Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

Documentation/devices.txt

@@ -94,6 +94,8 @@ Your cooperation is appreciated.
 		  9 = /dev/urandom	Faster, less secure random number gen.
 		 10 = /dev/aio		Asynchronous I/O notification interface
 		 11 = /dev/kmsg		Writes to this come out as printk's
+		 12 = /dev/oldmem	Used by crashdump kernels to access
+					the memory of the kernel that crashed.
 
   1 block	RAM disk
 		  0 = /dev/ram0		First RAM disk

Documentation/lockstat.txt

@@ -0,0 +1,120 @@
+
+LOCK STATISTICS
+
+- WHAT
+
+As the name suggests, it provides statistics on locks.
+
+- WHY
+
+Because things like lock contention can severely impact performance.
+
+- HOW
+
+Lockdep already has hooks in the lock functions and maps lock instances to
+lock classes. We build on that. The graph below shows the relation between
+the lock functions and the various hooks therein.
+
+        __acquire
+            |
+           lock _____
+            |        \
+            |    __contended
+            |         |
+            |       <wait>
+            | _______/
+            |/
+            |
+       __acquired
+            |
+            .
+          <hold>
+            .
+            |
+       __release
+            |
+         unlock
+
+lock, unlock	- the regular lock functions
+__*		- the hooks
+<> 		- states
+
+With these hooks we provide the following statistics:
+
+ con-bounces       - number of lock contention that involved x-cpu data
+ contentions       - number of lock acquisitions that had to wait
+ wait time min     - shortest (non-0) time we ever had to wait for a lock
+           max     - longest time we ever had to wait for a lock
+           total   - total time we spend waiting on this lock
+ acq-bounces       - number of lock acquisitions that involved x-cpu data
+ acquisitions      - number of times we took the lock
+ hold time min     - shortest (non-0) time we ever held the lock
+           max     - longest time we ever held the lock
+           total   - total time this lock was held
+
+From these number various other statistics can be derived, such as:
+
+ hold time average = hold time total / acquisitions
+
+These numbers are gathered per lock class, per read/write state (when
+applicable).
+
+It also tracks 4 contention points per class. A contention point is a call site
+that had to wait on lock acquisition.
+
+ - USAGE
+
+Look at the current lock statistics:
+
+( line numbers not part of actual output, done for clarity in the explanation
+  below )
+
+# less /proc/lock_stat
+
+01 lock_stat version 0.2
+02 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+03                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total
+04 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+05
+06               &inode->i_data.tree_lock-W:            15          21657           0.18     1093295.30 11547131054.85             58          10415           0.16          87.51        6387.60
+07               &inode->i_data.tree_lock-R:             0              0           0.00           0.00           0.00          23302         231198           0.25           8.45       98023.38
+08               --------------------------
+09                 &inode->i_data.tree_lock              0          [<ffffffff8027c08f>] add_to_page_cache+0x5f/0x190
+10
+11 ...............................................................................................................................................................................................
+12
+13                              dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
+14                              -----------
+15                              dcache_lock            180          [<ffffffff802c0d7e>] sys_getcwd+0x11e/0x230
+16                              dcache_lock            165          [<ffffffff802c002a>] d_alloc+0x15a/0x210
+17                              dcache_lock             33          [<ffffffff8035818d>] _atomic_dec_and_lock+0x4d/0x70
+18                              dcache_lock              1          [<ffffffff802beef8>] shrink_dcache_parent+0x18/0x130
+
+This excerpt shows the first two lock class statistics. Line 01 shows the
+output version - each time the format changes this will be updated. Line 02-04
+show the header with column descriptions. Lines 05-10 and 13-18 show the actual
+statistics. These statistics come in two parts; the actual stats separated by a
+short separator (line 08, 14) from the contention points.
+
+The first lock (05-10) is a read/write lock, and shows two lines above the
+short separator. The contention points don't match the column descriptors,
+they have two: contentions and [<IP>] symbol.
+
+
+View the top contending locks:
+
+# grep : /proc/lock_stat | head
+              &inode->i_data.tree_lock-W:            15          21657           0.18     1093295.30 11547131054.85             58          10415           0.16          87.51        6387.60
+              &inode->i_data.tree_lock-R:             0              0           0.00           0.00           0.00          23302         231198           0.25           8.45       98023.38
+                             dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
+                         &inode->i_mutex:           161            286 18446744073709       62882.54     1244614.55           3653          20598 18446744073709       62318.60     1693822.74
+                         &zone->lru_lock:            94             94           0.53           7.33          92.10           4366          32690           0.29          59.81       16350.06
+              &inode->i_data.i_mmap_lock:            79             79           0.40           3.77          53.03          11779          87755           0.28         116.93       29898.44
+                        &q->__queue_lock:            48             50           0.52          31.62          86.31            774          13131           0.17         113.08       12277.52
+                        &rq->rq_lock_key:            43             47           0.74          68.50         170.63           3706          33929           0.22         107.99       17460.62
+                      &rq->rq_lock_key#2:            39             46           0.75           6.68          49.03           2979          32292           0.17         125.17       17137.63
+                         tasklist_lock-W:            15             15           1.45          10.87          32.70           1201           7390           0.58          62.55       13648.47
+
+Clear the statistics:
+
+# echo 0 > /proc/lock_stat

Documentation/sysrq.txt

@@ -43,7 +43,7 @@ On x86   - You press the key combo 'ALT-SysRq-<command key>'. Note - Some
            keyboards may not have a key labeled 'SysRq'. The 'SysRq' key is
            also known as the 'Print Screen' key. Also some keyboards cannot
 	   handle so many keys being pressed at the same time, so you might
-	   have better luck with "press Alt", "press SysRq", "release Alt",
+	   have better luck with "press Alt", "press SysRq", "release SysRq",
 	   "press <command key>", release everything.
 
 On SPARC - You press 'ALT-STOP-<command key>', I believe.

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 23
-EXTRAVERSION =-rc8
+EXTRAVERSION =
 NAME = Arr Matey! A Hairy Bilge Rat!
 
 # *DOCUMENTATION*

arch/arm/kernel/bios32.c

@@ -338,7 +338,7 @@ pbus_assign_bus_resources(struct pci_bus *bus, struct pci_sys_data *root)
  * pcibios_fixup_bus - Called after each bus is probed,
  * but before its children are examined.
  */
-void __devinit pcibios_fixup_bus(struct pci_bus *bus)
+void pcibios_fixup_bus(struct pci_bus *bus)
 {
 	struct pci_sys_data *root = bus->sysdata;
 	struct pci_dev *dev;
@@ -419,7 +419,7 @@ void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 /*
  * Convert from Linux-centric to bus-centric addresses for bridge devices.
  */
-void __devinit
+void
 pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
 			 struct resource *res)
 {

arch/arm/mach-s3c2440/mach-osiris.c

@@ -276,7 +276,21 @@ static unsigned char pm_osiris_ctrl0;
 
 static int osiris_pm_suspend(struct sys_device *sd, pm_message_t state)
 {
+	unsigned int tmp;
+
 	pm_osiris_ctrl0 = __raw_readb(OSIRIS_VA_CTRL0);
+	tmp = pm_osiris_ctrl0 & ~OSIRIS_CTRL0_NANDSEL;
+
+	/* ensure correct NAND slot is selected on resume */
+	if ((pm_osiris_ctrl0 & OSIRIS_CTRL0_BOOT_INT) == 0)
+	        tmp |= 2;
+
+	__raw_writeb(tmp, OSIRIS_VA_CTRL0);
+
+	/* ensure that an nRESET is not generated on resume. */
+	s3c2410_gpio_setpin(S3C2410_GPA21, 1);
+	s3c2410_gpio_cfgpin(S3C2410_GPA21, S3C2410_GPA21_OUT);
+
 	return 0;
 }
 
@@ -285,6 +299,10 @@ static int osiris_pm_resume(struct sys_device *sd)
 	if (pm_osiris_ctrl0 & OSIRIS_CTRL0_FIX8)
 		__raw_writeb(OSIRIS_CTRL1_FIX8, OSIRIS_VA_CTRL1);
 
+	__raw_writeb(pm_osiris_ctrl0, OSIRIS_VA_CTRL0);
+
+	s3c2410_gpio_cfgpin(S3C2410_GPA21, S3C2410_GPA21_nRSTOUT);
+
 	return 0;
 }
 

arch/blackfin/kernel/bfin_gpio.c

@@ -84,6 +84,7 @@
 #include <linux/err.h>
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
+#include <asm/portmux.h>
 #include <linux/irq.h>
 
 #ifdef BF533_FAMILY
@@ -115,7 +116,11 @@ static struct gpio_port_t *gpio_bankb[gpio_bank(MAX_BLACKFIN_GPIOS)] = {
 };
 #endif
 
-static unsigned short reserved_map[gpio_bank(MAX_BLACKFIN_GPIOS)];
+static unsigned short reserved_gpio_map[gpio_bank(MAX_BLACKFIN_GPIOS)];
+static unsigned short reserved_peri_map[gpio_bank(MAX_BLACKFIN_GPIOS + 16)];
+char *str_ident = NULL;
+
+#define RESOURCE_LABEL_SIZE 16
 
 #ifdef CONFIG_PM
 static unsigned short wakeup_map[gpio_bank(MAX_BLACKFIN_GPIOS)];
@@ -143,22 +148,100 @@ inline int check_gpio(unsigned short gpio)
 	return 0;
 }
 
+static void set_label(unsigned short ident, const char *label)
+{
+
+	if (label && str_ident) {
+		strncpy(str_ident + ident * RESOURCE_LABEL_SIZE, label,
+			 RESOURCE_LABEL_SIZE);
+		str_ident[ident * RESOURCE_LABEL_SIZE +
+			 RESOURCE_LABEL_SIZE - 1] = 0;
+	}
+}
+
+static char *get_label(unsigned short ident)
+{
+	if (!str_ident)
+		return "UNKNOWN";
+
+	return (str_ident[ident * RESOURCE_LABEL_SIZE] ?
+		(str_ident + ident * RESOURCE_LABEL_SIZE) : "UNKNOWN");
+}
+
+static int cmp_label(unsigned short ident, const char *label)
+{
+	if (label && str_ident)
+		return strncmp(str_ident + ident * RESOURCE_LABEL_SIZE,
+				 label, strlen(label));
+	else
+		return -EINVAL;
+}
+
 #ifdef BF537_FAMILY
 static void port_setup(unsigned short gpio, unsigned short usage)
 {
-	if (usage == GPIO_USAGE) {
-		if (*port_fer[gpio_bank(gpio)] & gpio_bit(gpio))
-			printk(KERN_WARNING "bfin-gpio: Possible Conflict with Peripheral "
-			       "usage and GPIO %d detected!\n", gpio);
-		*port_fer[gpio_bank(gpio)] &= ~gpio_bit(gpio);
-	} else
-		*port_fer[gpio_bank(gpio)] |= gpio_bit(gpio);
-	SSYNC();
+	if (!check_gpio(gpio)) {
+		if (usage == GPIO_USAGE) {
+			*port_fer[gpio_bank(gpio)] &= ~gpio_bit(gpio);
+		} else
+			*port_fer[gpio_bank(gpio)] |= gpio_bit(gpio);
+		SSYNC();
+	}
 }
 #else
 # define port_setup(...)  do { } while (0)
 #endif
 
+#ifdef BF537_FAMILY
+
+#define PMUX_LUT_RES		0
+#define PMUX_LUT_OFFSET		1
+#define PMUX_LUT_ENTRIES	41
+#define PMUX_LUT_SIZE		2
+
+static unsigned short port_mux_lut[PMUX_LUT_ENTRIES][PMUX_LUT_SIZE] = {
+	{P_PPI0_D13, 11}, {P_PPI0_D14, 11}, {P_PPI0_D15, 11},
+	{P_SPORT1_TFS, 11}, {P_SPORT1_TSCLK, 11}, {P_SPORT1_DTPRI, 11},
+	{P_PPI0_D10, 10}, {P_PPI0_D11, 10}, {P_PPI0_D12, 10},
+	{P_SPORT1_RSCLK, 10}, {P_SPORT1_RFS, 10}, {P_SPORT1_DRPRI, 10},
+	{P_PPI0_D8, 9}, {P_PPI0_D9, 9}, {P_SPORT1_DRSEC, 9},
+	{P_SPORT1_DTSEC, 9}, {P_TMR2, 8}, {P_PPI0_FS3, 8}, {P_TMR3, 7},
+	{P_SPI0_SSEL4, 7}, {P_TMR4, 6}, {P_SPI0_SSEL5, 6}, {P_TMR5, 5},
+	{P_SPI0_SSEL6, 5}, {P_UART1_RX, 4}, {P_UART1_TX, 4}, {P_TMR6, 4},
+	{P_TMR7, 4}, {P_UART0_RX, 3}, {P_UART0_TX, 3}, {P_DMAR0, 3},
+	{P_DMAR1, 3}, {P_SPORT0_DTSEC, 1}, {P_SPORT0_DRSEC, 1},
+	{P_CAN0_RX, 1}, {P_CAN0_TX, 1}, {P_SPI0_SSEL7, 1},
+	{P_SPORT0_TFS, 0}, {P_SPORT0_DTPRI, 0}, {P_SPI0_SSEL2, 0},
+	{P_SPI0_SSEL3, 0}
+};
+
+static void portmux_setup(unsigned short per, unsigned short function)
+{
+	u16 y, muxreg, offset;
+
+	for (y = 0; y < PMUX_LUT_ENTRIES; y++) {
+		if (port_mux_lut[y][PMUX_LUT_RES] == per) {
+
+			/* SET PORTMUX REG */
+
+			offset = port_mux_lut[y][PMUX_LUT_OFFSET];
+			muxreg = bfin_read_PORT_MUX();
+
+			if (offset != 1) {
+				muxreg &= ~(1 << offset);
+			} else {
+				muxreg &= ~(3 << 1);
+			}
+
+			muxreg |= (function << offset);
+			bfin_write_PORT_MUX(muxreg);
+		}
+	}
+}
+
+#else
+# define portmux_setup(...)  do { } while (0)
+#endif
 
 static void default_gpio(unsigned short gpio)
 {
@@ -179,22 +262,15 @@ static void default_gpio(unsigned short gpio)
 
 static int __init bfin_gpio_init(void)
 {
-	int i;
-
-	printk(KERN_INFO "Blackfin GPIO Controller\n");
 
-	for (i = 0; i < MAX_BLACKFIN_GPIOS; i += GPIO_BANKSIZE)
-		reserved_map[gpio_bank(i)] = 0;
+	str_ident = kzalloc(RESOURCE_LABEL_SIZE * 256, GFP_KERNEL);
+	if (!str_ident)
+		return -ENOMEM;
 
-#if defined(BF537_FAMILY) && (defined(CONFIG_BFIN_MAC) || defined(CONFIG_BFIN_MAC_MODULE))
-# if defined(CONFIG_BFIN_MAC_RMII)
-	reserved_map[gpio_bank(PORT_H)] = 0xC373;
-# else
-	reserved_map[gpio_bank(PORT_H)] = 0xFFFF;
-# endif
-#endif
+	printk(KERN_INFO "Blackfin GPIO Controller\n");
 
 	return 0;
+
 }
 
 arch_initcall(bfin_gpio_init);
@@ -223,7 +299,7 @@ arch_initcall(bfin_gpio_init);
 void set_gpio_ ## name(unsigned short gpio, unsigned short arg) \
 { \
 	unsigned long flags; \
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio))); \
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio))); \
 	local_irq_save(flags); \
 	if (arg) \
 		gpio_bankb[gpio_bank(gpio)]->name |= gpio_bit(gpio); \
@@ -243,7 +319,7 @@ SET_GPIO(both)
 #define SET_GPIO_SC(name) \
 void set_gpio_ ## name(unsigned short gpio, unsigned short arg) \
 { \
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio))); \
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio))); \
 	if (arg) \
 		gpio_bankb[gpio_bank(gpio)]->name ## _set = gpio_bit(gpio); \
 	else \
@@ -258,7 +334,7 @@ SET_GPIO_SC(maskb)
 void set_gpio_data(unsigned short gpio, unsigned short arg)
 {
 	unsigned long flags;
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 	local_irq_save(flags);
 	if (arg)
 		gpio_bankb[gpio_bank(gpio)]->data_set = gpio_bit(gpio);
@@ -277,7 +353,7 @@ SET_GPIO_SC(data)
 void set_gpio_toggle(unsigned short gpio)
 {
 	unsigned long flags;
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 	local_irq_save(flags);
 	gpio_bankb[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
 	bfin_read_CHIPID();
@@ -286,7 +362,7 @@ void set_gpio_toggle(unsigned short gpio)
 #else
 void set_gpio_toggle(unsigned short gpio)
 {
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 	gpio_bankb[gpio_bank(gpio)]->toggle = gpio_bit(gpio);
 }
 #endif
@@ -350,7 +426,7 @@ unsigned short get_gpio_data(unsigned short gpio)
 {
 	unsigned long flags;
 	unsigned short ret;
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 	local_irq_save(flags);
 	ret = 0x01 & (gpio_bankb[gpio_bank(gpio)]->data >> gpio_sub_n(gpio));
 	bfin_read_CHIPID();
@@ -494,13 +570,14 @@ u32 gpio_pm_setup(void)
 			gpio_bank_saved[bank].dir   = gpio_bankb[bank]->dir;
 			gpio_bank_saved[bank].edge  = gpio_bankb[bank]->edge;
 			gpio_bank_saved[bank].both  = gpio_bankb[bank]->both;
-			gpio_bank_saved[bank].reserved = reserved_map[bank];
+			gpio_bank_saved[bank].reserved =
+						reserved_gpio_map[bank];
 
 			gpio = i;
 
 			while (mask) {
 				if (mask & 1) {
-					reserved_map[gpio_bank(gpio)] |=
+					reserved_gpio_map[gpio_bank(gpio)] |=
 							gpio_bit(gpio);
 					bfin_gpio_wakeup_type(gpio,
 						wakeup_flags_map[gpio]);
@@ -540,7 +617,8 @@ void gpio_pm_restore(void)
 			gpio_bankb[bank]->edge  = gpio_bank_saved[bank].edge;
 			gpio_bankb[bank]->both  = gpio_bank_saved[bank].both;
 
