Merge branch 'master'

.gitignore

@@ -0,0 +1,30 @@
+#
+# NOTE! Don't add files that are generated in specific
+# subdirectories here. Add them in the ".gitignore" file
+# in that subdirectory instead.
+#
+# Normal rules
+#
+.*
+*.o
+*.a
+*.s
+*.ko
+*.mod.c
+
+#
+# Top-level generic files
+#
+vmlinux*
+System.map
+Module.symvers
+
+#
+# Generated include files
+#
+include/asm
+include/config
+include/linux/autoconf.h
+include/linux/compile.h
+include/linux/version.h
+

Documentation/block/biodoc.txt

@@ -906,9 +906,20 @@ Aside:
 
 
 4. The I/O scheduler
-I/O schedulers are now per queue. They should be runtime switchable and modular
-but aren't yet. Jens has most bits to do this, but the sysfs implementation is
-missing.
+I/O scheduler, a.k.a. elevator, is implemented in two layers.  Generic dispatch
+queue and specific I/O schedulers.  Unless stated otherwise, elevator is used
+to refer to both parts and I/O scheduler to specific I/O schedulers.
+
+Block layer implements generic dispatch queue in ll_rw_blk.c and elevator.c.
+The generic dispatch queue is responsible for properly ordering barrier
+requests, requeueing, handling non-fs requests and all other subtleties.
+
+Specific I/O schedulers are responsible for ordering normal filesystem
+requests.  They can also choose to delay certain requests to improve
+throughput or whatever purpose.  As the plural form indicates, there are
+multiple I/O schedulers.  They can be built as modules but at least one should
+be built inside the kernel.  Each queue can choose different one and can also
+change to another one dynamically.
 
 A block layer call to the i/o scheduler follows the convention elv_xxx(). This
 calls elevator_xxx_fn in the elevator switch (drivers/block/elevator.c). Oh,
@@ -921,44 +932,36 @@ keeping work.
 The functions an elevator may implement are: (* are mandatory)
 elevator_merge_fn		called to query requests for merge with a bio
 
-elevator_merge_req_fn		" " "  with another request
+elevator_merge_req_fn		called when two requests get merged. the one
+				which gets merged into the other one will be
+				never seen by I/O scheduler again. IOW, after
+				being merged, the request is gone.
 
 elevator_merged_fn		called when a request in the scheduler has been
 				involved in a merge. It is used in the deadline
 				scheduler for example, to reposition the request
 				if its sorting order has changed.
 
-*elevator_next_req_fn		returns the next scheduled request, or NULL
-				if there are none (or none are ready).
+elevator_dispatch_fn		fills the dispatch queue with ready requests.
+				I/O schedulers are free to postpone requests by
+				not filling the dispatch queue unless @force
+				is non-zero.  Once dispatched, I/O schedulers
+				are not allowed to manipulate the requests -
+				they belong to generic dispatch queue.
 
-*elevator_add_req_fn		called to add a new request into the scheduler
+elevator_add_req_fn		called to add a new request into the scheduler
 
 elevator_queue_empty_fn		returns true if the merge queue is empty.
 				Drivers shouldn't use this, but rather check
 				if elv_next_request is NULL (without losing the
 				request if one exists!)
 
-elevator_remove_req_fn		This is called when a driver claims ownership of
-				the target request - it now belongs to the
-				driver. It must not be modified or merged.
-				Drivers must not lose the request! A subsequent
-				call of elevator_next_req_fn must  return the
-				_next_ request.
-
-elevator_requeue_req_fn		called to add a request to the scheduler. This
-				is used when the request has alrnadebeen
-				returned by elv_next_request, but hasn't
-				completed. If this is not implemented then
-				elevator_add_req_fn is called instead.
-
 elevator_former_req_fn
 elevator_latter_req_fn		These return the request before or after the
 				one specified in disk sort order. Used by the
 				block layer to find merge possibilities.
 
-elevator_completed_req_fn	called when a request is completed. This might
-				come about due to being merged with another or
-				when the device completes the request.
+elevator_completed_req_fn	called when a request is completed.
 
 elevator_may_queue_fn		returns true if the scheduler wants to allow the
 				current context to queue a new request even if
@@ -967,13 +970,33 @@ elevator_may_queue_fn		returns true if the scheduler wants to allow the
 
 elevator_set_req_fn
 elevator_put_req_fn		Must be used to allocate and free any elevator
-				specific storate for a request.
+				specific storage for a request.
+
+elevator_activate_req_fn	Called when device driver first sees a request.
+				I/O schedulers can use this callback to
+				determine when actual execution of a request
+				starts.
+elevator_deactivate_req_fn	Called when device driver decides to delay
+				a request by requeueing it.
 
 elevator_init_fn
 elevator_exit_fn		Allocate and free any elevator specific storage
 				for a queue.
 
