has /dev/tty opened pointing to a previosuly closed pty pair in that instance. In the case all ptmx and pts/N files are closed, umount can be done. If the program closes /dev/tty after umount is done, devpts_kill_index will use now an invalid super_block, which was already destroyed in the umount operation after running ->kill_sb. This is another "use after free" type of issue, but now related to the allocated super_block instance.

To avoid the problem (warning at ida_remove and potential crashes) for this specific case, I added two functions in devpts which grabs additional references to the super_block, which pty code now uses so it makes sure the super block structure is still valid until pty shutdown is done. I also moved the additional inode references to the same functions, which also covered similar case with inode being freed before /dev/tty final close/shutdown.

---
 drivers/tty/pty.c         |    9 ++++++---
 fs/devpts/inode.c         |   20 ++++++++++++++++++++
 include/linux/devpts_fs.h |    4 ++++
 3 files changed, 30 insertions(+), 3 deletions(-)

@@ -624,7 +624,7 @@ static void pty_unix98_shutdown(struct t
 	else
 		ptmx_inode = tty->link->driver_data;
 	devpts_kill_index(ptmx_inode, tty->index);
-	iput(ptmx_inode); /* drop reference we acquired at ptmx_open */
+	devpts_del_ref(ptmx_inode);
 }
 
 static const struct tty_operations ptm_unix98_ops = {

@@ -720,9 +720,12 @@ static int ptmx_open(struct inode *inode
 	 * still have /dev/tty opened pointing to the master/slave pair (ptmx
 	 * is closed/released before /dev/tty), we must make sure that the inode
 	 * is still valid when we call the final pty_unix98_shutdown, thus we
-	 * hold an additional reference to the ptmx inode
+	 * hold an additional reference to the ptmx inode. For the same /dev/tty
+	 * last close case, we also need to make sure the super_block isn't
+	 * destroyed (devpts instance unmounted), before /dev/tty is closed and
+	 * on its release devpts_kill_index is called.
 	 */
-	ihold(inode);
+	devpts_add_ref(inode);
 
 	tty_add_file(tty, filp);
 

@@ -564,6 +564,26 @@ void devpts_kill_index(struct inode *ptm
 	mutex_unlock(&allocated_ptys_lock);
 }
 
+/*
+ * pty code needs to hold extra references in case of last /dev/tty close
+ */
+
+void devpts_add_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	atomic_inc(&sb->s_active);
+	ihold(ptmx_inode);
+}
+
+void devpts_del_ref(struct inode *ptmx_inode)
+{
+	struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+
+	iput(ptmx_inode);
+	deactivate_super(sb);
+}
+
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master

@@ -19,6 +19,8 @@
 
 int devpts_new_index(struct inode *ptmx_inode);
 void devpts_kill_index(struct inode *ptmx_inode, int idx);
+void devpts_add_ref(struct inode *ptmx_inode);
+void devpts_del_ref(struct inode *ptmx_inode);
 /* mknod in devpts */
 struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
 		void *priv);

@@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode
 /* Dummy stubs in the no-pty case */
 static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
 static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
+static inline void devpts_add_ref(struct inode *ptmx_inode) { }
+static inline void devpts_del_ref(struct inode *ptmx_inode) { }
 static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
 		dev_t device, int index, void *priv)
 {

This is the start of the stable review cycle for the 3.14.62 release. There are 70 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 me know.

Responses should be made by Fri Feb 26 03:33:41 UTC 2016. 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/v3.x/stable-review/patch-3.14.62-rc1.gz

and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 3.14.62-rc1

Rusty Russell <[email protected]>
module: wrapper for symbol name.