-			reserved_map[bank] = gpio_bank_saved[bank].reserved;
+			reserved_gpio_map[bank] =
+					gpio_bank_saved[bank].reserved;
 
 		}
 
@@ -550,6 +628,141 @@ void gpio_pm_restore(void)
 
 #endif
 
+
+
+
+int peripheral_request(unsigned short per, const char *label)
+{
+	unsigned long flags;
+	unsigned short ident = P_IDENT(per);
+
+	/*
+	 * Don't cares are pins with only one dedicated function
+	 */
+
+	if (per & P_DONTCARE)
+		return 0;
+
+	if (!(per & P_DEFINED))
+		return -ENODEV;
+
+	local_irq_save(flags);
+
+	if (!check_gpio(ident)) {
+
+	if (unlikely(reserved_gpio_map[gpio_bank(ident)] & gpio_bit(ident))) {
+		printk(KERN_ERR
+		       "%s: Peripheral %d is already reserved as GPIO by %s !\n",
+		       __FUNCTION__, ident, get_label(ident));
+		dump_stack();
+		local_irq_restore(flags);
+		return -EBUSY;
+	}
+
+	}
+
+	if (unlikely(reserved_peri_map[gpio_bank(ident)] & gpio_bit(ident))) {
+
+	/*
+	 * Pin functions like AMC address strobes my
+	 * be requested and used by several drivers
+	 */
+
+	if (!(per & P_MAYSHARE)) {
+
+	/*
+	 * Allow that the identical pin function can
+	 * be requested from the same driver twice
+	 */
+
+		if (cmp_label(ident, label) == 0)
+			goto anyway;
+
+			printk(KERN_ERR
+			       "%s: Peripheral %d function %d is already"
+			       "reserved by %s !\n",
+			       __FUNCTION__, ident, P_FUNCT2MUX(per),
+				get_label(ident));
+			dump_stack();
+			local_irq_restore(flags);
+			return -EBUSY;
+		}
+
+	}
+
+anyway:
+
+
+	portmux_setup(per, P_FUNCT2MUX(per));
+
+	port_setup(ident, PERIPHERAL_USAGE);
+
+	reserved_peri_map[gpio_bank(ident)] |= gpio_bit(ident);
+	local_irq_restore(flags);
+	set_label(ident, label);
+
+	return 0;
+}
+EXPORT_SYMBOL(peripheral_request);
+
+int peripheral_request_list(unsigned short per[], const char *label)
+{
+	u16 cnt;
+	int ret;
+
+	for (cnt = 0; per[cnt] != 0; cnt++) {
+		ret = peripheral_request(per[cnt], label);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(peripheral_request_list);
+
+void peripheral_free(unsigned short per)
+{
+	unsigned long flags;
+	unsigned short ident = P_IDENT(per);
+
+	if (per & P_DONTCARE)
+		return;
+
+	if (!(per & P_DEFINED))
+		return;
+
+	if (check_gpio(ident) < 0)
+		return;
+
+	local_irq_save(flags);
+
+	if (unlikely(!(reserved_peri_map[gpio_bank(ident)]
+			 & gpio_bit(ident)))) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	if (!(per & P_MAYSHARE)) {
+		port_setup(ident, GPIO_USAGE);
+	}
+
+	reserved_peri_map[gpio_bank(ident)] &= ~gpio_bit(ident);
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(peripheral_free);
+
+void peripheral_free_list(unsigned short per[])
+{
+	u16 cnt;
+
+	for (cnt = 0; per[cnt] != 0; cnt++) {
+		peripheral_free(per[cnt]);
+	}
+
+}
+EXPORT_SYMBOL(peripheral_free_list);
+
 /***********************************************************
 *
 * FUNCTIONS: Blackfin GPIO Driver
@@ -574,13 +787,13 @@ int gpio_request(unsigned short gpio, const char *label)
 
 	local_irq_save(flags);
 
-	if (unlikely(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio))) {
+	if (unlikely(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio))) {
 		printk(KERN_ERR "bfin-gpio: GPIO %d is already reserved!\n", gpio);
 		dump_stack();
 		local_irq_restore(flags);
 		return -EBUSY;
 	}
-	reserved_map[gpio_bank(gpio)] |= gpio_bit(gpio);
+	reserved_gpio_map[gpio_bank(gpio)] |= gpio_bit(gpio);
 
 	local_irq_restore(flags);
 
@@ -599,7 +812,7 @@ void gpio_free(unsigned short gpio)
 
 	local_irq_save(flags);
 
-	if (unlikely(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)))) {
+	if (unlikely(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)))) {
 		printk(KERN_ERR "bfin-gpio: GPIO %d wasn't reserved!\n", gpio);
 		dump_stack();
 		local_irq_restore(flags);
@@ -608,7 +821,7 @@ void gpio_free(unsigned short gpio)
 
 	default_gpio(gpio);
 
-	reserved_map[gpio_bank(gpio)] &= ~gpio_bit(gpio);
+	reserved_gpio_map[gpio_bank(gpio)] &= ~gpio_bit(gpio);
 
 	local_irq_restore(flags);
 }
@@ -618,7 +831,7 @@ void gpio_direction_input(unsigned short gpio)
 {
 	unsigned long flags;
 
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 
 	local_irq_save(flags);
 	gpio_bankb[gpio_bank(gpio)]->dir &= ~gpio_bit(gpio);
@@ -631,7 +844,7 @@ void gpio_direction_output(unsigned short gpio)
 {
 	unsigned long flags;
 
-	BUG_ON(!(reserved_map[gpio_bank(gpio)] & gpio_bit(gpio)));
+	BUG_ON(!(reserved_gpio_map[gpio_bank(gpio)] & gpio_bit(gpio)));
 
 	local_irq_save(flags);
 	gpio_bankb[gpio_bank(gpio)]->inen &= ~gpio_bit(gpio);

arch/blackfin/mach-common/entry.S

@@ -815,7 +815,7 @@ _extable:
 
 ALIGN
 ENTRY(_sys_call_table)
-	.long _sys_ni_syscall	/* 0  -  old "setup()" system call*/
+	.long _sys_restart_syscall	/* 0 */
 	.long _sys_exit
 	.long _sys_fork
 	.long _sys_read
@@ -978,13 +978,13 @@ ENTRY(_sys_call_table)
 	.long _sys_sched_get_priority_min  /* 160 */
 	.long _sys_sched_rr_get_interval
 	.long _sys_nanosleep
-	.long _sys_ni_syscall	/* sys_mremap */
+	.long _sys_mremap
 	.long _sys_setresuid	/* setresuid16 */
 	.long _sys_getresuid	/* getresuid16 */	/* 165 */
 	.long _sys_ni_syscall	/* for vm86 */
 	.long _sys_ni_syscall	/* old "query_module" */
 	.long _sys_ni_syscall	/* sys_poll */
-	.long _sys_ni_syscall	/* sys_nfsservctl */
+	.long _sys_nfsservctl
 	.long _sys_setresgid	/* setresgid16 */	/* 170 */
 	.long _sys_getresgid	/* getresgid16 */
 	.long _sys_prctl
@@ -1040,7 +1040,7 @@ ENTRY(_sys_call_table)
 	.long _sys_ni_syscall	/* reserved for TUX */
 	.long _sys_ni_syscall
 	.long _sys_gettid
-	.long _sys_ni_syscall	/* 225 */ /* sys_readahead */
+	.long _sys_readahead	/* 225 */
 	.long _sys_setxattr
 	.long _sys_lsetxattr
 	.long _sys_fsetxattr
@@ -1157,6 +1157,21 @@ ENTRY(_sys_call_table)
 	.long _sys_shmctl
 	.long _sys_shmdt	/* 340 */
 	.long _sys_shmget
+	.long _sys_splice
+	.long _sys_sync_file_range
+	.long _sys_tee
+	.long _sys_vmsplice	/* 345 */
+	.long _sys_epoll_pwait
+	.long _sys_utimensat
+	.long _sys_signalfd
+	.long _sys_timerfd
+	.long _sys_eventfd	/* 350 */
+	.long _sys_pread64
+	.long _sys_pwrite64
+	.long _sys_fadvise64
+	.long _sys_set_robust_list
+	.long _sys_get_robust_list	/* 355 */
+	.long _sys_fallocate
 	.rept NR_syscalls-(.-_sys_call_table)/4
 	.long _sys_ni_syscall
 	.endr

arch/i386/kernel/cpu/cpufreq/longhaul.c

@@ -76,6 +76,7 @@ static unsigned int longhaul_index;
 /* Module parameters */
 static int scale_voltage;
 static int disable_acpi_c3;
+static int revid_errata;
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg)
 
@@ -168,7 +169,10 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index,
 
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	/* Setup new frequency */
-	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
+	if (!revid_errata)
+		longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
+	else
+		longhaul.bits.RevisionKey = 0;
 	longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf;
 	longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
 	/* Setup new voltage */
@@ -272,7 +276,7 @@ static void longhaul_setstate(unsigned int table_index)
 
 	dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
 			fsb, mult/10, mult%10, print_speed(speed/1000));
-
+retry_loop:
 	preempt_disable();
 	local_irq_save(flags);
 
@@ -344,6 +348,47 @@ static void longhaul_setstate(unsigned int table_index)
 	preempt_enable();
 
 	freqs.new = calc_speed(longhaul_get_cpu_mult());
+	/* Check if requested frequency is set. */
+	if (unlikely(freqs.new != speed)) {
+		printk(KERN_INFO PFX "Failed to set requested frequency!\n");
+		/* Revision ID = 1 but processor is expecting revision key
+		 * equal to 0. Jumpers at the bottom of processor will change
+		 * multiplier and FSB, but will not change bits in Longhaul
+		 * MSR nor enable voltage scaling. */
+		if (!revid_errata) {
+			printk(KERN_INFO PFX "Enabling \"Ignore Revision ID\" "
+						"option.\n");
+			revid_errata = 1;
+			msleep(200);
+			goto retry_loop;
+		}
+		/* Why ACPI C3 sometimes doesn't work is a mystery for me.
+		 * But it does happen. Processor is entering ACPI C3 state,
+		 * but it doesn't change frequency. I tried poking various
+		 * bits in northbridge registers, but without success. */
+		if (longhaul_flags & USE_ACPI_C3) {
+			printk(KERN_INFO PFX "Disabling ACPI C3 support.\n");
+			longhaul_flags &= ~USE_ACPI_C3;
+			if (revid_errata) {
+				printk(KERN_INFO PFX "Disabling \"Ignore "
+						"Revision ID\" option.\n");
+				revid_errata = 0;
+			}
+			msleep(200);
+			goto retry_loop;
+		}
+		/* This shouldn't happen. Longhaul ver. 2 was reported not
+		 * working on processors without voltage scaling, but with
+		 * RevID = 1. RevID errata will make things right. Just
+		 * to be 100% sure. */
+		if (longhaul_version == TYPE_LONGHAUL_V2) {
+			printk(KERN_INFO PFX "Switching to Longhaul ver. 1\n");
+			longhaul_version = TYPE_LONGHAUL_V1;
+			msleep(200);
+			goto retry_loop;
+		}
+	}
+	/* Report true CPU frequency */
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
 	if (!bm_timeout)
@@ -956,11 +1001,20 @@ static void __exit longhaul_exit(void)
 	kfree(longhaul_table);
 }
 
+/* Even if BIOS is exporting ACPI C3 state, and it is used
+ * with success when CPU is idle, this state doesn't
+ * trigger frequency transition in some cases. */
 module_param (disable_acpi_c3, int, 0644);
 MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support");
-
+/* Change CPU voltage with frequency. Very usefull to save
+ * power, but most VIA C3 processors aren't supporting it. */
 module_param (scale_voltage, int, 0644);
 MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
+/* Force revision key to 0 for processors which doesn't
+ * support voltage scaling, but are introducing itself as
+ * such. */
+module_param(revid_errata, int, 0644);
+MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID");
 
 MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>");
 MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors.");

arch/mips/au1000/common/pci.c

@@ -74,6 +74,7 @@ static int __init au1x_pci_setup(void)
 		printk(KERN_ERR "Unable to ioremap pci space\n");
 		return 1;
 	}
+	au1x_controller.io_map_base = virt_io_addr;
 
 #ifdef CONFIG_DMA_NONCOHERENT
 	{

arch/mips/au1000/mtx-1/board_setup.c

@@ -54,11 +54,11 @@ void board_reset (void)
 
 void __init board_setup(void)
 {
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	// enable USB power switch
 	au_writel( au_readl(GPIO2_DIR) | 0x10, GPIO2_DIR );
 	au_writel( 0x100000, GPIO2_OUTPUT );
-#endif // defined (CONFIG_USB_OHCI)
+#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
 
 #ifdef CONFIG_PCI
 #if defined(__MIPSEB__)

arch/mips/au1000/pb1000/board_setup.c

@@ -54,7 +54,7 @@ void __init board_setup(void)
 	au_writel(0, SYS_PINSTATERD);
 	udelay(100);
 
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	/* zero and disable FREQ2 */
 	sys_freqctrl = au_readl(SYS_FREQCTRL0);
 	sys_freqctrl &= ~0xFFF00000;
@@ -102,7 +102,7 @@ void __init board_setup(void)
 	/*
 	 * Route 48MHz FREQ2 into USB Host and/or Device
 	 */
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	sys_clksrc |= ((4<<12) | (0<<11) | (0<<10));
 #endif
 	au_writel(sys_clksrc, SYS_CLKSRC);
@@ -116,7 +116,7 @@ void __init board_setup(void)
 	au_writel(pin_func, SYS_PINFUNC);
 	au_writel(0x2800, SYS_TRIOUTCLR);
 	au_writel(0x0030, SYS_OUTPUTCLR);
-#endif // defined (CONFIG_USB_OHCI)
+#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
 
 	// make gpio 15 an input (for interrupt line)
 	pin_func = au_readl(SYS_PINFUNC) & (u32)(~0x100);

arch/mips/au1000/pb1100/board_setup.c

@@ -54,7 +54,7 @@ void __init board_setup(void)
 	au_writel(0, SYS_PININPUTEN);
 	udelay(100);
 
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	{
 		u32 pin_func, sys_freqctrl, sys_clksrc;
 
@@ -98,7 +98,7 @@ void __init board_setup(void)
 		pin_func |= 0x8000;
 		au_writel(pin_func, SYS_PINFUNC);
 	}
-#endif // defined (CONFIG_USB_OHCI)
+#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
 
 	/* Enable sys bus clock divider when IDLE state or no bus activity. */
 	au_writel(au_readl(SYS_POWERCTRL) | (0x3 << 5), SYS_POWERCTRL);

arch/mips/au1000/pb1500/board_setup.c

@@ -56,7 +56,7 @@ void __init board_setup(void)
 	au_writel(0, SYS_PINSTATERD);
 	udelay(100);
 
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 
 	/* GPIO201 is input for PCMCIA card detect */
 	/* GPIO203 is input for PCMCIA interrupt request */
@@ -85,7 +85,7 @@ void __init board_setup(void)
 	/*
 	 * Route 48MHz FREQ2 into USB Host and/or Device
 	 */
-#ifdef CONFIG_USB_OHCI
+#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
 	sys_clksrc |= ((4<<12) | (0<<11) | (0<<10));
 #endif
 	au_writel(sys_clksrc, SYS_CLKSRC);
@@ -95,7 +95,7 @@ void __init board_setup(void)
 	// 2nd USB port is USB host
 	pin_func |= 0x8000;
 	au_writel(pin_func, SYS_PINFUNC);
-#endif // defined (CONFIG_USB_OHCI)
+#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
 