-4.2 I/O scheduler implementation
+4.2 Request flows seen by I/O schedulers
+All requests seens by I/O schedulers strictly follow one of the following three
+flows.
+
+ set_req_fn ->
+
+ i.   add_req_fn -> (merged_fn ->)* -> dispatch_fn -> activate_req_fn ->
+      (deactivate_req_fn -> activate_req_fn ->)* -> completed_req_fn
+ ii.  add_req_fn -> (merged_fn ->)* -> merge_req_fn
+ iii. [none]
+
+ -> put_req_fn
+
+4.3 I/O scheduler implementation
 The generic i/o scheduler algorithm attempts to sort/merge/batch requests for
 optimal disk scan and request servicing performance (based on generic
 principles and device capabilities), optimized for:
@@ -993,18 +1016,7 @@ request in sort order to prevent binary tree lookups.
 This arrangement is not a generic block layer characteristic however, so
 elevators may implement queues as they please.
 
-ii. Last merge hint
-The last merge hint is part of the generic queue layer. I/O schedulers must do
-some management on it. For the most part, the most important thing is to make
-sure q->last_merge is cleared (set to NULL) when the request on it is no longer
-a candidate for merging (for example if it has been sent to the driver).
-
-The last merge performed is cached as a hint for the subsequent request. If
-sequential data is being submitted, the hint is used to perform merges without
-any scanning. This is not sufficient when there are multiple processes doing
-I/O though, so a "merge hash" is used by some schedulers.
-
-iii. Merge hash
+ii. Merge hash
 AS and deadline use a hash table indexed by the last sector of a request. This
 enables merging code to quickly look up "back merge" candidates, even when
 multiple I/O streams are being performed at once on one disk.
@@ -1013,29 +1025,8 @@ multiple I/O streams are being performed at once on one disk.
 are far less common than "back merges" due to the nature of most I/O patterns.
 Front merges are handled by the binary trees in AS and deadline schedulers.
 
-iv. Handling barrier cases
-A request with flags REQ_HARDBARRIER or REQ_SOFTBARRIER must not be ordered
-around. That is, they must be processed after all older requests, and before
-any newer ones. This includes merges!
-
-In AS and deadline schedulers, barriers have the effect of flushing the reorder
-queue. The performance cost of this will vary from nothing to a lot depending
-on i/o patterns and device characteristics. Obviously they won't improve
-performance, so their use should be kept to a minimum.
-
-v. Handling insertion position directives
-A request may be inserted with a position directive. The directives are one of
-ELEVATOR_INSERT_BACK, ELEVATOR_INSERT_FRONT, ELEVATOR_INSERT_SORT.
-
-ELEVATOR_INSERT_SORT is a general directive for non-barrier requests.
-ELEVATOR_INSERT_BACK is used to insert a barrier to the back of the queue.
-ELEVATOR_INSERT_FRONT is used to insert a barrier to the front of the queue, and
-overrides the ordering requested by any previous barriers. In practice this is
-harmless and required, because it is used for SCSI requeueing. This does not
-require flushing the reorder queue, so does not impose a performance penalty.
-
-vi. Plugging the queue to batch requests in anticipation of opportunities for
-  merge/sort optimizations
+iii. Plugging the queue to batch requests in anticipation of opportunities for
+     merge/sort optimizations
 
 This is just the same as in 2.4 so far, though per-device unplugging
 support is anticipated for 2.5. Also with a priority-based i/o scheduler,
@@ -1069,7 +1060,7 @@ Aside:
   blk_kick_queue() to unplug a specific queue (right away ?)
   or optionally, all queues, is in the plan.
 
-4.3 I/O contexts
+4.4 I/O contexts
 I/O contexts provide a dynamically allocated per process data area. They may
 be used in I/O schedulers, and in the block layer (could be used for IO statis,
 priorities for example). See *io_context in drivers/block/ll_rw_blk.c, and

Documentation/networking/bonding.txt

@@ -777,7 +777,7 @@ doing so is the same as described in the "Configuring Multiple Bonds
 Manually" section, below.
 
