[001/151] USB: usb-storage: fix bug in fill_inquiry

[001/151] USB: usb-storage: fix bug in fill_inquiry

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alan Stern <stern@rowland.harvard.edu>

commit f3f6faa9edf67c1018270793e0547b0f81abb47e upstream.

This patch (as1312) fixes a minor bug in usb-storage.  The
fill_inquiry() routine neglects to pre-load the inquiry data buffer
with spaces.  As a result, if the vendor name is shorter than 8
characters or the product name is shorter than 16, the remainder will
be filled with garbage.

The patch also removes some unnecessary calls to strlen().

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/storage/usb.c |   15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -228,6 +228,7 @@ void fill_inquiry_response(struct us_dat
 	if (data_len<36) // You lose.
 		return;
 
+	memset(data+8, ' ', 28);
 	if(data[0]&0x20) { /* USB device currently not connected. Return
 			      peripheral qualifier 001b ("...however, the
 			      physical device is not currently connected
@@ -237,15 +238,15 @@ void fill_inquiry_response(struct us_dat
 			      device, it may return zeros or ASCII spaces 
 			      (20h) in those fields until the data is
 			      available from the device."). */
-		memset(data+8,0,28);
 	} else {
 		u16 bcdDevice = le16_to_cpu(us->pusb_dev->descriptor.bcdDevice);
-		memcpy(data+8, us->unusual_dev->vendorName, 
-			strlen(us->unusual_dev->vendorName) > 8 ? 8 :
-			strlen(us->unusual_dev->vendorName));
-		memcpy(data+16, us->unusual_dev->productName, 
-			strlen(us->unusual_dev->productName) > 16 ? 16 :
-			strlen(us->unusual_dev->productName));
+		int n;
+
+		n = strlen(us->unusual_dev->vendorName);
+		memcpy(data+8, us->unusual_dev->vendorName, min(8, n));
+		n = strlen(us->unusual_dev->productName);
+		memcpy(data+16, us->unusual_dev->productName, min(16, n));
+
 		data[32] = 0x30 + ((bcdDevice>>12) & 0x0F);
 		data[33] = 0x30 + ((bcdDevice>>8) & 0x0F);
 		data[34] = 0x30 + ((bcdDevice>>4) & 0x0F);

[002/151] USB: option: add pid for ZTE

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: zhao.ming9@zte.com.cn <zhao.ming9@zte.com.cn>

commit 8d87cacda7c8db5c131bfcaaa1d90bfe918c2ebc upstream.

This patch adds ZTE modem devices.

Signed-off-by: Ming Zhao <zhao.ming9@zte.com.cn>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/serial/option.c |   36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -580,12 +580,48 @@ static struct usb_device_id option_ids[]
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0086, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0104, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0106, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0108, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0113, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0117, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0118, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0121, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0122, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0123, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0124, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0125, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0126, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0128, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0142, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0143, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0144, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0145, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0146, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0147, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0148, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0149, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0150, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0151, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0152, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0153, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0154, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0155, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0156, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0157, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0158, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0159, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0160, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0161, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0162, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0014, 0xff, 0xff, 0xff) }, /* ZTE CDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0027, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0059, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0060, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0070, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0073, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0130, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0141, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },

[003/151] firewire: ohci: handle receive packets with a data length of zero

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jay Fenlason <fenlason@redhat.com>

commit 8c0c0cc2d9f4c523fde04bdfe41e4380dec8ee54 upstream.

Queueing to receive an ISO packet with a payload length of zero
silently does nothing in dualbuffer mode, and crashes the kernel in
packet-per-buffer mode.  Return an error in dualbuffer mode, because
the DMA controller won't let us do what we want, and work correctly in
packet-per-buffer mode.

Signed-off-by: Jay Fenlason <fenlason@redhat.com>
Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/firewire/ohci.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2209,6 +2209,13 @@ static int ohci_queue_iso_receive_dualbu
 	page     = payload >> PAGE_SHIFT;
 	offset   = payload & ~PAGE_MASK;
 	rest     = p->payload_length;
+	/*
+	 * The controllers I've tested have not worked correctly when
+	 * second_req_count is zero.  Rather than do something we know won't
+	 * work, return an error
+	 */
+	if (rest == 0)
+		return -EINVAL;
 
 	/* FIXME: make packet-per-buffer/dual-buffer a context option */
 	while (rest > 0) {
@@ -2262,7 +2269,7 @@ static int ohci_queue_iso_receive_packet
 					unsigned long payload)
 {
 	struct iso_context *ctx = container_of(base, struct iso_context, base);
-	struct descriptor *d = NULL, *pd = NULL;
+	struct descriptor *d, *pd;
 	struct fw_iso_packet *p = packet;
 	dma_addr_t d_bus, page_bus;
 	u32 z, header_z, rest;
@@ -2300,8 +2307,9 @@ static int ohci_queue_iso_receive_packet
 		d->data_address = cpu_to_le32(d_bus + (z * sizeof(*d)));
 
 		rest = payload_per_buffer;
+		pd = d;
 		for (j = 1; j < z; j++) {
-			pd = d + j;
+			pd++;
 			pd->control = cpu_to_le16(DESCRIPTOR_STATUS |
 						  DESCRIPTOR_INPUT_MORE);
 

[004/151] rcu: Prepare for synchronization fixes: clean up for non-NO_HZ handling of ->completed counter

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

commit 281d150c5f8892f158747594ab49ce2823fd8b8c upstream.

Impose a clear locking design on non-NO_HZ handling of the
->completed counter.  This increases the distance between the
RCU and the CPU-hotplug mechanisms.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12571987491353-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/rcutree.c |   67 ++++++++++++++++++++++++-------------------------------
 kernel/rcutree.h |    8 +++---
 2 files changed, 34 insertions(+), 41 deletions(-)

--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -176,9 +176,29 @@ static struct rcu_node *rcu_get_root(str
 	return &rsp->node[0];
 }
 
+/*
+ * Record the specified "completed" value, which is later used to validate
+ * dynticks counter manipulations and CPU-offline checks.  Specify
+ * "rsp->completed - 1" to unconditionally invalidate any future dynticks
+ * manipulations and CPU-offline checks.  Such invalidation is useful at
+ * the beginning of a grace period.
+ */
+static void dyntick_record_completed(struct rcu_state *rsp, long comp)
+{
+	rsp->dynticks_completed = comp;
+}
+
 #ifdef CONFIG_SMP
 
 /*
+ * Recall the previously recorded value of the completion for dynticks.
+ */
+static long dyntick_recall_completed(struct rcu_state *rsp)
+{
+	return rsp->dynticks_completed;
+}
+
+/*
  * If the specified CPU is offline, tell the caller that it is in
  * a quiescent state.  Otherwise, whack it with a reschedule IPI.
  * Grace periods can end up waiting on an offline CPU when that
@@ -335,28 +355,9 @@ void rcu_irq_exit(void)
 		set_need_resched();
 }
 
-/*
- * Record the specified "completed" value, which is later used to validate
- * dynticks counter manipulations.  Specify "rsp->completed - 1" to
- * unconditionally invalidate any future dynticks manipulations (which is
- * useful at the beginning of a grace period).
- */
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-	rsp->dynticks_completed = comp;
-}
-
 #ifdef CONFIG_SMP
 
 /*
- * Recall the previously recorded value of the completion for dynticks.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
-	return rsp->dynticks_completed;
-}
-
-/*
  * Snapshot the specified CPU's dynticks counter so that we can later
  * credit them with an implicit quiescent state.  Return 1 if this CPU
  * is in dynticks idle mode, which is an extended quiescent state.
@@ -419,24 +420,8 @@ static int rcu_implicit_dynticks_qs(stru
 
 #else /* #ifdef CONFIG_NO_HZ */
 
-static void dyntick_record_completed(struct rcu_state *rsp, long comp)
-{
-}
-
 #ifdef CONFIG_SMP
 
-/*
- * If there are no dynticks, then the only way that a CPU can passively
- * be in a quiescent state is to be offline.  Unlike dynticks idle, which
- * is a point in time during the prior (already finished) grace period,
- * an offline CPU is always in a quiescent state, and thus can be
- * unconditionally applied.  So just return the current value of completed.
- */
-static long dyntick_recall_completed(struct rcu_state *rsp)
-{
-	return rsp->completed;
-}
-
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	return 0;
@@ -1144,6 +1129,7 @@ static void force_quiescent_state(struct
 	long lastcomp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	u8 signaled;
+	u8 forcenow;
 
 	if (!rcu_gp_in_progress(rsp))
 		return;  /* No grace period in progress, nothing to force. */
@@ -1180,16 +1166,23 @@ static void force_quiescent_state(struct
 		if (rcu_process_dyntick(rsp, lastcomp,
 					dyntick_save_progress_counter))
 			goto unlock_ret;
+		/* fall into next case. */
+
+	case RCU_SAVE_COMPLETED:
 
 		/* Update state, record completion counter. */
+		forcenow = 0;
 		spin_lock(&rnp->lock);
 		if (lastcomp == rsp->completed &&
-		    rsp->signaled == RCU_SAVE_DYNTICK) {
+		    rsp->signaled == signaled) {
 			rsp->signaled = RCU_FORCE_QS;
 			dyntick_record_completed(rsp, lastcomp);
+			forcenow = signaled == RCU_SAVE_COMPLETED;
 		}
 		spin_unlock(&rnp->lock);
-		break;
+		if (!forcenow)
+			break;
+		/* fall into next case. */
 
 	case RCU_FORCE_QS:
 
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -204,11 +204,12 @@ struct rcu_data {
 #define RCU_GP_IDLE		0	/* No grace period in progress. */
 #define RCU_GP_INIT		1	/* Grace period being initialized. */
 #define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
-#define RCU_FORCE_QS		3	/* Need to force quiescent state. */
+#define RCU_SAVE_COMPLETED	3	/* Need to save rsp->completed. */
+#define RCU_FORCE_QS		4	/* Need to force quiescent state. */
 #ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 #else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT		RCU_FORCE_QS
+#define RCU_SIGNAL_INIT		RCU_SAVE_COMPLETED
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
@@ -274,9 +275,8 @@ struct rcu_state {
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
-#ifdef CONFIG_NO_HZ
 	long dynticks_completed;		/* Value of completed @ snap. */
-#endif /* #ifdef CONFIG_NO_HZ */
+						/*  Protected by fqslock. */
 };
 
 #ifdef RCU_TREE_NONCORE

[005/151] rcu: Fix synchronization for rcu_process_gp_end() uses of ->completed counter

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

commit d09b62dfa336447c52a5ec9bb88adbc479b0f3b8 upstream.

Impose a clear locking design on the rcu_process_gp_end()
function's use of the ->completed counter.  This is done by
creating a ->completed field in the rcu_node structure, which
can safely be accessed under the protection of that structure's
lock.  Performance and scalability are maintained by using a
form of double-checked locking, so that rcu_process_gp_end()
only acquires the leaf rcu_node structure's ->lock if a grace
period has recently ended.

This fix reduces rcutorture failure rate by at least two orders
of magnitude under heavy stress with force_quiescent_state()
being invoked artificially often.  Without this fix,
unsynchronized access to the ->completed field can cause
rcu_process_gp_end() to advance callbacks whose grace period has
not yet expired.  (Bad idea!)

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12571987494069-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/rcutree.c |  128 ++++++++++++++++++++++++++++++++++---------------------
 kernel/rcutree.h |    3 +
 2 files changed, 83 insertions(+), 48 deletions(-)

--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -568,6 +568,76 @@ check_for_new_grace_period(struct rcu_st
 }
 
 /*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.  In addition, the corresponding leaf rcu_node structure's
+ * ->lock must be held by the caller, with irqs disabled.
+ */
+static void
+__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	/* Did another grace period end? */
+	if (rdp->completed != rnp->completed) {
+
+		/* Advance callbacks.  No harm if list empty. */
+		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+		/* Remember that we saw this grace-period completion. */
+		rdp->completed = rnp->completed;
+	}
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	local_irq_save(flags);
+	rnp = rdp->mynode;
+	if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
+	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+		local_irq_restore(flags);
+		return;
+	}
+	__rcu_process_gp_end(rsp, rnp, rdp);
+	spin_unlock_irqrestore(&rnp->lock, flags);
+}
+
+/*
+ * Do per-CPU grace-period initialization for running CPU.  The caller
+ * must hold the lock of the leaf rcu_node structure corresponding to
+ * this CPU.
+ */
+static void
+rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	/* Prior grace period ended, so advance callbacks for current CPU. */
+	__rcu_process_gp_end(rsp, rnp, rdp);
+
+	/*
+	 * Because this CPU just now started the new grace period, we know
+	 * that all of its callbacks will be covered by this upcoming grace
+	 * period, even the ones that were registered arbitrarily recently.
+	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
+	 *
+	 * Other CPUs cannot be sure exactly when the grace period started.
+	 * Therefore, their recently registered callbacks must pass through
+	 * an additional RCU_NEXT_READY stage, so that they will be handled
+	 * by the next RCU grace period.
+	 */
+	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+}
+
+/*
  * Start a new RCU grace period if warranted, re-initializing the hierarchy
  * in preparation for detecting the next grace period.  The caller must hold
  * the root node's ->lock, which is released before return.  Hard irqs must
@@ -594,26 +664,14 @@ rcu_start_gp(struct rcu_state *rsp, unsi
 	dyntick_record_completed(rsp, rsp->completed - 1);
 	note_new_gpnum(rsp, rdp);
 
-	/*
-	 * Because this CPU just now started the new grace period, we know
-	 * that all of its callbacks will be covered by this upcoming grace
-	 * period, even the ones that were registered arbitrarily recently.
-	 * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL.
-	 *
-	 * Other CPUs cannot be sure exactly when the grace period started.
-	 * Therefore, their recently registered callbacks must pass through
-	 * an additional RCU_NEXT_READY stage, so that they will be handled
-	 * by the next RCU grace period.
-	 */
-	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
 	/* Special-case the common single-level case. */
 	if (NUM_RCU_NODES == 1) {
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
+		rnp->completed = rsp->completed;
 		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+		rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
@@ -646,6 +704,9 @@ rcu_start_gp(struct rcu_state *rsp, unsi
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
+		rnp->completed = rsp->completed;
+		if (rnp == rdp->mynode)
+			rcu_start_gp_per_cpu(rsp, rnp, rdp);
 		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
@@ -657,34 +718,6 @@ rcu_start_gp(struct rcu_state *rsp, unsi
 }
 
 /*
- * Advance this CPU's callbacks, but only if the current grace period
- * has ended.  This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static void
-rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
-{
-	long completed_snap;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	completed_snap = ACCESS_ONCE(rsp->completed);  /* outside of lock. */
-
-	/* Did another grace period end? */
-	if (rdp->completed != completed_snap) {
-
-		/* Advance callbacks.  No harm if list empty. */
-		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
-		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
-		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
-
-		/* Remember that we saw this grace-period completion. */
-		rdp->completed = completed_snap;
-	}
-	local_irq_restore(flags);
-}
-
-/*
  * Clean up after the prior grace period and let rcu_start_gp() start up
  * the next grace period if one is needed.  Note that the caller must
  * hold rnp->lock, as required by rcu_start_gp(), which will release it.
@@ -695,7 +728,6 @@ static void cpu_quiet_msk_finish(struct 
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	rsp->completed = rsp->gpnum;
 	rsp->signaled = RCU_GP_IDLE;
-	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
 }
 
@@ -1537,21 +1569,16 @@ static void __cpuinit
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 {
 	unsigned long flags;
-	long lastcomp;
 	unsigned long mask;
 	struct rcu_data *rdp = rsp->rda[cpu];
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
 	spin_lock_irqsave(&rnp->lock, flags);
-	lastcomp = rsp->completed;
-	rdp->completed = lastcomp;
-	rdp->gpnum = lastcomp;
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->preemptable = preemptable;
-	rdp->passed_quiesc_completed = lastcomp - 1;
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -1573,6 +1600,11 @@ rcu_init_percpu_data(int cpu, struct rcu
 		spin_lock(&rnp->lock);	/* irqs already disabled. */
 		rnp->qsmaskinit |= mask;
 		mask = rnp->grpmask;
+		if (rnp == rdp->mynode) {
+			rdp->gpnum = rnp->completed; /* if GP in progress... */
+			rdp->completed = rnp->completed;
+			rdp->passed_quiesc_completed = rnp->completed - 1;
+		}
 		spin_unlock(&rnp->lock); /* irqs already disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,6 +84,9 @@ struct rcu_node {
 	long	gpnum;		/* Current grace period for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
+	long	completed;	/* Last grace period completed for this node. */
+				/*  This will either be equal to or one */
+				/*  behind the root rcu_node's gpnum. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */

[006/151] rcu: Fix note_new_gpnum() uses of ->gpnum

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

commit 9160306e6f5b68bb64630c9031c517ca1cf463db upstream.

Impose a clear locking design on the note_new_gpnum()
function's use of the ->gpnum counter.  This is done by updating
rdp->gpnum only from the corresponding leaf rcu_node structure's
rnp->gpnum field, and even then only under the protection of
that same rcu_node structure's ->lock field.  Performance and
scalability are maintained using a form of double-checked
locking, and excessive spinning is avoided by use of the
spin_trylock() function.  The use of spin_trylock() is safe due
to the fact that CPUs who fail to acquire this lock will try
again later. The hierarchical nature of the rcu_node data
structure limits contention (which could be limited further if
need be using the RCU_FANOUT kernel parameter).

Without this patch, obscure but quite possible races could
result in a quiescent state that occurred during one grace
period to be accounted to the following grace period, causing
this following grace period to end prematurely.  Not good!

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
LKML-Reference: <12571987492350-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/rcutree.c |   34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -538,13 +538,33 @@ static void check_cpu_stall(struct rcu_s
 /*
  * Update CPU-local rcu_data state to record the newly noticed grace period.
  * This is used both when we started the grace period and when we notice
- * that someone else started the grace period.
- */
+ * that someone else started the grace period.  The caller must hold the
+ * ->lock of the leaf rcu_node structure corresponding to the current CPU,
+ *  and must have irqs disabled.
+ */
+static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	if (rdp->gpnum != rnp->gpnum) {
+		rdp->qs_pending = 1;
+		rdp->passed_quiesc = 0;
+		rdp->gpnum = rnp->gpnum;
+	}
+}
+
 static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	rdp->qs_pending = 1;
-	rdp->passed_quiesc = 0;
-	rdp->gpnum = rsp->gpnum;
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	local_irq_save(flags);
+	rnp = rdp->mynode;
+	if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
+	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+		local_irq_restore(flags);
+		return;
+	}
+	__note_new_gpnum(rsp, rnp, rdp);
+	spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -635,6 +655,9 @@ rcu_start_gp_per_cpu(struct rcu_state *r
 	 */
 	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
 	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+	/* Set state so that this CPU will detect the next quiescent state. */
+	__note_new_gpnum(rsp, rnp, rdp);
 }
 
 /*
@@ -662,7 +685,6 @@ rcu_start_gp(struct rcu_state *rsp, unsi
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);
 	dyntick_record_completed(rsp, rsp->completed - 1);
-	note_new_gpnum(rsp, rdp);
 
 	/* Special-case the common single-level case. */
 	if (NUM_RCU_NODES == 1) {

[007/151] rcu: Remove inline from forward-referenced functions

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

commit dbe01350fa8ce0c11948ab7d6be71a4d901be151 upstream.

Some variants of gcc are reputed to dislike forward references
to functions declared "inline".  Remove the "inline" keyword
from such functions.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: dipankar@in.ibm.com
Cc: mathieu.desnoyers@polymtl.ca
Cc: josh@joshtriplett.org
Cc: dvhltc@us.ibm.com
Cc: niv@us.ibm.com
Cc: peterz@infradead.org
Cc: rostedt@goodmis.org
Cc: Valdis.Kletnieks@vt.edu
Cc: dhowells@redhat.com
Cc: Benjamin Gilbert <bgilbert@cs.cmu.edu>
LKML-Reference: <12578890422402-git-send-email->
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/rcutree.h        |    2 +-
 kernel/rcutree_plugin.h |    4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -301,7 +301,7 @@ DECLARE_PER_CPU(struct rcu_data, rcu_pre
 #else /* #ifdef RCU_TREE_NONCORE */
 
 /* Forward declarations for rcutree_plugin.h */
-static inline void rcu_bootup_announce(void);
+static void rcu_bootup_announce(void);
 long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(int cpu);
 static int rcu_preempted_readers(struct rcu_node *rnp);
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_pree
 /*
  * Tell them what RCU they are running.
  */
-static inline void rcu_bootup_announce(void)
+static void rcu_bootup_announce(void)
 {
 	printk(KERN_INFO
 	       "Experimental preemptable hierarchical RCU implementation.\n");
@@ -481,7 +481,7 @@ void exit_rcu(void)
 /*
  * Tell them what RCU they are running.
  */
-static inline void rcu_bootup_announce(void)
+static void rcu_bootup_announce(void)
 {
 	printk(KERN_INFO "Hierarchical RCU implementation.\n");
 }

[008/151] perf_event: Fix invalid type in ioctl definition

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Arjan van de Ven <arjan@infradead.org>

commit 4c49b12853fbb5eff4849b7b6a1e895776f027a1 upstream.

u64 is invalid in userspace headers, including ioctl
definitions; use __u64 instead

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
LKML-Reference: <20091113214733.7cd76be9@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

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

--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -219,7 +219,7 @@ struct perf_event_attr {
 #define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
 #define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
 #define PERF_EVENT_IOC_RESET		_IO ('$', 3)
-#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, u64)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
 #define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
 
 enum perf_event_ioc_flags {

[009/151] perf_event: Initialize data.period in perf_swevent_hrtimer()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

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

commit 59d069eb5ae9b033ed1c124c92e1532c4a958991 upstream.

In current code in perf_swevent_hrtimer(), data.period is not
initialized, The result is obvious wrong:

 # ./perf record -f -e cpu-clock make
 # ./perf report
 # Samples: 1740
 #
 # Overhead   Command                                   ......
 # ........  ........  ..........................................
 #
   1025422183050275328.00%        sh  libc-2.9.90.so ...
   1025422183050275328.00%      perl  libperl.so     ...
   1025422168240043264.00%      perl  [kernel]       ...
   1025422030011210752.00%      perl  [kernel]       ...

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14E220.2050107@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

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

--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3949,6 +3949,7 @@ static enum hrtimer_restart perf_swevent
 	event->pmu->read(event);
 
 	data.addr = 0;
+	data.period = event->hw.last_period;
 	regs = get_irq_regs();
 	/*
 	 * In case we exclude kernel IPs or are somehow not in interrupt

[010/151] perf: Dont free perf_mmap_data until work has been done

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 1626 bytes --]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Kristian Høgsberg <krh@bitplanet.net>

commit ec70ccd806111ba3caf596def91a8580138b12db upstream.

In the CONFIG_PERF_USE_VMALLOC case, perf_mmap_data_free() only
schedules the cleanup of the perf_mmap_data struct.  In that
case we have to wait until the work has been done before we free
data.

Signed-off-by: Kristian Høgsberg <krh@bitplanet.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1259697901-1747-1-git-send-email-krh@bitplanet.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/perf_event.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2174,6 +2174,7 @@ static void perf_mmap_data_free(struct p
 	perf_mmap_free_page((unsigned long)data->user_page);
 	for (i = 0; i < data->nr_pages; i++)
 		perf_mmap_free_page((unsigned long)data->data_pages[i]);
+	kfree(data);
 }
 
 #else
@@ -2214,6 +2215,7 @@ static void perf_mmap_data_free_work(str
 		perf_mmap_unmark_page(base + (i * PAGE_SIZE));
 
 	vfree(base);
+	kfree(data);
 }
 
 static void perf_mmap_data_free(struct perf_mmap_data *data)
@@ -2319,7 +2321,6 @@ static void perf_mmap_data_free_rcu(stru
 
 	data = container_of(rcu_head, struct perf_mmap_data, rcu_head);
 	perf_mmap_data_free(data);
-	kfree(data);
 }
 
 static void perf_mmap_data_release(struct perf_event *event)

[011/151] PM / Runtime: Fix lockdep warning in __pm_runtime_set_status()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Rafael J. Wysocki <rjw@sisk.pl>

commit bab636b921017f0db6e0c2979438f50b898a9808 upstream.

Lockdep complains about taking the parent lock in
__pm_runtime_set_status(), so mark it as nested.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Reported-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/base/power/runtime.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -777,7 +777,7 @@ int __pm_runtime_set_status(struct devic
 	}
 
 	if (parent) {
-		spin_lock(&parent->power.lock);
+		spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING);
 
 		/*
 		 * It is invalid to put an active child under a parent that is

[012/151] sched: Check for an idle shared cache in select_task_rq_fair()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mike Galbraith <efault@gmx.de>

commit a1f84a3ab8e002159498814eaa7e48c33752b04b upstream.

When waking affine, check for an idle shared cache, and if
found, wake to that CPU/sibling instead of the waker's CPU.

This improves pgsql+oltp ramp up by roughly 8%. Possibly more
for other loads, depending on overlap. The trade-off is a
roughly 1% peak downturn if tasks are truly synchronous.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1256654138.17752.7.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/sched_fair.c |   33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1398,11 +1398,36 @@ static int select_task_rq_fair(struct ta
 				want_sd = 0;
 		}
 
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+		if (want_affine && (tmp->flags & SD_WAKE_AFFINE)) {
+			int candidate = -1, i;
 
-			affine_sd = tmp;
-			want_affine = 0;
+			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+				candidate = cpu;
+
+			/*
+			 * Check for an idle shared cache.
+			 */
+			if (tmp->flags & SD_PREFER_SIBLING) {
+				if (candidate == cpu) {
+					if (!cpu_rq(prev_cpu)->cfs.nr_running)
+						candidate = prev_cpu;
+				}
+
+				if (candidate == -1 || candidate == cpu) {
+					for_each_cpu(i, sched_domain_span(tmp)) {
+						if (!cpu_rq(i)->cfs.nr_running) {
+							candidate = i;
+							break;
+						}
+					}
+				}
+			}
+
+			if (candidate >= 0) {
+				affine_sd = tmp;
+				want_affine = 0;
+				cpu = candidate;
+			}
 		}
 
 		if (!want_sd && !want_affine)

[013/151] sched: Fix affinity logic in select_task_rq_fair()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mike Galbraith <efault@gmx.de>

commit fd210738f6601d0fb462df9a2fe5a41896ff6a8f upstream.

Ingo Molnar reported:

[   26.804000] BUG: using smp_processor_id() in preemptible [00000000] code: events/1/10
[   26.808000] caller is vmstat_update+0x26/0x70
[   26.812000] Pid: 10, comm: events/1 Not tainted 2.6.32-rc5 #6887
[   26.816000] Call Trace:
[   26.820000]  [<c1924a24>] ? printk+0x28/0x3c
[   26.824000]  [<c13258a0>] debug_smp_processor_id+0xf0/0x110
[   26.824000] mount used greatest stack depth: 1464 bytes left
[   26.828000]  [<c111d086>] vmstat_update+0x26/0x70
[   26.832000]  [<c1086418>] worker_thread+0x188/0x310
[   26.836000]  [<c10863b7>] ? worker_thread+0x127/0x310
[   26.840000]  [<c108d310>] ? autoremove_wake_function+0x0/0x60
[   26.844000]  [<c1086290>] ? worker_thread+0x0/0x310
[   26.848000]  [<c108cf0c>] kthread+0x7c/0x90
[   26.852000]  [<c108ce90>] ? kthread+0x0/0x90
[   26.856000]  [<c100c0a7>] kernel_thread_helper+0x7/0x10
[   26.860000] BUG: using smp_processor_id() in preemptible [00000000] code: events/1/10
[   26.864000] caller is vmstat_update+0x3c/0x70

Because this commit:

  a1f84a3: sched: Check for an idle shared cache in select_task_rq_fair()

broke ->cpus_allowed.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: arjan@infradead.org
LKML-Reference: <1257415066.12867.1.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/sched_fair.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1415,6 +1415,8 @@ static int select_task_rq_fair(struct ta
 
 				if (candidate == -1 || candidate == cpu) {
 					for_each_cpu(i, sched_domain_span(tmp)) {
+						if (!cpumask_test_cpu(i, &p->cpus_allowed))
+							continue;
 						if (!cpu_rq(i)->cfs.nr_running) {
 							candidate = i;
 							break;

[014/151] sched: Rate-limit newidle

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mike Galbraith <efault@gmx.de>

commit 1b9508f6831e10d53256825de8904caa22d1ca2c upstream.

Rate limit newidle to migration_cost. It's a win for all
stages of sysbench oltp tests.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/sched.c       |   22 +++++++++++++++++++++-
 kernel/sched_debug.c |    4 ++++
 2 files changed, 25 insertions(+), 1 deletion(-)

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -591,6 +591,8 @@ struct rq {
 
 	u64 rt_avg;
 	u64 age_stamp;
+	u64 idle_stamp;
+	u64 avg_idle;
 #endif
 
 	/* calc_load related fields */
@@ -2384,6 +2386,17 @@ static int try_to_wake_up(struct task_st
 	if (rq != orig_rq)
 		update_rq_clock(rq);
 
+	if (rq->idle_stamp) {
+		u64 delta = rq->clock - rq->idle_stamp;
+		u64 max = 2*sysctl_sched_migration_cost;
+
+		if (delta > max)
+			rq->avg_idle = max;
+		else
+			update_avg(&rq->avg_idle, delta);
+		rq->idle_stamp = 0;
+	}
+
 	WARN_ON(p->state != TASK_WAKING);
 	cpu = task_cpu(p);
 
@@ -4429,6 +4442,11 @@ static void idle_balance(int this_cpu, s
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 
+	this_rq->idle_stamp = this_rq->clock;
+
+	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+		return;
+
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 
@@ -4443,8 +4461,10 @@ static void idle_balance(int this_cpu, s
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
 			next_balance = sd->last_balance + interval;
-		if (pulled_task)
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
 			break;
+		}
 	}
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m
 
 #ifdef CONFIG_SCHEDSTATS
 #define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
 
 	P(yld_count);
 
 	P(sched_switch);
 	P(sched_count);
 	P(sched_goidle);
+#ifdef CONFIG_SMP
+	P64(avg_idle);
+#endif
 
 	P(ttwu_count);
 	P(ttwu_local);

[015/151] sched: Fix and clean up rate-limit newidle code

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mike Galbraith <efault@gmx.de>

commit eae0c9dfb534cb3449888b9601228efa6480fdb5 upstream.

Commit 1b9508f, "Rate-limit newidle" has been confirmed to fix
the netperf UDP loopback regression reported by Alex Shi.

This is a cleanup and a fix:

 - moved to a more out of the way spot

 - fix to ensure that balancing doesn't try to balance
   runqueues which haven't gone online yet, which can
   mess up CPU enumeration during boot.

Reported-by: Alex Shi <alex.shi@intel.com>
Reported-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1257821402.5648.17.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/sched.c |   28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2386,17 +2386,6 @@ static int try_to_wake_up(struct task_st
 	if (rq != orig_rq)
 		update_rq_clock(rq);
 
-	if (rq->idle_stamp) {
-		u64 delta = rq->clock - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
-
-		if (delta > max)
-			rq->avg_idle = max;
-		else
-			update_avg(&rq->avg_idle, delta);
-		rq->idle_stamp = 0;
-	}
-
 	WARN_ON(p->state != TASK_WAKING);
 	cpu = task_cpu(p);
 
@@ -2453,6 +2442,17 @@ out_running:
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
 		p->sched_class->task_wake_up(rq, p);
+
+	if (unlikely(rq->idle_stamp)) {
+		u64 delta = rq->clock - rq->idle_stamp;
+		u64 max = 2*sysctl_sched_migration_cost;
+
+		if (delta > max)
+			rq->avg_idle = max;
+		else
+			update_avg(&rq->avg_idle, delta);
+		rq->idle_stamp = 0;
+	}
 #endif
 out:
 	task_rq_unlock(rq, &flags);
@@ -4139,7 +4139,7 @@ static int load_balance(int this_cpu, st
 	unsigned long flags;
 	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-	cpumask_setall(cpus);
+	cpumask_copy(cpus, cpu_online_mask);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -4302,7 +4302,7 @@ load_balance_newidle(int this_cpu, struc
 	int all_pinned = 0;
 	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
-	cpumask_setall(cpus);
+	cpumask_copy(cpus, cpu_online_mask);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -9542,6 +9542,8 @@ void __init sched_init(void)
 		rq->cpu = i;
 		rq->online = 0;
 		rq->migration_thread = NULL;
+		rq->idle_stamp = 0;
+		rq->avg_idle = 2*sysctl_sched_migration_cost;
 		INIT_LIST_HEAD(&rq->migration_queue);
 		rq_attach_root(rq, &def_root_domain);
 #endif

[016/151] x86/amd-iommu: attach devices to pre-allocated domains early

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Joerg Roedel <joerg.roedel@amd.com>

commit be831297716036de5b24308447ecb69f1706a846 upstream.

For some devices the ACPI table may define unity map
requirements which must me met when the IOMMU is enabled. So
we need to attach devices to their domains as early as
possible so that these mappings are in place when needed.
This patch assigns the domains right after they are
allocated. Otherwise this can result in I/O page faults
before a driver binds to a device and BIOS is still using
it.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/amd_iommu.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -2047,10 +2047,10 @@ static void prealloc_protection_domains(
 	struct pci_dev *dev = NULL;
 	struct dma_ops_domain *dma_dom;
 	struct amd_iommu *iommu;
-	u16 devid;
+	u16 devid, __devid;
 
 	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
-		devid = calc_devid(dev->bus->number, dev->devfn);
+		__devid = devid = calc_devid(dev->bus->number, dev->devfn);
 		if (devid > amd_iommu_last_bdf)
 			continue;
 		devid = amd_iommu_alias_table[devid];
@@ -2065,6 +2065,10 @@ static void prealloc_protection_domains(
 		init_unity_mappings_for_device(dma_dom, devid);
 		dma_dom->target_dev = devid;
 
+		attach_device(iommu, &dma_dom->domain, devid);
+		if (__devid != devid)
+			attach_device(iommu, &dma_dom->domain, __devid);
+
 		list_add_tail(&dma_dom->list, &iommu_pd_list);
 	}
 }

[017/151] x86/amd-iommu: un__init iommu_setup_msi

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Joerg Roedel <joerg.roedel@amd.com>

commit 9f800de38b05d84809e89f16671d636a140eede7 upstream.

This function may be called on the resume path and can not
be dropped after booting.

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/amd_iommu_init.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -925,7 +925,7 @@ static int __init init_iommu_all(struct 
  *
  ****************************************************************************/
 
-static int __init iommu_setup_msi(struct amd_iommu *iommu)
+static int iommu_setup_msi(struct amd_iommu *iommu)
 {
 	int r;
 

[018/151] x86, Calgary IOMMU quirk: Find nearest matching Calgary while walking up the PCI tree

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Darrick J. Wong <djwong@us.ibm.com>

commit 4528752f49c1f4025473d12bc5fa9181085c3f22 upstream.

On a multi-node x3950M2 system, there's a slight oddity in the
PCI device tree for all secondary nodes:

 30:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1)
  \-33:00.0 PCI bridge: IBM CalIOC2 PCI-E Root Port (rev 01)
     \-34:00.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID SAS 1078 (rev 04)

...as compared to the primary node:

 00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1)
  \-01:00.0 VGA compatible controller: ATI Technologies Inc ES1000 (rev 02)
 03:00.0 PCI bridge: IBM CalIOC2 PCI-E Root Port (rev 01)
  \-04:00.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID SAS 1078 (rev 04)

In both nodes, the LSI RAID controller hangs off a CalIOC2
device, but on the secondary nodes, the BIOS hides the VGA
device and substitutes the device tree ending with the disk
controller.

It would seem that Calgary devices don't necessarily appear at
the top of the PCI tree, which means that the current code to
find the Calgary IOMMU that goes with a particular device is
buggy.

Rather than walk all the way to the top of the PCI
device tree and try to match bus number with Calgary descriptor,
the code needs to examine each parent of the particular device;
if it encounters a Calgary with a matching bus number, simply
use that.

Otherwise, we BUG() when the bus number of the Calgary doesn't
match the bus number of whatever's at the top of the device tree.

Extra note: This patch appears to work correctly for the x3950
that came before the x3950 M2.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Acked-by: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Joerg Roedel <joerg.roedel@amd.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Jon D. Mason <jdmason@kudzu.us>
Cc: Corinna Schultz <coschult@us.ibm.com>
LKML-Reference: <20091202230556.GG10295@tux1.beaverton.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/pci-calgary_64.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -318,13 +318,15 @@ static inline struct iommu_table *find_i
 
 	pdev = to_pci_dev(dev);
 
+	/* search up the device tree for an iommu */
 	pbus = pdev->bus;
-
-	/* is the device behind a bridge? Look for the root bus */
-	while (pbus->parent)
+	do {
+		tbl = pci_iommu(pbus);
+		if (tbl && tbl->it_busno == pbus->number)
+			break;
+		tbl = NULL;
 		pbus = pbus->parent;
-
-	tbl = pci_iommu(pbus);
+	} while (pbus);
 
 	BUG_ON(tbl && (tbl->it_busno != pbus->number));
 

[019/151] x86: Fix iommu=nodac parameter handling

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Tejun Heo <tj@kernel.org>

commit 2ae8bb75db1f3de422eb5898f2a063c46c36dba8 upstream.

iommu=nodac should forbid dac instead of enabling it. Fix it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Matteo Frigo <athena@fftw.org>
LKML-Reference: <4AE5B52A.4050408@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/pci-dma.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -214,7 +214,7 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "allowdac", 8))
 			forbid_dac = 0;
 		if (!strncmp(p, "nodac", 5))
-			forbid_dac = -1;
+			forbid_dac = 1;
 		if (!strncmp(p, "usedac", 6)) {
 			forbid_dac = -1;
 			return 1;

[020/151] x86: GART: pci-gart_64.c: Use correct length in strncmp

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Joe Perches <joe@perches.com>

commit 41855b77547fa18d90ed6a5d322983d3fdab1959 upstream.

