Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Documentation/Changes

@@ -44,9 +44,9 @@ running, the suggested command should tell you.
 
 Again, keep in mind that this list assumes you are already
 functionally running a Linux 2.4 kernel.  Also, not all tools are
-necessary on all systems; obviously, if you don't have any PCMCIA (PC
-Card) hardware, for example, you probably needn't concern yourself
-with pcmcia-cs.
+necessary on all systems; obviously, if you don't have any ISDN
+hardware, for example, you probably needn't concern yourself with
+isdn4k-utils.
 
 o  Gnu C                  2.95.3                  # gcc --version
 o  Gnu make               3.79.1                  # make --version
@@ -57,6 +57,7 @@ o  e2fsprogs              1.29                    # tune2fs
 o  jfsutils               1.1.3                   # fsck.jfs -V
 o  reiserfsprogs          3.6.3                   # reiserfsck -V 2>&1|grep reiserfsprogs
 o  xfsprogs               2.6.0                   # xfs_db -V
+o  pcmciautils            001
 o  pcmcia-cs              3.1.21                  # cardmgr -V
 o  quota-tools            3.09                    # quota -V
 o  PPP                    2.4.0                   # pppd --version
@@ -186,13 +187,20 @@ architecture independent and any version from 2.0.0 onward should
 work correctly with this version of the XFS kernel code (2.6.0 or
 later is recommended, due to some significant improvements).
 
+PCMCIAutils
+-----------
+
+PCMCIAutils replaces pcmcia-cs (see below). It properly sets up
+PCMCIA sockets at system startup and loads the appropriate modules
+for 16-bit PCMCIA devices if the kernel is modularized and the hotplug
+subsystem is used.
 
 Pcmcia-cs
 ---------
 
 PCMCIA (PC Card) support is now partially implemented in the main
-kernel source.  Pay attention when you recompile your kernel ;-).
-Also, be sure to upgrade to the latest pcmcia-cs release.
+kernel source. The "pcmciautils" package (see above) replaces pcmcia-cs
+for newest kernels.
 
 Quota-tools
 -----------
@@ -349,9 +357,13 @@ Xfsprogs
 --------
 o  <ftp://oss.sgi.com/projects/xfs/download/>
 
+Pcmciautils
+-----------
+o  <ftp://ftp.kernel.org/pub/linux/utils/kernel/pcmcia/>
+
 Pcmcia-cs
 ---------
-o  <ftp://pcmcia-cs.sourceforge.net/pub/pcmcia-cs/pcmcia-cs-3.1.21.tar.gz>
+o  <http://pcmcia-cs.sourceforge.net/>
 
 Quota-tools
 ----------

Documentation/block/ioprio.txt

+Block io priorities
+===================
+
+
+Intro
+-----
+
+With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
+priorities is supported for reads on files. This enables users to io nice
+processes or process groups, similar to what has been possible to cpu
+scheduling for ages. This document mainly details the current possibilites
+with cfq, other io schedulers do not support io priorities so far.
+
+Scheduling classes
+------------------
+
+CFQ implements three generic scheduling classes that determine how io is
+served for a process.
+
+IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
+higher priority than any other in the system, processes from this class are
+given first access to the disk every time. Thus it needs to be used with some
+care, one io RT process can starve the entire system. Within the RT class,
+there are 8 levels of class data that determine exactly how much time this
+process needs the disk for on each service. In the future this might change
+to be more directly mappable to performance, by passing in a wanted data
+rate instead.
+
+IOPRIO_CLASS_BE: This is the best-effort scheduling class, which is the default
+for any process that hasn't set a specific io priority. The class data
+determines how much io bandwidth the process will get, it's directly mappable
+to the cpu nice levels just more coarsely implemented. 0 is the highest
+BE prio level, 7 is the lowest. The mapping between cpu nice level and io
+nice level is determined as: io_nice = (cpu_nice + 20) / 5.
+
+IOPRIO_CLASS_IDLE: This is the idle scheduling class, processes running at this
+level only get io time when no one else needs the disk. The idle class has no
+class data, since it doesn't really apply here.
+
+Tools
+-----
+
+See below for a sample ionice tool. Usage:
+
+# ionice -c<class> -n<level> -p<pid>
+
+If pid isn't given, the current process is assumed. IO priority settings
+are inherited on fork, so you can use ionice to start the process at a given
+level:
+
+# ionice -c2 -n0 /bin/ls
+
+will run ls at the best-effort scheduling class at the highest priority.
+For a running process, you can give the pid instead:
+
+# ionice -c1 -n2 -p100
+
+will change pid 100 to run at the realtime scheduling class, at priority 2.
+
+---> snip ionice.c tool <---
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <getopt.h>
+#include <unistd.h>
+#include <sys/ptrace.h>
+#include <asm/unistd.h>
+
+extern int sys_ioprio_set(int, int, int);
+extern int sys_ioprio_get(int, int);
+
+#if defined(__i386__)
+#define __NR_ioprio_set		289
+#define __NR_ioprio_get		290
+#elif defined(__ppc__)
+#define __NR_ioprio_set		273
+#define __NR_ioprio_get		274
+#elif defined(__x86_64__)
+#define __NR_ioprio_set		251
+#define __NR_ioprio_get		252
+#elif defined(__ia64__)
+#define __NR_ioprio_set		1274
+#define __NR_ioprio_get		1275
+#else
+#error "Unsupported arch"
+#endif
+
+_syscall3(int, ioprio_set, int, which, int, who, int, ioprio);
+_syscall2(int, ioprio_get, int, which, int, who);
+
+enum {
+	IOPRIO_CLASS_NONE,
+	IOPRIO_CLASS_RT,
+	IOPRIO_CLASS_BE,
+	IOPRIO_CLASS_IDLE,
+};
+
+enum {
+	IOPRIO_WHO_PROCESS = 1,
+	IOPRIO_WHO_PGRP,
+	IOPRIO_WHO_USER,
+};
+
+#define IOPRIO_CLASS_SHIFT	13
+
+const char *to_prio[] = { "none", "realtime", "best-effort", "idle", };
+
+int main(int argc, char *argv[])
+{
+	int ioprio = 4, set = 0, ioprio_class = IOPRIO_CLASS_BE;
+	int c, pid = 0;
+
+	while ((c = getopt(argc, argv, "+n:c:p:")) != EOF) {
+		switch (c) {
+		case 'n':
+			ioprio = strtol(optarg, NULL, 10);
+			set = 1;
+			break;
+		case 'c':
+			ioprio_class = strtol(optarg, NULL, 10);
+			set = 1;
+			break;
+		case 'p':
+			pid = strtol(optarg, NULL, 10);
+			break;
+		}
+	}
+
+	switch (ioprio_class) {
+		case IOPRIO_CLASS_NONE:
+			ioprio_class = IOPRIO_CLASS_BE;
+			break;
+		case IOPRIO_CLASS_RT:
+		case IOPRIO_CLASS_BE:
+			break;
+		case IOPRIO_CLASS_IDLE:
+			ioprio = 7;
+			break;
+		default:
+			printf("bad prio class %d\n", ioprio_class);
+			return 1;
+	}
+
+	if (!set) {
+		if (!pid && argv[optind])
+			pid = strtol(argv[optind], NULL, 10);
+
+		ioprio = ioprio_get(IOPRIO_WHO_PROCESS, pid);
+
+		printf("pid=%d, %d\n", pid, ioprio);
+
+		if (ioprio == -1)
+			perror("ioprio_get");
+		else {
+			ioprio_class = ioprio >> IOPRIO_CLASS_SHIFT;
+			ioprio = ioprio & 0xff;
+			printf("%s: prio %d\n", to_prio[ioprio_class], ioprio);
+		}
+	} else {
+		if (ioprio_set(IOPRIO_WHO_PROCESS, pid, ioprio | ioprio_class << IOPRIO_CLASS_SHIFT) == -1) {
+			perror("ioprio_set");
+			return 1;
+		}
+
+		if (argv[optind])
+			execvp(argv[optind], &argv[optind]);
+	}
+
+	return 0;
+}
+
+---> snip ionice.c tool <---
+
+
+March 11 2005, Jens Axboe <axboe@suse.de>

