@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 2
-SUBLEVEL = 1
+SUBLEVEL = 2
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

@@ -429,22 +429,24 @@ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN];
 static struct acpi_table_slit __initdata *slit_table;
 cpumask_t early_cpu_possible_map = CPU_MASK_NONE;
 
-static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
+static int __init
+get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
 {
 	int pxm;
 
 	pxm = pa->proximity_domain_lo;
-	if (ia64_platform_is("sn2"))
+	if (ia64_platform_is("sn2") || acpi_srat_revision >= 2)
 		pxm += pa->proximity_domain_hi[0] << 8;
 	return pxm;
 }
 
-static int get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
+static int __init
+get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
 {
 	int pxm;
 
 	pxm = ma->proximity_domain;
-	if (!ia64_platform_is("sn2"))
+	if (!ia64_platform_is("sn2") && acpi_srat_revision <= 1)
 		pxm &= 0xff;
 
 	return pxm;

@@ -408,7 +408,7 @@ ENTRY(handle_sys)
 	sw	r9, [r0, PT_EPC]
 
 	cmpi.c	r27, __NR_syscalls 	# check syscall number
-	bgtu	illegal_syscall
+	bgeu	illegal_syscall
 
 	slli	r8, r27, 2		# get syscall routine
 	la	r11, sys_call_table

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_AMD_NB_H
 #define _ASM_X86_AMD_NB_H
 
+#include <linux/ioport.h>
 #include <linux/pci.h>
 
 struct amd_nb_bus_dev_range {

@@ -13,6 +14,7 @@ extern const struct pci_device_id amd_nb_misc_ids[];
 extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
 
 extern bool early_is_amd_nb(u32 value);
+extern struct resource *amd_get_mmconfig_range(struct resource *res);
 extern int amd_cache_northbridges(void);
 extern void amd_flush_garts(void);
 extern int amd_numa_init(void);

@@ -65,7 +65,7 @@
  * UV2: Bit 19 selects between
  *  (0): 10 microsecond timebase and
  *  (1): 80 microseconds
- *  we're using 655us, similar to UV1: 65 units of 10us
+ *  we're using 560us, similar to UV1: 65 units of 10us
  */
 #define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
 #define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL)

@@ -167,6 +167,7 @@
 #define FLUSH_RETRY_TIMEOUT		2
 #define FLUSH_GIVEUP			3
 #define FLUSH_COMPLETE			4
+#define FLUSH_RETRY_BUSYBUG		5
 
 /*
  * tuning the action when the numalink network is extremely delayed

@@ -235,10 +236,10 @@ struct bau_msg_payload {
 
 
 /*
- * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * UV1 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
-struct bau_msg_header {
+struct uv1_bau_msg_header {
 	unsigned int	dest_subnodeid:6;	/* must be 0x10, for the LB */
 	/* bits 5:0 */
 	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */

@@ -318,19 +319,87 @@ struct bau_msg_header {
 };
 
 /*
+ * UV2 Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see figure 9-2 of harp_sys.pdf
+ */
+struct uv2_bau_msg_header {
+	unsigned int	base_dest_nasid:15;	/* nasid of the first bit */
+	/* bits 14:0 */				/* in uvhub map */
+	unsigned int	dest_subnodeid:5;	/* must be 0x10, for the LB */
+	/* bits 19:15 */
+	unsigned int	rsvd_1:1;		/* must be zero */
+	/* bit 20 */
+	/* Address bits 59:21 */
+	/* bits 25:2 of address (44:21) are payload */
+	/* these next 24 bits become bytes 12-14 of msg */
+	/* bits 28:21 land in byte 12 */
+	unsigned int	replied_to:1;		/* sent as 0 by the source to
+						   byte 12 */
+	/* bit 21 */
+	unsigned int	msg_type:3;		/* software type of the
+						   message */
+	/* bits 24:22 */
+	unsigned int	canceled:1;		/* message canceled, resource
+						   is to be freed*/
+	/* bit 25 */
+	unsigned int	payload_1:3;		/* not currently used */
+	/* bits 28:26 */
+
+	/* bits 36:29 land in byte 13 */
+	unsigned int	payload_2a:3;		/* not currently used */
+	unsigned int	payload_2b:5;		/* not currently used */
+	/* bits 36:29 */
+
+	/* bits 44:37 land in byte 14 */
+	unsigned int	payload_3:8;		/* not currently used */
+	/* bits 44:37 */
+
+	unsigned int	rsvd_2:7;		/* reserved */
+	/* bits 51:45 */
+	unsigned int	swack_flag:1;		/* software acknowledge flag */
+	/* bit 52 */
+	unsigned int	rsvd_3a:3;		/* must be zero */
+	unsigned int	rsvd_3b:8;		/* must be zero */
+	unsigned int	rsvd_3c:8;		/* must be zero */
+	unsigned int	rsvd_3d:3;		/* must be zero */
+	/* bits 74:53 */
+	unsigned int	fairness:3;		/* usually zero */
+	/* bits 77:75 */
+
+	unsigned int	sequence:16;		/* message sequence number */
+	/* bits 93:78  Suppl_A  */
+	unsigned int	chaining:1;		/* next descriptor is part of
+						   this activation*/
+	/* bit 94 */
+	unsigned int	multilevel:1;		/* multi-level multicast
+						   format */
+	/* bit 95 */
+	unsigned int	rsvd_4:24;		/* ordered / source node /
+						   source subnode / aging
+						   must be zero */
+	/* bits 119:96 */
+	unsigned int	command:8;		/* message type */
+	/* bits 127:120 */
+};
+
+/*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-	struct pnmask			distribution;
+	struct pnmask				distribution;
 	/*
 	 * message template, consisting of header and payload:
 	 */
-	struct bau_msg_header		header;
-	struct bau_msg_payload		payload;
+	union bau_msg_header {
+		struct uv1_bau_msg_header	uv1_hdr;
+		struct uv2_bau_msg_header	uv2_hdr;
+	} header;
+
+	struct bau_msg_payload			payload;
 };
-/*
+/* UV1:
  *   -payload--    ---------header------
  *   bytes 0-11    bits 41-56  bits 58-81
  *       A           B  (2)      C (3)

@@ -340,6 +409,16 @@ struct bau_desc {
  *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
  *   ------------payload queue-----------
  */
+/* UV2:
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 70-78  bits 21-44
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
 
 /*
  * The payload queue on the destination side is an array of these.

@@ -385,7 +464,6 @@ struct bau_pq_entry {
 struct msg_desc {
 	struct bau_pq_entry	*msg;
 	int			msg_slot;
-	int			swack_slot;
 	struct bau_pq_entry	*queue_first;
 	struct bau_pq_entry	*queue_last;
 };

@@ -439,6 +517,9 @@ struct ptc_stats {
 	unsigned long	s_retry_messages;	/* retry broadcasts */
 	unsigned long	s_bau_reenabled;	/* for bau enable/disable */
 	unsigned long	s_bau_disabled;		/* for bau enable/disable */
+	unsigned long	s_uv2_wars;		/* uv2 workaround, perm. busy */
+	unsigned long	s_uv2_wars_hw;		/* uv2 workaround, hiwater */
+	unsigned long	s_uv2_war_waits;	/* uv2 workaround, long waits */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */

@@ -511,9 +592,12 @@ struct bau_control {
 	short			osnode;
 	short			uvhub_cpu;
 	short			uvhub;
+	short			uvhub_version;
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
+	short			using_desc; /* an index, like uvhub_cpu */
+	unsigned int		inuse_map;
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];

@@ -531,6 +615,7 @@ struct bau_control {
 	int			cong_response_us;
 	int			cong_reps;
 	int			cong_period;
+	unsigned long		clocks_per_100_usec;
 	cycles_t		period_time;
 	long			period_requests;
 	struct hub_and_pnode	*thp;

@@ -591,6 +676,11 @@ static inline void write_mmr_sw_ack(unsigned long mr)
 	uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
 }
 
+static inline void write_gmmr_sw_ack(int pnode, unsigned long mr)
+{
+	write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
 static inline unsigned long read_mmr_sw_ack(void)
 {
 	return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);

@@ -119,6 +119,37 @@ bool __init early_is_amd_nb(u32 device)
 	return false;
 }
 
+struct resource *amd_get_mmconfig_range(struct resource *res)
+{
+	u32 address;
+	u64 base, msr;
+	unsigned segn_busn_bits;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return NULL;
+
+	/* assume all cpus from fam10h have mmconfig */
+        if (boot_cpu_data.x86 < 0x10)
+		return NULL;
+
+	address = MSR_FAM10H_MMIO_CONF_BASE;
+	rdmsrl(address, msr);
+
+	/* mmconfig is not enabled */
+	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+		return NULL;
+
+	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+	res->flags = IORESOURCE_MEM;
+	res->start = base;
+	res->end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
+	return res;
+}
+
 int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;

@@ -769,7 +769,12 @@ void __init uv_system_init(void)
 	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
 		uv_possible_blades +=
 		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
-	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
+
+	/* uv_num_possible_blades() is really the hub count */
+	printk(KERN_INFO "UV: Found %d blades, %d hubs\n",
+			is_uv1_hub() ? uv_num_possible_blades() :
+			(uv_num_possible_blades() + 1) / 2,
+			uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kzalloc(bytes, GFP_KERNEL);

@@ -75,9 +75,9 @@ static unsigned long mmap_rnd(void)
 	*/
 	if (current->flags & PF_RANDOMIZE) {
 		if (mmap_is_ia32())
-			rnd = (long)get_random_int() % (1<<8);
+			rnd = get_random_int() % (1<<8);
 		else
-			rnd = (long)(get_random_int() % (1<<28));
+			rnd = get_random_int() % (1<<28);
 	}
 	return rnd << PAGE_SHIFT;
 }

@@ -104,6 +104,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
 		return;
 	pxm = pa->proximity_domain_lo;
+	if (acpi_srat_revision >= 2)
+		pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
 	node = setup_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);

@@ -155,6 +157,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 	start = ma->base_address;
 	end = start + ma->length;
 	pxm = ma->proximity_domain;
+	if (acpi_srat_revision <= 1)
+		pxm &= 0xff;
 	node = setup_node(pxm);
 	if (node < 0) {
 		printk(KERN_ERR "SRAT: Too many proximity domains.\n");

@@ -18,8 +18,9 @@ obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
 obj-$(CONFIG_X86_MRST)		+= mrst.o
 
 obj-y				+= common.o early.o
-obj-y				+= amd_bus.o bus_numa.o
+obj-y				+= bus_numa.o
 
+obj-$(CONFIG_AMD_NB)		+= amd_bus.o
 obj-$(CONFIG_PCI_CNB20LE_QUIRK)	+= broadcom_bus.o
 
 ifeq ($(CONFIG_PCI_DEBUG),y)

@@ -149,7 +149,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 	unsigned long flags;
-	u64 start, end;
+	u64 start, orig_end, end;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))

@@ -165,7 +165,21 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 
 	start = addr.minimum + addr.translation_offset;
-	end = addr.maximum + addr.translation_offset;
+	orig_end = end = addr.maximum + addr.translation_offset;
+
+	/* Exclude non-addressable range or non-addressable portion of range */
+	end = min(end, (u64)iomem_resource.end);
+	if (end <= start) {
+		dev_info(&info->bridge->dev,
+			"host bridge window [%#llx-%#llx] "
+			"(ignored, not CPU addressable)\n", start, orig_end);
+		return AE_OK;
+	} else if (orig_end != end) {
+		dev_info(&info->bridge->dev,
+			"host bridge window [%#llx-%#llx] "
+			"([%#llx-%#llx] ignored, not CPU addressable)\n",
+			start, orig_end, end + 1, orig_end);
+	}
 
 	res = &info->res[info->res_num];
 	res->name = info->name;

@@ -30,34 +30,6 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = {
 	{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 },
 };
 
-static u64 __initdata fam10h_mmconf_start;
-static u64 __initdata fam10h_mmconf_end;
-static void __init get_pci_mmcfg_amd_fam10h_range(void)
-{
-	u32 address;
-	u64 base, msr;
-	unsigned segn_busn_bits;
-
-	/* assume all cpus from fam10h have mmconf */
-        if (boot_cpu_data.x86 < 0x10)
-		return;
-
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
-	/* mmconfig is not enable */
-	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
-		return;
-
-	base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
-
-	segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
-			 FAM10H_MMIO_CONF_BUSRANGE_MASK;
-
-	fam10h_mmconf_start = base;
-	fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
-}
-
 #define RANGE_NUM 16
 
 /**

@@ -85,6 +57,9 @@ static int __init early_fill_mp_bus_info(void)
 	u64 val;
 	u32 address;
 	bool found;
+	struct resource fam10h_mmconf_res, *fam10h_mmconf;
+	u64 fam10h_mmconf_start;
+	u64 fam10h_mmconf_end;
 
 	if (!early_pci_allowed())
 		return -1;

@@ -211,12 +186,17 @@ static int __init early_fill_mp_bus_info(void)
 		subtract_range(range, RANGE_NUM, 0, end);
 
 	/* get mmconfig */
-	get_pci_mmcfg_amd_fam10h_range();
+	fam10h_mmconf = amd_get_mmconfig_range(&fam10h_mmconf_res);
 	/* need to take out mmconf range */
-	if (fam10h_mmconf_end) {
-		printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
+	if (fam10h_mmconf) {
+		printk(KERN_DEBUG "Fam 10h mmconf %pR\n", fam10h_mmconf);
+		fam10h_mmconf_start = fam10h_mmconf->start;
+		fam10h_mmconf_end = fam10h_mmconf->end;
 		subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
 				 fam10h_mmconf_end + 1);
+	} else {
+		fam10h_mmconf_start = 0;
+		fam10h_mmconf_end = 0;
 	}
 
 	/* mmio resource */

@@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub)
  * clear of the Timeout bit (as well) will free the resource. No reply will
  * be sent (the hardware will only do one reply per message).
  */
-static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	unsigned long dw;
 	struct bau_pq_entry *msg;
 
 	msg = mdp->msg;
-	if (!msg->canceled) {
+	if (!msg->canceled && do_acknowledge) {
 		dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
 		write_mmr_sw_ack(dw);
 	}

@@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
 			if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
 				unsigned long mr;
 				/*
-				 * is the resource timed out?
-				 * make everyone ignore the cancelled message.
+				 * Is the resource timed out?
+				 * Make everyone ignore the cancelled message.
 				 */
 				msg2->canceled = 1;
 				stat->d_canceled++;

@@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
  * Do all the things a cpu should do for a TLB shootdown message.
  * Other cpu's may come here at the same time for this message.
  */
-static void bau_process_message(struct msg_desc *mdp,
-					struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
+						int do_acknowledge)
 {
 	short socket_ack_count = 0;
 	short *sp;

@@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp,
 		if (msg_ack_count == bcp->cpus_in_uvhub) {
 			/*
 			 * All cpus in uvhub saw it; reply
+			 * (unless we are in the UV2 workaround)
 			 */
-			reply_to_message(mdp, bcp);
+			reply_to_message(mdp, bcp, do_acknowledge);
 		}
 	}
 

@@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
 /*
  * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
  */
-static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
 {
 	unsigned long descriptor_status;
 	unsigned long descriptor_status2;
 
 	descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
-	descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+	descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL;
 	descriptor_status = (descriptor_status << 1) | descriptor_status2;
 	return descriptor_status;
 }
 
+/*
+ * Return whether the status of the descriptor that is normally used for this
+ * cpu (the one indexed by its hub-relative cpu number) is busy.
+ * The status of the original 32 descriptors is always reflected in the 64
+ * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0.
+ * The bit provided by the activation_status_2 register is irrelevant to
+ * the status if it is only being tested for busy or not busy.
+ */
+int normal_busy(struct bau_control *bcp)
+{
+	int cpu = bcp->uvhub_cpu;
+	int mmr_offset;
+	int right_shift;
+
+	mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+	right_shift = cpu * UV_ACT_STATUS_SIZE;
+	return (((((read_lmmr(mmr_offset) >> right_shift) &
+				UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY);
+}
+
+/*
+ * Entered when a bau descriptor has gone into a permanent busy wait because
+ * of a hardware bug.
+ * Workaround the bug.
+ */
+int handle_uv2_busy(struct bau_control *bcp)
+{
+	int busy_one = bcp->using_desc;
+	int normal = bcp->uvhub_cpu;
+	int selected = -1;
+	int i;
+	unsigned long descriptor_status;
+	unsigned long status;
+	int mmr_offset;
+	struct bau_desc *bau_desc_old;
+	struct bau_desc *bau_desc_new;
+	struct bau_control *hmaster = bcp->uvhub_master;
+	struct ptc_stats *stat = bcp->statp;
+	cycles_t ttm;
+
+	stat->s_uv2_wars++;
+	spin_lock(&hmaster->uvhub_lock);
+	/* try for the original first */
+	if (busy_one != normal) {
+		if (!normal_busy(bcp))
+			selected = normal;
+	}
+	if (selected < 0) {
+		/* can't use the normal, select an alternate */
+		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+		descriptor_status = read_lmmr(mmr_offset);
+
+		/* scan available descriptors 32-63 */
+		for (i = 0; i < UV_CPUS_PER_AS; i++) {
+			if ((hmaster->inuse_map & (1 << i)) == 0) {
+				status = ((descriptor_status >>
+						(i * UV_ACT_STATUS_SIZE)) &
+						UV_ACT_STATUS_MASK) << 1;
+				if (status != UV2H_DESC_BUSY) {
+					selected = i + UV_CPUS_PER_AS;
+					break;
+				}
+			}
+		}
+	}
+
+	if (busy_one != normal)
+		/* mark the busy alternate as not in-use */
+		hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS));
+
+	if (selected >= 0) {
+		/* switch to the selected descriptor */
+		if (selected != normal) {
+			/* set the selected alternate as in-use */
+			hmaster->inuse_map |=
+					(1 << (selected - UV_CPUS_PER_AS));
+			if (selected > stat->s_uv2_wars_hw)
+				stat->s_uv2_wars_hw = selected;
+		}
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * busy_one);
+		bcp->using_desc = selected;
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * selected);
+		*bau_desc_new = *bau_desc_old;
+	} else {
+		/*
+		 * All are busy. Wait for the normal one for this cpu to
+		 * free up.
+		 */
+		stat->s_uv2_war_waits++;
+		spin_unlock(&hmaster->uvhub_lock);
+		ttm = get_cycles();
+		do {
+			cpu_relax();
+		} while (normal_busy(bcp));
+		spin_lock(&hmaster->uvhub_lock);
+		/* switch to the original descriptor */
+		bcp->using_desc = normal;
+		bau_desc_old = bcp->descriptor_base;
+		bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc);
+		bcp->using_desc = (ITEMS_PER_DESC * normal);
+		bau_desc_new = bcp->descriptor_base;
+		bau_desc_new += (ITEMS_PER_DESC * normal);
+		*bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
+	}
+	spin_unlock(&hmaster->uvhub_lock);
+	return FLUSH_RETRY_BUSYBUG;
+}
+
 static int uv2_wait_completion(struct bau_desc *bau_desc,
 				unsigned long mmr_offset, int right_shift,
 				struct bau_control *bcp, long try)
 {
 	unsigned long descriptor_stat;
 	cycles_t ttm;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
+	long busy_reps = 0;
 	struct ptc_stats *stat = bcp->statp;
 
-	descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+	descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc);
 
 	/* spin on the status MMR, waiting for it to go idle */
 	while (descriptor_stat != UV2H_DESC_IDLE) {