Signed-off-by: Joe Perches <joe@perches.com>
LKML-Reference: <1257818330.12852.72.camel@Joe-Laptop.home>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/pci-gart_64.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -856,7 +856,7 @@ void __init gart_parse_options(char *p)
 #endif
 	if (isdigit(*p) && get_option(&p, &arg))
 		iommu_size = arg;
-	if (!strncmp(p, "fullflush", 8))
+	if (!strncmp(p, "fullflush", 9))
 		iommu_fullflush = 1;
 	if (!strncmp(p, "nofullflush", 11))
 		iommu_fullflush = 0;

[021/151] x86: ASUS P4S800 reboot=bios quirk

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Leann Ogasawara <leann.ogasawara@canonical.com>

commit 4832ddda2ec4df96ea1eed334ae2dbd65fc1f541 upstream.

Bug reporter noted their system with an ASUS P4S800 motherboard would
hang when rebooting unless reboot=b was specified.  Their dmidecode
didn't contain descriptive System Information for Manufacturer or
Product Name, so I used their Base Board Information to create a
reboot quirk patch.  The bug reporter confirmed this patch resolves
the reboot hang.

Handle 0x0001, DMI type 1, 25 bytes
System Information
       Manufacturer: System Manufacturer
       Product Name: System Name
       Version: System Version
       Serial Number: SYS-1234567890
       UUID: E0BFCD8B-7948-D911-A953-E486B4EEB67F
       Wake-up Type: Power Switch

Handle 0x0002, DMI type 2, 8 bytes
Base Board Information
     Manufacturer: ASUSTeK Computer INC.
     Product Name: P4S800
     Version: REV 1.xx
     Serial Number: xxxxxxxxxxx

BugLink: http://bugs.launchpad.net/bugs/366682

ASUS P4S800 will hang when rebooting unless reboot=b is specified.
Add a quirk to reboot through the bios.

Signed-off-by: Leann Ogasawara <leann.ogasawara@canonical.com>
LKML-Reference: <1259972107.4629.275.camel@emiko>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/reboot.c |    8 ++++++++
 1 file changed, 8 insertions(+)

--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -259,6 +259,14 @@ static struct dmi_system_id __initdata r
 			DMI_MATCH(DMI_PRODUCT_NAME, "SBC-FITPC2"),
 		},
 	},
+	{       /* Handle problems with rebooting on ASUS P4S800 */
+		.callback = set_bios_reboot,
+		.ident = "ASUS P4S800",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
+		},
+	},
 	{ }
 };
 

[022/151] x86, apic: Enable lapic nmi watchdog on AMD Family 11h

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mikael Pettersson <mikpe@it.uu.se>

commit 7d1849aff6687a135a8da3a75e32a00e3137a5e2 upstream.

The x86 lapic nmi watchdog does not recognize AMD Family 11h,
resulting in:

  NMI watchdog: CPU not supported

As far as I can see from available documentation (the BKDM),
family 11h looks identical to family 10h as far as the PMU
is concerned.

Extending the check to accept family 11h results in:

  Testing NMI watchdog ... OK.

I've been running with this change on a Turion X2 Ultra ZM-82
laptop for a couple of weeks now without problems.

Signed-off-by: Mikael Pettersson <mikpe@it.uu.se>
Cc: Andreas Herrmann <andreas.herrmann3@amd.com>
Cc: Joerg Roedel <joerg.roedel@amd.com>
LKML-Reference: <19223.53436.931768.278021@pilspetsen.it.uu.se>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/cpu/perfctr-watchdog.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -712,7 +712,7 @@ static void probe_nmi_watchdog(void)
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
 		if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
-		    boot_cpu_data.x86 != 16)
+		    boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17)
 			return;
 		wd_ops = &k7_wd_ops;
 		break;

[023/151] ssb: Fix range check in sprom write

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Michael Buesch <mb@bu3sch.de>

commit e33761e6f23881de9f3ee77cc2204ab2e26f3d9a upstream.

The range check in the sprom image parser hex2sprom() is broken.
One sprom word is 4 hex characters.
This fixes the check and also adds much better sanity checks to the code.
We better make sure the image is OK by doing some sanity checks to avoid
bricking the device by accident.

Signed-off-by: Michael Buesch <mb@bu3sch.de>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/ssb/sprom.c |   20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

--- a/drivers/ssb/sprom.c
+++ b/drivers/ssb/sprom.c
@@ -13,6 +13,8 @@
 
 #include "ssb_private.h"
 
+#include <linux/ctype.h>
+
 
 static const struct ssb_sprom *fallback_sprom;
 
@@ -33,17 +35,27 @@ static int sprom2hex(const u16 *sprom, c
 static int hex2sprom(u16 *sprom, const char *dump, size_t len,
 		     size_t sprom_size_words)
 {
-	char tmp[5] = { 0 };
-	int cnt = 0;
+	char c, tmp[5] = { 0 };
+	int err, cnt = 0;
 	unsigned long parsed;
 
-	if (len < sprom_size_words * 2)
+	/* Strip whitespace at the end. */
+	while (len) {
+		c = dump[len - 1];
+		if (!isspace(c) && c != '\0')
+			break;
+		len--;
+	}
+	/* Length must match exactly. */
+	if (len != sprom_size_words * 4)
 		return -EINVAL;
 
 	while (cnt < sprom_size_words) {
 		memcpy(tmp, dump, 4);
 		dump += 4;
-		parsed = simple_strtoul(tmp, NULL, 16);
+		err = strict_strtoul(tmp, 16, &parsed);
+		if (err)
+			return err;
 		sprom[cnt++] = swab16((u16)parsed);
 	}
 

[024/151] ath5k: allow setting txpower to 0

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Bob Copeland <me@bobcopeland.com>

commit 2eb2fa67e5462a36e98172fb92c78bc405b3035f upstream.

As a holdover from earlier code when we used to set
the power limit to '0' after a reset to configure the
default transmit power, ath5k interprets txpower=0 as
12.5 dBm.  Fix that by just passing 0 through.

This fixes http://bugzilla.kernel.org/show_bug.cgi?id=14567

Reported-by: Daniel Folkers <daniel.folkers@task24.nl>
Tested-by: Daniel Folkers <daniel.folkers@task24.nl>
Signed-off-by: Bob Copeland <me@bobcopeland.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/ath/ath5k/phy.c |    2 --
 1 file changed, 2 deletions(-)

--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -2954,8 +2954,6 @@ ath5k_hw_txpower(struct ath5k_hw *ah, st
 		ATH5K_ERR(ah->ah_sc, "invalid tx power: %u\n", txpower);
 		return -EINVAL;
 	}
-	if (txpower == 0)
-		txpower = AR5K_TUNE_DEFAULT_TXPOWER;
 
 	/* Reset TX power values */
 	memset(&ah->ah_txpower, 0, sizeof(ah->ah_txpower));

[025/151] ath5k: enable EEPROM checksum check

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Luis R. Rodriguez <lrodriguez@atheros.com>

commit 512414b0bed0d376ac4d5ec1dd6f0b1a3551febc upstream.

Without this we have no gaurantee of the integrity of the
EEPROM and are likely to encounter a lot of bogus bug reports
due to actual issues on the EEPROM. With the EEPROM checksum
check in place we can easily rule those issues out.

If you run patch during a revert *you* have a card with a busted
EEPROM and only older kernel will support that concoction. This
patch is a trade off between not accepitng bogus EEPROMs and
avoiding bogus bug reports allowing developers to focus instead
on real concrete issues.

If stable keeps bogus bug reports because of a possibly busted EEPROM
feel free to apply this there too.

Tested on an AR5414

Cc: jirislaby@gmail.com
Cc: akpm@linux-foundation.org
Cc: rjw@sisk.pl
Cc: me@bobcopeland.com
Cc: david.quan@atheros.com
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/ath/ath5k/eeprom.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/wireless/ath/ath5k/eeprom.c
+++ b/drivers/net/wireless/ath/ath5k/eeprom.c
@@ -97,6 +97,7 @@ ath5k_eeprom_init_header(struct ath5k_hw
 	struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom;
 	int ret;
 	u16 val;
+	u32 cksum, offset;
 
 	/*
 	 * Read values from EEPROM and store them in the capability structure
@@ -111,7 +112,6 @@ ath5k_eeprom_init_header(struct ath5k_hw
 	if (ah->ah_ee_version < AR5K_EEPROM_VERSION_3_0)
 		return 0;
 
-#ifdef notyet
 	/*
 	 * Validate the checksum of the EEPROM date. There are some
 	 * devices with invalid EEPROMs.
@@ -124,7 +124,6 @@ ath5k_eeprom_init_header(struct ath5k_hw
 		ATH5K_ERR(ah->ah_sc, "Invalid EEPROM checksum 0x%04x\n", cksum);
 		return -EIO;
 	}
-#endif
 
 	AR5K_EEPROM_READ_HDR(AR5K_EEPROM_ANT_GAIN(ah->ah_ee_version),
 	    ee_ant_gain);

[026/151] hrtimer: Fix /proc/timer_list regression

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Feng Tang <feng.tang@intel.com>

commit 8629ea2eaba8ca0de2e38ce1b4a825e16255976e upstream.

commit 507e1231 (timer stats: Optimize by adding quick check to avoid
function calls) introduced a regression in /proc/timer_list.

/proc/timer_list shows now
 #0: <c27d46b0>, tick_sched_timer, S:01, <(null)>, /-1
instead of
 #0: <c27d46b0>, tick_sched_timer, S:01, hrtimer_start, swapper/0

Revert the hrtimer quick check for now. The optimization needs more
thought, but this is neither 2.6.32-rc7 nor stable material.

[ tglx: - Removed unrelated changes from the original patch
  	- Prevent unneccesary call to timer_stats_update_stats
	- massaged the changelog ]

Signed-off-by: Feng Tang <feng.tang@intel.com>
LKML-Reference: <alpine.LFD.2.00.0911181933540.24119@localhost.localdomain>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/linux/hrtimer.h |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -446,7 +446,7 @@ extern void timer_stats_update_stats(voi
 
 static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
 {
-	if (likely(!timer->start_site))
+	if (likely(!timer_stats_active))
 		return;
 	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
 				 timer->function, timer->start_comm, 0);
@@ -457,8 +457,6 @@ extern void __timer_stats_hrtimer_set_st
 
 static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
 {
-	if (likely(!timer_stats_active))
-		return;
 	__timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0));
 }
 

[027/151] ALSA: hrtimer - Fix lock-up

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Takashi Iwai <tiwai@suse.de>

commit fcfdebe70759c74e2e701f69aaa7f0e5e32cf5a6 upstream.

The timer stop callback can be called from snd_timer_interrupt(), which
is called from the hrtimer callback.  Since hrtimer_cancel() waits for
the callback completion, this eventually results in a lock-up.

This patch fixes the problem by just toggling a flag at stop callback
and call hrtimer_cancel() later.

Reported-and-tested-by: Wojtek Zabolotny <W.Zabolotny@elka.pw.edu.pl>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 sound/core/hrtimer.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

--- a/sound/core/hrtimer.c
+++ b/sound/core/hrtimer.c
@@ -37,14 +37,22 @@ static unsigned int resolution;
 struct snd_hrtimer {
 	struct snd_timer *timer;
 	struct hrtimer hrt;
+	atomic_t running;
 };
 
 static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt)
 {
 	struct snd_hrtimer *stime = container_of(hrt, struct snd_hrtimer, hrt);
 	struct snd_timer *t = stime->timer;
+
+	if (!atomic_read(&stime->running))
+		return HRTIMER_NORESTART;
+
 	hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution));
 	snd_timer_interrupt(stime->timer, t->sticks);
+
+	if (!atomic_read(&stime->running))
+		return HRTIMER_NORESTART;
 	return HRTIMER_RESTART;
 }
 
@@ -58,6 +66,7 @@ static int snd_hrtimer_open(struct snd_t
 	hrtimer_init(&stime->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	stime->timer = t;
 	stime->hrt.function = snd_hrtimer_callback;
+	atomic_set(&stime->running, 0);
 	t->private_data = stime;
 	return 0;
 }
@@ -78,16 +87,18 @@ static int snd_hrtimer_start(struct snd_
 {
 	struct snd_hrtimer *stime = t->private_data;
 
+	atomic_set(&stime->running, 0);
+	hrtimer_cancel(&stime->hrt);
 	hrtimer_start(&stime->hrt, ns_to_ktime(t->sticks * resolution),
 		      HRTIMER_MODE_REL);
+	atomic_set(&stime->running, 1);
 	return 0;
 }
 
 static int snd_hrtimer_stop(struct snd_timer *t)
 {
 	struct snd_hrtimer *stime = t->private_data;
-
-	hrtimer_cancel(&stime->hrt);
+	atomic_set(&stime->running, 0);
 	return 0;
 }
 

[028/151] ALSA: hda - Terradici HDA controllers does not support 64-bit mode

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jaroslav Kysela <perex@perex.cz>

commit 396087eaead95fcb29eb36f1e59517aeb58c545e upstream.

Confirmed from vendor and tests in RedHat bugzilla #536782 .

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

---
 sound/pci/hda/hda_intel.c |    5 +++++
 1 file changed, 5 insertions(+)

--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2436,6 +2436,11 @@ static int __devinit azx_create(struct s
 		}
 	}
 
+	/* disable 64bit DMA address for Teradici */
+	/* it does not work with device 6549:1200 subsys e4a2:040b */
+	if (chip->driver_type == AZX_DRIVER_TERA)
+		gcap &= ~ICH6_GCAP_64OK;
+
 	/* allow 64bit DMA address if supported by H/W */
 	if ((gcap & ICH6_GCAP_64OK) && !pci_set_dma_mask(pci, DMA_BIT_MASK(64)))
 		pci_set_consistent_dma_mask(pci, DMA_BIT_MASK(64));

[029/151] KVM: x86 emulator: limit instructions to 15 bytes

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Avi Kivity <avi@redhat.com>

commit eb3c79e64a70fb8f7473e30fa07e89c1ecc2c9bb upstream.

While we are never normally passed an instruction that exceeds 15 bytes,
smp games can cause us to attempt to interpret one, which will cause
large latencies in non-preempt hosts.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -129,7 +129,7 @@ struct decode_cache {
 	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
-	unsigned long eip;
+	unsigned long eip, eip_orig;
 	/* modrm */
 	u8 modrm;
 	u8 modrm_mod;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d226dff..7e8faea 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -622,6 +622,9 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 {
 	int rc = 0;
 
+	/* x86 instructions are limited to 15 bytes. */
+	if (eip + size - ctxt->decode.eip_orig > 15)
+		return X86EMUL_UNHANDLEABLE;
 	eip += ctxt->cs_base;
 	while (size--) {
 		rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++);
@@ -880,7 +883,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	/* Shadow copy of register state. Committed on successful emulation. */
 
 	memset(c, 0, sizeof(struct decode_cache));
-	c->eip = kvm_rip_read(ctxt->vcpu);
+	c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu);
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 

[030/151] KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Carsten Otte <carsteno@de.ibm.com>

commit f50146bd7bdb75435638e60d4960edd9bcdf88b8 upstream.

This patch corrects the checking of the new address for the prefix register.
On s390, the prefix register is used to address the cpu's lowcore (address
0...8k). This check is supposed to verify that the memory is readable and
present.
copy_from_guest is a helper function, that can be used to read from guest
memory. It applies prefixing, adds the start address of the guest memory in
user, and then calls copy_from_user. Previous code was obviously broken for
two reasons:
- prefixing should not be applied here. The current prefix register is
  going to be updated soon, and the address we're looking for will be
  0..8k after we've updated the register
- we're adding the guest origin (gmsor) twice: once in subject code
  and once in copy_from_guest

With kuli, we did not hit this problem because (a) we were lucky with
previous prefix register content, and (b) our guest memory was mmaped
very low into user address space.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Reported-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -188,9 +188,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
-	if ((copy_from_guest(vcpu, &tmp,
-		(u64) (address + vcpu->arch.sie_block->gmsor) , 1)) ||
-	   (copy_from_guest(vcpu, &tmp, (u64) (address +
+	if ((copy_from_user(&tmp, (void __user *)
+		(address + vcpu->arch.sie_block->gmsor) , 1)) ||
+	   (copy_from_user(&tmp, (void __user *)(address +
 			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */

[031/151] KVM: s390: Make psw available on all exits, not just a subset

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Carsten Otte <carsteno@de.ibm.com>

commit d7b0b5eb3000c6fb902f08c619fcd673a23d8fab upstream.

This patch moves s390 processor status word into the base kvm_run
struct and keeps it up-to date on all userspace exits.

The userspace ABI is broken by this, however there are no applications
in the wild using this.  A capability check is provided so users can
verify the updated API exists.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/s390/include/asm/kvm.h |    3 ++-
 arch/s390/kvm/kvm-s390.c    |   25 +++++++++++++++++--------
 include/linux/kvm.h         |    8 ++++++--
 3 files changed, 25 insertions(+), 11 deletions(-)

--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -1,6 +1,5 @@
 #ifndef __LINUX_KVM_S390_H
 #define __LINUX_KVM_S390_H
-
 /*
  * asm-s390/kvm.h - KVM s390 specific structures and definitions
  *
@@ -15,6 +14,8 @@
  */
 #include <linux/types.h>
 
+#define __KVM_S390
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -116,10 +116,16 @@ long kvm_arch_dev_ioctl(struct file *fil
 
 int kvm_dev_ioctl_check_extension(long ext)
 {
+	int r;
+
 	switch (ext) {
+	case KVM_CAP_S390_PSW:
+		r = 1;
+		break;
 	default:
-		return 0;
+		r = 0;
 	}
+	return r;
 }
 
 /* Section: vm related */
@@ -419,8 +425,10 @@ static int kvm_arch_vcpu_ioctl_set_initi
 	vcpu_load(vcpu);
 	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
 		rc = -EBUSY;
-	else
-		vcpu->arch.sie_block->gpsw = psw;
+	else {
+		vcpu->run->psw_mask = psw.mask;
+		vcpu->run->psw_addr = psw.addr;
+	}
 	vcpu_put(vcpu);
 	return rc;
 }
@@ -508,9 +516,6 @@ rerun_vcpu:
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:
-		vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask;
-		vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
-		break;
 	case KVM_EXIT_UNKNOWN:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
@@ -519,6 +524,9 @@ rerun_vcpu:
 		BUG();
 	}
 
+	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+
 	might_fault();
 
 	do {
@@ -538,8 +546,6 @@ rerun_vcpu:
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
 		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
-		kvm_run->s390_sieic.mask     = vcpu->arch.sie_block->gpsw.mask;
-		kvm_run->s390_sieic.addr     = vcpu->arch.sie_block->gpsw.addr;
 		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
 		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
 		rc = 0;
@@ -551,6 +557,9 @@ rerun_vcpu:
 		rc = 0;
 	}
 
+	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
+	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -116,6 +116,11 @@ struct kvm_run {
 	__u64 cr8;
 	__u64 apic_base;
 
+#ifdef __KVM_S390
+	/* the processor status word for s390 */
+	__u64 psw_mask; /* psw upper half */
+	__u64 psw_addr; /* psw lower half */
+#endif
 	union {
 		/* KVM_EXIT_UNKNOWN */
 		struct {
@@ -167,8 +172,6 @@ struct kvm_run {
 		/* KVM_EXIT_S390_SIEIC */
 		struct {
 			__u8 icptcode;
-			__u64 mask; /* psw upper half */
-			__u64 addr; /* psw lower half */
 			__u16 ipa;
 			__u32 ipb;
 		} s390_sieic;
@@ -474,6 +477,7 @@ struct kvm_irq_routing {
 };
 
 #endif
+#define KVM_CAP_S390_PSW 42
 
 #ifdef KVM_CAP_MCE
 /* x86 MCE */

[032/151] KVM: fix irq_source_id size verification

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Marcelo Tosatti <mtosatti@redhat.com>

commit cd5a2685de4a642fd0bd763e8c19711ef08dbe27 upstream.

find_first_zero_bit works with bit numbers, not bytes.

Fixes

https://sourceforge.net/tracker/?func=detail&aid=2847560&group_id=180599&atid=893831

Reported-by: "Xu, Jiajun" <jiajun.xu@intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 virt/kvm/irq_comm.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -205,10 +205,9 @@ int kvm_request_irq_source_id(struct kvm
 	int irq_source_id;
 
 	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap,
-				sizeof(kvm->arch.irq_sources_bitmap));
+	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
 
-	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	if (irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
 		return -EFAULT;
 	}
@@ -228,7 +227,7 @@ void kvm_free_irq_source_id(struct kvm *
 
 	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
-	    irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
+	    irq_source_id >= BITS_PER_LONG) {
 		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
 		return;
 	}

[033/151] KVM: x86: include pvclock MSRs in msrs_to_save

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Glauber Costa <glommer@redhat.com>

commit e3267cbbbfbcbe9c18833e89b10beabb1117cb55 upstream.

For a while now, we are issuing a rdmsr instruction to find out which
msrs in our save list are really supported by the underlying machine.
However, it fails to account for kvm-specific msrs, such as the pvclock
ones.

This patch moves then to the beginning of the list, and skip testing them.

Signed-off-by: Glauber Costa <glommer@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kvm/x86.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -484,16 +484,19 @@ static inline u32 bit(int bitno)
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
  * This list is modified at module load time to reflect the
- * capabilities of the host cpu.
+ * capabilities of the host cpu. This capabilities test skips MSRs that are
+ * kvm-specific. Those are put in the beginning of the list.
  */
+
+#define KVM_SAVE_MSRS_BEGIN	2
 static u32 msrs_to_save[] = {
+	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+	MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
 };
 
 static unsigned num_msrs_to_save;
@@ -2433,7 +2436,8 @@ static void kvm_init_msr_list(void)
 	u32 dummy[2];
 	unsigned i, j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
+	/* skip the first msrs in the list. KVM-specific */
+	for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 		if (j < i)

[034/151] x86: Prevent GCC 4.4.x (pentium-mmx et al) function prologue wreckage

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Thomas Gleixner <tglx@linutronix.de>

commit 746357d6a526d6da9d89a2ec645b28406e959c2e upstream.

When the kernel is compiled with -pg for tracing GCC 4.4.x inserts
stack alignment of a function _before_ the mcount prologue if the
-march=pentium-mmx is set and -mtune=generic is not set. This breaks
the assumption of the function graph tracer which expects that the
mcount prologue

       push %ebp
       mov  %esp, %ebp

is the first stack operation in a function because it needs to modify
the function return address on the stack to trap into the tracer
before returning to the real caller.

The generated code is:

        push   %edi
        lea    0x8(%esp),%edi
        and    $0xfffffff0,%esp
        pushl  -0x4(%edi)
        push   %ebp
        mov    %esp,%ebp

so the tracer modifies the copy of the return address which is stored
after the stack alignment and therefor does not trap the return which
in turn breaks the call chain logic of the tracer and leads to a
kernel panic.

Aside of the fact that the generated code is horrible for no good
reason other -march -mtune options generate the expected:

        push   %ebp
        mov    %esp,%ebp
        and    $0xfffffff0,%esp

which does the same and keeps everything intact.

After some experimenting we found out that this problem is restricted
to gcc4.4.x and to the following -march settings:

i586, pentium, pentium-mmx, k6, k6-2, k6-3, winchip-c6, winchip2, c3,
geode

By adding -mtune=generic the code generator produces always the
expected code.

So forcing -mtune=generic when CONFIG_FUNCTION_GRAPH_TRACER=y is not
pretty, but at the moment the only way to prevent that the kernel
trips over gcc-shrooms induced code madness.

Most distro kernels have CONFIG_X86_GENERIC=y anyway which forces
-mtune=generic as well so it will not impact those.


2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <alpine.LFD.2.00.0911200206570.24119@localhost.localdomain>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
Cc: Jeff Law <law@redhat.com>
Cc: gcc@gcc.gnu.org
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Andrew Haley <aph@redhat.com>
Cc: Richard Guenther <richard.guenther@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/Makefile_32.cpu |    6 ++++++
 1 file changed, 6 insertions(+)

--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -46,6 +46,12 @@ cflags-$(CONFIG_MGEODEGX1)	+= -march=pen
 # cpu entries
 cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
 
+# Work around the pentium-mmx code generator madness of gcc4.4.x which
+# does stack alignment by generating horrible code _before_ the mcount
+# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
+# tracer assumptions
+cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-mtune=generic)
+
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.
 ifneq ($(CONFIG_X86_P6_NOP),y)

[035/151] x86: Use -maccumulate-outgoing-args for sane mcount prologues

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Thomas Gleixner <tglx@linutronix.de>

commit b8b7d791a8ff01d2380089279a69afa99115fb23 upstream.

commit 746357d (x86: Prevent GCC 4.4.x (pentium-mmx et al) function
prologue wreckage) uses -mtune=generic to work around the function
prologue problem with mcount on -march=pentium-mmx and others.

Jakub pointed out that we can use -maccumulate-outgoing-args instead
which is selected by -mtune=generic and prevents the problem without
losing the -march specific optimizations.

Pointed-out-by: Jakub Jelinek <jakub@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/Makefile_32.cpu |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -49,8 +49,9 @@ cflags-$(CONFIG_X86_GENERIC) 	+= $(call 
 # Work around the pentium-mmx code generator madness of gcc4.4.x which
 # does stack alignment by generating horrible code _before_ the mcount
 # prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
-# tracer assumptions
-cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-mtune=generic)
+# tracer assumptions. For i686, generic, core2 this is set by the
+# compiler anyway
+cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args)
 
 # Bug fix for binutils: this option is required in order to keep
 # binutils from generating NOPL instructions against our will.

[036/151] x86, mce: dont restart timer if disabled

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>

commit fe5ed91ddce85a0ed0e4f92c10b099873ef62167 upstream.

Even it is in error path unlikely taken, add_timer_on() at
CPU_DOWN_FAILED* needs to be skipped if mce_timer is disabled.

Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/cpu/mcheck/mce.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1991,9 +1991,11 @@ mce_cpu_callback(struct notifier_block *
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		t->expires = round_jiffies(jiffies +
+		if (!mce_ignore_ce && check_interval) {
+			t->expires = round_jiffies(jiffies +
 					   __get_cpu_var(mce_next_interval));
-		add_timer_on(t, cpu);
+			add_timer_on(t, cpu);
+		}
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
 	case CPU_POST_DEAD:

[037/151] x86/mce: Set up timer unconditionally

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jan Beulich <jbeulich@novell.com>

commit bc09effabf0c5c6c7021e5ef9af15a23579b32a8 upstream.

mce_timer must be passed to setup_timer() in all cases, no
matter whether it is going to be actually used. Otherwise, when
the CPU gets brought down, its call to del_timer_sync() will
never return, as the timer won't have a base associated, and
hence lock_timer_base() will loop infinitely.

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
LKML-Reference: <4B1DB831.2030801@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/cpu/mcheck/mce.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1374,13 +1374,14 @@ static void mce_init_timer(void)
 	struct timer_list *t = &__get_cpu_var(mce_timer);
 	int *n = &__get_cpu_var(mce_next_interval);
 
+	setup_timer(t, mcheck_timer, smp_processor_id());
+
 	if (mce_ignore_ce)
 		return;
 
 	*n = check_interval * HZ;
 	if (!*n)
 		return;
-	setup_timer(t, mcheck_timer, smp_processor_id());
 	t->expires = round_jiffies(jiffies + *n);
 	add_timer_on(t, smp_processor_id());
 }

[038/151] x86: SGI UV: Fix BAU initialization

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Cliff Wickman <cpw@sgi.com>

commit e38e2af1c57c3eb5211331a5b4fcaae0c4a2a918 upstream.

A memory mapped register that affects the SGI UV Broadcast
Assist Unit's interrupt handling may sometimes be unintialized.

Remove the condition on its initialization, as that condition
can be randomly satisfied by a hardware reset.

Signed-off-by: Cliff Wickman <cpw@sgi.com>
LKML-Reference: <E1NBGB9-0005nU-Dp@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/tlb_uv.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -817,10 +817,8 @@ static int __init uv_init_blade(int blad
 	 */
 	apicid = blade_to_first_apicid(blade);
 	pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG);
-	if ((pa & 0xff) != UV_BAU_MESSAGE) {
-		uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
+	uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
 				      ((apicid << 32) | UV_BAU_MESSAGE));
-	}
 	return 0;
 }
 

[039/151] x86: Fix duplicated UV BAU interrupt vector

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Cliff Wickman <cpw@sgi.com>

commit 1d865fb728bd6bbcdfbd6ec1e2b8ade3b4805641 upstream.

Interrupt vector 0xec has been doubly defined in irq_vectors.h

It seems arbitrary whether LOCAL_PENDING_VECTOR or
UV_BAU_MESSAGE is the higher number.  As long as they are
unique. If they are not unique we'll hit a BUG in
alloc_system_vector().

Signed-off-by: Cliff Wickman <cpw@sgi.com>
LKML-Reference: <E1NJ9Pe-0004P7-0Q@eag09.americas.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/include/asm/irq_vectors.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -113,7 +113,7 @@
  */
 #define LOCAL_PENDING_VECTOR		0xec
 
-#define UV_BAU_MESSAGE			0xec
+#define UV_BAU_MESSAGE			0xea
 
 /*
  * Self IPI vector for machine checks

[040/151] x86: Add new Intel CPU cache size descriptors

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Dave Jones <davej@redhat.com>

commit 85160b92fbd35321104819283c91bfed2b553e3c upstream.

The latest rev of Intel doc AP-485 details new cache descriptors
that we don't yet support. 12MB, 18MB and 24MB 24-way assoc L3
caches.

Signed-off-by: Dave Jones <davej@redhat.com>
LKML-Reference: <20091110184924.GA20337@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/cpu/intel_cacheinfo.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -102,6 +102,9 @@ static const struct _cache_table __cpuin
 	{ 0xe2, LVL_3,    2048 },	/* 16-way set assoc, 64 byte line size */
 	{ 0xe3, LVL_3,    4096 },	/* 16-way set assoc, 64 byte line size */
 	{ 0xe4, LVL_3,    8192 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xea, LVL_3,    12288 },	/* 24-way set assoc, 64 byte line size */
+	{ 0xeb, LVL_3,    18432 },	/* 24-way set assoc, 64 byte line size */
+	{ 0xec, LVL_3,    24576 },	/* 24-way set assoc, 64 byte line size */
 	{ 0x00, 0, 0}
 };
 

[041/151] x86: Fix typo in Intel CPU cache size descriptor

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Dave Jones <davej@redhat.com>

commit e02e0e1a130b9ca37c5186d38ad4b3aaf58bb149 upstream.

I double-checked the datasheet. One of the existing
descriptors has a typo: it should be 2MB not 2038 KB.

Signed-off-by: Dave Jones <davej@redhat.com>
LKML-Reference: <20091110200120.GA27090@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/cpu/intel_cacheinfo.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -94,7 +94,7 @@ static const struct _cache_table __cpuin
 	{ 0xd1, LVL_3,    1024 },	/* 4-way set assoc, 64 byte line size */
 	{ 0xd2, LVL_3,    2048 },	/* 4-way set assoc, 64 byte line size */
 	{ 0xd6, LVL_3,    1024 },	/* 8-way set assoc, 64 byte line size */
-	{ 0xd7, LVL_3,    2038 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd7, LVL_3,    2048 },	/* 8-way set assoc, 64 byte line size */
 	{ 0xd8, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
 	{ 0xdc, LVL_3,    2048 },	/* 12-way set assoc, 64 byte line size */
 	{ 0xdd, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */

[042/151] pata_hpt{37x|3x2n}: fix timing register masks (take 2)

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Sergei Shtylyov <sshtylyov@ru.mvista.com>

commit 5600c70e576199a7552e1c0fff43f3fe16f5566e upstream.

These drivers inherited from the older 'hpt366' IDE driver the buggy timing
register masks in their set_piomode() metods. As a result, too low command
cycle active time is programmed for slow PIO modes.  Quite fortunately, it's
later "fixed up" by the set_dmamode() methods which also "helpfully" reprogram
the command timings, usually to PIO mode 4; unfortunately, setting an UltraDMA
mode #N also reprograms already set PIO data timings, usually to MWDMA mode #
max(N, 2) timings...

However, the drivers added some breakage of their own too:  the bit that they
set/clear to control the FIFO is sometimes wrong -- it's actually the MSB of
the command cycle setup time; also, setting it in DMA mode is wrong as this
bit is only for PIO actually and clearing it for PIO modes is not needed as
no mode in any timing table has it set...

Fix all this, inverting the masks while at it, like in the 'hpt366' and
'pata_hpt366' drivers; bump the drivers' versions, accounting for recent
patches that forgot to do it...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/ata/pata_hpt37x.c  |   32 +++++++++++++++-----------------
 drivers/ata/pata_hpt3x2n.c |   17 ++++++++---------
 2 files changed, 23 insertions(+), 26 deletions(-)

--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -24,7 +24,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_hpt37x"
-#define DRV_VERSION	"0.6.12"
+#define DRV_VERSION	"0.6.14"
 
 struct hpt_clock {
 	u8	xfer_speed;
@@ -404,9 +404,8 @@ static void hpt370_set_piomode(struct at
 
 	pci_read_config_dword(pdev, addr1, &reg);
 	mode = hpt37x_find_mode(ap, adev->pio_mode);
-	mode &= ~0x8000000;	/* No FIFO in PIO */
-	mode &= ~0x30070000;	/* Leave config bits alone */
-	reg &= 0x30070000;	/* Strip timing bits */
+	mode &= 0xCFC3FFFF;	/* Leave DMA bits alone */
+	reg &= ~0xCFC3FFFF;	/* Strip timing bits */
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 
@@ -423,8 +422,7 @@ static void hpt370_set_dmamode(struct at
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	u32 addr1, addr2;
-	u32 reg;
-	u32 mode;
+	u32 reg, mode, mask;
 	u8 fast;
 
 	addr1 = 0x40 + 4 * (adev->devno + 2 * ap->port_no);
@@ -436,11 +434,12 @@ static void hpt370_set_dmamode(struct at
 	fast |= 0x01;
 	pci_write_config_byte(pdev, addr2, fast);
 
+	mask = adev->dma_mode < XFER_UDMA_0 ? 0x31C001FF : 0x303C0000;
+
 	pci_read_config_dword(pdev, addr1, &reg);
 	mode = hpt37x_find_mode(ap, adev->dma_mode);
-	mode |= 0x8000000;	/* FIFO in MWDMA or UDMA */
-	mode &= ~0xC0000000;	/* Leave config bits alone */
-	reg &= 0xC0000000;	/* Strip timing bits */
+	mode &= mask;
+	reg &= ~mask;
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 
@@ -508,9 +507,8 @@ static void hpt372_set_piomode(struct at
 	mode = hpt37x_find_mode(ap, adev->pio_mode);
 
 	printk("Find mode for %d reports %X\n", adev->pio_mode, mode);
-	mode &= ~0x80000000;	/* No FIFO in PIO */
-	mode &= ~0x30070000;	/* Leave config bits alone */
-	reg &= 0x30070000;	/* Strip timing bits */
+	mode &= 0xCFC3FFFF;	/* Leave DMA bits alone */
+	reg &= ~0xCFC3FFFF;	/* Strip timing bits */
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 
@@ -527,8 +525,7 @@ static void hpt372_set_dmamode(struct at
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	u32 addr1, addr2;
-	u32 reg;
-	u32 mode;
+	u32 reg, mode, mask;
 	u8 fast;
 
 	addr1 = 0x40 + 4 * (adev->devno + 2 * ap->port_no);
@@ -539,12 +536,13 @@ static void hpt372_set_dmamode(struct at
 	fast &= ~0x07;
 	pci_write_config_byte(pdev, addr2, fast);
 
+	mask = adev->dma_mode < XFER_UDMA_0 ? 0x31C001FF : 0x303C0000;
+
 	pci_read_config_dword(pdev, addr1, &reg);
 	mode = hpt37x_find_mode(ap, adev->dma_mode);
 	printk("Find mode for DMA %d reports %X\n", adev->dma_mode, mode);
-	mode &= ~0xC0000000;	/* Leave config bits alone */
-	mode |= 0x80000000;	/* FIFO in MWDMA or UDMA */
-	reg &= 0xC0000000;	/* Strip timing bits */
+	mode &= mask;
+	reg &= ~mask;
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 
--- a/drivers/ata/pata_hpt3x2n.c
+++ b/drivers/ata/pata_hpt3x2n.c
@@ -25,7 +25,7 @@
 #include <linux/libata.h>
 
 #define DRV_NAME	"pata_hpt3x2n"
-#define DRV_VERSION	"0.3.4"
+#define DRV_VERSION	"0.3.7"
 
 enum {
 	HPT_PCI_FAST	=	(1 << 31),
@@ -185,9 +185,8 @@ static void hpt3x2n_set_piomode(struct a
 
 	pci_read_config_dword(pdev, addr1, &reg);
 	mode = hpt3x2n_find_mode(ap, adev->pio_mode);
-	mode &= ~0x8000000;	/* No FIFO in PIO */
-	mode &= ~0x30070000;	/* Leave config bits alone */
-	reg &= 0x30070000;	/* Strip timing bits */
+	mode &= 0xCFC3FFFF;	/* Leave DMA bits alone */
+	reg &= ~0xCFC3FFFF;	/* Strip timing bits */
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 
@@ -204,8 +203,7 @@ static void hpt3x2n_set_dmamode(struct a
 {
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	u32 addr1, addr2;
-	u32 reg;
-	u32 mode;
+	u32 reg, mode, mask;
 	u8 fast;
 
 	addr1 = 0x40 + 4 * (adev->devno + 2 * ap->port_no);
@@ -216,11 +214,12 @@ static void hpt3x2n_set_dmamode(struct a
 	fast &= ~0x07;
 	pci_write_config_byte(pdev, addr2, fast);
 
+	mask = adev->dma_mode < XFER_UDMA_0 ? 0x31C001FF : 0x303C0000;
+
 	pci_read_config_dword(pdev, addr1, &reg);
 	mode = hpt3x2n_find_mode(ap, adev->dma_mode);
-	mode |= 0x8000000;	/* FIFO in MWDMA or UDMA */
-	mode &= ~0xC0000000;	/* Leave config bits alone */
-	reg &= 0xC0000000;	/* Strip timing bits */
+	mode &= mask;
+	reg &= ~mask;
 	pci_write_config_dword(pdev, addr1, reg | mode);
 }
 

[043/151] [S390] s390: clear high-order bits of registers after sam64

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>

commit cf87b7439ec81b9374e7772e44e9cb2eb9e57160 upstream.