 
 

arch/mips/kernel/vmlinux.lds.S

@@ -45,6 +45,8 @@ SECTIONS
   __dbe_table : { *(__dbe_table) }
   __stop___dbe_table = .;
 
+  NOTES
+
   RODATA
 
   /* writeable */

arch/mips/mm/pg-r4k.c

@@ -209,7 +209,7 @@ static inline void build_cdex_p(void)
 	}
 
 	if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-		build_insn_word(0x3c01a000);	/* lui     $at, 0xa000  */
+		build_insn_word(0x8c200000);	/* lw      $zero, ($at) */
 
 	mi.c_format.opcode     = cache_op;
 	mi.c_format.rs         = 4;		/* $a0 */

arch/mips/pci/ops-mace.c

@@ -29,22 +29,20 @@
  * 4  N/C
  */
 
-#define chkslot(_bus,_devfn)					\
-do {							        \
-	if ((_bus)->number > 0 || PCI_SLOT (_devfn) < 1	\
-	    || PCI_SLOT (_devfn) > 3)			        \
-		return PCIBIOS_DEVICE_NOT_FOUND;		\
-} while (0)
+static inline int mkaddr(struct pci_bus *bus, unsigned int devfn,
+	unsigned int reg)
+{
+	return ((bus->number & 0xff) << 16) |
+		((devfn & 0xff) << 8) |
+		(reg & 0xfc);
+}
 
-#define mkaddr(_devfn, _reg) \
-((((_devfn) & 0xffUL) << 8) | ((_reg) & 0xfcUL))
 
 static int
 mace_pci_read_config(struct pci_bus *bus, unsigned int devfn,
 		     int reg, int size, u32 *val)
 {
-	chkslot(bus, devfn);
-	mace->pci.config_addr = mkaddr(devfn, reg);
+	mace->pci.config_addr = mkaddr(bus, devfn, reg);
 	switch (size) {
 	case 1:
 		*val = mace->pci.config_data.b[(reg & 3) ^ 3];
@@ -66,8 +64,7 @@ static int
 mace_pci_write_config(struct pci_bus *bus, unsigned int devfn,
 		      int reg, int size, u32 val)
 {
-	chkslot(bus, devfn);
-	mace->pci.config_addr = mkaddr(devfn, reg);
+	mace->pci.config_addr = mkaddr(bus, devfn, reg);
 	switch (size) {
 	case 1:
 		mace->pci.config_data.b[(reg & 3) ^ 3] = val;

arch/powerpc/platforms/pseries/xics.c

@@ -419,7 +419,7 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask)
 	 * For the moment only implement delivery to all cpus or one cpu.
 	 * Get current irq_server for the given irq
 	 */
-	irq_server = get_irq_server(irq, 1);
+	irq_server = get_irq_server(virq, 1);
 	if (irq_server == -1) {
 		char cpulist[128];
 		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);

arch/sparc/kernel/ebus.c

@@ -156,6 +156,8 @@ void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_device *d
 	dev->prom_node = dp;
 
 	regs = of_get_property(dp, "reg", &len);
+	if (!regs)
+		len = 0;
 	if (len % sizeof(struct linux_prom_registers)) {
 		prom_printf("UGH: proplen for %s was %d, need multiple of %d\n",
 			    dev->prom_node->name, len,

arch/sparc64/kernel/binfmt_aout32.c

@@ -177,7 +177,7 @@ static u32 __user *create_aout32_tables(char __user *p, struct linux_binprm *bpr
 			get_user(c,p++);
 		} while (c);
 	}
-	put_user(NULL,argv);
+	put_user(0,argv);
 	current->mm->arg_end = current->mm->env_start = (unsigned long) p;
 	while (envc-->0) {
 		char c;
@@ -186,7 +186,7 @@ static u32 __user *create_aout32_tables(char __user *p, struct linux_binprm *bpr
 			get_user(c,p++);
 		} while (c);
 	}
-	put_user(NULL,envp);
+	put_user(0,envp);
 	current->mm->env_end = (unsigned long) p;
 	return sp;
 }

arch/sparc64/kernel/ebus.c

@@ -375,7 +375,10 @@ static void __init fill_ebus_device(struct device_node *dp, struct linux_ebus_de
 		dev->num_addrs = 0;
 		dev->num_irqs = 0;
 	} else {
-		(void) of_get_property(dp, "reg", &len);
+		const int *regs = of_get_property(dp, "reg", &len);
+
+		if (!regs)
+			len = 0;
 		dev->num_addrs = len / sizeof(struct linux_prom_registers);
 
 		for (i = 0; i < dev->num_addrs; i++)

arch/sparc64/kernel/pci_common.c

@@ -264,7 +264,7 @@ static int sun4v_read_pci_cfg(struct pci_bus *bus_dev, unsigned int devfn,
 	unsigned int func = PCI_FUNC(devfn);
 	unsigned long ret;
 
-	if (bus_dev == pbm->pci_bus && devfn == 0x00)
+	if (!bus && devfn == 0x00)
 		return pci_host_bridge_read_pci_cfg(bus_dev, devfn, where,
 						    size, value);
 	if (config_out_of_range(pbm, bus, devfn, where)) {
@@ -300,7 +300,7 @@ static int sun4v_write_pci_cfg(struct pci_bus *bus_dev, unsigned int devfn,
 	unsigned int func = PCI_FUNC(devfn);
 	unsigned long ret;
 
-	if (bus_dev == pbm->pci_bus && devfn == 0x00)
+	if (!bus && devfn == 0x00)
 		return pci_host_bridge_write_pci_cfg(bus_dev, devfn, where,
 						     size, value);
 	if (config_out_of_range(pbm, bus, devfn, where)) {

arch/sparc64/kernel/prom.c

@@ -1046,7 +1046,8 @@ static void __init irq_trans_init(struct device_node *dp)
 	if (!strcmp(dp->name, "fhc") &&
 	    !strcmp(dp->parent->name, "central"))
 		return central_irq_trans_init(dp);
-	if (!strcmp(dp->name, "virtual-devices"))
+	if (!strcmp(dp->name, "virtual-devices") ||
+	    !strcmp(dp->name, "niu"))
 		return sun4v_vdev_irq_trans_init(dp);
 }
 

arch/sparc64/kernel/smp.c

@@ -353,6 +353,8 @@ static int __devinit smp_boot_one_cpu(unsigned int cpu)
 	int timeout, ret;
 
 	p = fork_idle(cpu);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 	callin_flag = 0;
 	cpu_new_thread = task_thread_info(p);
 

arch/sparc64/kernel/vio.c

@@ -292,7 +292,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	}
 	vdev->dp = dp;
 
-	printk(KERN_ERR "VIO: Adding device %s\n", vdev->dev.bus_id);
+	printk(KERN_INFO "VIO: Adding device %s\n", vdev->dev.bus_id);
 
 	err = device_register(&vdev->dev);
 	if (err) {
@@ -342,8 +342,33 @@ static struct mdesc_notifier_client vio_device_notifier = {
 	.node_name	= "virtual-device-port",
 };
 
+/* We are only interested in domain service ports under the
+ * "domain-services" node.  On control nodes there is another port
+ * under "openboot" that we should not mess with as aparently that is
+ * reserved exclusively for OBP use.
+ */
+static void vio_add_ds(struct mdesc_handle *hp, u64 node)
+{
+	int found;
+	u64 a;
+
+	found = 0;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target = mdesc_arc_target(hp, a);
+		const char *name = mdesc_node_name(hp, target);
+
+		if (!strcmp(name, "domain-services")) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (found)
+		(void) vio_create_one(hp, node, &root_vdev->dev);
+}
+
 static struct mdesc_notifier_client vio_ds_notifier = {
-	.add		= vio_add,
+	.add		= vio_add_ds,
 	.remove		= vio_remove,
 	.node_name	= "domain-services-port",
 };

arch/sparc64/lib/NGcopy_from_user.S

@@ -1,6 +1,6 @@
 /* NGcopy_from_user.S: Niagara optimized copy from userspace.
  *
- * Copyright (C) 2006 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
 #define EX_LD(x)		\
@@ -8,8 +8,8 @@
 	.section .fixup;	\
 	.align 4;		\
 99:	wr	%g0, ASI_AIUS, %asi;\
-	retl;			\
-	 mov	1, %o0;		\
+	ret;			\
+	 restore %g0, 1, %o0;	\
 	.section __ex_table,"a";\
 	.align 4;		\
 	.word 98b, 99b;		\
@@ -24,7 +24,7 @@
 #define LOAD(type,addr,dest)	type##a [addr] ASI_AIUS, dest
 #define LOAD_TWIN(addr_reg,dest0,dest1)	\
 	ldda [addr_reg] ASI_BLK_INIT_QUAD_LDD_AIUS, dest0
-#define EX_RETVAL(x)		0
+#define EX_RETVAL(x)		%g0
 
 #ifdef __KERNEL__
 #define PREAMBLE					\

arch/sparc64/lib/NGcopy_to_user.S

@@ -1,6 +1,6 @@
 /* NGcopy_to_user.S: Niagara optimized copy to userspace.
  *
- * Copyright (C) 2006 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
 #define EX_ST(x)		\
@@ -8,8 +8,8 @@
 	.section .fixup;	\
 	.align 4;		\
 99:	wr	%g0, ASI_AIUS, %asi;\
-	retl;			\
-	 mov	1, %o0;		\
+	ret;			\
+	 restore %g0, 1, %o0;	\
 	.section __ex_table,"a";\
 	.align 4;		\
 	.word 98b, 99b;		\
@@ -23,7 +23,7 @@
 #define FUNC_NAME		NGcopy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] ASI_AIUS
 #define STORE_ASI		ASI_BLK_INIT_QUAD_LDD_AIUS
-#define EX_RETVAL(x)		0
+#define EX_RETVAL(x)		%g0
 
 #ifdef __KERNEL__
 	/* Writing to %asi is _expensive_ so we hardcode it.

arch/sparc64/lib/NGmemcpy.S

@@ -1,6 +1,6 @@
 /* NGmemcpy.S: Niagara optimized memcpy.
  *
- * Copyright (C) 2006 David S. Miller (davem@davemloft.net)
+ * Copyright (C) 2006, 2007 David S. Miller (davem@davemloft.net)
  */
 
 #ifdef __KERNEL__
@@ -16,6 +16,12 @@
 	wr	%g0, ASI_PNF, %asi
 #endif
 
+#ifdef __sparc_v9__
+#define SAVE_AMOUNT	128
+#else
+#define SAVE_AMOUNT	64
+#endif
+
 #ifndef STORE_ASI
 #define STORE_ASI	ASI_BLK_INIT_QUAD_LDD_P
 #endif
@@ -50,7 +56,11 @@
 #endif
 
 #ifndef STORE_INIT
+#ifndef SIMULATE_NIAGARA_ON_NON_NIAGARA
 #define STORE_INIT(src,addr)	stxa src, [addr] %asi
+#else
+#define STORE_INIT(src,addr)	stx src, [addr + 0x00]
+#endif
 #endif
 
 #ifndef FUNC_NAME
@@ -73,18 +83,19 @@
 
 	.globl	FUNC_NAME
 	.type	FUNC_NAME,#function
-FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
-	srlx		%o2, 31, %g2
+FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
+	PREAMBLE
+	save		%sp, -SAVE_AMOUNT, %sp
+	srlx		%i2, 31, %g2
 	cmp		%g2, 0
 	tne		%xcc, 5
-	PREAMBLE
-	mov		%o0, GLOBAL_SPARE
-	cmp		%o2, 0
+	mov		%i0, %o0
+	cmp		%i2, 0
 	be,pn		%XCC, 85f
-	 or		%o0, %o1, %o3
-	cmp		%o2, 16
+	 or		%o0, %i1, %i3
+	cmp		%i2, 16
 	blu,a,pn	%XCC, 80f
-	 or		%o3, %o2, %o3
+	 or		%i3, %i2, %i3
 
 	/* 2 blocks (128 bytes) is the minimum we can do the block
 	 * copy with.  We need to ensure that we'll iterate at least
@@ -93,31 +104,31 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 * to (64 - 1) bytes from the length before we perform the
 	 * block copy loop.
 	 */
-	cmp		%o2, (2 * 64)
+	cmp		%i2, (2 * 64)
 	blu,pt		%XCC, 70f
-	 andcc		%o3, 0x7, %g0
+	 andcc		%i3, 0x7, %g0
 
 	/* %o0:	dst
-	 * %o1:	src
-	 * %o2:	len  (known to be >= 128)
+	 * %i1:	src
+	 * %i2:	len  (known to be >= 128)
 	 *
-	 * The block copy loops will use %o4/%o5,%g2/%g3 as
+	 * The block copy loops will use %i4/%i5,%g2/%g3 as
 	 * temporaries while copying the data.
 	 */
 
-	LOAD(prefetch, %o1, #one_read)
+	LOAD(prefetch, %i1, #one_read)
 	wr		%g0, STORE_ASI, %asi
 
 	/* Align destination on 64-byte boundary.  */
-	andcc		%o0, (64 - 1), %o4
+	andcc		%o0, (64 - 1), %i4
 	be,pt		%XCC, 2f
-	 sub		%o4, 64, %o4
-	sub		%g0, %o4, %o4	! bytes to align dst
-	sub		%o2, %o4, %o2
-1:	subcc		%o4, 1, %o4
-	EX_LD(LOAD(ldub, %o1, %g1))
+	 sub		%i4, 64, %i4
+	sub		%g0, %i4, %i4	! bytes to align dst
+	sub		%i2, %i4, %i2
+1:	subcc		%i4, 1, %i4
+	EX_LD(LOAD(ldub, %i1, %g1))
 	EX_ST(STORE(stb, %g1, %o0))
-	add		%o1, 1, %o1
+	add		%i1, 1, %i1
 	bne,pt		%XCC, 1b
 	add		%o0, 1, %o0
 
@@ -136,111 +147,155 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 * aligned store data at a time, this is easy to ensure.
 	 */
 2:
-	andcc		%o1, (16 - 1), %o4
-	andn		%o2, (64 - 1), %g1	! block copy loop iterator
-	sub		%o2, %g1, %o2		! final sub-block copy bytes
+	andcc		%i1, (16 - 1), %i4
+	andn		%i2, (64 - 1), %g1	! block copy loop iterator
 	be,pt		%XCC, 50f
-	 cmp		%o4, 8
-	be,a,pt		%XCC, 10f
-	 sub		%o1, 0x8, %o1
+	 sub		%i2, %g1, %i2		! final sub-block copy bytes
+
+	cmp		%i4, 8
+	be,pt		%XCC, 10f
+	 sub		%i1, %i4, %i1
 
 	/* Neither 8-byte nor 16-byte aligned, shift and mask.  */
-	mov		%g1, %o4
-	and		%o1, 0x7, %g1
-	sll		%g1, 3, %g1
-	mov		64, %o3
-	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
-	sub		%o3, %g1, %o3
-	sllx		%g2, %g1, %g2
+	and		%i4, 0x7, GLOBAL_SPARE
+	sll		GLOBAL_SPARE, 3, GLOBAL_SPARE
+	mov		64, %i5
+	EX_LD(LOAD_TWIN(%i1, %g2, %g3))
+	sub		%i5, GLOBAL_SPARE, %i5
+	mov		16, %o4
+	mov		32, %o5
+	mov		48, %o7
+	mov		64, %i3
+
+	bg,pn	   	%XCC, 9f
+	 nop
 
-#define SWIVEL_ONE_DWORD(SRC, TMP1, TMP2, PRE_VAL, PRE_SHIFT, POST_SHIFT, DST)\
-	EX_LD(LOAD(ldx, SRC, TMP1)); \
-	srlx		TMP1, PRE_SHIFT, TMP2; \
-	or		TMP2, PRE_VAL, TMP2; \
-	EX_ST(STORE_INIT(TMP2, DST)); \
-	sllx		TMP1, POST_SHIFT, PRE_VAL;
-
-1:	add		%o1, 0x8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x00)
-	add		%o1, 0x8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x08)
-	add		%o1, 0x8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x10)
-	add		%o1, 0x8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x18)
-	add		%o1, 32, %o1
-	LOAD(prefetch, %o1, #one_read)
-	sub		%o1, 32 - 8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x20)
-	add		%o1, 8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x28)
-	add		%o1, 8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x30)
-	add		%o1, 8, %o1
-	SWIVEL_ONE_DWORD(%o1, %g3, %o5, %g2, %o3, %g1, %o0 + 0x38)
-	subcc		%o4, 64, %o4
-	bne,pt		%XCC, 1b
+#define MIX_THREE_WORDS(WORD1, WORD2, WORD3, PRE_SHIFT, POST_SHIFT, TMP) \
+	sllx		WORD1, POST_SHIFT, WORD1; \
+	srlx		WORD2, PRE_SHIFT, TMP; \
+	sllx		WORD2, POST_SHIFT, WORD2; \
+	or		WORD1, TMP, WORD1; \
+	srlx		WORD3, PRE_SHIFT, TMP; \
+	or		WORD2, TMP, WORD2;
+
+8:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
+	LOAD(prefetch, %i1 + %i3, #one_read)
+
+	EX_ST(STORE_INIT(%g2, %o0 + 0x00))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x08))
+
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	MIX_THREE_WORDS(%g2, %g3, %o2, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%g2, %o0 + 0x20))
+	EX_ST(STORE_INIT(%g3, %o0 + 0x28))
+
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	add		%i1, 64, %i1
+	MIX_THREE_WORDS(%o2, %o3, %g2, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
+
+	subcc		%g1, 64, %g1
+	bne,pt		%XCC, 8b
 	 add		%o0, 64, %o0
 