@@ -542,12 +655,23 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
 			bcp->conseccompletes = 0;
 			return FLUSH_RETRY_TIMEOUT;
 		} else {
+			busy_reps++;
+			if (busy_reps > 1000000) {
+				/* not to hammer on the clock */
+				busy_reps = 0;
+				ttm = get_cycles();
+				if ((ttm - bcp->send_message) >
+					(bcp->clocks_per_100_usec)) {
+					return handle_uv2_busy(bcp);
+				}
+			}
 			/*
 			 * descriptor_stat is still BUSY
 			 */
 			cpu_relax();
 		}
-		descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+		descriptor_stat = uv2_read_status(mmr_offset, right_shift,
+									desc);
 	}
 	bcp->conseccompletes++;
 	return FLUSH_COMPLETE;

@@ -563,17 +687,17 @@ static int wait_completion(struct bau_desc *bau_desc,
 {
 	int right_shift;
 	unsigned long mmr_offset;
-	int cpu = bcp->uvhub_cpu;
+	int desc = bcp->using_desc;
 
-	if (cpu < UV_CPUS_PER_AS) {
+	if (desc < UV_CPUS_PER_AS) {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-		right_shift = cpu * UV_ACT_STATUS_SIZE;
+		right_shift = desc * UV_ACT_STATUS_SIZE;
 	} else {
 		mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-		right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
+		right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
 	}
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
 								bcp, try);
 	else

@@ -752,19 +876,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
  * Returns 1 if it gives up entirely and the original cpu mask is to be
  * returned to the kernel.
  */
-int uv_flush_send_and_wait(struct bau_desc *bau_desc,
-			struct cpumask *flush_mask, struct bau_control *bcp)
+int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp)
 {
 	int seq_number = 0;
 	int completion_stat = 0;
+	int uv1 = 0;
 	long try = 0;
 	unsigned long index;
 	cycles_t time1;
 	cycles_t time2;
 	struct ptc_stats *stat = bcp->statp;
 	struct bau_control *hmaster = bcp->uvhub_master;
+	struct uv1_bau_msg_header *uv1_hdr = NULL;
+	struct uv2_bau_msg_header *uv2_hdr = NULL;
+	struct bau_desc *bau_desc;
 
-	if (is_uv1_hub())
+	if (bcp->uvhub_version == 1)
 		uv1_throttle(hmaster, stat);
 
 	while (hmaster->uvhub_quiesce)

@@ -772,22 +899,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 
 	time1 = get_cycles();
 	do {
-		if (try == 0) {
-			bau_desc->header.msg_type = MSG_REGULAR;
+		bau_desc = bcp->descriptor_base;
+		bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
+		if (bcp->uvhub_version == 1) {
+			uv1 = 1;
+			uv1_hdr = &bau_desc->header.uv1_hdr;
+		} else
+			uv2_hdr = &bau_desc->header.uv2_hdr;
+		if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) {
+			if (uv1)
+				uv1_hdr->msg_type = MSG_REGULAR;
+			else
+				uv2_hdr->msg_type = MSG_REGULAR;
 			seq_number = bcp->message_number++;
 		} else {
-			bau_desc->header.msg_type = MSG_RETRY;
+			if (uv1)
+				uv1_hdr->msg_type = MSG_RETRY;
+			else
+				uv2_hdr->msg_type = MSG_RETRY;
 			stat->s_retry_messages++;
 		}
 
-		bau_desc->header.sequence = seq_number;
-		index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
+		if (uv1)
+			uv1_hdr->sequence = seq_number;
+		else
+			uv2_hdr->sequence = seq_number;
+		index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc;
 		bcp->send_message = get_cycles();
 
 		write_mmr_activation(index);
 
 		try++;
 		completion_stat = wait_completion(bau_desc, bcp, try);
+		/* UV2: wait_completion() may change the bcp->using_desc */
 
 		handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 

@@ -798,6 +942,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 		}
 		cpu_relax();
 	} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+		 (completion_stat == FLUSH_RETRY_BUSYBUG) ||
 		 (completion_stat == FLUSH_RETRY_TIMEOUT));
 
 	time2 = get_cycles();

@@ -812,6 +957,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
 	record_send_stats(time1, time2, bcp, stat, completion_stat, try);
 
 	if (completion_stat == FLUSH_GIVEUP)
+		/* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */
 		return 1;
 	return 0;
 }

@@ -967,7 +1113,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 		stat->s_ntargself++;
 
 	bau_desc = bcp->descriptor_base;
-	bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
+	bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
 	bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 	if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
 		return NULL;

@@ -980,13 +1126,86 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
 	 * or 1 if it gave up and the original cpumask should be returned.
 	 */
-	if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp))
+	if (!uv_flush_send_and_wait(flush_mask, bcp))
 		return NULL;
 	else
 		return cpumask;
 }
 
 /*
+ * Search the message queue for any 'other' message with the same software
+ * acknowledge resource bit vector.
+ */
+struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
+			struct bau_control *bcp, unsigned char swack_vec)
+{
+	struct bau_pq_entry *msg_next = msg + 1;
+
+	if (msg_next > bcp->queue_last)
+		msg_next = bcp->queue_first;
+	while ((msg_next->swack_vec != 0) && (msg_next != msg)) {
+		if (msg_next->swack_vec == swack_vec)
+			return msg_next;
+		msg_next++;
+		if (msg_next > bcp->queue_last)
+			msg_next = bcp->queue_first;
+	}
+	return NULL;
+}
+
+/*
+ * UV2 needs to work around a bug in which an arriving message has not
+ * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
+ * Such a message must be ignored.
+ */
+void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+{
+	unsigned long mmr_image;
+	unsigned char swack_vec;
+	struct bau_pq_entry *msg = mdp->msg;
+	struct bau_pq_entry *other_msg;
+
+	mmr_image = read_mmr_sw_ack();
+	swack_vec = msg->swack_vec;
+
+	if ((swack_vec & mmr_image) == 0) {
+		/*
+		 * This message was assigned a swack resource, but no
+		 * reserved acknowlegment is pending.
+		 * The bug has prevented this message from setting the MMR.
+		 * And no other message has used the same sw_ack resource.
+		 * Do the requested shootdown but do not reply to the msg.
+		 * (the 0 means make no acknowledge)
+		 */
+		bau_process_message(mdp, bcp, 0);
+		return;
+	}
+
+	/*
+	 * Some message has set the MMR 'pending' bit; it might have been
+	 * another message.  Look for that message.
+	 */
+	other_msg = find_another_by_swack(msg, bcp, msg->swack_vec);
+	if (other_msg) {
+		/* There is another.  Do not ack the current one. */
+		bau_process_message(mdp, bcp, 0);
+		/*
+		 * Let the natural processing of that message acknowledge
+		 * it. Don't get the processing of sw_ack's out of order.
+		 */
+		return;
+	}
+
+	/*
+	 * There is no other message using this sw_ack, so it is safe to
+	 * acknowledge it.
+	 */
+	bau_process_message(mdp, bcp, 1);
+
+	return;
+}
+
+/*
  * The BAU message interrupt comes here. (registered by set_intr_gate)
  * See entry_64.S
  *

@@ -1022,9 +1241,11 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 		count++;
 
 		msgdesc.msg_slot = msg - msgdesc.queue_first;
-		msgdesc.swack_slot = ffs(msg->swack_vec) - 1;
 		msgdesc.msg = msg;
-		bau_process_message(&msgdesc, bcp);
+		if (bcp->uvhub_version == 2)
+			process_uv2_message(&msgdesc, bcp);
+		else
+			bau_process_message(&msgdesc, bcp, 1);
 
 		msg++;
 		if (msg > msgdesc.queue_last)

@@ -1083,7 +1304,7 @@ static void __init enable_timeouts(void)
 		 */
 		mmr_image |= (1L << SOFTACK_MSHIFT);
 		if (is_uv2_hub()) {
-			mmr_image |= (1L << UV2_LEG_SHFT);
+			mmr_image &= ~(1L << UV2_LEG_SHFT);
 			mmr_image |= (1L << UV2_EXT_SHFT);
 		}
 		write_mmr_misc_control(pnode, mmr_image);

@@ -1142,7 +1363,7 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file,
 			"all one mult none retry canc nocan reset rcan ");
 		seq_printf(file,
-			"disable enable\n");
+			"disable enable wars warshw warwaits\n");
 	}
 	if (cpu < num_possible_cpus() && cpu_online(cpu)) {
 		stat = &per_cpu(ptcstats, cpu);

@@ -1173,8 +1394,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 			   stat->d_nomsg, stat->d_retries, stat->d_canceled,
 			   stat->d_nocanceled, stat->d_resets,
 			   stat->d_rcanceled);
-		seq_printf(file, "%ld %ld\n",
-			stat->s_bau_disabled, stat->s_bau_reenabled);
+		seq_printf(file, "%ld %ld %ld %ld %ld\n",
+			stat->s_bau_disabled, stat->s_bau_reenabled,
+			stat->s_uv2_wars, stat->s_uv2_wars_hw,
+			stat->s_uv2_war_waits);
 	}
 	return 0;
 }

@@ -1432,12 +1655,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 {
 	int i;
 	int cpu;
+	int uv1 = 0;
 	unsigned long gpa;
 	unsigned long m;
 	unsigned long n;
 	size_t dsize;
 	struct bau_desc *bau_desc;
 	struct bau_desc *bd2;
+	struct uv1_bau_msg_header *uv1_hdr;
+	struct uv2_bau_msg_header *uv2_hdr;
 	struct bau_control *bcp;
 
 	/*

@@ -1451,6 +1677,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	gpa = uv_gpa(bau_desc);
 	n = uv_gpa_to_gnode(gpa);
 	m = uv_gpa_to_offset(gpa);
+	if (is_uv1_hub())
+		uv1 = 1;
 
 	/* the 14-bit pnode */
 	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));

@@ -1461,21 +1689,33 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 	 */
 	for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) {
 		memset(bd2, 0, sizeof(struct bau_desc));
-		bd2->header.swack_flag =	1;
-		/*
-		 * The base_dest_nasid set in the message header is the nasid
-		 * of the first uvhub in the partition. The bit map will
-		 * indicate destination pnode numbers relative to that base.
-		 * They may not be consecutive if nasid striding is being used.
-		 */
-		bd2->header.base_dest_nasid =	UV_PNODE_TO_NASID(base_pnode);
-		bd2->header.dest_subnodeid =	UV_LB_SUBNODEID;
-		bd2->header.command =		UV_NET_ENDPOINT_INTD;
-		bd2->header.int_both =		1;
-		/*
-		 * all others need to be set to zero:
-		 *   fairness chaining multilevel count replied_to
-		 */
+		if (uv1) {
+			uv1_hdr = &bd2->header.uv1_hdr;
+			uv1_hdr->swack_flag =	1;
+			/*
+			 * The base_dest_nasid set in the message header
+			 * is the nasid of the first uvhub in the partition.
+			 * The bit map will indicate destination pnode numbers
+			 * relative to that base. They may not be consecutive
+			 * if nasid striding is being used.
+			 */
+			uv1_hdr->base_dest_nasid =
+						UV_PNODE_TO_NASID(base_pnode);
+			uv1_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
+			uv1_hdr->command =		UV_NET_ENDPOINT_INTD;
+			uv1_hdr->int_both =		1;
+			/*
+			 * all others need to be set to zero:
+			 *   fairness chaining multilevel count replied_to
+			 */
+		} else {
+			uv2_hdr = &bd2->header.uv2_hdr;
+			uv2_hdr->swack_flag =	1;
+			uv2_hdr->base_dest_nasid =
+						UV_PNODE_TO_NASID(base_pnode);
+			uv2_hdr->dest_subnodeid =	UV_LB_SUBNODEID;
+			uv2_hdr->command =		UV_NET_ENDPOINT_INTD;
+		}
 	}
 	for_each_present_cpu(cpu) {
 		if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu)))

@@ -1531,6 +1771,7 @@ static void pq_init(int node, int pnode)
 	write_mmr_payload_first(pnode, pn_first);
 	write_mmr_payload_tail(pnode, first);
 	write_mmr_payload_last(pnode, last);
+	write_gmmr_sw_ack(pnode, 0xffffUL);
 
 	/* in effect, all msg_type's are set to MSG_NOOP */
 	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);

@@ -1584,14 +1825,14 @@ static int calculate_destination_timeout(void)
 		ts_ns = base * mult1 * mult2;
 		ret = ts_ns / 1000;
 	} else {
-		/* 4 bits  0/1 for 10/80us, 3 bits of multiplier */
-		mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+		/* 4 bits  0/1 for 10/80us base, 3 bits of multiplier */
+		mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL);
 		mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
 		if (mmr_image & (1L << UV2_ACK_UNITS_SHFT))
-			mult1 = 80;
+			base = 80;
 		else
-			mult1 = 10;
-		base = mmr_image & UV2_ACK_MASK;
+			base = 10;
+		mult1 = mmr_image & UV2_ACK_MASK;
 		ret = mult1 * base;
 	}
 	return ret;

@@ -1618,6 +1859,7 @@ static void __init init_per_cpu_tunables(void)
 		bcp->cong_response_us		= congested_respns_us;
 		bcp->cong_reps			= congested_reps;
 		bcp->cong_period		= congested_period;
+		bcp->clocks_per_100_usec =	usec_2_cycles(100);
 	}
 }
 

@@ -1728,8 +1970,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
 		bcp->cpus_in_socket = sdp->num_cpus;
 		bcp->socket_master = *smasterp;
 		bcp->uvhub = bdp->uvhub;
+		if (is_uv1_hub())
+			bcp->uvhub_version = 1;
+		else if (is_uv2_hub())
+			bcp->uvhub_version = 2;
+		else {
+			printk(KERN_EMERG "uvhub version not 1 or 2\n");
+			return 1;
+		}
 		bcp->uvhub_master = *hmasterp;
 		bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+		bcp->using_desc = bcp->uvhub_cpu;
 		if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
 			printk(KERN_EMERG "%d cpus per uvhub invalid\n",
 				bcp->uvhub_cpu);

@@ -1845,6 +2096,8 @@ static int __init uv_bau_init(void)
 			uv_base_pnode = uv_blade_to_pnode(uvhub);
 	}
 
+	enable_timeouts();
+
 	if (init_per_cpu(nuvhubs, uv_base_pnode)) {
 		nobau = 1;
 		return 0;

@@ -1855,7 +2108,6 @@ static int __init uv_bau_init(void)
 		if (uv_blade_nr_possible_cpus(uvhub))
 			init_uvhub(uvhub, vector, uv_base_pnode);
 
-	enable_timeouts();
 	alloc_intr_gate(vector, uv_bau_message_intr1);
 
 	for_each_possible_blade(uvhub) {

@@ -1867,7 +2119,8 @@ static int __init uv_bau_init(void)
 			val = 1L << 63;
 			write_gmmr_activation(pnode, val);
 			mmr = 1; /* should be 1 to broadcast to both sockets */
-			write_mmr_data_broadcast(pnode, mmr);
+			if (!is_uv1_hub())
+				write_mmr_data_broadcast(pnode, mmr);
 		}
 	}
 

@@ -24,6 +24,7 @@
 #include <linux/capability.h>
 #include <linux/completion.h>
 #include <linux/cdrom.h>
+#include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/times.h>
 #include <asm/uaccess.h>

@@ -690,6 +691,57 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod
 }
 EXPORT_SYMBOL(scsi_cmd_ioctl);
 
+int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
+{
+	if (bd && bd == bd->bd_contains)
+		return 0;
+
+	/* Actually none of these is particularly useful on a partition,
+	 * but they are safe.
+	 */
+	switch (cmd) {
+	case SCSI_IOCTL_GET_IDLUN:
+	case SCSI_IOCTL_GET_BUS_NUMBER:
+	case SCSI_IOCTL_GET_PCI:
+	case SCSI_IOCTL_PROBE_HOST:
+	case SG_GET_VERSION_NUM:
+	case SG_SET_TIMEOUT:
+	case SG_GET_TIMEOUT:
+	case SG_GET_RESERVED_SIZE:
+	case SG_SET_RESERVED_SIZE:
+	case SG_EMULATED_HOST:
+		return 0;
+	case CDROM_GET_CAPABILITY:
+		/* Keep this until we remove the printk below.  udev sends it
+		 * and we do not want to spam dmesg about it.   CD-ROMs do
+		 * not have partitions, so we get here only for disks.
+		 */
+		return -ENOTTY;
+	default:
+		break;
+	}
+
+	/* In particular, rule out all resets and host-specific ioctls.  */
+	printk_ratelimited(KERN_WARNING
+			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
+
+	return capable(CAP_SYS_RAWIO) ? 0 : -ENOTTY;
+}
+EXPORT_SYMBOL(scsi_verify_blk_ioctl);
+
+int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
+		       unsigned int cmd, void __user *arg)
+{
+	int ret;
+
+	ret = scsi_verify_blk_ioctl(bd, cmd);
+	if (ret < 0)
+		return ret;
+
+	return scsi_cmd_ioctl(bd->bd_disk->queue, bd->bd_disk, mode, cmd, arg);
+}
+EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
+
 static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);

@@ -387,5 +387,29 @@ acpi_status acpi_ds_get_region_arguments(union acpi_operand_object *obj_desc)
 	status = acpi_ds_execute_arguments(node, node->parent,
 					   extra_desc->extra.aml_length,
 					   extra_desc->extra.aml_start);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Validate the region address/length via the host OS */
+
+	status = acpi_os_validate_address(obj_desc->region.space_id,
+					  obj_desc->region.address,
+					  (acpi_size) obj_desc->region.length,
+					  acpi_ut_get_node_name(node));
+
+	if (ACPI_FAILURE(status)) {
+		/*
+		 * Invalid address/length. We will emit an error message and mark
+		 * the region as invalid, so that it will cause an additional error if
+		 * it is ever used. Then return AE_OK.
+		 */
+		ACPI_EXCEPTION((AE_INFO, status,
+				"During address validation of OpRegion [%4.4s]",
+				node->name.ascii));
+		obj_desc->common.flags |= AOPOBJ_INVALID;
+		status = AE_OK;
+	}
+
 	return_ACPI_STATUS(status);
 }

@@ -45,6 +45,8 @@ static int pxm_to_node_map[MAX_PXM_DOMAINS]
 static int node_to_pxm_map[MAX_NUMNODES]
 			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
 
+unsigned char acpi_srat_revision __initdata;
+
 int pxm_to_node(int pxm)
 {
 	if (pxm < 0)

@@ -255,9 +257,13 @@ acpi_parse_memory_affinity(struct acpi_subtable_header * header,
 
 static int __init acpi_parse_srat(struct acpi_table_header *table)
 {
+	struct acpi_table_srat *srat;
 	if (!table)
 		return -EINVAL;
 
+	srat = (struct acpi_table_srat *)table;
+	acpi_srat_revision = srat->header.revision;
+
 	/* Real work done in acpi_table_parse_srat below. */
 
 	return 0;

@@ -173,8 +173,30 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 	apic_id = map_mat_entry(handle, type, acpi_id);
 	if (apic_id == -1)
 		apic_id = map_madt_entry(type, acpi_id);
-	if (apic_id == -1)
-		return apic_id;
+	if (apic_id == -1) {
+		/*
+		 * On UP processor, there is no _MAT or MADT table.
+		 * So above apic_id is always set to -1.
+		 *
+		 * BIOS may define multiple CPU handles even for UP processor.
+		 * For example,
+		 *
+		 * Scope (_PR)
+                 * {
+		 *     Processor (CPU0, 0x00, 0x00000410, 0x06) {}
+		 *     Processor (CPU1, 0x01, 0x00000410, 0x06) {}
+		 *     Processor (CPU2, 0x02, 0x00000410, 0x06) {}
+		 *     Processor (CPU3, 0x03, 0x00000410, 0x06) {}
+		 * }
+		 *
+		 * Ignores apic_id and always return 0 for CPU0's handle.
+		 * Return -1 for other CPU's handle.
+		 */
+		if (acpi_id == 0)
+			return acpi_id;
+		else
+			return apic_id;
+	}
 