When the kernel is IPLed without the CLEAR option and switches
to 64-bit, the high-order half of the registers might contain
random values.  This can cause addressing exceptions and the
kernel enters an interrupt loop.

Initialize the high-order half of the general purpose registers
with zeros after switching to 64-bit mode.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/s390/kernel/head64.S |    3 +++
 1 file changed, 3 insertions(+)

--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -83,6 +83,8 @@ startup_continue:
 	slr	%r0,%r0 		# set cpuid to zero
 	sigp	%r1,%r0,0x12		# switch to esame mode
 	sam64				# switch to 64 bit mode
+	llgfr	%r13,%r13		# clear high-order half of base reg
+	lmh	%r0,%r15,.Lzero64-.LPG1(%r13)	# clear high-order half
 	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
 	lg	%r12,.Lparmaddr-.LPG1(%r13)	# pointer to parameter area
 					# move IPL device to lowcore
@@ -127,6 +129,7 @@ startup_continue:
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
 .Lnop:	.long	0x07000700
+.Lzero64:.fill	16,4,0x0
 #ifdef CONFIG_ZFCPDUMP
 .Lcurrent_cpu:
 	.long 0x0

[044/151] V4L/DVB: Fix test in copy_reg_bits()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Roel Kluin <roel.kluin@gmail.com>

commit c95a419a5604ec8a23cd73f61e9bb151e8cbe89b upstream.

The reg_pair2[j].reg was tested twice.

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Acked-by: Michael Krufky <mkrufky@linuxtv.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/media/common/tuners/mxl5007t.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/media/common/tuners/mxl5007t.c
+++ b/drivers/media/common/tuners/mxl5007t.c
@@ -196,7 +196,7 @@ static void copy_reg_bits(struct reg_pai
 	i = j = 0;
 
 	while (reg_pair1[i].reg || reg_pair1[i].val) {
-		while (reg_pair2[j].reg || reg_pair2[j].reg) {
+		while (reg_pair2[j].reg || reg_pair2[j].val) {
 			if (reg_pair1[i].reg != reg_pair2[j].reg) {
 				j++;
 				continue;

[045/151] bsdacct: fix uid/gid misreporting

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alexey Dobriyan <adobriyan@gmail.com>

commit 4b731d50ff3df6b9141a6c12b088e8eb0109e83c upstream.

commit d8e180dcd5bbbab9cd3ff2e779efcf70692ef541 "bsdacct: switch
credentials for writing to the accounting file" introduced credential
switching during final acct data collecting.  However, uid/gid pair
continued to be collected from current which became credentials of who
created acct file, not who exits.

Addresses http://bugzilla.kernel.org/show_bug.cgi?id=14676

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Reported-by: Juho K. Juopperi <jkj@kapsi.fi>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Acked-by: David Howells <dhowells@redhat.com>
Reviewed-by: Michal Schmidt <mschmidt@redhat.com>
Cc: James Morris <jmorris@namei.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/acct.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -536,7 +536,8 @@ static void do_acct_process(struct bsd_a
 	do_div(elapsed, AHZ);
 	ac.ac_btime = get_seconds() - elapsed;
 	/* we really need to bite the bullet and change layout */
-	current_uid_gid(&ac.ac_uid, &ac.ac_gid);
+	ac.ac_uid = orig_cred->uid;
+	ac.ac_gid = orig_cred->gid;
 #if ACCT_VERSION==2
 	ac.ac_ahz = AHZ;
 #endif

[046/151] UBI: flush wl before clearing update marker

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>

commit 6afaf8a484cbbfd2ccf58a4e5396d1f280469789 upstream.

ubiupdatevol -t does the following:
- ubi_start_update()
  - set_update_marker()
  - for all LEBs ubi_eba_unmap_leb()
  - clear_update_marker()
  - ubi_wl_flush()

ubi_wl_flush() physically erases all PEB, once it returns all PEBs are
empty. clear_update_marker() has the update marker written after return.
If there is a power cut between the last two functions then the UBI
volume has no longer the "update" marker set and may have some valid
LEBs while some of them may be gone.
If that volume in question happens to be a UBIFS volume, then mount
will fail with

|UBIFS error (pid 1361): ubifs_read_node: bad node type (255 but expected 6)
|UBIFS error (pid 1361): ubifs_read_node: bad node at LEB 0:0
|Not a node, first 24 bytes:
|00000000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

if there is at least one valid LEB and the wear-leveling worker managed
to clear LEB 0.

The patch waits for the wl worker to finish prior clearing the "update"
marker on flash. The two new LEB which are scheduled for erasing after
clear_update_marker() should not matter because they are only visible to
UBI.

Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/mtd/ubi/upd.c |   20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -147,12 +147,14 @@ int ubi_start_update(struct ubi_device *
 	}
 
 	if (bytes == 0) {
+		err = ubi_wl_flush(ubi);
+		if (err)
+			return err;
+
 		err = clear_update_marker(ubi, vol, 0);
 		if (err)
 			return err;
-		err = ubi_wl_flush(ubi);
-		if (!err)
-			vol->updating = 0;
+		vol->updating = 0;
 	}
 
 	vol->upd_buf = vmalloc(ubi->leb_size);
@@ -362,16 +364,16 @@ int ubi_more_update_data(struct ubi_devi
 
 	ubi_assert(vol->upd_received <= vol->upd_bytes);
 	if (vol->upd_received == vol->upd_bytes) {
+		err = ubi_wl_flush(ubi);
+		if (err)
+			return err;
 		/* The update is finished, clear the update marker */
 		err = clear_update_marker(ubi, vol, vol->upd_bytes);
 		if (err)
 			return err;
-		err = ubi_wl_flush(ubi);
-		if (err == 0) {
-			vol->updating = 0;
-			err = to_write;
-			vfree(vol->upd_buf);
-		}
+		vol->updating = 0;
+		err = to_write;
+		vfree(vol->upd_buf);
 	}
 
 	return err;

[047/151] jbd2: dont wipe the journal on a failed journal checksum

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Theodore Ts'o <tytso@mit.edu>

commit e6a47428de84e19fda52f21ab73fde2906c40d09 upstream.

If there is a failed journal checksum, don't reset the journal.  This
allows for userspace programs to decide how to recover from this
situation.  It may be that ignoring the journal checksum failure might
be a better way of recovering the file system.  Once we add per-block
checksums, we can definitely do better.  Until then, a system
administrator can try backing up the file system image (or taking a
snapshot) and and trying to determine experimentally whether ignoring
the checksum failure or aborting the journal replay results in less
data loss.

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

---
 fs/jbd2/journal.c |    7 +++++++
 1 file changed, 7 insertions(+)

--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1253,6 +1253,13 @@ int jbd2_journal_load(journal_t *journal
 	if (jbd2_journal_recover(journal))
 		goto recovery_error;
 
+	if (journal->j_failed_commit) {
+		printk(KERN_ERR "JBD2: journal transaction %u on %s "
+		       "is corrupt.\n", journal->j_failed_commit,
+		       journal->j_devname);
+		return -EIO;
+	}
+
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */

[048/151] USB: xhci: Add correct email and files to MAINTAINERS entry.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Sarah Sharp <sarah.a.sharp@linux.intel.com>

commit 36d0344c254a7b333272757f858c403ea3a2d29f upstream.

Add the xHCI driver files to its MAINTAINERS entry so that I'm Cc'd on
cleanup patches.  Update the email address to one I actually use for
sending patches and responding to Linux mailing list emails.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 MAINTAINERS |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5594,9 +5594,11 @@ S:	Maintained
 F:	drivers/net/wireless/rndis_wlan.c
 
 USB XHCI DRIVER
-M:	Sarah Sharp <sarah.a.sharp@intel.com>
+M:	Sarah Sharp <sarah.a.sharp@linux.intel.com>
 L:	linux-usb@vger.kernel.org
 S:	Supported
+F:	drivers/usb/host/xhci*
+F:	drivers/usb/host/pci-quirks*
 
 USB ZC0301 DRIVER
 M:	Luca Risolia <luca.risolia@studio.unibo.it>

[049/151] USB: musb_gadget_ep0: fix unhandled endpoint 0 IRQs, again

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Sergei Shtylyov <sshtylyov@ru.mvista.com>

commit 196f1b7a387546f425df2f1fad26772e3d513aea upstream.

Commit a5073b52833e4df8e16c93dc4cbb7e0c558c74a2 (musb_gadget: fix
unhandled endpoint 0 IRQs) somehow missed its key change:

"The gadget EP0 code routinely ignores an interrupt at end of
the data phase because of musb_g_ep0_giveback() resetting the
state machine to "idle, waiting for SETUP" phase prematurely."

So, the majority of the cases of unhandled IRQs is still unfixed...

Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: Anand Gadiyar <gadiyar@ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/musb/musb_gadget_ep0.c |    1 -
 1 file changed, 1 deletion(-)

--- a/drivers/usb/musb/musb_gadget_ep0.c
+++ b/drivers/usb/musb/musb_gadget_ep0.c
@@ -199,7 +199,6 @@ service_in_request(struct musb *musb, co
 static void musb_g_ep0_giveback(struct musb *musb, struct usb_request *req)
 {
 	musb_g_giveback(&musb->endpoints[0].ep_in, req, 0);
-	musb->ep0_state = MUSB_EP0_STAGE_SETUP;
 }
 
 /*

[050/151] USB: option.c: add support for D-Link DWM-162-U5

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhang Le <r0bertz@gentoo.org>

commit 54a8e144acad6506920f385f4ef2779664f05b21 upstream.

Add D-Link DWM-162-U5 device id 1e0e:ce16 into option driver.  The device
has 4 interfaces, of which 1 is handled by storage and the other 3 by
option driver.

The device appears first as CD-only 05c6:2100 device and must be switched
to 1e0e:ce16 mode either by using "eject CD" or usb_modeswitch.

The MessageContent for usb_modeswitch.conf is:
"55534243e0c26a85000000000000061b000000020000000000000000000000"

Signed-off-by: Zhang Le <r0bertz@gentoo.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/serial/option.c |    1 +
 1 file changed, 1 insertion(+)

--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -635,6 +635,7 @@ static struct usb_device_id option_ids[]
 	{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_G450) },
 	{ USB_DEVICE(TOSHIBA_VENDOR_ID, TOSHIBA_PRODUCT_HSDPA_MINICARD ) }, /* Toshiba 3G HSDPA == Novatel Expedite EU870D MiniCard */
 	{ USB_DEVICE(ALINK_VENDOR_ID, 0x9000) },
+	{ USB_DEVICE(ALINK_VENDOR_ID, 0xce16) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S) },
 	{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },

[051/151] USB: usbtmc: repeat usb_bulk_msg until whole message is transfered

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Andre Herms <andre.herms@tec-venture.de>

commit ec412b92dbe3ea839716853eea058d1bcc5e6ca4 upstream.

usb_bulk_msg() transfers only bytes up to the maximum packet size.
It must be repeated by the usbtmc driver until all bytes of a TMC message
are transfered.

Without this patch, ETIMEDOUT is reported when writing TMC messages
larger than the maximum USB bulk size and the transfer remains incomplete.
The user will notice that the device hangs and must be reset by either closing
the application or pulling the plug.

Signed-off-by: Andre Herms <andre.herms@tec-venture.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/class/usbtmc.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -562,10 +562,16 @@ static ssize_t usbtmc_write(struct file 
 		n_bytes = roundup(12 + this_part, 4);
 		memset(buffer + 12 + this_part, 0, n_bytes - (12 + this_part));
 
-		retval = usb_bulk_msg(data->usb_dev,
-				      usb_sndbulkpipe(data->usb_dev,
-						      data->bulk_out),
-				      buffer, n_bytes, &actual, USBTMC_TIMEOUT);
+		do {
+			retval = usb_bulk_msg(data->usb_dev,
+					      usb_sndbulkpipe(data->usb_dev,
+							      data->bulk_out),
+					      buffer, n_bytes,
+					      &actual, USBTMC_TIMEOUT);
+			if (retval != 0)
+				break;
+			n_bytes -= actual;
+		} while (n_bytes);
 
 		data->bTag_last_write = data->bTag;
 		data->bTag++;

[052/151] USB: usb-storage: add BAD_SENSE flag

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alan Stern <stern@rowland.harvard.edu>

commit a0bb108112a872c0b0c4b3ef4974f95fb75b155d upstream.

This patch (as1311) fixes a problem in usb-storage: Some devices are
pretty broken when it comes to reporting sense data.  The information
they send back indicates that they have more than 18 bytes of sense
data available, but when the system asks for more than 18 they fail or
hang.  The symptom is that probing fails with multiple resets.

The patch adds a new BAD_SENSE flag to indicate that usb-storage
should never ask for more than 18 bytes of sense data.  The flag can
be set in an unusual_devs entry or via the "quirks=" module parameter,
and it is set automatically whenever a REQUEST SENSE command for more
than 18 bytes fails or times out.

An unusual_devs entry is added for the Agfa photo frame, which uses a
Prolific chip having this bug.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Tested-by: Daniel Kukula <daniel.kuku@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2663,6 +2663,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			to a common usb-storage quirk flag as follows:
 				a = SANE_SENSE (collect more than 18 bytes
 					of sense data);
+				b = BAD_SENSE (don't collect more than 18
+					bytes of sense data);
 				c = FIX_CAPACITY (decrease the reported
 					device capacity by one sector);
 				h = CAPACITY_HEURISTICS (decrease the
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 589f6b4..cc313d1 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -666,10 +666,11 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 	 * to wait for at least one CHECK_CONDITION to determine
 	 * SANE_SENSE support
 	 */
-	if ((srb->cmnd[0] == ATA_16 || srb->cmnd[0] == ATA_12) &&
+	if (unlikely((srb->cmnd[0] == ATA_16 || srb->cmnd[0] == ATA_12) &&
 	    result == USB_STOR_TRANSPORT_GOOD &&
 	    !(us->fflags & US_FL_SANE_SENSE) &&
-	    !(srb->cmnd[2] & 0x20)) {
+	    !(us->fflags & US_FL_BAD_SENSE) &&
+	    !(srb->cmnd[2] & 0x20))) {
 		US_DEBUGP("-- SAT supported, increasing auto-sense\n");
 		us->fflags |= US_FL_SANE_SENSE;
 	}
@@ -718,6 +719,12 @@ Retry_Sense:
 		if (test_bit(US_FLIDX_TIMED_OUT, &us->dflags)) {
 			US_DEBUGP("-- auto-sense aborted\n");
 			srb->result = DID_ABORT << 16;
+
+			/* If SANE_SENSE caused this problem, disable it */
+			if (sense_size != US_SENSE_SIZE) {
+				us->fflags &= ~US_FL_SANE_SENSE;
+				us->fflags |= US_FL_BAD_SENSE;
+			}
 			goto Handle_Errors;
 		}
 
@@ -727,10 +734,11 @@ Retry_Sense:
 		 * (small) sense request. This fixes some USB GSM modems
 		 */
 		if (temp_result == USB_STOR_TRANSPORT_FAILED &&
-		    (us->fflags & US_FL_SANE_SENSE) &&
-		    sense_size != US_SENSE_SIZE) {
+				sense_size != US_SENSE_SIZE) {
 			US_DEBUGP("-- auto-sense failure, retry small sense\n");
 			sense_size = US_SENSE_SIZE;
+			us->fflags &= ~US_FL_SANE_SENSE;
+			us->fflags |= US_FL_BAD_SENSE;
 			goto Retry_Sense;
 		}
 
@@ -754,6 +762,7 @@ Retry_Sense:
 		 */
 		if (srb->sense_buffer[7] > (US_SENSE_SIZE - 8) &&
 		    !(us->fflags & US_FL_SANE_SENSE) &&
+		    !(us->fflags & US_FL_BAD_SENSE) &&
 		    (srb->sense_buffer[0] & 0x7C) == 0x70) {
 			US_DEBUGP("-- SANE_SENSE support enabled\n");
 			us->fflags |= US_FL_SANE_SENSE;
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index d4f034e..64a0a2c 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -818,6 +818,13 @@ UNUSUAL_DEV( 0x066f, 0x8000, 0x0001, 0x0001,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
+/* Reported by Daniel Kukula <daniel.kuku@gmail.com> */
+UNUSUAL_DEV( 0x067b, 0x1063, 0x0100, 0x0100,
+		"Prolific Technology, Inc.",
+		"Prolific Storage Gadget",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_BAD_SENSE ),
+
 /* Reported by Rogerio Brito <rbrito@ime.usp.br> */
 UNUSUAL_DEV( 0x067b, 0x2317, 0x0001, 0x001,
 		"Prolific Technology, Inc.",
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 1599d86..f5c0264 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -463,6 +463,9 @@ static void adjust_quirks(struct us_data *us)
 		case 'a':
 			f |= US_FL_SANE_SENSE;
 			break;
+		case 'b':
+			f |= US_FL_BAD_SENSE;
+			break;
 		case 'c':
 			f |= US_FL_FIX_CAPACITY;
 			break;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 3d15fb9..a4b947e 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -56,7 +56,9 @@
 	US_FLAG(SANE_SENSE,     0x00008000)			\
 		/* Sane Sense (> 18 bytes) */			\
 	US_FLAG(CAPACITY_OK,	0x00010000)			\
-		/* READ CAPACITY response is correct */
+		/* READ CAPACITY response is correct */		\
+	US_FLAG(BAD_SENSE,	0x00020000)			\
+		/* Bad Sense (never more than 18 bytes) */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };

[053/151] USB: Close usb_find_interface race v3

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Russ Dill <Russ.Dill@gmail.com>

commit c2d284ee04ab6f6718de2ddcf1b43160e046c41d upstream.

USB drivers that create character devices call usb_register_dev in their
probe function. This associates the usb_interface device with that minor
number and creates the character device and announces it to the world.
However, the driver's probe function is called before the new
usb_interface is added to the driver's klist_devices.

This is a problem because userspace will respond to the character device
creation announcement by opening the character device. The driver's open
function will the call usb_find_interface to find the usb_interface
associated with that minor number. usb_find_interface will walk the
driver's list of devices and find the usb_interface with the matching
minor number.

Because the announcement happens before the usb_interface is added to the
driver's klist_devices, a race condition exists. A straightforward fix
is to walk the list of devices on usb_bus_type instead since the device
is added to that list before the announcement occurs.

bus_find_device calls get_device to bump the reference count on the found
device. It is arguable that the reference count should be dropped by the
caller of usb_find_interface instead of usb_find_interface, however,
the current users of usb_find_interface do not expect this.

The original version of this patch only matched against minor number
instead of driver and minor number. This version matches against both.

Signed-off-by: Russ Dill <Russ.Dill@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/usb/core/usb.c |   31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -132,7 +132,7 @@ EXPORT_SYMBOL_GPL(usb_altnum_to_altsetti
 
 struct find_interface_arg {
 	int minor;
-	struct usb_interface *interface;
+	struct device_driver *drv;
 };
 
 static int __find_interface(struct device *dev, void *data)
@@ -143,12 +143,10 @@ static int __find_interface(struct devic
 	if (!is_usb_interface(dev))
 		return 0;
 
+	if (dev->driver != arg->drv)
+		return 0;
 	intf = to_usb_interface(dev);
-	if (intf->minor != -1 && intf->minor == arg->minor) {
-		arg->interface = intf;
-		return 1;
-	}
-	return 0;
+	return intf->minor == arg->minor;
 }
 
 /**
@@ -156,21 +154,24 @@ static int __find_interface(struct devic
  * @drv: the driver whose current configuration is considered
  * @minor: the minor number of the desired device
  *
- * This walks the driver device list and returns a pointer to the interface
- * with the matching minor.  Note, this only works for devices that share the
- * USB major number.
+ * This walks the bus device list and returns a pointer to the interface
+ * with the matching minor and driver.  Note, this only works for devices
+ * that share the USB major number.
  */
 struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor)
 {
 	struct find_interface_arg argb;
-	int retval;
+	struct device *dev;
 
 	argb.minor = minor;
-	argb.interface = NULL;
-	/* eat the error, it will be in argb.interface */
-	retval = driver_for_each_device(&drv->drvwrap.driver, NULL, &argb,
-					__find_interface);
-	return argb.interface;
+	argb.drv = &drv->drvwrap.driver;
+
+	dev = bus_find_device(&usb_bus_type, NULL, &argb, __find_interface);
+
+	/* Drop reference count from bus_find_device */
+	put_device(dev);
+
+	return dev ? to_usb_interface(dev) : NULL;
 }
 EXPORT_SYMBOL_GPL(usb_find_interface);
 

[054/151] [ARM] pxa/em-x270: fix usb hub power up/reset sequence

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Igor Grinberg <grinberg@compulab.co.il>

commit 1b82e4c32fba96d8805b1e2126ba5382e56fac32 upstream.

Signed-off-by: Igor Grinberg <grinberg@compulab.co.il>
Signed-off-by: Mike Rapoport <mike@compulab.co.il>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/arm/mach-pxa/em-x270.c |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -497,16 +497,15 @@ static int em_x270_usb_hub_init(void)
 		goto err_free_vbus_gpio;
 
 	/* USB Hub power-on and reset */
-	gpio_direction_output(usb_hub_reset, 0);
+	gpio_direction_output(usb_hub_reset, 1);
+	gpio_direction_output(GPIO9_USB_VBUS_EN, 0);
 	regulator_enable(em_x270_usb_ldo);
-	gpio_set_value(usb_hub_reset, 1);
 	gpio_set_value(usb_hub_reset, 0);
+	gpio_set_value(usb_hub_reset, 1);
 	regulator_disable(em_x270_usb_ldo);
 	regulator_enable(em_x270_usb_ldo);
-	gpio_set_value(usb_hub_reset, 1);
-
-	/* enable VBUS */
-	gpio_direction_output(GPIO9_USB_VBUS_EN, 1);
+	gpio_set_value(usb_hub_reset, 0);
+	gpio_set_value(GPIO9_USB_VBUS_EN, 1);
 
 	return 0;
 

[055/151] hfs: fix a potential buffer overflow

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Amerigo Wang <amwang@redhat.com>

commit ec81aecb29668ad71f699f4e7b96ec46691895b6 upstream.

A specially-crafted Hierarchical File System (HFS) filesystem could cause
a buffer overflow to occur in a process's kernel stack during a memcpy()
call within the hfs_bnode_read() function (at fs/hfs/bnode.c:24).  The
attacker can provide the source buffer and length, and the destination
buffer is a local variable of a fixed length.  This local variable (passed
as "&entry" from fs/hfs/dir.c:112 and allocated on line 60) is stored in
the stack frame of hfs_bnode_read()'s caller, which is hfs_readdir().
Because the hfs_readdir() function executes upon any attempt to read a
directory on the filesystem, it gets called whenever a user attempts to
inspect any filesystem contents.

[amwang@redhat.com: modify this patch and fix coding style problems]
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Eugene Teo <eteo@redhat.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Dave Anderson <anderson@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/hfs/catalog.c |    4 ++++
 fs/hfs/dir.c     |   11 +++++++++++
 fs/hfs/super.c   |    7 ++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -289,6 +289,10 @@ int hfs_cat_move(u32 cnid, struct inode 
 	err = hfs_brec_find(&src_fd);
 	if (err)
 		goto out;
+	if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) {
+		err = -EIO;
+		goto out;
+	}
 
 	hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset,
 			    src_fd.entrylength);
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -79,6 +79,11 @@ static int hfs_readdir(struct file *filp
 		filp->f_pos++;
 		/* fall through */
 	case 1:
+		if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) {
+			err = -EIO;
+			goto out;
+		}
+
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength);
 		if (entry.type != HFS_CDR_THD) {
 			printk(KERN_ERR "hfs: bad catalog folder thread\n");
@@ -109,6 +114,12 @@ static int hfs_readdir(struct file *filp
 			err = -EIO;
 			goto out;
 		}
+
+		if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) {
+			err = -EIO;
+			goto out;
+		}
+
 		hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength);
 		type = entry.type;
 		len = hfs_mac2asc(sb, strbuf, &fd.key->cat.CName);
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -409,8 +409,13 @@ static int hfs_fill_super(struct super_b
 	/* try to get the root inode */
 	hfs_find_init(HFS_SB(sb)->cat_tree, &fd);
 	res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd);
-	if (!res)
+	if (!res) {
+		if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) {
+			res =  -EIO;
+			goto bail;
+		}
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength);
+	}
 	if (res) {
 		hfs_find_exit(&fd);
 		goto bail_no_root;

[056/151] SUNRPC: IS_ERR/PTR_ERR confusion

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Roel Kluin <roel.kluin@gmail.com>

commit 480e3243df156e39eea6c91057e2ae612a6bbe19 upstream.

IS_ERR returns 1 or 0, PTR_ERR returns the error value.

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/sunrpc/auth_gss/auth_gss.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -485,7 +485,7 @@ gss_refresh_upcall(struct rpc_task *task
 	dprintk("RPC: %5u gss_refresh_upcall for uid %u\n", task->tk_pid,
 								cred->cr_uid);
 	gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred);
-	if (IS_ERR(gss_msg) == -EAGAIN) {
+	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		/* XXX: warning on the first, under the assumption we
 		 * shouldn't normally hit this case on a refresh. */
 		warn_gssd();

[057/151] NFS: Fix nfs_migrate_page()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Trond Myklebust <Trond.Myklebust@netapp.com>

commit 190f38e5cedc910940b1da9015f00458c18f97b4 upstream.

The call to migrate_page() will cause the page->private field to be
cleared.
Also fix up the locking around the page->private transfer, so that we ensure
that calls to nfs_page_find_request() don't end up racing.

Finally, fix up a double free bug: nfs_unlock_request() already calls
nfs_release_request() for us...

Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Tested-by: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/nfs/write.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1612,15 +1612,16 @@ int nfs_migrate_page(struct address_spac
 	if (ret)
 		goto out_unlock;
 	page_cache_get(newpage);
+	spin_lock(&mapping->host->i_lock);
 	req->wb_page = newpage;
 	SetPagePrivate(newpage);
-	set_page_private(newpage, page_private(page));
+	set_page_private(newpage, (unsigned long)req);
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
+	spin_unlock(&mapping->host->i_lock);
 	page_cache_release(page);
 out_unlock:
 	nfs_clear_page_tag_locked(req);
-	nfs_release_request(req);
 out:
 	return ret;
 }

[058/151] md/bitmap: protect against bitmap removal while being updated.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: NeilBrown <neilb@suse.de>

commit aa5cbd103887011b4830355f88fb055f9ad2d556 upstream.

A write intent bitmap can be removed from an array while the
array is active.
When this happens, all IO is suspended and flushed before the
bitmap is removed.
However it is possible that bitmap_daemon_work is still running to
clear old bits from the bitmap.  If it is, it can dereference the
bitmap after it has been freed.

So introduce a new mutex to protect bitmap_daemon_work and get it
before destroying a bitmap.

This is suitable for any current -stable kernel.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/bitmap.c |   24 ++++++++++++++++++------
 drivers/md/bitmap.h |    2 +-
 drivers/md/md.c     |    3 ++-
 drivers/md/md.h     |    1 +
 4 files changed, 22 insertions(+), 8 deletions(-)

--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1078,23 +1078,31 @@ static bitmap_counter_t *bitmap_get_coun
  *			out to disk
  */
 
-void bitmap_daemon_work(struct bitmap *bitmap)
+void bitmap_daemon_work(mddev_t *mddev)
 {
+	struct bitmap *bitmap;
 	unsigned long j;
 	unsigned long flags;
 	struct page *page = NULL, *lastpage = NULL;
 	int blocks;
 	void *paddr;
 
-	if (bitmap == NULL)
+	/* Use a mutex to guard daemon_work against
+	 * bitmap_destroy.
+	 */
+	mutex_lock(&mddev->bitmap_mutex);
+	bitmap = mddev->bitmap;
+	if (bitmap == NULL) {
+		mutex_unlock(&mddev->bitmap_mutex);
 		return;
+	}
 	if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
 		goto done;
 
 	bitmap->daemon_lastrun = jiffies;
 	if (bitmap->allclean) {
 		bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
-		return;
+		goto done;
 	}
 	bitmap->allclean = 1;
 
@@ -1203,6 +1211,7 @@ void bitmap_daemon_work(struct bitmap *b
  done:
 	if (bitmap->allclean == 0)
 		bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ;
+	mutex_unlock(&mddev->bitmap_mutex);
 }
 
 static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
@@ -1541,9 +1550,9 @@ void bitmap_flush(mddev_t *mddev)
 	 */
 	sleep = bitmap->daemon_sleep;
 	bitmap->daemon_sleep = 0;
-	bitmap_daemon_work(bitmap);
-	bitmap_daemon_work(bitmap);
-	bitmap_daemon_work(bitmap);
+	bitmap_daemon_work(mddev);
+	bitmap_daemon_work(mddev);
+	bitmap_daemon_work(mddev);
 	bitmap->daemon_sleep = sleep;
 	bitmap_update_sb(bitmap);
 }
@@ -1574,6 +1583,7 @@ static void bitmap_free(struct bitmap *b
 	kfree(bp);
 	kfree(bitmap);
 }
+
 void bitmap_destroy(mddev_t *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -1581,7 +1591,9 @@ void bitmap_destroy(mddev_t *mddev)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
+	mutex_lock(&mddev->bitmap_mutex);
 	mddev->bitmap = NULL; /* disconnect from the md device */
+	mutex_unlock(&mddev->bitmap_mutex);
 	if (mddev->thread)
 		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
 
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -282,7 +282,7 @@ void bitmap_close_sync(struct bitmap *bi
 void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
 
 void bitmap_unplug(struct bitmap *bitmap);
-void bitmap_daemon_work(struct bitmap *bitmap);
+void bitmap_daemon_work(mddev_t *mddev);
 #endif
 
 #endif
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -367,6 +367,7 @@ static mddev_t * mddev_find(dev_t unit)
 
 	mutex_init(&new->open_mutex);
 	mutex_init(&new->reconfig_mutex);
+	mutex_init(&new->bitmap_mutex);
 	INIT_LIST_HEAD(&new->disks);
 	INIT_LIST_HEAD(&new->all_mddevs);
 	init_timer(&new->safemode_timer);
@@ -6629,7 +6630,7 @@ void md_check_recovery(mddev_t *mddev)
 
 
 	if (mddev->bitmap)
-		bitmap_daemon_work(mddev->bitmap);
+		bitmap_daemon_work(mddev);
 
 	if (mddev->ro)
 		return;
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -289,6 +289,7 @@ struct mddev_s
 								* hot-adding a bitmap.  It should
 								* eventually be settable by sysfs.
 								*/
+	struct mutex			bitmap_mutex;
 
 	struct list_head		all_mddevs;
 };

[059/151] futex: Take mmap_sem for get_user_pages in fault_in_user_writeable

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Andi Kleen <andi@firstfloor.org>

commit 722d0172377a5697919b9f7e5beb95165b1dec4e upstream.

get_user_pages() must be called with mmap_sem held.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Andrew Morton <akpm@linuxfoundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Darren Hart <dvhltc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20091208121942.GA21298@basil.fritz.box>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/futex.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -304,8 +304,14 @@ void put_futex_key(int fshared, union fu
  */
 static int fault_in_user_writeable(u32 __user *uaddr)
 {
-	int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
-				 1, 1, 0, NULL, NULL);
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(current, mm, (unsigned long)uaddr,
+			     1, 1, 0, NULL, NULL);
+	up_read(&mm->mmap_sem);
+
 	return ret < 0 ? ret : 0;
 }
 

[060/151] devpts_get_tty() should validate inode

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>

commit edfacdd6f81119b9005615593f2cbd94b8c7e2d8 upstream.

devpts_get_tty() assumes that the inode passed in is associated with a valid
pty.  But if the only reference to the pty is via a bind-mount, the inode
passed to devpts_get_tty() while valid, would refer to a pty that no longer
exists.

With a lot of debug effort, Grzegorz Nosek developed a small program (see
below) to reproduce a crash on recent kernels. This crash is a regression
introduced by the commit:

	commit 527b3e4773628b30d03323a2cb5fb0d84441990f
	Author: Sukadev Bhattiprolu <sukadev@us.ibm.com>
	Date:   Mon Oct 13 10:43:08 2008 +0100

To fix, ensure that the dentry associated with the inode has not yet been
deleted/unhashed by devpts_pty_kill().

See also:
https://lists.linux-foundation.org/pipermail/containers/2009-July/019273.html

tty-bug.c:

#define _GNU_SOURCE
#include <fcntl.h>
#include <sched.h>
#include <stdlib.h>
#include <sys/mount.h>
#include <sys/signal.h>
#include <unistd.h>
#include <stdio.h>

#include <linux/fs.h>

void dummy(int sig)
{
}

static int child(void *unused)
{
	int fd;

	signal(SIGINT, dummy); signal(SIGHUP, dummy);
	pause(); /* cheesy synchronisation to wait for /dev/pts/0 to appear */

	mount("/dev/pts/0", "/dev/console", NULL, MS_BIND, NULL);
	sleep(2);

	fd = open("/dev/console", O_RDWR);
	dup(0); dup(0);
	write(1, "Hello world!\n", sizeof("Hello world!\n")-1);
	return 0;
}

int main(void)
{
	pid_t pid;
	char *stack;

	stack = malloc(16384);
	pid = clone(child, stack+16384, CLONE_NEWNS|SIGCHLD, NULL);

	open("/dev/ptmx", O_RDWR|O_NOCTTY|O_NONBLOCK);

	unlockpt(fd); grantpt(fd);

	sleep(2);
	kill(pid, SIGHUP);
	sleep(1);
	return 0; /* exit before child opens /dev/console */
}

Reported-by: Grzegorz Nosek <root@localdomain.pl>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Tested-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/devpts/inode.c |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -517,11 +517,23 @@ int devpts_pty_new(struct inode *ptmx_in
 
 struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number)
 {
+	struct dentry *dentry;
+	struct tty_struct *tty;
+
 	BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
 
+	/* Ensure dentry has not been deleted by devpts_pty_kill() */
+	dentry = d_find_alias(pts_inode);
+	if (!dentry)
+		return NULL;
+
+	tty = NULL;
 	if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
-		return (struct tty_struct *)pts_inode->i_private;
-	return NULL;
+		tty = (struct tty_struct *)pts_inode->i_private;
+
+	dput(dentry);
+
+	return tty;
 }
 
 void devpts_pty_kill(struct tty_struct *tty)

[061/151] debugfs: fix create mutex racy fops and private data

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

commit d3a3b0adad0865c12e39b712ca89efbd0a3a0dbc upstream.

