Merge ../torvalds-2.6/

17 files changed, 322 insertions, 208 deletions

diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index 7fedc00c3d3..555c8cf3650 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -153,10 +153,13 @@ scaling_governor,		and by "echoing" the name of another
 				that some governors won't load - they only
 				work on some specific architectures or
 				processors.
-scaling_min_freq and 
+scaling_min_freq and
 scaling_max_freq		show the current "policy limits" (in
 				kHz). By echoing new values into these
 				files, you can change these limits.
+				NOTE: when setting a policy you need to
+				first set scaling_max_freq, then
+				scaling_min_freq.
 
 
 If you have selected the "userspace" governor which allows you to
diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig
index e44a4c6a4fe..ccc1edff5c9 100644
--- a/arch/i386/kernel/cpu/cpufreq/Kconfig
+++ b/arch/i386/kernel/cpu/cpufreq/Kconfig
@@ -96,6 +96,7 @@ config X86_POWERNOW_K8_ACPI
 
 config X86_GX_SUSPMOD
 	tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation"
+	depends on PCI
 	help
 	 This add the CPUFreq driver for NatSemi Geode processors which
 	 support suspend modulation.
@@ -202,7 +203,7 @@ config X86_LONGRUN
 config X86_LONGHAUL
 	tristate "VIA Cyrix III Longhaul"
 	select CPU_FREQ_TABLE
-	depends on BROKEN
+	depends on ACPI_PROCESSOR
 	help
 	  This adds the CPUFreq driver for VIA Samuel/CyrixIII,
 	  VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T
diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
index 567b39bea07..efb41e81351 100644
--- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -384,8 +384,7 @@ static int acpi_cpufreq_early_init_acpi(void)
 	}
 
 	/* Do initialization in ACPI core */
-	acpi_processor_preregister_performance(acpi_perf_data);
-	return 0;
+	return acpi_processor_preregister_performance(acpi_perf_data);
 }
 
 static int
diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c
index 146f607e9c4..4f2c3aeef72 100644
--- a/arch/i386/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c
@@ -29,11 +29,13 @@
 #include <linux/cpufreq.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/pci.h>
 
 #include <asm/msr.h>
 #include <asm/timex.h>
 #include <asm/io.h>
+#include <asm/acpi.h>
+#include <linux/acpi.h>
+#include <acpi/processor.h>
 
 #include "longhaul.h"
 
@@ -56,6 +58,8 @@ static int minvid, maxvid;
 static unsigned int minmult, maxmult;
 static int can_scale_voltage;
 static int vrmrev;
+static struct acpi_processor *pr = NULL;
+static struct acpi_processor_cx *cx = NULL;
 
 /* Module parameters */
 static int dont_scale_voltage;
@@ -118,84 +122,65 @@ static int longhaul_get_cpu_mult(void)
 	return eblcr_table[invalue];
 }
 
+/* For processor with BCR2 MSR */
 
-static void do_powersaver(union msr_longhaul *longhaul,
-			unsigned int clock_ratio_index)
+static void do_longhaul1(int cx_address, unsigned int clock_ratio_index)
 {
-	struct pci_dev *dev;
-	unsigned long flags;
-	unsigned int tmp_mask;
-	int version;
-	int i;
-	u16 pci_cmd;
-	u16 cmd_state[64];
+	union msr_bcr2 bcr2;
+	u32 t;
 
-	switch (cpu_model) {
-	case CPU_EZRA_T:
-		version = 3;
-		break;
-	case CPU_NEHEMIAH:
-		version = 0xf;
-		break;
-	default:
-		return;
-	}
+	rdmsrl(MSR_VIA_BCR2, bcr2.val);
+	/* Enable software clock multiplier */
+	bcr2.bits.ESOFTBF = 1;
+	bcr2.bits.CLOCKMUL = clock_ratio_index;
 
-	rdmsrl(MSR_VIA_LONGHAUL, longhaul->val);
-	longhaul->bits.SoftBusRatio = clock_ratio_index & 0xf;
-	longhaul->bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
-	longhaul->bits.EnableSoftBusRatio = 1;
-	longhaul->bits.RevisionKey = 0;
+	/* Sync to timer tick */
+	safe_halt();
+	ACPI_FLUSH_CPU_CACHE();
+	/* Change frequency on next halt or sleep */
+	wrmsrl(MSR_VIA_BCR2, bcr2.val);
+	/* Invoke C3 */
+	inb(cx_address);
+	/* Dummy op - must do something useless after P_LVL3 read */
+	t = inl(acpi_fadt.xpm_tmr_blk.address);
+
+	/* Disable software clock multiplier */
+	local_irq_disable();
+	rdmsrl(MSR_VIA_BCR2, bcr2.val);
+	bcr2.bits.ESOFTBF = 0;
+	wrmsrl(MSR_VIA_BCR2, bcr2.val);
+}
 
