16 files changed, 256 insertions, 116 deletions

diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index 67e18509d7b..b0d6b32654c 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -17,9 +17,9 @@
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/sched.h>
+#include <linux/cnt32_to_63.h>
 
 #include <asm/div64.h>
-#include <asm/cnt32_to_63.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 #include <mach/pxa-regs.h>
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 1362994c78a..b422526f6d8 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -18,9 +18,9 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>	/* just for sched_clock() - funny that */
 #include <linux/platform_device.h>
+#include <linux/cnt32_to_63.h>
 
 #include <asm/div64.h>
-#include <asm/cnt32_to_63.h>
 #include <mach/hardware.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index d75e795c893..b638f10411e 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -28,8 +28,8 @@
 #include <linux/amba/clcd.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/cnt32_to_63.h>
 
-#include <asm/cnt32_to_63.h>
 #include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/io.h>
diff --git a/arch/mips/au1000/common/gpio.c b/arch/mips/au1000/common/gpio.c
index b485d94ce8a..1f058434b72 100644
--- a/arch/mips/au1000/common/gpio.c
+++ b/arch/mips/au1000/common/gpio.c
@@ -61,7 +61,8 @@ static int au1xxx_gpio2_direction_input(unsigned gpio)
 static int au1xxx_gpio2_direction_output(unsigned gpio, int value)
 {
 	gpio -= AU1XXX_GPIO_BASE;
-	gpio2->dir = (0x01 << gpio) | (value << gpio);
+	gpio2->dir |= 0x01 << gpio;
+	gpio2->output = (GPIO2_OUTPUT_ENABLE_MASK << gpio) | (value << gpio);
 	return 0;
 }
 
@@ -90,6 +91,7 @@ static int au1xxx_gpio1_direction_input(unsigned gpio)
 static int au1xxx_gpio1_direction_output(unsigned gpio, int value)
 {
 	gpio1->trioutclr = (0x01 & gpio);
+	au1xxx_gpio1_write(gpio, value);
 	return 0;
 }
 
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c
index babb7c2ac37..e4606586f94 100644
--- a/arch/mn10300/kernel/time.c
+++ b/arch/mn10300/kernel/time.c
@@ -1,6 +1,6 @@
 /* MN10300 Low level time management
  *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2007-2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  * - Derived from arch/i386/kernel/time.c
  *
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/profile.h>
+#include <linux/cnt32_to_63.h>
 #include <asm/irq.h>
 #include <asm/div64.h>
 #include <asm/processor.h>
@@ -40,27 +41,54 @@ static struct irqaction timer_irq = {
 	.name		= "timer",
 };
 
+static unsigned long sched_clock_multiplier;
+
 /*
  * scheduler clock - returns current time in nanosec units.
  */
 unsigned long long sched_clock(void)
 {
 	union {
-		unsigned long long l;
-		u32 w[2];
-	} quot;
+		unsigned long long ll;
+		unsigned l[2];
+	} tsc64, result;
+	unsigned long tsc, tmp;
+	unsigned product[3]; /* 96-bit intermediate value */
+
+	/* read the TSC value
+	 */
+	tsc = 0 - get_cycles(); /* get_cycles() counts down */
 
-	quot.w[0] = mn10300_last_tsc - get_cycles();
-	quot.w[1] = 1000000000;
+	/* expand to 64-bits.
+	 * - sched_clock() must be called once a minute or better or the
+	 *   following will go horribly wrong - see cnt32_to_63()
+	 */
+	tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL;
 
-	asm("mulu %2,%3,%0,%1"
-	    : "=r"(quot.w[1]), "=r"(quot.w[0])
-	    : "0"(quot.w[1]), "1"(quot.w[0])
+	/* scale the 64-bit TSC value to a nanosecond value via a 96-bit
+	 * intermediate
+	 */
+	asm("mulu	%2,%0,%3,%0	\n"	/* LSW * mult ->  0:%3:%0 */
+	    "mulu	%2,%1,%2,%1	\n"	/* MSW * mult -> %2:%1:0 */
+	    "add	%3,%1		\n"
+	    "addc	0,%2		\n"	/* result in %2:%1:%0 */
+	    : "=r"(product[0]), "=r"(product[1]), "=r"(product[2]), "=r"(tmp)
+	    :  "0"(tsc64.l[0]),  "1"(tsc64.l[1]),  "2"(sched_clock_multiplier)
 	    : "cc");
 