Setting fops and private data outside of the mutex at debugfs file
creation introduces a race where the files can be opened with the wrong
file operations and private data.  It is easy to trigger with a process
waiting on file creation notification.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/debugfs/inode.c |   55 ++++++++++++++++++++++++++++++-----------------------
 1 file changed, 32 insertions(+), 23 deletions(-)

--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -32,7 +32,9 @@ static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
 static bool debugfs_registered;
 
-static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t dev)
+static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t dev,
+				       void *data, const struct file_operations *fops)
+
 {
 	struct inode *inode = new_inode(sb);
 
@@ -44,14 +46,18 @@ static struct inode *debugfs_get_inode(s
 			init_special_inode(inode, mode, dev);
 			break;
 		case S_IFREG:
-			inode->i_fop = &debugfs_file_operations;
+			inode->i_fop = fops ? fops : &debugfs_file_operations;
+			inode->i_private = data;
 			break;
 		case S_IFLNK:
 			inode->i_op = &debugfs_link_operations;
+			inode->i_fop = fops;
+			inode->i_private = data;
 			break;
 		case S_IFDIR:
 			inode->i_op = &simple_dir_inode_operations;
-			inode->i_fop = &simple_dir_operations;
+			inode->i_fop = fops ? fops : &simple_dir_operations;
+			inode->i_private = data;
 
 			/* directory inodes start off with i_nlink == 2
 			 * (for "." entry) */
@@ -64,7 +70,8 @@ static struct inode *debugfs_get_inode(s
 
 /* SMP-safe */
 static int debugfs_mknod(struct inode *dir, struct dentry *dentry,
-			 int mode, dev_t dev)
+			 int mode, dev_t dev, void *data,
+			 const struct file_operations *fops)
 {
 	struct inode *inode;
 	int error = -EPERM;
@@ -72,7 +79,7 @@ static int debugfs_mknod(struct inode *d
 	if (dentry->d_inode)
 		return -EEXIST;
 
-	inode = debugfs_get_inode(dir->i_sb, mode, dev);
+	inode = debugfs_get_inode(dir->i_sb, mode, dev, data, fops);
 	if (inode) {
 		d_instantiate(dentry, inode);
 		dget(dentry);
@@ -81,12 +88,13 @@ static int debugfs_mknod(struct inode *d
 	return error;
 }
 
-static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, int mode,
+			 void *data, const struct file_operations *fops)
 {
 	int res;
 
 	mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
-	res = debugfs_mknod(dir, dentry, mode, 0);
+	res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
 	if (!res) {
 		inc_nlink(dir);
 		fsnotify_mkdir(dir, dentry);
@@ -94,18 +102,20 @@ static int debugfs_mkdir(struct inode *d
 	return res;
 }
 
-static int debugfs_link(struct inode *dir, struct dentry *dentry, int mode)
+static int debugfs_link(struct inode *dir, struct dentry *dentry, int mode,
+			void *data, const struct file_operations *fops)
 {
 	mode = (mode & S_IALLUGO) | S_IFLNK;
-	return debugfs_mknod(dir, dentry, mode, 0);
+	return debugfs_mknod(dir, dentry, mode, 0, data, fops);
 }
 
-static int debugfs_create(struct inode *dir, struct dentry *dentry, int mode)
+static int debugfs_create(struct inode *dir, struct dentry *dentry, int mode,
+			  void *data, const struct file_operations *fops)
 {
 	int res;
 
 	mode = (mode & S_IALLUGO) | S_IFREG;
-	res = debugfs_mknod(dir, dentry, mode, 0);
+	res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
 	if (!res)
 		fsnotify_create(dir, dentry);
 	return res;
@@ -139,7 +149,9 @@ static struct file_system_type debug_fs_
 
 static int debugfs_create_by_name(const char *name, mode_t mode,
 				  struct dentry *parent,
-				  struct dentry **dentry)
+				  struct dentry **dentry,
+				  void *data,
+				  const struct file_operations *fops)
 {
 	int error = 0;
 
@@ -164,13 +176,16 @@ static int debugfs_create_by_name(const 
 	if (!IS_ERR(*dentry)) {
 		switch (mode & S_IFMT) {
 		case S_IFDIR:
-			error = debugfs_mkdir(parent->d_inode, *dentry, mode);
+			error = debugfs_mkdir(parent->d_inode, *dentry, mode,
+					      data, fops);
 			break;
 		case S_IFLNK:
-			error = debugfs_link(parent->d_inode, *dentry, mode);
+			error = debugfs_link(parent->d_inode, *dentry, mode,
+					     data, fops);
 			break;
 		default:
-			error = debugfs_create(parent->d_inode, *dentry, mode);
+			error = debugfs_create(parent->d_inode, *dentry, mode,
+					       data, fops);
 			break;
 		}
 		dput(*dentry);
@@ -221,19 +236,13 @@ struct dentry *debugfs_create_file(const
 	if (error)
 		goto exit;
 
-	error = debugfs_create_by_name(name, mode, parent, &dentry);
+	error = debugfs_create_by_name(name, mode, parent, &dentry,
+				       data, fops);
 	if (error) {
 		dentry = NULL;
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 		goto exit;
 	}
-
-	if (dentry->d_inode) {
-		if (data)
-			dentry->d_inode->i_private = data;
-		if (fops)
-			dentry->d_inode->i_fop = fops;
-	}
 exit:
 	return dentry;
 }

[062/151] Driver core: fix race in dev_driver_string

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alan Stern <stern@rowland.harvard.edu>

commit 3589972e51fac1e02d0aaa576fa47f568cb94d40 upstream.

This patch (as1310) works around a race in dev_driver_string().  If
the device is unbound while the function is running, dev->driver might
become NULL after we test it and before we dereference it.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/base/core.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -56,7 +56,14 @@ static inline int device_is_not_partitio
  */
 const char *dev_driver_string(const struct device *dev)
 {
-	return dev->driver ? dev->driver->name :
+	struct device_driver *drv;
+
+	/* dev->driver can change to NULL underneath us because of unbinding,
+	 * so be careful about accessing it.  dev->bus and dev->class should
+	 * never change once they are set, so they don't need special care.
+	 */
+	drv = ACCESS_ONCE(dev->driver);
+	return drv ? drv->name :
 			(dev->bus ? dev->bus->name :
 			(dev->class ? dev->class->name : ""));
 }

[063/151] Serial: Do not read IIR in serial8250_start_tx when UART_BUG_TXEN

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Jackson <ian.jackson@eu.citrix.com>

commit 68cb4f8e246bbbc649980be0628cae9265870a91 upstream.

Do not read IIR in serial8250_start_tx when UART_BUG_TXEN

Reading the IIR clears some oustanding interrupts so it is not safe.
Instead, simply transmit immediately if the buffer is empty without
regard to IIR.

Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Jiri Kosina <jkosina@suse.cz>
Cc: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/serial/8250.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -1339,14 +1339,12 @@ static void serial8250_start_tx(struct u
 		serial_out(up, UART_IER, up->ier);
 
 		if (up->bugs & UART_BUG_TXEN) {
-			unsigned char lsr, iir;
+			unsigned char lsr;
 			lsr = serial_in(up, UART_LSR);
 			up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS;
-			iir = serial_in(up, UART_IIR) & 0x0f;
 			if ((up->port.type == PORT_RM9000) ?
-				(lsr & UART_LSR_THRE &&
-				(iir == UART_IIR_NO_INT || iir == UART_IIR_THRI)) :
-				(lsr & UART_LSR_TEMT && iir & UART_IIR_NO_INT))
+				(lsr & UART_LSR_THRE) :
+				(lsr & UART_LSR_TEMT))
 				transmit_chars(up);
 		}
 	}

[064/151] mac80211: Fix bug in computing crc over dynamic IEs in beacon

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Vasanthakumar Thiagarajan <vasanth@atheros.com>

commit 1814077fd12a9cdf478c10076e9c42094e9d9250 upstream.

On a 32-bit machine, BIT() macro does not give the required
bit value if the bit is mroe than 31. In ieee802_11_parse_elems_crc(),
BIT() is suppossed to get the bit value more than 31 (42 (id of ERP_INFO_IE),
37 (CHANNEL_SWITCH_IE), (42), 32 (POWER_CONSTRAINT_IE), 45 (HT_CAP_IE),
61 (HT_INFO_IE)). As we do not get the required bit value for the above
IEs, crc over these IEs are never calculated, so any dynamic change in these
IEs after the association is not really handled on 32-bit platforms.
This patch fixes this issue.

Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/mac80211/util.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -579,7 +579,7 @@ u32 ieee802_11_parse_elems_crc(u8 *start
 		if (elen > left)
 			break;
 
-		if (calc_crc && id < 64 && (filter & BIT(id)))
+		if (calc_crc && id < 64 && (filter & (1ULL << id)))
 			crc = crc32_be(crc, pos - 2, elen + 2);
 
 		switch (id) {

[065/151] mac80211: Fixed bug in mesh portal paths

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Javier Cardona <javier@cozybit.com>

commit 5d618cb81aeea19879975cd1f9a1e707694dfd7c upstream.

Paths to mesh portals were being timed out immediately after each use in
intermediate forwarding nodes.  mppath->exp_time is set to the expiration time
so assigning it to jiffies was marking the path as expired.

Signed-off-by: Javier Cardona <javier@cozybit.com>
Signed-off-by: Andrey Yurovsky <andrey@cozybit.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/mac80211/rx.c |    1 -
 1 file changed, 1 deletion(-)

--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1514,7 +1514,6 @@ ieee80211_rx_h_mesh_fwding(struct ieee80
 			mpp_path_add(mesh_hdr->eaddr2, hdr->addr4, sdata);
 		} else {
 			spin_lock_bh(&mppath->state_lock);
-			mppath->exp_time = jiffies;
 			if (compare_ether_addr(mppath->mpp, hdr->addr4) != 0)
 				memcpy(mppath->mpp, hdr->addr4, ETH_ALEN);
 			spin_unlock_bh(&mppath->state_lock);

[066/151] mac80211: Revert Use correct sign for mesh active path refresh

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Javier Cardona <javier@cozybit.com>

commit 7b324d28a94dac5a451e8cba66e8d324601e5b9a upstream.

The patch ("mac80211: Use correct sign for mesh active path
refresh.") was actually a bug.  Reverted it and improved the
explanation of how mesh path refresh works.

Signed-off-by: Javier Cardona <javier@cozybit.com>
Signed-off-by: Andrey Yurovsky <andrey@cozybit.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/mac80211/mesh.h      |    5 +++--
 net/mac80211/mesh_hwmp.c |    2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -186,8 +186,9 @@ struct mesh_rmc {
  */
 #define MESH_PREQ_MIN_INT	10
 #define MESH_DIAM_TRAVERSAL_TIME 50
-/* Paths will be refreshed if they are closer than PATH_REFRESH_TIME to their
- * expiration
+/* A path will be refreshed if it is used PATH_REFRESH_TIME milliseconds before
+ * timing out.  This way it will remain ACTIVE and no data frames will be
+ * unnecesarily held in the pending queue.
  */
 #define MESH_PATH_REFRESH_TIME			1000
 #define MESH_MIN_DISCOVERY_TIMEOUT (2 * MESH_DIAM_TRAVERSAL_TIME)
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -813,7 +813,7 @@ int mesh_nexthop_lookup(struct sk_buff *
 	}
 
 	if (mpath->flags & MESH_PATH_ACTIVE) {
-		if (time_after(jiffies, mpath->exp_time +
+		if (time_after(jiffies, mpath->exp_time -
 			msecs_to_jiffies(sdata->u.mesh.mshcfg.path_refresh_time))
 				&& !memcmp(sdata->dev->dev_addr, hdr->addr4,
 					   ETH_ALEN)

[067/151] mac80211: fix scan abort sanity checks

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Johannes Berg <johannes@sipsolutions.net>

commit 6d3560d4fc9c5b9fe1a07a63926ea70512c69c32 upstream.

Since sometimes mac80211 queues up a scan request
to only act on it later, it must be allowed to
(internally) cancel a not-yet-running scan, e.g.
when the interface is taken down. This condition
was missing since we always checked only the
local->scanning variable which isn't yet set in
that situation.

Reported-by: Luis R. Rodriguez <mcgrof@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/mac80211/scan.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -264,10 +264,14 @@ void ieee80211_scan_completed(struct iee
 
 	mutex_lock(&local->scan_mtx);
 
-	if (WARN_ON(!local->scanning)) {
-		mutex_unlock(&local->scan_mtx);
-		return;
-	}
+	/*
+	 * It's ok to abort a not-yet-running scan (that
+	 * we have one at all will be verified by checking
+	 * local->scan_req next), but not to complete it
+	 * successfully.
+	 */
+	if (WARN_ON(!local->scanning && !aborted))
+		aborted = true;
 
 	if (WARN_ON(!local->scan_req)) {
 		mutex_unlock(&local->scan_mtx);

[068/151] wireless: correctly report signal value for IEEE80211_HW_SIGNAL_UNSPEC

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: John W. Linville <linville@tuxdriver.com>

commit 19deffbeba930030cfaf000b920333c6ba99ad52 upstream.

This part was missed in "cfg80211: implement get_wireless_stats",
probably because sta_set_sinfo already existed and was only handling
dBm signals.

Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/mac80211/cfg.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -338,7 +338,8 @@ static void sta_set_sinfo(struct sta_inf
 	sinfo->rx_packets = sta->rx_packets;
 	sinfo->tx_packets = sta->tx_packets;
 
-	if (sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) {
+	if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) ||
+	    (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) {
 		sinfo->filled |= STATION_INFO_SIGNAL;
 		sinfo->signal = (s8)sta->last_signal;
 	}

[069/151] rtl8187: Fix wrong rfkill switch mask for some models

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 3697 bytes --]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Larry Finger <Larry.Finger@lwfinger.net>

commit 70d57139f932b9ca21026253d02af71cf53d764a upstream.

There are different bits used to convey the setting of the rfkill
switch to the driver. The current driver only supports one of these
possibilities. These changes were derived from the latest version
of the vendor driver.

This patch fixes the regression noted in kernel Bugzilla #14743.

Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Reported-and-tested-by: Antti Kaijanmäki <antti@kaijanmaki.net>
Tested-by: Hin-Tak Leung <hintak.leung@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/rtl818x/rtl8187.h        |    5 +++++
 drivers/net/wireless/rtl818x/rtl8187_dev.c    |   12 ++++++++++--
 drivers/net/wireless/rtl818x/rtl8187_rfkill.c |    4 ++--
 3 files changed, 17 insertions(+), 4 deletions(-)

--- a/drivers/net/wireless/rtl818x/rtl8187_dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8187_dev.c
@@ -1329,6 +1329,7 @@ static int __devinit rtl8187_probe(struc
 	struct ieee80211_channel *channel;
 	const char *chip_name;
 	u16 txpwr, reg;
+	u16 product_id = le16_to_cpu(udev->descriptor.idProduct);
 	int err, i;
 
 	dev = ieee80211_alloc_hw(sizeof(*priv), &rtl8187_ops);
@@ -1488,6 +1489,13 @@ static int __devinit rtl8187_probe(struc
 		(*channel++).hw_value = txpwr & 0xFF;
 		(*channel++).hw_value = txpwr >> 8;
 	}
+	/* Handle the differing rfkill GPIO bit in different models */
+	priv->rfkill_mask = RFKILL_MASK_8187_89_97;
+	if (product_id == 0x8197 || product_id == 0x8198) {
+		eeprom_93cx6_read(&eeprom, RTL8187_EEPROM_SELECT_GPIO, &reg);
+		if (reg & 0xFF00)
+			priv->rfkill_mask = RFKILL_MASK_8198;
+	}
 
 	/*
 	 * XXX: Once this driver supports anything that requires
@@ -1516,9 +1524,9 @@ static int __devinit rtl8187_probe(struc
 	mutex_init(&priv->conf_mutex);
 	skb_queue_head_init(&priv->b_tx_status.queue);
 
-	printk(KERN_INFO "%s: hwaddr %pM, %s V%d + %s\n",
+	printk(KERN_INFO "%s: hwaddr %pM, %s V%d + %s, rfkill mask %d\n",
 	       wiphy_name(dev->wiphy), dev->wiphy->perm_addr,
-	       chip_name, priv->asic_rev, priv->rf->name);
+	       chip_name, priv->asic_rev, priv->rf->name, priv->rfkill_mask);
 
 #ifdef CONFIG_RTL8187_LEDS
 	eeprom_93cx6_read(&eeprom, 0x3F, &reg);
--- a/drivers/net/wireless/rtl818x/rtl8187.h
+++ b/drivers/net/wireless/rtl818x/rtl8187.h
@@ -23,6 +23,7 @@
 #define RTL8187_EEPROM_TXPWR_CHAN_1	0x16	/* 3 channels */
 #define RTL8187_EEPROM_TXPWR_CHAN_6	0x1B	/* 2 channels */
 #define RTL8187_EEPROM_TXPWR_CHAN_4	0x3D	/* 2 channels */
+#define RTL8187_EEPROM_SELECT_GPIO	0x3B
 
 #define RTL8187_REQT_READ	0xC0
 #define RTL8187_REQT_WRITE	0x40
@@ -31,6 +32,9 @@
 
 #define RTL8187_MAX_RX		0x9C4
 
+#define RFKILL_MASK_8187_89_97	0x2
+#define RFKILL_MASK_8198	0x4
+
 struct rtl8187_rx_info {
 	struct urb *urb;
 	struct ieee80211_hw *dev;
@@ -123,6 +127,7 @@ struct rtl8187_priv {
 	u8 noise;
 	u8 slot_time;
 	u8 aifsn[4];
+	u8 rfkill_mask;
 	struct {
 		__le64 buf;
 		struct sk_buff_head queue;
--- a/drivers/net/wireless/rtl818x/rtl8187_rfkill.c
+++ b/drivers/net/wireless/rtl818x/rtl8187_rfkill.c
@@ -25,10 +25,10 @@ static bool rtl8187_is_radio_enabled(str
 	u8 gpio;
 
 	gpio = rtl818x_ioread8(priv, &priv->map->GPIO0);
-	rtl818x_iowrite8(priv, &priv->map->GPIO0, gpio & ~0x02);
+	rtl818x_iowrite8(priv, &priv->map->GPIO0, gpio & ~priv->rfkill_mask);
 	gpio = rtl818x_ioread8(priv, &priv->map->GPIO1);
 
-	return gpio & 0x02;
+	return gpio & priv->rfkill_mask;
 }
 
 void rtl8187_rfkill_init(struct ieee80211_hw *hw)

[070/151] x86: Fix bogus warning in apic_noop.apic_write()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Thomas Gleixner <tglx@linutronix.de>

commit a946d8f11f0da9cfc714248036fcfd3a794d1e27 upstream.

apic_noop is used to provide dummy apic functions. It's installed
when the CPU has no APIC or when the APIC is disabled on the kernel
command line.

The apic_noop implementation of apic_write() warns when the CPU has
an APIC or when the APIC is not disabled.

That's bogus. The warning should only happen when the CPU has an
APIC _AND_ the APIC is not disabled. apic_noop.apic_read() has the
correct check.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
LKML-Reference: <alpine.LFD.2.00.0912071255420.3089@localhost.localdomain>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/apic/apic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -246,7 +246,7 @@ static int modern_apic(void)
  */
 static void native_apic_write_dummy(u32 reg, u32 v)
 {
-	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+	WARN_ON_ONCE(cpu_has_apic && !disable_apic);
 }
 
 static u32 native_apic_read_dummy(u32 reg)

[071/151] mm: hugetlb: fix hugepage memory leak in mincore()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit 4f16fc107d9c9b8a72aa19b189a9216e90a7aaef upstream.

Most callers of pmd_none_or_clear_bad() check whether the target page is
in a hugepage or not, but mincore() and walk_page_range() do not check it.
 So if we use mincore() on a hugepage on x86 machine, the hugepage memory
is leaked as shown below.  This patch fixes it by extending mincore()
system call to support hugepages.

Details
=======
My test program (leak_mincore) works as follows:
 - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,)
 - read()/write() something on it,
 - call mincore() for first ten pages and printf() the values of *vec
 - munmap() and unlink() the file on hugetlbfs

Without my patch
----------------
$ cat /proc/meminfo| grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_mincore
vec[0] 0
vec[1] 0
vec[2] 0
vec[3] 0
vec[4] 0
vec[5] 0
vec[6] 0
vec[7] 0
vec[8] 0
vec[9] 0
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:      999
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs/
$

Return values in *vec from mincore() are set to 0, while the hugepage
should be in memory, and 1 hugepage is still accounted as used while
there is no file on hugetlbfs.

With my patch
-------------
$ cat /proc/meminfo| grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_mincore
vec[0] 1
vec[1] 1
vec[2] 1
vec[3] 1
vec[4] 1
vec[5] 1
vec[6] 1
vec[7] 1
vec[8] 1
vec[9] 1
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs/
$

Return value in *vec set to 1 and no memory leaks.

[akpm@linux-foundation.org: cleanup]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -14,6 +14,7 @@
 #include <linux/syscalls.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/hugetlb.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -72,6 +73,42 @@ static long do_mincore(unsigned long addr, unsigned char *vec, unsigned long pag
 	if (!vma || addr < vma->vm_start)
 		return -ENOMEM;
 
+#ifdef CONFIG_HUGETLB_PAGE
+	if (is_vm_hugetlb_page(vma)) {
+		struct hstate *h;
+		unsigned long nr_huge;
+		unsigned char present;
+
+		i = 0;
+		nr = min(pages, (vma->vm_end - addr) >> PAGE_SHIFT);
+		h = hstate_vma(vma);
+		nr_huge = ((addr + pages * PAGE_SIZE - 1) >> huge_page_shift(h))
+			  - (addr >> huge_page_shift(h)) + 1;
+		nr_huge = min(nr_huge,
+			      (vma->vm_end - addr) >> huge_page_shift(h));
+		while (1) {
+			/* hugepage always in RAM for now,
+			 * but generally it needs to be check */
+			ptep = huge_pte_offset(current->mm,
+					       addr & huge_page_mask(h));
+			present = !!(ptep &&
+				     !huge_pte_none(huge_ptep_get(ptep)));
+			while (1) {
+				vec[i++] = present;
+				addr += PAGE_SIZE;
+				/* reach buffer limit */
+				if (i == nr)
+					return nr;
+				/* check hugepage border */
+				if (!((addr & ~huge_page_mask(h))
+				      >> PAGE_SHIFT))
+					break;
+			}
+		}
+		return nr;
+	}
+#endif
+
 	/*
 	 * Calculate how many pages there are left in the last level of the
 	 * PTE array for our address.

[072/151] mm: hugetlb: fix hugepage memory leak in walk_page_range()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

commit d33b9f45bd24a6391bc05e2b5a13c1b5787ca9c2 upstream.

Most callers of pmd_none_or_clear_bad() check whether the target page is
in a hugepage or not, but walk_page_range() do not check it.  So if we
read /proc/pid/pagemap for the hugepage on x86 machine, the hugepage
memory is leaked as shown below.  This patch fixes it.

Details
=======
My test program (leak_pagemap) works as follows:
 - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,)
 - read()/write() something on it,
 - call page-types with option -p (walk around the page tables),
 - munmap() and unlink() the file on hugetlbfs

Without my patches
------------------
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_pagemap
[snip output]
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:      900
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs/
$

100 hugepages are accounted as used while there is no file on hugetlbfs.

With my patches
---------------
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ./leak_pagemap
[snip output]
$ cat /proc/meminfo |grep "HugePage"
HugePages_Total:    1000
HugePages_Free:     1000
HugePages_Rsvd:        0
HugePages_Surp:        0
$ ls /hugetlbfs
$

No memory leaks.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 mm/pagewalk.c |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -1,6 +1,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 
 static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			  struct mm_walk *walk)
@@ -107,6 +108,7 @@ int walk_page_range(unsigned long addr, 
 	pgd_t *pgd;
 	unsigned long next;
 	int err = 0;
+	struct vm_area_struct *vma;
 
 	if (addr >= end)
 		return err;
@@ -117,11 +119,22 @@ int walk_page_range(unsigned long addr, 
 	pgd = pgd_offset(walk->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
+
+		/* skip hugetlb vma to avoid hugepage PMD being cleared
+		 * in pmd_none_or_clear_bad(). */
+		vma = find_vma(walk->mm, addr);
+		if (vma && is_vm_hugetlb_page(vma)) {
+			if (vma->vm_end < next)
+				next = vma->vm_end;
+			continue;
+		}
+
 		if (pgd_none_or_clear_bad(pgd)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
+			pgd++;
 			continue;
 		}
 		if (walk->pgd_entry)
@@ -131,7 +144,8 @@ int walk_page_range(unsigned long addr, 
 			err = walk_pud_range(pgd, addr, next, walk);
 		if (err)
 			break;
-	} while (pgd++, addr = next, addr != end);
+		pgd++;
+	} while (addr = next, addr != end);
 
 	return err;
 }

[073/151] powerpc/windfarm: Add detection for second cpu pump

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Bolko Maass <krautilein@gmx.de>

commit 529586dc39b0ec47c6290c4e7bed6ea3ffd1d8fb upstream.

Windfarm SMU control is explicitly missing support for a second CPU pump in G5 PowerMacs. Such machines actually exist  (specifically Quads with a second pump), so this patch adds detection for it.

Signed-off by: Bolko Maass <bmaass@math.uni-bremen.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/macintosh/windfarm_smu_controls.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/drivers/macintosh/windfarm_smu_controls.c
+++ b/drivers/macintosh/windfarm_smu_controls.c
@@ -202,6 +202,8 @@ static struct smu_fan_control *smu_fan_c
 		fct->ctrl.name = "cpu-front-fan-1";
 	else if (!strcmp(l, "CPU A PUMP"))
 		fct->ctrl.name = "cpu-pump-0";
+	else if (!strcmp(l, "CPU B PUMP"))
+		fct->ctrl.name = "cpu-pump-1";
 	else if (!strcmp(l, "Slots Fan") || !strcmp(l, "Slots fan") ||
 		 !strcmp(l, "EXPANSION SLOTS INTAKE"))
 		fct->ctrl.name = "slots-fan";

[074/151] powerpc/therm_adt746x: Record pwm invert bit at module load time]

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Darrick J. Wong <djwong@us.ibm.com>

commit 1496e89ae2a0962748e55165a590fa3209c6f158 upstream.

In commit 0512a9a8e277a9de2820211eef964473b714ae65, we unilaterally zero the
"pwm invert" bit in the fan behavior configuration register.  On my PowerBook
G4, this results in the fans going to full speed at low temperature and
shutting off at high temperature because the pwm invert bit is supposed to be
set.

Therefore, record the pwm invert bit at driver load time, and write the bit
into the fan behavior control register.  This restores correct behavior on my
PBG4 and should work around the bit being set to the wrong value after
suspend/resume (which is what the original patch was trying to fix).  It also
fixes a minor omission where the pwm invert bit correction is NOT performed
when switching into automatic mode.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/macintosh/therm_adt746x.c |   13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -79,6 +79,7 @@ struct thermostat {
 	u8			limits[3];
 	int			last_speed[2];
 	int			last_var[2];
+	int			pwm_inv[2];
 };
 
 static enum {ADT7460, ADT7467} therm_type;
@@ -229,19 +230,23 @@ static void write_fan_speed(struct therm
 	
 	if (speed >= 0) {
 		manual = read_reg(th, MANUAL_MODE[fan]);
+		manual &= ~INVERT_MASK;
 		write_reg(th, MANUAL_MODE[fan],
-			(manual|MANUAL_MASK) & (~INVERT_MASK));
+			manual | MANUAL_MASK | th->pwm_inv[fan]);
 		write_reg(th, FAN_SPD_SET[fan], speed);
 	} else {
 		/* back to automatic */
 		if(therm_type == ADT7460) {
 			manual = read_reg(th,
 				MANUAL_MODE[fan]) & (~MANUAL_MASK);
-
+			manual &= ~INVERT_MASK;
+			manual |= th->pwm_inv[fan];
 			write_reg(th,
 				MANUAL_MODE[fan], manual|REM_CONTROL[fan]);
 		} else {
 			manual = read_reg(th, MANUAL_MODE[fan]);
+			manual &= ~INVERT_MASK;
+			manual |= th->pwm_inv[fan];
 			write_reg(th, MANUAL_MODE[fan], manual&(~AUTO_MASK));
 		}
 	}
@@ -418,6 +423,10 @@ static int probe_thermostat(struct i2c_c
 
 	thermostat = th;
 
+	/* record invert bit status because fw can corrupt it after suspend */
+	th->pwm_inv[0] = read_reg(th, MANUAL_MODE[0]) & INVERT_MASK;
+	th->pwm_inv[1] = read_reg(th, MANUAL_MODE[1]) & INVERT_MASK;
+
 	/* be sure to really write fan speed the first time */
 	th->last_speed[0] = -2;
 	th->last_speed[1] = -2;

[075/151] powerpc: Fix usage of 64-bit instruction in 32-bit altivec code

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Benjamin Herrenschmidt <benh@kernel.crashing.org>

commit e090aa80321b64c3b793f3b047e31ecf1af9538d upstream.

e821ea70f3b4873b50056a1e0f74befed1014c09 introduced a bug by copying
some 64-bit originated code as-is to be used by both 32 and 64-bit
but this code contains a 64-bit ony "cmpdi" instruction.

This changes it to cmpwi, which is fine since VRSAVE can only contains
a 32-bit value anyway.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/powerpc/kernel/vector.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -58,7 +58,7 @@ _GLOBAL(load_up_altivec)
 	 * all 1's
 	 */
 	mfspr	r4,SPRN_VRSAVE
-	cmpdi	0,r4,0
+	cmpwi	0,r4,0
 	bne+	1f
 	li	r4,-1
 	mtspr	SPRN_VRSAVE,r4

[076/151] drm/radeon/kms: Add quirk for HIS X1300 board

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alex Deucher <alexdeucher@gmail.com>

commit 4e3f9b78ff917cc5c833858fdb5d96bc262e0bf3 upstream.

Board is DVI+VGA, not DVI+DVI

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/radeon/radeon_atombios.c |    8 ++++++++
 1 file changed, 8 insertions(+)

--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -135,6 +135,14 @@ static bool radeon_atom_apply_quirks(str
 		}
 	}
 
+	/* HIS X1300 is DVI+VGA, not DVI+DVI */
+	if ((dev->pdev->device == 0x7146) &&
+	    (dev->pdev->subsystem_vendor == 0x17af) &&
+	    (dev->pdev->subsystem_device == 0x2058)) {
+		if (supported_device == ATOM_DEVICE_DFP1_SUPPORT)
+			return false;
+	}
+
 	/* Funky macbooks */
 	if ((dev->pdev->device == 0x71C5) &&
 	    (dev->pdev->subsystem_vendor == 0x106b) &&

[077/151] drm/radeon/kms: handle vblanks properly with dpms on

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alex Deucher <alexdeucher@gmail.com>

commit 500b758725314ab1b5316eb0caa5b0fa26740e6b upstream.

avivo chips

Copied from pre-avivo code.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/radeon/atombios_crtc.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -241,6 +241,7 @@ void atombios_crtc_dpms(struct drm_crtc 
 {
 	struct drm_device *dev = crtc->dev;
 	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -248,20 +249,19 @@ void atombios_crtc_dpms(struct drm_crtc 
 		if (ASIC_IS_DCE3(rdev))
 			atombios_enable_crtc_memreq(crtc, 1);
 		atombios_blank_crtc(crtc, 0);
+		drm_vblank_post_modeset(dev, radeon_crtc->crtc_id);
+		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
+		drm_vblank_pre_modeset(dev, radeon_crtc->crtc_id);
 		atombios_blank_crtc(crtc, 1);
 		if (ASIC_IS_DCE3(rdev))
 			atombios_enable_crtc_memreq(crtc, 0);
 		atombios_enable_crtc(crtc, 0);
 		break;
 	}
-
-	if (mode != DRM_MODE_DPMS_OFF) {
-		radeon_crtc_load_lut(crtc);
-	}
 }
 
 static void

[078/151] drm/radeon/kms: fix legacy crtc2 dpms

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alex Deucher <alexdeucher@gmail.com>

commit 8de21525439e6b5bb8d8c81e49094d867bf82f6d upstream.

noticed by Matthijs Kooijman on fdo bug 22140

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/radeon/radeon_legacy_crtc.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -292,8 +292,7 @@ void radeon_crtc_dpms(struct drm_crtc *c
 	uint32_t mask;
 
 	if (radeon_crtc->crtc_id)
-		mask = (RADEON_CRTC2_EN |
-			RADEON_CRTC2_DISP_DIS |
+		mask = (RADEON_CRTC2_DISP_DIS |
 			RADEON_CRTC2_VSYNC_DIS |
 			RADEON_CRTC2_HSYNC_DIS |
 			RADEON_CRTC2_DISP_REQ_EN_B);
@@ -305,7 +304,7 @@ void radeon_crtc_dpms(struct drm_crtc *c
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
 		if (radeon_crtc->crtc_id)
-			WREG32_P(RADEON_CRTC2_GEN_CNTL, RADEON_CRTC2_EN, ~mask);
+			WREG32_P(RADEON_CRTC2_GEN_CNTL, RADEON_CRTC2_EN, ~(RADEON_CRTC2_EN | mask));
 		else {
 			WREG32_P(RADEON_CRTC_GEN_CNTL, RADEON_CRTC_EN, ~(RADEON_CRTC_EN |
 									 RADEON_CRTC_DISP_REQ_EN_B));
@@ -319,7 +318,7 @@ void radeon_crtc_dpms(struct drm_crtc *c
 	case DRM_MODE_DPMS_OFF:
 		drm_vblank_pre_modeset(dev, radeon_crtc->crtc_id);
 		if (radeon_crtc->crtc_id)
-			WREG32_P(RADEON_CRTC2_GEN_CNTL, mask, ~mask);
+			WREG32_P(RADEON_CRTC2_GEN_CNTL, mask, ~(RADEON_CRTC2_EN | mask));
 		else {
 			WREG32_P(RADEON_CRTC_GEN_CNTL, RADEON_CRTC_DISP_REQ_EN_B, ~(RADEON_CRTC_EN |
 										    RADEON_CRTC_DISP_REQ_EN_B));

[079/151] drm/radeon/kms: fix vram setup on rs600

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alex Deucher <alexdeucher@gmail.com>

commit 722f29434e72188b2d20f9b41f4b5952073ed568 upstream.

also fix up rs690 mem width.

should fix fdo bug 25408

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/radeon/rs600.c |    6 ++++++
 drivers/gpu/drm/radeon/rs690.c |   10 ++--------
 2 files changed, 8 insertions(+), 8 deletions(-)

--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -315,6 +315,12 @@ void rs600_vram_info(struct radeon_devic
 	/* FIXME: to do or is these values sane ? */
 	rdev->mc.vram_is_ddr = true;
 	rdev->mc.vram_width = 128;
+
+	rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE);
+	rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+
+	rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0);
+	rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0);
 }
 
 void rs600_bandwidth_update(struct radeon_device *rdev)
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -131,19 +131,13 @@ void rs690_pm_info(struct radeon_device 
 
 void rs690_vram_info(struct radeon_device *rdev)
 {
-	uint32_t tmp;
 	fixed20_12 a;
 
 	rs400_gart_adjust_size(rdev);
 	/* DDR for all card after R300 & IGP */
 	rdev->mc.vram_is_ddr = true;
-	/* FIXME: is this correct for RS690/RS740 ? */
-	tmp = RREG32(RADEON_MEM_CNTL);
-	if (tmp & R300_MEM_NUM_CHANNELS_MASK) {
-		rdev->mc.vram_width = 128;
-	} else {
-		rdev->mc.vram_width = 64;
-	}
+	rdev->mc.vram_width = 128;
+
 	rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE);
 	rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
 

[080/151] drm/radeon/kms: rs6xx/rs740: clamp vram to aperture size

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alex Deucher <alexdeucher@gmail.com>

commit 0088dbdb809e8799cb8f26da5ac64b15201fa99d upstream.

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/radeon/rs600.c |    9 ++++++---
 drivers/gpu/drm/radeon/rs690.c |    9 ++++++++-
 2 files changed, 14 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -301,9 +301,7 @@ int rs600_mc_wait_for_idle(struct radeon
 
 void rs600_gpu_init(struct radeon_device *rdev)
 {
-	/* FIXME: HDP same place on rs600 ? */
 	r100_hdp_reset(rdev);
-	/* FIXME: is this correct ? */
 	r420_pipes_init(rdev);
 	/* Wait for mc idle */
 	if (rs600_mc_wait_for_idle(rdev))
@@ -312,7 +310,6 @@ void rs600_gpu_init(struct radeon_device
 
 void rs600_vram_info(struct radeon_device *rdev)
 {
-	/* FIXME: to do or is these values sane ? */
 	rdev->mc.vram_is_ddr = true;
 	rdev->mc.vram_width = 128;
 
@@ -321,6 +318,12 @@ void rs600_vram_info(struct radeon_devic
 
 	rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0);
 	rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0);
+
+	if (rdev->mc.mc_vram_size > rdev->mc.aper_size)
+		rdev->mc.mc_vram_size = rdev->mc.aper_size;
+
+	if (rdev->mc.real_vram_size > rdev->mc.aper_size)
+		rdev->mc.real_vram_size = rdev->mc.aper_size;
 }
 
 void rs600_bandwidth_update(struct radeon_device *rdev)
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -134,7 +134,7 @@ void rs690_vram_info(struct radeon_devic
 	fixed20_12 a;
 
 	rs400_gart_adjust_size(rdev);
-	/* DDR for all card after R300 & IGP */
+
 	rdev->mc.vram_is_ddr = true;
 	rdev->mc.vram_width = 128;
 
@@ -143,6 +143,13 @@ void rs690_vram_info(struct radeon_devic
 
 	rdev->mc.aper_base = drm_get_resource_start(rdev->ddev, 0);
 	rdev->mc.aper_size = drm_get_resource_len(rdev->ddev, 0);
+
+	if (rdev->mc.mc_vram_size > rdev->mc.aper_size)
+		rdev->mc.mc_vram_size = rdev->mc.aper_size;
+
+	if (rdev->mc.real_vram_size > rdev->mc.aper_size)
+		rdev->mc.real_vram_size = rdev->mc.aper_size;
+
 	rs690_pm_info(rdev);
 	/* FIXME: we should enforce default clock in case GPU is not in
 	 * default setup

[081/151] drm/ttm: Fix build failure due to missing struct page

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Martin Michlmayr <tbm@cyrius.com>

commit c3a73ba13bac7fd96030f39202b2d37fb19c46a6 upstream.

drm/ttm fails to build on MIPS because "struct page" is not known:
| In file included from drivers/gpu/drm/ttm/ttm_memory.c:28:
| include/drm/ttm/ttm_memory.h:154: warning: 'struct page' declared inside parameter list
| include/drm/ttm/ttm_memory.h:154: warning: its scope is only this definition or declaration, which is probably not what you want
| include/drm/ttm/ttm_memory.h:156: warning: 'struct page' declared inside parameter list
| drivers/gpu/drm/ttm/ttm_memory.c:540: error: conflicting types for 'ttm_mem_global_alloc_page'
| include/drm/ttm/ttm_memory.h:154: error: previous declaration of 'ttm_mem_global_alloc_page' was here
| drivers/gpu/drm/ttm/ttm_memory.c:561: error: conflicting types for 'ttm_mem_global_free_page'
| include/drm/ttm/ttm_memory.h:156: error: previous declaration of 'ttm_mem_global_free_page' was here

Signed-off-by: Martin Michlmayr <tbm@cyrius.com>
Acked-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/drm/ttm/ttm_memory.h |    1 +
 1 file changed, 1 insertion(+)

--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -33,6 +33,7 @@
 #include <linux/wait.h>
 #include <linux/errno.h>
 #include <linux/kobject.h>
+#include <linux/mm.h>
 
 /**
  * struct ttm_mem_shrink - callback to shrink TTM memory usage.

[082/151] drm/i915: Set the error code after failing to insert new offset into mm ht.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Chris Wilson <chris@chris-wilson.co.uk>

commit 5618ca6abc2d6f475b258badc017a5254cf43d1b upstream.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/i915/i915_gem.c |    1 +
 1 file changed, 1 insertion(+)

--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1288,6 +1288,7 @@ i915_gem_create_mmap_offset(struct drm_g
 	list->hash.key = list->file_offset_node->start;
 	if (drm_ht_insert_item(&mm->offset_hash, &list->hash)) {
 		DRM_ERROR("failed to add to map hash\n");
+		ret = -ENOMEM;
 		goto out_free_mm;
 	}
 

[083/151] drm/i915: Add the missing clonemask for display port on Ironlake

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhao Yakui <yakui.zhao@intel.com>

commit 652af9d74e1a3a10bb10f0d8e8f42ddac26bbc1a upstream.