WANG Cong <[email protected]>
ip6mr: call del_timer_sync() in ip6mr_free_table()

Thomas Gleixner <[email protected]>
futex: Drop refcount if requeue_pi() acquired the rtmutex

Dan Carpenter <[email protected]>
intel_scu_ipcutil: underflow in scu_reg_access()

Eric Dumazet <[email protected]>
dump_stack: avoid potential deadlocks

Konstantin Khlebnikov <[email protected]>
radix-tree: fix oops after radix_tree_iter_retry

Matthew Wilcox <[email protected]>
radix-tree: fix race in gang lookup

Martijn Coenen <[email protected]>
memcg: only free spare array when readers are done

Sergey Senozhatsky <[email protected]>
scripts/bloat-o-meter: fix python3 syntax error

Laura Abbott <[email protected]>
dma-debug: switch check from _text to _stext

Daniel Mentz <[email protected]>
dma-debug: Fix dma_debug_entry offset calculation

Sudip Mukherjee <[email protected]>
m32r: fix m32104ut_defconfig build fail

Mathias Nyman <[email protected]>
xhci: Fix list corruption in urb dequeue at host removal

Andrew Banman <[email protected]>
mm/memory_hotplug.c: check for missing sections in test_pages_in_a_zone()

CQ Tang <[email protected]>
iommu/vt-d: Fix 64-bit accesses to 32-bit DMAR_GSTS_REG

Aurélien Francillon <[email protected]>
Input: i8042 - add Fujitsu Lifebook U745 to the nomux list

Benjamin Tissoires <[email protected]>
Input: elantech - mark protocols v2 and v3 as semi-mt

Takashi Iwai <[email protected]>
Input: elantech - add Fujitsu Lifebook U745 to force crc_enabled

Kirill A. Shutemov <[email protected]>
mm: fix mlock accouting

Naoya Horiguchi <[email protected]>
mm: soft-offline: check return value in second __get_any_page() call

Roman Gushchin <[email protected]>
fuse: break infinite loop in fuse_fill_write_pages()

Thomas Huth <[email protected]>
KVM: PPC: Fix emulation of H_SET_DABR/X on POWER8

Linus Walleij <[email protected]>
ARM: 8517/1: ICST: avoid arithmetic overflow in icst_hz()

Linus Walleij <[email protected]>
ARM: 8519/1: ICST: try other dividends than 1

Anson Huang <[email protected]>
ARM: 8471/1: need to save/restore arm register(r11) when it is corrupted

Helmut Klein <[email protected]>
ARM: dts: Kirkwood: Fix QNAP TS219 power-off

Andrew Gabbasov <[email protected]>
udf: Check output buffer length when converting name to CS0

Andrew Gabbasov <[email protected]>
udf: Prevent buffer overrun with multi-byte characters

Vegard Nossum <[email protected]>
udf: limit the maximum number of indirect extents in a row

Andrew Elble <[email protected]>
nfs: Fix race in __update_open_stateid()

Anton Protopopov <[email protected]>
cifs: fix erroneous return value

Vasily Averin <[email protected]>
cifs_dbg() outputs an uninitialized buffer in cifs_readdir()

Yong Li <[email protected]>
iio: dac: mcp4725: set iio name property in sysfs

Lars-Peter Clausen <[email protected]>
iio: adis_buffer: Fix out-of-bounds memory access

Dan Carpenter <[email protected]>
iio: fix some warning messages

Lars-Peter Clausen <[email protected]>

    iio: ad5064: Fix ad5629/ad5669 shift

Michael Hennerich <[email protected]>

    iio:ad5064: Make sure ad5064_i2c_write() returns 0 on success

Vladimir Zapolskiy <[email protected]>
iio: lpc32xx_adc: fix warnings caused by enabling unprepared clock

Lars-Peter Clausen <[email protected]>

    iio:ad7793: Fix ad7785 product ID

James Bottomley <[email protected]>
scsi: fix soft lockup in scsi_remove_target() on module removal

Mika Westerberg <[email protected]>
SCSI: Add Marvell Console to VPD blacklist

Hannes Reinecke <[email protected]>
scsi_dh_rdac: always retry MODE SELECT on command lock violation

Kirill A. Shutemov <[email protected]>
drivers/scsi/sg.c: mark VMA as VM_IO to prevent migration

Alan Stern <[email protected]>
SCSI: fix crashes in sd and sr runtime PM

Nicholas Bellinger <[email protected]>
iscsi-target: Fix potential dead-lock during node acl delete

Ken Xue <[email protected]>
Revert "SCSI: Fix NULL pointer dereference in runtime PM"

Ken Xue <[email protected]>
SCSI: Fix NULL pointer dereference in runtime PM

Bart Van Assche <[email protected]>
Fix a memory leak in scsi_host_dev_release()