-	do_div(quot.l, MN10300_TSCCLK);
+	result.l[0] = product[1] << 16 | product[0] >> 16;
+	result.l[1] = product[2] << 16 | product[1] >> 16;
 
-	return quot.l;
+	return result.ll;
+}
+
+/*
+ * initialise the scheduler clock
+ */
+static void __init mn10300_sched_clock_init(void)
+{
+	sched_clock_multiplier =
+		__muldiv64u(NSEC_PER_SEC, 1 << 16, MN10300_TSCCLK);
 }
 
 /*
@@ -128,4 +156,6 @@ void __init time_init(void)
 	/* start the watchdog timer */
 	watchdog_go();
 #endif
+
+	mn10300_sched_clock_init();
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4b3cfdf5421..31f40b24bf5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -55,6 +55,7 @@
 #include <asm/tlbflush.h>
 #include <asm/cpu.h>
 #include <asm/kdebug.h>
+#include <asm/idle.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index c95295c6504..e83aa5ebe86 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -626,8 +626,7 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	return NULL;
 
 error:
-	if (fid)
-		p9_client_clunk(fid);
+	p9_client_clunk(fid);
 
 	return ERR_PTR(result);
 }
diff --git a/include/asm-mips/pgtable-32.h b/include/asm-mips/pgtable-32.h
index 4396e9ffd41..55813d6150c 100644
--- a/include/asm-mips/pgtable-32.h
+++ b/include/asm-mips/pgtable-32.h
@@ -57,7 +57,7 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1,
 #define PMD_ORDER	1
 #define PTE_ORDER	0
 
-#define PTRS_PER_PGD	((PAGE_SIZE << PGD_ORDER) / sizeof(pgd_t))
+#define PTRS_PER_PGD	(USER_PTRS_PER_PGD * 2)
 #define PTRS_PER_PTE	((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t))
 
 #define USER_PTRS_PER_PGD	(0x80000000UL/PGDIR_SIZE)
diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h
new file mode 100644
index 00000000000..8c0f9505b48
--- /dev/null
+++ b/include/linux/cnt32_to_63.h
@@ -0,0 +1,80 @@
+/*
+ *  Extend a 32-bit counter to 63 bits
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	December 3, 2006
+ *  Copyright:	MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CNT32_TO_63_H__
+#define __LINUX_CNT32_TO_63_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* this is used only to give gcc a clue about good code generation */
+union cnt32_to_63 {
+	struct {
+#if defined(__LITTLE_ENDIAN)
+		u32 lo, hi;
+#elif defined(__BIG_ENDIAN)
+		u32 hi, lo;
+#endif
+	};
+	u64 val;
+};
+
+
+/**
+ * cnt32_to_63 - Expand a 32-bit counter to a 63-bit counter
+ * @cnt_lo: The low part of the counter
+ *
+ * Many hardware clock counters are only 32 bits wide and therefore have
+ * a relatively short period making wrap-arounds rather frequent.  This
+ * is a problem when implementing sched_clock() for example, where a 64-bit
+ * non-wrapping monotonic value is expected to be returned.
+ *
+ * To overcome that limitation, let's extend a 32-bit counter to 63 bits
+ * in a completely lock free fashion. Bits 0 to 31 of the clock are provided
+ * by the hardware while bits 32 to 62 are stored in memory.  The top bit in
+ * memory is used to synchronize with the hardware clock half-period.  When
+ * the top bit of both counters (hardware and in memory) differ then the
+ * memory is updated with a new value, incrementing it when the hardware
+ * counter wraps around.
+ *
+ * Because a word store in memory is atomic then the incremented value will
+ * always be in synch with the top bit indicating to any potential concurrent
+ * reader if the value in memory is up to date or not with regards to the
+ * needed increment.  And any race in updating the value in memory is harmless
+ * as the same value would simply be stored more than once.
+ *
+ * The only restriction for the algorithm to work properly is that this
+ * code must be executed at least once per each half period of the 32-bit
+ * counter to properly update the state bit in memory. This is usually not a
+ * problem in practice, but if it is then a kernel timer could be scheduled
+ * to manage for this code to be executed often enough.
+ *
+ * Note that the top bit (bit 63) in the returned value should be considered
+ * as garbage.  It is not cleared here because callers are likely to use a
+ * multiplier on the returned value which can get rid of the top bit
+ * implicitly by making the multiplier even, therefore saving on a runtime
+ * clear-bit instruction. Otherwise caller must remember to clear the top
+ * bit explicitly.
+ */
+#define cnt32_to_63(cnt_lo) \
+({ \
+	static volatile u32 __m_cnt_hi; \
+	union cnt32_to_63 __x; \
+	__x.hi = __m_cnt_hi; \
+	__x.lo = (cnt_lo); \
+	if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
+		__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
+	__x.val; \
+})
+
+#endif
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index b3d3e27c629..c3626c0ba9d 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -596,4 +596,5 @@ int p9_idpool_check(int id, struct p9_idpool *p);
 int p9_error_init(void);
 int p9_errstr2errno(char *, int);
 int p9_trans_fd_init(void);
+void p9_trans_fd_exit(void);
 #endif /* NET_9P_H */
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 0db3a4038dc..3ca737120a9 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -26,6 +26,8 @@
 #ifndef NET_9P_TRANSPORT_H
 #define NET_9P_TRANSPORT_H
 