 #ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {

@@ -227,11 +227,14 @@ static void bcma_host_pci_remove(struct pci_dev *dev)
 #ifdef CONFIG_PM
 static int bcma_host_pci_suspend(struct pci_dev *dev, pm_message_t state)
 {
+	struct bcma_bus *bus = pci_get_drvdata(dev);
+
 	/* Host specific */
 	pci_save_state(dev);
 	pci_disable_device(dev);
 	pci_set_power_state(dev, pci_choose_state(dev, state));
 
+	bus->mapped_core = NULL;
 	return 0;
 }
 

@@ -1735,7 +1735,7 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 	case CCISS_BIG_PASSTHRU:
 		return cciss_bigpassthru(h, argp);
 
-	/* scsi_cmd_ioctl handles these, below, though some are not */
+	/* scsi_cmd_blk_ioctl handles these, below, though some are not */
 	/* very meaningful for cciss.  SG_IO is the main one people want. */
 
 	case SG_GET_VERSION_NUM:

@@ -1746,9 +1746,9 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 	case SG_EMULATED_HOST:
 	case SG_IO:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
+		return scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
 
-	/* scsi_cmd_ioctl would normally handle these, below, but */
+	/* scsi_cmd_blk_ioctl would normally handle these, below, but */
 	/* they aren't a good fit for cciss, as CD-ROMs are */
 	/* not supported, and we don't have any bus/target/lun */
 	/* which we present to the kernel. */

@@ -1744,12 +1744,11 @@ static int ub_bd_release(struct gendisk *disk, fmode_t mode)
 static int ub_bd_ioctl(struct block_device *bdev, fmode_t mode,
     unsigned int cmd, unsigned long arg)
 {
-	struct gendisk *disk = bdev->bd_disk;
 	void __user *usermem = (void __user *) arg;
 	int ret;
 
 	mutex_lock(&ub_mutex);
-	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, usermem);
+	ret = scsi_cmd_blk_ioctl(bdev, mode, cmd, usermem);
 	mutex_unlock(&ub_mutex);
 
 	return ret;

@@ -243,8 +243,8 @@ static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
 		return -ENOTTY;
 
-	return scsi_cmd_ioctl(disk->queue, disk, mode, cmd,
-			      (void __user *)data);
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
 }
 
 /* We provide getgeo only to please some old bootloader/partitioning tools */

@@ -2747,12 +2747,11 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
 {
 	void __user *argp = (void __user *)arg;
 	int ret;
-	struct gendisk *disk = bdev->bd_disk;
 
 	/*
 	 * Try the generic SCSI command ioctl's first.
 	 */
-	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
+	ret = scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
 	if (ret != -ENOTTY)
 		return ret;
 

@@ -2177,6 +2177,7 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev)
 void r100_bm_disable(struct radeon_device *rdev)
 {
 	u32 tmp;
+	u16 tmp16;
 
 	/* disable bus mastering */
 	tmp = RREG32(R_000030_BUS_CNTL);

@@ -2187,8 +2188,8 @@ void r100_bm_disable(struct radeon_device *rdev)
 	WREG32(R_000030_BUS_CNTL, (tmp & 0xFFFFFFFF) | 0x00000040);
 	tmp = RREG32(RADEON_BUS_CNTL);
 	mdelay(1);
-	pci_read_config_word(rdev->pdev, 0x4, (u16*)&tmp);
-	pci_write_config_word(rdev->pdev, 0x4, tmp & 0xFFFB);
+	pci_read_config_word(rdev->pdev, 0x4, &tmp16);
+	pci_write_config_word(rdev->pdev, 0x4, tmp16 & 0xFFFB);
 	mdelay(1);
 }
 

@@ -196,6 +196,13 @@ static void r600_hdmi_videoinfoframe(
 	frame[0xD] = (right_bar >> 8);
 
 	r600_hdmi_infoframe_checksum(0x82, 0x02, 0x0D, frame);
+	/* Our header values (type, version, length) should be alright, Intel
+	 * is using the same. Checksum function also seems to be OK, it works
+	 * fine for audio infoframe. However calculated value is always lower
+	 * by 2 in comparison to fglrx. It breaks displaying anything in case
+	 * of TVs that strictly check the checksum. Hack it manually here to
+	 * workaround this issue. */
+	frame[0x0] += 2;
 
 	WREG32(offset+R600_HDMI_VIDEOINFOFRAME_0,
 		frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24));

@@ -224,8 +224,11 @@ int radeon_wb_init(struct radeon_device *rdev)
 	if (radeon_no_wb == 1)
 		rdev->wb.enabled = false;
 	else {
-		/* often unreliable on AGP */
 		if (rdev->flags & RADEON_IS_AGP) {
+			/* often unreliable on AGP */
+			rdev->wb.enabled = false;
+		} else if (rdev->family < CHIP_R300) {
+			/* often unreliable on pre-r300 */
 			rdev->wb.enabled = false;
 		} else {
 			rdev->wb.enabled = true;

@@ -324,10 +324,10 @@ void rs600_hpd_fini(struct radeon_device *rdev)
 
 void rs600_bm_disable(struct radeon_device *rdev)
 {
-	u32 tmp;
+	u16 tmp;
 
 	/* disable bus mastering */
-	pci_read_config_word(rdev->pdev, 0x4, (u16*)&tmp);
+	pci_read_config_word(rdev->pdev, 0x4, &tmp);
 	pci_write_config_word(rdev->pdev, 0x4, tmp & 0xFFFB);
 	mdelay(1);
 }

@@ -335,6 +335,7 @@ config HID_MULTITOUCH
 	  Say Y here if you have one of the following devices:
 	  - 3M PCT touch screens
 	  - ActionStar dual touch panels
+	  - Atmel panels
 	  - Cando dual touch panels
 	  - Chunghwa panels
 	  - CVTouch panels

@@ -355,6 +356,7 @@ config HID_MULTITOUCH
 	  - Touch International Panels
 	  - Unitec Panels
 	  - XAT optical touch panels
+	  - Xiroku optical touch panels
 
 	  If unsure, say N.
 

@@ -620,6 +622,7 @@ config HID_WIIMOTE
 	depends on BT_HIDP
 	depends on LEDS_CLASS
 	select POWER_SUPPLY
+	select INPUT_FF_MEMLESS
 	---help---
 	Support for the Nintendo Wii Remote bluetooth device.
 

@@ -362,7 +362,7 @@ static int hid_parser_global(struct hid_parser *parser, struct hid_item *item)
 
 	case HID_GLOBAL_ITEM_TAG_REPORT_SIZE:
 		parser->global.report_size = item_udata(item);
-		if (parser->global.report_size > 32) {
+		if (parser->global.report_size > 96) {
 			dbg_hid("invalid report_size %d\n",
 					parser->global.report_size);
 			return -1;

@@ -1404,11 +1404,13 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_TRUETOUCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0011) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH1) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH2) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH3) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH4) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480D) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480E) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_720C) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_726B) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_72A1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7302) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2515) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_EMS, USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II) },

@@ -1423,6 +1425,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE_3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HANVON, USB_DEVICE_ID_HANVON_MULTITOUCH) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_HANVON_ALT, USB_DEVICE_ID_HANVON_ALT_MULTITOUCH) },
  	{ HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6650) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK, USB_DEVICE_ID_HOLTEK_ON_LINE_GRIP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ILITEK, USB_DEVICE_ID_ILITEK_MULTITOUCH) },

@@ -1549,6 +1552,15 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_10_6_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_MEDIA_TABLET_14_1_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_XAT, USB_DEVICE_ID_XAT_CSR) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_SPX) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_MPX) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_SPX1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_MPX1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_SPX2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_MPX2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_X_TENSIONS, USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) },

@@ -21,6 +21,7 @@
 #define USB_VENDOR_ID_3M		0x0596
 #define USB_DEVICE_ID_3M1968		0x0500
 #define USB_DEVICE_ID_3M2256		0x0502
+#define USB_DEVICE_ID_3M3266		0x0506
 
 #define USB_VENDOR_ID_A4TECH		0x09da
 #define USB_DEVICE_ID_A4TECH_WCP32PU	0x0006

@@ -145,6 +146,9 @@
 #define USB_DEVICE_ID_ATEN_4PORTKVM	0x2205
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
 
+#define USB_VENDOR_ID_ATMEL		0x03eb
+#define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
+
 #define USB_VENDOR_ID_AVERMEDIA		0x07ca
 #define USB_DEVICE_ID_AVER_FM_MR800	0xb800
 

@@ -230,11 +234,14 @@
 
 #define USB_VENDOR_ID_DWAV		0x0eef
 #define USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER	0x0001
-#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH	0x480d
-#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH1	0x720c
-#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH2	0x72a1
-#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH3	0x480e
-#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH4	0x726b
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480D	0x480d
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480E	0x480e
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_720C	0x720c
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_726B	0x726b
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_72A1	0x72a1
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_72FA	0x72fa
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7302	0x7302
+#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001	0xa001
 
 #define USB_VENDOR_ID_ELECOM		0x056e
 #define USB_DEVICE_ID_ELECOM_BM084	0x0061

@@ -356,6 +363,9 @@
 #define USB_VENDOR_ID_HANVON		0x20b3
 #define USB_DEVICE_ID_HANVON_MULTITOUCH	0x0a18
 
+#define USB_VENDOR_ID_HANVON_ALT	0x22ed
+#define USB_DEVICE_ID_HANVON_ALT_MULTITOUCH	0x1010
+
 #define USB_VENDOR_ID_HAPP		0x078b
 #define USB_DEVICE_ID_UGCI_DRIVING	0x0010
 #define USB_DEVICE_ID_UGCI_FLYING	0x0020

@@ -707,6 +717,17 @@
 #define USB_VENDOR_ID_XAT	0x2505
 #define USB_DEVICE_ID_XAT_CSR	0x0220
 
+#define USB_VENDOR_ID_XIROKU		0x1477
+#define USB_DEVICE_ID_XIROKU_SPX	0x1006
+#define USB_DEVICE_ID_XIROKU_MPX	0x1007
+#define USB_DEVICE_ID_XIROKU_CSR	0x100e
+#define USB_DEVICE_ID_XIROKU_SPX1	0x1021
+#define USB_DEVICE_ID_XIROKU_CSR1	0x1022
+#define USB_DEVICE_ID_XIROKU_MPX1	0x1023
+#define USB_DEVICE_ID_XIROKU_SPX2	0x1024
+#define USB_DEVICE_ID_XIROKU_CSR2	0x1025
+#define USB_DEVICE_ID_XIROKU_MPX2	0x1026
+
 #define USB_VENDOR_ID_YEALINK		0x6993
 #define USB_DEVICE_ID_YEALINK_P1K_P4K_B2K	0xb001
 

@@ -609,12 +609,20 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_3M,
 		HID_USB_DEVICE(USB_VENDOR_ID_3M,
 			USB_DEVICE_ID_3M2256) },
+	{ .driver_data = MT_CLS_3M,
+		HID_USB_DEVICE(USB_VENDOR_ID_3M,
+			USB_DEVICE_ID_3M3266) },
 
 	/* ActionStar panels */
 	{ .driver_data = MT_CLS_DEFAULT,
 		HID_USB_DEVICE(USB_VENDOR_ID_ACTIONSTAR,
 			USB_DEVICE_ID_ACTIONSTAR_1011) },
 
+	/* Atmel panels */
+	{ .driver_data = MT_CLS_SERIAL,
+		HID_USB_DEVICE(USB_VENDOR_ID_ATMEL,
+			USB_DEVICE_ID_ATMEL_MULTITOUCH) },
+
 	/* Cando panels */
 	{ .driver_data = MT_CLS_DUAL_INRANGE_CONTACTNUMBER,
 		HID_USB_DEVICE(USB_VENDOR_ID_CANDO,

@@ -645,23 +653,32 @@ static const struct hid_device_id mt_devices[] = {
 			USB_DEVICE_ID_CYPRESS_TRUETOUCH) },
 
 	/* eGalax devices (resistive) */
-	{  .driver_data = MT_CLS_EGALAX,
+	{ .driver_data = MT_CLS_EGALAX,
 		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
-			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH) },
-	{  .driver_data = MT_CLS_EGALAX,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480D) },
+	{ .driver_data = MT_CLS_EGALAX,
 		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
-			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH3) },
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_480E) },
 
 	/* eGalax devices (capacitive) */
-	{  .driver_data = MT_CLS_EGALAX,
+	{ .driver_data = MT_CLS_EGALAX,
+		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_720C) },
+	{ .driver_data = MT_CLS_EGALAX,
 		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
-			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH1) },
-	{  .driver_data = MT_CLS_EGALAX,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_726B) },
+	{ .driver_data = MT_CLS_EGALAX,
 		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
-			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH2) },
-	{  .driver_data = MT_CLS_EGALAX,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_72A1) },
+	{ .driver_data = MT_CLS_EGALAX,
 		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
-			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH4) },
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_72FA) },
+	{ .driver_data = MT_CLS_EGALAX,
+		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7302) },
+	{ .driver_data = MT_CLS_EGALAX,
+		HID_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) },
 
 	/* Elo TouchSystems IntelliTouch Plus panel */
 	{ .driver_data = MT_CLS_DUAL_NSMU_CONTACTID,

@@ -678,6 +695,11 @@ static const struct hid_device_id mt_devices[] = {
 		HID_USB_DEVICE(USB_VENDOR_ID_GOODTOUCH,
 			USB_DEVICE_ID_GOODTOUCH_000f) },
 
+	/* Hanvon panels */
+	{ .driver_data = MT_CLS_DUAL_INRANGE_CONTACTID,
+		HID_USB_DEVICE(USB_VENDOR_ID_HANVON_ALT,
+			USB_DEVICE_ID_HANVON_ALT_MULTITOUCH) },
+
 	/* Ideacom panel */
 	{ .driver_data = MT_CLS_SERIAL,
 		HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM,

@@ -758,6 +780,35 @@ static const struct hid_device_id mt_devices[] = {
 		HID_USB_DEVICE(USB_VENDOR_ID_XAT,
 			USB_DEVICE_ID_XAT_CSR) },
 
+	/* Xiroku */
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_SPX) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_MPX) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_CSR) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_SPX1) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_MPX1) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_CSR1) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_SPX2) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_MPX2) },
+	{ .driver_data = MT_CLS_DEFAULT,
+		HID_USB_DEVICE(USB_VENDOR_ID_XIROKU,
+			USB_DEVICE_ID_XIROKU_CSR2) },
+
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, mt_devices);

@@ -140,7 +140,7 @@ static unsigned short ali1535_smba;
    defined to make the transition easier. */
 static int __devinit ali1535_setup(struct pci_dev *dev)
 {
-	int retval = -ENODEV;
+	int retval;
 	unsigned char temp;
 
 	/* Check the following things:

@@ -155,6 +155,7 @@ static int __devinit ali1535_setup(struct pci_dev *dev)
 	if (ali1535_smba == 0) {
 		dev_warn(&dev->dev,
 			"ALI1535_smb region uninitialized - upgrade BIOS?\n");
+		retval = -ENODEV;
 		goto exit;
 	}
 

@@ -167,6 +168,7 @@ static int __devinit ali1535_setup(struct pci_dev *dev)
 			    ali1535_driver.name)) {
 		dev_err(&dev->dev, "ALI1535_smb region 0x%x already in use!\n",
 			ali1535_smba);
+		retval = -EBUSY;
 		goto exit;
 	}
 

@@ -174,6 +176,7 @@ static int __devinit ali1535_setup(struct pci_dev *dev)
 	pci_read_config_byte(dev, SMBCFG, &temp);
 	if ((temp & ALI1535_SMBIO_EN) == 0) {
 		dev_err(&dev->dev, "SMB device not enabled - upgrade BIOS?\n");
+		retval = -ENODEV;
 		goto exit_free;
 	}
 

@@ -181,6 +184,7 @@ static int __devinit ali1535_setup(struct pci_dev *dev)
 	pci_read_config_byte(dev, SMBHSTCFG, &temp);
 	if ((temp & 1) == 0) {
 		dev_err(&dev->dev, "SMBus controller not enabled - upgrade BIOS?\n");
+		retval = -ENODEV;
 		goto exit_free;
 	}
 

@@ -198,12 +202,11 @@ static int __devinit ali1535_setup(struct pci_dev *dev)
 	dev_dbg(&dev->dev, "SMBREV = 0x%X\n", temp);
 	dev_dbg(&dev->dev, "ALI1535_smba = 0x%X\n", ali1535_smba);
 
-	retval = 0;
-exit:
-	return retval;
+	return 0;
 
 exit_free:
 	release_region(ali1535_smba, ALI1535_SMB_IOSIZE);
+exit:
 	return retval;
 }
 

@@ -243,7 +243,7 @@ static void pch_i2c_init(struct i2c_algo_pch_data *adap)
 	if (pch_clk > PCH_MAX_CLK)
 		pch_clk = 62500;
 
-	pch_i2cbc = (pch_clk + (pch_i2c_speed * 4)) / pch_i2c_speed * 8;
+	pch_i2cbc = (pch_clk + (pch_i2c_speed * 4)) / (pch_i2c_speed * 8);
 	/* Set transfer speed in I2CBC */
 	iowrite32(pch_i2cbc, p + PCH_I2CBC);
 

@@ -356,7 +356,7 @@ static int __devinit nforce2_probe_smb (struct pci_dev *dev, int bar,
 	error = acpi_check_region(smbus->base, smbus->size,
 				  nforce2_driver.name);
 	if (error)
-		return -1;
+		return error;
 
 	if (!request_region(smbus->base, smbus->size, nforce2_driver.name)) {
 		dev_err(&smbus->adapter.dev, "Error requesting region %02x .. %02X for %s\n",

@@ -235,7 +235,7 @@ static const u8 reg_map_ip_v2[] = {
 	[OMAP_I2C_BUF_REG] = 0x94,
 	[OMAP_I2C_CNT_REG] = 0x98,
 	[OMAP_I2C_DATA_REG] = 0x9c,
-	[OMAP_I2C_SYSC_REG] = 0x20,
+	[OMAP_I2C_SYSC_REG] = 0x10,
 	[OMAP_I2C_CON_REG] = 0xa4,
 	[OMAP_I2C_OA_REG] = 0xa8,
 	[OMAP_I2C_SA_REG] = 0xac,

@@ -147,7 +147,7 @@ static int __devinit sis5595_setup(struct pci_dev *SIS5595_dev)
 	u16 a;
 	u8 val;
 	int *i;
-	int retval = -ENODEV;
+	int retval;
 
 	/* Look for imposters */
 	for (i = blacklist; *i != 0; i++) {

@@ -223,7 +223,7 @@ static int __devinit sis5595_setup(struct pci_dev *SIS5595_dev)
 
 error:
 	release_region(sis5595_base + SMB_INDEX, 2);
-	return retval;
+	return -ENODEV;
 }
 
 static int sis5595_transaction(struct i2c_adapter *adap)