-	preempt_disable();
-	local_irq_save(flags);
+/* For processor with Longhaul MSR */
 
-	/*
-	 * get current pci bus master state for all devices
-	 * and clear bus master bit
-	 */
-	dev = NULL;
-	i = 0;
-	do {
-		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-		if (dev != NULL) {
-			pci_read_config_word(dev, PCI_COMMAND, &pci_cmd);
-			cmd_state[i++] = pci_cmd;
-			pci_cmd &= ~PCI_COMMAND_MASTER;
-			pci_write_config_word(dev, PCI_COMMAND, pci_cmd);
-		}
-	} while (dev != NULL);
+static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
+{
+	union msr_longhaul longhaul;
+	u32 t;
 
-	tmp_mask=inb(0x21);	/* works on C3. save mask. */
-	outb(0xFE,0x21);	/* TMR0 only */
-	outb(0xFF,0x80);	/* delay */
+	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
+	longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf;
+	longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
+	longhaul.bits.EnableSoftBusRatio = 1;
 
+	/* Sync to timer tick */
 	safe_halt();
-	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
-	halt();
-
+	ACPI_FLUSH_CPU_CACHE();
+	/* Change frequency on next halt or sleep */
+	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+	/* Invoke C3 */
+	inb(cx_address);
+	/* Dummy op - must do something useless after P_LVL3 read */
+	t = inl(acpi_fadt.xpm_tmr_blk.address);
+
+	/* Disable bus ratio bit */
 	local_irq_disable();
-
-	outb(tmp_mask,0x21);	/* restore mask */
-
-	/* restore pci bus master state for all devices */
-	dev = NULL;
-	i = 0;
-	do {
-		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
-		if (dev != NULL) {
-			pci_cmd = cmd_state[i++];
-			pci_write_config_byte(dev, PCI_COMMAND, pci_cmd);
-		}
-	} while (dev != NULL);
-	local_irq_restore(flags);
-	preempt_enable();
-
-	/* disable bus ratio bit */
-	rdmsrl(MSR_VIA_LONGHAUL, longhaul->val);
-	longhaul->bits.EnableSoftBusRatio = 0;
-	longhaul->bits.RevisionKey = version;
-	wrmsrl(MSR_VIA_LONGHAUL, longhaul->val);
+	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
+	longhaul.bits.EnableSoftBusRatio = 0;
+	longhaul.bits.EnableSoftBSEL = 0;
+	longhaul.bits.EnableSoftVID = 0;
+	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 }
 
 /**
@@ -209,9 +194,9 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 {
 	int speed, mult;
 	struct cpufreq_freqs freqs;
-	union msr_longhaul longhaul;
-	union msr_bcr2 bcr2;
 	static unsigned int old_ratio=-1;
+	unsigned long flags;
+	unsigned int pic1_mask, pic2_mask;
 
 	if (old_ratio == clock_ratio_index)
 		return;
@@ -234,6 +219,20 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
 			fsb, mult/10, mult%10, print_speed(speed/1000));
 
+	preempt_disable();
+	local_irq_save(flags);
+
+	pic2_mask = inb(0xA1);
+	pic1_mask = inb(0x21);	/* works on C3. save mask. */
+	outb(0xFF,0xA1);	/* Overkill */
+	outb(0xFE,0x21);	/* TMR0 only */
+
+	/* Disable bus master arbitration */
+	if (pr->flags.bm_check) {
+		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1,
+				  ACPI_MTX_DO_NOT_LOCK);
+	}
+
 	switch (longhaul_version) {
 
 	/*
@@ -245,20 +244,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	 */
 	case TYPE_LONGHAUL_V1:
 	case TYPE_LONGHAUL_V2:
-		rdmsrl (MSR_VIA_BCR2, bcr2.val);
-		/* Enable software clock multiplier */
-		bcr2.bits.ESOFTBF = 1;
-		bcr2.bits.CLOCKMUL = clock_ratio_index;
-		local_irq_disable();
-		wrmsrl (MSR_VIA_BCR2, bcr2.val);
-		safe_halt();
-
-		/* Disable software clock multiplier */
-		rdmsrl (MSR_VIA_BCR2, bcr2.val);
-		bcr2.bits.ESOFTBF = 0;
-		local_irq_disable();
-		wrmsrl (MSR_VIA_BCR2, bcr2.val);
-		local_irq_enable();
+		do_longhaul1(cx->address, clock_ratio_index);
 		break;
 