+#include <linux/module.h>
+
 /**
  * enum p9_trans_status - different states of underlying transports
  * @Connected: transport is connected and healthy
@@ -91,9 +93,12 @@ struct p9_trans_module {
 	int maxsize;		/* max message size of transport */
 	int def;		/* this transport should be default */
 	struct p9_trans * (*create)(const char *, char *, int, unsigned char);
+	struct module *owner;
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);
-struct p9_trans_module *v9fs_match_trans(const substring_t *name);
-struct p9_trans_module *v9fs_default_trans(void);
+void v9fs_unregister_trans(struct p9_trans_module *m);
+struct p9_trans_module *v9fs_get_trans_by_name(const substring_t *name);
+struct p9_trans_module *v9fs_get_default_trans(void);
+void v9fs_put_trans(struct p9_trans_module *m);
 #endif /* NET_9P_TRANSPORT_H */
diff --git a/net/9p/client.c b/net/9p/client.c
index 2ffe40cf2f0..10e320307ec 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -75,7 +75,6 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	int option;
 	int ret = 0;
 
-	clnt->trans_mod = v9fs_default_trans();
 	clnt->dotu = 1;
 	clnt->msize = 8192;
 
@@ -108,7 +107,7 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 			clnt->msize = option;
 			break;
 		case Opt_trans:
-			clnt->trans_mod = v9fs_match_trans(&args[0]);
+			clnt->trans_mod = v9fs_get_trans_by_name(&args[0]);
 			break;
 		case Opt_legacy:
 			clnt->dotu = 0;
@@ -117,6 +116,10 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 			continue;
 		}
 	}
+
+	if (!clnt->trans_mod)
+		clnt->trans_mod = v9fs_get_default_trans();
+
 	kfree(options);
 	return ret;
 }
@@ -150,6 +153,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 	if (!clnt)
 		return ERR_PTR(-ENOMEM);
 
+	clnt->trans_mod = NULL;
 	clnt->trans = NULL;
 	spin_lock_init(&clnt->lock);
 	INIT_LIST_HEAD(&clnt->fidlist);
@@ -235,6 +239,8 @@ void p9_client_destroy(struct p9_client *clnt)
 		clnt->trans = NULL;
 	}
 
+	v9fs_put_trans(clnt->trans_mod);
+
 	list_for_each_entry_safe(fid, fidptr, &clnt->fidlist, flist)
 		p9_fid_destroy(fid);
 
diff --git a/net/9p/conv.c b/net/9p/conv.c
index 44547201f5b..5ad3a3bd73b 100644
--- a/net/9p/conv.c
+++ b/net/9p/conv.c
@@ -451,8 +451,10 @@ p9_put_data(struct cbuf *bufp, const char *data, int count,
 		   unsigned char **pdata)
 {
 	*pdata = buf_alloc(bufp, count);
+	if (*pdata == NULL)
+		return -ENOMEM;
 	memmove(*pdata, data, count);
-	return count;
+	return 0;
 }
 
 static int
@@ -460,6 +462,8 @@ p9_put_user_data(struct cbuf *bufp, const char __user *data, int count,
 		   unsigned char **pdata)
 {
 	*pdata = buf_alloc(bufp, count);
+	if (*pdata == NULL)
+		return -ENOMEM;
 	return copy_from_user(*pdata, data, count);
 }
 
diff --git a/net/9p/mod.c b/net/9p/mod.c
index bdee1fb7cc6..1084feb24cb 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -31,6 +31,7 @@
 #include <linux/parser.h>
 #include <net/9p/transport.h>
 #include <linux/list.h>
+#include <linux/spinlock.h>
 