@@ -393,7 +393,7 @@ static int __devinit sis630_setup(struct pci_dev *sis630_dev)
 {
 	unsigned char b;
 	struct pci_dev *dummy = NULL;
-	int retval = -ENODEV, i;
+	int retval, i;
 
 	/* check for supported SiS devices */
 	for (i=0; supported[i] > 0 ; i++) {

@@ -418,18 +418,21 @@ static int __devinit sis630_setup(struct pci_dev *sis630_dev)
 	*/
 	if (pci_read_config_byte(sis630_dev, SIS630_BIOS_CTL_REG,&b)) {
 		dev_err(&sis630_dev->dev, "Error: Can't read bios ctl reg\n");
+		retval = -ENODEV;
 		goto exit;
 	}
 	/* if ACPI already enabled , do nothing */
 	if (!(b & 0x80) &&
 	    pci_write_config_byte(sis630_dev, SIS630_BIOS_CTL_REG, b | 0x80)) {
 		dev_err(&sis630_dev->dev, "Error: Can't enable ACPI\n");
+		retval = -ENODEV;
 		goto exit;
 	}
 
 	/* Determine the ACPI base address */
 	if (pci_read_config_word(sis630_dev,SIS630_ACPI_BASE_REG,&acpi_base)) {
 		dev_err(&sis630_dev->dev, "Error: Can't determine ACPI base address\n");
+		retval = -ENODEV;
 		goto exit;
 	}
 

@@ -445,6 +448,7 @@ static int __devinit sis630_setup(struct pci_dev *sis630_dev)
 			    sis630_driver.name)) {
 		dev_err(&sis630_dev->dev, "SMBus registers 0x%04x-0x%04x already "
 			"in use!\n", acpi_base + SMB_STS, acpi_base + SMB_SAA);
+		retval = -EBUSY;
 		goto exit;
 	}
 

@@ -324,7 +324,7 @@ static int __devinit vt596_probe(struct pci_dev *pdev,
 				 const struct pci_device_id *id)
 {
 	unsigned char temp;
-	int error = -ENODEV;
+	int error;
 
 	/* Determine the address of the SMBus areas */
 	if (force_addr) {

@@ -390,6 +390,7 @@ found:
 			dev_err(&pdev->dev, "SMBUS: Error: Host SMBus "
 				"controller not enabled! - upgrade BIOS or "
 				"use force=1\n");
+			error = -ENODEV;
 			goto release_region;
 		}
 	}

@@ -422,9 +423,11 @@ found:
 		 "SMBus Via Pro adapter at %04x", vt596_smba);
 
 	vt596_pdev = pci_dev_get(pdev);
-	if (i2c_add_adapter(&vt596_adapter)) {
+	error = i2c_add_adapter(&vt596_adapter);
+	if (error) {
 		pci_dev_put(vt596_pdev);
 		vt596_pdev = NULL;
+		goto release_region;
 	}
 
 	/* Always return failure here.  This is to allow other drivers to bind

@@ -292,8 +292,7 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	 * and CDROM_SEND_PACKET (legacy) ioctls
 	 */
 	if (cmd != CDROM_SEND_PACKET && cmd != SCSI_IOCTL_SEND_COMMAND)
-		err = scsi_cmd_ioctl(bdev->bd_disk->queue, bdev->bd_disk,
-				mode, cmd, argp);
+		err = scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
 
 	if (err == -ENOTTY)
 		err = generic_ide_ioctl(drive, bdev, cmd, arg);

@@ -348,7 +348,8 @@ static int intel_idle_probe(void)
 	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
 
 	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
-		!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK) ||
+	    !mwait_substates)
 			return -ENODEV;
 
 	pr_debug(PREFIX "MWAIT substates: 0x%x\n", mwait_substates);

@@ -394,7 +395,7 @@ static int intel_idle_probe(void)
 	if (boot_cpu_has(X86_FEATURE_ARAT))	/* Always Reliable APIC Timer */
 		lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
 	else {
-		smp_call_function(__setup_broadcast_timer, (void *)true, 1);
+		on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
 		register_cpu_notifier(&setup_broadcast_notifier);
 	}
 

@@ -471,7 +472,7 @@ static int intel_idle_cpuidle_driver_init(void)
 	}
 
 	if (auto_demotion_disable_flags)
-		smp_call_function(auto_demotion_disable, NULL, 1);
+		on_each_cpu(auto_demotion_disable, NULL, 1);
 
 	return 0;
 }

@@ -568,7 +569,7 @@ static void __exit intel_idle_exit(void)
 	cpuidle_unregister_driver(&intel_idle_driver);
 
 	if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
-		smp_call_function(__setup_broadcast_timer, (void *)false, 1);
+		on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
 		unregister_cpu_notifier(&setup_broadcast_notifier);
 	}
 

@@ -368,8 +368,17 @@ static int flakey_status(struct dm_target *ti, status_type_t type,
 static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long arg)
 {
 	struct flakey_c *fc = ti->private;
+	struct dm_dev *dev = fc->dev;
+	int r = 0;
 
-	return __blkdev_driver_ioctl(fc->dev->bdev, fc->dev->mode, cmd, arg);
+	/*
+	 * Only pass ioctls through if the device sizes match exactly.
+	 */
+	if (fc->start ||
+	    ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
+		r = scsi_verify_blk_ioctl(NULL, cmd);
+
+	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
 static int flakey_merge(struct dm_target *ti, struct bvec_merge_data *bvm,

@@ -116,7 +116,17 @@ static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
 			unsigned long arg)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
-	return __blkdev_driver_ioctl(lc->dev->bdev, lc->dev->mode, cmd, arg);
+	struct dm_dev *dev = lc->dev;
+	int r = 0;
+
+	/*
+	 * Only pass ioctls through if the device sizes match exactly.
+	 */
+	if (lc->start ||
+	    ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
+		r = scsi_verify_blk_ioctl(NULL, cmd);
+
+	return r ? : __blkdev_driver_ioctl(dev->bdev, dev->mode, cmd, arg);
 }
 
 static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,

@@ -1520,6 +1520,12 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
+	/*
+	 * Only pass ioctls through if the device sizes match exactly.
+	 */
+	if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
+		r = scsi_verify_blk_ioctl(NULL, cmd);
+
 	return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 }
 

@@ -525,8 +525,17 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		if (test_bit(WriteMostly, &rdev->flags)) {
 			/* Don't balance among write-mostly, just
 			 * use the first as a last resort */
-			if (best_disk < 0)
+			if (best_disk < 0) {
+				if (is_badblock(rdev, this_sector, sectors,
+						&first_bad, &bad_sectors)) {
+					if (first_bad < this_sector)
+						/* Cannot use this */
+						continue;
+					best_good_sectors = first_bad - this_sector;
+				} else
+					best_good_sectors = sectors;
 				best_disk = disk;
+			}
 			continue;
 		}
 		/* This is a reasonable device to use.  It might

@@ -940,6 +940,11 @@ static int dvb_register(struct cx23885_tsport *port)
 
 			fe = dvb_attach(xc4000_attach, fe0->dvb.frontend,
 					&dev->i2c_bus[1].i2c_adap, &cfg);
+			if (!fe) {
+				printk(KERN_ERR "%s/2: xc4000 attach failed\n",
+				       dev->name);
+				goto frontend_detach;
+			}
 		}
 		break;
 	case CX23885_BOARD_TBS_6920:

@@ -1573,8 +1573,8 @@ static const struct cx88_board cx88_boards[] = {
 		.name           = "Pinnacle Hybrid PCTV",
 		.tuner_type     = TUNER_XC2028,
 		.tuner_addr     = 0x61,
-		.radio_type     = TUNER_XC2028,
-		.radio_addr     = 0x61,
+		.radio_type     = UNSET,
+		.radio_addr     = ADDR_UNSET,
 		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,

@@ -1611,8 +1611,8 @@ static const struct cx88_board cx88_boards[] = {
 		.name           = "Leadtek TV2000 XP Global",
 		.tuner_type     = TUNER_XC2028,
 		.tuner_addr     = 0x61,
-		.radio_type     = TUNER_XC2028,
-		.radio_addr     = 0x61,
+		.radio_type     = UNSET,
+		.radio_addr     = ADDR_UNSET,
 		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,

@@ -2043,8 +2043,8 @@ static const struct cx88_board cx88_boards[] = {
 		.name           = "Terratec Cinergy HT PCI MKII",
 		.tuner_type     = TUNER_XC2028,
 		.tuner_addr     = 0x61,
-		.radio_type     = TUNER_XC2028,
-		.radio_addr     = 0x61,
+		.radio_type     = UNSET,
+		.radio_addr     = ADDR_UNSET,
 		.input          = { {
 			.type   = CX88_VMUX_TELEVISION,
 			.vmux   = 0,

@@ -2082,9 +2082,9 @@ static const struct cx88_board cx88_boards[] = {
 	[CX88_BOARD_WINFAST_DTV1800H] = {
 		.name           = "Leadtek WinFast DTV1800 Hybrid",
 		.tuner_type     = TUNER_XC2028,
-		.radio_type     = TUNER_XC2028,
+		.radio_type     = UNSET,
 		.tuner_addr     = 0x61,
-		.radio_addr     = 0x61,
+		.radio_addr     = ADDR_UNSET,
 		/*
 		 * GPIO setting
 		 *

@@ -2123,9 +2123,9 @@ static const struct cx88_board cx88_boards[] = {
 	[CX88_BOARD_WINFAST_DTV1800H_XC4000] = {
 		.name		= "Leadtek WinFast DTV1800 H (XC4000)",
 		.tuner_type	= TUNER_XC4000,
-		.radio_type	= TUNER_XC4000,
+		.radio_type	= UNSET,
 		.tuner_addr	= 0x61,
-		.radio_addr	= 0x61,
+		.radio_addr	= ADDR_UNSET,
 		/*
 		 * GPIO setting
 		 *

@@ -2164,9 +2164,9 @@ static const struct cx88_board cx88_boards[] = {
 	[CX88_BOARD_WINFAST_DTV2000H_PLUS] = {
 		.name		= "Leadtek WinFast DTV2000 H PLUS",
 		.tuner_type	= TUNER_XC4000,
-		.radio_type	= TUNER_XC4000,
+		.radio_type	= UNSET,
 		.tuner_addr	= 0x61,
-		.radio_addr	= 0x61,
+		.radio_addr	= ADDR_UNSET,
 		/*
 		 * GPIO
 		 *   2: 1: mute audio

@@ -58,6 +58,15 @@ static int uvc_ioctl_ctrl_map(struct uvc_video_chain *chain,
 		break;
 
 	case V4L2_CTRL_TYPE_MENU:
+		/* Prevent excessive memory consumption, as well as integer
+		 * overflows.
+		 */
+		if (xmap->menu_count == 0 ||
+		    xmap->menu_count > UVC_MAX_CONTROL_MENU_ENTRIES) {
+			ret = -EINVAL;
+			goto done;
+		}
+
 		size = xmap->menu_count * sizeof(*map->menu_info);
 		map->menu_info = kmalloc(size, GFP_KERNEL);
 		if (map->menu_info == NULL) {

@@ -113,6 +113,7 @@
 
 /* Maximum allowed number of control mappings per device */
 #define UVC_MAX_CONTROL_MAPPINGS	1024
+#define UVC_MAX_CONTROL_MENU_ENTRIES	32
 
 /* Devices quirks */
 #define UVC_QUIRK_STATUS_INTERVAL	0x00000001

@@ -2226,6 +2226,10 @@ static int check_array_args(unsigned int cmd, void *parg, size_t *array_size,
 		struct v4l2_ext_controls *ctrls = parg;
 
 		if (ctrls->count != 0) {
+			if (ctrls->count > V4L2_CID_MAX_CTRLS) {
+				ret = -EINVAL;
+				break;
+			}
 			*user_ptr = (void __user *)ctrls->controls;
 			*kernel_ptr = (void *)&ctrls->controls;
 			*array_size = sizeof(struct v4l2_ext_control)

@@ -1048,7 +1048,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			 *
 			 * WARNING: eMMC rules are NOT the same as SD DDR
 			 */
-			if (ddr == EXT_CSD_CARD_TYPE_DDR_1_2V) {
+			if (ddr == MMC_1_2V_DDR_MODE) {
 				err = mmc_set_signal_voltage(host,
 					MMC_SIGNAL_VOLTAGE_120, 0);
 				if (err)

@@ -1364,8 +1364,7 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 		if ((ios->timing == MMC_TIMING_UHS_SDR50) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR104) ||
 		    (ios->timing == MMC_TIMING_UHS_DDR50) ||
-		    (ios->timing == MMC_TIMING_UHS_SDR25) ||
-		    (ios->timing == MMC_TIMING_UHS_SDR12))
+		    (ios->timing == MMC_TIMING_UHS_SDR25))
 			ctrl |= SDHCI_CTRL_HISPD;
 
 		ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);

@@ -2336,9 +2335,8 @@ int sdhci_suspend_host(struct sdhci_host *host)
 	/* Disable tuning since we are suspending */
 	if (host->version >= SDHCI_SPEC_300 && host->tuning_count &&
 	    host->tuning_mode == SDHCI_TUNING_MODE_1) {
+		del_timer_sync(&host->tuning_timer);
 		host->flags &= ~SDHCI_NEEDS_RETUNING;
-		mod_timer(&host->tuning_timer, jiffies +
-			host->tuning_count * HZ);
 	}
 
 	ret = mmc_suspend_host(host->mmc);

@@ -215,7 +215,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 
 	mutex_lock(&dev->lock);
 
-	if (dev->open++)
+	if (dev->open)
 		goto unlock;
 
 	kref_get(&dev->ref);

@@ -235,6 +235,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 		goto error_release;
 
 unlock:
+	dev->open++;
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;

@@ -253,6 +253,9 @@ static void find_next_position(struct mtdoops_context *cxt)
 	size_t retlen;
 
 	for (page = 0; page < cxt->oops_pages; page++) {
+		if (mtd->block_isbad &&
+		    mtd->block_isbad(mtd, page * record_size))
+			continue;
 		/* Assume the page is used */
 		mark_page_used(cxt, page);
 		ret = mtd->read(mtd, page * record_size, MTDOOPS_HEADER_SIZE,

@@ -369,7 +372,7 @@ static void mtdoops_notify_add(struct mtd_info *mtd)
 
 	/* oops_page_used is a bit field */
 	cxt->oops_page_used = vmalloc(DIV_ROUND_UP(mtdoops_pages,
-			BITS_PER_LONG));
+			BITS_PER_LONG) * sizeof(unsigned long));
 	if (!cxt->oops_page_used) {
 		printk(KERN_ERR "mtdoops: could not allocate page array\n");
 		return;

@@ -284,6 +284,12 @@ static int __init mtd_stresstest_init(void)
 	       (unsigned long long)mtd->size, mtd->erasesize,
 	       pgsize, ebcnt, pgcnt, mtd->oobsize);
 
+	if (ebcnt < 2) {
+		printk(PRINT_PREF "error: need at least 2 eraseblocks\n");
+		err = -ENOSPC;
+		goto out_put_mtd;
+	}
+
 	/* Read or write up 2 eraseblocks at a time */
 	bufsize = mtd->erasesize * 2;
 

@@ -322,6 +328,7 @@ out:
 	kfree(bbt);
 	vfree(writebuf);
 	vfree(readbuf);
+out_put_mtd:
 	put_mtd_device(mtd);
 	if (err)
 		printk(PRINT_PREF "error %d occurred\n", err);

@@ -632,6 +632,9 @@ static int verify_mkvol_req(const struct ubi_device *ubi,
 	if (req->alignment != 1 && n)
 		goto bad;
 
+	if (!req->name[0] || !req->name_len)
+		goto bad;
+
 	if (req->name_len > UBI_VOL_NAME_MAX) {
 		err = -ENAMETOOLONG;
 		goto bad;

@@ -43,7 +43,10 @@
 	pr_debug("UBI DBG " type ": " fmt "\n", ##__VA_ARGS__)
 
 /* Just a debugging messages not related to any specific UBI subsystem */
-#define dbg_msg(fmt, ...) ubi_dbg_msg("msg", fmt, ##__VA_ARGS__)
+#define dbg_msg(fmt, ...)                                    \
+	printk(KERN_DEBUG "UBI DBG (pid %d): %s: " fmt "\n", \
+	       current->pid, __func__, ##__VA_ARGS__)
+
 /* General debugging messages */
 #define dbg_gen(fmt, ...) ubi_dbg_msg("gen", fmt, ##__VA_ARGS__)
 /* Messages from the eraseblock association sub-system */

@@ -1028,12 +1028,14 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
 	 * 'ubi_wl_put_peb()' function on the @ubi->move_mutex. In turn, we are
 	 * holding @ubi->move_mutex and go sleep on the LEB lock. So, if the
 	 * LEB is already locked, we just do not move it and return
-	 * %MOVE_CANCEL_RACE, which means that UBI will re-try, but later.
+	 * %MOVE_RETRY. Note, we do not return %MOVE_CANCEL_RACE here because
+	 * we do not know the reasons of the contention - it may be just a
+	 * normal I/O on this LEB, so we want to re-try.
 	 */
 	err = leb_write_trylock(ubi, vol_id, lnum);
 	if (err) {
 		dbg_wl("contention on LEB %d:%d, cancel", vol_id, lnum);
-		return MOVE_CANCEL_RACE;
+		return MOVE_RETRY;
 	}
 
 	/*

@@ -120,6 +120,7 @@ enum {
  *                     PEB
  * MOVE_CANCEL_BITFLIPS: canceled because a bit-flip was detected in the
  *                       target PEB
+ * MOVE_RETRY: retry scrubbing the PEB
  */
 enum {
 	MOVE_CANCEL_RACE = 1,

@@ -127,6 +128,7 @@ enum {
 	MOVE_TARGET_RD_ERR,
 	MOVE_TARGET_WR_ERR,
 	MOVE_CANCEL_BITFLIPS,
+	MOVE_RETRY,
 };
 
 /**

@@ -306,7 +306,7 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_scan_info *si,
 		       int copy, void *vtbl)
 {
 	int err, tries = 0;
-	static struct ubi_vid_hdr *vid_hdr;
+	struct ubi_vid_hdr *vid_hdr;
 	struct ubi_scan_leb *new_seb;
 
 	ubi_msg("create volume table (copy #%d)", copy + 1);

@@ -795,7 +795,10 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
 			protect = 1;
 			goto out_not_moved;
 		}
-
+		if (err == MOVE_RETRY) {
+			scrubbing = 1;
+			goto out_not_moved;
+		}
 		if (err == MOVE_CANCEL_BITFLIPS || err == MOVE_TARGET_WR_ERR ||
 		    err == MOVE_TARGET_RD_ERR) {
 			/*

@@ -1049,7 +1052,6 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
 
 	ubi_err("failed to erase PEB %d, error %d", pnum, err);
 	kfree(wl_wrk);
-	kmem_cache_free(ubi_wl_entry_slab, e);
 
 	if (err == -EINTR || err == -ENOMEM || err == -EAGAIN ||
 	    err == -EBUSY) {

@@ -1062,14 +1064,16 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
 			goto out_ro;
 		}
 		return err;
-	} else if (err != -EIO) {
+	}
+
+	kmem_cache_free(ubi_wl_entry_slab, e);
+	if (err != -EIO)
 		/*
 		 * If this is not %-EIO, we have no idea what to do. Scheduling
 		 * this physical eraseblock for erasure again would cause
 		 * errors again and again. Well, lets switch to R/O mode.
 		 */
 		goto out_ro;
-	}
 