Nicholas Bellinger <[email protected]>
iscsi-target: Fix rx_login_comp hang after login failure

Peter Oberparleiter <[email protected]>
scsi_sysfs: Fix queue_ramp_up_period return code

Christoph Hellwig <[email protected]>
scsi: restart list search after unlock in scsi_remove_target

James Bottomley <[email protected]>
klist: fix starting point removed bug in klist iterators

Arnd Bergmann <[email protected]>
tracing: Fix freak link error caused by branch tracer

Steven Rostedt <[email protected]>
tools lib traceevent: Fix output of %llu for 64 bit values read on 32 bit machines

Jann Horn <[email protected]>
ptrace: use fsuid, fsgid, effective creds for fs access checks

Peter Feiner <[email protected]>
perf trace: Fix documentation for -i

Peter Zijlstra <[email protected]>
perf: Fix inherited events vs. tracepoint filters

Filipe Manana <[email protected]>
Btrfs: fix hang on extent buffer lock caused by the inode_paths ioctl

David Sterba <[email protected]>

    btrfs: properly set the termination value of ctx->pos in readdir

Insu Yun <[email protected]>
ext4: fix potential integer overflow

Greg Kroah-Hartman <[email protected]>
AIO: properly check iovec sizes

Soeren Grunewald <[email protected]>
serial: 8250_pci: Correct uartclk for xr17v35x expansion chips

Herton R. Krzesinski <[email protected]>
pty: make sure super_block is still valid in final /dev/tty close

Herton R. Krzesinski <[email protected]>

    pty: fix possible use after free of tty->driver_data

Peter Hurley <[email protected]>
staging/speakup: Use tty_ldisc_ref() for paste kworker

Peter Hurley <[email protected]>

    wan/x25: Fix use-after-free in x25_asy_open_tty()

Tony Lindgren <[email protected]>
phy: twl4030-usb: Relase usb phy on unload

Takashi Iwai <[email protected]>
ALSA: seq: Fix double port list deletion

Imre Deak <[email protected]>
drm/i915: get runtime PM reference around GEM set_caching IOCTL

Matt Fleming <[email protected]>

    x86/mm/pat: Avoid truncation when converting cpa->numpages to address

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

Diffstat:

 Makefile                                     |  4 +-
 arch/arm/boot/dts/kirkwood-ts219.dtsi        |  2 +-
 arch/arm/common/icst.c                       |  9 ++-
 arch/arm/mm/proc-v7.S                        |  4 +-
 arch/m32r/kernel/setup.c                     |  3 +
 arch/powerpc/kvm/book3s_hv_rmhandlers.S      |  2 +-
 arch/x86/mm/pageattr.c                       |  4 +-
 block/blk-core.c                             | 12 ++++
 drivers/gpu/drm/i915/i915_gem.c              |  8 ++-
 drivers/iio/adc/ad7793.c                     |  2 +-
 drivers/iio/dac/ad5064.c                     | 91 +++++++++++++++++++---------
 drivers/iio/dac/mcp4725.c                    |  1 +
 drivers/iio/imu/adis_buffer.c                |  2 +-
 drivers/iio/industrialio-buffer.c            |  2 +-
 drivers/iio/industrialio-core.c              |  2 +-
 drivers/input/mouse/elantech.c               |  9 ++-
 drivers/input/serio/i8042-x86ia64io.h        |  7 +++
 drivers/iommu/dmar.c                         |  2 +-
 drivers/iommu/intel_irq_remapping.c          |  2 +-
 drivers/net/wan/x25_asy.c                    |  6 +-
 drivers/phy/phy-twl4030-usb.c                |  1 +
 drivers/platform/x86/intel_scu_ipcutil.c     |  2 +-
 drivers/scsi/device_handler/scsi_dh_rdac.c   |  4 +-
 drivers/scsi/hosts.c                         | 11 ++++
 drivers/scsi/scsi_devinfo.c                  |  1 +
 drivers/scsi/scsi_pm.c                       | 20 +++---
 drivers/scsi/scsi_sysfs.c                    | 22 +++----
 drivers/scsi/sd.c                            |  7 ++-
 drivers/scsi/sg.c                            |  2 +-
 drivers/scsi/sr.c                            |  4 ++
 drivers/staging/iio/adc/lpc32xx_adc.c        |  4 +-
 drivers/staging/speakup/selection.c          |  5 +-
 drivers/target/iscsi/iscsi_target.c          | 13 +++-
 drivers/target/iscsi/iscsi_target_configfs.c | 16 ++++-
 drivers/target/iscsi/iscsi_target_nego.c     |  1 +
 drivers/tty/pty.c                            | 21 ++++++-
 drivers/tty/serial/8250/8250_pci.c           | 22 ++++++-
 drivers/usb/host/xhci.c                      |  4 +-
 fs/aio.c                                     |  9 ++-
 fs/btrfs/backref.c                           | 10 +--
 fs/btrfs/delayed-inode.c                     |  3 +-
 fs/btrfs/delayed-inode.h                     |  2 +-
 fs/btrfs/inode.c                             | 14 ++++-
 fs/cifs/cifsencrypt.c                        |  2 +-
 fs/cifs/readdir.c                            |  1 +
 fs/devpts/inode.c                            | 20 ++++++
 fs/ext4/resize.c                             |  2 +-
 fs/fuse/file.c                               |  2 +-
 fs/nfs/nfs4proc.c                            |  2 +-
 fs/proc/array.c                              |  2 +-
 fs/proc/base.c                               | 20 +++---
 fs/proc/namespaces.c                         |  4 +-
 fs/udf/inode.c                               | 15 +++++
 fs/udf/unicode.c                             | 21 ++++++-
 include/linux/compiler.h                     |  2 +-
 include/linux/devpts_fs.h                    |  4 ++
 include/linux/ptrace.h                       | 24 +++++++-
 include/linux/radix-tree.h                   | 22 ++++++-
 kernel/events/core.c                         |  6 +-
 kernel/futex.c                               |  7 ++-
 kernel/futex_compat.c                        |  2 +-
 kernel/kcmp.c                                |  4 +-
 kernel/module.c                              | 26 ++++----
 kernel/ptrace.c                              | 39 +++++++++---
 lib/dma-debug.c                              |  6 +-
 lib/dump_stack.c                             |  7 ++-
 lib/klist.c                                  |  6 +-
 lib/radix-tree.c                             | 12 +++-
 mm/memcontrol.c                              | 11 ++--
 mm/memory-failure.c                          |  2 +-
 mm/memory_hotplug.c                          | 31 ++++++----
 mm/mlock.c                                   |  2 +-
 mm/process_vm_access.c                       |  2 +-
 net/ipv6/ip6mr.c                             |  2 +-
 scripts/bloat-o-meter                        |  8 +--
 security/commoncap.c                         |  7 ++-
 sound/core/seq/seq_ports.c                   | 13 ++--
 tools/lib/traceevent/event-parse.c           |  5 +-
 tools/perf/Documentation/perf-trace.txt      |  1 -
 79 files changed, 521 insertions(+), 193 deletions(-)

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Laura Abbott <[email protected]>

commit ea535e418c01837d07b6c94e817540f50bfdadb0 upstream.

In include/asm-generic/sections.h:

/*
* Usage guidelines:
* _text, _data: architecture specific, don't use them in
* arch-independent code
* [_stext, _etext]: contains .text.* sections, may also contain
* .rodata.*
* and/or .init.* sections

_text is not guaranteed across architectures. Architectures such as ARM may reuse parts which are not actually text and erroneously trigger a bug. Switch to using _stext which is guaranteed to contain text sections.

Came out of https://lkml.kernel.org/g/<[email protected]>

---
 lib/dma-debug.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1165,7 +1165,7 @@ static inline bool overlap(void *addr, u
 
 static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
 {
-	if (overlap(addr, len, _text, _etext) ||
+	if (overlap(addr, len, _stext, _etext) ||
 	    overlap(addr, len, __start_rodata, __end_rodata))
 		err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Sergey Senozhatsky <[email protected]>

commit 72214a24a7677d4c7501eecc9517ed681b5f2db2 upstream.