 #ifdef CONFIG_NET_9P_DEBUG
 unsigned int p9_debug_level = 0;	/* feature-rific global debug level  */
@@ -44,8 +45,8 @@ MODULE_PARM_DESC(debug, "9P debugging level");
  *
  */
 
+static DEFINE_SPINLOCK(v9fs_trans_lock);
 static LIST_HEAD(v9fs_trans_list);
-static struct p9_trans_module *v9fs_default_transport;
 
 /**
  * v9fs_register_trans - register a new transport with 9p
@@ -54,48 +55,87 @@ static struct p9_trans_module *v9fs_default_transport;
  */
 void v9fs_register_trans(struct p9_trans_module *m)
 {
+	spin_lock(&v9fs_trans_lock);
 	list_add_tail(&m->list, &v9fs_trans_list);
-	if (m->def)
-		v9fs_default_transport = m;
+	spin_unlock(&v9fs_trans_lock);
 }
 EXPORT_SYMBOL(v9fs_register_trans);
 
 /**
- * v9fs_match_trans - match transport versus registered transports
+ * v9fs_unregister_trans - unregister a 9p transport
+ * @m: the transport to remove
+ *
+ */
+void v9fs_unregister_trans(struct p9_trans_module *m)
+{
+	spin_lock(&v9fs_trans_lock);
+	list_del_init(&m->list);
+	spin_unlock(&v9fs_trans_lock);
+}
+EXPORT_SYMBOL(v9fs_unregister_trans);
+
+/**
+ * v9fs_get_trans_by_name - get transport with the matching name
  * @name: string identifying transport
  *
  */
-struct p9_trans_module *v9fs_match_trans(const substring_t *name)
+struct p9_trans_module *v9fs_get_trans_by_name(const substring_t *name)
 {
-	struct list_head *p;
-	struct p9_trans_module *t = NULL;
-
-	list_for_each(p, &v9fs_trans_list) {
-		t = list_entry(p, struct p9_trans_module, list);
-		if (strncmp(t->name, name->from, name->to-name->from) == 0)
-			return t;
-	}
-	return NULL;
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (strncmp(t->name, name->from, name->to-name->from) == 0 &&
+		    try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
 }
-EXPORT_SYMBOL(v9fs_match_trans);
+EXPORT_SYMBOL(v9fs_get_trans_by_name);
 
 /**
- * v9fs_default_trans - returns pointer to default transport
+ * v9fs_get_default_trans - get the default transport
  *
  */
 
-struct p9_trans_module *v9fs_default_trans(void)
+struct p9_trans_module *v9fs_get_default_trans(void)
 {
-	if (v9fs_default_transport)
-		return v9fs_default_transport;
-	else if (!list_empty(&v9fs_trans_list))
-		return list_first_entry(&v9fs_trans_list,
-					struct p9_trans_module, list);
-	else
-		return NULL;
+	struct p9_trans_module *t, *found = NULL;
+
+	spin_lock(&v9fs_trans_lock);
+
+	list_for_each_entry(t, &v9fs_trans_list, list)
+		if (t->def && try_module_get(t->owner)) {
+			found = t;
+			break;
+		}
+
+	if (!found)
+		list_for_each_entry(t, &v9fs_trans_list, list)
+			if (try_module_get(t->owner)) {
+				found = t;
+				break;
+			}
+
+	spin_unlock(&v9fs_trans_lock);
+	return found;
 }
-EXPORT_SYMBOL(v9fs_default_trans);
+EXPORT_SYMBOL(v9fs_get_default_trans);
 
+/**
+ * v9fs_put_trans - put trans
+ * @m: transport to put
+ *
+ */
+void v9fs_put_trans(struct p9_trans_module *m)
+{
+	if (m)
+		module_put(m->owner);
+}
 
 /**
  * v9fs_init - Initialize module
@@ -120,6 +160,8 @@ static int __init init_p9(void)
 static void __exit exit_p9(void)
 {
 	printk(KERN_INFO "Unloading 9P2000 support\n");
+
+	p9_trans_fd_exit();
 }
 
 module_init(init_p9)
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index cdf137af7ad..d652baf5ff9 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -151,7 +151,6 @@ struct p9_mux_poll_task {
  * @trans: reference to transport instance for this connection
  * @tagpool: id accounting for transactions
  * @err: error state
- * @equeue: event wait_q (?)
  * @req_list: accounting for requests which have been sent
  * @unsent_req_list: accounting for requests that haven't been sent
  * @rcall: current response &p9_fcall structure
@@ -178,7 +177,6 @@ struct p9_conn {
 	struct p9_trans *trans;
 	struct p9_idpool *tagpool;
 	int err;
-	wait_queue_head_t equeue;
 	struct list_head req_list;
 	struct list_head unsent_req_list;
 	struct p9_fcall *rcall;
@@ -240,22 +238,6 @@ static int p9_conn_rpcnb(struct p9_conn *m, struct p9_fcall *tc,
 
 static void p9_conn_cancel(struct p9_conn *m, int err);
 