 	/*
@@ -273,10 +259,22 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	 * to work in practice.
 	 */
 	case TYPE_POWERSAVER:
-		do_powersaver(&longhaul, clock_ratio_index);
+		do_powersaver(cx->address, clock_ratio_index);
 		break;
 	}
 
+	/* Enable bus master arbitration */
+	if (pr->flags.bm_check) {
+		acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0,
+				  ACPI_MTX_DO_NOT_LOCK);
+	}
+
+	outb(pic2_mask,0xA1);	/* restore mask */
+	outb(pic1_mask,0x21);
+
+	local_irq_restore(flags);
+	preempt_enable();
+
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 }
 
@@ -324,9 +322,11 @@ static int guess_fsb(void)
 static int __init longhaul_get_ranges(void)
 {
 	unsigned long invalue;
-	unsigned int multipliers[32]= {
-		50,30,40,100,55,35,45,95,90,70,80,60,120,75,85,65,
-		-1,110,120,-1,135,115,125,105,130,150,160,140,-1,155,-1,145 };
+	unsigned int ezra_t_multipliers[32]= {
+			90,  30,  40, 100,  55,  35,  45,  95,
+			50,  70,  80,  60, 120,  75,  85,  65,
+			-1, 110, 120,  -1, 135, 115, 125, 105,
+			130, 150, 160, 140,  -1, 155,  -1, 145 };
 	unsigned int j, k = 0;
 	union msr_longhaul longhaul;
 	unsigned long lo, hi;
@@ -355,13 +355,13 @@ static int __init longhaul_get_ranges(void)
 			invalue = longhaul.bits.MaxMHzBR;
 			if (longhaul.bits.MaxMHzBR4)
 				invalue += 16;
-			maxmult=multipliers[invalue];
+			maxmult=ezra_t_multipliers[invalue];
 
 			invalue = longhaul.bits.MinMHzBR;
 			if (longhaul.bits.MinMHzBR4 == 1)
 				minmult = 30;
 			else
-				minmult = multipliers[invalue];
+				minmult = ezra_t_multipliers[invalue];
 			fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB];
 			break;
 		}
@@ -527,6 +527,18 @@ static unsigned int longhaul_get(unsigned int cpu)
 	return calc_speed(longhaul_get_cpu_mult());
 }
 
+static acpi_status longhaul_walk_callback(acpi_handle obj_handle,
+					  u32 nesting_level,
+					  void *context, void **return_value)
+{
+	struct acpi_device *d;
+
+	if ( acpi_bus_get_device(obj_handle, &d) ) {
+		return 0;
+	}
+	*return_value = (void *)acpi_driver_data(d);
+	return 1;
+}
 
 static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 {
@@ -534,6 +546,15 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	char *cpuname=NULL;
 	int ret;
 
+	/* Check ACPI support for C3 state */
+	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
+			 &longhaul_walk_callback, NULL, (void *)&pr);
+	if (pr == NULL) goto err_acpi;
+
+	cx = &pr->power.states[ACPI_STATE_C3];
+	if (cx->address == 0 || cx->latency > 1000) goto err_acpi;
+
+	/* Now check what we have on this motherboard */
 	switch (c->x86_model) {
 	case 6:
 		cpu_model = CPU_SAMUEL;
@@ -634,6 +655,10 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	cpufreq_frequency_table_get_attr(longhaul_table, policy->cpu);
 
 	return 0;
+
+err_acpi:
+	printk(KERN_ERR PFX "No ACPI support for CPU frequency changes.\n");
+	return -ENODEV;
 }
 
 static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy)
@@ -666,6 +691,18 @@ static int __init longhaul_init(void)
 	if (c->x86_vendor != X86_VENDOR_CENTAUR || c->x86 != 6)
 		return -ENODEV;
 
+#ifdef CONFIG_SMP
+	if (num_online_cpus() > 1) {
+		return -ENODEV;
+		printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n");
+	}
+#endif
+#ifdef CONFIG_X86_IO_APIC
+	if (cpu_has_apic) {
+		printk(KERN_ERR PFX "APIC detected. Longhaul is currently broken in this configuration.\n");
+		return -ENODEV;
+	}
+#endif
 	switch (c->x86_model) {
 	case 6 ... 9:
 		return cpufreq_register_driver(&longhaul_driver);
@@ -699,6 +736,6 @@ MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>");
 MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors.");
 MODULE_LICENSE ("GPL");
 