 	/* It is %-EIO, the PEB went bad */
 

@@ -974,6 +974,7 @@ static int ax88772_link_reset(struct usbnet *dev)
 
 static int ax88772_reset(struct usbnet *dev)
 {
+	struct asix_data *data = (struct asix_data *)&dev->data;
 	int ret, embd_phy;
 	u16 rx_ctl;
 

@@ -1051,6 +1052,13 @@ static int ax88772_reset(struct usbnet *dev)
 		goto out;
 	}
 
+	/* Rewrite MAC address */
+	memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN);
+	ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+							data->mac_addr);
+	if (ret < 0)
+		goto out;
+
 	/* Set RX_CTL to default values with 2k buffer, and enable cactus */
 	ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL);
 	if (ret < 0)

@@ -1316,6 +1324,13 @@ static int ax88178_reset(struct usbnet *dev)
 	if (ret < 0)
 		return ret;
 
+	/* Rewrite MAC address */
+	memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN);
+	ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
+							data->mac_addr);
+	if (ret < 0)
+		return ret;
+
 	ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL);
 	if (ret < 0)
 		return ret;

@@ -526,10 +526,11 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs,
 			rxs->rs_status |= ATH9K_RXERR_DECRYPT;
 		else if (rxsp->status11 & AR_MichaelErr)
 			rxs->rs_status |= ATH9K_RXERR_MIC;
-		if (rxsp->status11 & AR_KeyMiss)
-			rxs->rs_status |= ATH9K_RXERR_KEYMISS;
 	}
 
+	if (rxsp->status11 & AR_KeyMiss)
+		rxs->rs_status |= ATH9K_RXERR_KEYMISS;
+
 	return 0;
 }
 EXPORT_SYMBOL(ath9k_hw_process_rxdesc_edma);

@@ -402,6 +402,7 @@ bool ath9k_hw_getnf(struct ath_hw *ah, struct ath9k_channel *chan)
 	ah->noise = ath9k_hw_getchan_noise(ah, chan);
 	return true;
 }
+EXPORT_SYMBOL(ath9k_hw_getnf);
 
 void ath9k_init_nfcal_hist_buffer(struct ath_hw *ah,
 				  struct ath9k_channel *chan)

@@ -621,10 +621,11 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds,
 			rs->rs_status |= ATH9K_RXERR_DECRYPT;
 		else if (ads.ds_rxstatus8 & AR_MichaelErr)
 			rs->rs_status |= ATH9K_RXERR_MIC;
-		if (ads.ds_rxstatus8 & AR_KeyMiss)
-			rs->rs_status |= ATH9K_RXERR_KEYMISS;
 	}
 
+	if (ads.ds_rxstatus8 & AR_KeyMiss)
+		rs->rs_status |= ATH9K_RXERR_KEYMISS;
+
 	return 0;
 }
 EXPORT_SYMBOL(ath9k_hw_rxprocdesc);

@@ -1667,7 +1667,6 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed)
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
 		struct ieee80211_channel *curchan = hw->conf.channel;
-		struct ath9k_channel old_chan;
 		int pos = curchan->hw_value;
 		int old_pos = -1;
 		unsigned long flags;

@@ -1693,11 +1692,8 @@ static int ath9k_config(struct ieee80211_hw *hw, u32 changed)
 		 * Preserve the current channel values, before updating
 		 * the same channel
 		 */
-		if (old_pos == pos) {
-			memcpy(&old_chan, &sc->sc_ah->channels[pos],
-				sizeof(struct ath9k_channel));
-			ah->curchan = &old_chan;
-		}
+		if (ah->curchan && (old_pos == pos))
+			ath9k_hw_getnf(ah, ah->curchan);
 
 		ath9k_cmn_update_ichannel(&sc->sc_ah->channels[pos],
 					  curchan, conf->channel_type);

@@ -2656,14 +2656,13 @@ int iwl3945_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
 		IWL_WARN(priv, "Invalid scan band\n");
 		return -EIO;
 	}
-
 	/*
-	 * If active scaning is requested but a certain channel
-	 * is marked passive, we can do active scanning if we
-	 * detect transmissions.
+	 * If active scaning is requested but a certain channel is marked
+	 * passive, we can do active scanning if we detect transmissions. For
+	 * passive only scanning disable switching to active on any channel.
 	 */
 	scan->good_CRC_th = is_active ? IWL_GOOD_CRC_TH_DEFAULT :
-					IWL_GOOD_CRC_TH_DISABLED;
+					IWL_GOOD_CRC_TH_NEVER;
 
 	len = iwl_legacy_fill_probe_req(priv, (struct ieee80211_mgmt *)scan->data,
 					vif->addr, priv->scan_request->ie,

@@ -827,6 +827,7 @@ static int iwl_get_idle_rx_chain_count(struct iwl_priv *priv, int active_cnt)
 	case IEEE80211_SMPS_STATIC:
 	case IEEE80211_SMPS_DYNAMIC:
 		return IWL_NUM_IDLE_CHAINS_SINGLE;
+	case IEEE80211_SMPS_AUTOMATIC:
 	case IEEE80211_SMPS_OFF:
 		return active_cnt;
 	default:

@@ -559,6 +559,9 @@ int iwlagn_mac_config(struct ieee80211_hw *hw, u32 changed)
 
 	mutex_lock(&priv->shrd->mutex);
 
+	if (test_bit(STATUS_EXIT_PENDING, &priv->shrd->status))
+		goto out;
+
 	if (unlikely(test_bit(STATUS_SCANNING, &priv->shrd->status))) {
 		IWL_DEBUG_MAC80211(priv, "leave - scanning\n");
 		goto out;

@@ -422,7 +422,6 @@ static int rt2800pci_init_queues(struct rt2x00_dev *rt2x00dev)
 static void rt2800pci_toggle_irq(struct rt2x00_dev *rt2x00dev,
 				 enum dev_state state)
 {
-	int mask = (state == STATE_RADIO_IRQ_ON);
 	u32 reg;
 	unsigned long flags;
 

@@ -436,25 +435,14 @@ static void rt2800pci_toggle_irq(struct rt2x00_dev *rt2x00dev,
 	}
 
 	spin_lock_irqsave(&rt2x00dev->irqmask_lock, flags);
-	rt2x00pci_register_read(rt2x00dev, INT_MASK_CSR, &reg);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_RXDELAYINT, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_TXDELAYINT, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_RX_DONE, mask);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_AC0_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_AC1_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_AC2_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_AC3_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_HCCA_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_MGMT_DMA_DONE, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_MCU_COMMAND, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_RXTX_COHERENT, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_TBTT, mask);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_PRE_TBTT, mask);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_TX_FIFO_STATUS, mask);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_AUTO_WAKEUP, mask);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_GPTIMER, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_RX_COHERENT, 0);
-	rt2x00_set_field32(&reg, INT_MASK_CSR_TX_COHERENT, 0);
+	reg = 0;
+	if (state == STATE_RADIO_IRQ_ON) {
+		rt2x00_set_field32(&reg, INT_MASK_CSR_RX_DONE, 1);
+		rt2x00_set_field32(&reg, INT_MASK_CSR_TBTT, 1);
+		rt2x00_set_field32(&reg, INT_MASK_CSR_PRE_TBTT, 1);
+		rt2x00_set_field32(&reg, INT_MASK_CSR_TX_FIFO_STATUS, 1);
+		rt2x00_set_field32(&reg, INT_MASK_CSR_AUTO_WAKEUP, 1);
+	}
 	rt2x00pci_register_write(rt2x00dev, INT_MASK_CSR, reg);
 	spin_unlock_irqrestore(&rt2x00dev->irqmask_lock, flags);
 

@@ -196,6 +196,8 @@ static bool _rtl92s_firmware_downloadcode(struct ieee80211_hw *hw,
 		/* Allocate skb buffer to contain firmware */
 		/* info and tx descriptor info. */
 		skb = dev_alloc_skb(frag_length);
+		if (!skb)
+			return false;
 		skb_reserve(skb, extra_descoffset);
 		seg_ptr = (u8 *)skb_put(skb, (u32)(frag_length -
 					extra_descoffset));

@@ -573,6 +575,8 @@ static bool _rtl92s_firmware_set_h2c_cmd(struct ieee80211_hw *hw, u8 h2c_cmd,
 
 	len = _rtl92s_get_h2c_cmdlen(MAX_TRANSMIT_BUFFER_SIZE, 1, &cmd_len);
 	skb = dev_alloc_skb(len);
+	if (!skb)
+		return false;
 	cb_desc = (struct rtl_tcb_desc *)(skb->cb);
 	cb_desc->queue_index = TXCMD_QUEUE;
 	cb_desc->cmd_or_init = DESC_PACKET_TYPE_NORMAL;

@@ -870,5 +870,15 @@ EXPORT_SYMBOL(pci_msi_enabled);
 
 void pci_msi_init_pci_dev(struct pci_dev *dev)
 {
+	int pos;
 	INIT_LIST_HEAD(&dev->msi_list);
+
+	/* Disable the msi hardware to avoid screaming interrupts
+	 * during boot.  This is the power on reset default so
+	 * usually this should be a noop.
+	 */
+	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (pos)
+		msi_set_enable(dev, pos, 0);
+	msix_set_enable(dev, 0);
 }

@@ -295,6 +295,45 @@ static void quirk_system_pci_resources(struct pnp_dev *dev)
 	}
 }
 
+#ifdef CONFIG_AMD_NB
+
+#include <asm/amd_nb.h>
+
+static void quirk_amd_mmconfig_area(struct pnp_dev *dev)
+{
+	resource_size_t start, end;
+	struct pnp_resource *pnp_res;
+	struct resource *res;
+	struct resource mmconfig_res, *mmconfig;
+
+	mmconfig = amd_get_mmconfig_range(&mmconfig_res);
+	if (!mmconfig)
+		return;
+
+	list_for_each_entry(pnp_res, &dev->resources, list) {
+		res = &pnp_res->res;
+		if (res->end < mmconfig->start || res->start > mmconfig->end ||
+		    (res->start == mmconfig->start && res->end == mmconfig->end))
+			continue;
+
+		dev_info(&dev->dev, FW_BUG
+			 "%pR covers only part of AMD MMCONFIG area %pR; adding more reservations\n",
+			 res, mmconfig);
+		if (mmconfig->start < res->start) {
+			start = mmconfig->start;
+			end = res->start - 1;
+			pnp_add_mem_resource(dev, start, end, 0);
+		}
+		if (mmconfig->end > res->end) {
+			start = res->end + 1;
+			end = mmconfig->end;
+			pnp_add_mem_resource(dev, start, end, 0);
+		}
+		break;
+	}
+}
+#endif
+
 /*
  *  PnP Quirks
  *  Cards or devices that need some tweaking due to incomplete resource info

@@ -322,6 +361,9 @@ static struct pnp_fixup pnp_fixups[] = {
 	/* PnP resources that might overlap PCI BARs */
 	{"PNP0c01", quirk_system_pci_resources},
 	{"PNP0c02", quirk_system_pci_resources},
+#ifdef CONFIG_AMD_NB
+	{"PNP0c01", quirk_amd_mmconfig_area},
+#endif
 	{""}
 };
 

@@ -228,11 +228,11 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 		alarm->time.tm_hour = now.tm_hour;
 
 	/* For simplicity, only support date rollover for now */
-	if (alarm->time.tm_mday == -1) {
+	if (alarm->time.tm_mday < 1 || alarm->time.tm_mday > 31) {
 		alarm->time.tm_mday = now.tm_mday;
 		missing = day;
 	}
-	if (alarm->time.tm_mon == -1) {
+	if ((unsigned)alarm->time.tm_mon >= 12) {
 		alarm->time.tm_mon = now.tm_mon;
 		if (missing == none)
 			missing = month;

@@ -65,6 +65,8 @@ static MPT_CALLBACK	mpt_callbacks[MPT_MAX_CALLBACKS];
 
 #define FAULT_POLLING_INTERVAL 1000 /* in milliseconds */
 
+#define MAX_HBA_QUEUE_DEPTH	30000
+#define MAX_CHAIN_DEPTH		100000
 static int max_queue_depth = -1;
 module_param(max_queue_depth, int, 0);
 MODULE_PARM_DESC(max_queue_depth, " max controller queue depth ");

@@ -2311,8 +2313,6 @@ _base_release_memory_pools(struct MPT2SAS_ADAPTER *ioc)
 		}
 		if (ioc->chain_dma_pool)
 			pci_pool_destroy(ioc->chain_dma_pool);
-	}
-	if (ioc->chain_lookup) {
 		free_pages((ulong)ioc->chain_lookup, ioc->chain_pages);
 		ioc->chain_lookup = NULL;
 	}

@@ -2330,9 +2330,7 @@ static int
 _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc,  int sleep_flag)
 {
 	struct mpt2sas_facts *facts;
-	u32 queue_size, queue_diff;
 	u16 max_sge_elements;
-	u16 num_of_reply_frames;
 	u16 chains_needed_per_io;
 	u32 sz, total_sz, reply_post_free_sz;
 	u32 retry_sz;

@@ -2359,7 +2357,8 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc,  int sleep_flag)
 		max_request_credit = (max_queue_depth < facts->RequestCredit)
 		    ? max_queue_depth : facts->RequestCredit;
 	else
-		max_request_credit = facts->RequestCredit;
+		max_request_credit = min_t(u16, facts->RequestCredit,
+		    MAX_HBA_QUEUE_DEPTH);
 
 	ioc->hba_queue_depth = max_request_credit;
 	ioc->hi_priority_depth = facts->HighPriorityCredit;

@@ -2400,50 +2399,25 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc,  int sleep_flag)
 	}
 	ioc->chains_needed_per_io = chains_needed_per_io;
 
-	/* reply free queue sizing - taking into account for events */
-	num_of_reply_frames = ioc->hba_queue_depth + 32;
-
-	/* number of replies frames can't be a multiple of 16 */
-	/* decrease number of reply frames by 1 */
-	if (!(num_of_reply_frames % 16))
-		num_of_reply_frames--;
-
-	/* calculate number of reply free queue entries
-	 *  (must be multiple of 16)
-	 */
-
-	/* (we know reply_free_queue_depth is not a multiple of 16) */
-	queue_size = num_of_reply_frames;
-	queue_size += 16 - (queue_size % 16);
-	ioc->reply_free_queue_depth = queue_size;
-
-	/* reply descriptor post queue sizing */
-	/* this size should be the number of request frames + number of reply
-	 * frames
-	 */
-
-	queue_size = ioc->hba_queue_depth + num_of_reply_frames + 1;
-	/* round up to 16 byte boundary */
-	if (queue_size % 16)
-		queue_size += 16 - (queue_size % 16);
-
-	/* check against IOC maximum reply post queue depth */
-	if (queue_size > facts->MaxReplyDescriptorPostQueueDepth) {
-		queue_diff = queue_size -
-		    facts->MaxReplyDescriptorPostQueueDepth;
+	/* reply free queue sizing - taking into account for 64 FW events */
+	ioc->reply_free_queue_depth = ioc->hba_queue_depth + 64;
 
-		/* round queue_diff up to multiple of 16 */
-		if (queue_diff % 16)
-			queue_diff += 16 - (queue_diff % 16);
-
-		/* adjust hba_queue_depth, reply_free_queue_depth,
-		 * and queue_size
-		 */
-		ioc->hba_queue_depth -= (queue_diff / 2);
-		ioc->reply_free_queue_depth -= (queue_diff / 2);
-		queue_size = facts->MaxReplyDescriptorPostQueueDepth;
+	/* align the reply post queue on the next 16 count boundary */
+	if (!ioc->reply_free_queue_depth % 16)
+		ioc->reply_post_queue_depth = ioc->reply_free_queue_depth + 16;
+	else
+		ioc->reply_post_queue_depth = ioc->reply_free_queue_depth +
+				32 - (ioc->reply_free_queue_depth % 16);
+	if (ioc->reply_post_queue_depth >
+	    facts->MaxReplyDescriptorPostQueueDepth) {
+		ioc->reply_post_queue_depth = min_t(u16,
+		    (facts->MaxReplyDescriptorPostQueueDepth -
+		    (facts->MaxReplyDescriptorPostQueueDepth % 16)),
+		    (ioc->hba_queue_depth - (ioc->hba_queue_depth % 16)));
+		ioc->reply_free_queue_depth = ioc->reply_post_queue_depth - 16;
+		ioc->hba_queue_depth = ioc->reply_free_queue_depth - 64;
 	}
-	ioc->reply_post_queue_depth = queue_size;
+
 
 	dinitprintk(ioc, printk(MPT2SAS_INFO_FMT "scatter gather: "
 	    "sge_in_main_msg(%d), sge_per_chain(%d), sge_per_io(%d), "

@@ -2529,15 +2503,12 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc,  int sleep_flag)
 	    "depth(%d)\n", ioc->name, ioc->request,
 	    ioc->scsiio_depth));
 
-	/* loop till the allocation succeeds */
-	do {
-		sz = ioc->chain_depth * sizeof(struct chain_tracker);
-		ioc->chain_pages = get_order(sz);
-		ioc->chain_lookup = (struct chain_tracker *)__get_free_pages(
-		    GFP_KERNEL, ioc->chain_pages);
-		if (ioc->chain_lookup == NULL)
-			ioc->chain_depth -= 100;
-	} while (ioc->chain_lookup == NULL);
+	ioc->chain_depth = min_t(u32, ioc->chain_depth, MAX_CHAIN_DEPTH);
+	sz = ioc->chain_depth * sizeof(struct chain_tracker);
+	ioc->chain_pages = get_order(sz);
+
+	ioc->chain_lookup = (struct chain_tracker *)__get_free_pages(
+	    GFP_KERNEL, ioc->chain_pages);
 	ioc->chain_dma_pool = pci_pool_create("chain pool", ioc->pdev,
 	    ioc->request_sz, 16, 0);
 	if (!ioc->chain_dma_pool) {

@@ -1007,8 +1007,8 @@ _scsih_get_chain_buffer_tracker(struct MPT2SAS_ADAPTER *ioc, u16 smid)
 	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
 	if (list_empty(&ioc->free_chain_list)) {
 		spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
-		printk(MPT2SAS_WARN_FMT "chain buffers not available\n",
-		    ioc->name);
+		dfailprintk(ioc, printk(MPT2SAS_WARN_FMT "chain buffers not "
+			"available\n", ioc->name));
 		return NULL;
 	}
 	chain_req = list_entry(ioc->free_chain_list.next,

@@ -6714,6 +6714,7 @@ _scsih_mark_responding_raid_device(struct MPT2SAS_ADAPTER *ioc, u64 wwid,
 			} else
 				sas_target_priv_data = NULL;
 			raid_device->responding = 1;
+			spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
 			starget_printk(KERN_INFO, raid_device->starget,
 			    "handle(0x%04x), wwid(0x%016llx)\n", handle,
 			    (unsigned long long)raid_device->wwid);

@@ -6724,16 +6725,16 @@ _scsih_mark_responding_raid_device(struct MPT2SAS_ADAPTER *ioc, u64 wwid,
 			 */
 			_scsih_init_warpdrive_properties(ioc, raid_device);
 			if (raid_device->handle == handle)
-				goto out;
+				return;
 			printk(KERN_INFO "\thandle changed from(0x%04x)!!!\n",
 			    raid_device->handle);
 			raid_device->handle = handle;
 			if (sas_target_priv_data)
 				sas_target_priv_data->handle = handle;
-			goto out;
+			return;
 		}
 	}
- out:
+
 	spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
 }
 

@@ -1074,6 +1074,10 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode,
 	SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, "
 				    "cmd=0x%x\n", disk->disk_name, cmd));
 