-static int p9_mux_global_init(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(p9_mux_poll_tasks); i++)
-		p9_mux_poll_tasks[i].task = NULL;
-
-	p9_mux_wq = create_workqueue("v9fs");
-	if (!p9_mux_wq) {
-		printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n");
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
 static u16 p9_mux_get_tag(struct p9_conn *m)
 {
 	int tag;
@@ -409,11 +391,11 @@ static void p9_mux_poll_stop(struct p9_conn *m)
 static struct p9_conn *p9_conn_create(struct p9_trans *trans)
 {
 	int i, n;
-	struct p9_conn *m, *mtmp;
+	struct p9_conn *m;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "transport %p msize %d\n", trans,
 								trans->msize);
-	m = kmalloc(sizeof(struct p9_conn), GFP_KERNEL);
+	m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL);
 	if (!m)
 		return ERR_PTR(-ENOMEM);
 
@@ -424,25 +406,14 @@ static struct p9_conn *p9_conn_create(struct p9_trans *trans)
 	m->trans = trans;
 	m->tagpool = p9_idpool_create();
 	if (IS_ERR(m->tagpool)) {
-		mtmp = ERR_PTR(-ENOMEM);
 		kfree(m);
-		return mtmp;
+		return ERR_PTR(-ENOMEM);
 	}
 
-	m->err = 0;
-	init_waitqueue_head(&m->equeue);
 	INIT_LIST_HEAD(&m->req_list);
 	INIT_LIST_HEAD(&m->unsent_req_list);
-	m->rcall = NULL;
-	m->rpos = 0;
-	m->rbuf = NULL;
-	m->wpos = m->wsize = 0;
-	m->wbuf = NULL;
 	INIT_WORK(&m->rq, p9_read_work);
 	INIT_WORK(&m->wq, p9_write_work);
-	m->wsched = 0;
-	memset(&m->poll_waddr, 0, sizeof(m->poll_waddr));
-	m->poll_task = NULL;
 	n = p9_mux_poll_start(m);
 	if (n) {
 		kfree(m);
@@ -463,10 +434,8 @@ static struct p9_conn *p9_conn_create(struct p9_trans *trans)
 	for (i = 0; i < ARRAY_SIZE(m->poll_waddr); i++) {
 		if (IS_ERR(m->poll_waddr[i])) {
 			p9_mux_poll_stop(m);
-			mtmp = (void *)m->poll_waddr;	/* the error code */
 			kfree(m);
-			m = mtmp;
-			break;
+			return (void *)m->poll_waddr;	/* the error code */
 		}
 	}
 
@@ -483,18 +452,13 @@ static void p9_conn_destroy(struct p9_conn *m)
 {
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p prev %p next %p\n", m,
 		m->mux_list.prev, m->mux_list.next);
-	p9_conn_cancel(m, -ECONNRESET);
-
-	if (!list_empty(&m->req_list)) {
-		/* wait until all processes waiting on this session exit */
-		P9_DPRINTK(P9_DEBUG_MUX,
-			"mux %p waiting for empty request queue\n", m);
-		wait_event_timeout(m->equeue, (list_empty(&m->req_list)), 5000);
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p request queue empty: %d\n", m,
-			list_empty(&m->req_list));
-	}
 
 	p9_mux_poll_stop(m);
+	cancel_work_sync(&m->rq);
+	cancel_work_sync(&m->wq);
+
+	p9_conn_cancel(m, -ECONNRESET);
+
 	m->trans = NULL;
 	p9_idpool_destroy(m->tagpool);
 	kfree(m);
@@ -840,8 +804,6 @@ static void p9_read_work(struct work_struct *work)
 					(*req->cb) (req, req->cba);
 				else
 					kfree(req->rcall);
-
-				wake_up(&m->equeue);
 			}
 		} else {
 			if (err >= 0 && rcall->id != P9_RFLUSH)
@@ -908,8 +870,10 @@ static struct p9_req *p9_send_request(struct p9_conn *m,
 	else
 		n = p9_mux_get_tag(m);
 