 	NOTE: It has been observed that some Red Hat supplied kernels
-are apparently unable to rename modules at load time (the "-obonding1"
+are apparently unable to rename modules at load time (the "-o bond1"
 part).  Attempts to pass that option to modprobe will produce an
 "Operation not permitted" error.  This has been reported on some
 Fedora Core kernels, and has been seen on RHEL 4 as well.  On kernels
@@ -883,7 +883,8 @@ the above does not work, and the second bonding instance never sees
 its options.  In that case, the second options line can be substituted
 as follows:
 
-install bonding1 /sbin/modprobe bonding -obond1 mode=balance-alb miimon=50
+install bond1 /sbin/modprobe --ignore-install bonding -o bond1 \
+	mode=balance-alb miimon=50
 
 	This may be repeated any number of times, specifying a new and
 unique name in place of bond1 for each subsequent instance.

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 14
-EXTRAVERSION =-rc4
+EXTRAVERSION =
 NAME=Affluent Albatross
 
 # *DOCUMENTATION*
@@ -334,7 +334,7 @@ KALLSYMS	= scripts/kallsyms
 PERL		= perl
 CHECK		= sparse
 
-CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ $(CF)
+CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ -Wbitwise $(CF)
 MODFLAGS	= -DMODULE
 CFLAGS_MODULE   = $(MODFLAGS)
 AFLAGS_MODULE   = $(MODFLAGS)
@@ -372,7 +372,7 @@ export MODVERDIR := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_ve
 # Files to ignore in find ... statements
 
 RCS_FIND_IGNORE := \( -name SCCS -o -name BitKeeper -o -name .svn -o -name CVS -o -name .pc -o -name .hg \) -prune -o
-RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn --exclude CVS --exclude .pc --exclude .hg
+export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn --exclude CVS --exclude .pc --exclude .hg
 
 # ===========================================================================
 # Rules shared between *config targets and build targets

arch/alpha/kernel/pci-noop.c

@@ -154,7 +154,7 @@ pci_dma_supported(struct pci_dev *hwdev, dma_addr_t mask)
 
 void *
 dma_alloc_coherent(struct device *dev, size_t size,
-		   dma_addr_t *dma_handle, int gfp)
+		   dma_addr_t *dma_handle, gfp_t gfp)
 {
 	void *ret;
 

arch/alpha/kernel/pci_iommu.c

@@ -397,7 +397,7 @@ pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_addrp)
 {
 	void *cpu_addr;
 	long order = get_order(size);
-	int gfp = GFP_ATOMIC;
+	gfp_t gfp = GFP_ATOMIC;
 
 try_again:
 	cpu_addr = (void *)__get_free_pages(gfp, order);

arch/arm/mach-integrator/impd1.c

@@ -67,7 +67,7 @@ static void impd1_setvco(struct clk *clk, struct icst525_vco vco)
 	}
 	writel(0, impd1->base + IMPD1_LOCK);
 
-#if DEBUG
+#ifdef DEBUG
 	vco.v = val & 0x1ff;
 	vco.r = (val >> 9) & 0x7f;
 	vco.s = (val >> 16) & 7;
@@ -427,17 +427,18 @@ static int impd1_probe(struct lm_device *dev)
 	return ret;
 }
 
+static int impd1_remove_one(struct device *dev, void *data)
+{
+	device_unregister(dev);
+	return 0;
+}
+
 static void impd1_remove(struct lm_device *dev)
 {
 	struct impd1_module *impd1 = lm_get_drvdata(dev);
-	struct list_head *l, *n;
 	int i;
 
-	list_for_each_safe(l, n, &dev->dev.children) {
-		struct device *d = list_to_dev(l);
-
-		device_unregister(d);
-	}
+	device_for_each_child(&dev->dev, NULL, impd1_remove_one);
 
 	for (i = 0; i < ARRAY_SIZE(impd1->vcos); i++)
 		clk_unregister(&impd1->vcos[i]);

arch/arm/mach-pxa/corgi_lcd.c

@@ -488,6 +488,7 @@ static int is_pxafb_device(struct device * dev, void * data)
 
 unsigned long spitz_get_hsync_len(void)
 {
+#ifdef CONFIG_FB_PXA
 	if (!spitz_pxafb_dev) {
 		spitz_pxafb_dev = bus_find_device(&platform_bus_type, NULL, NULL, is_pxafb_device);
 		if (!spitz_pxafb_dev)
@@ -496,6 +497,7 @@ unsigned long spitz_get_hsync_len(void)
 	if (!get_hsync_time)
 		get_hsync_time = symbol_get(pxafb_get_hsync_time);
 	if (!get_hsync_time)
+#endif
 		return 0;
 
 	return pxafb_get_hsync_time(spitz_pxafb_dev);

arch/arm/mach-pxa/generic.c

@@ -250,6 +250,25 @@ void __init pxa_set_i2c_info(struct i2c_pxa_platform_data *info)
 	i2c_device.dev.platform_data = info;
 }
 