-#undef SWIVEL_ONE_DWORD
+	ba,pt		%XCC, 60f
+	 add		%i1, %i4, %i1
+
+9:	EX_LD(LOAD_TWIN(%i1 + %o4, %o2, %o3))
+	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
+	LOAD(prefetch, %i1 + %i3, #one_read)
+
+	EX_ST(STORE_INIT(%g3, %o0 + 0x00))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+
+	EX_LD(LOAD_TWIN(%i1 + %o5, %g2, %g3))
+	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x18))
+
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	MIX_THREE_WORDS(%g3, %o2, %o3, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%g3, %o0 + 0x20))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+
+	EX_LD(LOAD_TWIN(%i1 + %i3, %g2, %g3))
+	add		%i1, 64, %i1
+	MIX_THREE_WORDS(%o3, %g2, %g3, %i5, GLOBAL_SPARE, %o1)
+
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
+	EX_ST(STORE_INIT(%g2, %o0 + 0x38))
+
+	subcc		%g1, 64, %g1
+	bne,pt		%XCC, 9b
+	 add		%o0, 64, %o0
 
-	srl		%g1, 3, %g1
 	ba,pt		%XCC, 60f
-	 add		%o1, %g1, %o1
+	 add		%i1, %i4, %i1
 
 10:	/* Destination is 64-byte aligned, source was only 8-byte
 	 * aligned but it has been subtracted by 8 and we perform
 	 * one twin load ahead, then add 8 back into source when
 	 * we finish the loop.
 	 */
-	EX_LD(LOAD_TWIN(%o1, %o4, %o5))
-1:	add		%o1, 16, %o1
-	EX_LD(LOAD_TWIN(%o1, %g2, %g3))
-	add		%o1, 16 + 32, %o1
-	LOAD(prefetch, %o1, #one_read)
-	sub		%o1, 32, %o1
+	EX_LD(LOAD_TWIN(%i1, %o4, %o5))
+	mov	16, %o7
+	mov	32, %g2
+	mov	48, %g3
+	mov	64, %o1
+1:	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	LOAD(prefetch, %i1 + %o1, #one_read)
 	EX_ST(STORE_INIT(%o5, %o0 + 0x00))	! initializes cache line
-	EX_ST(STORE_INIT(%g2, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%o1, %o4, %o5))
-	add		%o1, 16, %o1
-	EX_ST(STORE_INIT(%g3, %o0 + 0x10))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x08))
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x10))
 	EX_ST(STORE_INIT(%o4, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%o1, %g2, %g3))
-	add		%o1, 16, %o1
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
 	EX_ST(STORE_INIT(%o5, %o0 + 0x20))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x28))
-	EX_LD(LOAD_TWIN(%o1, %o4, %o5))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x30))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x28))
+	EX_LD(LOAD_TWIN(%i1 + %o1, %o4, %o5))
+	add		%i1, 64, %i1
+	EX_ST(STORE_INIT(%o3, %o0 + 0x30))
 	EX_ST(STORE_INIT(%o4, %o0 + 0x38))
 	subcc		%g1, 64, %g1
 	bne,pt		%XCC, 1b
 	 add		%o0, 64, %o0
 
 	ba,pt		%XCC, 60f
-	 add		%o1, 0x8, %o1
+	 add		%i1, 0x8, %i1
 
 50:	/* Destination is 64-byte aligned, and source is 16-byte
 	 * aligned.
 	 */
-1:	EX_LD(LOAD_TWIN(%o1, %o4, %o5))
-	add	%o1, 16, %o1
-	EX_LD(LOAD_TWIN(%o1, %g2, %g3))
-	add	%o1, 16 + 32, %o1
-	LOAD(prefetch, %o1, #one_read)
-	sub	%o1, 32, %o1
+	mov	16, %o7
+	mov	32, %g2
+	mov	48, %g3
+	mov	64, %o1
+1:	EX_LD(LOAD_TWIN(%i1 + %g0, %o4, %o5))
+	EX_LD(LOAD_TWIN(%i1 + %o7, %o2, %o3))
+	LOAD(prefetch, %i1 + %o1, #one_read)
 	EX_ST(STORE_INIT(%o4, %o0 + 0x00))	! initializes cache line
 	EX_ST(STORE_INIT(%o5, %o0 + 0x08))
-	EX_LD(LOAD_TWIN(%o1, %o4, %o5))
-	add	%o1, 16, %o1
-	EX_ST(STORE_INIT(%g2, %o0 + 0x10))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x18))
-	EX_LD(LOAD_TWIN(%o1, %g2, %g3))
-	add	%o1, 16, %o1
+	EX_LD(LOAD_TWIN(%i1 + %g2, %o4, %o5))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x10))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x18))
+	EX_LD(LOAD_TWIN(%i1 + %g3, %o2, %o3))
+	add	%i1, 64, %i1
 	EX_ST(STORE_INIT(%o4, %o0 + 0x20))
 	EX_ST(STORE_INIT(%o5, %o0 + 0x28))
-	EX_ST(STORE_INIT(%g2, %o0 + 0x30))
-	EX_ST(STORE_INIT(%g3, %o0 + 0x38))
+	EX_ST(STORE_INIT(%o2, %o0 + 0x30))
+	EX_ST(STORE_INIT(%o3, %o0 + 0x38))
 	subcc	%g1, 64, %g1
 	bne,pt	%XCC, 1b
 	 add	%o0, 64, %o0
@@ -249,47 +304,47 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 60:	
 	membar		#Sync
 
-	/* %o2 contains any final bytes still needed to be copied
+	/* %i2 contains any final bytes still needed to be copied
 	 * over. If anything is left, we copy it one byte at a time.
 	 */
-	RESTORE_ASI(%o3)
-	brz,pt		%o2, 85f
-	 sub		%o0, %o1, %o3
+	RESTORE_ASI(%i3)
+	brz,pt		%i2, 85f
+	 sub		%o0, %i1, %i3
 	ba,a,pt		%XCC, 90f
 
 	.align		64
 70: /* 16 < len <= 64 */
 	bne,pn		%XCC, 75f
-	 sub		%o0, %o1, %o3
+	 sub		%o0, %i1, %i3
 
 72:
-	andn		%o2, 0xf, %o4
-	and		%o2, 0xf, %o2
-1:	subcc		%o4, 0x10, %o4
-	EX_LD(LOAD(ldx, %o1, %o5))
-	add		%o1, 0x08, %o1
-	EX_LD(LOAD(ldx, %o1, %g1))
-	sub		%o1, 0x08, %o1
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
-	add		%o1, 0x8, %o1
-	EX_ST(STORE(stx, %g1, %o1 + %o3))
+	andn		%i2, 0xf, %i4
+	and		%i2, 0xf, %i2
+1:	subcc		%i4, 0x10, %i4
+	EX_LD(LOAD(ldx, %i1, %o4))
+	add		%i1, 0x08, %i1
+	EX_LD(LOAD(ldx, %i1, %g1))
+	sub		%i1, 0x08, %i1
+	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	add		%i1, 0x8, %i1
+	EX_ST(STORE(stx, %g1, %i1 + %i3))
 	bgu,pt		%XCC, 1b
-	 add		%o1, 0x8, %o1
-73:	andcc		%o2, 0x8, %g0
+	 add		%i1, 0x8, %i1
+73:	andcc		%i2, 0x8, %g0
 	be,pt		%XCC, 1f
 	 nop
-	sub		%o2, 0x8, %o2
-	EX_LD(LOAD(ldx, %o1, %o5))
-	EX_ST(STORE(stx, %o5, %o1 + %o3))
-	add		%o1, 0x8, %o1
-1:	andcc		%o2, 0x4, %g0
+	sub		%i2, 0x8, %i2
+	EX_LD(LOAD(ldx, %i1, %o4))
+	EX_ST(STORE(stx, %o4, %i1 + %i3))
+	add		%i1, 0x8, %i1
+1:	andcc		%i2, 0x4, %g0
 	be,pt		%XCC, 1f
 	 nop
-	sub		%o2, 0x4, %o2
-	EX_LD(LOAD(lduw, %o1, %o5))
-	EX_ST(STORE(stw, %o5, %o1 + %o3))
-	add		%o1, 0x4, %o1
-1:	cmp		%o2, 0
+	sub		%i2, 0x4, %i2
+	EX_LD(LOAD(lduw, %i1, %i5))
+	EX_ST(STORE(stw, %i5, %i1 + %i3))
+	add		%i1, 0x4, %i1
+1:	cmp		%i2, 0
 	be,pt		%XCC, 85f
 	 nop
 	ba,pt		%xcc, 90f
@@ -300,71 +355,71 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	sub		%g1, 0x8, %g1
 	be,pn		%icc, 2f
 	 sub		%g0, %g1, %g1
-	sub		%o2, %g1, %o2
+	sub		%i2, %g1, %i2
 
 1:	subcc		%g1, 1, %g1
-	EX_LD(LOAD(ldub, %o1, %o5))
-	EX_ST(STORE(stb, %o5, %o1 + %o3))
+	EX_LD(LOAD(ldub, %i1, %i5))
+	EX_ST(STORE(stb, %i5, %i1 + %i3))
 	bgu,pt		%icc, 1b
-	 add		%o1, 1, %o1
+	 add		%i1, 1, %i1
 
-2:	add		%o1, %o3, %o0
-	andcc		%o1, 0x7, %g1
+2:	add		%i1, %i3, %o0
+	andcc		%i1, 0x7, %g1
 	bne,pt		%icc, 8f
 	 sll		%g1, 3, %g1
 
-	cmp		%o2, 16
+	cmp		%i2, 16
 	bgeu,pt		%icc, 72b
 	 nop
 	ba,a,pt		%xcc, 73b
 
-8:	mov		64, %o3
-	andn		%o1, 0x7, %o1
-	EX_LD(LOAD(ldx, %o1, %g2))
-	sub		%o3, %g1, %o3
-	andn		%o2, 0x7, %o4
+8:	mov		64, %i3
+	andn		%i1, 0x7, %i1
+	EX_LD(LOAD(ldx, %i1, %g2))
+	sub		%i3, %g1, %i3
+	andn		%i2, 0x7, %i4
 	sllx		%g2, %g1, %g2
-1:	add		%o1, 0x8, %o1
-	EX_LD(LOAD(ldx, %o1, %g3))
-	subcc		%o4, 0x8, %o4
-	srlx		%g3, %o3, %o5
-	or		%o5, %g2, %o5
-	EX_ST(STORE(stx, %o5, %o0))
+1:	add		%i1, 0x8, %i1
+	EX_LD(LOAD(ldx, %i1, %g3))
+	subcc		%i4, 0x8, %i4
+	srlx		%g3, %i3, %i5
+	or		%i5, %g2, %i5
+	EX_ST(STORE(stx, %i5, %o0))
 	add		%o0, 0x8, %o0
 	bgu,pt		%icc, 1b
 	 sllx		%g3, %g1, %g2
 
 	srl		%g1, 3, %g1
-	andcc		%o2, 0x7, %o2
+	andcc		%i2, 0x7, %i2
 	be,pn		%icc, 85f
-	 add		%o1, %g1, %o1
+	 add		%i1, %g1, %i1
 	ba,pt		%xcc, 90f
-	 sub		%o0, %o1, %o3
+	 sub		%o0, %i1, %i3
 
 	.align		64
 80: /* 0 < len <= 16 */
-	andcc		%o3, 0x3, %g0
+	andcc		%i3, 0x3, %g0
 	bne,pn		%XCC, 90f
-	 sub		%o0, %o1, %o3
+	 sub		%o0, %i1, %i3
 
 1:
-	subcc		%o2, 4, %o2
-	EX_LD(LOAD(lduw, %o1, %g1))
-	EX_ST(STORE(stw, %g1, %o1 + %o3))
+	subcc		%i2, 4, %i2
+	EX_LD(LOAD(lduw, %i1, %g1))
+	EX_ST(STORE(stw, %g1, %i1 + %i3))
 	bgu,pt		%XCC, 1b
-	 add		%o1, 4, %o1
+	 add		%i1, 4, %i1
 
-85:	retl
-	 mov		EX_RETVAL(GLOBAL_SPARE), %o0
+85:	ret
+	 restore	EX_RETVAL(%i0), %g0, %o0
 
 	.align		32
 90:
-	subcc		%o2, 1, %o2
-	EX_LD(LOAD(ldub, %o1, %g1))
-	EX_ST(STORE(stb, %g1, %o1 + %o3))
+	subcc		%i2, 1, %i2
+	EX_LD(LOAD(ldub, %i1, %g1))
+	EX_ST(STORE(stb, %g1, %i1 + %i3))
 	bgu,pt		%XCC, 90b
-	 add		%o1, 1, %o1
-	retl
-	 mov		EX_RETVAL(GLOBAL_SPARE), %o0
+	 add		%i1, 1, %i1
+	ret
+	 restore	EX_RETVAL(%i0), %g0, %o0
 
 	.size		FUNC_NAME, .-FUNC_NAME

arch/x86_64/vdso/voffset.h

@@ -1 +1 @@
-#define VDSO_TEXT_OFFSET 0x500
+#define VDSO_TEXT_OFFSET 0x600

drivers/ata/ata_piix.c

@@ -920,6 +920,13 @@ static void ich_set_dmamode (struct ata_port *ap, struct ata_device *adev)
 static int piix_broken_suspend(void)
 {
 	static struct dmi_system_id sysids[] = {
+		{
+			.ident = "TECRA M3",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "TECRA M3"),
+			},
+		},
 		{
 			.ident = "TECRA M5",
 			.matches = {

drivers/ata/pata_ixp4xx_cf.c

@@ -189,6 +189,9 @@ static __devinit int ixp4xx_pata_probe(struct platform_device *pdev)
 	data->cs0 = devm_ioremap(&pdev->dev, cs0->start, 0x1000);
 	data->cs1 = devm_ioremap(&pdev->dev, cs1->start, 0x1000);
 
+	if (!data->cs0 || !data->cs1)
+		return -ENOMEM;
+
 	irq = platform_get_irq(pdev, 0);
 	if (irq)
 		set_irq_type(irq, IRQT_RISING);

drivers/ata/pata_marvell.c

@@ -44,10 +44,10 @@ static int marvell_pre_reset(struct ata_port *ap, unsigned long deadline)
 		return -ENOMEM;
 	printk("BAR5:");
 	for(i = 0; i <= 0x0F; i++)
-		printk("%02X:%02X ", i, readb(barp + i));
+		printk("%02X:%02X ", i, ioread8(barp + i));
 	printk("\n");
 
-	devices = readl(barp + 0x0C);
+	devices = ioread32(barp + 0x0C);
 	pci_iounmap(pdev, barp);
 
 	if ((pdev->device == 0x6145) && (ap->port_no == 0) &&

drivers/ata/sata_mv.c

@@ -313,7 +313,10 @@ enum {
 #define IS_GEN_IIE(hpriv) ((hpriv)->hp_flags & MV_HP_GEN_IIE)
 
 enum {
-	MV_DMA_BOUNDARY		= 0xffffffffU,
+	/* DMA boundary 0xffff is required by the s/g splitting
+	 * we need on /length/ in mv_fill-sg().
+	 */
+	MV_DMA_BOUNDARY		= 0xffffU,
 