-	if (n < 0)
+	if (n < 0) {
+		kfree(req);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	p9_set_tag(tc, n);
 
@@ -984,8 +948,6 @@ static void p9_mux_flush_cb(struct p9_req *freq, void *a)
 			(*req->cb) (req, req->cba);
 		else
 			kfree(req->rcall);
-
-		wake_up(&m->equeue);
 	}
 
 	kfree(freq->tcall);
@@ -1191,8 +1153,6 @@ void p9_conn_cancel(struct p9_conn *m, int err)
 		else
 			kfree(req->rcall);
 	}
-
-	wake_up(&m->equeue);
 }
 
 /**
@@ -1370,7 +1330,6 @@ p9_fd_poll(struct p9_trans *trans, struct poll_table_struct *pt)
 {
 	int ret, n;
 	struct p9_trans_fd *ts = NULL;
-	mm_segment_t oldfs;
 
 	if (trans && trans->status == Connected)
 		ts = trans->priv;
@@ -1384,24 +1343,17 @@ p9_fd_poll(struct p9_trans *trans, struct poll_table_struct *pt)
 	if (!ts->wr->f_op || !ts->wr->f_op->poll)
 		return -EIO;
 
-	oldfs = get_fs();
-	set_fs(get_ds());
-
 	ret = ts->rd->f_op->poll(ts->rd, pt);
 	if (ret < 0)
-		goto end;
+		return ret;
 
 	if (ts->rd != ts->wr) {
 		n = ts->wr->f_op->poll(ts->wr, pt);
-		if (n < 0) {
-			ret = n;
-			goto end;
-		}
+		if (n < 0)
+			return n;
 		ret = (ret & ~POLLOUT) | (n & ~POLLIN);
 	}
 
-end:
-	set_fs(oldfs);
 	return ret;
 }
 
@@ -1629,6 +1581,7 @@ static struct p9_trans_module p9_tcp_trans = {
 	.maxsize = MAX_SOCK_BUF,
 	.def = 1,
 	.create = p9_trans_create_tcp,
+	.owner = THIS_MODULE,
 };
 
 static struct p9_trans_module p9_unix_trans = {
@@ -1636,6 +1589,7 @@ static struct p9_trans_module p9_unix_trans = {
 	.maxsize = MAX_SOCK_BUF,
 	.def = 0,
 	.create = p9_trans_create_unix,
+	.owner = THIS_MODULE,
 };
 
 static struct p9_trans_module p9_fd_trans = {
@@ -1643,14 +1597,20 @@ static struct p9_trans_module p9_fd_trans = {
 	.maxsize = MAX_SOCK_BUF,
 	.def = 0,
 	.create = p9_trans_create_fd,
+	.owner = THIS_MODULE,
 };
 
 int p9_trans_fd_init(void)
 {
-	int ret = p9_mux_global_init();
-	if (ret) {
-		printk(KERN_WARNING "9p: starting mux failed\n");
-		return ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(p9_mux_poll_tasks); i++)
+		p9_mux_poll_tasks[i].task = NULL;
+
+	p9_mux_wq = create_workqueue("v9fs");
+	if (!p9_mux_wq) {
+		printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n");
+		return -ENOMEM;
 	}
 
 	v9fs_register_trans(&p9_tcp_trans);
@@ -1659,4 +1619,12 @@ int p9_trans_fd_init(void)
 
 	return 0;
 }
-EXPORT_SYMBOL(p9_trans_fd_init);
+
+void p9_trans_fd_exit(void)
+{
+	v9fs_unregister_trans(&p9_tcp_trans);
+	v9fs_unregister_trans(&p9_unix_trans);
+	v9fs_unregister_trans(&p9_fd_trans);
+
+	destroy_workqueue(p9_mux_wq);
+}
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 42adc052b14..94912e077a5 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -528,6 +528,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.create = p9_virtio_create,
 	.maxsize = PAGE_SIZE*16,
 	.def = 0,
+	.owner = THIS_MODULE,
 };
 
 /* The standard init function */
@@ -545,6 +546,7 @@ static int __init p9_virtio_init(void)
 static void __exit p9_virtio_cleanup(void)
 {
 	unregister_virtio_driver(&p9_virtio_drv);
+	v9fs_unregister_trans(&p9_virtio_trans);
 }
 
 module_init(p9_virtio_init);