-module_init(longhaul_init);
+late_initcall(longhaul_init);
 module_exit(longhaul_exit);
 
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 5f03b9e524d..4c73a676366 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -32,32 +32,38 @@
 
 extern void __init efi_memmap_walk_uc(efi_freemem_callback_t, void *);
 
-#define MAX_UNCACHED_GRANULES	5
-static int allocated_granules;
+struct uncached_pool {
+	struct gen_pool *pool;
+	struct mutex add_chunk_mutex;	/* serialize adding a converted chunk */
+	int nchunks_added;		/* #of converted chunks added to pool */
+	atomic_t status;		/* smp called function's return status*/
+};
+
+#define MAX_CONVERTED_CHUNKS_PER_NODE	2
 
-struct gen_pool *uncached_pool[MAX_NUMNODES];
+struct uncached_pool uncached_pools[MAX_NUMNODES];
 
 
 static void uncached_ipi_visibility(void *data)
 {
 	int status;
+	struct uncached_pool *uc_pool = (struct uncached_pool *)data;
 
 	status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL);
 	if ((status != PAL_VISIBILITY_OK) &&
 	    (status != PAL_VISIBILITY_OK_REMOTE_NEEDED))
-		printk(KERN_DEBUG "pal_prefetch_visibility() returns %i on "
-		       "CPU %i\n", status, raw_smp_processor_id());
+		atomic_inc(&uc_pool->status);
 }
 
 
 static void uncached_ipi_mc_drain(void *data)
 {
 	int status;
+	struct uncached_pool *uc_pool = (struct uncached_pool *)data;
 
 	status = ia64_pal_mc_drain();
-	if (status)
-		printk(KERN_WARNING "ia64_pal_mc_drain() failed with %i on "
-		       "CPU %i\n", status, raw_smp_processor_id());
+	if (status != PAL_STATUS_SUCCESS)
+		atomic_inc(&uc_pool->status);
 }
 
 
@@ -70,21 +76,34 @@ static void uncached_ipi_mc_drain(void *data)
  * This is accomplished by first allocating a granule of cached memory pages
  * and then converting them to uncached memory pages.
  */
-static int uncached_add_chunk(struct gen_pool *pool, int nid)
+static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 {
 	struct page *page;
-	int status, i;
+	int status, i, nchunks_added = uc_pool->nchunks_added;
 	unsigned long c_addr, uc_addr;
 
-	if (allocated_granules >= MAX_UNCACHED_GRANULES)
+	if (mutex_lock_interruptible(&uc_pool->add_chunk_mutex) != 0)
+		return -1;	/* interrupted by a signal */
+
+	if (uc_pool->nchunks_added > nchunks_added) {
+		/* someone added a new chunk while we were waiting */
+		mutex_unlock(&uc_pool->add_chunk_mutex);
+		return 0;
+	}
+
+	if (uc_pool->nchunks_added >= MAX_CONVERTED_CHUNKS_PER_NODE) {
+		mutex_unlock(&uc_pool->add_chunk_mutex);
 		return -1;
+	}
 
 	/* attempt to allocate a granule's worth of cached memory pages */
 
 	page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
-	if (!page)
+	if (!page) {
+		mutex_unlock(&uc_pool->add_chunk_mutex);
 		return -1;
+	}
 
 	/* convert the memory pages from cached to uncached */
 
@@ -102,11 +121,14 @@ static int uncached_add_chunk(struct gen_pool *pool, int nid)
 	flush_tlb_kernel_range(uc_addr, uc_adddr + IA64_GRANULE_SIZE);
 
 	status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL);
-	if (!status) {
-		status = smp_call_function(uncached_ipi_visibility, NULL, 0, 1);
-		if (status)
+	if (status == PAL_VISIBILITY_OK_REMOTE_NEEDED) {
+		atomic_set(&uc_pool->status, 0);
+		status = smp_call_function(uncached_ipi_visibility, uc_pool,
+					   0, 1);
+		if (status || atomic_read(&uc_pool->status))
 			goto failed;
-	}
+	} else if (status != PAL_VISIBILITY_OK)
+		goto failed;
 
 	preempt_disable();
 
@@ -120,20 +142,24 @@ static int uncached_add_chunk(struct gen_pool *pool, int nid)
 
 	preempt_enable();
 