+static struct resource i2s_resources[] = {
+	{
+		.start	= 0x40400000,
+		.end	= 0x40400083,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.start	= IRQ_I2S,
+		.end	= IRQ_I2S,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device i2s_device = {
+	.name		= "pxa2xx-i2s",
+	.id		= -1,
+	.resource	= i2c_resources,
+	.num_resources	= ARRAY_SIZE(i2s_resources),
+};
+
 static struct platform_device *devices[] __initdata = {
 	&pxamci_device,
 	&udc_device,
@@ -258,6 +277,7 @@ static struct platform_device *devices[] __initdata = {
 	&btuart_device,
 	&stuart_device,
 	&i2c_device,
+	&i2s_device,
 };
 
 static int __init pxa_init(void)

arch/arm/mach-s3c2410/clock.c

@@ -98,7 +98,10 @@ struct clk *clk_get(struct device *dev, const char *id)
 	struct clk *clk = ERR_PTR(-ENOENT);
 	int idno;
 
-	idno = (dev == NULL) ? -1 : to_platform_device(dev)->id;
+	if (dev == NULL || dev->bus != &platform_bus_type)
+		idno = -1;
+	else
+		idno = to_platform_device(dev)->id;
 
 	down(&clocks_sem);
 

arch/arm/mach-s3c2410/mach-bast.c

@@ -307,9 +307,9 @@ static void bast_nand_select(struct s3c2410_nand_set *set, int slot)
 }
 
 static struct s3c2410_platform_nand bast_nand_info = {
-	.tacls		= 40,
-	.twrph0		= 80,
-	.twrph1		= 80,
+	.tacls		= 30,
+	.twrph0		= 60,
+	.twrph1		= 60,
 	.nr_sets	= ARRAY_SIZE(bast_nand_sets),
 	.sets		= bast_nand_sets,
 	.select_chip	= bast_nand_select,

arch/arm/mm/consistent.c

@@ -75,7 +75,7 @@ static struct vm_region consistent_head = {
 };
 
 static struct vm_region *
-vm_region_alloc(struct vm_region *head, size_t size, int gfp)
+vm_region_alloc(struct vm_region *head, size_t size, gfp_t gfp)
 {
 	unsigned long addr = head->vm_start, end = head->vm_end - size;
 	unsigned long flags;
@@ -133,7 +133,7 @@ static struct vm_region *vm_region_find(struct vm_region *head, unsigned long ad
 #endif
 
 static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, int gfp,
+__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	    pgprot_t prot)
 {
 	struct page *page;
@@ -251,7 +251,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, int gfp,
  * virtual and bus address for that space.
  */
 void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, int gfp)
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
 			   pgprot_noncached(pgprot_kernel));
@@ -263,7 +263,7 @@ EXPORT_SYMBOL(dma_alloc_coherent);
  * dma_alloc_coherent above.
  */
 void *
-dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, int gfp)
+dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
 	return __dma_alloc(dev, size, handle, gfp,
 			   pgprot_writecombine(pgprot_kernel));

arch/arm/mm/proc-v6.S

@@ -55,7 +55,14 @@ ENTRY(cpu_v6_proc_init)
 	mov	pc, lr
 
 ENTRY(cpu_v6_proc_fin)
-	mov	pc, lr
+	stmfd	sp!, {lr}
+	cpsid	if				@ disable interrupts
+	bl	v6_flush_kern_cache_all
+	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
+	bic	r0, r0, #0x1000			@ ...i............
+	bic	r0, r0, #0x0006			@ .............ca.
+	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
+	ldmfd	sp!, {pc}
 
 /*
  *	cpu_v6_reset(loc)

arch/frv/mb93090-mb00/pci-dma-nommu.c

@@ -33,7 +33,7 @@ struct dma_alloc_record {
 static DEFINE_SPINLOCK(dma_alloc_lock);
 static LIST_HEAD(dma_alloc_list);
 