Add the missing clonemask for display port on Ironlake.

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/i915/intel_dp.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1254,11 +1254,11 @@ intel_dp_init(struct drm_device *dev, in
 	else
 		intel_output->type = INTEL_OUTPUT_DISPLAYPORT;
 
-	if (output_reg == DP_B)
+	if (output_reg == DP_B || output_reg == PCH_DP_B)
 		intel_output->clone_mask = (1 << INTEL_DP_B_CLONE_BIT);
-	else if (output_reg == DP_C)
+	else if (output_reg == DP_C || output_reg == PCH_DP_C)
 		intel_output->clone_mask = (1 << INTEL_DP_C_CLONE_BIT);
-	else if (output_reg == DP_D)
+	else if (output_reg == DP_D || output_reg == PCH_DP_D)
 		intel_output->clone_mask = (1 << INTEL_DP_D_CLONE_BIT);
 
 	if (IS_eDP(intel_output)) {

[084/151] xen/xenbus: make DEVICE_ATTR()s static

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

commit db05fed0ad72f264e39bcb366795f7367384ec92 upstream.

They don't need to be global, and may cause linker clashes.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/xenbus/xenbus_probe.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -454,21 +454,21 @@ static ssize_t xendev_show_nodename(stru
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->nodename);
 }
-DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL);
+static DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL);
 
 static ssize_t xendev_show_devtype(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_xenbus_device(dev)->devicetype);
 }
-DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL);
+static DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL);
 
 static ssize_t xendev_show_modalias(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "xen:%s\n", to_xenbus_device(dev)->devicetype);
 }
-DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL);
+static DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL);
 
 int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,

[085/151] xen: re-register runstate area earlier on resume.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <Ian.Campbell@citrix.com>

commit be012920ecba161ad20303a3f6d9e96c58cf97c7 upstream.

This is necessary to ensure the runstate area is available to
xen_sched_clock before any calls to printk which will require it in
order to provide a timestamp.

I chose to pull the xen_setup_runstate_info out of xen_time_init into
the caller in order to maintain parity with calling
xen_setup_runstate_info separately from calling xen_time_resume.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/enlighten.c |    2 ++
 arch/x86/xen/time.c      |    5 ++---
 arch/x86/xen/xen-ops.h   |    1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -148,6 +148,8 @@ void xen_vcpu_restore(void)
 			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
 				BUG();
 
+			xen_setup_runstate_info(cpu);
+
 			xen_vcpu_setup(cpu);
 
 			if (other_cpu &&
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -100,7 +100,7 @@ bool xen_vcpu_stolen(int vcpu)
 	return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
 }
 
-static void setup_runstate_info(int cpu)
+void xen_setup_runstate_info(int cpu)
 {
 	struct vcpu_register_runstate_memory_area area;
 
@@ -442,8 +442,6 @@ void xen_setup_timer(int cpu)
 
 	evt->cpumask = cpumask_of(cpu);
 	evt->irq = irq;
-
-	setup_runstate_info(cpu);
 }
 
 void xen_teardown_timer(int cpu)
@@ -494,6 +492,7 @@ __init void xen_time_init(void)
 
 	setup_force_cpu_cap(X86_FEATURE_TSC);
 
+	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_setup_cpu_clockevents();
 }
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -41,6 +41,7 @@ void __init xen_build_dynamic_phys_to_ma
 
 void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
+void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
 cycle_t xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);

[086/151] xen: restore runstate_info even if !have_vcpu_info_placement

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

commit 3905bb2aa7bb801b31946b37a4635ebac4009051 upstream.

Even if have_vcpu_info_placement is not set, we still need to set up
the runstate area on each resumed vcpu.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/enlighten.c |   25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -138,26 +138,23 @@ static void xen_vcpu_setup(int cpu)
  */
 void xen_vcpu_restore(void)
 {
-	if (have_vcpu_info_placement) {
-		int cpu;
+	int cpu;
 
-		for_each_online_cpu(cpu) {
-			bool other_cpu = (cpu != smp_processor_id());
+	for_each_online_cpu(cpu) {
+		bool other_cpu = (cpu != smp_processor_id());
 
-			if (other_cpu &&
-			    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
-				BUG();
+		if (other_cpu &&
+		    HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+			BUG();
 
-			xen_setup_runstate_info(cpu);
+		xen_setup_runstate_info(cpu);
 
+		if (have_vcpu_info_placement)
 			xen_vcpu_setup(cpu);
 
-			if (other_cpu &&
-			    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
-				BUG();
-		}
-
-		BUG_ON(!have_vcpu_info_placement);
+		if (other_cpu &&
+		    HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+			BUG();
 	}
 }
 

[087/151] xen: correctly restore pfn_to_mfn_list_list after resume

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit fa24ba62ea2869308ffc9f0b286ac9650b4ca6cb upstream.

pvops kernels >= 2.6.30 can currently only be saved and restored once. The
second attempt to save results in:

    ERROR Internal error: Frame# in pfn-to-mfn frame list is not in pseudophys
    ERROR Internal error: entry 0: p2m_frame_list[0] is 0xf2c2c2c2, max 0x120000
    ERROR Internal error: Failed to map/save the p2m frame list

I finally narrowed it down to:

    commit cdaead6b4e657f960d6d6f9f380e7dfeedc6a09b
        Author: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
        Date:   Fri Feb 27 15:34:59 2009 -0800

            xen: split construction of p2m mfn tables from registration

            Build the p2m_mfn_list_list early with the rest of the p2m table, but
            register it later when the real shared_info structure is in place.

            Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

The unforeseen side-effect of this change was to cause the mfn list list to not
be rebuilt on resume. Prior to this change it would have been rebuilt via
xen_post_suspend() -> xen_setup_shared_info() -> xen_setup_mfn_list_list().

Fix by explicitly calling xen_build_mfn_list_list() from xen_post_suspend().

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/mmu.c     |    2 +-
 arch/x86/xen/suspend.c |    2 ++
 arch/x86/xen/xen-ops.h |    1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -185,7 +185,7 @@ static inline unsigned p2m_index(unsigne
 }
 
 /* Build the parallel p2m_top_mfn structures */
-static void __init xen_build_mfn_list_list(void)
+void xen_build_mfn_list_list(void)
 {
 	unsigned pfn, idx;
 
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -27,6 +27,8 @@ void xen_pre_suspend(void)
 
 void xen_post_suspend(int suspend_cancelled)
 {
+	xen_build_mfn_list_list();
+
 	xen_setup_shared_info();
 
 	if (suspend_cancelled) {
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -25,6 +25,7 @@ extern struct shared_info *HYPERVISOR_sh
 
 void xen_setup_mfn_list_list(void);
 void xen_setup_shared_info(void);
+void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);

[088/151] xen: register timer interrupt with IRQF_TIMER

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit f350c7922faad3397c98c81a9e5658f5a1ef0214 upstream.

Otherwise the timer is disabled by dpm_suspend_noirq() which in turn prevents
correct operation of stop_machine on multi-processor systems and breaks
suspend.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/time.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -434,7 +434,7 @@ void xen_setup_timer(int cpu)
 		name = "<timer kasprintf failed>";
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
-				      IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+				      IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER,
 				      name, NULL);
 
 	evt = &per_cpu(xen_clock_events, cpu);

[089/151] xen: register runstate on secondary CPUs

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit 028896721ac04f6fa0697f3ecac3f98761746363 upstream.

The commit "xen: re-register runstate area earlier on resume" caused us
to never try and setup the runstate area for secondary CPUs. Ensure that
we do this...

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/smp.c |    1 +
 1 file changed, 1 insertion(+)

--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -295,6 +295,7 @@ static int __cpuinit xen_cpu_up(unsigned
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
 #endif
+	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_init_lock_cpu(cpu);
 

[090/151] xen: dont call dpm_resume_noirq() with interrupts disabled.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

commit 922cc38ab71d1360978e65207e4a4f4988987127 upstream.

dpm_resume_noirq() takes a mutex, so it can't be called from a no-interrupt
context.  Don't call it from within the stop-machine function, but just
afterwards, since we're resuming anyway, regardless of what happened.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/manage.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -43,7 +43,6 @@ static int xen_suspend(void *data)
 	if (err) {
 		printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n",
 			err);
-		dpm_resume_noirq(PMSG_RESUME);
 		return err;
 	}
 
@@ -69,7 +68,6 @@ static int xen_suspend(void *data)
 	}
 
 	sysdev_resume();
-	dpm_resume_noirq(PMSG_RESUME);
 
 	return 0;
 }
@@ -108,6 +106,9 @@ static void do_suspend(void)
 	}
 
 	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
+
+	dpm_resume_noirq(PMSG_RESUME);
+
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
 		goto out;
@@ -119,8 +120,6 @@ static void do_suspend(void)
 	} else
 		xs_suspend_cancel();
 
-	dpm_resume_noirq(PMSG_RESUME);
-
 resume_devices:
 	dpm_resume_end(PMSG_RESUME);
 

[091/151] xen: register runstate info for boot CPU early

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

commit 499d19b82b586aef18727b9ae1437f8f37b66e91 upstream.

printk timestamping uses sched_clock, which in turn relies on runstate
info under Xen.  So make sure we set it up before any printks can
be called.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/enlighten.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1181,6 +1181,8 @@ asmlinkage void __init xen_start_kernel(
 
 	xen_raw_console_write("about to get started...\n");
 
+	xen_setup_runstate_info(0);
+
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();

[092/151] xen: call clock resume notifier on all CPUs

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <Ian.Campbell@citrix.com>

commit f6eafe3665bcc374c66775d58312d1c06c55303f upstream.

tick_resume() is never called on secondary processors. Presumably this
is because they are offlined for suspend on native and so this is
normally taken care of in the CPU onlining path. Under Xen we keep all
CPUs online over a suspend.

This patch papers over the issue for me but I will investigate a more
generic, less hacky, way of doing to the same.

tick_suspend is also only called on the boot CPU which I presume should
be fixed too.

Signed-off-by: Ian Campbell <Ian.Campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/suspend.c |   15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <linux/clockchips.h>
 
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
@@ -46,7 +47,19 @@ void xen_post_suspend(int suspend_cancel
 
 }
 
+static void xen_vcpu_notify_restore(void *data)
+{
+	unsigned long reason = (unsigned long)data;
+
+	/* Boot processor notified via generic timekeeping_resume() */
+	if ( smp_processor_id() == 0)
+		return;
+
+	clockevents_notify(reason, NULL);
+}
+
 void xen_arch_resume(void)
 {
-	/* nothing */
+	smp_call_function(xen_vcpu_notify_restore,
+			       (void *)CLOCK_EVT_NOTIFY_RESUME, 1);
 }

[093/151] xen: improve error handling in do_suspend.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit 65f63384b391bf4d384327d8a7c6de9860290b5c upstream.

The existing error handling has a few issues:
- If freeze_processes() fails it exits with shutting_down = SHUTDOWN_SUSPEND.
- If dpm_suspend_noirq() fails it exits without resuming xenbus.
- If stop_machine() fails it exits without resuming xenbus or calling
  dpm_resume_end().
- xs_suspend()/xs_resume() and dpm_suspend_noirq()/dpm_resume_noirq() were not
  nested in the obvious way.

Fix by ensuring each failure case goto's the correct label. Treat a failure of
stop_machine() as a cancelled suspend in order to follow the correct resume
path.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/manage.c |   20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -86,32 +86,32 @@ static void do_suspend(void)
 	err = freeze_processes();
 	if (err) {
 		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
-		return;
+		goto out;
 	}
 #endif
 
 	err = dpm_suspend_start(PMSG_SUSPEND);
 	if (err) {
 		printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", err);
-		goto out;
+		goto out_thaw;
 	}
 
-	printk(KERN_DEBUG "suspending xenstore...\n");
-	xs_suspend();
-
 	err = dpm_suspend_noirq(PMSG_SUSPEND);
 	if (err) {
 		printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err);
-		goto resume_devices;
+		goto out_resume;
 	}
 
+	printk(KERN_DEBUG "suspending xenstore...\n");
+	xs_suspend();
+
 	err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
 
 	dpm_resume_noirq(PMSG_RESUME);
 
 	if (err) {
 		printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
-		goto out;
+		cancelled = 1;
 	}
 
 	if (!cancelled) {
@@ -120,15 +120,17 @@ static void do_suspend(void)
 	} else
 		xs_suspend_cancel();
 
-resume_devices:
+out_resume:
 	dpm_resume_end(PMSG_RESUME);
 
 	/* Make sure timer events get retriggered on all CPUs */
 	clock_was_set();
-out:
+
+out_thaw:
 #ifdef CONFIG_PREEMPT
 	thaw_processes();
 #endif
+out:
 	shutting_down = SHUTDOWN_INVALID;
 }
 #endif	/* CONFIG_PM_SLEEP */

[094/151] xen: dont leak IRQs over suspend/resume.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit fed5ea87e02aaf902ff38c65b4514233db03dc09 upstream.

On resume irq_info[*].evtchn is reset to 0 since event channel mappings
are not preserved over suspend/resume. The other contents of irq_info
is preserved to allow rebind_evtchn_irq() to function.

However when a device resumes it will try to unbind from the
previous IRQ (e.g.  blkfront goes blkfront_resume() -> blkif_free() ->
unbind_from_irqhandler() -> unbind_from_irq()). This will fail due to the
check for VALID_EVTCHN in unbind_from_irq() and the IRQ is leaked. The
device will then continue to resume and allocate a new IRQ, eventually
leading to find_unbound_irq() panic()ing.

Fix this by changing unbind_from_irq() to handle teardown of interrupts
which have type!=IRQT_UNBOUND but are not currently bound to a specific
event channel.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/events.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -474,6 +474,9 @@ static void unbind_from_irq(unsigned int
 		bind_evtchn_to_cpu(evtchn, 0);
 
 		evtchn_to_irq[evtchn] = -1;
+	}
+
+	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
 		dynamic_irq_cleanup(irq);

[095/151] xen: use iret for return from 64b kernel to 32b usermode

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>

commit 6aaf5d633bb6cead81b396d861d7bae4b9a0ba7e upstream.

If Xen wants to return to a 32b usermode with sysret it must use the
right form.  When using VCGF_in_syscall to trigger this, it looks at
the code segment and does a 32b sysret if it is FLAT_USER_CS32.
However, this is different from __USER32_CS, so it fails to return
properly if we use the normal Linux segment.

So avoid the whole mess by dropping VCGF_in_syscall and simply use
plain iret to return to usermode.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/xen/xen-asm_64.S |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -96,7 +96,7 @@ ENTRY(xen_sysret32)
 	pushq $__USER32_CS
 	pushq %rcx
 
-	pushq $VGCF_in_syscall
+	pushq $0
 1:	jmp hypercall_iret
 ENDPATCH(xen_sysret32)
 RELOC(xen_sysret32, 1b+1)
@@ -151,7 +151,7 @@ ENTRY(xen_syscall32_target)
 ENTRY(xen_sysenter_target)
 	lea 16(%rsp), %rsp	/* strip %rcx, %r11 */
 	mov $-ENOSYS, %rax
-	pushq $VGCF_in_syscall
+	pushq $0
 	jmp hypercall_iret
 ENDPROC(xen_syscall32_target)
 ENDPROC(xen_sysenter_target)

[096/151] xen: explicitly create/destroy stop_machine workqueues outside suspend/resume region.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit b4606f2165153833247823e8c04c5e88cb3d298b upstream.

I have observed cases where the implicit stop_machine_destroy() done by
stop_machine() hangs while destroying the workqueues, specifically in
kthread_stop(). This seems to be because timer ticks are not restarted
until after stop_machine() returns.

Fortunately stop_machine provides a facility to pre-create/post-destroy
the workqueues so use this to ensure that workqueues are only destroyed
after everything is really up and running again.

I only actually observed this failure with 2.6.30. It seems that newer
kernels are somehow more robust against doing kthread_stop() without timer
interrupts (I tried some backports of some likely looking candidates but
did not track down the commit which added this robustness). However this
change seems like a reasonable belt&braces thing to do.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/manage.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -79,6 +79,12 @@ static void do_suspend(void)
 
 	shutting_down = SHUTDOWN_SUSPEND;
 
+	err = stop_machine_create();
+	if (err) {
+		printk(KERN_ERR "xen suspend: failed to setup stop_machine %d\n", err);
+		goto out;
+	}
+
 #ifdef CONFIG_PREEMPT
 	/* If the kernel is preemptible, we need to freeze all the processes
 	   to prevent them from being in the middle of a pagetable update
@@ -86,7 +92,7 @@ static void do_suspend(void)
 	err = freeze_processes();
 	if (err) {
 		printk(KERN_ERR "xen suspend: freeze failed %d\n", err);
-		goto out;
+		goto out_destroy_sm;
 	}
 #endif
 
@@ -129,7 +135,11 @@ out_resume:
 out_thaw:
 #ifdef CONFIG_PREEMPT
 	thaw_processes();
+
+out_destroy_sm:
 #endif
+	stop_machine_destroy();
+
 out:
 	shutting_down = SHUTDOWN_INVALID;
 }

[097/151] Xen balloon: fix totalram_pages counting.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Gianluca Guida <gianluca.guida@citrix.com>

commit 3d65c9488cadd2f11bd4d60c7266e639ece5d0d6 upstream.

Change totalram_pages when a single page is added/removed to the
ballooned list. This avoid totalram_pages to be set erroneously to
max_pfn at boot.

Signed-off-by: Gianluca Guida <gianluca.guida@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/balloon.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -136,6 +136,8 @@ static void balloon_append(struct page *
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
 	}
+
+	totalram_pages--;
 }
 
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
@@ -156,6 +158,8 @@ static struct page *balloon_retrieve(voi
 	else
 		balloon_stats.balloon_low--;
 
+	totalram_pages++;
+
 	return page;
 }
 
@@ -260,7 +264,6 @@ static int increase_reservation(unsigned
 	}
 
 	balloon_stats.current_pages += nr_pages;
-	totalram_pages = balloon_stats.current_pages;
 
  out:
 	spin_unlock_irqrestore(&balloon_lock, flags);
@@ -323,7 +326,6 @@ static int decrease_reservation(unsigned
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;
-	totalram_pages = balloon_stats.current_pages;
 
 	spin_unlock_irqrestore(&balloon_lock, flags);
 
@@ -422,7 +424,6 @@ static int __init balloon_init(void)
 	pr_info("xen_balloon: Initialising balloon driver.\n");
 
 	balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
-	totalram_pages   = balloon_stats.current_pages;
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;

[098/151] xen: try harder to balloon up under memory pressure.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Ian Campbell <ian.campbell@citrix.com>

commit bc2c0303226ec716854d3c208c7f84fe7aa35cd7 upstream.

Currently if the balloon driver is unable to increase the guest's
reservation it assumes the failure was due to reaching its full
allocation, gives up on the ballooning operation and records the limit
it reached as the "hard limit". The driver will not try again until
the target is set again (even to the same value).

However it is possible that ballooning has in fact failed due to
memory pressure in the host and therefore it is desirable to keep
attempting to reach the target in case memory becomes available. The
most likely scenario is that some guests are ballooning down while
others are ballooning up and therefore there is temporary memory
pressure while things stabilise. You would not expect a well behaved
toolstack to ask a domain to balloon to more than its allocation nor
would you expect it to deliberately over-commit memory by setting
balloon targets which exceed the total host memory.

This patch drops the concept of a hard limit and causes the balloon
driver to retry increasing the reservation on a timer in the same
manner as when decreasing the reservation.

Also if we partially succeed in increasing the reservation
(i.e. receive less pages than we asked for) then we may as well keep
those pages rather than returning them to Xen.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/xen/balloon.c |   31 +++++--------------------------
 1 file changed, 5 insertions(+), 26 deletions(-)

--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -66,8 +66,6 @@ struct balloon_stats {
 	/* We aim for 'current allocation' == 'target allocation'. */
 	unsigned long current_pages;
 	unsigned long target_pages;
-	/* We may hit the hard limit in Xen. If we do then we remember it. */
-	unsigned long hard_limit;
 	/*
 	 * Drivers may alter the memory reservation independently, but they
 	 * must inform the balloon driver so we avoid hitting the hard limit.
@@ -185,7 +183,7 @@ static void balloon_alarm(unsigned long 
 
 static unsigned long current_target(void)
 {
-	unsigned long target = min(balloon_stats.target_pages, balloon_stats.hard_limit);
+	unsigned long target = balloon_stats.target_pages;
 
 	target = min(target,
 		     balloon_stats.current_pages +
@@ -221,23 +219,10 @@ static int increase_reservation(unsigned
 	set_xen_guest_handle(reservation.extent_start, frame_list);
 	reservation.nr_extents = nr_pages;
 	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
-	if (rc < nr_pages) {
-		if (rc > 0) {
-			int ret;
-
-			/* We hit the Xen hard limit: reprobe. */
-			reservation.nr_extents = rc;
-			ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
-						   &reservation);
-			BUG_ON(ret != rc);
-		}
-		if (rc >= 0)
-			balloon_stats.hard_limit = (balloon_stats.current_pages + rc -
-						    balloon_stats.driver_pages);
+	if (rc < 0)
 		goto out;
-	}
 
-	for (i = 0; i < nr_pages; i++) {
+	for (i = 0; i < rc; i++) {
 		page = balloon_retrieve();
 		BUG_ON(page == NULL);
 
@@ -263,12 +248,12 @@ static int increase_reservation(unsigned
 		__free_page(page);
 	}
 
-	balloon_stats.current_pages += nr_pages;
+	balloon_stats.current_pages += rc;
 
  out:
 	spin_unlock_irqrestore(&balloon_lock, flags);
 
-	return 0;
+	return rc < 0 ? rc : rc != nr_pages;
 }
 
 static int decrease_reservation(unsigned long nr_pages)
@@ -369,7 +354,6 @@ static void balloon_process(struct work_
 static void balloon_set_new_target(unsigned long target)
 {
 	/* No need for lock. Not read-modify-write updates. */
-	balloon_stats.hard_limit   = ~0UL;
 	balloon_stats.target_pages = target;
 	schedule_work(&balloon_worker);
 }
@@ -428,7 +412,6 @@ static int __init balloon_init(void)
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
 	balloon_stats.driver_pages  = 0UL;
-	balloon_stats.hard_limit    = ~0UL;
 
 	init_timer(&balloon_timer);
 	balloon_timer.data = 0;
@@ -473,9 +456,6 @@ module_exit(balloon_exit);
 BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages));
 BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low));
 BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high));
-BALLOON_SHOW(hard_limit_kb,
-	     (balloon_stats.hard_limit!=~0UL) ? "%lu\n" : "???\n",
-	     (balloon_stats.hard_limit!=~0UL) ? PAGES2KB(balloon_stats.hard_limit) : 0);
 BALLOON_SHOW(driver_kb, "%lu\n", PAGES2KB(balloon_stats.driver_pages));
 
 static ssize_t show_target_kb(struct sys_device *dev, struct sysdev_attribute *attr,
@@ -545,7 +525,6 @@ static struct attribute *balloon_info_at
 	&attr_current_kb.attr,
 	&attr_low_kb.attr,
 	&attr_high_kb.attr,
-	&attr_hard_limit_kb.attr,
 	&attr_driver_kb.attr,
 	NULL
 };

[099/151] dm exception store: free tmp_store on persistent flag error

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Julia Lawall <julia@diku.dk>

commit 613978f8711c7fd4d0aa856872375d2abd7c92ff upstream.

Error handling code following a kmalloc should free the allocated data.

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-exception-store.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -216,7 +216,8 @@ int dm_exception_store_create(struct dm_
 		type = get_type("N");
 	else {
 		ti->error = "Persistent flag is not P or N";
-		return -EINVAL;
+		r = -EINVAL;
+		goto bad_type;
 	}
 
 	if (!type) {

[100/151] dm snapshot: only take lock for statustype info not table

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mikulas Patocka <mpatocka@redhat.com>

commit 94e76572b5dd37b1f0f4b3742ee8a565daead932 upstream.

Take snapshot lock only for STATUSTYPE_INFO, not STATUSTYPE_TABLE.

Commit 4c6fff445d7aa753957856278d4d93bcad6e2c14
(dm-snapshot-lock-snapshot-while-supplying-status.patch)
introduced this use of the lock, but userspace applications using
libdevmapper have been found to request STATUSTYPE_TABLE while the device
is suspended and the lock is already held, leading to deadlock.  Since
the lock is not necessary in this case, don't try to take it.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-snap.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1152,10 +1152,11 @@ static int snapshot_status(struct dm_tar
 	unsigned sz = 0;
 	struct dm_snapshot *snap = ti->private;
 
-	down_write(&snap->lock);
-
 	switch (type) {
 	case STATUSTYPE_INFO:
+
+		down_write(&snap->lock);
+
 		if (!snap->valid)
 			DMEMIT("Invalid");
 		else {
@@ -1171,6 +1172,9 @@ static int snapshot_status(struct dm_tar
 			else
 				DMEMIT("Unknown");
 		}
+
+		up_write(&snap->lock);
+
 		break;
 
 	case STATUSTYPE_TABLE:
@@ -1185,8 +1189,6 @@ static int snapshot_status(struct dm_tar
 		break;
 	}
 
-	up_write(&snap->lock);
-
 	return 0;
 }
 

[101/151] dm crypt: move private iv fields to structs

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Milan Broz <mbroz@redhat.com>

commit 6047359277517c4e56d8bfd6ea4966d7a3924151 upstream.

Define private structures for IV so it's easy to add further attributes
in a following patch which fixes the way key material is wiped from
memory.  Also move ESSIV destructor and remove unnecessary 'status'
operation.

There are no functional changes in this patch.

Signed-off-by: Milan Broz <mbroz@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-crypt.c |   35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -71,10 +71,17 @@ struct crypt_iv_operations {
 	int (*ctr)(struct crypt_config *cc, struct dm_target *ti,
 		   const char *opts);
 	void (*dtr)(struct crypt_config *cc);
-	const char *(*status)(struct crypt_config *cc);
 	int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector);
 };
 
+struct iv_essiv_private {
+	struct crypto_cipher *tfm;
+};
+
+struct iv_benbi_private {
+	int shift;
+};
+
 /*
  * Crypt: maps a linear range of a block device
  * and encrypts / decrypts at the same time.
@@ -102,8 +109,8 @@ struct crypt_config {
 	struct crypt_iv_operations *iv_gen_ops;
 	char *iv_mode;
 	union {
-		struct crypto_cipher *essiv_tfm;
-		int benbi_shift;
+		struct iv_essiv_private essiv;
+		struct iv_benbi_private benbi;
 	} iv_gen_private;
 	sector_t iv_offset;
 	unsigned int iv_size;
@@ -169,6 +176,14 @@ static int crypt_iv_plain_gen(struct cry
 	return 0;
 }
 
+static void crypt_iv_essiv_dtr(struct crypt_config *cc)
+{
+	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
+
+	crypto_free_cipher(essiv->tfm);
+	essiv->tfm = NULL;
+}
+
 static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
@@ -236,21 +251,15 @@ static int crypt_iv_essiv_ctr(struct cry
 	}
 	kfree(salt);
 
-	cc->iv_gen_private.essiv_tfm = essiv_tfm;
+	cc->iv_gen_private.essiv.tfm = essiv_tfm;
 	return 0;
 }
 
-static void crypt_iv_essiv_dtr(struct crypt_config *cc)
-{
-	crypto_free_cipher(cc->iv_gen_private.essiv_tfm);
-	cc->iv_gen_private.essiv_tfm = NULL;
-}
-
 static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector)
 {
 	memset(iv, 0, cc->iv_size);
 	*(u64 *)iv = cpu_to_le64(sector);
-	crypto_cipher_encrypt_one(cc->iv_gen_private.essiv_tfm, iv, iv);
+	crypto_cipher_encrypt_one(cc->iv_gen_private.essiv.tfm, iv, iv);
 	return 0;
 }
 
@@ -273,7 +282,7 @@ static int crypt_iv_benbi_ctr(struct cry
 		return -EINVAL;
 	}
 
-	cc->iv_gen_private.benbi_shift = 9 - log;
+	cc->iv_gen_private.benbi.shift = 9 - log;
 
 	return 0;
 }
@@ -288,7 +297,7 @@ static int crypt_iv_benbi_gen(struct cry
 
 	memset(iv, 0, cc->iv_size - sizeof(u64)); /* rest is cleared below */
 
-	val = cpu_to_be64(((u64)sector << cc->iv_gen_private.benbi_shift) + 1);
+	val = cpu_to_be64(((u64)sector << cc->iv_gen_private.benbi.shift) + 1);
 	put_unaligned(val, (__be64 *)(iv + cc->iv_size - sizeof(u64)));
 
 	return 0;

[102/151] dm crypt: restructure essiv error path

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Milan Broz <mbroz@redhat.com>

commit 5861f1be00b3b70f8ab5e5a81392a6cf69666cd2 upstream.

Use kzfree for salt deallocation because it is derived from the volume
key.  Use a common error path in ESSIV constructor.

Required by a later patch which fixes the way key material is wiped
from memory.

Signed-off-by: Milan Broz <mbroz@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-crypt.c |   46 ++++++++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 20 deletions(-)

--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -187,15 +187,15 @@ static void crypt_iv_essiv_dtr(struct cr
 static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
-	struct crypto_cipher *essiv_tfm;
-	struct crypto_hash *hash_tfm;
+	struct crypto_cipher *essiv_tfm = NULL;
+	struct crypto_hash *hash_tfm = NULL;
 	struct hash_desc desc;
 	struct scatterlist sg;
 	unsigned int saltsize;
-	u8 *salt;
+	u8 *salt = NULL;
 	int err;
 
-	if (opts == NULL) {
+	if (!opts) {
 		ti->error = "Digest algorithm missing for ESSIV mode";
 		return -EINVAL;
 	}
@@ -204,15 +204,16 @@ static int crypt_iv_essiv_ctr(struct cry
 	hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(hash_tfm)) {
 		ti->error = "Error initializing ESSIV hash";
-		return PTR_ERR(hash_tfm);
+		err = PTR_ERR(hash_tfm);
+		goto bad;
 	}
 
 	saltsize = crypto_hash_digestsize(hash_tfm);
-	salt = kmalloc(saltsize, GFP_KERNEL);
-	if (salt == NULL) {
+	salt = kzalloc(saltsize, GFP_KERNEL);
+	if (!salt) {
 		ti->error = "Error kmallocing salt storage in ESSIV";
-		crypto_free_hash(hash_tfm);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto bad;
 	}
 
 	sg_init_one(&sg, cc->key, cc->key_size);
@@ -220,39 +221,44 @@ static int crypt_iv_essiv_ctr(struct cry
 	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	err = crypto_hash_digest(&desc, &sg, cc->key_size, salt);
 	crypto_free_hash(hash_tfm);
+	hash_tfm = NULL;
 
 	if (err) {
 		ti->error = "Error calculating hash in ESSIV";
-		kfree(salt);
-		return err;
+		goto bad;
 	}
 
 	/* Setup the essiv_tfm with the given salt */
 	essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(essiv_tfm)) {
 		ti->error = "Error allocating crypto tfm for ESSIV";
-		kfree(salt);
-		return PTR_ERR(essiv_tfm);
+		err = PTR_ERR(essiv_tfm);
+		goto bad;
 	}
 	if (crypto_cipher_blocksize(essiv_tfm) !=
 	    crypto_ablkcipher_ivsize(cc->tfm)) {
 		ti->error = "Block size of ESSIV cipher does "
 			    "not match IV size of block cipher";
-		crypto_free_cipher(essiv_tfm);
-		kfree(salt);
-		return -EINVAL;
+		err = -EINVAL;
+		goto bad;
 	}
 	err = crypto_cipher_setkey(essiv_tfm, salt, saltsize);
 	if (err) {
 		ti->error = "Failed to set key for ESSIV cipher";
-		crypto_free_cipher(essiv_tfm);
-		kfree(salt);
-		return err;
+		goto bad;
 	}
-	kfree(salt);
+	kzfree(salt);
 
 	cc->iv_gen_private.essiv.tfm = essiv_tfm;
 	return 0;
+
+bad:
+	if (essiv_tfm && !IS_ERR(essiv_tfm))
+		crypto_free_cipher(essiv_tfm);
+	if (hash_tfm && !IS_ERR(hash_tfm))
+		crypto_free_hash(hash_tfm);
+	kzfree(salt);
+	return err;
 }
 
 static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv, sector_t sector)

[103/151] dm: avoid _hash_lock deadlock

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mikulas Patocka <mpatocka@redhat.com>

commit 6076905b5ef39e0ea58db32583c9e0036c05e47b upstream.

Fix a reported deadlock if there are still unprocessed multipath events
on a device that is being removed.

_hash_lock is held during dev_remove while trying to send the
outstanding events.  Sending the events requests the _hash_lock
again in dm_copy_name_and_uuid.

This patch introduces a separate lock around regions that modify the
link to the hash table (dm_set_mdptr) or the name or uuid so that
dm_copy_name_and_uuid no longer needs _hash_lock.

Additionally, dm_copy_name_and_uuid can only be called if md exists
so we can drop the dm_get() and dm_put() which can lead to a BUG()
while md is being freed.

The deadlock:
 #0 [ffff8106298dfb48] schedule at ffffffff80063035
 #1 [ffff8106298dfc20] __down_read at ffffffff8006475d
 #2 [ffff8106298dfc60] dm_copy_name_and_uuid at ffffffff8824f740
 #3 [ffff8106298dfc90] dm_send_uevents at ffffffff88252685
 #4 [ffff8106298dfcd0] event_callback at ffffffff8824c678
 #5 [ffff8106298dfd00] dm_table_event at ffffffff8824dd01
 #6 [ffff8106298dfd10] __hash_remove at ffffffff882507ad
 #7 [ffff8106298dfd30] dev_remove at ffffffff88250865
 #8 [ffff8106298dfd60] ctl_ioctl at ffffffff88250d80
 #9 [ffff8106298dfee0] do_ioctl at ffffffff800418c4
#10 [ffff8106298dff00] vfs_ioctl at ffffffff8002fab9
#11 [ffff8106298dff40] sys_ioctl at ffffffff8004bdaf
#12 [ffff8106298dff80] tracesys at ffffffff8005d28d (via system_call)

Reported-by: guy keren <choo@actcom.co.il>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-ioctl.c  |   17 +++++++++++++----
 drivers/md/dm-uevent.c |    9 ++++-----
 2 files changed, 17 insertions(+), 9 deletions(-)

--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -56,6 +56,11 @@ static void dm_hash_remove_all(int keep_
  */
 static DECLARE_RWSEM(_hash_lock);
 
+/*
+ * Protects use of mdptr to obtain hash cell name and uuid from mapped device.
+ */
+static DEFINE_MUTEX(dm_hash_cells_mutex);
+
 static void init_buckets(struct list_head *buckets)
 {
 	unsigned int i;
@@ -206,7 +211,9 @@ static int dm_hash_insert(const char *na
 		list_add(&cell->uuid_list, _uuid_buckets + hash_str(uuid));
 	}
 	dm_get(md);
+	mutex_lock(&dm_hash_cells_mutex);
 	dm_set_mdptr(md, cell);
+	mutex_unlock(&dm_hash_cells_mutex);
 	up_write(&_hash_lock);
 
 	return 0;
@@ -224,7 +231,9 @@ static void __hash_remove(struct hash_ce
 	/* remove from the dev hash */
 	list_del(&hc->uuid_list);
 	list_del(&hc->name_list);
+	mutex_lock(&dm_hash_cells_mutex);
 	dm_set_mdptr(hc->md, NULL);
+	mutex_unlock(&dm_hash_cells_mutex);
 
 	table = dm_get_table(hc->md);
 	if (table) {
@@ -321,7 +330,9 @@ static int dm_hash_rename(uint32_t cooki
 	 */
 	list_del(&hc->name_list);
 	old_name = hc->name;
+	mutex_lock(&dm_hash_cells_mutex);
 	hc->name = new_name;
+	mutex_unlock(&dm_hash_cells_mutex);
 	list_add(&hc->name_list, _name_buckets + hash_str(new_name));
 
 	/*
@@ -1582,8 +1593,7 @@ int dm_copy_name_and_uuid(struct mapped_
 	if (!md)
 		return -ENXIO;
 
-	dm_get(md);
-	down_read(&_hash_lock);
+	mutex_lock(&dm_hash_cells_mutex);
 	hc = dm_get_mdptr(md);
 	if (!hc || hc->md != md) {
 		r = -ENXIO;
@@ -1596,8 +1606,7 @@ int dm_copy_name_and_uuid(struct mapped_
 		strcpy(uuid, hc->uuid ? : "");
 
 out:
-	up_read(&_hash_lock);
-	dm_put(md);
+	mutex_unlock(&dm_hash_cells_mutex);
 
 	return r;
 }
--- a/drivers/md/dm-uevent.c
+++ b/drivers/md/dm-uevent.c
@@ -139,14 +139,13 @@ void dm_send_uevents(struct list_head *e
 		list_del_init(&event->elist);
 
 		/*
-		 * Need to call dm_copy_name_and_uuid from here for now.
-		 * Context of previous var adds and locking used for
-		 * hash_cell not compatable.
+		 * When a device is being removed this copy fails and we
+		 * discard these unsent events.
 		 */
 		if (dm_copy_name_and_uuid(event->md, event->name,
 					  event->uuid)) {
-			DMERR("%s: dm_copy_name_and_uuid() failed",
-			      __func__);
+			DMINFO("%s: skipping sending uevent for lost device",
+			       __func__);
 			goto uevent_free;
 		}
 

[104/151] dm snapshot: cope with chunk size larger than origin

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Mikulas Patocka <mpatocka@redhat.com>

commit 8e87b9b81b3c370f7e53c1ab6e1c3519ef37a644 upstream.