-	ia64_pal_mc_drain();
-	status = smp_call_function(uncached_ipi_mc_drain, NULL, 0, 1);
-	if (status)
+	status = ia64_pal_mc_drain();
+	if (status != PAL_STATUS_SUCCESS)
+		goto failed;
+	atomic_set(&uc_pool->status, 0);
+	status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 0, 1);
+	if (status || atomic_read(&uc_pool->status))
 		goto failed;
 
 	/*
 	 * The chunk of memory pages has been converted to uncached so now we
 	 * can add it to the pool.
 	 */
-	status = gen_pool_add(pool, uc_addr, IA64_GRANULE_SIZE, nid);
+	status = gen_pool_add(uc_pool->pool, uc_addr, IA64_GRANULE_SIZE, nid);
 	if (status)
 		goto failed;
 
-	allocated_granules++;
+	uc_pool->nchunks_added++;
+	mutex_unlock(&uc_pool->add_chunk_mutex);
 	return 0;
 
 	/* failed to convert or add the chunk so give it back to the kernel */
@@ -142,6 +168,7 @@ failed:
 		ClearPageUncached(&page[i]);
 
 	free_pages(c_addr, IA64_GRANULE_SHIFT-PAGE_SHIFT);
+	mutex_unlock(&uc_pool->add_chunk_mutex);
 	return -1;
 }
 
@@ -158,7 +185,7 @@ failed:
 unsigned long uncached_alloc_page(int starting_nid)
 {
 	unsigned long uc_addr;
-	struct gen_pool *pool;
+	struct uncached_pool *uc_pool;
 	int nid;
 
 	if (unlikely(starting_nid >= MAX_NUMNODES))
@@ -171,14 +198,14 @@ unsigned long uncached_alloc_page(int starting_nid)
 	do {
 		if (!node_online(nid))
 			continue;
-		pool = uncached_pool[nid];
-		if (pool == NULL)
+		uc_pool = &uncached_pools[nid];
+		if (uc_pool->pool == NULL)
 			continue;
 		do {
-			uc_addr = gen_pool_alloc(pool, PAGE_SIZE);
+			uc_addr = gen_pool_alloc(uc_pool->pool, PAGE_SIZE);
 			if (uc_addr != 0)
 				return uc_addr;
-		} while (uncached_add_chunk(pool, nid) == 0);
+		} while (uncached_add_chunk(uc_pool, nid) == 0);
 
 	} while ((nid = (nid + 1) % MAX_NUMNODES) != starting_nid);
 
@@ -197,7 +224,7 @@ EXPORT_SYMBOL(uncached_alloc_page);
 void uncached_free_page(unsigned long uc_addr)
 {
 	int nid = paddr_to_nid(uc_addr - __IA64_UNCACHED_OFFSET);
-	struct gen_pool *pool = uncached_pool[nid];
+	struct gen_pool *pool = uncached_pools[nid].pool;
 
 	if (unlikely(pool == NULL))
 		return;
@@ -224,7 +251,7 @@ static int __init uncached_build_memmap(unsigned long uc_start,
 					unsigned long uc_end, void *arg)
 {
 	int nid = paddr_to_nid(uc_start - __IA64_UNCACHED_OFFSET);
-	struct gen_pool *pool = uncached_pool[nid];
+	struct gen_pool *pool = uncached_pools[nid].pool;
 	size_t size = uc_end - uc_start;
 
 	touch_softlockup_watchdog();
@@ -242,7 +269,8 @@ static int __init uncached_init(void)
 	int nid;
 
 	for_each_online_node(nid) {
-		uncached_pool[nid] = gen_pool_create(PAGE_SHIFT, nid);
+		uncached_pools[nid].pool = gen_pool_create(PAGE_SHIFT, nid);
+		mutex_init(&uncached_pools[nid].add_chunk_mutex);
 	}
 
 	efi_memmap_walk_uc(uncached_build_memmap, NULL);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index bc1088d9b37..b3df613ae4e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -284,39 +284,69 @@ EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
  *                          SYSFS INTERFACE                          *
  *********************************************************************/
 