In Python3+ print is a function so the old syntax is not correct anymore:

  $ ./scripts/bloat-o-meter vmlinux.o vmlinux.o.old
    File "./scripts/bloat-o-meter", line 61
      print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \
                                                                     ^
  SyntaxError: invalid syntax

Fix by calling print as a function.

Tested on python 2.7.11, 3.5.1

---
 scripts/bloat-o-meter |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -56,8 +56,8 @@ for name in common:
 delta.sort()
 delta.reverse()
 
-print "add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \
-      (add, remove, grow, shrink, up, -down, up-down)
-print "%-40s %7s %7s %+7s" % ("function", "old", "new", "delta")
+print("add/remove: %s/%s grow/shrink: %s/%s up/down: %s/%s (%s)" % \
+      (add, remove, grow, shrink, up, -down, up-down))
+print("%-40s %7s %7s %+7s" % ("function", "old", "new", "delta"))
 for d, n in delta:
-    if d: print "%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d)
+    if d: print("%-40s %7s %7s %+7d" % (n, old.get(n,"-"), new.get(n,"-"), d))

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Martijn Coenen <[email protected]>

commit 6611d8d76132f86faa501de9451a89bf23fb2371 upstream.

A spare array holding mem cgroup threshold events is kept around to make sure we can always safely deregister an event and have an array to store the new set of events in.

In the scenario where we're going from 1 to 0 registered events, the pointer to the primary array containing 1 event is copied to the spare slot, and then the spare slot is freed because no events are left. However, it is freed before calling synchronize_rcu(), which means readers may still be accessing threshold->primary after it is freed.

Fixed by only freeing after synchronize_rcu().

---
 mm/memcontrol.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

@@ -5858,16 +5858,17 @@ static void __mem_cgroup_usage_unregiste
 swap_buffers:
 	/* Swap primary and spare array */
 	thresholds->spare = thresholds->primary;
-	/* If all events are unregistered, free the spare array */
-	if (!new) {
-		kfree(thresholds->spare);
-		thresholds->spare = NULL;
-	}
 
 	rcu_assign_pointer(thresholds->primary, new);
 
 	/* To be sure that nobody uses thresholds */
 	synchronize_rcu();
+
+	/* If all events are unregistered, free the spare array */
+	if (!new) {
+		kfree(thresholds->spare);
+		thresholds->spare = NULL;
+	}
 unlock:
 	mutex_unlock(&memcg->thresholds_lock);
 }

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Matthew Wilcox <[email protected]>

commit 46437f9a554fbe3e110580ca08ab703b59f2f95a upstream.

If the indirect_ptr bit is set on a slot, that indicates we need to redo the lookup. Introduce a new function radix_tree_iter_retry() which forces the loop to retry the lookup by setting 'slot' to NULL and turning the iterator back to point at the problematic entry.

This is a pretty rare problem to hit at the moment; the lookup has to race with a grow of the radix tree from a height of 0. The consequences of hitting this race are that gang lookup could return a pointer to a radix_tree_node instead of a pointer to whatever the user had inserted in the tree.

---
 include/linux/radix-tree.h |   16 ++++++++++++++++
 lib/radix-tree.c           |   12 ++++++++++--
 2 files changed, 26 insertions(+), 2 deletions(-)

@@ -320,6 +320,22 @@ void **radix_tree_next_chunk(struct radi
 			     struct radix_tree_iter *iter, unsigned flags);
 
 /**
+ * radix_tree_iter_retry - retry this chunk of the iteration
+ * @iter:	iterator state
+ *
+ * If we iterate over a tree protected only by the RCU lock, a race
+ * against deletion or creation may result in seeing a slot for which
+ * radix_tree_deref_retry() returns true.  If so, call this function
+ * and continue the iteration.
+ */
+static inline __must_check
+void **radix_tree_iter_retry(struct radix_tree_iter *iter)
+{
+	iter->next_index = iter->index;
+	return NULL;
+}
+
+/**
  * radix_tree_chunk_size - get current chunk size
  *
  * @iter:	pointer to radix tree iterator

@@ -977,9 +977,13 @@ radix_tree_gang_lookup(struct radix_tree
 		return 0;
 
 	radix_tree_for_each_slot(slot, root, &iter, first_index) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}

@@ -1056,9 +1060,13 @@ radix_tree_gang_lookup_tag(struct radix_
 		return 0;
 
 	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

commit d7ce36924344ace0dbdc855b1206cacc46b36d45 upstream.