 	/* mask of register bits containing lower 32 bits
 	 * of EDMA request queue DMA address
@@ -448,7 +451,7 @@ static struct scsi_host_template mv5_sht = {
 	.queuecommand		= ata_scsi_queuecmd,
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
-	.sg_tablesize		= MV_MAX_SG_CT,
+	.sg_tablesize		= MV_MAX_SG_CT / 2,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= 1,
@@ -466,7 +469,7 @@ static struct scsi_host_template mv6_sht = {
 	.queuecommand		= ata_scsi_queuecmd,
 	.can_queue		= ATA_DEF_QUEUE,
 	.this_id		= ATA_SHT_THIS_ID,
-	.sg_tablesize		= MV_MAX_SG_CT,
+	.sg_tablesize		= MV_MAX_SG_CT / 2,
 	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
 	.emulated		= ATA_SHT_EMULATED,
 	.use_clustering		= 1,
@@ -1139,15 +1142,27 @@ static unsigned int mv_fill_sg(struct ata_queued_cmd *qc)
 		dma_addr_t addr = sg_dma_address(sg);
 		u32 sg_len = sg_dma_len(sg);
 
-		mv_sg->addr = cpu_to_le32(addr & 0xffffffff);
-		mv_sg->addr_hi = cpu_to_le32((addr >> 16) >> 16);
-		mv_sg->flags_size = cpu_to_le32(sg_len & 0xffff);
+		while (sg_len) {
+			u32 offset = addr & 0xffff;
+			u32 len = sg_len;
+
+			if ((offset + sg_len > 0x10000))
+				len = 0x10000 - offset;
+
+			mv_sg->addr = cpu_to_le32(addr & 0xffffffff);
+			mv_sg->addr_hi = cpu_to_le32((addr >> 16) >> 16);
+			mv_sg->flags_size = cpu_to_le32(len);
 
-		if (ata_sg_is_last(sg, qc))
-			mv_sg->flags_size |= cpu_to_le32(EPRD_FLAG_END_OF_TBL);
+			sg_len -= len;
+			addr += len;
+
+			if (!sg_len && ata_sg_is_last(sg, qc))
+				mv_sg->flags_size |= cpu_to_le32(EPRD_FLAG_END_OF_TBL);
+
+			mv_sg++;
+			n_sg++;
+		}
 
-		mv_sg++;
-		n_sg++;
 	}
 
 	return n_sg;

drivers/base/core.c

@@ -586,9 +586,13 @@ void device_initialize(struct device *dev)
 static struct kobject * get_device_parent(struct device *dev,
 					  struct device *parent)
 {
-	/* Set the parent to the class, not the parent device */
-	/* this keeps sysfs from having a symlink to make old udevs happy */
-	if (dev->class)
+	/*
+	 * Set the parent to the class, not the parent device
+	 * for topmost devices in class hierarchy.
+	 * This keeps sysfs from having a symlink to make old
+	 * udevs happy
+	 */
+	if (dev->class && (!parent || parent->class != dev->class))
 		return &dev->class->subsys.kobj;
 	else if (parent)
 		return &parent->kobj;

drivers/char/Makefile

@@ -129,7 +129,7 @@ $(obj)/defkeymap.o:  $(obj)/defkeymap.c
 
 ifdef GENERATE_KEYMAP
 
-$(obj)/defkeymap.c $(obj)/%.c: $(src)/%.map
+$(obj)/defkeymap.c: $(obj)/%.c: $(src)/%.map
 	loadkeys --mktable $< > $@.tmp
 	sed -e 's/^static *//' $@.tmp > $@
 	rm $@.tmp

drivers/char/agp/intel-agp.c

@@ -506,11 +506,6 @@ static void intel_i830_init_gtt_entries(void)
 			break;
 		}
 	} else {
-		/* G33's GTT stolen memory is separate from gfx data
-		 * stolen memory.
-		 */
-		if (IS_G33)
-			size = 0;
 		switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
 		case I855_GMCH_GMS_STOLEN_1M:
 			gtt_entries = MB(1) - KB(size);

drivers/char/random.c

@@ -1550,11 +1550,13 @@ __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 	 *	As close as possible to RFC 793, which
 	 *	suggests using a 250 kHz clock.
 	 *	Further reading shows this assumes 2 Mb/s networks.
-	 *	For 10 Gb/s Ethernet, a 1 GHz clock is appropriate.
-	 *	That's funny, Linux has one built in!  Use it!
-	 *	(Networks are faster now - should this be increased?)
+	 *	For 10 Mb/s Ethernet, a 1 MHz clock is appropriate.
+	 *	For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but
+	 *	we also need to limit the resolution so that the u32 seq
+	 *	overlaps less than one time per MSL (2 minutes).
+	 *	Choosing a clock of 64 ns period is OK. (period of 274 s)
 	 */
-	seq += ktime_get_real().tv64;
+	seq += ktime_get_real().tv64 >> 6;
 #if 0
 	printk("init_seq(%lx, %lx, %d, %d) = %d\n",
 	       saddr, daddr, sport, dport, seq);

drivers/char/vt_ioctl.c

@@ -770,6 +770,7 @@ int vt_ioctl(struct tty_struct *tty, struct file * file,
 		/*
 		 * Switching-from response
 		 */
+		acquire_console_sem();
 		if (vc->vt_newvt >= 0) {
 			if (arg == 0)
 				/*
@@ -784,7 +785,6 @@ int vt_ioctl(struct tty_struct *tty, struct file * file,
 				 * complete the switch.
 				 */
 				int newvt;
-				acquire_console_sem();
 				newvt = vc->vt_newvt;
 				vc->vt_newvt = -1;
 				i = vc_allocate(newvt);
@@ -798,7 +798,6 @@ int vt_ioctl(struct tty_struct *tty, struct file * file,
 				 * other console switches..
 				 */
 				complete_change_console(vc_cons[newvt].d);
-				release_console_sem();
 			}
 		}
 
@@ -810,9 +809,12 @@ int vt_ioctl(struct tty_struct *tty, struct file * file,
 			/*
 			 * If it's just an ACK, ignore it
 			 */
-			if (arg != VT_ACKACQ)
+			if (arg != VT_ACKACQ) {
+				release_console_sem();
 				return -EINVAL;
+			}
 		}
+		release_console_sem();
 
 		return 0;
 
@@ -1030,7 +1032,7 @@ static DECLARE_WAIT_QUEUE_HEAD(vt_activate_queue);
 
 /*
  * Sleeps until a vt is activated, or the task is interrupted. Returns
- * 0 if activation, -EINTR if interrupted.
+ * 0 if activation, -EINTR if interrupted by a signal handler.
  */
 int vt_waitactive(int vt)
 {
@@ -1055,7 +1057,7 @@ int vt_waitactive(int vt)
 			break;
 		}
 		release_console_sem();
-		retval = -EINTR;
+		retval = -ERESTARTNOHAND;
 		if (signal_pending(current))
 			break;
 		schedule();

drivers/firewire/Kconfig

@@ -11,7 +11,8 @@ config FIREWIRE
 	  This is the "Juju" FireWire stack, a new alternative implementation
 	  designed for robustness and simplicity.  You can build either this
 	  stack, or the classic stack (the ieee1394 driver, ohci1394 etc.)
-	  or both.
+	  or both.  Please read http://wiki.linux1394.org/JujuMigration before
+	  you enable the new stack.
 
 	  To compile this driver as a module, say M here: the module will be
 	  called firewire-core.  It functionally replaces ieee1394, raw1394,

drivers/ide/ppc/pmac.c

@@ -1546,6 +1546,7 @@ static struct pci_device_id pmac_ide_pci_match[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{ PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_IPID2_ATA,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
+	{},
 };
 
 static struct pci_driver pmac_ide_pci_driver = {

drivers/isdn/i4l/isdn_common.c

@@ -1135,7 +1135,7 @@ isdn_read(struct file *file, char __user *buf, size_t count, loff_t * off)
 			if (count > dev->drv[drvidx]->stavail)
 				count = dev->drv[drvidx]->stavail;
 			len = dev->drv[drvidx]->interface->readstat(buf, count,
-						drvidx, isdn_minor2chan(minor));
+				drvidx, isdn_minor2chan(minor - ISDN_MINOR_CTRL));
 			if (len < 0) {
 				retval = len;
 				goto out;
@@ -1207,7 +1207,8 @@ isdn_write(struct file *file, const char __user *buf, size_t count, loff_t * off
 		 */
 		if (dev->drv[drvidx]->interface->writecmd)
 			retval = dev->drv[drvidx]->interface->
-				writecmd(buf, count, drvidx, isdn_minor2chan(minor));
+				writecmd(buf, count, drvidx,
+				isdn_minor2chan(minor - ISDN_MINOR_CTRL));
 		else
 			retval = count;
 		goto out;

drivers/media/video/ivtv/ivtv-fileops.c

@@ -754,9 +754,11 @@ static void ivtv_stop_decoding(struct ivtv_open_id *id, int flags, u64 pts)
 		ivtv_yuv_close(itv);
 	}
 	if (s->type == IVTV_DEC_STREAM_TYPE_YUV && itv->output_mode == OUT_YUV)
-	    itv->output_mode = OUT_NONE;
+		itv->output_mode = OUT_NONE;
+	else if (s->type == IVTV_DEC_STREAM_TYPE_YUV && itv->output_mode == OUT_UDMA_YUV)
+		itv->output_mode = OUT_NONE;
 	else if (s->type == IVTV_DEC_STREAM_TYPE_MPG && itv->output_mode == OUT_MPG)
-	    itv->output_mode = OUT_NONE;
+		itv->output_mode = OUT_NONE;
 
 	itv->speed = 0;
 	clear_bit(IVTV_F_I_DEC_PAUSED, &itv->i_flags);

drivers/net/mv643xx_eth.c

@@ -1357,7 +1357,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 #endif
 
 	dev->watchdog_timeo = 2 * HZ;
-	dev->tx_queue_len = mp->tx_ring_size;
 	dev->base_addr = 0;
 	dev->change_mtu = mv643xx_eth_change_mtu;
 	dev->do_ioctl = mv643xx_eth_do_ioctl;

drivers/net/qla3xxx.c

@@ -2248,6 +2248,13 @@ static int ql_tx_rx_clean(struct ql3_adapter *qdev,
 		qdev->rsp_consumer_index) && (work_done < work_to_do)) {
 
 		net_rsp = qdev->rsp_current;
+		rmb();
+		/*
+		 * Fix 4032 chipe undocumented "feature" where bit-8 is set if the
+		 * inbound completion is for a VLAN.
+		 */
+		if (qdev->device_id == QL3032_DEVICE_ID)
+			net_rsp->opcode &= 0x7f;
 		switch (net_rsp->opcode) {
 
 		case OPCODE_OB_MAC_IOCB_FN0:

drivers/net/r8169.c

@@ -1918,7 +1918,11 @@ static void rtl_hw_start_8169(struct net_device *dev)
 
 	rtl_set_rx_max_size(ioaddr);
 
-	rtl_set_rx_tx_config_registers(tp);
+	if ((tp->mac_version == RTL_GIGA_MAC_VER_01) ||
+	    (tp->mac_version == RTL_GIGA_MAC_VER_02) ||
+	    (tp->mac_version == RTL_GIGA_MAC_VER_03) ||
+	    (tp->mac_version == RTL_GIGA_MAC_VER_04))
+		rtl_set_rx_tx_config_registers(tp);
 
 	tp->cp_cmd |= rtl_rw_cpluscmd(ioaddr) | PCIMulRW;
 
@@ -1941,6 +1945,14 @@ static void rtl_hw_start_8169(struct net_device *dev)
 
 	rtl_set_rx_tx_desc_registers(tp, ioaddr);
 
+	if ((tp->mac_version != RTL_GIGA_MAC_VER_01) &&
+	    (tp->mac_version != RTL_GIGA_MAC_VER_02) &&
+	    (tp->mac_version != RTL_GIGA_MAC_VER_03) &&
+	    (tp->mac_version != RTL_GIGA_MAC_VER_04)) {
+		RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb);
+		rtl_set_rx_tx_config_registers(tp);
+	}
+
 	RTL_W8(Cfg9346, Cfg9346_Lock);
 
 	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
@@ -1955,8 +1967,6 @@ static void rtl_hw_start_8169(struct net_device *dev)
 
 	/* Enable all known interrupts by setting the interrupt mask. */
 	RTL_W16(IntrMask, tp->intr_event);
-
-	RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb);
 }
 
 static void rtl_hw_start_8168(struct net_device *dev)

drivers/net/sky2.c

@@ -2163,9 +2163,6 @@ static struct sk_buff *sky2_receive(struct net_device *dev,
 	sky2->rx_next = (sky2->rx_next + 1) % sky2->rx_pending;
 	prefetch(sky2->rx_ring + sky2->rx_next);
 
-	if (length < ETH_ZLEN || length > sky2->rx_data_size)
-		goto len_error;
-
 	/* This chip has hardware problems that generates bogus status.
 	 * So do only marginal checking and expect higher level protocols
 	 * to handle crap frames.

drivers/net/usb/dm9601.c

@@ -405,7 +405,7 @@ static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->ethtool_ops = &dm9601_ethtool_ops;
 	dev->net->hard_header_len += DM_TX_OVERHEAD;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
-	dev->rx_urb_size = dev->net->mtu + DM_RX_OVERHEAD;
+	dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD;
 
 	dev->mii.dev = dev->net;
 	dev->mii.mdio_read = dm9601_mdio_read;

drivers/net/wireless/Makefile

@@ -43,7 +43,7 @@ obj-$(CONFIG_PCMCIA_RAYCS)	+= ray_cs.o
 obj-$(CONFIG_PCMCIA_WL3501)	+= wl3501_cs.o
 
 obj-$(CONFIG_USB_ZD1201)	+= zd1201.o
-obj-$(CONFIG_LIBERTAS_USB)     += libertas/
+obj-$(CONFIG_LIBERTAS)		+= libertas/
 
 rtl8187-objs		:= rtl8187_dev.o rtl8187_rtl8225.o
 obj-$(CONFIG_RTL8187)	+= rtl8187.o

drivers/net/wireless/bcm43xx/bcm43xx_wx.c

@@ -444,7 +444,7 @@ static int bcm43xx_wx_set_xmitpower(struct net_device *net_dev,
 	u16 maxpower;
 
 	if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) {
-		printk(PFX KERN_ERR "TX power not in dBm.\n");
+		printk(KERN_ERR PFX "TX power not in dBm.\n");
 		return -EOPNOTSUPP;
 	}
 

drivers/scsi/aic94xx/aic94xx_task.c

@@ -451,7 +451,7 @@ static int asd_build_smp_ascb(struct asd_ascb *ascb, struct sas_task *task,
 	struct scb *scb;
 
 	pci_map_sg(asd_ha->pcidev, &task->smp_task.smp_req, 1,
-		   PCI_DMA_FROMDEVICE);
+		   PCI_DMA_TODEVICE);
 	pci_map_sg(asd_ha->pcidev, &task->smp_task.smp_resp, 1,
 		   PCI_DMA_FROMDEVICE);
 
@@ -486,7 +486,7 @@ static void asd_unbuild_smp_ascb(struct asd_ascb *a)
 
 	BUG_ON(!task);
 	pci_unmap_sg(a->ha->pcidev, &task->smp_task.smp_req, 1,
-		     PCI_DMA_FROMDEVICE);
+		     PCI_DMA_TODEVICE);
 	pci_unmap_sg(a->ha->pcidev, &task->smp_task.smp_resp, 1,
 		     PCI_DMA_FROMDEVICE);
 }

drivers/scsi/megaraid.c

@@ -1753,6 +1753,14 @@ mega_build_sglist(adapter_t *adapter, scb_t *scb, u32 *buf, u32 *len)
 
 	*len = 0;
 
+	if (scsi_sg_count(cmd) == 1 && !adapter->has_64bit_addr) {
+		sg = scsi_sglist(cmd);
+		scb->dma_h_bulkdata = sg_dma_address(sg);
+		*buf = (u32)scb->dma_h_bulkdata;
+		*len = sg_dma_len(sg);
+		return 0;
+	}
+
 	scsi_for_each_sg(cmd, sg, sgcnt, idx) {
 		if (adapter->has_64bit_addr) {
 			scb->sgl64[idx].address = sg_dma_address(sg);

drivers/serial/serial_cs.c

@@ -943,6 +943,7 @@ static struct pcmcia_device_id serial_ids[] = {
 	PCMCIA_MFC_DEVICE_PROD_ID12(1,"Elan","Serial Port: SL432",0x3beb8cf2,0x1cce7ac4),
 	PCMCIA_MFC_DEVICE_PROD_ID12(2,"Elan","Serial Port: SL432",0x3beb8cf2,0x1cce7ac4),
 	PCMCIA_MFC_DEVICE_PROD_ID12(3,"Elan","Serial Port: SL432",0x3beb8cf2,0x1cce7ac4),
+	PCMCIA_DEVICE_MANF_CARD(0x0279, 0x950b),
 	/* too generic */
 	/* PCMCIA_MFC_DEVICE_MANF_CARD(0, 0x0160, 0x0002), */
 	/* PCMCIA_MFC_DEVICE_MANF_CARD(1, 0x0160, 0x0002), */

fs/aio.c

@@ -1562,6 +1562,7 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		fput(file);
 		return -EAGAIN;
 	}
+	req->ki_filp = file;
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
@@ -1576,7 +1577,6 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		}
 	}
 