+static struct cpufreq_governor *__find_governor(const char *str_governor)
+{
+	struct cpufreq_governor *t;
+
+	list_for_each_entry(t, &cpufreq_governor_list, governor_list)
+		if (!strnicmp(str_governor,t->name,CPUFREQ_NAME_LEN))
+			return t;
+
+	return NULL;
+}
+
 /**
  * cpufreq_parse_governor - parse a governor string
  */
 static int cpufreq_parse_governor (char *str_governor, unsigned int *policy,
 				struct cpufreq_governor **governor)
 {
+	int err = -EINVAL;
+
 	if (!cpufreq_driver)
-		return -EINVAL;
+		goto out;
+
 	if (cpufreq_driver->setpolicy) {
 		if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_PERFORMANCE;
-			return 0;
+			err = 0;
 		} else if (!strnicmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_POWERSAVE;
-			return 0;
+			err = 0;
 		}
-		return -EINVAL;
-	} else {
+	} else if (cpufreq_driver->target) {
 		struct cpufreq_governor *t;
+
 		mutex_lock(&cpufreq_governor_mutex);
-		if (!cpufreq_driver || !cpufreq_driver->target)
-			goto out;
-		list_for_each_entry(t, &cpufreq_governor_list, governor_list) {
-			if (!strnicmp(str_governor,t->name,CPUFREQ_NAME_LEN)) {
-				*governor = t;
+
+		t = __find_governor(str_governor);
+
+		if (t == NULL) {
+			char *name = kasprintf(GFP_KERNEL, "cpufreq_%s", str_governor);
+
+			if (name) {
+				int ret;
+
 				mutex_unlock(&cpufreq_governor_mutex);
-				return 0;
+				ret = request_module(name);
+				mutex_lock(&cpufreq_governor_mutex);
+
+				if (ret == 0)
+					t = __find_governor(str_governor);
 			}
+
+			kfree(name);
 		}
-out:
+
+		if (t != NULL) {
+			*governor = t;
+			err = 0;
+		}
+
 		mutex_unlock(&cpufreq_governor_mutex);
 	}
-	return -EINVAL;
+  out:
+	return err;
 }
 
 
@@ -1265,23 +1295,21 @@ static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
 
 int cpufreq_register_governor(struct cpufreq_governor *governor)
 {
-	struct cpufreq_governor *t;
+	int err;
 
 	if (!governor)
 		return -EINVAL;
 
 	mutex_lock(&cpufreq_governor_mutex);
 
-	list_for_each_entry(t, &cpufreq_governor_list, governor_list) {
-		if (!strnicmp(governor->name,t->name,CPUFREQ_NAME_LEN)) {
-			mutex_unlock(&cpufreq_governor_mutex);
-			return -EBUSY;
-		}
+	err = -EBUSY;
+	if (__find_governor(governor->name) == NULL) {
+		err = 0;
+		list_add(&governor->governor_list, &cpufreq_governor_list);
 	}
-	list_add(&governor->governor_list, &cpufreq_governor_list);
 
 	mutex_unlock(&cpufreq_governor_mutex);
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_governor);
 
@@ -1343,6 +1371,11 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli
 
 	memcpy(&policy->cpuinfo, &data->cpuinfo, sizeof(struct cpufreq_cpuinfo));
 
+	if (policy->min > data->min && policy->min > policy->max) {
+		ret = -EINVAL;
+		goto error_out;
+	}
+
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(policy);
 	if (ret)
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index baf5ae51348..c9d419703cf 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -638,9 +638,6 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 	if (task->tk_status < 0) {
 		/* RPC error: Re-insert for retransmission */
 		timeout = 10 * HZ;
-	} else if (block->b_done) {
-		/* Block already removed, kill it for real */
-		timeout = 0;
 	} else {
 		/* Call was successful, now wait for client callback */
 		timeout = 60 * HZ;
@@ -709,13 +706,10 @@ nlmsvc_retry_blocked(void)
 			break;
 	        if (time_after(block->b_when,jiffies))
 			break;
-		dprintk("nlmsvc_retry_blocked(%p, when=%ld, done=%d)\n",
-			block, block->b_when, block->b_done);
+		dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
+			block, block->b_when);
 		kref_get(&block->b_count);
-		if (block->b_done)
-			nlmsvc_unlink_block(block);
-		else
-			nlmsvc_grant_blocked(block);
+		nlmsvc_grant_blocked(block);
 		nlmsvc_release_block(block);
 	}
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 19b98ca468e..86b3169c8ca 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -51,7 +51,7 @@ char *nfs_path(const char *base, const struct dentry *dentry,
 		namelen = dentry->d_name.len;
 		buflen -= namelen + 1;
 		if (buflen < 0)
-			goto Elong;
+			goto Elong_unlock;
 		end -= namelen;
 		memcpy(end, dentry->d_name.name, namelen);
 		*--end = '/';
@@ -68,6 +68,8 @@ char *nfs_path(const char *base, const struct dentry *dentry,
 	end -= namelen;
 	memcpy(end, base, namelen);
 	return end;
+Elong_unlock:
+	spin_unlock(&dcache_lock);
 Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 52bf634260a..65c0c5b3235 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -63,7 +63,7 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 	return p;
 }
 