Some servers experienced fatal deadlocks because of a combination of bugs, leading to multiple cpus calling dump_stack().

The checksumming bug was fixed in commit 34ae6a1aa054 ("ipv6: update skb->csum when CE mark is propagated").

The second problem is a faulty locking in dump_stack()

CPU1 runs in process context and calls dump_stack(), grabs dump_lock.

CPU2 receives a TCP packet under softirq, grabs socket spinlock, and call dump_stack() from netdev_rx_csum_fault().

dump_stack() spins on atomic_cmpxchg(&dump_lock, -1, 2), since dump_lock is owned by CPU1

While dumping its stack, CPU1 is interrupted by a softirq, and happens to process a packet for the TCP socket locked by CPU2.

CPU1 spins forever in spin_lock() : deadlock

Stack trace on CPU1 looked like :

    NMI backtrace for cpu 1
    RIP: _raw_spin_lock+0x25/0x30
    ...
    Call Trace:
      <IRQ>
      tcp_v6_rcv+0x243/0x620
      ip6_input_finish+0x11f/0x330
      ip6_input+0x38/0x40
      ip6_rcv_finish+0x3c/0x90
      ipv6_rcv+0x2a9/0x500
      process_backlog+0x461/0xaa0
      net_rx_action+0x147/0x430
      __do_softirq+0x167/0x2d0
      call_softirq+0x1c/0x30
      do_softirq+0x3f/0x80
      irq_exit+0x6e/0xc0
      smp_call_function_single_interrupt+0x35/0x40
      call_function_single_interrupt+0x6a/0x70
      <EOI>
      printk+0x4d/0x4f
      printk_address+0x31/0x33
      print_trace_address+0x33/0x3c
      print_context_stack+0x7f/0x119
      dump_trace+0x26b/0x28e
      show_trace_log_lvl+0x4f/0x5c
      show_stack_log_lvl+0x104/0x113
      show_stack+0x42/0x44
      dump_stack+0x46/0x58
      netdev_rx_csum_fault+0x38/0x3c
      __skb_checksum_complete_head+0x6e/0x80
      __skb_checksum_complete+0x11/0x20
      tcp_rcv_established+0x2bd5/0x2fd0
      tcp_v6_do_rcv+0x13c/0x620
      sk_backlog_rcv+0x15/0x30
      release_sock+0xd2/0x150
      tcp_recvmsg+0x1c1/0xfc0
      inet_recvmsg+0x7d/0x90
      sock_recvmsg+0xaf/0xe0
      ___sys_recvmsg+0x111/0x3b0
      SyS_recvmsg+0x5c/0xb0
      system_call_fastpath+0x16/0x1b

---
 lib/dump_stack.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(
 
 asmlinkage void dump_stack(void)
 {
+	unsigned long flags;
 	int was_locked;
 	int old;
 	int cpu;

@@ -33,9 +34,8 @@ asmlinkage void dump_stack(void)
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-	preempt_disable();
-
 retry:
+	local_irq_save(flags);
 	cpu = smp_processor_id();
 	old = atomic_cmpxchg(&dump_lock, -1, cpu);
 	if (old == -1) {

@@ -43,6 +43,7 @@ retry:
 	} else if (old == cpu) {
 		was_locked = 1;
 	} else {
+		local_irq_restore(flags);
 		cpu_relax();
 		goto retry;
 	}

@@ -52,7 +53,7 @@ retry:
 	if (!was_locked)
 		atomic_set(&dump_lock, -1);
 
-	preempt_enable();
+	local_irq_restore(flags);
 }
 #else
 asmlinkage void dump_stack(void)

3.14-stable review patch. If anyone has any objections, please let me know.

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

From: Dan Carpenter <[email protected]>

commit b1d353ad3d5835b16724653b33c05124e1b5acf1 upstream.

"count" is controlled by the user and it can be negative. Let's prevent that by making it unsigned. You have to have CAP_SYS_RAWIO to call this function so the bug is not as serious as it could be.