+	error = scsi_verify_blk_ioctl(bdev, cmd);
+	if (error < 0)
+		return error;
+
 	/*
 	 * If we are in the middle of error recovery, don't let anyone
 	 * else try and use this device.  Also, if error recovery fails, it

@@ -1096,7 +1100,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode,
 			error = scsi_ioctl(sdp, cmd, p);
 			break;
 		default:
-			error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p);
+			error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p);
 			if (error != -ENOTTY)
 				break;
 			error = scsi_ioctl(sdp, cmd, p);

@@ -1266,6 +1270,11 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
 	struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device;
+	int ret;
+
+	ret = scsi_verify_blk_ioctl(bdev, cmd);
+	if (ret < 0)
+		return -ENOIOCTLCMD;
 
 	/*
 	 * If we are in the middle of error recovery, don't let anyone

@@ -1277,8 +1286,6 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
 		return -ENODEV;
 	       
 	if (sdev->host->hostt->compat_ioctl) {
-		int ret;
-
 		ret = sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg);
 
 		return ret;

@@ -839,6 +839,10 @@ static void sym53c8xx_slave_destroy(struct scsi_device *sdev)
 	struct sym_lcb *lp = sym_lp(tp, sdev->lun);
 	unsigned long flags;
 
+	/* if slave_alloc returned before allocating a sym_lcb, return */
+	if (!lp)
+		return;
+
 	spin_lock_irqsave(np->s.host->host_lock, flags);
 
 	if (lp->busy_itlq || lp->busy_itl) {

@@ -94,6 +94,18 @@ target_emulate_inquiry_std(struct se_cmd *cmd)
 	buf[2] = dev->transport->get_device_rev(dev);
 
 	/*
+	 * NORMACA and HISUP = 0, RESPONSE DATA FORMAT = 2
+	 *
+	 * SPC4 says:
+	 *   A RESPONSE DATA FORMAT field set to 2h indicates that the
+	 *   standard INQUIRY data is in the format defined in this
+	 *   standard. Response data format values less than 2h are
+	 *   obsolete. Response data format values greater than 2h are
+	 *   reserved.
+	 */
+	buf[3] = 2;
+
+	/*
 	 * Enable SCCS and TPGS fields for Emulated ALUA
 	 */
 	if (dev->se_sub_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED)

@@ -4353,6 +4353,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_NON_EXISTENT_LUN:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ILLEGAL REQUEST */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
 		/* LOGICAL UNIT NOT SUPPORTED */

@@ -4362,6 +4363,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_SECTOR_COUNT_TOO_MANY:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ILLEGAL REQUEST */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
 		/* INVALID COMMAND OPERATION CODE */

@@ -4370,6 +4372,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_UNKNOWN_MODE_PAGE:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ILLEGAL REQUEST */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
 		/* INVALID FIELD IN CDB */

@@ -4378,6 +4381,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_CHECK_CONDITION_ABORT_CMD:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* BUS DEVICE RESET FUNCTION OCCURRED */

@@ -4387,6 +4391,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_INCORRECT_AMOUNT_OF_DATA:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* WRITE ERROR */

@@ -4397,6 +4402,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_INVALID_CDB_FIELD:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* INVALID FIELD IN CDB */

@@ -4405,6 +4411,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_INVALID_PARAMETER_LIST:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* INVALID FIELD IN PARAMETER LIST */

@@ -4413,6 +4420,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_UNEXPECTED_UNSOLICITED_DATA:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* WRITE ERROR */

@@ -4423,6 +4431,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_SERVICE_CRC_ERROR:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* PROTOCOL SERVICE CRC ERROR */

@@ -4433,6 +4442,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_SNACK_REJECTED:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ABORTED COMMAND */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ABORTED_COMMAND;
 		/* READ ERROR */

@@ -4443,6 +4453,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_WRITE_PROTECTED:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* DATA PROTECT */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = DATA_PROTECT;
 		/* WRITE PROTECTED */

@@ -4451,6 +4462,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_CHECK_CONDITION_UNIT_ATTENTION:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* UNIT ATTENTION */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = UNIT_ATTENTION;
 		core_scsi3_ua_for_check_condition(cmd, &asc, &ascq);

@@ -4460,6 +4472,7 @@ int transport_send_check_condition_and_sense(
 	case TCM_CHECK_CONDITION_NOT_READY:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* Not Ready */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = NOT_READY;
 		transport_get_sense_codes(cmd, &asc, &ascq);

@@ -4470,6 +4483,7 @@ int transport_send_check_condition_and_sense(
 	default:
 		/* CURRENT ERROR */
 		buffer[offset] = 0x70;
+		buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10;
 		/* ILLEGAL REQUEST */
 		buffer[offset+SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST;
 		/* LOGICAL UNIT COMMUNICATION FAILURE */

@@ -801,6 +801,12 @@ static int process_msg(void)
 		goto out;
 	}
 
+	if (msg->hdr.len > XENSTORE_PAYLOAD_MAX) {
+		kfree(msg);
+		err = -EINVAL;
+		goto out;
+	}
+
 	body = kmalloc(msg->hdr.len + 1, GFP_NOIO | __GFP_HIGH);
 	if (body == NULL) {
 		kfree(msg);

@@ -476,14 +476,21 @@ static void kiocb_batch_init(struct kiocb_batch *batch, long total)
 	batch->count = total;
 }
 
-static void kiocb_batch_free(struct kiocb_batch *batch)
+static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
 {
 	struct kiocb *req, *n;
 
+	if (list_empty(&batch->head))
+		return;
+
+	spin_lock_irq(&ctx->ctx_lock);
 	list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
 		list_del(&req->ki_batch);
+		list_del(&req->ki_list);
 		kmem_cache_free(kiocb_cachep, req);
+		ctx->reqs_active--;
 	}
+	spin_unlock_irq(&ctx->ctx_lock);
 }
 
 /*

@@ -1742,7 +1749,7 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 	}
 	blk_finish_plug(&plug);
 
-	kiocb_batch_free(&batch);
+	kiocb_batch_free(ctx, &batch);
 	put_ioctx(ctx);
 	return i ? i : ret;
 }

@@ -2914,18 +2914,33 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 #define CIFS_DEFAULT_IOSIZE (1024 * 1024)
 
 /*
- * Windows only supports a max of 60k reads. Default to that when posix
- * extensions aren't in force.
+ * Windows only supports a max of 60kb reads and 65535 byte writes. Default to
+ * those values when posix extensions aren't in force. In actuality here, we
+ * use 65536 to allow for a write that is a multiple of 4k. Most servers seem
+ * to be ok with the extra byte even though Windows doesn't send writes that
+ * are that large.
+ *
+ * Citation:
+ *
+ * http://blogs.msdn.com/b/openspecification/archive/2009/04/10/smb-maximum-transmit-buffer-size-and-performance-tuning.aspx
  */
 #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024)
+#define CIFS_DEFAULT_NON_POSIX_WSIZE (65536)
 
 static unsigned int
 cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info)
 {
 	__u64 unix_cap = le64_to_cpu(tcon->fsUnixInfo.Capability);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	unsigned int wsize = pvolume_info->wsize ? pvolume_info->wsize :
-				CIFS_DEFAULT_IOSIZE;
+	unsigned int wsize;
+
+	/* start with specified wsize, or default */
+	if (pvolume_info->wsize)
+		wsize = pvolume_info->wsize;
+	else if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_WRITE_CAP))
+		wsize = CIFS_DEFAULT_IOSIZE;
+	else
+		wsize = CIFS_DEFAULT_NON_POSIX_WSIZE;
 
 	/* can server support 24-bit write sizes? (via UNIX extensions) */
 	if (!tcon->unix_ext || !(unix_cap & CIFS_UNIX_LARGE_WRITE_CAP))

@@ -242,6 +242,7 @@ static void dentry_lru_add(struct dentry *dentry)
 static void __dentry_lru_del(struct dentry *dentry)
 {
 	list_del_init(&dentry->d_lru);
+	dentry->d_flags &= ~DCACHE_SHRINK_LIST;
 	dentry->d_sb->s_nr_dentry_unused--;
 	dentry_stat.nr_unused--;
 }

@@ -275,15 +276,15 @@ static void dentry_lru_prune(struct dentry *dentry)
 	}
 }
 
-static void dentry_lru_move_tail(struct dentry *dentry)
+static void dentry_lru_move_list(struct dentry *dentry, struct list_head *list)
 {
 	spin_lock(&dcache_lru_lock);
 	if (list_empty(&dentry->d_lru)) {
-		list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+		list_add_tail(&dentry->d_lru, list);
 		dentry->d_sb->s_nr_dentry_unused++;
 		dentry_stat.nr_unused++;
 	} else {
-		list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+		list_move_tail(&dentry->d_lru, list);
 	}
 	spin_unlock(&dcache_lru_lock);
 }

@@ -769,14 +770,18 @@ static void shrink_dentry_list(struct list_head *list)
 }
 
 /**
- * __shrink_dcache_sb - shrink the dentry LRU on a given superblock
- * @sb:		superblock to shrink dentry LRU.
- * @count:	number of entries to prune
- * @flags:	flags to control the dentry processing
+ * prune_dcache_sb - shrink the dcache
+ * @sb: superblock
+ * @count: number of entries to try to free
+ *
+ * Attempt to shrink the superblock dcache LRU by @count entries. This is
+ * done when we need more memory an called from the superblock shrinker
+ * function.
  *
- * If flags contains DCACHE_REFERENCED reference dentries will not be pruned.
+ * This function may fail to free any resources if all the dentries are in
+ * use.
  */
-static void __shrink_dcache_sb(struct super_block *sb, int count, int flags)
+void prune_dcache_sb(struct super_block *sb, int count)
 {
 	struct dentry *dentry;
 	LIST_HEAD(referenced);

@@ -795,18 +800,13 @@ relock:
 			goto relock;
 		}
 
-		/*
-		 * If we are honouring the DCACHE_REFERENCED flag and the
-		 * dentry has this flag set, don't free it.  Clear the flag
-		 * and put it back on the LRU.
-		 */
-		if (flags & DCACHE_REFERENCED &&
-				dentry->d_flags & DCACHE_REFERENCED) {
+		if (dentry->d_flags & DCACHE_REFERENCED) {
 			dentry->d_flags &= ~DCACHE_REFERENCED;
 			list_move(&dentry->d_lru, &referenced);
 			spin_unlock(&dentry->d_lock);
 		} else {
 			list_move_tail(&dentry->d_lru, &tmp);
+			dentry->d_flags |= DCACHE_SHRINK_LIST;
 			spin_unlock(&dentry->d_lock);
 			if (!--count)
 				break;

@@ -821,23 +821,6 @@ relock:
 }
 
 /**
- * prune_dcache_sb - shrink the dcache
- * @sb: superblock
- * @nr_to_scan: number of entries to try to free
- *
- * Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
- * done when we need more memory an called from the superblock shrinker
- * function.
- *
- * This function may fail to free any resources if all the dentries are in
- * use.
- */
-void prune_dcache_sb(struct super_block *sb, int nr_to_scan)
-{
-	__shrink_dcache_sb(sb, nr_to_scan, DCACHE_REFERENCED);
-}
-
-/**
  * shrink_dcache_sb - shrink dcache for a superblock
  * @sb: superblock
  *

@@ -1091,7 +1074,7 @@ EXPORT_SYMBOL(have_submounts);
  * drop the lock and return early due to latency
  * constraints.
  */
-static int select_parent(struct dentry * parent)
+static int select_parent(struct dentry *parent, struct list_head *dispose)
 {
 	struct dentry *this_parent;
 	struct list_head *next;

@@ -1113,17 +1096,21 @@ resume:
 
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 
-		/* 
-		 * move only zero ref count dentries to the end 
-		 * of the unused list for prune_dcache
+		/*
+		 * move only zero ref count dentries to the dispose list.
+		 *
+		 * Those which are presently on the shrink list, being processed
+		 * by shrink_dentry_list(), shouldn't be moved.  Otherwise the
+		 * loop in shrink_dcache_parent() might not make any progress
+		 * and loop forever.
 		 */
-		if (!dentry->d_count) {
-			dentry_lru_move_tail(dentry);
-			found++;
-		} else {
+		if (dentry->d_count) {
 			dentry_lru_del(dentry);
+		} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
+			dentry_lru_move_list(dentry, dispose);
+			dentry->d_flags |= DCACHE_SHRINK_LIST;
+			found++;
 		}
-
 		/*
 		 * We can return to the caller if we have found some (this
 		 * ensures forward progress). We'll be coming back to find

@@ -1180,14 +1167,13 @@ rename_retry:
  *
  * Prune the dcache to remove unused children of the parent dentry.
  */
- 
 void shrink_dcache_parent(struct dentry * parent)
 {
-	struct super_block *sb = parent->d_sb;
+	LIST_HEAD(dispose);
 	int found;
 
-	while ((found = select_parent(parent)) != 0)
-		__shrink_dcache_sb(sb, found, 0);
+	while ((found = select_parent(parent, &dispose)) != 0)
+		shrink_dentry_list(&dispose);
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 

@@ -182,19 +182,22 @@ setversion_out:
 		if (err)
 			return err;
 
-		if (get_user(n_blocks_count, (__u32 __user *)arg))
-			return -EFAULT;
+		if (get_user(n_blocks_count, (__u32 __user *)arg)) {
+			err = -EFAULT;
+			goto group_extend_out;
+		}
 
 		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 			ext4_msg(sb, KERN_ERR,
 				 "Online resizing not supported with bigalloc");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto group_extend_out;
 		}
 
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
-			return err;
+			goto group_extend_out;
 
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {

@@ -204,9 +207,10 @@ setversion_out:
 		}
 		if (err == 0)
 			err = err2;
+
 		mnt_drop_write(filp->f_path.mnt);
+group_extend_out:
 		ext4_resize_end(sb);
-
 		return err;
 	}
 

@@ -267,19 +271,22 @@ mext_out:
 			return err;
 
 		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
-				sizeof(input)))
-			return -EFAULT;
+				sizeof(input))) {
+			err = -EFAULT;
+			goto group_add_out;
+		}
 
 		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 			ext4_msg(sb, KERN_ERR,
 				 "Online resizing not supported with bigalloc");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto group_add_out;
 		}
 
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
-			return err;
+			goto group_add_out;
 
 		err = ext4_group_add(sb, &input);
 		if (EXT4_SB(sb)->s_journal) {

@@ -289,9 +296,10 @@ mext_out:
 		}
 		if (err == 0)
 			err = err2;
+
 		mnt_drop_write(filp->f_path.mnt);
+group_add_out:
 		ext4_resize_end(sb);
-
 		return err;
 	}
 

@@ -2006,17 +2006,16 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	struct ext4_group_desc *gdp = NULL;
 	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
-	int groups_per_flex = 0;
+	unsigned int groups_per_flex = 0;
 	size_t size;
 	int i;
 
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
-	if (groups_per_flex < 2) {
+	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +

@@ -146,14 +146,19 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
 {
 	struct bio *bio;
 
+	npg = min(npg, BIO_MAX_PAGES);
 	bio = bio_alloc(GFP_NOIO, npg);
-	if (!bio)
-		return NULL;
+	if (!bio && (current->flags & PF_MEMALLOC)) {
+		while (!bio && (npg /= 2))
+			bio = bio_alloc(GFP_NOIO, npg);
+	}
 
-	bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
-	bio->bi_bdev = be->be_mdev;
-	bio->bi_end_io = end_io;
-	bio->bi_private = par;
+	if (bio) {
+		bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+		bio->bi_bdev = be->be_mdev;
+		bio->bi_end_io = end_io;
+		bio->bi_private = par;
+	}
 	return bio;
 }
 

@@ -779,16 +784,13 @@ bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata)
 static void free_blk_mountid(struct block_mount_id *mid)
 {
 	if (mid) {
-		struct pnfs_block_dev *dev;
-		spin_lock(&mid->bm_lock);
-		while (!list_empty(&mid->bm_devlist)) {
-			dev = list_first_entry(&mid->bm_devlist,
-					       struct pnfs_block_dev,
-					       bm_node);
+		struct pnfs_block_dev *dev, *tmp;
+
+		/* No need to take bm_lock as we are last user freeing bm_devlist */
+		list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) {
 			list_del(&dev->bm_node);
 			bl_free_block_dev(dev);
 		}
-		spin_unlock(&mid->bm_lock);
 		kfree(mid);
 	}
 }

@@ -139,11 +139,13 @@ static int _set_range(struct my_tree *tree, int32_t tag, u64 s, u64 length)
 }
 
 /* Ensure that future operations on given range of tree will not malloc */
-static int _preload_range(struct my_tree *tree, u64 offset, u64 length)
+static int _preload_range(struct pnfs_inval_markings *marks,
+		u64 offset, u64 length)
 {
 	u64 start, end, s;
 	int count, i, used = 0, status = -ENOMEM;
 	struct pnfs_inval_tracking **storage;
+	struct my_tree  *tree = &marks->im_tree;
 
 	dprintk("%s(%llu, %llu) enter\n", __func__, offset, length);
 	start = normalize(offset, tree->mtt_step_size);

@@ -161,12 +163,11 @@ static int _preload_range(struct my_tree *tree, u64 offset, u64 length)
 			goto out_cleanup;
 	}
 
-	/* Now need lock - HOW??? */
-
+	spin_lock(&marks->im_lock);
 	for (s = start; s < end; s += tree->mtt_step_size)
 		used += _add_entry(tree, s, INTERNAL_EXISTS, storage[used]);
+	spin_unlock(&marks->im_lock);
 
-	/* Unlock - HOW??? */
 	status = 0;
 
  out_cleanup:

@@ -286,7 +287,7 @@ int bl_mark_sectors_init(struct pnfs_inval_markings *marks,
 
 	start = normalize(offset, marks->im_block_size);
 	end = normalize_up(offset + length, marks->im_block_size);
-	if (_preload_range(&marks->im_tree, start, end - start))
+	if (_preload_range(marks, start, end - start))
 		goto outerr;
 
 	spin_lock(&marks->im_lock);

@@ -339,7 +339,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
 	dprintk("%s enter. slotid %d seqid %d\n",
 		__func__, args->csa_slotid, args->csa_sequenceid);
 
-	if (args->csa_slotid > NFS41_BC_MAX_CALLBACKS)
+	if (args->csa_slotid >= NFS41_BC_MAX_CALLBACKS)
 		return htonl(NFS4ERR_BADSLOT);
 
 	slot = tbl->slots + args->csa_slotid;

@@ -272,13 +272,13 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			datasync);
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
-		return ret;
 	mutex_lock(&inode->i_mutex);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
+	if (status >= 0 && ret < 0)
+		status = ret;
 	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	if (have_error)
 		ret = xchg(&ctx->error, 0);

@@ -3430,19 +3430,6 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
  */
 #define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
 
-static void buf_to_pages(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
-{
-	const void *p = buf;
-
-	*pgbase = offset_in_page(buf);
-	p -= *pgbase;
-	while (p < buf + buflen) {
-		*(pages++) = virt_to_page(p);
-		p += PAGE_CACHE_SIZE;
-	}
-}
-
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
 {

@@ -3539,9 +3526,19 @@ out:
 	nfs4_set_cached_acl(inode, acl);
 }
 
+/*
+ * The getxattr API returns the required buffer length when called with a
+ * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating
+ * the required buf.  On a NULL buf, we send a page of data to the server
+ * guessing that the ACL request can be serviced by a page. If so, we cache
+ * up to the page of ACL data, and the 2nd call to getxattr is serviced by
+ * the cache. If not so, we throw away the page, and cache the required
+ * length. The next getxattr call will then produce another round trip to
+ * the server, this time with the input buf of the required size.
+ */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES];
+	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,