Under some special conditions the snapshot hash_size is calculated as zero.
This patch instead sets a minimum value of 64, the same as for the
pending exception table.

rounddown_pow_of_two(0) is an undefined operation (it expands to shift
by -1).  init_exception_table with an argument of 0 would fail with -ENOMEM.

The way to trigger the problem is to create a snapshot with a chunk size
that is larger than the origin device.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-snap.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -553,6 +553,8 @@ static int init_hash_tables(struct dm_sn
 	hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
 	hash_size = min(hash_size, max_buckets);
 
+	if (hash_size < 64)
+		hash_size = 64;
 	hash_size = rounddown_pow_of_two(hash_size);
 	if (init_exception_table(&s->complete, hash_size,
 				 DM_CHUNK_CONSECUTIVE_BITS))

[105/151] dm crypt: separate essiv allocation from initialisation

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Milan Broz <mbroz@redhat.com>

commit b95bf2d3d5a48b095bffe2a0cd8c40453cf59557 upstream.

This patch separates the construction of IV from its initialisation.
(For ESSIV it is a hash calculation based on volume key.)

Constructor code now preallocates hash tfm and salt array
and saves it in a private IV structure.

The next patch requires this to reinitialise the wiped IV
without reallocating memory when resuming a suspended device.

Signed-off-by: Milan Broz <mbroz@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-crypt.c |   69 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 43 insertions(+), 26 deletions(-)

--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -71,11 +71,14 @@ struct crypt_iv_operations {
 	int (*ctr)(struct crypt_config *cc, struct dm_target *ti,
 		   const char *opts);
 	void (*dtr)(struct crypt_config *cc);
+	int (*init)(struct crypt_config *cc);
 	int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector);
 };
 
 struct iv_essiv_private {
 	struct crypto_cipher *tfm;
+	struct crypto_hash *hash_tfm;
+	u8 *salt;
 };
 
 struct iv_benbi_private {
@@ -176,12 +179,38 @@ static int crypt_iv_plain_gen(struct cry
 	return 0;
 }
 
+/* Initialise ESSIV - compute salt but no local memory allocations */
+static int crypt_iv_essiv_init(struct crypt_config *cc)
+{
+	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
+	struct hash_desc desc;
+	struct scatterlist sg;
+	int err;
+
+	sg_init_one(&sg, cc->key, cc->key_size);
+	desc.tfm = essiv->hash_tfm;
+	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	err = crypto_hash_digest(&desc, &sg, cc->key_size, essiv->salt);
+	if (err)
+		return err;
+
+	return crypto_cipher_setkey(essiv->tfm, essiv->salt,
+				    crypto_hash_digestsize(essiv->hash_tfm));
+}
+
 static void crypt_iv_essiv_dtr(struct crypt_config *cc)
 {
 	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
 
 	crypto_free_cipher(essiv->tfm);
 	essiv->tfm = NULL;
+
+	crypto_free_hash(essiv->hash_tfm);
+	essiv->hash_tfm = NULL;
+
+	kzfree(essiv->salt);
+	essiv->salt = NULL;
 }
 
 static int crypt_iv_essiv_ctr(struct crypt_config *cc, struct dm_target *ti,
@@ -189,9 +218,6 @@ static int crypt_iv_essiv_ctr(struct cry
 {
 	struct crypto_cipher *essiv_tfm = NULL;
 	struct crypto_hash *hash_tfm = NULL;
-	struct hash_desc desc;
-	struct scatterlist sg;
-	unsigned int saltsize;
 	u8 *salt = NULL;
 	int err;
 
@@ -200,7 +226,7 @@ static int crypt_iv_essiv_ctr(struct cry
 		return -EINVAL;
 	}
 
-	/* Hash the cipher key with the given hash algorithm */
+	/* Allocate hash algorithm */
 	hash_tfm = crypto_alloc_hash(opts, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(hash_tfm)) {
 		ti->error = "Error initializing ESSIV hash";
@@ -208,27 +234,14 @@ static int crypt_iv_essiv_ctr(struct cry
 		goto bad;
 	}
 
-	saltsize = crypto_hash_digestsize(hash_tfm);
-	salt = kzalloc(saltsize, GFP_KERNEL);
+	salt = kzalloc(crypto_hash_digestsize(hash_tfm), GFP_KERNEL);
 	if (!salt) {
 		ti->error = "Error kmallocing salt storage in ESSIV";
 		err = -ENOMEM;
 		goto bad;
 	}
 
-	sg_init_one(&sg, cc->key, cc->key_size);
-	desc.tfm = hash_tfm;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-	err = crypto_hash_digest(&desc, &sg, cc->key_size, salt);
-	crypto_free_hash(hash_tfm);
-	hash_tfm = NULL;
-
-	if (err) {
-		ti->error = "Error calculating hash in ESSIV";
-		goto bad;
-	}
-
-	/* Setup the essiv_tfm with the given salt */
+	/* Allocate essiv_tfm */
 	essiv_tfm = crypto_alloc_cipher(cc->cipher, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(essiv_tfm)) {
 		ti->error = "Error allocating crypto tfm for ESSIV";
@@ -242,14 +255,11 @@ static int crypt_iv_essiv_ctr(struct cry
 		err = -EINVAL;
 		goto bad;
 	}
-	err = crypto_cipher_setkey(essiv_tfm, salt, saltsize);
-	if (err) {
-		ti->error = "Failed to set key for ESSIV cipher";
-		goto bad;
-	}
-	kzfree(salt);
 
+	cc->iv_gen_private.essiv.salt = salt;
 	cc->iv_gen_private.essiv.tfm = essiv_tfm;
+	cc->iv_gen_private.essiv.hash_tfm = hash_tfm;
+
 	return 0;
 
 bad:
@@ -257,7 +267,7 @@ bad:
 		crypto_free_cipher(essiv_tfm);
 	if (hash_tfm && !IS_ERR(hash_tfm))
 		crypto_free_hash(hash_tfm);
-	kzfree(salt);
+	kfree(salt);
 	return err;
 }
 
@@ -323,6 +333,7 @@ static struct crypt_iv_operations crypt_
 static struct crypt_iv_operations crypt_iv_essiv_ops = {
 	.ctr       = crypt_iv_essiv_ctr,
 	.dtr       = crypt_iv_essiv_dtr,
+	.init      = crypt_iv_essiv_init,
 	.generator = crypt_iv_essiv_gen
 };
 
@@ -1054,6 +1065,12 @@ static int crypt_ctr(struct dm_target *t
 	    cc->iv_gen_ops->ctr(cc, ti, ivopts) < 0)
 		goto bad_ivmode;
 
+	if (cc->iv_gen_ops && cc->iv_gen_ops->init &&
+	    cc->iv_gen_ops->init(cc) < 0) {
+		ti->error = "Error initialising IV";
+		goto bad_slab_pool;
+	}
+
 	cc->iv_size = crypto_ablkcipher_ivsize(tfm);
 	if (cc->iv_size)
 		/* at least a 64 bit sector number should fit in our buffer */

[106/151] dm crypt: make wipe message also wipe essiv key

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Milan Broz <mbroz@redhat.com>

commit 542da317668c35036e8471822a564b609d05af66 upstream.

The "wipe key" message is used to wipe the volume key from memory
temporarily, for example when suspending to RAM.

But the initialisation vector in ESSIV mode is calculated from the
hashed volume key, so the wipe message should wipe this IV key too and
reinitialise it when the volume key is reinstated.

This patch adds an IV wipe method called from a wipe message callback.
ESSIV is then reinitialised using the init function added by the
last patch.

Signed-off-by: Milan Broz <mbroz@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/md/dm-crypt.c |   34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1,7 +1,7 @@
 /*
  * Copyright (C) 2003 Christophe Saout <christophe@saout.de>
  * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
- * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
@@ -72,6 +72,7 @@ struct crypt_iv_operations {
 		   const char *opts);
 	void (*dtr)(struct crypt_config *cc);
 	int (*init)(struct crypt_config *cc);
+	int (*wipe)(struct crypt_config *cc);
 	int (*generator)(struct crypt_config *cc, u8 *iv, sector_t sector);
 };
 
@@ -199,6 +200,17 @@ static int crypt_iv_essiv_init(struct cr
 				    crypto_hash_digestsize(essiv->hash_tfm));
 }
 
+/* Wipe salt and reset key derived from volume key */
+static int crypt_iv_essiv_wipe(struct crypt_config *cc)
+{
+	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
+	unsigned salt_size = crypto_hash_digestsize(essiv->hash_tfm);
+
+	memset(essiv->salt, 0, salt_size);
+
+	return crypto_cipher_setkey(essiv->tfm, essiv->salt, salt_size);
+}
+
 static void crypt_iv_essiv_dtr(struct crypt_config *cc)
 {
 	struct iv_essiv_private *essiv = &cc->iv_gen_private.essiv;
@@ -334,6 +346,7 @@ static struct crypt_iv_operations crypt_
 	.ctr       = crypt_iv_essiv_ctr,
 	.dtr       = crypt_iv_essiv_dtr,
 	.init      = crypt_iv_essiv_init,
+	.wipe      = crypt_iv_essiv_wipe,
 	.generator = crypt_iv_essiv_gen
 };
 
@@ -1310,6 +1323,7 @@ static void crypt_resume(struct dm_targe
 static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
 {
 	struct crypt_config *cc = ti->private;
+	int ret = -EINVAL;
 
 	if (argc < 2)
 		goto error;
@@ -1319,10 +1333,22 @@ static int crypt_message(struct dm_targe
 			DMWARN("not suspended during key manipulation.");
 			return -EINVAL;
 		}
-		if (argc == 3 && !strnicmp(argv[1], MESG_STR("set")))
-			return crypt_set_key(cc, argv[2]);
-		if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe")))
+		if (argc == 3 && !strnicmp(argv[1], MESG_STR("set"))) {
+			ret = crypt_set_key(cc, argv[2]);
+			if (ret)
+				return ret;
+			if (cc->iv_gen_ops && cc->iv_gen_ops->init)
+				ret = cc->iv_gen_ops->init(cc);
+			return ret;
+		}
+		if (argc == 2 && !strnicmp(argv[1], MESG_STR("wipe"))) {
+			if (cc->iv_gen_ops && cc->iv_gen_ops->wipe) {
+				ret = cc->iv_gen_ops->wipe(cc);
+				if (ret)
+					return ret;
+			}
 			return crypt_wipe_key(cc);
+		}
 	}
 
 error:

[107/151] slc90e66: fix UDMA handling

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>

[ Upstream commit ee31527a02b0a8e1aa4a5e4084d2db5fa34737ed ]

Fix checking of the currently programmed UDMA mode.

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/ide/slc90e66.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/ide/slc90e66.c
+++ b/drivers/ide/slc90e66.c
@@ -91,8 +91,7 @@ static void slc90e66_set_dma_mode(ide_dr
 
 		if (!(reg48 & u_flag))
 			pci_write_config_word(dev, 0x48, reg48|u_flag);
-		/* FIXME: (reg4a & a_speed) ? */
-		if ((reg4a & u_speed) != u_speed) {
+		if ((reg4a & a_speed) != u_speed) {
 			pci_write_config_word(dev, 0x4a, reg4a & ~a_speed);
 			pci_read_config_word(dev, 0x4a, &reg4a);
 			pci_write_config_word(dev, 0x4a, reg4a|u_speed);

[108/151] tcp: Stalling connections: Fix timeout calculation routine

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 2769 bytes --]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Damian Lukowski <damian@tvk.rwth-aachen.de>

[ Upstream commit 07f29bc5bbae4e53e982ab956fed7207990a7786 ]

This patch fixes a problem in the TCP connection timeout calculation.
Currently, timeout decisions are made on the basis of the current
tcp_time_stamp and retrans_stamp, which is usually set at the first
retransmission.
However, if the retransmission fails in tcp_retransmit_skb(),
retrans_stamp is not updated and remains zero. This leads to wrong
decisions in retransmits_timed_out() if tcp_time_stamp is larger than
the specified timeout, which is very likely.
In this case, the TCP connection dies after the first attempted
(and unsuccessful) retransmission.

With this patch, tcp_skb_cb->when is used instead, when retrans_stamp
is not available.

This bug has been introduced together with retransmits_timed_out() in
2.6.32, as the number of retransmissions has been used for timeout
decisions before. The corresponding commit was
6fa12c85031485dff38ce550c24f10da23b0adaa (Revert Backoff [v3]:
Calculate TCP's connection close threshold as a time value.).

Thanks to Ilpo Järvinen for code suggestions and Frederic Leroy for
testing.

Reported-by: Frederic Leroy <fredo@starox.org>
Signed-off-by: Damian Lukowski <damian@tvk.rwth-aachen.de>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/net/tcp.h |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1263,14 +1263,20 @@ static inline struct sk_buff *tcp_write_
  * TCP connection after "boundary" unsucessful, exponentially backed-off
  * retransmissions with an initial RTO of TCP_RTO_MIN.
  */
-static inline bool retransmits_timed_out(const struct sock *sk,
+static inline bool retransmits_timed_out(struct sock *sk,
 					 unsigned int boundary)
 {
 	unsigned int timeout, linear_backoff_thresh;
+	unsigned int start_ts;
 
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
+	if (unlikely(!tcp_sk(sk)->retrans_stamp))
+		start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when;
+	else
+		start_ts = tcp_sk(sk)->retrans_stamp;
+
 	linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
 
 	if (boundary <= linear_backoff_thresh)
@@ -1279,7 +1285,7 @@ static inline bool retransmits_timed_out
 		timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
 			  (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 
-	return (tcp_time_stamp - tcp_sk(sk)->retrans_stamp) >= timeout;
+	return (tcp_time_stamp - start_ts) >= timeout;
 }
 
 static inline struct sk_buff *tcp_send_head(struct sock *sk)

[109/151] ip_fragment: also adjust skb->truesize for packets not owned by a socket

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Patrick McHardy <kaber@trash.net>

[ Upstream commit b2722b1c3a893ec6021508da15b32282ec79f4da ]

When a large packet gets reassembled by ip_defrag(), the head skb
accounts for all the fragments in skb->truesize. If this packet is
refragmented again, skb->truesize is not re-adjusted to reflect only
the head size since its not owned by a socket. If the head fragment
then gets recycled and reused for another received fragment, it might
exceed the defragmentation limits due to its large truesize value.

skb_recycle_check() explicitly checks for linear skbs, so any recycled
skb should reflect its true size in skb->truesize. Change ip_fragment()
to also adjust the truesize value of skbs not owned by a socket.

Reported-and-tested-by: Ben Menchaca <ben@bigfootnetworks.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 net/ipv4/ip_output.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -501,8 +501,8 @@ int ip_fragment(struct sk_buff *skb, int
 			if (skb->sk) {
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
-				truesizes += frag->truesize;
 			}
+			truesizes += frag->truesize;
 		}
 
 		/* Everything is OK. Generate! */

[110/151] b44 WOL setup: one-bit-off stack corruption kernel panic fix

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Stanislav Brabec <sbrabec@suse.cz>

[ Upstream commit: e0188829cb724e7d12a2d4e343b368ff1d6e1471 ]

About 50% of shutdowns of b44 Ethernet adapter ends by kernel panic
with kernels compiled with stack-protector.

Checking b44_magic_pattern() return values, one call of
b44_magic_pattern() returns 127. It means, that set_bit(128, pmask)
was called on line 1509. It means that bit 0 of 17th byte of pmask was
overwritten. But pmask has only 16 bytes. Stack corruption happens.

It seems that set_bit() on line 1509 always writes one bit off.

The fix does not only solve the stack corruption, but also makes Wake
On LAN working on my onboard B44 on Asus A7V-333X mainboard.

It seems that this problem affects all kernel versions since commit
725ad800 ([PATCH] b44: add wol for old nic) on 2006-06-20.

Signed-off-by: Stanislav Brabec <sbrabec@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/net/b44.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/drivers/net/b44.c
+++ b/drivers/net/b44.c
@@ -1505,8 +1505,7 @@ static int b44_magic_pattern(u8 *macaddr
 		for (k = 0; k< ethaddr_bytes; k++) {
 			ppattern[offset + magicsync +
 				(j * ETH_ALEN) + k] = macaddr[k];
-			len++;
-			set_bit(len, (unsigned long *) pmask);
+			set_bit(len++, (unsigned long *) pmask);
 		}
 	}
 	return len - 1;

[111/151] sparc64: Dont specify IRQF_SHARED for LDC interrupts.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David S. Miller <davem@davemloft.net>

[ Upstream commit 08a036d583409e3517e3d15b7478d029b25f2cf2 ]

IRQF_SHARED and IRQF_DISABLED don't mix.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/sparc/kernel/ldc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1242,13 +1242,13 @@ int ldc_bind(struct ldc_channel *lp, con
 	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
 
 	err = request_irq(lp->cfg.rx_irq, ldc_rx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED | IRQF_SHARED,
+			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
 			  lp->rx_irq_name, lp);
 	if (err)
 		return err;
 
 	err = request_irq(lp->cfg.tx_irq, ldc_tx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED | IRQF_SHARED,
+			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
 			  lp->tx_irq_name, lp);
 	if (err) {
 		free_irq(lp->cfg.rx_irq, lp);

[112/151] sparc64: Fix overly strict range type matching for PCI devices.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David S. Miller <davem@davemloft.net>

[ Upstream commit 4230fa3b89ea1c413766bd411a8315a3d05aa6c7 ]

When we are trying to see if a range property entry applies
to a given address, we are overly strict about the type.

We should only allow I/O ranges for I/O addresses, and only allow
CONFIG space ranges for CONFIG space address.

However for MEM ranges, they come in 32-bit and 64-bit flavors.
And a lack of an exact match is OK if the range is 32-bit and
the address is 64-bit.  We can assign a 64-bit address properly
into a 32-bit parent range just fine.

So allow it.

Reported-by: Patrick Finnegan <pat@computer-refuge.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/sparc/kernel/of_device_64.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

--- a/arch/sparc/kernel/of_device_64.c
+++ b/arch/sparc/kernel/of_device_64.c
@@ -104,9 +104,19 @@ static int of_bus_pci_map(u32 *addr, con
 	int i;
 
 	/* Check address type match */
-	if ((addr[0] ^ range[0]) & 0x03000000)
-		return -EINVAL;
+	if (!((addr[0] ^ range[0]) & 0x03000000))
+		goto type_match;
+
+	/* Special exception, we can map a 64-bit address into
+	 * a 32-bit range.
+	 */
+	if ((addr[0] & 0x03000000) == 0x03000000 &&
+	    (range[0] & 0x03000000) == 0x02000000)
+		goto type_match;
+
+	return -EINVAL;
 
+type_match:
 	if (of_out_of_range(addr + 1, range + 1, range + na + pna,
 			    na - 1, ns))
 		return -EINVAL;

[113/151] sparc64: Fix stack debugging IRQ stack regression.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David S. Miller <davem@davemloft.net>

[ Upstream commit 166e553a575f09485f6d0df8a1ef3c5991f7d953 ]

Commit 4f70f7a91bffdcc39f088748dc678953eb9a3fbd
(sparc64: Implement IRQ stacks.) has two bugs.

First, the softirq range check forgets to subtract STACK_BIAS
before comparing with %sp.  Next, on failure the wrong label
is jumped to, resulting in a bogus stack being loaded.

Reported-by: Igor Kovalenko <igor.v.kovalenko@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/sparc/lib/mcount.S |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/arch/sparc/lib/mcount.S
+++ b/arch/sparc/lib/mcount.S
@@ -64,8 +64,9 @@ mcount:
 2:	 sethi		%hi(softirq_stack), %g3
 	or		%g3, %lo(softirq_stack), %g3
 	ldx		[%g3 + %g1], %g7
+	sub		%g7, STACK_BIAS, %g7
 	cmp		%sp, %g7
-	bleu,pt		%xcc, 2f
+	bleu,pt		%xcc, 3f
 	 sethi		%hi(THREAD_SIZE), %g3
 	add		%g7, %g3, %g7
 	cmp		%sp, %g7
@@ -75,7 +76,7 @@ mcount:
 	 * again, we are already trying to output the stack overflow
 	 * message.
 	 */
-	sethi		%hi(ovstack), %g7		! cant move to panic stack fast enough
+3:	sethi		%hi(ovstack), %g7		! cant move to panic stack fast enough
 	 or		%g7, %lo(ovstack), %g7
 	add		%g7, OVSTACKSIZE, %g3
 	sub		%g3, STACK_BIAS + 192, %g3

[114/151] sparc: Set UTS_MACHINE correctly.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David S. Miller <davem@davemloft.net>

[ Upstream commit 7f5620a5fcd658f219e85831d3691908f1eccbde ]

"ARCH" can be just about anything, so we shouldn't end up
with UTS_MACHINE of "sparc" in a 64-bit kernel build just
because someone set the personality using 'sparc32' or
similar.  CONFIG_SPARC64 drives the compilation and
therefore provides the definitive value, not "ARCH".

This mirrors commit 8c6531f7a99f29ba8817ffb12cc9ecf190049bd6
(x86: correctly set UTS_MACHINE for "make ARCH=x86")

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 arch/sparc/Makefile |    2 ++
 1 file changed, 2 insertions(+)

--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -27,6 +27,7 @@ AS             := $(AS) -32
 LDFLAGS        := -m elf32_sparc
 CHECKFLAGS     += -D__sparc__
 export BITS    := 32
+UTS_MACHINE    := sparc
 
 #KBUILD_CFLAGS += -g -pipe -fcall-used-g5 -fcall-used-g7
 KBUILD_CFLAGS += -m32 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7
@@ -46,6 +47,7 @@ CHECKFLAGS      += -D__sparc__ -D__sparc
 
 LDFLAGS              := -m elf64_sparc
 export BITS          := 64
+UTS_MACHINE          := sparc64
 
 KBUILD_CFLAGS += -m64 -pipe -mno-fpu -mcpu=ultrasparc -mcmodel=medlow   \
                  -ffixed-g4 -ffixed-g5 -fcall-used-g7 -Wno-sign-compare \

[115/151] b43legacy: avoid PPC fault during resume

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Larry Finger <Larry.Finger@lwfinger.net>

commit 316a4d966cae3c2dec83ebb1ee1a3515f97b30ff upstream.

For PPC architecture with PHY Revision < 3, a read of the register
B43_MMIO_HWENABLED_LO will cause a CPU fault unless b43legacy_status()
returns a value of 2 (B43legacy_STAT_STARTED); however, one finds that
the driver is unable to associate after resuming from hibernation unless
this routine returns 1. To satisfy both conditions, the routine is rewritten
to return TRUE whenever b43legacy_status() returns a value < 2.

This patch fixes the second problem listed in the postings for Red Hat
Bugzilla #538523.

Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/b43legacy/rfkill.c |    7 +++++++
 1 file changed, 7 insertions(+)

--- a/drivers/net/wireless/b43legacy/rfkill.c
+++ b/drivers/net/wireless/b43legacy/rfkill.c
@@ -34,6 +34,13 @@ bool b43legacy_is_hw_radio_enabled(struc
 		      & B43legacy_MMIO_RADIO_HWENABLED_HI_MASK))
 			return 1;
 	} else {
+		/* To prevent CPU fault on PPC, do not read a register
+		 * unless the interface is started; however, on resume
+		 * for hibernation, this routine is entered early. When
+		 * that happens, unconditionally return TRUE.
+		 */
+		if (b43legacy_status(dev) < B43legacy_STAT_STARTED)
+			return 1;
 		if (b43legacy_read16(dev, B43legacy_MMIO_RADIO_HWENABLED_LO)
 		    & B43legacy_MMIO_RADIO_HWENABLED_LO_MASK)
 			return 1;

[116/151] tracing: Fix event format export

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Johannes Berg <johannes@sipsolutions.net>

commit 811cb50baf63461ce0bdb234927046131fc7fa8b upstream.

For some reason the export of the event print format to userspace
uses '#fmt' which breaks if the format string is anything but a plain
string, for example if it is built with macros then the macro names
are exported instead of their contents.

Use
	"\"%s\"", fmt
instead of
	"%s", #fmt
to export the string and not the way it is built.

For example, in net/mac80211/driver-trace.h for the trace event drv_start
there is:

        TP_printk(
                LOCAL_PR_FMT, LOCAL_PR_ARG
        )

Which use to produce:

 print fmt: LOCAL_PR_FMT, REC->wiphy_name

Now produces:

 print fmt: "%s", REC->wiphy_name

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
LKML-Reference: <20091113224009.GB23942@elte.hu>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

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

--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -159,7 +159,7 @@
 #undef __get_str
 
 #undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+#define TP_printk(fmt, args...) "\"%s\", %s\n", fmt, __stringify(args)
 
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args

[117/151] ath9k: Fix TX hang poll routine

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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


From: Sujith <Sujith.Manoharan@atheros.com>

This is a backport of upstream commit: 332c556633b8c5fb4e890b1783122f2315526590

When TX is hung, the chip is reset. Ensure that
the chip is awake by using the PS wrappers.


Signed-off-by: Sujith <Sujith.Manoharan@atheros.com>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/ath/ath9k/xmit.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2065,7 +2065,9 @@ static void ath_tx_complete_poll_work(st
 
 	if (needreset) {
 		DPRINTF(sc, ATH_DBG_RESET, "tx hung, resetting the chip\n");
+		ath9k_ps_wakeup(sc);
 		ath_reset(sc, false);
+		ath9k_ps_restore(sc);
 	}
 
 	ieee80211_queue_delayed_work(sc->hw, &sc->tx_complete_work,

[118/151] ath9k: fix processing of TX PS null data frames

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: "Luis R. Rodriguez" <lrodriguez@atheros.com>

This is a backport of upstream commit: e7824a50662f7f79b1a739f705b4d906c31cf221

When mac80211 was telling us to go into Powersave we listened
and immediately turned RX off. This meant hardware would not
see the ACKs from the AP we're associated with and hardware
we'd end up retransmiting the null data frame in a loop
helplessly.

Fix this by keeping track of the transmitted nullfunc frames
and only when we are sure the AP has sent back an ACK do we
go ahead and shut RX off.


Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: Vivek Natarajan <Vivek.Natarajan@atheros.com>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/net/wireless/ath/ath9k/ath9k.h |    3 +++
 drivers/net/wireless/ath/ath9k/mac.c   |    2 ++
 drivers/net/wireless/ath/ath9k/mac.h   |    1 +
 drivers/net/wireless/ath/ath9k/main.c  |    9 ++++++++-
 drivers/net/wireless/ath/ath9k/xmit.c  |   16 ++++++++++++++++
 5 files changed, 30 insertions(+), 1 deletion(-)

--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -139,6 +139,7 @@ struct ath_buf {
 	dma_addr_t bf_daddr;		/* physical addr of desc */
 	dma_addr_t bf_buf_addr;		/* physical addr of data buffer */
 	bool bf_stale;
+	bool bf_isnullfunc;
 	u16 bf_flags;
 	struct ath_buf_state bf_state;
 	dma_addr_t bf_dmacontext;
@@ -524,6 +525,8 @@ struct ath_led {
 #define SC_OP_BEACON_SYNC       BIT(19)
 #define SC_OP_BTCOEX_ENABLED    BIT(20)
 #define SC_OP_BT_PRIORITY_DETECTED BIT(21)
+#define SC_OP_NULLFUNC_COMPLETED   BIT(22)
+#define SC_OP_PS_ENABLED	BIT(23)
 
 struct ath_bus_ops {
 	void		(*read_cachesize)(struct ath_softc *sc, int *csz);
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -222,6 +222,8 @@ int ath9k_hw_txprocdesc(struct ath_hw *a
 	ds->ds_txstat.ts_status = 0;
 	ds->ds_txstat.ts_flags = 0;
 
+	if (ads->ds_txstatus1 & AR_FrmXmitOK)
+		ds->ds_txstat.ts_status |= ATH9K_TX_ACKED;
 	if (ads->ds_txstatus1 & AR_ExcessiveRetries)
 		ds->ds_txstat.ts_status |= ATH9K_TXERR_XRETRY;
 	if (ads->ds_txstatus1 & AR_Filtered)
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -76,6 +76,7 @@
 #define ATH9K_TXERR_FIFO           0x04
 #define ATH9K_TXERR_XTXOP          0x08
 #define ATH9K_TXERR_TIMER_EXPIRED  0x10
+#define ATH9K_TX_ACKED		   0x20
 
 #define ATH9K_TX_BA                0x01
 #define ATH9K_TX_PWRMGMT           0x02
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2327,6 +2327,7 @@ static int ath9k_config(struct ieee80211
 
 	if (changed & IEEE80211_CONF_CHANGE_PS) {
 		if (conf->flags & IEEE80211_CONF_PS) {
+			sc->sc_flags |= SC_OP_PS_ENABLED;
 			if (!(ah->caps.hw_caps &
 			      ATH9K_HW_CAP_AUTOSLEEP)) {
 				if ((sc->imask & ATH9K_INT_TIM_TIMER) == 0) {
@@ -2334,11 +2335,17 @@ static int ath9k_config(struct ieee80211
 					ath9k_hw_set_interrupts(sc->sc_ah,
 							sc->imask);
 				}
-				ath9k_hw_setrxabort(sc->sc_ah, 1);
 			}
 			sc->ps_enabled = true;
+			if ((sc->sc_flags & SC_OP_NULLFUNC_COMPLETED)) {
+				sc->sc_flags &= ~SC_OP_NULLFUNC_COMPLETED;
+				sc->ps_enabled = true;
+				ath9k_hw_setrxabort(sc->sc_ah, 1);
+			}
 		} else {
 			sc->ps_enabled = false;
+			sc->sc_flags &= ~(SC_OP_PS_ENABLED |
+					  SC_OP_NULLFUNC_COMPLETED);
 			ath9k_hw_setpower(sc->sc_ah, ATH9K_PM_AWAKE);
 			if (!(ah->caps.hw_caps &
 			      ATH9K_HW_CAP_AUTOSLEEP)) {
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1592,6 +1592,13 @@ static int ath_tx_setup_buffer(struct ie
 	}
 
 	bf->bf_buf_addr = bf->bf_dmacontext;
+
+	if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc)) {
+		bf->bf_isnullfunc = true;
+		sc->sc_flags &= ~SC_OP_NULLFUNC_COMPLETED;
+	} else
+		bf->bf_isnullfunc = false;
+
 	return 0;
 }
 
@@ -1989,6 +1996,15 @@ static void ath_tx_processq(struct ath_s
 		if (ds == txq->axq_gatingds)
 			txq->axq_gatingds = NULL;
 
+		if (bf->bf_isnullfunc &&
+		    (ds->ds_txstat.ts_status & ATH9K_TX_ACKED)) {
+			if ((sc->sc_flags & SC_OP_PS_ENABLED)) {
+				sc->ps_enabled = true;
+				ath9k_hw_setrxabort(sc->sc_ah, 1);
+			} else
+				sc->sc_flags |= SC_OP_NULLFUNC_COMPLETED;
+		}
+
 		/*
 		 * Remove ath_buf's of the same transmit unit from txq,
 		 * however leave the last descriptor back as the holding

[119/151] ath9k: Fix maximum tx fifo settings for single stream devices

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: "Luis R. Rodriguez" <lrodriguez@atheros.com>

This is a backport of upstream commit: f4709fdf683e1ed37b321c258b614ebe39752bf3

Atheros single stream AR9285 and AR9271 have half the PCU TX FIFO
buffer size of that of dual stream devices. Dual stream devices
have a max PCU TX FIFO size of 8 KB while single stream devices
have 4 KB. Single stream devices have an issue though and require
hardware only to use half of the amount of its capable PCU TX FIFO
size, 2 KB and this requires a change in software.

Technically a change would not have been required (except for frame
burst considerations of 128 bytes) if these devices would have been
able to use the full 4 KB of the PCU TX FIFO size but our systems
engineers recommend 2 KB to be used only. We enforce this through
software by reducing the max frame triggger level to 2 KB.

Fixing the max frame trigger level should then have a few benefits:

  * The PER will now be adjusted as designed for underruns when the
    max trigger level is reached. This should help alleviate the
    bus as the rate control algorithm chooses a slower rate which
    should ensure frames are transmitted properly under high system
    bus load.

  * The poll we use on our TX queues should now trigger and work
    as designed for single stream devices. The hardware passes
    data from each TX queue on the PCU TX FIFO queue respecting each
    queue's priority. The new trigger level ensures this seeding of
    the PCU TX FIFO queue occurs as designed which could mean avoiding
    false resets and actually reseting hw correctly when a TX queue
    is indeed stuck.

  * Some undocumented / unsupported behaviour could have been triggered
    when the max trigger level level was being set to 4 KB on single
    stream devices. Its not clear what this issue was to me yet.

Cc: Kyungwan Nam <kyungwan.nam@atheros.com>
Cc: Bennyam Malavazi <bennyam.malavazi@atheros.com>
Cc: Stephen Chen <stephen.chen@atheros.com>
Cc: Shan Palanisamy <shan.palanisamy@atheros.com>
Cc: Paul Shaw <paul.shaw@atheros.com>
Signed-off-by: Vasanthakumar Thiagarajan <vasanth@atheros.com>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/net/wireless/ath/ath9k/hw.c  |   11 ++++++++++-
 drivers/net/wireless/ath/ath9k/hw.h  |    1 +
 drivers/net/wireless/ath/ath9k/mac.c |    4 ++--
 3 files changed, 13 insertions(+), 3 deletions(-)

--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -937,6 +937,11 @@ int ath9k_hw_init(struct ath_hw *ah)
 	DPRINTF(ah->ah_sc, ATH_DBG_RESET, "serialize_regmode is %d\n",
 		ah->config.serialize_regmode);
 
+	if (AR_SREV_9285(ah) || AR_SREV_9271(ah))
+		ah->config.max_txtrig_level = MAX_TX_FIFO_THRESHOLD >> 1;
+	else
+		ah->config.max_txtrig_level = MAX_TX_FIFO_THRESHOLD;
+
 	if (!ath9k_hw_macversion_supported(ah->hw_version.macVersion)) {
 		DPRINTF(ah->ah_sc, ATH_DBG_FATAL,
 			"Mac Chip Rev 0x%02x.%x is not supported by "
@@ -3670,7 +3675,11 @@ void ath9k_hw_fill_cap_info(struct ath_h
 		pCap->keycache_size = AR_KEYTABLE_SIZE;
 
 	pCap->hw_caps |= ATH9K_HW_CAP_FASTCC;
-	pCap->tx_triglevel_max = MAX_TX_FIFO_THRESHOLD;
+
+	if (AR_SREV_9285(ah) || AR_SREV_9271(ah))
+		pCap->tx_triglevel_max = MAX_TX_FIFO_THRESHOLD >> 1;
+	else
+		pCap->tx_triglevel_max = MAX_TX_FIFO_THRESHOLD;
 
 	if (AR_SREV_9285_10_OR_LATER(ah))
 		pCap->num_gpio_pins = AR9285_NUM_GPIO;
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -218,6 +218,7 @@ struct ath9k_ops_config {
 #define AR_SPUR_FEEQ_BOUND_HT20 10
 	int spurmode;
 	u16 spurchans[AR_EEPROM_MODAL_SPURS][2];
+	u8 max_txtrig_level;
 };
 
 enum ath9k_int {
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -70,7 +70,7 @@ bool ath9k_hw_updatetxtriglevel(struct a
 	u32 txcfg, curLevel, newLevel;
 	enum ath9k_int omask;
 
-	if (ah->tx_trig_level >= MAX_TX_FIFO_THRESHOLD)
+	if (ah->tx_trig_level >= ah->config.max_txtrig_level)
 		return false;
 
 	omask = ath9k_hw_set_interrupts(ah, ah->mask_reg & ~ATH9K_INT_GLOBAL);
@@ -79,7 +79,7 @@ bool ath9k_hw_updatetxtriglevel(struct a
 	curLevel = MS(txcfg, AR_FTRIG);
 	newLevel = curLevel;
 	if (bIncTrigLevel) {
-		if (curLevel < MAX_TX_FIFO_THRESHOLD)
+		if (curLevel < ah->config.max_txtrig_level)
 			newLevel++;
 	} else if (curLevel > MIN_TX_FIFO_THRESHOLD)
 		newLevel--;

[120/151] ath9k: fix tx status reporting

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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


From: Felix Fietkau <nbd@openwrt.org>

This is a backport of upstream commit: e8c6342d989e241513baeba4b05a04b6b1f3bc8b

This patch fixes a bug in ath9k's tx status check, which
caused mac80211 to consider regularly transmitted unicast frames
as un-acked.

When checking the ts_status field for errors, it needs to be masked
with ATH9K_TXERR_FILT, because this field also contains other fields
like ATH9K_TX_ACKED.

Without this patch, AP mode is pretty much unusable, as hostapd
checks the ACK status for the frames that it injects.


Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/net/wireless/ath/ath9k/xmit.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2020,7 +2020,7 @@ static void ath_tx_processq(struct ath_s
 		if (bf_isaggr(bf))
 			txq->axq_aggr_depth--;
 
-		txok = (ds->ds_txstat.ts_status == 0);
+		txok = !(ds->ds_txstat.ts_status & ATH9K_TXERR_FILT);
 		txq->axq_tx_inprogress = false;
 		spin_unlock_bh(&txq->axq_lock);
 

[121/151] mac80211: Fix dynamic power save for scanning.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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


From: Vivek Natarajan <vnatarajan@atheros.com>

Upstream commit: 7c3f4bbedc241ddcd3abe1f419c356e625231da1

Not only ps_sdata but also IEEE80211_CONF_PS is to be considered
before restoring PS in scan_ps_disable(). For instance, when ps_sdata
is set but CONF_PS is not set just because the dynamic timer is still
running, a sw scan leads to setting of CONF_PS in scan_ps_disable
instead of restarting the dynamic PS timer.
Also for the above case, a null data frame is to be sent after
returning to operating channel which was not happening with the
current implementation. This patch fixes this too.