-	req->ki_filp = file;
 	ret = put_user(req->ki_key, &user_iocb->aio_key);
 	if (unlikely(ret)) {
 		dprintk("EFAULT: aio_key\n");

fs/binfmt_flat.c

@@ -742,6 +742,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 	 * __start to address 4 so that is okay).
 	 */
 	if (rev > OLD_FLAT_VERSION) {
+		unsigned long persistent = 0;
 		for (i=0; i < relocs; i++) {
 			unsigned long addr, relval;
 
@@ -749,6 +750,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 			   relocated (of course, the address has to be
 			   relocated first).  */
 			relval = ntohl(reloc[i]);
+			if (flat_set_persistent (relval, &persistent))
+				continue;
 			addr = flat_get_relocate_addr(relval);
 			rp = (unsigned long *) calc_reloc(addr, libinfo, id, 1);
 			if (rp == (unsigned long *)RELOC_FAILED) {
@@ -757,7 +760,8 @@ static int load_flat_file(struct linux_binprm * bprm,
 			}
 
 			/* Get the pointer's value.  */
-			addr = flat_get_addr_from_rp(rp, relval, flags);
+			addr = flat_get_addr_from_rp(rp, relval, flags,
+							&persistent);
 			if (addr != 0) {
 				/*
 				 * Do the relocation.  PIC relocs in the data section are

fs/lockd/svclock.c

@@ -485,8 +485,10 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 			return nlm_granted;
 		/* Create host handle for callback */
 		host = nlmsvc_lookup_host(rqstp, lock->caller, lock->len);
-		if (host == NULL)
+		if (host == NULL) {
+			kfree(conf);
 			return nlm_lck_denied_nolocks;
+		}
 		block = nlmsvc_create_block(rqstp, host, file, lock, cookie);
 		if (block == NULL) {
 			kfree(conf);

fs/ocfs2/localalloc.c

@@ -514,8 +514,10 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 	ac->ac_bh = osb->local_alloc_bh;
 	status = 0;
 bail:
-	if (status < 0 && local_alloc_inode)
+	if (status < 0 && local_alloc_inode) {
+		mutex_unlock(&local_alloc_inode->i_mutex);
 		iput(local_alloc_inode);
+	}
 
 	mlog_exit(status);
 	return status;

fs/splice.c

@@ -1223,6 +1223,33 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 	return -EINVAL;
 }
 
+/*
+ * Do a copy-from-user while holding the mmap_semaphore for reading, in a
+ * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
+ * for writing) and page faulting on the user memory pointed to by src.
+ * This assumes that we will very rarely hit the partial != 0 path, or this
+ * will not be a win.
+ */
+static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
+{
+	int partial;
+
+	pagefault_disable();
+	partial = __copy_from_user_inatomic(dst, src, n);
+	pagefault_enable();
+
+	/*
+	 * Didn't copy everything, drop the mmap_sem and do a faulting copy
+	 */
+	if (unlikely(partial)) {
+		up_read(&current->mm->mmap_sem);
+		partial = copy_from_user(dst, src, n);
+		down_read(&current->mm->mmap_sem);
+	}
+
+	return partial;
+}
+
 /*
  * Map an iov into an array of pages and offset/length tupples. With the
  * partial_page structure, we can map several non-contiguous ranges into
@@ -1236,31 +1263,26 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 {
 	int buffers = 0, error = 0;
 
-	/*
-	 * It's ok to take the mmap_sem for reading, even
-	 * across a "get_user()".
-	 */
 	down_read(&current->mm->mmap_sem);
 
 	while (nr_vecs) {
 		unsigned long off, npages;
+		struct iovec entry;
 		void __user *base;
 		size_t len;
 		int i;
 
-		/*
-		 * Get user address base and length for this iovec.
-		 */
-		error = get_user(base, &iov->iov_base);
-		if (unlikely(error))
-			break;
-		error = get_user(len, &iov->iov_len);
-		if (unlikely(error))
+		error = -EFAULT;
+		if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
 			break;
 
+		base = entry.iov_base;
+		len = entry.iov_len;
+
 		/*
 		 * Sanity check this iovec. 0 read succeeds.
 		 */
+		error = 0;
 		if (unlikely(!len))
 			break;
 		error = -EFAULT;

include/asm-blackfin/mach-bf533/bfin_serial_5xx.h

@@ -1,5 +1,6 @@
 #include <linux/serial.h>
 #include <asm/dma.h>
+#include <asm/portmux.h>
 
 #define NR_PORTS                1
 
@@ -92,18 +93,24 @@ struct bfin_serial_res bfin_serial_resource[] = {
 	}
 };
 
+#define DRIVER_NAME "bfin-uart"
 
 int nr_ports = NR_PORTS;
 static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 {
 
+#ifdef CONFIG_SERIAL_BFIN_UART0
+	peripheral_request(P_UART0_TX, DRIVER_NAME);
+	peripheral_request(P_UART0_RX, DRIVER_NAME);
+#endif
+
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
 	if (uart->cts_pin >= 0) {
-		gpio_request(uart->cts_pin, NULL);
+		gpio_request(uart->cts_pin, DRIVER_NAME);
 		gpio_direction_input(uart->cts_pin);
 	}
 	if (uart->rts_pin >= 0) {
-		gpio_request(uart->rts_pin, NULL);
+		gpio_request(uart->rts_pin, DRIVER_NAME);
 		gpio_direction_input(uart->rts_pin);
 	}
 #endif

include/asm-blackfin/mach-bf537/bfin_serial_5xx.h

@@ -1,5 +1,6 @@
 #include <linux/serial.h>
 #include <asm/dma.h>
+#include <asm/portmux.h>
 
 #define NR_PORTS		2
 
@@ -122,25 +123,29 @@ struct bfin_serial_res bfin_serial_resource[] = {
 
 int nr_ports = ARRAY_SIZE(bfin_serial_resource);
 
+#define DRIVER_NAME "bfin-uart"
+
 static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 {
-	unsigned short val;
-	val = bfin_read16(BFIN_PORT_MUX);
-	val &= ~(PFDE | PFTE);
-	bfin_write16(BFIN_PORT_MUX, val);
 
-	val = bfin_read16(PORTF_FER);
-	val |= 0xF;
-	bfin_write16(PORTF_FER, val);
+#ifdef CONFIG_SERIAL_BFIN_UART0
+	peripheral_request(P_UART0_TX, DRIVER_NAME);
+	peripheral_request(P_UART0_RX, DRIVER_NAME);
+#endif
+
+#ifdef CONFIG_SERIAL_BFIN_UART1
+	peripheral_request(P_UART1_TX, DRIVER_NAME);
+	peripheral_request(P_UART1_RX, DRIVER_NAME);
+#endif
 
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
 	if (uart->cts_pin >= 0) {
-		gpio_request(uart->cts_pin, NULL);
+		gpio_request(uart->cts_pin, DRIVER_NAME);
 		gpio_direction_input(uart->cts_pin);
 	}
 
 	if (uart->rts_pin >= 0) {
-		gpio_request(uart->rts_pin, NULL);
+		gpio_request(uart->rts_pin, DRIVER_NAME);
 		gpio_direction_output(uart->rts_pin);
 	}
 #endif

include/asm-blackfin/mach-bf537/portmux.h

@@ -106,4 +106,37 @@
 #define P_SPI0_SSEL2	(P_DEFINED | P_IDENT(PORT_PJ11) | P_FUNCT(1))
 #define P_SPI0_SSEL7	(P_DEFINED | P_IDENT(PORT_PJ5) | P_FUNCT(2))
 
-#endif /* _MACH_PORTMUX_H_ */
+#define P_MII0 {\
+	P_MII0_ETxD0, \
+	P_MII0_ETxD1, \
+	P_MII0_ETxD2, \
+	P_MII0_ETxD3, \
+	P_MII0_ETxEN, \
+	P_MII0_TxCLK, \
+	P_MII0_PHYINT, \
+	P_MII0_COL, \
+	P_MII0_ERxD0, \
+	P_MII0_ERxD1, \
+	P_MII0_ERxD2, \
+	P_MII0_ERxD3, \
+	P_MII0_ERxDV, \
+	P_MII0_ERxCLK, \
+	P_MII0_ERxER, \
+	P_MII0_CRS, \
+	P_MDC, \
+	P_MDIO, 0}
+
+
+#define P_RMII0 {\
+	P_MII0_ETxD0, \
+	P_MII0_ETxD1, \
+	P_MII0_ETxEN, \
+	P_MII0_ERxD0, \
+	P_MII0_ERxD1, \
+	P_MII0_ERxER, \
+	P_RMII0_REF_CLK, \
+	P_RMII0_MDINT, \
+	P_RMII0_CRS_DV, \
+	P_MDC, \
+	P_MDIO, 0}
+#endif			        	/* _MACH_PORTMUX_H_ */

include/asm-blackfin/mach-bf561/bfin_serial_5xx.h

@@ -1,5 +1,6 @@
 #include <linux/serial.h>
 #include <asm/dma.h>
+#include <asm/portmux.h>
 
 #define NR_PORTS                1
 
@@ -92,18 +93,24 @@ struct bfin_serial_res bfin_serial_resource[] = {
 	}
 };
 
+#define DRIVER_NAME "bfin-uart"
 
 int nr_ports = NR_PORTS;
 static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 {
 
+#ifdef CONFIG_SERIAL_BFIN_UART0
+	peripheral_request(P_UART0_TX, DRIVER_NAME);
+	peripheral_request(P_UART0_RX, DRIVER_NAME);
+#endif
+
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
 	if (uart->cts_pin >= 0) {
-		gpio_request(uart->cts_pin, NULL);
+		gpio_request(uart->cts_pin, DRIVER_NAME);
 		gpio_direction_input(uart->cts_pin);
 	}
 	if (uart->rts_pin >= 0) {
-		gpio_request(uart->rts_pin, NULL);
+		gpio_request(uart->rts_pin, DRIVER_NAME);
 		gpio_direction_input(uart->rts_pin);
 	}
 #endif

include/asm-blackfin/portmux.h

@@ -14,6 +14,12 @@
 #define P_MAYSHARE	0x2000
 #define P_DONTCARE	0x1000
 
+
+int peripheral_request(unsigned short per, const char *label);
+void peripheral_free(unsigned short per);
+int peripheral_request_list(unsigned short per[], const char *label);
+void peripheral_free_list(unsigned short per[]);
+
 #include <asm/gpio.h>
 #include <asm/mach/portmux.h>
 
@@ -145,6 +151,22 @@
 #define P_SPI2_SSEL3 P_UNDEF
 #endif
 
+#ifndef P_SPI2_SSEL4
+#define P_SPI2_SSEL4 P_UNDEF
+#endif
+
+#ifndef P_SPI2_SSEL5
+#define P_SPI2_SSEL5 P_UNDEF
+#endif
+
+#ifndef P_SPI2_SSEL6
+#define P_SPI2_SSEL6 P_UNDEF
+#endif
+
+#ifndef P_SPI2_SSEL7
+#define P_SPI2_SSEL7 P_UNDEF
+#endif
+
 #ifndef P_SPI2_SCK
 #define P_SPI2_SCK P_UNDEF
 #endif
@@ -513,6 +535,22 @@
 #define P_SPI0_SSEL3 P_UNDEF
 #endif
 
+#ifndef P_SPI0_SSEL4
+#define P_SPI0_SSEL4 P_UNDEF
+#endif
+
+#ifndef P_SPI0_SSEL5
+#define P_SPI0_SSEL5 P_UNDEF
+#endif
+
+#ifndef P_SPI0_SSEL6
+#define P_SPI0_SSEL6 P_UNDEF
+#endif
+
+#ifndef P_SPI0_SSEL7
+#define P_SPI0_SSEL7 P_UNDEF
+#endif
+
 #ifndef P_UART0_TX
 #define P_UART0_TX P_UNDEF
 #endif
@@ -741,6 +779,23 @@
 #define P_SPI1_SSEL3 P_UNDEF
 #endif
 
+
+#ifndef P_SPI1_SSEL4
+#define P_SPI1_SSEL4 P_UNDEF
+#endif
+
+#ifndef P_SPI1_SSEL5
+#define P_SPI1_SSEL5 P_UNDEF
+#endif
+
+#ifndef P_SPI1_SSEL6
+#define P_SPI1_SSEL6 P_UNDEF
+#endif
+
+#ifndef P_SPI1_SSEL7
+#define P_SPI1_SSEL7 P_UNDEF
+#endif
+
 #ifndef P_SPI1_SCK
 #define P_SPI1_SCK P_UNDEF
 #endif

include/asm-blackfin/unistd.h

@@ -3,6 +3,7 @@
 /*
  * This file contains the system call numbers.
  */
+#define __NR_restart_syscall	  0
 #define __NR_exit		  1
 #define __NR_fork		  2
 #define __NR_read		  3
@@ -165,13 +166,13 @@
 #define __NR_sched_get_priority_min	160
 #define __NR_sched_rr_get_interval	161
 #define __NR_nanosleep		162
-				/* 163 __NR_mremap */
+#define __NR_mremap		163
 #define __NR_setresuid		164
 #define __NR_getresuid		165
 				/* 166 __NR_vm86 */
 				/* 167 __NR_query_module */
 				/* 168 __NR_poll */
-				/* 169 __NR_nfsservctl */
+#define __NR_nfsservctl		169
 #define __NR_setresgid		170
 #define __NR_getresgid		171
 #define __NR_prctl		172
@@ -227,7 +228,7 @@
 				/* 222 reserved for TUX */
 				/* 223 reserved for TUX */
 #define __NR_gettid		224
-				/* 225 __NR_readahead */
+#define __NR_readahead		225
 #define __NR_setxattr		226
 #define __NR_lsetxattr		227
 #define __NR_fsetxattr		228
@@ -287,7 +288,7 @@
 #define __NR_mq_timedreceive	(__NR_mq_open+3)
 #define __NR_mq_notify		(__NR_mq_open+4)
 #define __NR_mq_getsetattr	(__NR_mq_open+5)
-				/* 284 __NR_sys_kexec_load */
+#define __NR_kexec_load		284
 #define __NR_waitid		285
 #define __NR_add_key		286
 #define __NR_request_key	287
@@ -352,9 +353,54 @@
 #define __NR_shmdt		340
 #define __NR_shmget		341
 
-#define __NR_syscall		342
+#define __NR_splice		342
+#define __NR_sync_file_range	343
+#define __NR_tee		344
+#define __NR_vmsplice		345
+
+#define __NR_epoll_pwait	346
+#define __NR_utimensat		347
+#define __NR_signalfd		348
+#define __NR_timerfd		349
+#define __NR_eventfd		350
+#define __NR_pread64		351
+#define __NR_pwrite64		352
+#define __NR_fadvise64		353
+#define __NR_set_robust_list	354
+#define __NR_get_robust_list	355
+#define __NR_fallocate		356
+
+#define __NR_syscall		357
 #define NR_syscalls		__NR_syscall
 
+/* Old optional stuff no one actually uses */
+#define __IGNORE_sysfs
+#define __IGNORE_uselib
+
+/* Implement the newer interfaces */
+#define __IGNORE_mmap
+#define __IGNORE_poll
+#define __IGNORE_select
+#define __IGNORE_utime
+
+/* Not relevant on no-mmu */
+#define __IGNORE_swapon
+#define __IGNORE_swapoff
+#define __IGNORE_msync
+#define __IGNORE_mlock
+#define __IGNORE_munlock
+#define __IGNORE_mlockall
+#define __IGNORE_munlockall
+#define __IGNORE_mincore
+#define __IGNORE_madvise
+#define __IGNORE_remap_file_pages
+#define __IGNORE_mbind
+#define __IGNORE_get_mempolicy
+#define __IGNORE_set_mempolicy
+#define __IGNORE_migrate_pages
+#define __IGNORE_move_pages
+#define __IGNORE_getcpu
+
 #ifdef __KERNEL__
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64

include/asm-h8300/flat.h

@@ -9,6 +9,7 @@
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		1
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
+#define	flat_set_persistent(relval, p)		0
 
 /*
  * on the H8 a couple of the relocations have an instruction in the
@@ -18,7 +19,7 @@
  */
 
 #define	flat_get_relocate_addr(rel)		(rel)
-#define flat_get_addr_from_rp(rp, relval, flags) \
+#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
         (get_unaligned(rp) & ((flags & FLAT_FLAG_GOTPIC) ? 0xffffffff: 0x00ffffff))
 #define flat_put_addr_at_rp(rp, addr, rel) \
 	put_unaligned (((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), rp)

include/asm-m32r/flat.h

@@ -15,9 +15,10 @@
 #define	flat_stack_align(sp)		(*sp += (*sp & 3 ? (4 - (*sp & 3)): 0))
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
+#define	flat_set_persistent(relval, p)		0
 #define	flat_reloc_valid(reloc, size)		\
 	(((reloc) - textlen_for_m32r_lo16_data) <= (size))
-#define flat_get_addr_from_rp(rp, relval, flags) \
+#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
 	m32r_flat_get_addr_from_rp(rp, relval, (text_len) )
 