@@ -3556,41 +3553,60 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct page *localpage = NULL;
-	int ret;
+	int ret = -ENOMEM, npages, i, acl_len = 0;
 
-	if (buflen < PAGE_SIZE) {
-		/* As long as we're doing a round trip to the server anyway,
-		 * let's be prepared for a page of acl data. */
-		localpage = alloc_page(GFP_KERNEL);
-		resp_buf = page_address(localpage);
-		if (localpage == NULL)
-			return -ENOMEM;
-		args.acl_pages[0] = localpage;
-		args.acl_pgbase = 0;
-		args.acl_len = PAGE_SIZE;
-	} else {
-		resp_buf = buf;
-		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
+	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	/* As long as we're doing a round trip to the server anyway,
+	 * let's be prepared for a page of acl data. */
+	if (npages == 0)
+		npages = 1;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free;
+	}
+	if (npages > 1) {
+		/* for decoding across pages */
+		args.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!args.acl_scratch)
+			goto out_free;
 	}
-	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0);
+	args.acl_len = npages * PAGE_SIZE;
+	args.acl_pgbase = 0;
+	/* Let decode_getfacl know not to fail if the ACL data is larger than
+	 * the page we send as a guess */
+	if (buf == NULL)
+		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
+	resp_buf = page_address(pages[0]);
+
+	dprintk("%s  buf %p buflen %ld npages %d args.acl_len %ld\n",
+		__func__, buf, buflen, npages, args.acl_len);
+	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
+			     &msg, &args.seq_args, &res.seq_res, 0);
 	if (ret)
 		goto out_free;
-	if (res.acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, res.acl_len);
+
+	acl_len = res.acl_len - res.acl_data_offset;
+	if (acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
+		nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+				      acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (res.acl_len > buflen)
+		if (acl_len > buflen)
 			goto out_free;
-		if (localpage)
-			memcpy(buf, resp_buf, res.acl_len);
+		_copy_from_pages(buf, pages, res.acl_data_offset,
+				res.acl_len);
 	}
-	ret = res.acl_len;
+	ret = acl_len;
 out_free:
-	if (localpage)
-		__free_page(localpage);
+	for (i = 0; i < npages; i++)
+		if (pages[i])
+			__free_page(pages[i]);
+	if (args.acl_scratch)
+		__free_page(args.acl_scratch);
 	return ret;
 }
 

@@ -3621,6 +3637,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
+		/* -ENOENT is returned if there is no ACL or if there is an ACL
+		 * but no cached acl data, just the acl length */
 		return ret;
 	return nfs4_get_acl_uncached(inode, buf, buflen);
 }

@@ -2517,11 +2517,13 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz + 1;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
 		args->acl_pages, args->acl_pgbase, args->acl_len);
+	xdr_set_scratch_buffer(xdr, page_address(args->acl_scratch), PAGE_SIZE);
+
 	encode_nops(&hdr);
 }
 

@@ -4957,17 +4959,18 @@ decode_restorefh(struct xdr_stream *xdr)
 }
 
 static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
-		size_t *acl_len)
+			 struct nfs_getaclres *res)
 {
-	__be32 *savep;
+	__be32 *savep, *bm_p;
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	struct kvec *iov = req->rq_rcv_buf.head;
 	int status;
 
-	*acl_len = 0;
+	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
 		goto out;
+	bm_p = xdr->p;
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)

@@ -4979,18 +4982,30 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		size_t hdrlen;
 		u32 recvd;
 
+		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
+		 * are stored with the acl data to handle the problem of
+		 * variable length bitmaps.*/
+		xdr->p = bm_p;
+		res->acl_data_offset = be32_to_cpup(bm_p) + 2;
+		res->acl_data_offset <<= 2;
+
 		/* We ignore &savep and don't do consistency checks on
 		 * the attr length.  Let userspace figure it out.... */
 		hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
+		attrlen += res->acl_data_offset;
 		recvd = req->rq_rcv_buf.len - hdrlen;
 		if (attrlen > recvd) {
-			dprintk("NFS: server cheating in getattr"
-					" acl reply: attrlen %u > recvd %u\n",
+			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
+				/* getxattr interface called with a NULL buf */
+				res->acl_len = attrlen;
+				goto out;
+			}
+			dprintk("NFS: acl reply: attrlen %u > recvd %u\n",
 					attrlen, recvd);
 			return -EINVAL;
 		}
 		xdr_read_pages(xdr, attrlen);
-		*acl_len = attrlen;
+		res->acl_len = attrlen;
 	} else
 		status = -EOPNOTSUPP;
 

@@ -6028,7 +6043,7 @@ nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_getacl(xdr, rqstp, &res->acl_len);
+	status = decode_getacl(xdr, rqstp, res);
 
 out:
 	return status;

@@ -551,7 +551,8 @@ static const struct nfs_pageio_ops objio_pg_write_ops = {
 static struct pnfs_layoutdriver_type objlayout_type = {
 	.id = LAYOUT_OSD2_OBJECTS,
 	.name = "LAYOUT_OSD2_OBJECTS",
-	.flags                   = PNFS_LAYOUTRET_ON_SETATTR,
+	.flags                   = PNFS_LAYOUTRET_ON_SETATTR |
+				   PNFS_LAYOUTRET_ON_ERROR,
 
 	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
 	.free_layout_hdr         = objlayout_free_layout_hdr,

@@ -254,6 +254,8 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	oir->status = rdata->task.tk_status = status;
 	if (status >= 0)
 		rdata->res.count = status;
+	else
+		rdata->pnfs_error = status;
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
 

@@ -334,6 +336,8 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	if (status >= 0) {
 		wdata->res.count = status;
 		wdata->verf.committed = oir->committed;
+	} else {
+		wdata->pnfs_error = status;
 	}
 	objlayout_iodone(oir);
 	/* must not use oir after this point */

@@ -1178,6 +1178,15 @@ void pnfs_ld_write_done(struct nfs_write_data *data)
 		put_lseg(data->lseg);
 		data->lseg = NULL;
 		dprintk("pnfs write error = %d\n", data->pnfs_error);
+		if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+						PNFS_LAYOUTRET_ON_ERROR) {
+			/* Don't lo_commit on error, Server will needs to
+			 * preform a file recovery.
+			 */
+			clear_bit(NFS_INO_LAYOUTCOMMIT,
+				  &NFS_I(data->inode)->flags);
+			pnfs_return_layout(data->inode);
+		}
 	}
 	data->mds_ops->rpc_release(data);
 }

@@ -1267,6 +1276,9 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 	put_lseg(data->lseg);
 	data->lseg = NULL;
 	dprintk("pnfs write error = %d\n", data->pnfs_error);
+	if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
+						PNFS_LAYOUTRET_ON_ERROR)
+		pnfs_return_layout(data->inode);
 
 	nfs_pageio_init_read_mds(&pgio, data->inode);
 

@@ -68,6 +68,7 @@ enum {
 enum layoutdriver_policy_flags {
 	/* Should the pNFS client commit and return the layout upon a setattr */
 	PNFS_LAYOUTRET_ON_SETATTR	= 1 << 0,
+	PNFS_LAYOUTRET_ON_ERROR		= 1 << 1,
 };
 
 struct nfs4_deviceid_node;

@@ -909,10 +909,24 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
 		data->auth_flavor_len	= 1;
 		data->version		= version;
 		data->minorversion	= 0;
+		security_init_mnt_opts(&data->lsm_opts);
 	}
 	return data;
 }
 
+static void nfs_free_parsed_mount_data(struct nfs_parsed_mount_data *data)
+{
+	if (data) {
+		kfree(data->client_address);
+		kfree(data->mount_server.hostname);
+		kfree(data->nfs_server.export_path);
+		kfree(data->nfs_server.hostname);
+		kfree(data->fscache_uniq);
+		security_free_mnt_opts(&data->lsm_opts);
+		kfree(data);
+	}
+}
+
 /*
  * Sanity-check a server address provided by the mount command.
  *

@@ -2220,9 +2234,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);

@@ -2234,8 +2246,6 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 #ifdef CONFIG_NFS_V4
 	if (data->version == 4) {
 		mntroot = nfs4_try_mount(flags, dev_name, data);
-		kfree(data->client_address);
-		kfree(data->nfs_server.export_path);
 		goto out;
 	}
 #endif	/* CONFIG_NFS_V4 */

@@ -2290,13 +2300,8 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 	s->s_flags |= MS_ACTIVE;
 
 out:
-	kfree(data->nfs_server.hostname);
-	kfree(data->mount_server.hostname);
-	kfree(data->fscache_uniq);
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
+	nfs_free_parsed_mount_data(data);
 	nfs_free_fhandle(mntfh);
-	kfree(data);
 	return mntroot;
 
 out_err_nosb:

@@ -2623,9 +2628,7 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	mntfh = nfs_alloc_fhandle();
 	if (data == NULL || mntfh == NULL)
-		goto out_free_fh;
-
-	security_init_mnt_opts(&data->lsm_opts);
+		goto out;
 
 	/* Get a volume representation */
 	server = nfs4_create_server(data, mntfh);

@@ -2677,13 +2680,10 @@ nfs4_remote_mount(struct file_system_type *fs_type, int flags,
 
 	s->s_flags |= MS_ACTIVE;
 
-	security_free_mnt_opts(&data->lsm_opts);
 	nfs_free_fhandle(mntfh);
 	return mntroot;
 
 out:
-	security_free_mnt_opts(&data->lsm_opts);
-out_free_fh:
 	nfs_free_fhandle(mntfh);
 	return ERR_PTR(error);
 

@@ -2838,7 +2838,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 
 	data = nfs_alloc_parsed_mount_data(4);
 	if (data == NULL)
-		goto out_free_data;
+		goto out;
 
 	/* Validate the mount data */
 	error = nfs4_validate_mount_data(raw_data, data, dev_name);

@@ -2852,12 +2852,7 @@ static struct dentry *nfs4_mount(struct file_system_type *fs_type,
 		error = PTR_ERR(res);
 
 out:
-	kfree(data->client_address);
-	kfree(data->nfs_server.export_path);
-	kfree(data->nfs_server.hostname);
-	kfree(data->fscache_uniq);
-out_free_data:
-	kfree(data);
+	nfs_free_parsed_mount_data(data);
 	dprintk("<-- nfs4_mount() = %d%s\n", error,
 			error != 0 ? " [error]" : "");
 	return res;

@@ -87,7 +87,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 	struct svc_expkey key;
 	struct svc_expkey *ek = NULL;
 
-	if (mesg[mlen-1] != '\n')
+	if (mlen < 1 || mesg[mlen-1] != '\n')
 		return -EINVAL;
 	mesg[mlen-1] = 0;
 

@@ -3809,16 +3809,29 @@ nevermind:
 		deny->ld_type = NFS4_WRITE_LT;
 }
 
+static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, clientid_t *clid, struct xdr_netobj *owner)
+{
+	struct nfs4_ol_stateid *lst;
+
+	if (!same_owner_str(&lo->lo_owner, owner, clid))
+		return false;
+	lst = list_first_entry(&lo->lo_owner.so_stateids,
+			       struct nfs4_ol_stateid, st_perstateowner);
+	return lst->st_file->fi_inode == inode;
+}
+
 static struct nfs4_lockowner *
 find_lockowner_str(struct inode *inode, clientid_t *clid,
 		struct xdr_netobj *owner)
 {
 	unsigned int hashval = lock_ownerstr_hashval(inode, clid->cl_id, owner);
+	struct nfs4_lockowner *lo;
 	struct nfs4_stateowner *op;
 
 	list_for_each_entry(op, &lock_ownerstr_hashtbl[hashval], so_strhash) {
-		if (same_owner_str(op, owner, clid))
-			return lockowner(op);
+		lo = lockowner(op);
+		if (same_lockowner_ino(lo, inode, clid, owner))
+			return lo;
 	}
 	return NULL;
 }

@@ -135,9 +135,6 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 
-	/* 1 from caller and 1 for being on i_list/g_list */
-	BUG_ON(atomic_read(&mark->refcnt) < 2);
-
 	spin_lock(&group->mark_lock);
 
 	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {

@@ -182,6 +179,11 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 		iput(inode);
 
 	/*
+	 * We don't necessarily have a ref on mark from caller so the above iput
+	 * may have already destroyed it.  Don't touch from now on.
+	 */
+
+	/*
 	 * it's possible that this group tried to destroy itself, but this
 	 * this mark was simultaneously being freed by inode.  If that's the
 	 * case, we finish freeing the group here.

@@ -194,65 +194,7 @@ static int proc_root_link(struct inode *inode, struct path *path)
 	return result;
 }
 
-static struct mm_struct *__check_mem_permission(struct task_struct *task)
-{
-	struct mm_struct *mm;
-
-	mm = get_task_mm(task);
-	if (!mm)
-		return ERR_PTR(-EINVAL);
-
-	/*
-	 * A task can always look at itself, in case it chooses
-	 * to use system calls instead of load instructions.
-	 */
-	if (task == current)
-		return mm;
-
-	/*
-	 * If current is actively ptrace'ing, and would also be
-	 * permitted to freshly attach with ptrace now, permit it.
-	 */
-	if (task_is_stopped_or_traced(task)) {
-		int match;
-		rcu_read_lock();
-		match = (ptrace_parent(task) == current);
-		rcu_read_unlock();
-		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
-			return mm;
-	}
-
-	/*
-	 * No one else is allowed.
-	 */
-	mmput(mm);
-	return ERR_PTR(-EPERM);
-}
-
-/*
- * If current may access user memory in @task return a reference to the
- * corresponding mm, otherwise ERR_PTR.
- */
-static struct mm_struct *check_mem_permission(struct task_struct *task)
-{
-	struct mm_struct *mm;
-	int err;
-
-	/*
-	 * Avoid racing if task exec's as we might get a new mm but validate
-	 * against old credentials.
-	 */
-	err = mutex_lock_killable(&task->signal->cred_guard_mutex);
-	if (err)
-		return ERR_PTR(err);
-
-	mm = __check_mem_permission(task);
-	mutex_unlock(&task->signal->cred_guard_mutex);
-
-	return mm;
-}
-
-struct mm_struct *mm_for_maps(struct task_struct *task)
+static struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 {
 	struct mm_struct *mm;
 	int err;

@@ -263,7 +205,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 
 	mm = get_task_mm(task);
 	if (mm && mm != current->mm &&
-			!ptrace_may_access(task, PTRACE_MODE_READ)) {
+			!ptrace_may_access(task, mode)) {
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}

@@ -272,6 +214,11 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
 	return mm;
 }
 
+struct mm_struct *mm_for_maps(struct task_struct *task)
+{
+	return mm_access(task, PTRACE_MODE_READ);
+}
+
 static int proc_pid_cmdline(struct task_struct *task, char * buffer)
 {
 	int res = 0;

@@ -816,38 +763,39 @@ static const struct file_operations proc_single_file_operations = {
 
 static int mem_open(struct inode* inode, struct file* file)
 {
-	file->private_data = (void*)((long)current->self_exec_id);
+	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	struct mm_struct *mm;
+
+	if (!task)
+		return -ESRCH;
+
+	mm = mm_access(task, PTRACE_MODE_ATTACH);
+	put_task_struct(task);
+
+	if (IS_ERR(mm))
+		return PTR_ERR(mm);
+
 	/* OK to pass negative loff_t, we can catch out-of-range */
 	file->f_mode |= FMODE_UNSIGNED_OFFSET;
+	file->private_data = mm;
+
 	return 0;
 }
 
 static ssize_t mem_read(struct file * file, char __user * buf,
 			size_t count, loff_t *ppos)
 {
-	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	int ret;
 	char *page;
 	unsigned long src = *ppos;
-	int ret = -ESRCH;
-	struct mm_struct *mm;
+	struct mm_struct *mm = file->private_data;
 
-	if (!task)
-		goto out_no_task;
+	if (!mm)
+		return 0;
 
-	ret = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out;
-
-	mm = check_mem_permission(task);
-	ret = PTR_ERR(mm);
-	if (IS_ERR(mm))
-		goto out_free;
-
-	ret = -EIO;
- 
-	if (file->private_data != (void*)((long)current->self_exec_id))
-		goto out_put;
+		return -ENOMEM;
 
 	ret = 0;
  

@@ -874,13 +822,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
 	}
 	*ppos = src;
 
-out_put:
-	mmput(mm);
-out_free:
 	free_page((unsigned long) page);
-out:
-	put_task_struct(task);
-out_no_task:
 	return ret;
 }
 

@@ -889,27 +831,15 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 {
 	int copied;
 	char *page;
-	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
 	unsigned long dst = *ppos;
-	struct mm_struct *mm;
+	struct mm_struct *mm = file->private_data;
 
-	copied = -ESRCH;
-	if (!task)
-		goto out_no_task;
+	if (!mm)
+		return 0;
 
-	copied = -ENOMEM;
 	page = (char *)__get_free_page(GFP_TEMPORARY);
 	if (!page)
-		goto out_task;
-
-	mm = check_mem_permission(task);
-	copied = PTR_ERR(mm);
-	if (IS_ERR(mm))
-		goto out_free;
-
-	copied = -EIO;
-	if (file->private_data != (void *)((long)current->self_exec_id))
-		goto out_mm;
+		return -ENOMEM;
 
 	copied = 0;
 	while (count > 0) {

@@ -933,13 +863,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
 	}
 	*ppos = dst;
 
-out_mm:
-	mmput(mm);
-out_free:
 	free_page((unsigned long) page);
-out_task:
-	put_task_struct(task);
-out_no_task:
 	return copied;
 }
 

@@ -959,11 +883,20 @@ loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 	return file->f_pos;
 }
 
+static int mem_release(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+
+	mmput(mm);
+	return 0;
+}
+
 static const struct file_operations proc_mem_operations = {
 	.llseek		= mem_lseek,
 	.read		= mem_read,
 	.write		= mem_write,
 	.open		= mem_open,
+	.release	= mem_release,
 };
 
 static ssize_t environ_read(struct file *file, char __user *buf,

@@ -518,6 +518,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		if (!page)
 			continue;
 
+		if (PageReserved(page))
+			continue;
+
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
 		ClearPageReferenced(page);

@@ -11,15 +11,20 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
+	cputime64_t idletime;
+	u64 nsec;
+	u32 rem;
 	int i;
-	cputime_t idletime = cputime_zero;
 
+	idletime = 0;
 	for_each_possible_cpu(i)
 		idletime = cputime64_add(idletime, kstat_cpu(i).cpustat.idle);
 
 	do_posix_clock_monotonic_gettime(&uptime);
 	monotonic_to_bootbased(&uptime);
-	cputime_to_timespec(idletime, &idle);
+	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
+	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
 			(unsigned long) uptime.tv_sec,
 			(uptime.tv_nsec / (NSEC_PER_SEC / 100)),

@@ -175,22 +175,23 @@ const char *dbg_key_str1(const struct ubifs_info *c,
 			 const union ubifs_key *key);
 
 /*
- * DBGKEY macros require @dbg_lock to be held, which it is in the dbg message
- * macros.
+ * TODO: these macros are now broken because there is no locking around them
+ * and we use a global buffer for the key string. This means that in case of
+ * concurrent execution we will end up with incorrect and messy key strings.
  */
 #define DBGKEY(key) dbg_key_str0(c, (key))
 #define DBGKEY1(key) dbg_key_str1(c, (key))
 
 extern spinlock_t dbg_lock;
 
-#define ubifs_dbg_msg(type, fmt, ...) do {                        \
-	spin_lock(&dbg_lock);                                     \
-	pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__); \
-	spin_unlock(&dbg_lock);                                   \
-} while (0)
+#define ubifs_dbg_msg(type, fmt, ...) \
+	pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__)
 
 /* Just a debugging messages not related to any specific UBIFS subsystem */
-#define dbg_msg(fmt, ...)   ubifs_dbg_msg("msg", fmt, ##__VA_ARGS__)
+#define dbg_msg(fmt, ...)                                                     \
+	printk(KERN_DEBUG "UBIFS DBG (pid %d): %s: " fmt "\n", current->pid,  \
+	       __func__, ##__VA_ARGS__)
+
 /* General messages */
 #define dbg_gen(fmt, ...)   ubifs_dbg_msg("gen", fmt, ##__VA_ARGS__)
 /* Additional journal messages */

@@ -68,7 +68,7 @@ xfs_trim_extents(
 	 * Look up the longest btree in the AGF and start with it.
 	 */
 	error = xfs_alloc_lookup_le(cur, 0,
-				    XFS_BUF_TO_AGF(agbp)->agf_longest, &i);
+			    be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest), &i);
 	if (error)
 		goto out_del_cursor;
 

@@ -84,7 +84,7 @@ xfs_trim_extents(
 		if (error)
 			goto out_del_cursor;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, out_del_cursor);
-		ASSERT(flen <= XFS_BUF_TO_AGF(agbp)->agf_longest);
+		ASSERT(flen <= be32_to_cpu(XFS_BUF_TO_AGF(agbp)->agf_longest));
 
 		/*
 		 * Too small?  Give up.