Signed-off-by: Vivek Natarajan <vnatarajan@atheros.com>
Reviewed-by: Kalle Valo <kalle.valo@nokia.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 net/mac80211/ieee80211_i.h |    1 +
 net/mac80211/scan.c        |   20 ++++++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -808,6 +808,7 @@ struct ieee80211_local {
 	unsigned int wmm_acm; /* bit field of ACM bits (BIT(802.1D tag)) */
 
 	bool pspolling;
+	bool scan_ps_enabled;
 	/*
 	 * PS can only be enabled when we have exactly one managed
 	 * interface (and monitors) in PS, this then points there.
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -196,7 +196,8 @@ ieee80211_scan_rx(struct ieee80211_sub_i
 static void ieee80211_scan_ps_enable(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
-	bool ps = false;
+
+	local->scan_ps_enabled = false;
 
 	/* FIXME: what to do when local->pspolling is true? */
 
@@ -204,12 +205,13 @@ static void ieee80211_scan_ps_enable(str
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 
 	if (local->hw.conf.flags & IEEE80211_CONF_PS) {
-		ps = true;
+		local->scan_ps_enabled = true;
 		local->hw.conf.flags &= ~IEEE80211_CONF_PS;
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
 	}
 
-	if (!ps || !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK))
+	if (!(local->scan_ps_enabled) ||
+	    !(local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK))
 		/*
 		 * If power save was enabled, no need to send a nullfunc
 		 * frame because AP knows that we are sleeping. But if the
@@ -230,7 +232,7 @@ static void ieee80211_scan_ps_disable(st
 
 	if (!local->ps_sdata)
 		ieee80211_send_nullfunc(local, sdata, 0);
-	else {
+	else if (local->scan_ps_enabled) {
 		/*
 		 * In !IEEE80211_HW_PS_NULLFUNC_STACK case the hardware
 		 * will send a nullfunc frame with the powersave bit set
@@ -246,6 +248,16 @@ static void ieee80211_scan_ps_disable(st
 		 */
 		local->hw.conf.flags |= IEEE80211_CONF_PS;
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
+	} else if (local->hw.conf.dynamic_ps_timeout > 0) {
+		/*
+		 * If IEEE80211_CONF_PS was not set and the dynamic_ps_timer
+		 * had been running before leaving the operating channel,
+		 * restart the timer now and send a nullfunc frame to inform
+		 * the AP that we are awake.
+		 */
+		ieee80211_send_nullfunc(local, sdata, 0);
+		mod_timer(&local->dynamic_ps_timer, jiffies +
+			  msecs_to_jiffies(local->hw.conf.dynamic_ps_timeout));
 	}
 }
 

[122/151] drm/i915: Fix sync to vblank when VGA output is turned off

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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


From: Li Peng <peng.li@linux.intel.com>

commit 778c902640530371a169ad1c03566e7c51b09874 upstream

In current vblank-wait implementation, if we turn off VGA output,
drm_wait_vblank will still wait on the disabled pipe until timeout,
because vblank on the pipe is assumed be enabled. This would cause
slow system response on some system such as moblin.

This patch resolve the issue by adding a drm helper function
drm_vblank_off which explicitly clear vblank_enabled[crtc], wake up
any waiting queue and save last vblank counter before turning off
crtc. It also slightly change drm_vblank_get to ensure that we will
will return immediately if trying to wait on a disabled pipe.

Signed-off-by: Li Peng <peng.li@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[anholt: hand-applied for conflicts with overlay changes]
Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/gpu/drm/drm_irq.c            |   34 ++++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/intel_display.c |    1 +
 include/drm/drmP.h                   |    1 +
 3 files changed, 28 insertions(+), 8 deletions(-)

--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -429,15 +429,21 @@ int drm_vblank_get(struct drm_device *de
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	/* Going from 0->1 means we have to enable interrupts again */
-	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1 &&
-	    !dev->vblank_enabled[crtc]) {
-		ret = dev->driver->enable_vblank(dev, crtc);
-		DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret);
-		if (ret)
+	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
+		if (!dev->vblank_enabled[crtc]) {
+			ret = dev->driver->enable_vblank(dev, crtc);
+			DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret);
+			if (ret)
+				atomic_dec(&dev->vblank_refcount[crtc]);
+			else {
+				dev->vblank_enabled[crtc] = 1;
+				drm_update_vblank_count(dev, crtc);
+			}
+		}
+	} else {
+		if (!dev->vblank_enabled[crtc]) {
 			atomic_dec(&dev->vblank_refcount[crtc]);
-		else {
-			dev->vblank_enabled[crtc] = 1;
-			drm_update_vblank_count(dev, crtc);
+			ret = -EINVAL;
 		}
 	}
 	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
@@ -464,6 +470,18 @@ void drm_vblank_put(struct drm_device *d
 }
 EXPORT_SYMBOL(drm_vblank_put);
 
+void drm_vblank_off(struct drm_device *dev, int crtc)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	DRM_WAKEUP(&dev->vbl_queue[crtc]);
+	dev->vblank_enabled[crtc] = 0;
+	dev->last_vblank[crtc] = dev->driver->get_vblank_counter(dev, crtc);
+	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+}
+EXPORT_SYMBOL(drm_vblank_off);
+
 /**
  * drm_vblank_pre_modeset - account for vblanks across mode sets
  * @dev: DRM device
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1845,6 +1845,7 @@ static void i9xx_crtc_dpms(struct drm_cr
 		intel_update_watermarks(dev);
 		/* Give the overlay scaler a chance to disable if it's on this pipe */
 		//intel_crtc_dpms_video(crtc, FALSE); TODO
+		drm_vblank_off(dev, pipe);
 
 		if (dev_priv->cfb_plane == plane &&
 		    dev_priv->display.disable_fbc)
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1295,6 +1295,7 @@ extern u32 drm_vblank_count(struct drm_d
 extern void drm_handle_vblank(struct drm_device *dev, int crtc);
 extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
+extern void drm_vblank_off(struct drm_device *dev, int crtc);
 extern void drm_vblank_cleanup(struct drm_device *dev);
 /* Modesetting support */
 extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc);

[123/151] memcg: fix memory.memsw.usage_in_bytes for root cgroup

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Kirill A. Shutemov <kirill@shutemov.name>

commit cd9b45b78a61e8df250e69385c74e729e5b66abf upstream.

A memory cgroup has a memory.memsw.usage_in_bytes file.  It shows the sum
of the usage of pages and swapents in the cgroup.  Presently the root
cgroup's memsw.usage_in_bytes shows the wrong value - the number of
swapents are not added.

So take MEM_CGROUP_STAT_SWAPOUT into account.

Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 mm/memcontrol.c |    1 +
 1 file changed, 1 insertion(+)

--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2541,6 +2541,7 @@ static u64 mem_cgroup_read(struct cgroup
 			val += idx_val;
 			mem_cgroup_get_recursive_idx_stat(mem,
 				MEM_CGROUP_STAT_SWAPOUT, &idx_val);
+			val += idx_val;
 			val <<= PAGE_SHIFT;
 		} else
 			val = res_counter_read_u64(&mem->memsw, name);

[124/151] thinkpad-acpi: fix default brightness_mode for R50e/R51

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Henrique de Moraes Holschuh <hmh@hmh.eng.br>

commit a9f8eacca4e9e8693de9b896c1fa7aadaa9402e8 upstream.

According to a report, the R50e wants EC-based brightness control,
even if it uses an Intel GPU.  The current driver default was reported
to not work at all.

This bug can be worked around by the "brightness_mode=3" module
parameter.

Change the default of the R50e and R51 2xxx models (which use the same
EC firmware, 1V) to TPACPI_BRGHT_Q_EC, but keep TPACPI_BRGHT_Q_ASK set
for now, as I'd like to get more reports.

This fixes a regression caused by commit
59fe4fe34d7afdf63208124f313be9056feaa2f4,
"thinkpad-acpi: fix incorrect use of TPACPI_BRGHT_MODE_ECNVRAM"

Kernel 2.6.31 also needs this fix.

Reported-by: Ferenc Wagner <wferi@niif.hu>
Tested-by: Ferenc Wagner <wferi@niif.hu>
Signed-off-by: Henrique de Moraes Holschuh <hmh@hmh.eng.br>
Cc: stable@kernel.org
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/platform/x86/thinkpad_acpi.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -6123,8 +6123,8 @@ static const struct tpacpi_quirk brightn
 
 	/* Models with Intel Extreme Graphics 2 */
 	TPACPI_Q_IBM('1', 'U', TPACPI_BRGHT_Q_NOEC),
-	TPACPI_Q_IBM('1', 'V', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_NOEC),
-	TPACPI_Q_IBM('1', 'W', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_NOEC),
+	TPACPI_Q_IBM('1', 'V', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC),
+	TPACPI_Q_IBM('1', 'W', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC),
 
 	/* Models with Intel GMA900 */
 	TPACPI_Q_IBM('7', '0', TPACPI_BRGHT_Q_NOEC),	/* T43, R52 */

[125/151] thinkpad-acpi: preserve rfkill state across suspend/resume

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Henrique de Moraes Holschuh <hmh@hmh.eng.br>

commit 208b996b6c460285650d39b2330f8ef82c007d10 upstream.

Since the rfkill rework in 2.6.31, the driver is always resuming with
the radios disabled.

Change thinkpad-acpi to ask the firmware to resume with the radios in
the last state.  This fixes the Bluetooth and WWAN rfkill switches.

Note that it means we respect the firmware's oddities.  Should the
user toggle the hardware rfkill switch on and off, it might cause the
radios to resume enabled.

UWB is an unknown quantity since it has nowhere the same level of
firmware support (no control over state storage in NVRAM, for
example), and might need further fixing.  Testers welcome.

This change fixes a regression from 2.6.30.

Reported-by: Jerone Young <jerone.young@canonical.com>
Reported-by: Ian Molton <ian.molton@collabora.co.uk>
Signed-off-by: Henrique de Moraes Holschuh <hmh@hmh.eng.br>
Tested-by: Ian Molton <ian.molton@collabora.co.uk>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/platform/x86/thinkpad_acpi.c |   32 +++++---------------------------
 1 file changed, 5 insertions(+), 27 deletions(-)

--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -3866,15 +3866,6 @@ enum {
 
 #define TPACPI_RFK_BLUETOOTH_SW_NAME	"tpacpi_bluetooth_sw"
 
-static void bluetooth_suspend(pm_message_t state)
-{
-	/* Try to make sure radio will resume powered off */
-	if (!acpi_evalf(NULL, NULL, "\\BLTH", "vd",
-		   TP_ACPI_BLTH_PWR_OFF_ON_RESUME))
-		vdbg_printk(TPACPI_DBG_RFKILL,
-			"bluetooth power down on resume request failed\n");
-}
-
 static int bluetooth_get_status(void)
 {
 	int status;
@@ -3908,10 +3899,9 @@ static int bluetooth_set_status(enum tpa
 #endif
 
 	/* We make sure to keep TP_ACPI_BLUETOOTH_RESUMECTRL off */
+	status = TP_ACPI_BLUETOOTH_RESUMECTRL;
 	if (state == TPACPI_RFK_RADIO_ON)
-		status = TP_ACPI_BLUETOOTH_RADIOSSW;
-	else
-		status = 0;
+		status |= TP_ACPI_BLUETOOTH_RADIOSSW;
 
 	if (!acpi_evalf(hkey_handle, NULL, "SBDC", "vd", status))
 		return -EIO;
@@ -4050,7 +4040,6 @@ static struct ibm_struct bluetooth_drive
 	.read = bluetooth_read,
 	.write = bluetooth_write,
 	.exit = bluetooth_exit,
-	.suspend = bluetooth_suspend,
 	.shutdown = bluetooth_shutdown,
 };
 
@@ -4068,15 +4057,6 @@ enum {
 
 #define TPACPI_RFK_WWAN_SW_NAME		"tpacpi_wwan_sw"
 
-static void wan_suspend(pm_message_t state)
-{
-	/* Try to make sure radio will resume powered off */
-	if (!acpi_evalf(NULL, NULL, "\\WGSV", "qvd",
-		   TP_ACPI_WGSV_PWR_OFF_ON_RESUME))
-		vdbg_printk(TPACPI_DBG_RFKILL,
-			"WWAN power down on resume request failed\n");
-}
-
 static int wan_get_status(void)
 {
 	int status;
@@ -4109,11 +4089,10 @@ static int wan_set_status(enum tpacpi_rf
 	}
 #endif
 
-	/* We make sure to keep TP_ACPI_WANCARD_RESUMECTRL off */
+	/* We make sure to set TP_ACPI_WANCARD_RESUMECTRL */
+	status = TP_ACPI_WANCARD_RESUMECTRL;
 	if (state == TPACPI_RFK_RADIO_ON)
-		status = TP_ACPI_WANCARD_RADIOSSW;
-	else
-		status = 0;
+		status |= TP_ACPI_WANCARD_RADIOSSW;
 
 	if (!acpi_evalf(hkey_handle, NULL, "SWAN", "vd", status))
 		return -EIO;
@@ -4251,7 +4230,6 @@ static struct ibm_struct wan_driver_data
 	.read = wan_read,
 	.write = wan_write,
 	.exit = wan_exit,
-	.suspend = wan_suspend,
 	.shutdown = wan_shutdown,
 };
 

[126/151] sysctl_max_map_count should be non-negative

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Amerigo Wang <amwang@redhat.com>

commit 70da2340fbc68e91e701762f785479ab495a0869 upstream.

Jan Engelhardt reported we have this problem:

setting max_map_count to a value large enough results in programs dying at
first try.  This is on 2.6.31.6:

15:59 borg:/proc/sys/vm # echo $[1<<31-1] >max_map_count
15:59 borg:/proc/sys/vm # cat max_map_count
1073741824
15:59 borg:/proc/sys/vm # echo $[1<<31] >max_map_count
15:59 borg:/proc/sys/vm # cat max_map_count
Killed

This is because we have a chance to make 'max_map_count' negative.  but
it's meaningless.  Make it only accept non-negative values.

Reported-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: James Morris <jmorris@namei.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/sysctl.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1605,7 +1605,8 @@ static struct ctl_table debug_table[] = 
 		.data		= &show_unhandled_signals,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
 	},
 #endif
 	{ .ctl_name = 0 }

[127/151] ipw2100: fix rebooting hang with driver loaded

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhu Yi <yi.zhu@intel.com>

commit 52ce3e9a7db754b78cf2cbabc87013f921b25b28 upstream.

Add PCI .shutdown method so that we can disable the device during
shutdown or reboot. Without this, the reboot doesn't work well on
some platforms.

This fixes http://bugzilla.intellinuxwireless.org/show_bug.cgi?id=2124

Tested-by: pablo <pablolm2005@gmail.com>
Signed-off-by: Zhu Yi <yi.zhu@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/wireless/ipw2x00/ipw2100.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -6487,6 +6487,16 @@ static int ipw2100_resume(struct pci_dev
 }
 #endif
 
+static void ipw2100_shutdown(struct pci_dev *pci_dev)
+{
+	struct ipw2100_priv *priv = pci_get_drvdata(pci_dev);
+
+	/* Take down the device; powers it off, etc. */
+	ipw2100_down(priv);
+
+	pci_disable_device(pci_dev);
+}
+
 #define IPW2100_DEV_ID(x) { PCI_VENDOR_ID_INTEL, 0x1043, 0x8086, x }
 
 static struct pci_device_id ipw2100_pci_id_table[] __devinitdata = {
@@ -6550,6 +6560,7 @@ static struct pci_driver ipw2100_pci_dri
 	.suspend = ipw2100_suspend,
 	.resume = ipw2100_resume,
 #endif
+	.shutdown = ipw2100_shutdown,
 };
 
 /**

[128/151] matroxfb: fix problems with display stability

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Alan Cox <alan@linux.intel.com>

commit 8c651311a3a08c1e4815de6933e00a760e498dae upstream.

Regression caused in 2.6.23 and then despite repeated requests never fixed
or dealt with (Petr promised to sort it in 2008 but seems to have
forgotten).

Enough is enough - remove the problem line that was added.  If it upsets
someone they've had two years to deal with it and at the very least it'll
rattle their cage and wake them up.

Addresses http://bugzilla.kernel.org/show_bug.cgi?id=9709

Signed-off-by: Alan Cox <alan@linux.intel.com>
Reported-by: Damon <account@bugzilla.kernel.org.juxtaposition.net>
Tested-by: Ruud van Melick <rvm1974@raketnet.nl>
Cc: Petr Vandrovec <VANDROVE@vc.cvut.cz>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Paul A. Clarke <pc@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/video/matrox/g450_pll.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/video/matrox/g450_pll.c
+++ b/drivers/video/matrox/g450_pll.c
@@ -368,7 +368,8 @@ static int __g450_setclk(struct matrox_f
 					M1064_XDVICLKCTRL_C1DVICLKEN |
 					M1064_XDVICLKCTRL_DVILOOPCTL |
 					M1064_XDVICLKCTRL_P1LOOPBWDTCTL;
-				matroxfb_DAC_out(minfo, M1064_XDVICLKCTRL, tmp);
+                                /* Setting this breaks PC systems so don't do it */
+				/* matroxfb_DAC_out(minfo, M1064_XDVICLKCTRL, tmp); */
 				matroxfb_DAC_out(minfo, M1064_XPWRCTRL,
 						 xpwrctrl);
 

[129/151] acerhdf: add new BIOS versions

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Peter Feuerer <peter@piie.net>

commit 360657463679dee44f0b167ffa61f563b4fee101 upstream.

Added new BIOS versions for following netbooks: Acer 1410, Gateway LT31,
Packard Bell DOA150.  As the Gateway LT31 machines have different register
values for setting and checking the off-state, the "cmd_off" variable has
been splitted up to "cmd_off" and "chk_off".

Signed-off-by: Peter Feuerer <peter@piie.net>
Cc: Borislav Petkov <petkovbb@gmail.com>
Cc: Andreas Mohr <andi@lisas.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/platform/x86/acerhdf.c |   63 ++++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 26 deletions(-)

--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -52,7 +52,7 @@
  */
 #undef START_IN_KERNEL_MODE
 
-#define DRV_VER "0.5.18"
+#define DRV_VER "0.5.20"
 
 /*
  * According to the Atom N270 datasheet,
@@ -112,12 +112,14 @@ module_param_string(force_product, force
 MODULE_PARM_DESC(force_product, "Force BIOS product and omit BIOS check");
 
 /*
- * cmd_off: to switch the fan completely off / to check if the fan is off
+ * cmd_off: to switch the fan completely off
+ * chk_off: to check if the fan is off
  *	cmd_auto: to set the BIOS in control of the fan. The BIOS regulates then
  *		the fan speed depending on the temperature
  */
 struct fancmd {
 	u8 cmd_off;
+	u8 chk_off;
 	u8 cmd_auto;
 };
 
@@ -134,32 +136,41 @@ struct bios_settings_t {
 /* Register addresses and values for different BIOS versions */
 static const struct bios_settings_t bios_tbl[] = {
 	/* AOA110 */
-	{"Acer", "AOA110", "v0.3109", 0x55, 0x58, {0x1f, 0x00} },
-	{"Acer", "AOA110", "v0.3114", 0x55, 0x58, {0x1f, 0x00} },
-	{"Acer", "AOA110", "v0.3301", 0x55, 0x58, {0xaf, 0x00} },
-	{"Acer", "AOA110", "v0.3304", 0x55, 0x58, {0xaf, 0x00} },
-	{"Acer", "AOA110", "v0.3305", 0x55, 0x58, {0xaf, 0x00} },
-	{"Acer", "AOA110", "v0.3307", 0x55, 0x58, {0xaf, 0x00} },
-	{"Acer", "AOA110", "v0.3308", 0x55, 0x58, {0x21, 0x00} },
-	{"Acer", "AOA110", "v0.3309", 0x55, 0x58, {0x21, 0x00} },
-	{"Acer", "AOA110", "v0.3310", 0x55, 0x58, {0x21, 0x00} },
+	{"Acer", "AOA110", "v0.3109", 0x55, 0x58, {0x1f, 0x1f, 0x00} },
+	{"Acer", "AOA110", "v0.3114", 0x55, 0x58, {0x1f, 0x1f, 0x00} },
+	{"Acer", "AOA110", "v0.3301", 0x55, 0x58, {0xaf, 0xaf, 0x00} },
+	{"Acer", "AOA110", "v0.3304", 0x55, 0x58, {0xaf, 0xaf, 0x00} },
+	{"Acer", "AOA110", "v0.3305", 0x55, 0x58, {0xaf, 0xaf, 0x00} },
+	{"Acer", "AOA110", "v0.3307", 0x55, 0x58, {0xaf, 0xaf, 0x00} },
+	{"Acer", "AOA110", "v0.3308", 0x55, 0x58, {0x21, 0x21, 0x00} },
+	{"Acer", "AOA110", "v0.3309", 0x55, 0x58, {0x21, 0x21, 0x00} },
+	{"Acer", "AOA110", "v0.3310", 0x55, 0x58, {0x21, 0x21, 0x00} },
 	/* AOA150 */
-	{"Acer", "AOA150", "v0.3114", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3301", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3304", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3305", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3307", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3308", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3309", 0x55, 0x58, {0x20, 0x00} },
-	{"Acer", "AOA150", "v0.3310", 0x55, 0x58, {0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3114", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3301", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3304", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3305", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3307", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3308", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3309", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Acer", "AOA150", "v0.3310", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	/* Acer 1410 */
+	{"Acer", "Aspire 1410", "v0.3120", 0x55, 0x58, {0x9e, 0x9e, 0x00} },
 	/* special BIOS / other */
-	{"Gateway", "AOA110", "v0.3103", 0x55, 0x58, {0x21, 0x00} },
-	{"Gateway", "AOA150", "v0.3103", 0x55, 0x58, {0x20, 0x00} },
-	{"Packard Bell", "DOA150", "v0.3104", 0x55, 0x58, {0x21, 0x00} },
-	{"Packard Bell", "AOA110", "v0.3105", 0x55, 0x58, {0x21, 0x00} },
-	{"Packard Bell", "AOA150", "v0.3105", 0x55, 0x58, {0x20, 0x00} },
+	{"Gateway", "AOA110", "v0.3103", 0x55, 0x58, {0x21, 0x21, 0x00} },
+	{"Gateway", "AOA150", "v0.3103", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Gateway         ", "LT31            ", "v1.3103 ", 0x55, 0x58,
+		{0x10, 0x0f, 0x00} },
+	{"Gateway         ", "LT31            ", "v1.3201 ", 0x55, 0x58,
+		{0x10, 0x0f, 0x00} },
+	{"Gateway         ", "LT31            ", "v1.3302 ", 0x55, 0x58,
+		{0x10, 0x0f, 0x00} },
+	{"Packard Bell", "DOA150", "v0.3104", 0x55, 0x58, {0x21, 0x21, 0x00} },
+	{"Packard Bell", "DOA150", "v0.3105", 0x55, 0x58, {0x20, 0x20, 0x00} },
+	{"Packard Bell", "AOA110", "v0.3105", 0x55, 0x58, {0x21, 0x21, 0x00} },
+	{"Packard Bell", "AOA150", "v0.3105", 0x55, 0x58, {0x20, 0x20, 0x00} },
 	/* pewpew-terminator */
-	{"", "", "", 0, 0, {0, 0} }
+	{"", "", "", 0, 0, {0, 0, 0} }
 };
 
 static const struct bios_settings_t *bios_cfg __read_mostly;
@@ -183,7 +194,7 @@ static int acerhdf_get_fanstate(int *sta
 	if (ec_read(bios_cfg->fanreg, &fan))
 		return -EINVAL;
 
-	if (fan != bios_cfg->cmd.cmd_off)
+	if (fan != bios_cfg->cmd.chk_off)
 		*state = ACERHDF_FAN_AUTO;
 	else
 		*state = ACERHDF_FAN_OFF;

[130/151] asus-laptop: change light sens default values.

[Greg KH]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 1721 bytes --]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Corentin Chary <corentincj@iksaif.net>

commit d951d4cc84e8b5ddb8e0ab81cf6a72cc73fdd668 upstream.

The light sensor disable brightness key and
/sys/class/backlight/ control. There was a lot of report
from users who didn't understand why they couldn't change their
brightness, including:

https://bugs.launchpad.net/bugs/222171
https://bugzilla.novell.com/show_bug.cgi?id=514747
http://bugzilla.kernel.org/show_bug.cgi?id=13671
http://bugzilla.kernel.org/show_bug.cgi?id=14432

Now the light sensor is disabled, and if the user want to enable
it, the level should be ok.

The funny thing is that comments where ok, not code.

Cc: stable@kernel.org
Cc: Thomas Renninger <trenn@suse.de>
Cc: Peter Küppers <peter-mailbox@web.de>
Cc: Michael Franzl <michaelfranzl@gmx.at>
Cc: Ian Turner <vectro@vectro.org>
Signed-off-by: Corentin Chary <corentincj@iksaif.net>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/platform/x86/asus-laptop.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -1283,8 +1283,8 @@ static int asus_hotk_add(struct acpi_dev
 	hotk->ledd_status = 0xFFF;
 
 	/* Set initial values of light sensor and level */
-	hotk->light_switch = 1;	/* Default to light sensor disabled */
-	hotk->light_level = 0;	/* level 5 for sensor sensitivity */
+	hotk->light_switch = 0;	/* Default to light sensor disabled */
+	hotk->light_level = 5;	/* level 5 for sensor sensitivity */
 
 	if (ls_switch_handle)
 		set_light_sens_switch(hotk->light_switch);

[131/151] vmalloc: conditionalize build of pcpu_get_vm_areas()

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Tejun Heo <teheo@novell.com>

No matching upstream commit as it was resolved differently there.


pcpu_get_vm_areas() is used only when dynamic percpu allocator is used
by the architecture.  In 2.6.32, ia64 doesn't use dynamic percpu
allocator and has a macro which makes pcpu_get_vm_areas() buggy via
local/global variable aliasing and triggers compile warning.

The problem is fixed in upstream and ia64 uses dynamic percpu
allocators, so the only left issue is inclusion of unnecessary code
and compile warning on ia64 on 2.6.32.

Don't build pcpu_get_vm_areas() if legacy percpu allocator is in use.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Jan Beulich <JBeulich@novell.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 include/linux/vmalloc.h |    2 ++
 mm/vmalloc.c            |    2 ++
 2 files changed, 4 insertions(+)

--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -115,9 +115,11 @@ extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 				     const size_t *sizes, int nr_vms,
 				     size_t align, gfp_t gfp_mask);
+#endif
 
 void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
 
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1993,6 +1993,7 @@ void free_vm_area(struct vm_struct *area
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
 
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
 	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
@@ -2257,6 +2258,7 @@ err_free:
 	kfree(vms);
 	return NULL;
 }
+#endif
 
 /**
  * pcpu_free_vm_areas - free vmalloc areas for percpu allocator

[132/151] ACPI: Use the ARB_DISABLE for the CPU which model id is less than 0x0f.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhao Yakui <yakui.zhao@intel.com>

commit 03a05ed1152944000151d57b71000de287a1eb02 upstream.

Currently, ARB_DISABLE is a NOP on all of the recent Intel platforms.
For such platforms, reduce contention on c3_lock by skipping the fake
ARB_DISABLE.

The cpu model id on one laptop is 14. If we disable ARB_DISABLE on this box,
the box can't be booted correctly. But if we still enable ARB_DISABLE on this
box, the box can be booted correctly.

So we still use the ARB_DISABLE for the cpu which mode id is less than 0x0f.

http://bugzilla.kernel.org/show_bug.cgi?id=14700

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Acked-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/kernel/acpi/cstate.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -48,7 +48,7 @@ void acpi_processor_power_init_bm_check(
 	 * P4, Core and beyond CPUs
 	 */
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
-	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 14)))
+	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
 			flags->bm_control = 0;
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);

[133/151] net: Fix userspace RTM_NEWLINK notifications.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

commit d90a909e1f3e006a1d57fe11fd417173b6494701 upstream.

I received some bug reports about userspace programs having problems
because after RTM_NEWLINK was received they could not immeidate
access files under /proc/sys/net/ because they had not been
registered yet.

The problem was trivailly fixed by moving the userspace
notification from rtnetlink_event to the end of register_netdevice.

Signed-off-by: Eric W. Biederman <ebiederm@aristanetworks.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/core/dev.c       |   11 +++++++++++
 net/core/rtnetlink.c |    4 +---
 2 files changed, 12 insertions(+), 3 deletions(-)

--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4860,6 +4860,11 @@ int register_netdevice(struct net_device
 		rollback_registered(dev);
 		dev->reg_state = NETREG_UNREGISTERED;
 	}
+	/*
+	 *	Prevent userspace races by waiting until the network
+	 *	device is fully setup before sending notifications.
+	 */
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
 
 out:
 	return ret;
@@ -5398,6 +5403,12 @@ int dev_change_net_namespace(struct net_
 	/* Notify protocols, that a new device appeared. */
 	call_netdevice_notifiers(NETDEV_REGISTER, dev);
 
+	/*
+	 *	Prevent userspace races by waiting until the network
+	 *	device is fully setup before sending notifications.
+	 */
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+
 	synchronize_net();
 	err = 0;
 out:
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1334,13 +1334,11 @@ static int rtnetlink_event(struct notifi
 	case NETDEV_UNREGISTER:
 		rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
 		break;
-	case NETDEV_REGISTER:
-		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
-		break;
 	case NETDEV_UP:
 	case NETDEV_DOWN:
 		rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
 		break;
+	case NETDEV_REGISTER:
 	case NETDEV_CHANGE:
 	case NETDEV_GOING_DOWN:
 		break;

[134/151] ext3: Fix data / filesystem corruption when write fails to copy data

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jan Kara <jack@suse.cz>

commit 68eb3db08344286733adac48304d9fb7a0e53b27 upstream.

When ext3_write_begin fails after allocating some blocks or
generic_perform_write fails to copy data to write, we truncate blocks already
instantiated beyond i_size. Although these blocks were never inside i_size, we
have to truncate pagecache of these blocks so that corresponding buffers get
unmapped. Otherwise subsequent __block_prepare_write (called because we are
retrying the write) will find the buffers mapped, not call ->get_block, and
thus the page will be backed by already freed blocks leading to filesystem and
data corruption.

Reported-by: James Y Knight <foom@fuhm.net>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/ext3/inode.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1151,6 +1151,16 @@ static int do_journal_get_write_access(h
 	return ext3_journal_get_write_access(handle, bh);
 }
 
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext3_truncate_failed_write(struct inode *inode)
+{
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext3_truncate(inode);
+}
+
 static int ext3_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
@@ -1209,7 +1219,7 @@ write_begin_failed:
 		unlock_page(page);
 		page_cache_release(page);
 		if (pos + len > inode->i_size)
-			ext3_truncate(inode);
+			ext3_truncate_failed_write(inode);
 	}
 	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
@@ -1304,7 +1314,7 @@ static int ext3_ordered_write_end(struct
 	page_cache_release(page);
 
 	if (pos + len > inode->i_size)
-		ext3_truncate(inode);
+		ext3_truncate_failed_write(inode);
 	return ret ? ret : copied;
 }
 
@@ -1330,7 +1340,7 @@ static int ext3_writeback_write_end(stru
 	page_cache_release(page);
 
 	if (pos + len > inode->i_size)
-		ext3_truncate(inode);
+		ext3_truncate_failed_write(inode);
 	return ret ? ret : copied;
 }
 
@@ -1383,7 +1393,7 @@ static int ext3_journalled_write_end(str
 	page_cache_release(page);
 
 	if (pos + len > inode->i_size)
-		ext3_truncate(inode);
+		ext3_truncate_failed_write(inode);
 	return ret ? ret : copied;
 }
 

[135/151] V4L/DVB (13116): gspca - ov519: Webcam 041e:4067 added.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Rafal Milecki <zajec5@gmail.com>

commit 518c8df77c21b7d1690dd8b96eb0e54c4ec1c9c1 upstream.

Signed-off-by: Rafal Milecki <zajec5@gmail.com>
Signed-off-by: Jean-Francois Moine <moinejf@free.fr>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Cc: Surbhi Palande <surbhi.palande@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -37,6 +37,7 @@ ov519		041e:405f	Creative Live! VISTA VF0330
 ov519		041e:4060	Creative Live! VISTA VF0350
 ov519		041e:4061	Creative Live! VISTA VF0400
 ov519		041e:4064	Creative Live! VISTA VF0420
+ov519		041e:4067	Creative Live! Cam Video IM (VF0350)
 ov519		041e:4068	Creative Live! VISTA VF0470
 spca561		0458:7004	Genius VideoCAM Express V2
 sunplus		0458:7006	Genius Dsc 1.3 Smart
diff --git a/drivers/media/video/gspca/ov519.c b/drivers/media/video/gspca/ov519.c
index a5c190e..e165578 100644
--- a/drivers/media/video/gspca/ov519.c
+++ b/drivers/media/video/gspca/ov519.c
@@ -3364,6 +3364,7 @@ static const __devinitdata struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x041e, 0x4061), .driver_info = BRIDGE_OV519 },
 	{USB_DEVICE(0x041e, 0x4064),
 	 .driver_info = BRIDGE_OV519 | BRIDGE_INVERT_LED },
+	{USB_DEVICE(0x041e, 0x4067), .driver_info = BRIDGE_OV519 },
 	{USB_DEVICE(0x041e, 0x4068),
 	 .driver_info = BRIDGE_OV519 | BRIDGE_INVERT_LED },
 	{USB_DEVICE(0x045e, 0x028c), .driver_info = BRIDGE_OV519 },

[136/151] bcm63xx_enet: fix compilation failure after get_stats_count removal

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Florian Fainelli <ffainelli@freebox.fr>

commit a3f92eea04101d9a8e14d50f8048cc5b7bca07a8 upstream.

This patch converts bcm63xx_enet to uset get_sset_count
like the other drivers do.

Signed-off-by: Florian Fainelli <ffainelli@freebox.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/net/bcm63xx_enet.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

--- a/drivers/net/bcm63xx_enet.c
+++ b/drivers/net/bcm63xx_enet.c
@@ -1248,9 +1248,15 @@ static void bcm_enet_get_drvinfo(struct 
 	drvinfo->n_stats = BCM_ENET_STATS_LEN;
 }
 
-static int bcm_enet_get_stats_count(struct net_device *netdev)
+static int bcm_enet_get_sset_count(struct net_device *netdev,
+					int string_set)
 {
-	return BCM_ENET_STATS_LEN;
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return BCM_ENET_STATS_LEN;
+	default:
+		return -EINVAL;
+	}
 }
 
 static void bcm_enet_get_strings(struct net_device *netdev,
@@ -1476,7 +1482,7 @@ static int bcm_enet_set_pauseparam(struc
 
 static struct ethtool_ops bcm_enet_ethtool_ops = {
 	.get_strings		= bcm_enet_get_strings,
-	.get_stats_count	= bcm_enet_get_stats_count,
+	.get_sset_count		= bcm_enet_get_sset_count,
 	.get_ethtool_stats      = bcm_enet_get_ethtool_stats,
 	.get_settings		= bcm_enet_get_settings,
 	.set_settings		= bcm_enet_set_settings,

[137/151] x86: Under BIOS control, restore APs APIC_LVTTHMR to the BSP value

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Yong Wang <yong.y.wang@linux.intel.com>

Upstream commit a2202aa29289db64ca7988b12343158b67b27f10.

On platforms where bios handles the thermal monitor interrupt,
APIC_LVTTHMR on each logical CPU is programmed to generate a SMI and OS
can't touch it.

Unfortunately AP bringup sequence using INIT-SIPI-SIPI clear all
the LVT entries except the mask bit. Essentially this results in
all LVT entries including the thermal monitoring interrupt set to masked
(clearing the bios programmed value for APIC_LVTTHMR).

And this leads to kernel take over the thermal monitoring interrupt
on AP's but not on BSP (leaving the bios programmed value only on BSP).

As a result of this, we have seen system hangs when the thermal
monitoring interrupt is generated.

Fix this by reading the initial value of thermal LVT entry on BSP
and if bios has taken over the control, then program the same value
on all AP's and leave the thermal monitoring interrupt control
on all the logical cpu's to the bios.

Signed-off-by: Yong Wang <yong.y.wang@intel.com>
Reviewed-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Borislav Petkov <borislav.petkov@amd.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <20091110013824.GA24940@ywang-moblin2.bj.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/x86/include/asm/mce.h               |    6 ++++++
 arch/x86/kernel/cpu/mcheck/therm_throt.c |   29 ++++++++++++++++++++++++++++-
 arch/x86/kernel/setup.c                  |    3 +++
 3 files changed, 37 insertions(+), 1 deletion(-)

--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -214,5 +214,11 @@ void intel_init_thermal(struct cpuinfo_x
 
 void mce_log_therm_throt_event(__u64 status);
 
+#ifdef CONFIG_X86_THERMAL_VECTOR
+extern void mcheck_intel_therm_init(void);
+#else
+static inline void mcheck_intel_therm_init(void) { }
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -49,6 +49,8 @@ static DEFINE_PER_CPU(struct thermal_sta
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
 
+static u32 lvtthmr_init __read_mostly;
+
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)				\
 	static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)
@@ -254,6 +256,18 @@ asmlinkage void smp_thermal_interrupt(st
 	ack_APIC_irq();
 }
 
+void __init mcheck_intel_therm_init(void)
+{
+	/*
+	 * This function is only called on boot CPU. Save the init thermal
+	 * LVT value on BSP and use that value to restore APs' thermal LVT
+	 * entry BIOS programmed later
+	 */
+	if (cpu_has(&boot_cpu_data, X86_FEATURE_ACPI) &&
+		cpu_has(&boot_cpu_data, X86_FEATURE_ACC))
+		lvtthmr_init = apic_read(APIC_LVTTHMR);
+}
+
 void intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	unsigned int cpu = smp_processor_id();
@@ -270,7 +284,20 @@ void intel_init_thermal(struct cpuinfo_x
 	 * since it might be delivered via SMI already:
 	 */
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-	h = apic_read(APIC_LVTTHMR);
+
+	/*
+	 * The initial value of thermal LVT entries on all APs always reads
+	 * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
+	 * sequence to them and LVT registers are reset to 0s except for
+	 * the mask bits which are set to 1s when APs receive INIT IPI.
+	 * Always restore the value that BIOS has programmed on AP based on
+	 * BSP's info we saved since BIOS is always setting the same value
+	 * for all threads/cores
+	 */
+	apic_write(APIC_LVTTHMR, lvtthmr_init);
+
+	h = lvtthmr_init;
+
 	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG
 		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -109,6 +109,7 @@
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
+#include <asm/mce.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -1031,6 +1032,8 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #endif
 	x86_init.oem.banner();
+
+	mcheck_intel_therm_init();
 }
 
 #ifdef CONFIG_X86_32

[138/151] drm/i915: Avoid NULL dereference with component_only tv_modes

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Chris Wilson <chris@chris-wilson.co.uk>

commit d271817baecbccb47da0d9f28c285a0dae8a06b7 upstream.