-void nfs_readdata_free(struct nfs_read_data *p)
+static void nfs_readdata_free(struct nfs_read_data *p)
 {
 	if (p && (p->pagevec != &p->page_array[0]))
 		kfree(p->pagevec);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 86bac6a5008..50774991f8d 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -137,7 +137,7 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
 	return p;
 }
 
-void nfs_writedata_free(struct nfs_write_data *p)
+static void nfs_writedata_free(struct nfs_write_data *p)
 {
 	if (p && (p->pagevec != &p->page_array[0]))
 		kfree(p->pagevec);
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index aa4fe905bb4..0d92c468d55 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -123,7 +123,6 @@ struct nlm_block {
 	unsigned int		b_id;		/* block id */
 	unsigned char		b_queued;	/* re-queued */
 	unsigned char		b_granted;	/* VFS granted lock */
-	unsigned char		b_done;		/* callback complete */
 	struct nlm_file *	b_file;		/* file in question */
 };
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 55ea853d57b..247434553ae 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -476,10 +476,9 @@ static inline int nfs_wb_page(struct inode *inode, struct page* page)
 }
 
 /*
- * Allocate and free nfs_write_data structures
+ * Allocate nfs_write_data structures
  */
 extern struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount);
-extern void nfs_writedata_free(struct nfs_write_data *p);
 
 /*
  * linux/fs/nfs/read.c
@@ -491,10 +490,9 @@ extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern void nfs_readdata_release(void *data);
 
 /*
- * Allocate and free nfs_read_data structures
+ * Allocate nfs_read_data structures
  */
 extern struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount);
-extern void nfs_readdata_free(struct nfs_read_data *p);
 
 /*
  * linux/fs/nfs3proc.c
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index e8bbe8118de..840e47a4ccc 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -229,7 +229,7 @@ int			xprt_reserve_xprt(struct rpc_task *task);
 int			xprt_reserve_xprt_cong(struct rpc_task *task);
 int			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
-void			xprt_abort_transmit(struct rpc_task *task);
+void			xprt_end_transmit(struct rpc_task *task);
 int			xprt_adjust_timeout(struct rpc_rqst *req);
 void			xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 4ba271f892c..d6409e75721 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -921,26 +921,43 @@ call_transmit(struct rpc_task *task)
 	task->tk_status = xprt_prepare_transmit(task);
 	if (task->tk_status != 0)
 		return;
+	task->tk_action = call_transmit_status;
 	/* Encode here so that rpcsec_gss can use correct sequence number. */
 	if (rpc_task_need_encode(task)) {
-		task->tk_rqstp->rq_bytes_sent = 0;
+		BUG_ON(task->tk_rqstp->rq_bytes_sent != 0);
 		call_encode(task);
 		/* Did the encode result in an error condition? */
 		if (task->tk_status != 0)
-			goto out_nosend;
+			return;
 	}
-	task->tk_action = call_transmit_status;
 	xprt_transmit(task);
 	if (task->tk_status < 0)
 		return;
-	if (!task->tk_msg.rpc_proc->p_decode) {
-		task->tk_action = rpc_exit_task;
-		rpc_wake_up_task(task);
-	}
-	return;
-out_nosend:
-	/* release socket write lock before attempting to handle error */
-	xprt_abort_transmit(task);
+	/*
+	 * On success, ensure that we call xprt_end_transmit() before sleeping
+	 * in order to allow access to the socket to other RPC requests.
+	 */
+	call_transmit_status(task);
+	if (task->tk_msg.rpc_proc->p_decode != NULL)
+		return;
+	task->tk_action = rpc_exit_task;
+	rpc_wake_up_task(task);
+}
+
+/*
+ * 5a.	Handle cleanup after a transmission
+ */
+static void
+call_transmit_status(struct rpc_task *task)
+{
+	task->tk_action = call_status;
+	/*
+	 * Special case: if we've been waiting on the socket's write_space()
+	 * callback, then don't call xprt_end_transmit().
+	 */
+	if (task->tk_status == -EAGAIN)
+		return;
+	xprt_end_transmit(task);
 	rpc_task_force_reencode(task);
 }
 