 #define flat_put_addr_at_rp(rp, addr, relval) \

include/asm-m68knommu/flat.h

@@ -9,8 +9,9 @@
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags)	get_unaligned(rp)
+#define	flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
 #define	flat_put_addr_at_rp(rp, val, relval)	put_unaligned(val,rp)
 #define	flat_get_relocate_addr(rel)		(rel)
+#define	flat_set_persistent(relval, p)		0
 
 #endif /* __M68KNOMMU_FLAT_H__ */

include/asm-mips/cmpxchg.h

@@ -0,0 +1,107 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
+ */
+#ifndef __ASM_CMPXCHG_H
+#define __ASM_CMPXCHG_H
+
+#include <linux/irqflags.h>
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+#define __cmpxchg_asm(ld, st, m, old, new)				\
+({									\
+	__typeof(*(m)) __ret;						\
+									\
+	if (cpu_has_llsc && R10000_LLSC_WAR) {				\
+		__asm__ __volatile__(					\
+		"	.set	push				\n"	\
+		"	.set	noat				\n"	\
+		"	.set	mips3				\n"	\
+		"1:	" ld "	%0, %2		# __cmpxchg_asm	\n"	\
+		"	bne	%0, %z3, 2f			\n"	\
+		"	.set	mips0				\n"	\
+		"	move	$1, %z4				\n"	\
+		"	.set	mips3				\n"	\
+		"	" st "	$1, %1				\n"	\
+		"	beqzl	$1, 1b				\n"	\
+		"2:						\n"	\
+		"	.set	pop				\n"	\
+		: "=&r" (__ret), "=R" (*m)				\
+		: "R" (*m), "Jr" (old), "Jr" (new)			\
+		: "memory");						\
+	} else if (cpu_has_llsc) {					\
+		__asm__ __volatile__(					\
+		"	.set	push				\n"	\
+		"	.set	noat				\n"	\
+		"	.set	mips3				\n"	\
+		"1:	" ld "	%0, %2		# __cmpxchg_asm	\n"	\
+		"	bne	%0, %z3, 2f			\n"	\
+		"	.set	mips0				\n"	\
+		"	move	$1, %z4				\n"	\
+		"	.set	mips3				\n"	\
+		"	" st "	$1, %1				\n"	\
+		"	beqz	$1, 3f				\n"	\
+		"2:						\n"	\
+		"	.subsection 2				\n"	\
+		"3:	b	1b				\n"	\
+		"	.previous				\n"	\
+		"	.set	pop				\n"	\
+		: "=&r" (__ret), "=R" (*m)				\
+		: "R" (*m), "Jr" (old), "Jr" (new)			\
+		: "memory");						\
+	} else {							\
+		unsigned long __flags;					\
+									\
+		raw_local_irq_save(__flags);				\
+		__ret = *m;						\
+		if (__ret == old)					\
+			*m = new;					\
+		raw_local_irq_restore(__flags);				\
+	}								\
+									\
+	__ret;								\
+})
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+#define __cmpxchg(ptr,old,new,barrier)					\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	__typeof__(*(ptr)) __res = 0;					\
+									\
+	barrier;							\
+									\
+	switch (sizeof(*(__ptr))) {					\
+	case 4:								\
+		__res = __cmpxchg_asm("ll", "sc", __ptr, __old, __new);	\
+		break;							\
+	case 8:								\
+		if (sizeof(long) == 8) {				\
+			__res = __cmpxchg_asm("lld", "scd", __ptr,	\
+					   __old, __new);		\
+			break;						\
+		}							\
+	default:							\
+		__cmpxchg_called_with_bad_pointer();			\
+		break;							\
+	}								\
+									\
+	barrier;							\
+									\
+	__res;								\
+})
+
+#define cmpxchg(ptr, old, new)		__cmpxchg(ptr, old, new, smp_llsc_mb())
+#define cmpxchg_local(ptr, old, new)	__cmpxchg(ptr, old, new,)
+
+#endif /* __ASM_CMPXCHG_H */

include/asm-mips/fcntl.h

@@ -13,6 +13,7 @@
 #define O_SYNC		0x0010
 #define O_NONBLOCK	0x0080
 #define O_CREAT         0x0100	/* not fcntl */
+#define O_TRUNC		0x0200	/* not fcntl */
 #define O_EXCL		0x0400	/* not fcntl */
 #define O_NOCTTY	0x0800	/* not fcntl */
 #define FASYNC		0x1000	/* fcntl, for BSD compatibility */

include/asm-mips/local.h

@@ -4,6 +4,7 @@
 #include <linux/percpu.h>
 #include <linux/bitops.h>
 #include <asm/atomic.h>
+#include <asm/cmpxchg.h>
 #include <asm/war.h>
 
 typedef struct
@@ -114,68 +115,6 @@ static __inline__ long local_sub_return(long i, local_t * l)
 	return result;
 }
 
-/*
- * local_sub_if_positive - conditionally subtract integer from atomic variable
- * @i: integer value to subtract
- * @l: pointer of type local_t
- *
- * Atomically test @l and subtract @i if @l is greater or equal than @i.
- * The function returns the old value of @l minus @i.
- */
-static __inline__ long local_sub_if_positive(long i, local_t * l)
-{
-	unsigned long result;
-
-	if (cpu_has_llsc && R10000_LLSC_WAR) {
-		unsigned long temp;
-
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:"	__LL	"%1, %2		# local_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-			__SC	"%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
-		: "Ir" (i), "m" (l->a.counter)
-		: "memory");
-	} else if (cpu_has_llsc) {
-		unsigned long temp;
-
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:"	__LL	"%1, %2		# local_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-			__SC	"%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (l->a.counter)
-		: "Ir" (i), "m" (l->a.counter)
-		: "memory");
-	} else {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		result = l->a.counter;
-		result -= i;
-		if (result >= 0)
-			l->a.counter = result;
-		local_irq_restore(flags);
-	}
-
-	return result;
-}
-
 #define local_cmpxchg(l, o, n) \
 	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
 #define local_xchg(l, n) (xchg_local(&((l)->a.counter),(n)))
@@ -233,12 +172,6 @@ static __inline__ long local_sub_if_positive(long i, local_t * l)
  */
 #define local_dec_and_test(l) (local_sub_return(1, (l)) == 0)
 
-/*
- * local_dec_if_positive - decrement by 1 if old value positive
- * @l: pointer of type local_t
- */
-#define local_dec_if_positive(l)	local_sub_if_positive(1, l)
-
 /*
  * local_add_negative - add and test if negative
  * @l: pointer of type local_t

include/asm-mips/system.h

@@ -17,6 +17,7 @@
 
 #include <asm/addrspace.h>
 #include <asm/barrier.h>
+#include <asm/cmpxchg.h>
 #include <asm/cpu-features.h>
 #include <asm/dsp.h>
 #include <asm/war.h>
@@ -194,266 +195,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 
 #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG 1
-
-static inline unsigned long __cmpxchg_u32(volatile int * m, unsigned long old,
-	unsigned long new)
-{
-	__u32 retval;
-
-	if (cpu_has_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
-		"	.set	mips3					\n"
-		"	sc	$1, %1					\n"
-		"	beqzl	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else if (cpu_has_llsc) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
-		"	.set	mips3					\n"
-		"	sc	$1, %1					\n"
-		"	beqz	$1, 3f					\n"
-		"2:							\n"
-		"	.subsection 2					\n"
-		"3:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		retval = *m;
-		if (retval == old)
-			*m = new;
-		raw_local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	smp_llsc_mb();
-
-	return retval;
-}
-
-static inline unsigned long __cmpxchg_u32_local(volatile int * m,
-	unsigned long old, unsigned long new)
-{
-	__u32 retval;
-
-	if (cpu_has_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
-		"	.set	mips3					\n"
-		"	sc	$1, %1					\n"
-		"	beqzl	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else if (cpu_has_llsc) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	ll	%0, %2			# __cmpxchg_u32	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	.set	mips0					\n"
-		"	move	$1, %z4					\n"
-		"	.set	mips3					\n"
-		"	sc	$1, %1					\n"
-		"	beqz	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		retval = *m;
-		if (retval == old)
-			*m = new;
-		local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	return retval;
-}
-
-#ifdef CONFIG_64BIT
-static inline unsigned long __cmpxchg_u64(volatile int * m, unsigned long old,
-	unsigned long new)
-{
-	__u64 retval;
-
-	if (cpu_has_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	move	$1, %z4					\n"
-		"	scd	$1, %1					\n"
-		"	beqzl	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else if (cpu_has_llsc) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	move	$1, %z4					\n"
-		"	scd	$1, %1					\n"
-		"	beqz	$1, 3f					\n"
-		"2:							\n"
-		"	.subsection 2					\n"
-		"3:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else {
-		unsigned long flags;
-
-		raw_local_irq_save(flags);
-		retval = *m;
-		if (retval == old)
-			*m = new;
-		raw_local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	smp_llsc_mb();
-
-	return retval;
-}
-
-static inline unsigned long __cmpxchg_u64_local(volatile int * m,
-	unsigned long old, unsigned long new)
-{
-	__u64 retval;
-
-	if (cpu_has_llsc && R10000_LLSC_WAR) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	move	$1, %z4					\n"
-		"	scd	$1, %1					\n"
-		"	beqzl	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else if (cpu_has_llsc) {
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noat					\n"
-		"	.set	mips3					\n"
-		"1:	lld	%0, %2			# __cmpxchg_u64	\n"
-		"	bne	%0, %z3, 2f				\n"
-		"	move	$1, %z4					\n"
-		"	scd	$1, %1					\n"
-		"	beqz	$1, 1b					\n"
-		"2:							\n"
-		"	.set	pop					\n"
-		: "=&r" (retval), "=R" (*m)
-		: "R" (*m), "Jr" (old), "Jr" (new)
-		: "memory");
-	} else {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		retval = *m;
-		if (retval == old)
-			*m = new;
-		local_irq_restore(flags);	/* implies memory barrier  */
-	}
-
-	return retval;
-}
-
-#else
-extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
-	volatile int * m, unsigned long old, unsigned long new);
-#define __cmpxchg_u64 __cmpxchg_u64_unsupported_on_32bit_kernels
-extern unsigned long __cmpxchg_u64_local_unsupported_on_32bit_kernels(
-	volatile int * m, unsigned long old, unsigned long new);
-#define __cmpxchg_u64_local __cmpxchg_u64_local_unsupported_on_32bit_kernels
-#endif
-
-/* This function doesn't exist, so you'll get a linker error
-   if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
-	unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32(ptr, old, new);
-	case 8:
-		return __cmpxchg_u64(ptr, old, new);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-static inline unsigned long __cmpxchg_local(volatile void * ptr,
-	unsigned long old, unsigned long new, int size)
-{
-	switch (size) {
-	case 4:
-		return __cmpxchg_u32_local(ptr, old, new);
-	case 8:
-		return __cmpxchg_u64_local(ptr, old, new);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr,old,new) \
-	((__typeof__(*(ptr)))__cmpxchg((ptr), \
-		(unsigned long)(old), (unsigned long)(new),sizeof(*(ptr))))
-
-#define cmpxchg_local(ptr,old,new) \
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), \
-		(unsigned long)(old), (unsigned long)(new),sizeof(*(ptr))))
-
 extern void set_handler (unsigned long offset, void *addr, unsigned long len);
 extern void set_uncached_handler (unsigned long offset, void *addr, unsigned long len);
 

include/asm-sh/flat.h

@@ -16,8 +16,9 @@
 #define	flat_argvp_envp_on_stack()		0
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
-#define	flat_get_addr_from_rp(rp, relval, flags)	get_unaligned(rp)
+#define	flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
 #define	flat_put_addr_at_rp(rp, val, relval)	put_unaligned(val,rp)
 #define	flat_get_relocate_addr(rel)		(rel)
+#define	flat_set_persistent(relval, p)		0
 
 #endif /* __ASM_SH_FLAT_H */

include/asm-v850/flat.h

@@ -25,6 +25,7 @@
 #define	flat_stack_align(sp)		/* nothing needed */
 #define	flat_argvp_envp_on_stack()	0
 #define	flat_old_ram_flag(flags)	(flags)
+#define	flat_set_persistent(relval, p)	0
 
 /* We store the type of relocation in the top 4 bits of the `relval.' */
 
@@ -46,7 +47,8 @@ flat_get_relocate_addr (unsigned long relval)
    For the v850, RP should always be half-word aligned.  */
 static inline unsigned long flat_get_addr_from_rp (unsigned long *rp,
 						   unsigned long relval,
-						   unsigned long flags)
+						   unsigned long flags,
+						   unsigned long *persistent)
 {
 	short *srp = (short *)rp;
 

include/asm-x86_64/processor.h

@@ -371,7 +371,7 @@ static inline void sync_core(void)
 #define ARCH_HAS_PREFETCH
 static inline void prefetch(void *x) 
 { 
-	asm volatile("prefetcht0 %0" :: "m" (*(unsigned long *)x));
+	asm volatile("prefetcht0 (%0)" :: "r" (x));
 } 
 
 #define ARCH_HAS_PREFETCHW 1

include/linux/sched.h

@@ -113,7 +113,7 @@ extern unsigned long avenrun[];		/* Load averages */
 
 #define FSHIFT		11		/* nr of bits of precision */
 #define FIXED_1		(1<<FSHIFT)	/* 1.0 as fixed-point */
-#define LOAD_FREQ	(5*HZ)		/* 5 sec intervals */
+#define LOAD_FREQ	(5*HZ+1)	/* 5 sec intervals */
 #define EXP_1		1884		/* 1/exp(5sec/1min) as fixed-point */
 #define EXP_5		2014		/* 1/exp(5sec/5min) */
 #define EXP_15		2037		/* 1/exp(5sec/15min) */

include/linux/writeback.h

@@ -127,7 +127,7 @@ int sync_page_range(struct inode *inode, struct address_space *mapping,
 			loff_t pos, loff_t count);
 int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
 			   loff_t pos, loff_t count);
-void set_page_dirty_balance(struct page *page);
+void set_page_dirty_balance(struct page *page, int page_mkwrite);
 void writeback_set_ratelimit(void);
 
 /* pdflush.c */

include/net/rose.h

@@ -188,7 +188,7 @@ extern void rose_kick(struct sock *);
 extern void rose_enquiry_response(struct sock *);
 
 /* rose_route.c */
-extern struct rose_neigh rose_loopback_neigh;
+extern struct rose_neigh *rose_loopback_neigh;
 extern const struct file_operations rose_neigh_fops;
 extern const struct file_operations rose_nodes_fops;
 extern const struct file_operations rose_routes_fops;

kernel/futex.c

@@ -1943,9 +1943,10 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
 void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
 	unsigned long futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -1965,11 +1966,13 @@ void exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
 		return;
 
-	if (pending)
-		handle_futex_death((void __user *)pending + futex_offset,
-				   curr, pip);
-
+	next_entry = NULL;	/* avoid warning with gcc */
 	while (entry != &head->list) {
+		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi);
 		/*
 		 * A pending lock might already be on the list, so
 		 * don't process it twice:
@@ -1978,11 +1981,10 @@ void exit_robust_list(struct task_struct *curr)
 			if (handle_futex_death((void __user *)entry + futex_offset,
 						curr, pi))
 				return;
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&entry, &entry->next, &pi))
+		if (rc)
 			return;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -1991,6 +1993,10 @@ void exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,

kernel/futex_compat.c

@@ -38,10 +38,11 @@ fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
 void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	compat_uptr_t uentry, upending;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -61,10 +62,15 @@ void compat_exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&upending, &pending,
 			       &head->list_op_pending, &pip))
 		return;
-	if (pending)
-		handle_futex_death((void __user *)pending + futex_offset, curr, pip);
 
+	next_entry = NULL;	/* avoid warning with gcc */
 	while (entry != (struct robust_list __user *) &head->list) {
+		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_uentry, &next_entry,
+			(compat_uptr_t __user *)&entry->next, &next_pi);
 		/*
 		 * A pending lock might already be on the list, so
 		 * dont process it twice:
@@ -74,12 +80,11 @@ void compat_exit_robust_list(struct task_struct *curr)
 						curr, pi))
 				return;
 