In commit d2d9f2324, the guard for a valid video mode was removed. This
caused the regression:

  kernel crash during kms graphic boot on Intel GM4500 platform
  https://bugzilla.redhat.com/show_bug.cgi?id=540218

This patches changes the logic slightly not to rely on a coupled
variable, but to just check whether the video_modes is valid before
dereferencing.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Zhenyu Wang <zhenyu.z.wang@intel.com>
[ickle: Actually reference the correct bug report]
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/i915/intel_tv.c |   11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1213,20 +1213,17 @@ intel_tv_mode_set(struct drm_encoder *en
 		tv_ctl |= TV_TRILEVEL_SYNC;
 	if (tv_mode->pal_burst)
 		tv_ctl |= TV_PAL_BURST;
+
 	scctl1 = 0;
-	/* dda1 implies valid video levels */
-	if (tv_mode->dda1_inc) {
+	if (tv_mode->dda1_inc)
 		scctl1 |= TV_SC_DDA1_EN;
-	}
-
 	if (tv_mode->dda2_inc)
 		scctl1 |= TV_SC_DDA2_EN;
-
 	if (tv_mode->dda3_inc)
 		scctl1 |= TV_SC_DDA3_EN;
-
 	scctl1 |= tv_mode->sc_reset;
-	scctl1 |= video_levels->burst << TV_BURST_LEVEL_SHIFT;
+	if (video_levels)
+		scctl1 |= video_levels->burst << TV_BURST_LEVEL_SHIFT;
 	scctl1 |= tv_mode->dda1_inc << TV_SCDDA1_INC_SHIFT;
 
 	scctl2 = tv_mode->dda2_size << TV_SCDDA2_SIZE_SHIFT |

[139/151] drm/i915: PineView only has LVDS and CRT ports

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhenyu Wang <zhenyuw@linux.intel.com>

commit 103a196f4224dc6872081305cf7f82ebf67aa7bd upstream.

PineView only has 2 ports for LVDS and CRT. Don't enable other
ports for it.

Cc: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/i915/i915_drv.h      |    4 ++++
 drivers/gpu/drm/i915/intel_display.c |    6 +++---
 2 files changed, 7 insertions(+), 3 deletions(-)

--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -957,6 +957,7 @@ extern int i915_wait_ring(struct drm_dev
 #define IS_I85X(dev) ((dev)->pci_device == 0x3582)
 #define IS_I855(dev) ((dev)->pci_device == 0x3582)
 #define IS_I865G(dev) ((dev)->pci_device == 0x2572)
+#define IS_I8XX(dev) (IS_I830(dev) || IS_845G(dev) || IS_I85X(dev) || IS_I865G(dev))
 
 #define IS_I915G(dev) ((dev)->pci_device == 0x2582 || (dev)->pci_device == 0x258a)
 #define IS_I915GM(dev) ((dev)->pci_device == 0x2592)
@@ -1018,9 +1019,12 @@ extern int i915_wait_ring(struct drm_dev
  */
 #define HAS_128_BYTE_Y_TILING(dev) (IS_I9XX(dev) && !(IS_I915G(dev) || \
 						      IS_I915GM(dev)))
+#define SUPPORTS_DIGITAL_OUTPUTS(dev)	(IS_I9XX(dev) && !IS_IGD(dev))
 #define SUPPORTS_INTEGRATED_HDMI(dev)	(IS_G4X(dev) || IS_IGDNG(dev))
 #define SUPPORTS_INTEGRATED_DP(dev)	(IS_G4X(dev) || IS_IGDNG(dev))
 #define SUPPORTS_EDP(dev)		(IS_IGDNG_M(dev))
+#define SUPPORTS_TV(dev)		(IS_I9XX(dev) && IS_MOBILE(dev) && \
+					!IS_IGDNG(dev) && !IS_IGD(dev))
 #define I915_HAS_HOTPLUG(dev) (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev) || IS_I965G(dev))
 /* dsparb controlled by hw only */
 #define DSPARB_HWCONTROL(dev) (IS_G4X(dev) || IS_IGDNG(dev))
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4119,7 +4119,7 @@ static void intel_setup_outputs(struct d
 		if (I915_READ(PCH_DP_D) & DP_DETECTED)
 			intel_dp_init(dev, PCH_DP_D);
 
-	} else if (IS_I9XX(dev)) {
+	} else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) {
 		bool found = false;
 
 		if (I915_READ(SDVOB) & SDVO_DETECTED) {
@@ -4146,10 +4146,10 @@ static void intel_setup_outputs(struct d
 
 		if (SUPPORTS_INTEGRATED_DP(dev) && (I915_READ(DP_D) & DP_DETECTED))
 			intel_dp_init(dev, DP_D);
-	} else
+	} else if (IS_I8XX(dev))
 		intel_dvo_init(dev);
 
-	if (IS_I9XX(dev) && IS_MOBILE(dev) && !IS_IGDNG(dev))
+	if (SUPPORTS_TV(dev))
 		intel_tv_init(dev);
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {

[140/151] drm/i915: Fix LVDS stability issue on Ironlake

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Zhenyu Wang <zhenyuw@linux.intel.com>

commit 1b3c7a47f993bf9ab6c4c7cc3bbf5588052b58f4 upstream.

In disable sequence, all output ports on PCH have to be disabled
before PCH transcoder, but LVDS port was left always enabled. This
one fixes that by disable LVDS port properly during pipe disable
process, and resolved stability issue seen on Ironlake. Also move
panel fitting disable time just after pipe disable to align with
the spec.

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/gpu/drm/i915/intel_display.c |   60 +++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 19 deletions(-)

--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1482,6 +1482,15 @@ static void igdng_crtc_dpms(struct drm_c
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 		DRM_DEBUG("crtc %d dpms on\n", pipe);
+
+		if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
+			temp = I915_READ(PCH_LVDS);
+			if ((temp & LVDS_PORT_EN) == 0) {
+				I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN);
+				POSTING_READ(PCH_LVDS);
+			}
+		}
+
 		if (HAS_eDP) {
 			/* enable eDP PLL */
 			igdng_enable_pll_edp(crtc);
@@ -1666,8 +1675,6 @@ static void igdng_crtc_dpms(struct drm_c
 	case DRM_MODE_DPMS_OFF:
 		DRM_DEBUG("crtc %d dpms off\n", pipe);
 
-		i915_disable_vga(dev);
-
 		/* Disable display plane */
 		temp = I915_READ(dspcntr_reg);
 		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
@@ -1677,6 +1684,8 @@ static void igdng_crtc_dpms(struct drm_c
 			I915_READ(dspbase_reg);
 		}
 
+		i915_disable_vga(dev);
+
 		/* disable cpu pipe, disable after all planes disabled */
 		temp = I915_READ(pipeconf_reg);
 		if ((temp & PIPEACONF_ENABLE) != 0) {
@@ -1697,9 +1706,15 @@ static void igdng_crtc_dpms(struct drm_c
 		} else
 			DRM_DEBUG("crtc %d is disabled\n", pipe);
 
-		if (HAS_eDP) {
-			igdng_disable_pll_edp(crtc);
+		udelay(100);
+
+		/* Disable PF */
+		temp = I915_READ(pf_ctl_reg);
+		if ((temp & PF_ENABLE) != 0) {
+			I915_WRITE(pf_ctl_reg, temp & ~PF_ENABLE);
+			I915_READ(pf_ctl_reg);
 		}
+		I915_WRITE(pf_win_size, 0);
 
 		/* disable CPU FDI tx and PCH FDI rx */
 		temp = I915_READ(fdi_tx_reg);
@@ -1725,6 +1740,13 @@ static void igdng_crtc_dpms(struct drm_c
 
 		udelay(100);
 
+		if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) {
+			temp = I915_READ(PCH_LVDS);
+			I915_WRITE(PCH_LVDS, temp & ~LVDS_PORT_EN);
+			I915_READ(PCH_LVDS);
+			udelay(100);
+		}
+
 		/* disable PCH transcoder */
 		temp = I915_READ(transconf_reg);
 		if ((temp & TRANS_ENABLE) != 0) {
@@ -1744,6 +1766,8 @@ static void igdng_crtc_dpms(struct drm_c
 			}
 		}
 
+		udelay(100);
+
 		/* disable PCH DPLL */
 		temp = I915_READ(pch_dpll_reg);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
@@ -1751,14 +1775,20 @@ static void igdng_crtc_dpms(struct drm_c
 			I915_READ(pch_dpll_reg);
 		}
 
-		temp = I915_READ(fdi_rx_reg);
-		if ((temp & FDI_RX_PLL_ENABLE) != 0) {
-			temp &= ~FDI_SEL_PCDCLK;
-			temp &= ~FDI_RX_PLL_ENABLE;
-			I915_WRITE(fdi_rx_reg, temp);
-			I915_READ(fdi_rx_reg);
+		if (HAS_eDP) {
+			igdng_disable_pll_edp(crtc);
 		}
 
+		temp = I915_READ(fdi_rx_reg);
+		temp &= ~FDI_SEL_PCDCLK;
+		I915_WRITE(fdi_rx_reg, temp);
+		I915_READ(fdi_rx_reg);
+
+		temp = I915_READ(fdi_rx_reg);
+		temp &= ~FDI_RX_PLL_ENABLE;
+		I915_WRITE(fdi_rx_reg, temp);
+		I915_READ(fdi_rx_reg);
+
 		/* Disable CPU FDI TX PLL */
 		temp = I915_READ(fdi_tx_reg);
 		if ((temp & FDI_TX_PLL_ENABLE) != 0) {
@@ -1767,16 +1797,8 @@ static void igdng_crtc_dpms(struct drm_c
 			udelay(100);
 		}
 
-		/* Disable PF */
-		temp = I915_READ(pf_ctl_reg);
-		if ((temp & PF_ENABLE) != 0) {
-			I915_WRITE(pf_ctl_reg, temp & ~PF_ENABLE);
-			I915_READ(pf_ctl_reg);
-		}
-		I915_WRITE(pf_win_size, 0);
-
 		/* Wait for the clocks to turn off. */
-		udelay(150);
+		udelay(100);
 		break;
 	}
 }

[141/151] mm: sigbus instead of abusing oom

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Hugh Dickins <hugh.dickins@tiscali.co.uk>

commit d99be1a8ecf377c2c9b3372d36411ad6547bbd4c upstream.

When do_nonlinear_fault() realizes that the page table must have been
corrupted for it to have been called, it does print_bad_pte() and returns
...  VM_FAULT_OOM, which is hard to understand.

It made some sense when I did it for 2.6.15, when do_page_fault() just
killed the current process; but nowadays it lets the OOM killer decide who
to kill - so page table corruption in one process would be liable to kill
another.

Change it to return VM_FAULT_SIGBUS instead: that doesn't guarantee that
the process will be killed, but is good enough for such a rare
abnormality, accompanied as it is by the "BUG: Bad page map" message.

And recent HWPOISON work has copied that code into do_swap_page(), when it
finds an impossible swap entry: fix that to VM_FAULT_SIGBUS too.

Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Nick Piggin <npiggin@suse.de>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <andi@firstfloor.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 mm/memory.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2514,7 +2514,7 @@ static int do_swap_page(struct mm_struct
 			ret = VM_FAULT_HWPOISON;
 		} else {
 			print_bad_pte(vma, address, orig_pte, NULL);
-			ret = VM_FAULT_OOM;
+			ret = VM_FAULT_SIGBUS;
 		}
 		goto out;
 	}
@@ -2910,7 +2910,7 @@ static int do_nonlinear_fault(struct mm_
 		 * Page table corrupted: show pte and kill process.
 		 */
 		print_bad_pte(vma, address, orig_pte, NULL);
-		return VM_FAULT_OOM;
+		return VM_FAULT_SIGBUS;
 	}
 
 	pgoff = pte_to_pgoff(orig_pte);

[142/151] ipvs: zero usvc and udest

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Simon Horman <horms@verge.net.au>

commit 258c889362aa95d0ab534b38ce8c15d3009705b1 upstream.

Make sure that any otherwise uninitialised fields of usvc are zero.

This has been obvserved to cause a problem whereby the port of
fwmark services may end up as a non-zero value which causes
scheduling of a destination server to fail for persisitent services.

As observed by Deon van der Merwe <dvdm@truteq.co.za>.
This fix suggested by Julian Anastasov <ja@ssi.bg>.

For good measure also zero udest.

Cc: Deon van der Merwe <dvdm@truteq.co.za>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 net/netfilter/ipvs/ip_vs_ctl.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2714,6 +2714,8 @@ static int ip_vs_genl_parse_service(stru
 	if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr))))
 		return -EINVAL;
 
+	memset(usvc, 0, sizeof(*usvc));
+
 	usvc->af = nla_get_u16(nla_af);
 #ifdef CONFIG_IP_VS_IPV6
 	if (usvc->af != AF_INET && usvc->af != AF_INET6)
@@ -2901,6 +2903,8 @@ static int ip_vs_genl_parse_dest(struct 
 	if (!(nla_addr && nla_port))
 		return -EINVAL;
 
+	memset(udest, 0, sizeof(*udest));
+
 	nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
 	udest->port = nla_get_u16(nla_port);
 

[143/151] jffs2: Fix long-standing bug with symlink garbage collection.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David Woodhouse <David.Woodhouse@intel.com>

commit 2e16cfca6e17ae37ae21feca080a6f2eca9087dc upstream.

Ever since jffs2_garbage_collect_metadata() was first half-written in
February 2001, it's been broken on architectures where 'char' is signed.
When garbage collecting a symlink with target length above 127, the payload
length would end up negative, causing interesting and bad things to happen.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 fs/jffs2/gc.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -700,7 +700,8 @@ static int jffs2_garbage_collect_metadat
 	struct jffs2_raw_inode ri;
 	struct jffs2_node_frag *last_frag;
 	union jffs2_device_node dev;
-	char *mdata = NULL, mdatalen = 0;
+	char *mdata = NULL;
+	int mdatalen = 0;
 	uint32_t alloclen, ilen;
 	int ret;
 

[144/151] intel-iommu: Detect DMAR in hyperspace at probe time.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Chris Wright <chrisw@sous-sol.org>

commit 2c99220810c1c79322034628b993573b088ff2da upstream.

Many BIOSes will lie to us about the existence of an IOMMU, and claim
that there is one at an address which actually returns all 0xFF.

We need to detect this early, so that we know we don't have a viable
IOMMU and can set up swiotlb before it's too late.

Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/pci/dmar.c |   34 +++++++++++++++++++++++++++++-----
 1 file changed, 29 insertions(+), 5 deletions(-)

--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -601,6 +601,9 @@ int __init check_zero_address(void)
 		}
 
 		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
+			void __iomem *addr;
+			u64 cap, ecap;
+
 			drhd = (void *)entry_header;
 			if (!drhd->address) {
 				/* Promote an attitude of violence to a BIOS engineer today */
@@ -609,17 +612,38 @@ int __init check_zero_address(void)
 				     dmi_get_system_info(DMI_BIOS_VENDOR),
 				     dmi_get_system_info(DMI_BIOS_VERSION),
 				     dmi_get_system_info(DMI_PRODUCT_VERSION));
-#ifdef CONFIG_DMAR
-				dmar_disabled = 1;
-#endif
-				return 0;
+				goto failed;
+			}
+
+			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
+			if (!addr ) {
+				printk("IOMMU: can't validate: %llx\n", drhd->address);
+				goto failed;
+			}
+			cap = dmar_readq(addr + DMAR_CAP_REG);
+			ecap = dmar_readq(addr + DMAR_ECAP_REG);
+			early_iounmap(addr, VTD_PAGE_SIZE);
+			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
+				/* Promote an attitude of violence to a BIOS engineer today */
+				WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
+				     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+				      drhd->address,
+				      dmi_get_system_info(DMI_BIOS_VENDOR),
+				      dmi_get_system_info(DMI_BIOS_VERSION),
+				      dmi_get_system_info(DMI_PRODUCT_VERSION));
+				goto failed;
 			}
-			break;
 		}
 
 		entry_header = ((void *)entry_header + entry_header->length);
 	}
 	return 1;
+
+failed:
+#ifdef CONFIG_DMAR
+	dmar_disabled = 1;
+#endif
+	return 0;
 }
 
 void __init detect_intel_iommu(void)

[145/151] intel-iommu: Apply BIOS sanity checks for interrupt remapping too.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David Woodhouse <David.Woodhouse@intel.com>

commit 6ecbf01c7ce4c0f4c3bdfa0e64ac6258328fda6c upstream.

The BIOS errors where an IOMMU is reported either at zero or a bogus
address are causing problems even when the IOMMU is disabled -- because
interrupt remapping uses the same hardware. Ensure that the checks get
applied for the interrupt remapping initialisation too.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/pci/dmar.c |   33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -582,6 +582,8 @@ int __init dmar_table_init(void)
 	return 0;
 }
 
+static int bios_warned;
+
 int __init check_zero_address(void)
 {
 	struct acpi_table_dmar *dmar;
@@ -612,6 +614,7 @@ int __init check_zero_address(void)
 				     dmi_get_system_info(DMI_BIOS_VENDOR),
 				     dmi_get_system_info(DMI_BIOS_VERSION),
 				     dmi_get_system_info(DMI_PRODUCT_VERSION));
+				bios_warned = 1;
 				goto failed;
 			}
 
@@ -631,6 +634,7 @@ int __init check_zero_address(void)
 				      dmi_get_system_info(DMI_BIOS_VENDOR),
 				      dmi_get_system_info(DMI_BIOS_VERSION),
 				      dmi_get_system_info(DMI_PRODUCT_VERSION));
+				bios_warned = 1;
 				goto failed;
 			}
 		}
@@ -688,6 +692,18 @@ int alloc_iommu(struct dmar_drhd_unit *d
 	int agaw = 0;
 	int msagaw = 0;
 
+	if (!drhd->reg_base_addr) {
+		if (!bios_warned) {
+			WARN(1, "Your BIOS is broken; DMAR reported at address zero!\n"
+			     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			     dmi_get_system_info(DMI_BIOS_VENDOR),
+			     dmi_get_system_info(DMI_BIOS_VERSION),
+			     dmi_get_system_info(DMI_PRODUCT_VERSION));
+			bios_warned = 1;
+		}
+		return -EINVAL;
+	}
+
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
 		return -ENOMEM;
@@ -704,13 +720,16 @@ int alloc_iommu(struct dmar_drhd_unit *d
 	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);
 
 	if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
-		/* Promote an attitude of violence to a BIOS engineer today */
-		WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
-		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-		     drhd->reg_base_addr,
-		     dmi_get_system_info(DMI_BIOS_VENDOR),
-		     dmi_get_system_info(DMI_BIOS_VERSION),
-		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		if (!bios_warned) {
+			/* Promote an attitude of violence to a BIOS engineer today */
+			WARN(1, "Your BIOS is broken; DMAR reported at address %llx returns all ones!\n"
+			     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			     drhd->reg_base_addr,
+			     dmi_get_system_info(DMI_BIOS_VENDOR),
+			     dmi_get_system_info(DMI_BIOS_VERSION),
+			     dmi_get_system_info(DMI_PRODUCT_VERSION));
+			bios_warned = 1;
+		}
 		goto err_unmap;
 	}
 

[146/151] intel-iommu: Check for an RMRR which ends before it starts.

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David Woodhouse <David.Woodhouse@intel.com>

commit 5595b528b49a702c0428c0762bab60999648254c upstream.

Some HP BIOSes report an RMRR region (a region which needs a 1:1 mapping
in the IOMMU for a given device) which has an end address lower than its
start address. Detect that and warn, rather than triggering the
BUG() in dma_pte_clear_range().

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/pci/intel-iommu.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1991,6 +1991,16 @@ static int iommu_prepare_identity_map(st
 	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
 	       pci_name(pdev), start, end);
 	
+	if (end < start) {
+		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
+			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			dmi_get_system_info(DMI_BIOS_VENDOR),
+			dmi_get_system_info(DMI_BIOS_VERSION),
+		     dmi_get_system_info(DMI_PRODUCT_VERSION));
+		ret = -EIO;
+		goto error;
+	}
+
 	if (end >> agaw_to_width(domain->agaw)) {
 		WARN(1, "Your BIOS is broken; RMRR exceeds permitted address width (%d bits)\n"
 		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",

[147/151] intel-iommu: Fix oops with intel_iommu=igfx_off

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: David Woodhouse <David.Woodhouse@intel.com>

commit 44cd613c0e4cd93079ea2a93aa06649d8ca0830a upstream.

The hotplug notifier will call find_domain() to see if the device in
question has been assigned an IOMMU domain. However, this should never
be called for devices with a "dummy" domain, such as graphics devices
when intel_iommu=igfx_off is set and the corresponding IOMMU isn't even
initialised. If you do that, it'll oops as it dereferences the (-1)
pointer.

The notifier function should check iommu_no_mapping() for the
device before doing anything else.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/pci/intel-iommu.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -3238,6 +3238,9 @@ static int device_notifier(struct notifi
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct dmar_domain *domain;
 
+	if (iommu_no_mapping(dev))
+		return 0;
+
 	domain = find_domain(pdev);
 	if (!domain)
 		return 0;

[148/151] intel-iommu: ignore page table validation in pass through mode

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Chris Wright <chrisw@sous-sol.org>

commit 1672af1164d3d50ba8908014fd34cc0b58afdc1e upstream.

We are seeing a bug when booting w/ iommu=pt with current upstream
(bisect blames 19943b0e30b05d42e494ae6fef78156ebc8c637e "intel-iommu:
Unify hardware and software passthrough support).

The issue is specific to this loop during identity map initialization
of each device:

domain_context_mapping_one(si_domain, ..., CONTEXT_TT_PASS_THROUGH)
...
		/* Skip top levels of page tables for
		* iommu which has less agaw than default.
		*/
		for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
			pgd = phys_to_virt(dma_pte_addr(pgd));
			if (!dma_pte_present(pgd)) {      <------ failing here
				spin_unlock_irqrestore(&iommu->lock, flags);
			return -ENOMEM;
		}

This box has 2 iommu's in it.  The catchall iommu has MGAW == 48, and
SAGAW == 4.  The other iommu has MGAW == 39, SAGAW == 2.

The device that's failing the above pgd test is the only device connected
to the non-catchall iommu, which has a smaller address width than the
domain default.  This test is not necessary since the context is in PT
mode and the ASR is ignored.

Thanks to Don Dutile for discovering and debugging this one.

Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 drivers/pci/intel-iommu.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -1523,12 +1523,15 @@ static int domain_context_mapping_one(st
 
 		/* Skip top levels of page tables for
 		 * iommu which has less agaw than default.
+		 * Unnecessary for PT mode.
 		 */
-		for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
-			pgd = phys_to_virt(dma_pte_addr(pgd));
-			if (!dma_pte_present(pgd)) {
-				spin_unlock_irqrestore(&iommu->lock, flags);
-				return -ENOMEM;
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd)) {
+					spin_unlock_irqrestore(&iommu->lock, flags);
+					return -ENOMEM;
+				}
 			}
 		}
 	}

[149/151] netfilter: xtables: document minimal required version

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Jan Engelhardt <jengelh@medozas.de>

commit 7a92263705435d046d37a0990d0edfcb517f7ad3 upstream.

For both .33 and .32-stable.

Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 Documentation/Changes |    2 ++
 1 file changed, 2 insertions(+)

--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -49,6 +49,8 @@ o  oprofile               0.9           
 o  udev                   081                     # udevinfo -V
 o  grub                   0.93                    # grub --version
 o  mcelog		  0.6
+o  iptables               1.4.1                   # iptables -V
+
 
 Kernel compilation
 ==================

[150/151] perf_event: Fix incorrect range check on cpu number

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Paul Mackerras <paulus@samba.org>

commit 0f624e7e5625f4c30c836b7a5decfe2553582391 upstream.

It is quite legitimate for CPUs to be numbered sparsely, meaning
that it possible for an online CPU to have a number which is
greater than the total count of possible CPUs.

Currently find_get_context() has a sanity check on the cpu
number where it checks it against num_possible_cpus().  This
test can fail for a legitimate cpu number if the
cpu_possible_mask is sparsely populated.

This fixes the problem by checking the CPU number against
nr_cpumask_bits instead, since that is the appropriate check to
ensure that the cpu number is same to pass to cpu_isset()
subsequently.

Reported-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Michael Neuling <mikey@neuling.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20091215084032.GA18661@brick.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 kernel/perf_event.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1583,7 +1583,7 @@ static struct perf_event_context *find_g
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		if (cpu < 0 || cpu > num_possible_cpus())
+		if (cpu < 0 || cpu >= nr_cpumask_bits)
 			return ERR_PTR(-EINVAL);
 
 		/*

[151/151] implement early_io{re,un}map for ia64

[Greg KH]

2.6.32-stable review patch.  If anyone has any objections, please let us know.

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

From: Luck, Tony <tony.luck@intel.com>

commit cd7bcf32d42b15891620b3f1387a00178b54291a upstream.

Needed for commit 2c992208 ("intel-iommu: Detect DMAR in hyperspace at
probe time.) to build on IA64.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

---
 arch/ia64/include/asm/io.h |    2 ++
 arch/ia64/mm/ioremap.c     |   11 +++++++++++
 2 files changed, 13 insertions(+)

--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -424,6 +424,8 @@ __writeq (unsigned long val, volatile vo
 extern void __iomem * ioremap(unsigned long offset, unsigned long size);
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
 extern void iounmap (volatile void __iomem *addr);
+extern void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size);
+extern void early_iounmap (volatile void __iomem *addr, unsigned long size);
 
 /*
  * String version of IO memory access ops:
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -22,6 +22,12 @@ __ioremap (unsigned long phys_addr)
 }
 
 void __iomem *
+early_ioremap (unsigned long phys_addr, unsigned long size)
+{
+	return __ioremap(phys_addr);
+}
+
+void __iomem *
 ioremap (unsigned long phys_addr, unsigned long size)
 {
 	void __iomem *addr;
@@ -102,6 +108,11 @@ ioremap_nocache (unsigned long phys_addr
 EXPORT_SYMBOL(ioremap_nocache);
 
 void
+early_iounmap (volatile void __iomem *addr, unsigned long size)
+{
+}
+
+void
 iounmap (volatile void __iomem *addr)
 {
 	if (REGION_NUMBER(addr) == RGN_GATE)

[000/151] 2.6.32.2-stable review

[Greg KH]

This is the start of the stable review cycle for the 2.6.23.2 release.
There are 151 patches in this series, all will be posted as a response
to this one.  If anyone has any issues with these being applied, please
let us know.  If anyone is a maintainer of the proper subsystem, and
wants to add a Signed-off-by: line to the patch, please respond with it.

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

The whole patch series can be found in one patch at:
	kernel.org/pub/linux/kernel/v2.6/stable-review/patch-2.6.32.2-rc1.gz
and the diffstat can be found below.

thanks,

greg k-h

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

 Documentation/Changes                         |    2 +
 Documentation/kernel-parameters.txt           |    2 +
 Documentation/video4linux/gspca.txt           |    1 +
 MAINTAINERS                                   |    4 +-
 Makefile                                      |    2 +-
 arch/arm/mach-pxa/em-x270.c                   |   11 +-
 arch/ia64/include/asm/io.h                    |    2 +
 arch/ia64/mm/ioremap.c                        |   11 ++
 arch/powerpc/kernel/vector.S                  |    2 +-
 arch/s390/include/asm/kvm.h                   |    3 +-
 arch/s390/kernel/head64.S                     |    3 +
 arch/s390/kvm/kvm-s390.c                      |   25 ++-
 arch/s390/kvm/sigp.c                          |    6 +-
 arch/sparc/Makefile                           |    2 +
 arch/sparc/kernel/ldc.c                       |    4 +-
 arch/sparc/kernel/of_device_64.c              |   14 ++-
 arch/sparc/lib/mcount.S                       |    5 +-
 arch/x86/Makefile_32.cpu                      |    7 +
 arch/x86/include/asm/irq_vectors.h            |    2 +-
 arch/x86/include/asm/kvm_emulate.h            |    2 +-
 arch/x86/include/asm/mce.h                    |    6 +
 arch/x86/kernel/acpi/cstate.c                 |    2 +-
 arch/x86/kernel/amd_iommu.c                   |    8 +-
 arch/x86/kernel/amd_iommu_init.c              |    2 +-
 arch/x86/kernel/apic/apic.c                   |    2 +-
 arch/x86/kernel/cpu/intel_cacheinfo.c         |    5 +-
 arch/x86/kernel/cpu/mcheck/mce.c              |    9 +-
 arch/x86/kernel/cpu/mcheck/therm_throt.c      |   29 +++-
 arch/x86/kernel/cpu/perfctr-watchdog.c        |    2 +-
 arch/x86/kernel/pci-calgary_64.c              |   12 +-
 arch/x86/kernel/pci-dma.c                     |    2 +-
 arch/x86/kernel/pci-gart_64.c                 |    2 +-
 arch/x86/kernel/reboot.c                      |    8 +
 arch/x86/kernel/setup.c                       |    3 +
 arch/x86/kernel/tlb_uv.c                      |    4 +-
 arch/x86/kvm/emulate.c                        |    5 +-
 arch/x86/kvm/x86.c                            |   12 +-
 arch/x86/xen/enlighten.c                      |   27 ++--
 arch/x86/xen/mmu.c                            |    2 +-
 arch/x86/xen/smp.c                            |    1 +
 arch/x86/xen/suspend.c                        |   17 ++-
 arch/x86/xen/time.c                           |    7 +-
 arch/x86/xen/xen-asm_64.S                     |    4 +-
 arch/x86/xen/xen-ops.h                        |    2 +
 drivers/ata/pata_hpt37x.c                     |   32 ++--
 drivers/ata/pata_hpt3x2n.c                    |   17 +-
 drivers/base/core.c                           |    9 +-
 drivers/base/power/runtime.c                  |    2 +-
 drivers/firewire/ohci.c                       |   12 +-
 drivers/gpu/drm/drm_irq.c                     |   34 +++-
 drivers/gpu/drm/i915/i915_drv.h               |    4 +
 drivers/gpu/drm/i915/i915_gem.c               |    1 +
 drivers/gpu/drm/i915/intel_display.c          |   67 +++++---
 drivers/gpu/drm/i915/intel_dp.c               |    6 +-
 drivers/gpu/drm/i915/intel_tv.c               |   11 +-
 drivers/gpu/drm/radeon/atombios_crtc.c        |    8 +-
 drivers/gpu/drm/radeon/radeon_atombios.c      |    8 +
 drivers/gpu/drm/radeon/radeon_legacy_crtc.c   |    7 +-
 drivers/gpu/drm/radeon/rs600.c                |   15 ++-
 drivers/gpu/drm/radeon/rs690.c                |   19 +-
 drivers/ide/slc90e66.c                        |    3 +-
 drivers/macintosh/therm_adt746x.c             |   13 ++-
 drivers/macintosh/windfarm_smu_controls.c     |    2 +
 drivers/md/bitmap.c                           |   24 ++-
 drivers/md/bitmap.h                           |    2 +-
 drivers/md/dm-crypt.c                         |  170 +++++++++++++------
 drivers/md/dm-exception-store.c               |    3 +-
 drivers/md/dm-ioctl.c                         |   17 ++-
 drivers/md/dm-snap.c                          |   12 +-
 drivers/md/dm-uevent.c                        |    9 +-
 drivers/md/md.c                               |    3 +-
 drivers/md/md.h                               |    1 +
 drivers/media/common/tuners/mxl5007t.c        |    2 +-
 drivers/media/video/gspca/ov519.c             |    1 +
 drivers/mtd/ubi/upd.c                         |   20 ++-
 drivers/net/b44.c                             |    3 +-
 drivers/net/bcm63xx_enet.c                    |   12 +-
 drivers/net/wireless/ath/ath5k/eeprom.c       |    3 +-
 drivers/net/wireless/ath/ath5k/phy.c          |    2 -
 drivers/net/wireless/ath/ath9k/ath9k.h        |    3 +
 drivers/net/wireless/ath/ath9k/hw.c           |   11 +-
 drivers/net/wireless/ath/ath9k/hw.h           |    1 +
 drivers/net/wireless/ath/ath9k/mac.c          |    6 +-
 drivers/net/wireless/ath/ath9k/mac.h          |    1 +
 drivers/net/wireless/ath/ath9k/main.c         |    9 +-
 drivers/net/wireless/ath/ath9k/xmit.c         |   20 ++-
 drivers/net/wireless/b43legacy/rfkill.c       |    7 +
 drivers/net/wireless/ipw2x00/ipw2100.c        |   11 ++
 drivers/net/wireless/rtl818x/rtl8187.h        |    5 +
 drivers/net/wireless/rtl818x/rtl8187_dev.c    |   12 +-
 drivers/net/wireless/rtl818x/rtl8187_rfkill.c |    4 +-
 drivers/pci/dmar.c                            |   67 ++++++--
 drivers/pci/intel-iommu.c                     |   26 +++-
 drivers/platform/x86/acerhdf.c                |   63 ++++---
 drivers/platform/x86/asus-laptop.c            |    4 +-
 drivers/platform/x86/thinkpad_acpi.c          |   36 +---
 drivers/serial/8250.c                         |    8 +-
 drivers/ssb/sprom.c                           |   20 ++-
 drivers/usb/class/usbtmc.c                    |   14 +-
 drivers/usb/core/usb.c                        |   31 ++--
 drivers/usb/musb/musb_gadget_ep0.c            |    1 -
 drivers/usb/serial/option.c                   |   37 ++++
 drivers/usb/storage/transport.c               |   17 ++-
 drivers/usb/storage/unusual_devs.h            |    7 +
 drivers/usb/storage/usb.c                     |   18 ++-
 drivers/video/matrox/g450_pll.c               |    3 +-
 drivers/xen/balloon.c                         |   38 +---
 drivers/xen/events.c                          |    3 +
 drivers/xen/manage.c                          |   37 +++--
 drivers/xen/xenbus/xenbus_probe.c             |    6 +-
 fs/debugfs/inode.c                            |   55 ++++---
 fs/devpts/inode.c                             |   16 ++-
 fs/ext3/inode.c                               |   18 ++-
 fs/hfs/catalog.c                              |    4 +
 fs/hfs/dir.c                                  |   11 ++
 fs/hfs/super.c                                |    7 +-
 fs/jbd2/journal.c                             |    7 +
 fs/jffs2/gc.c                                 |    3 +-
 fs/nfs/write.c                                |    5 +-
 include/drm/drmP.h                            |    1 +
 include/drm/ttm/ttm_memory.h                  |    1 +
 include/linux/hrtimer.h                       |    4 +-
 include/linux/kvm.h                           |    8 +-
 include/linux/perf_event.h                    |    2 +-
 include/linux/usb_usual.h                     |    4 +-
 include/linux/vmalloc.h                       |    2 +
 include/net/tcp.h                             |   10 +-
 include/trace/ftrace.h                        |    2 +-
 kernel/acct.c                                 |    3 +-
 kernel/futex.c                                |   10 +-
 kernel/perf_event.c                           |    6 +-
 kernel/rcutree.c                              |  227 +++++++++++++++----------
 kernel/rcutree.h                              |   13 +-
 kernel/rcutree_plugin.h                       |    4 +-
 kernel/sched.c                                |   28 +++-
 kernel/sched_debug.c                          |    4 +
 kernel/sched_fair.c                           |   35 ++++-
 kernel/sysctl.c                               |    3 +-
 mm/memcontrol.c                               |    1 +
 mm/memory.c                                   |    4 +-
 mm/mincore.c                                  |   37 ++++
 mm/pagewalk.c                                 |   16 ++-
 mm/vmalloc.c                                  |    2 +
 net/core/dev.c                                |   11 ++
 net/core/rtnetlink.c                          |    4 +-
 net/ipv4/ip_output.c                          |    2 +-
 net/mac80211/cfg.c                            |    3 +-
 net/mac80211/ieee80211_i.h                    |    1 +
 net/mac80211/mesh.h                           |    5 +-
 net/mac80211/mesh_hwmp.c                      |    2 +-
 net/mac80211/rx.c                             |    1 -
 net/mac80211/scan.c                           |   32 +++-
 net/mac80211/util.c                           |    2 +-
 net/netfilter/ipvs/ip_vs_ctl.c                |    4 +
 net/sunrpc/auth_gss/auth_gss.c                |    2 +-
 sound/core/hrtimer.c                          |   15 ++-
 sound/pci/hda/hda_intel.c                     |    5 +
 virt/kvm/irq_comm.c                           |    7 +-
 158 files changed, 1395 insertions(+), 617 deletions(-)