-void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, int gfp)
+void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t gfp)
 {
 	struct dma_alloc_record *new;
 	struct list_head *this = &dma_alloc_list;

arch/frv/mb93090-mb00/pci-dma.c

@@ -17,7 +17,7 @@
 #include <linux/highmem.h>
 #include <asm/io.h>
 
-void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, int gfp)
+void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t gfp)
 {
 	void *ret;
 

arch/frv/mm/dma-alloc.c

@@ -81,7 +81,7 @@ static int map_page(unsigned long va, unsigned long pa, pgprot_t prot)
  * portions of the kernel with single large page TLB entries, and
  * still get unique uncached pages for consistent DMA.
  */
-void *consistent_alloc(int gfp, size_t size, dma_addr_t *dma_handle)
+void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle)
 {
 	struct vm_struct *area;
 	unsigned long page, va, pa;

arch/i386/kernel/cpu/cpufreq/powernow-k8.c

@@ -44,7 +44,7 @@
 
 #define PFX "powernow-k8: "
 #define BFX PFX "BIOS error: "
-#define VERSION "version 1.50.3"
+#define VERSION "version 1.50.4"
 #include "powernow-k8.h"
 
 /* serialize freq changes  */
@@ -111,8 +111,8 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
 	u32 i = 0;
 
 	do {
-		if (i++ > 0x1000000) {
-			printk(KERN_ERR PFX "detected change pending stuck\n");
+		if (i++ > 10000) {
+			dprintk("detected change pending stuck\n");
 			return 1;
 		}
 		rdmsr(MSR_FIDVID_STATUS, lo, hi);
@@ -159,6 +159,7 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid)
 {
 	u32 lo;
 	u32 savevid = data->currvid;
+	u32 i = 0;
 
 	if ((fid & INVALID_FID_MASK) || (data->currvid & INVALID_VID_MASK)) {
 		printk(KERN_ERR PFX "internal error - overflow on fid write\n");
@@ -170,10 +171,13 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid)
 	dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n",
 		fid, lo, data->plllock * PLL_LOCK_CONVERSION);
 
-	wrmsr(MSR_FIDVID_CTL, lo, data->plllock * PLL_LOCK_CONVERSION);
-
-	if (query_current_values_with_pending_wait(data))
-		return 1;
+	do {
+		wrmsr(MSR_FIDVID_CTL, lo, data->plllock * PLL_LOCK_CONVERSION);
+		if (i++ > 100) {
+			printk(KERN_ERR PFX "internal error - pending bit very stuck - no further pstate changes possible\n");
+			return 1;
+		}			
+	} while (query_current_values_with_pending_wait(data));
 
 	count_off_irt(data);
 
@@ -197,6 +201,7 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid)
 {
 	u32 lo;
 	u32 savefid = data->currfid;
+	int i = 0;
 
 	if ((data->currfid & INVALID_FID_MASK) || (vid & INVALID_VID_MASK)) {
 		printk(KERN_ERR PFX "internal error - overflow on vid write\n");
@@ -208,10 +213,13 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid)
 	dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n",
 		vid, lo, STOP_GRANT_5NS);
 
-	wrmsr(MSR_FIDVID_CTL, lo, STOP_GRANT_5NS);
-
-	if (query_current_values_with_pending_wait(data))
-		return 1;
+	do {
+		wrmsr(MSR_FIDVID_CTL, lo, STOP_GRANT_5NS);
+                if (i++ > 100) {
+                        printk(KERN_ERR PFX "internal error - pending bit very stuck - no further pstate changes possible\n");
+                        return 1;
+                }
+	} while (query_current_values_with_pending_wait(data));
 
 	if (savefid != data->currfid) {
 		printk(KERN_ERR PFX "fid changed on vid trans, old 0x%x new 0x%x\n",

arch/ia64/hp/common/hwsw_iommu.c

@@ -71,7 +71,7 @@ hwsw_init (void)
 }
 
 void *
-hwsw_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, int flags)
+hwsw_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
 {
 	if (use_swiotlb(dev))
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);

arch/ia64/hp/common/sba_iommu.c

@@ -1076,7 +1076,7 @@ void sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size, int dir)
  * See Documentation/DMA-mapping.txt
  */
 void *
-sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, int flags)
+sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags)
 {
 	struct ioc *ioc;
 	void *addr;