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&uentry, &entry,
-				       (compat_uptr_t __user *)&entry->next, &pi))
+		if (rc)
 			return;
+		uentry = next_uentry;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -88,6 +93,9 @@ void compat_exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 asmlinkage long

kernel/sched_fair.c

@@ -639,6 +639,16 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 		se->block_start = 0;
 		se->sum_sleep_runtime += delta;
+
+		/*
+		 * Blocking time is in units of nanosecs, so shift by 20 to
+		 * get a milliseconds-range estimation of the amount of
+		 * time that the task spent sleeping:
+		 */
+		if (unlikely(prof_on == SLEEP_PROFILING)) {
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
+				     delta >> 20);
+		}
 	}
 #endif
 }

kernel/signal.c

@@ -531,18 +531,18 @@ static int check_kill_permission(int sig, struct siginfo *info,
 	if (!valid_signal(sig))
 		return error;
 
-	error = audit_signal_info(sig, t); /* Let audit system see the signal */
-	if (error)
-		return error;
-
-	error = -EPERM;
-	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
-	    && ((sig != SIGCONT) ||
-		(process_session(current) != process_session(t)))
-	    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
-	    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
-	    && !capable(CAP_KILL))
+	if (info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) {
+		error = audit_signal_info(sig, t); /* Let audit system see the signal */
+		if (error)
+			return error;
+		error = -EPERM;
+		if (((sig != SIGCONT) ||
+			(process_session(current) != process_session(t)))
+		    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
+		    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
+		    && !capable(CAP_KILL))
 		return error;
+	}
 
 	return security_task_kill(t, info, sig, 0);
 }

kernel/sys.c

@@ -32,6 +32,7 @@
 #include <linux/getcpu.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/seccomp.h>
+#include <linux/cpu.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -878,6 +879,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
+	disable_nonboot_cpus();
 	sysdev_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	machine_power_off();

kernel/time/timer_stats.c

@@ -327,8 +327,9 @@ static int tstats_show(struct seq_file *m, void *v)
 		ms = 1;
 
 	if (events && period.tv_sec)
-		seq_printf(m, "%ld total events, %ld.%ld events/sec\n", events,
-			   events / period.tv_sec, events * 1000 / ms);
+		seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
+			   events, events * 1000 / ms,
+			   (events * 1000000 / ms) % 1000);
 	else
 		seq_printf(m, "%ld total events\n", events);
 

lib/Kconfig.debug

@@ -294,6 +294,8 @@ config LOCK_STAT
 	help
 	 This feature enables tracking lock contention points
 
+	 For more details, see Documentation/lockstat.txt
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP

lib/Makefile

@@ -2,7 +2,7 @@
 # Makefile for some libs needed in the kernel.
 #
 
-lib-y := ctype.o string.o vsprintf.o kasprintf.o cmdline.o \
+lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o bitmap.o extable.o prio_tree.o \
 	 sha1.o irq_regs.o reciprocal_div.o argv_split.o
@@ -13,7 +13,7 @@ lib-$(CONFIG_SMP) += cpumask.o
 lib-y	+= kobject.o kref.o kobject_uevent.o klist.o
 
 obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
-	 bust_spinlocks.o hexdump.o
+	 bust_spinlocks.o hexdump.o kasprintf.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG

mm/Kconfig

@@ -137,6 +137,7 @@ config SPLIT_PTLOCK_CPUS
 	int
 	default "4096" if ARM && !CPU_CACHE_VIPT
 	default "4096" if PARISC && !PA20
+	default "4096" if XEN
 	default "4"
 
 #

mm/filemap.c

@@ -1388,6 +1388,7 @@ retry_find:
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	if (unlikely(vmf->pgoff >= size)) {
 		unlock_page(page);
+		page_cache_release(page);
 		goto outside_data_content;
 	}
 

mm/fremap.c

@@ -160,7 +160,7 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
 		goto out;
 
-	if (!vma->vm_flags & VM_CAN_NONLINEAR)
+	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
 		goto out;
 
 	if (end <= start || start < vma->vm_start || end > vma->vm_end)

mm/hugetlb.c

@@ -42,7 +42,7 @@ static void clear_huge_page(struct page *page, unsigned long addr)
 	might_sleep();
 	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
 		cond_resched();
-		clear_user_highpage(page + i, addr);
+		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
 	}
 }
 

mm/memory.c

@@ -1639,6 +1639,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *old_page, *new_page;
 	pte_t entry;
 	int reuse = 0, ret = 0;
+	int page_mkwrite = 0;
 	struct page *dirty_page = NULL;
 
 	old_page = vm_normal_page(vma, address, orig_pte);
@@ -1687,6 +1688,8 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			page_cache_release(old_page);
 			if (!pte_same(*page_table, orig_pte))
 				goto unlock;
+
+			page_mkwrite = 1;
 		}
 		dirty_page = old_page;
 		get_page(dirty_page);
@@ -1774,7 +1777,7 @@ unlock:
 		 * do_no_page is protected similarly.
 		 */
 		wait_on_page_locked(dirty_page);
-		set_page_dirty_balance(dirty_page);
+		set_page_dirty_balance(dirty_page, page_mkwrite);
 		put_page(dirty_page);
 	}
 	return ret;
@@ -2307,13 +2310,14 @@ oom:
  * do not need to flush old virtual caches or the TLB.
  *
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
+ * but allow concurrent faults), and pte neither mapped nor locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
 static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		unsigned long address, pmd_t *pmd,
 		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
 {
+	pte_t *page_table;
 	spinlock_t *ptl;
 	struct page *page;
 	pte_t entry;
@@ -2321,13 +2325,13 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *dirty_page = NULL;
 	struct vm_fault vmf;
 	int ret;
+	int page_mkwrite = 0;
 
 	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.page = NULL;
 
-	pte_unmap(page_table);
 	BUG_ON(vma->vm_flags & VM_PFNMAP);
 
 	if (likely(vma->vm_ops->fault)) {
@@ -2398,6 +2402,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 					anon = 1; /* no anon but release vmf.page */
 					goto out;
 				}
+				page_mkwrite = 1;
 			}
 		}
 
@@ -2453,7 +2458,7 @@ out_unlocked:
 	if (anon)
 		page_cache_release(vmf.page);
 	else if (dirty_page) {
-		set_page_dirty_balance(dirty_page);
+		set_page_dirty_balance(dirty_page, page_mkwrite);
 		put_page(dirty_page);
 	}
 
@@ -2468,8 +2473,8 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			- vma->vm_start) >> PAGE_CACHE_SHIFT) + vma->vm_pgoff;
 	unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
 
-	return __do_fault(mm, vma, address, page_table, pmd, pgoff,
-							flags, orig_pte);
+	pte_unmap(page_table);
+	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
 
@@ -2552,9 +2557,7 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	pgoff = pte_to_pgoff(orig_pte);
-
-	return __do_fault(mm, vma, address, page_table, pmd, pgoff,
-							flags, orig_pte);
+	return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
 /*

mm/page-writeback.c

@@ -274,9 +274,9 @@ static void balance_dirty_pages(struct address_space *mapping)
 		pdflush_operation(background_writeout, 0);
 }
 
-void set_page_dirty_balance(struct page *page)
+void set_page_dirty_balance(struct page *page, int page_mkwrite)
 {
-	if (set_page_dirty(page)) {
+	if (set_page_dirty(page) || page_mkwrite) {
 		struct address_space *mapping = page_mapping(page);
 
 		if (mapping)

net/ieee80211/ieee80211_rx.c

@@ -366,6 +366,12 @@ int ieee80211_rx(struct ieee80211_device *ieee, struct sk_buff *skb,
 	frag = WLAN_GET_SEQ_FRAG(sc);
 	hdrlen = ieee80211_get_hdrlen(fc);
 
+	if (skb->len < hdrlen) {
+		printk(KERN_INFO "%s: invalid SKB length %d\n",
+			dev->name, skb->len);
+		goto rx_dropped;
+	}
+
 	/* Put this code here so that we avoid duplicating it in all
 	 * Rx paths. - Jean II */
 #ifdef CONFIG_WIRELESS_EXT

net/ieee80211/softmac/ieee80211softmac_wx.c

@@ -114,7 +114,7 @@ check_assoc_again:
 	sm->associnfo.associating = 1;
 	/* queue lower level code to do work (if necessary) */
 	schedule_delayed_work(&sm->associnfo.work, 0);
-out:
+
 	mutex_unlock(&sm->associnfo.mutex);
 
 	return 0;

net/ipv4/tcp_input.c

@@ -2420,6 +2420,9 @@ static int tcp_tso_acked(struct sock *sk, struct sk_buff *skb,
 			__u32 dval = min(tp->fackets_out, packets_acked);
 			tp->fackets_out -= dval;
 		}
+		/* hint's skb might be NULL but we don't need to care */
+		tp->fastpath_cnt_hint -= min_t(u32, packets_acked,
+					       tp->fastpath_cnt_hint);
 		tp->packets_out -= packets_acked;
 
 		BUG_ON(tcp_skb_pcount(skb) == 0);

net/ipv6/ndisc.c

@@ -1268,9 +1268,10 @@ static void ndisc_redirect_rcv(struct sk_buff *skb)
 
 	if (ipv6_addr_equal(dest, target)) {
 		on_link = 1;
-	} else if (!(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) {
+	} else if (ipv6_addr_type(target) !=
+		   (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
 		ND_PRINTK2(KERN_WARNING
-			   "ICMPv6 Redirect: target address is not link-local.\n");
+			   "ICMPv6 Redirect: target address is not link-local unicast.\n");
 		return;
 	}
 
@@ -1344,9 +1345,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	}
 
 	if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) &&
-	    !(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) {
+	    ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
 		ND_PRINTK2(KERN_WARNING
-			"ICMPv6 Redirect: target address is not link-local.\n");
+			"ICMPv6 Redirect: target address is not link-local unicast.\n");
 		return;
 	}
 

net/rose/rose_loopback.c

@@ -79,7 +79,7 @@ static void rose_loopback_timer(unsigned long param)
 
 		skb_reset_transport_header(skb);
 
-		sk = rose_find_socket(lci_o, &rose_loopback_neigh);
+		sk = rose_find_socket(lci_o, rose_loopback_neigh);
 		if (sk) {
 			if (rose_process_rx_frame(sk, skb) == 0)
 				kfree_skb(skb);
@@ -88,7 +88,7 @@ static void rose_loopback_timer(unsigned long param)
 
 		if (frametype == ROSE_CALL_REQUEST) {
 			if ((dev = rose_dev_get(dest)) != NULL) {
-				if (rose_rx_call_request(skb, dev, &rose_loopback_neigh, lci_o) == 0)
+				if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0)
 					kfree_skb(skb);
 			} else {
 				kfree_skb(skb);

net/rose/rose_route.c

@@ -45,7 +45,7 @@ static DEFINE_SPINLOCK(rose_neigh_list_lock);
 static struct rose_route *rose_route_list;
 static DEFINE_SPINLOCK(rose_route_list_lock);
 
-struct rose_neigh rose_loopback_neigh;
+struct rose_neigh *rose_loopback_neigh;
 
 /*
  *	Add a new route to a node, and in the process add the node and the
@@ -362,7 +362,12 @@ out:
  */
 void rose_add_loopback_neigh(void)
 {
-	struct rose_neigh *sn = &rose_loopback_neigh;
+	struct rose_neigh *sn;
+
+	rose_loopback_neigh = kmalloc(sizeof(struct rose_neigh), GFP_KERNEL);
+	if (!rose_loopback_neigh)
+		return;
+	sn = rose_loopback_neigh;
 
 	sn->callsign  = null_ax25_address;
 	sn->digipeat  = NULL;
@@ -417,13 +422,13 @@ int rose_add_loopback_node(rose_address *address)
 	rose_node->mask         = 10;
 	rose_node->count        = 1;
 	rose_node->loopback     = 1;
-	rose_node->neighbour[0] = &rose_loopback_neigh;
+	rose_node->neighbour[0] = rose_loopback_neigh;
 
 	/* Insert at the head of list. Address is always mask=10 */
 	rose_node->next = rose_node_list;
 	rose_node_list  = rose_node;
 
-	rose_loopback_neigh.count++;
+	rose_loopback_neigh->count++;
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);
@@ -454,7 +459,7 @@ void rose_del_loopback_node(rose_address *address)
 
 	rose_remove_node(rose_node);
 
-	rose_loopback_neigh.count--;
+	rose_loopback_neigh->count--;
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);

net/sched/cls_u32.c

@@ -502,7 +502,7 @@ static int u32_set_parms(struct tcf_proto *tp, unsigned long base,
 
 #ifdef CONFIG_NET_CLS_IND
 	if (tb[TCA_U32_INDEV-1]) {
-		int err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]);
+		err = tcf_change_indev(tp, n->indev, tb[TCA_U32_INDEV-1]);
 		if (err < 0)
 			goto errout;
 	}

net/sched/sch_sfq.c

@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/ipv6.h>
 #include <linux/skbuff.h>
+#include <linux/jhash.h>
 #include <net/ip.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
@@ -95,7 +96,7 @@ struct sfq_sched_data
 
 /* Variables */
 	struct timer_list perturb_timer;
-	int		perturbation;
+	u32		perturbation;
 	sfq_index	tail;		/* Index of current slot in round */
 	sfq_index	max_depth;	/* Maximal depth */
 
@@ -109,12 +110,7 @@ struct sfq_sched_data
 
 static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
 {
-	int pert = q->perturbation;
-
-	/* Have we any rotation primitives? If not, WHY? */
-	h ^= (h1<<pert) ^ (h1>>(0x1F - pert));
-	h ^= h>>10;
-	return h & 0x3FF;
+	return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1);
 }
 
 static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
@@ -256,6 +252,13 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc* sch)
 		q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
 		q->hash[x] = hash;
 	}
+	/* If selected queue has length q->limit, this means that
+	 * all another queues are empty and that we do simple tail drop,
+	 * i.e. drop _this_ packet.
+	 */
+	if (q->qs[x].qlen >= q->limit)
+		return qdisc_drop(skb, sch);
+
 	sch->qstats.backlog += skb->len;
 	__skb_queue_tail(&q->qs[x], skb);
 	sfq_inc(q, x);
@@ -294,6 +297,19 @@ sfq_requeue(struct sk_buff *skb, struct Qdisc* sch)
 	}
 	sch->qstats.backlog += skb->len;
 	__skb_queue_head(&q->qs[x], skb);
+	/* If selected queue has length q->limit+1, this means that
+	 * all another queues are empty and we do simple tail drop.
+	 * This packet is still requeued at head of queue, tail packet
+	 * is dropped.
+	 */
+	if (q->qs[x].qlen > q->limit) {
+		skb = q->qs[x].prev;
+		__skb_unlink(skb, &q->qs[x]);
+		sch->qstats.drops++;
+		sch->qstats.backlog -= skb->len;
+		kfree_skb(skb);
+		return NET_XMIT_CN;
+	}
 	sfq_inc(q, x);
 	if (q->qs[x].qlen == 1) {		/* The flow is new */
 		if (q->tail == SFQ_DEPTH) {	/* It is the first flow */
@@ -370,12 +386,10 @@ static void sfq_perturbation(unsigned long arg)
 	struct Qdisc *sch = (struct Qdisc*)arg;
 	struct sfq_sched_data *q = qdisc_priv(sch);
 
-	q->perturbation = net_random()&0x1F;
+	get_random_bytes(&q->perturbation, 4);
 
-	if (q->perturb_period) {
-		q->perturb_timer.expires = jiffies + q->perturb_period;
-		add_timer(&q->perturb_timer);
-	}
+	if (q->perturb_period)
+		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
 }
 
 static int sfq_change(struct Qdisc *sch, struct rtattr *opt)
@@ -391,7 +405,7 @@ static int sfq_change(struct Qdisc *sch, struct rtattr *opt)
 	q->quantum = ctl->quantum ? : psched_mtu(sch->dev);
 	q->perturb_period = ctl->perturb_period*HZ;
 	if (ctl->limit)
-		q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 2);
+		q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
 
 	qlen = sch->q.qlen;
 	while (sch->q.qlen > q->limit)
@@ -400,8 +414,8 @@ static int sfq_change(struct Qdisc *sch, struct rtattr *opt)
 
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
-		q->perturb_timer.expires = jiffies + q->perturb_period;
-		add_timer(&q->perturb_timer);
+		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
+		get_random_bytes(&q->perturbation, 4);
 	}
 	sch_tree_unlock(sch);
 	return 0;
@@ -423,12 +437,13 @@ static int sfq_init(struct Qdisc *sch, struct rtattr *opt)
 		q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH;
 		q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH;
 	}
-	q->limit = SFQ_DEPTH - 2;
+	q->limit = SFQ_DEPTH - 1;
 	q->max_depth = 0;
 	q->tail = SFQ_DEPTH;
 	if (opt == NULL) {
 		q->quantum = psched_mtu(sch->dev);
 		q->perturb_period = 0;
+		get_random_bytes(&q->perturbation, 4);
 	} else {
 		int err = sfq_change(sch, opt);
 		if (err)