@@ -992,18 +1009,7 @@ call_status(struct rpc_task *task)
 }
 
 /*
- * 6a.	Handle transmission errors.
- */
-static void
-call_transmit_status(struct rpc_task *task)
-{
-	if (task->tk_status != -EAGAIN)
-		rpc_task_force_reencode(task);
-	call_status(task);
-}
-
-/*
- * 6b.	Handle RPC timeout
+ * 6a.	Handle RPC timeout
  * 	We do not release the request slot, so we keep using the
  *	same XID for all retransmits.
  */
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index dc6cb93c883..a3bd2db2e02 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -667,10 +667,11 @@ rpc_mkdir(char *path, struct rpc_clnt *rpc_client)
 			RPCAUTH_info, RPCAUTH_EOF);
 	if (error)
 		goto err_depopulate;
+	dget(dentry);
 out:
 	mutex_unlock(&dir->i_mutex);
 	rpc_release_path(&nd);
-	return dget(dentry);
+	return dentry;
 err_depopulate:
 	rpc_depopulate(dentry);
 	__rpc_rmdir(dir, dentry);
@@ -731,10 +732,11 @@ rpc_mkpipe(char *path, void *private, struct rpc_pipe_ops *ops, int flags)
 	rpci->flags = flags;
 	rpci->ops = ops;
 	inode_dir_notify(dir, DN_CREATE);
+	dget(dentry);
 out:
 	mutex_unlock(&dir->i_mutex);
 	rpc_release_path(&nd);
-	return dget(dentry);
+	return dentry;
 err_dput:
 	dput(dentry);
 	dentry = ERR_PTR(-ENOMEM);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 313b68d892c..e8c2bc4977f 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -707,12 +707,9 @@ out_unlock:
 	return err;
 }
 
-void
-xprt_abort_transmit(struct rpc_task *task)
+void xprt_end_transmit(struct rpc_task *task)
 {
-	struct rpc_xprt	*xprt = task->tk_xprt;
-
-	xprt_release_write(xprt, task);
+	xprt_release_write(task->tk_xprt, task);
 }
 
 /**
@@ -761,8 +758,6 @@ void xprt_transmit(struct rpc_task *task)
 			task->tk_status = -ENOTCONN;
 		else if (!req->rq_received)
 			rpc_sleep_on(&xprt->pending, task, NULL, xprt_timer);
-
-		xprt->ops->release_xprt(xprt, task);
 		spin_unlock_bh(&xprt->transport_lock);
 		return;
 	}
@@ -772,18 +767,8 @@ void xprt_transmit(struct rpc_task *task)
 	 *	 schedq, and being picked up by a parallel run of rpciod().
 	 */
 	task->tk_status = status;
-
-	switch (status) {
-	case -ECONNREFUSED:
+	if (status == -ECONNREFUSED)
 		rpc_sleep_on(&xprt->sending, task, NULL, NULL);
-	case -EAGAIN:
-	case -ENOTCONN:
-		return;
-	default:
-		break;
-	}
-	xprt_release_write(xprt, task);
-	return;
 }
 
 static inline void do_xprt_reserve(struct rpc_task *task)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ee678ed13b6..441bd53f5ec 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -414,6 +414,33 @@ static int xs_tcp_send_request(struct rpc_task *task)
 }
 
 /**
+ * xs_tcp_release_xprt - clean up after a tcp transmission
+ * @xprt: transport
+ * @task: rpc task
+ *
+ * This cleans up if an error causes us to abort the transmission of a request.
+ * In this case, the socket may need to be reset in order to avoid confusing
+ * the server.
+ */
+static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
+{
+	struct rpc_rqst *req;
+
+	if (task != xprt->snd_task)
+		return;
+	if (task == NULL)
+		goto out_release;
+	req = task->tk_rqstp;
+	if (req->rq_bytes_sent == 0)
+		goto out_release;
+	if (req->rq_bytes_sent == req->rq_snd_buf.len)
+		goto out_release;
+	set_bit(XPRT_CLOSE_WAIT, &task->tk_xprt->state);
+out_release:
+	xprt_release_xprt(xprt, task);
+}
+
+/**
  * xs_close - close a socket
  * @xprt: transport
  *
@@ -1250,7 +1277,7 @@ static struct rpc_xprt_ops xs_udp_ops = {
 
 static struct rpc_xprt_ops xs_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
-	.release_xprt		= xprt_release_xprt,
+	.release_xprt		= xs_tcp_release_xprt,
 	.set_port		= xs_set_port,
 	.connect		= xs_connect,
 	.buf_alloc		= rpc_malloc,