@@ -15,6 +15,7 @@ extern int pxm_to_node(int);
 extern int node_to_pxm(int);
 extern void __acpi_map_pxm_to_node(int, int);
 extern int acpi_map_pxm_to_node(int);
+extern unsigned char acpi_srat_revision;
 
 #endif				/* CONFIG_ACPI_NUMA */
 #endif				/* __ACP_NUMA_H */

@@ -675,6 +675,9 @@ extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
+extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
+extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
+			      unsigned int, void __user *);
 extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			  unsigned int, void __user *);
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,

@@ -5,6 +5,7 @@
 #include <linux/kexec.h>
 #include <linux/device.h>
 #include <linux/proc_fs.h>
+#include <linux/elf.h>
 
 #define ELFCORE_ADDR_MAX	(-1ULL)
 #define ELFCORE_ADDR_ERR	(-2ULL)

@@ -203,6 +203,7 @@ struct dentry_operations {
 
 #define DCACHE_CANT_MOUNT	0x0100
 #define DCACHE_GENOCIDE		0x0200
+#define DCACHE_SHRINK_LIST	0x0400
 
 #define DCACHE_NFSFS_RENAMED	0x1000
      /* this dentry has been "silly renamed" and has to be deleted on the last

@@ -119,6 +119,8 @@ struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page);
 extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 					struct task_struct *p);
+extern void mem_cgroup_replace_page_cache(struct page *oldpage,
+					struct page *newpage);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 extern int do_swap_account;

@@ -366,6 +368,10 @@ static inline
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
+				struct page *newpage)
+{
+}
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)

@@ -602,11 +602,16 @@ struct nfs_getaclargs {
 	size_t				acl_len;
 	unsigned int			acl_pgbase;
 	struct page **			acl_pages;
+	struct page *			acl_scratch;
 	struct nfs4_sequence_args 	seq_args;
 };
 
+/* getxattr ACL interface flags */
+#define NFS4_ACL_LEN_REQUEST	0x0001	/* zero length getxattr buffer */
 struct nfs_getaclres {
 	size_t				acl_len;
+	size_t				acl_data_offset;
+	int				acl_flags;
 	struct nfs4_sequence_res	seq_res;
 };
 

@@ -392,7 +392,7 @@
 #define  PCI_EXP_TYPE_DOWNSTREAM 0x6	/* Downstream Port */
 #define  PCI_EXP_TYPE_PCI_BRIDGE 0x7	/* PCI/PCI-X Bridge */
 #define  PCI_EXP_TYPE_RC_END	0x9	/* Root Complex Integrated Endpoint */
-#define  PCI_EXP_TYPE_RC_EC	0x10	/* Root Complex Event Collector */
+#define  PCI_EXP_TYPE_RC_EC	0xa	/* Root Complex Event Collector */
 #define PCI_EXP_FLAGS_SLOT	0x0100	/* Slot implemented */
 #define PCI_EXP_FLAGS_IRQ	0x3e00	/* Interrupt message number */
 #define PCI_EXP_DEVCAP		4	/* Device capabilities */

@@ -48,6 +48,7 @@ extern struct file *shmem_file_setup(const char *name,
 					loff_t size, unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
 extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);

@@ -34,7 +34,7 @@ struct svc_sock {
 /*
  * Function prototypes.
  */
-void		svc_close_all(struct list_head *);
+void		svc_close_all(struct svc_serv *);
 int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);

@@ -191,6 +191,8 @@ extern int xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
 extern int xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
 			     struct xdr_array2_desc *desc);
+extern void _copy_from_pages(char *p, struct page **pages, size_t pgbase,
+			     size_t len);
 
 /*
  * Provide some simple tools for XDR buffer overflow-checking etc.

@@ -272,7 +272,7 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 #endif
 
 extern int page_evictable(struct page *page, struct vm_area_struct *vma);
-extern void scan_mapping_unevictable_pages(struct address_space *);
+extern void check_move_unevictable_pages(struct page **, int nr_pages);
 
 extern unsigned long scan_unevictable_pages;
 extern int scan_unevictable_handler(struct ctl_table *, int,

@@ -1131,6 +1131,7 @@ struct v4l2_querymenu {
 #define V4L2_CTRL_FLAG_NEXT_CTRL	0x80000000
 
 /*  User-class control IDs defined by V4L2 */
+#define V4L2_CID_MAX_CTRLS		1024
 #define V4L2_CID_BASE			(V4L2_CTRL_CLASS_USER | 0x900)
 #define V4L2_CID_USER_BASE 		V4L2_CID_BASE
 /*  IDs reserved for driver specific controls */

@@ -127,7 +127,6 @@
 #define TUNER_PHILIPS_FMD1216MEX_MK3	78
 #define TUNER_PHILIPS_FM1216MK5		79
 #define TUNER_PHILIPS_FQ1216LME_MK3	80	/* Active loopthrough, no FM */
-#define TUNER_XC4000			81	/* Xceive Silicon Tuner */
 
 #define TUNER_PARTSNIC_PTI_5NF05	81
 #define TUNER_PHILIPS_CU1216L           82

@@ -136,6 +135,8 @@
 #define TUNER_PHILIPS_FQ1236_MK5	85	/* NTSC, TDA9885, no FM radio */
 #define TUNER_TENA_TNF_5337		86
 
+#define TUNER_XC4000			87	/* Xceive Silicon Tuner */
+
 /* tv card specific */
 #define TDA9887_PRESENT 		(1<<0)
 #define TDA9887_PORT1_INACTIVE 		(1<<1)

@@ -34,6 +34,7 @@
 #define TRANSPORT_SENSE_BUFFER			SCSI_SENSE_BUFFERSIZE
 /* Used by transport_send_check_condition_and_sense() */
 #define SPC_SENSE_KEY_OFFSET			2
+#define SPC_ADD_SENSE_LEN_OFFSET		7
 #define SPC_ASC_KEY_OFFSET			12
 #define SPC_ASCQ_KEY_OFFSET			13
 #define TRANSPORT_IQN_LEN			224

@@ -87,4 +87,7 @@ struct xenstore_domain_interface {
     XENSTORE_RING_IDX rsp_cons, rsp_prod;
 };
 
+/* Violating this is very bad.  See docs/misc/xenstore.txt. */
+#define XENSTORE_PAYLOAD_MAX 4096
+
 #endif /* _XS_WIRE_H */

@@ -398,15 +398,42 @@ out:
 }
  
 #ifdef CONFIG_ROOT_NFS
+
+#define NFSROOT_TIMEOUT_MIN	5
+#define NFSROOT_TIMEOUT_MAX	30
+#define NFSROOT_RETRY_MAX	5
+
 static int __init mount_nfs_root(void)
 {
 	char *root_dev, *root_data;
+	unsigned int timeout;
+	int try, err;
 
-	if (nfs_root_data(&root_dev, &root_data) != 0)
-		return 0;
-	if (do_mount_root(root_dev, "nfs", root_mountflags, root_data) != 0)
+	err = nfs_root_data(&root_dev, &root_data);
+	if (err != 0)
 		return 0;
-	return 1;
+
+	/*
+	 * The server or network may not be ready, so try several
+	 * times.  Stop after a few tries in case the client wants
+	 * to fall back to other boot methods.
+	 */
+	timeout = NFSROOT_TIMEOUT_MIN;
+	for (try = 1; ; try++) {
+		err = do_mount_root(root_dev, "nfs",
+					root_mountflags, root_data);
+		if (err == 0)
+			return 1;
+		if (try > NFSROOT_RETRY_MAX)
+			break;
+
+		/* Wait, in case the server refused us immediately */
+		ssleep(timeout);
+		timeout <<= 1;
+		if (timeout > NFSROOT_TIMEOUT_MAX)
+			timeout = NFSROOT_TIMEOUT_MAX;
+	}
+	return 0;
 }
 #endif
 

@@ -870,9 +870,7 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 	case SHM_LOCK:
 	case SHM_UNLOCK:
 	{
-		struct file *uninitialized_var(shm_file);
-
-		lru_add_drain_all();  /* drain pagevecs to lru lists */
+		struct file *shm_file;
 
 		shp = shm_lock_check(ns, shmid);
 		if (IS_ERR(shp)) {

@@ -895,22 +893,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
 		err = security_shm_shmctl(shp, cmd);
 		if (err)
 			goto out_unlock;
-		
-		if(cmd==SHM_LOCK) {
+
+		shm_file = shp->shm_file;
+		if (is_file_hugepages(shm_file))
+			goto out_unlock;
+
+		if (cmd == SHM_LOCK) {
 			struct user_struct *user = current_user();
-			if (!is_file_hugepages(shp->shm_file)) {
-				err = shmem_lock(shp->shm_file, 1, user);
-				if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){
-					shp->shm_perm.mode |= SHM_LOCKED;
-					shp->mlock_user = user;
-				}
+			err = shmem_lock(shm_file, 1, user);
+			if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
+				shp->shm_perm.mode |= SHM_LOCKED;
+				shp->mlock_user = user;
 			}
-		} else if (!is_file_hugepages(shp->shm_file)) {
-			shmem_lock(shp->shm_file, 0, shp->mlock_user);
-			shp->shm_perm.mode &= ~SHM_LOCKED;
-			shp->mlock_user = NULL;
+			goto out_unlock;
 		}
+
+		/* SHM_UNLOCK */
+		if (!(shp->shm_perm.mode & SHM_LOCKED))
+			goto out_unlock;
+		shmem_lock(shm_file, 0, shp->mlock_user);
+		shp->shm_perm.mode &= ~SHM_LOCKED;
+		shp->mlock_user = NULL;
+		get_file(shm_file);
 		shm_unlock(shp);
+		shmem_unlock_mapping(shm_file->f_mapping);
+		fput(shm_file);
 		goto out;
 	}
 	case IPC_RMID:

@@ -1077,6 +1077,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk)
 		/* Early boot.  kretprobe_table_locks not yet initialized. */
 		return;
 
+	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
 	kretprobe_table_lock(hash, &flags);

@@ -1085,7 +1086,6 @@ void __kprobes kprobe_flush_task(struct task_struct *tk)
 			recycle_rp_inst(ri, &empty_rp);
 	}
 	kretprobe_table_unlock(hash, &flags);
-	INIT_HLIST_HEAD(&empty_rp);
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);

@@ -948,7 +948,7 @@ struct ftrace_func_probe {
 };
 
 enum {
-	FTRACE_ENABLE_CALLS		= (1 << 0),
+	FTRACE_UPDATE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
 	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
 	FTRACE_START_FUNC_RET		= (1 << 3),

@@ -1519,7 +1519,7 @@ int ftrace_text_reserved(void *start, void *end)
 
 
 static int
-__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+__ftrace_replace_code(struct dyn_ftrace *rec, int update)
 {
 	unsigned long ftrace_addr;
 	unsigned long flag = 0UL;

@@ -1527,17 +1527,17 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
 	/*
-	 * If we are enabling tracing:
+	 * If we are updating calls:
 	 *
 	 *   If the record has a ref count, then we need to enable it
 	 *   because someone is using it.
 	 *
 	 *   Otherwise we make sure its disabled.
 	 *
-	 * If we are disabling tracing, then disable all records that
+	 * If we are disabling calls, then disable all records that
 	 * are enabled.
 	 */
-	if (enable && (rec->flags & ~FTRACE_FL_MASK))
+	if (update && (rec->flags & ~FTRACE_FL_MASK))
 		flag = FTRACE_FL_ENABLED;
 
 	/* If the state of this record hasn't changed, then do nothing */

@@ -1553,7 +1553,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
-static void ftrace_replace_code(int enable)
+static void ftrace_replace_code(int update)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;

@@ -1567,7 +1567,7 @@ static void ftrace_replace_code(int enable)
 		if (rec->flags & FTRACE_FL_FREE)
 			continue;
 
-		failed = __ftrace_replace_code(rec, enable);
+		failed = __ftrace_replace_code(rec, update);
 		if (failed) {
 			ftrace_bug(failed, rec->ip);
 			/* Stop processing */

@@ -1623,7 +1623,7 @@ static int __ftrace_modify_code(void *data)
 	 */
 	function_trace_stop++;
 
-	if (*command & FTRACE_ENABLE_CALLS)
+	if (*command & FTRACE_UPDATE_CALLS)
 		ftrace_replace_code(1);
 	else if (*command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);

@@ -1691,7 +1691,7 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 		return -ENODEV;
 
 	ftrace_start_up++;
-	command |= FTRACE_ENABLE_CALLS;
+	command |= FTRACE_UPDATE_CALLS;
 
 	/* ops marked global share the filter hashes */
 	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {

@@ -1743,8 +1743,7 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command)
 	if (ops != &global_ops || !global_start_up)
 		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
 
-	if (!ftrace_start_up)
-		command |= FTRACE_DISABLE_CALLS;
+	command |= FTRACE_UPDATE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
 		saved_ftrace_func = ftrace_trace_function;

@@ -1766,7 +1765,7 @@ static void ftrace_startup_sysctl(void)
 	saved_ftrace_func = NULL;
 	/* ftrace_start_up is true if we want ftrace running */
 	if (ftrace_start_up)
-		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+		ftrace_run_update_code(FTRACE_UPDATE_CALLS);
 }
 
 static void ftrace_shutdown_sysctl(void)

@@ -2919,7 +2918,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
 	if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED
 	    && ftrace_enabled)
-		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+		ftrace_run_update_code(FTRACE_UPDATE_CALLS);
 
 	mutex_unlock(&ftrace_lock);
 

@@ -3107,7 +3106,7 @@ ftrace_regex_release(struct inode *inode, struct file *file)
 				       orig_hash, iter->hash);
 		if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED)
 		    && ftrace_enabled)
-			ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+			ftrace_run_update_code(FTRACE_UPDATE_CALLS);
 
 		mutex_unlock(&ftrace_lock);
 	}

@@ -634,10 +634,11 @@ static int tracepoint_module_coming(struct module *mod)
 	int ret = 0;
 
 	/*
-	 * We skip modules that tain the kernel, especially those with different
-	 * module header (for forced load), to make sure we don't cause a crash.
+	 * We skip modules that taint the kernel, especially those with different
+	 * module headers (for forced load), to make sure we don't cause a crash.
+	 * Staging and out-of-tree GPL modules are fine.
 	 */
-	if (mod->taints)
+	if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
 		return 0;
 	mutex_lock(&tracepoints_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);

@@ -393,24 +393,11 @@ EXPORT_SYMBOL(filemap_write_and_wait_range);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 {
 	int error;
-	struct mem_cgroup *memcg = NULL;
 
 	VM_BUG_ON(!PageLocked(old));
 	VM_BUG_ON(!PageLocked(new));
 	VM_BUG_ON(new->mapping);
 
-	/*
-	 * This is not page migration, but prepare_migration and
-	 * end_migration does enough work for charge replacement.
-	 *
-	 * In the longer term we probably want a specialized function
-	 * for moving the charge from old to new in a more efficient
-	 * manner.
-	 */
-	error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
-	if (error)
-		return error;
-
 	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
 	if (!error) {
 		struct address_space *mapping = old->mapping;

@@ -432,13 +419,12 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		if (PageSwapBacked(new))
 			__inc_zone_page_state(new, NR_SHMEM);
 		spin_unlock_irq(&mapping->tree_lock);
+		/* mem_cgroup codes must not be called under tree_lock */
+		mem_cgroup_replace_page_cache(old, new);
 		radix_tree_preload_end();
 		if (freepage)
 			freepage(old);
 		page_cache_release(old);
-		mem_cgroup_end_migration(memcg, old, new, true);
-	} else {
-		mem_cgroup_end_migration(memcg, old, new, false);
 	}
 
 	return error;

@@ -3366,6 +3366,50 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
+/*
+ * At replace page cache, newpage is not under any memcg but it's on
+ * LRU. So, this function doesn't touch res_counter but handles LRU
+ * in correct way. Both pages are locked so we cannot race with uncharge.
+ */
+void mem_cgroup_replace_page_cache(struct page *oldpage,
+				  struct page *newpage)
+{
+	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
+	struct zone *zone;
+	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	unsigned long flags;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	pc = lookup_page_cgroup(oldpage);
+	/* fix accounting on old pages */
+	lock_page_cgroup(pc);
+	memcg = pc->mem_cgroup;
+	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -1);
+	ClearPageCgroupUsed(pc);
+	unlock_page_cgroup(pc);
+
+	if (PageSwapBacked(oldpage))
+		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+
+	zone = page_zone(newpage);
+	pc = lookup_page_cgroup(newpage);
+	/*
+	 * Even if newpage->mapping was NULL before starting replacement,
+	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
+	 * LRU while we overwrite pc->mem_cgroup.
+	 */
+	spin_lock_irqsave(&zone->lru_lock, flags);
+	if (PageLRU(newpage))
+		del_page_from_lru_list(zone, newpage, page_lru(newpage));
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, type);
+	if (PageLRU(newpage))
+		add_page_to_lru_list(zone, newpage, page_lru(newpage));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
 #ifdef CONFIG_DEBUG_VM
 static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
 {

@@ -5608,6 +5608,17 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 bool is_pageblock_removable_nolock(struct page *page)
 {
 	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+
+	/*
+	 * We have to be careful here because we are iterating over memory
+	 * sections which are not zone aware so we might end up outside of
+	 * the zone but still within the section.
+	 */
+	if (!zone || zone->zone_start_pfn > pfn ||
+			zone->zone_start_pfn + zone->spanned_pages <= pfn)
+		return false;
+
 	return __count_immobile_pages(zone, page, 0);
 }
 

@@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping,
 /*
  * Pagevec may contain swap entries, so shuffle up pages before releasing.
  */
-static void shmem_pagevec_release(struct pagevec *pvec)
+static void shmem_deswap_pagevec(struct pagevec *pvec)
 {
 	int i, j;