Documentation/cciss.txt

@@ -17,6 +17,7 @@ This driver is known to work with the following cards:
 	* SA P600
 	* SA P800
 	* SA E400
+	* SA E300
 
 If nodes are not already created in the /dev/cciss directory, run as root:
 

Documentation/kernel-parameters.txt

@@ -1119,7 +1119,7 @@ running once the system is up.
 			See Documentation/ramdisk.txt.
 
 	psmouse.proto=  [HW,MOUSE] Highest PS2 mouse protocol extension to
-			probe for (bare|imps|exps).
+			probe for (bare|imps|exps|lifebook|any).
 	psmouse.rate=	[HW,MOUSE] Set desired mouse report rate, in reports
 			per second.
 	psmouse.resetafter=

Documentation/pcmcia/devicetable.txt

+Matching of PCMCIA devices to drivers is done using one or more of the
+following criteria:
+
+- manufactor ID
+- card ID
+- product ID strings _and_ hashes of these strings
+- function ID
+- device function (actual and pseudo)
+
+You should use the helpers in include/pcmcia/device_id.h for generating the
+struct pcmcia_device_id[] entries which match devices to drivers.
+
+If you want to match product ID strings, you also need to pass the crc32
+hashes of the string to the macro, e.g. if you want to match the product ID
+string 1, you need to use
+
+PCMCIA_DEVICE_PROD_ID1("some_string", 0x(hash_of_some_string)),
+
+If the hash is incorrect, the kernel will inform you about this in "dmesg"
+upon module initialization, and tell you of the correct hash.
+
+You can determine the hash of the product ID strings by running
+"pcmcia-modalias %n.%m" [%n being replaced with the socket number and %m being
+replaced with the device function] from pcmciautils. It generates a string
+in the following form:
+pcmcia:m0149cC1ABf06pfn00fn00pa725B842DpbF1EFEE84pc0877B627pd00000000
+
+The hex value after "pa" is the hash of product ID string 1, after "pb" for
+string 2 and so on.
+
+Alternatively, you can use this small tool to determine the crc32 hash.
+simply pass the string you want to evaluate as argument to this program,
+e.g.
+$ ./crc32hash "Dual Speed"
+
+-------------------------------------------------------------------------
+/* crc32hash.c - derived from linux/lib/crc32.c, GNU GPL v2 */
+#include <string.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <stdlib.h>
+
+unsigned int crc32(unsigned char const *p, unsigned int len)
+{
+	int i;
+	unsigned int crc = 0;
+	while (len--) {
+		crc ^= *p++;
+		for (i = 0; i < 8; i++)
+			crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0);
+	}
+	return crc;
+}
+
+int main(int argc, char **argv) {
+	unsigned int result;
+	if (argc != 2) {
+		printf("no string passed as argument\n");
+		return -1;
+	}
+	result = crc32(argv[1], strlen(argv[1]));
+	printf("0x%x\n", result);
+	return 0;
+}

Documentation/pcmcia/driver-changes.txt

+This file details changes in 2.6 which affect PCMCIA card driver authors:
+
+* in-kernel device<->driver matching
+   PCMCIA devices and their correct drivers can now be matched in
+   kernelspace. See 'devicetable.txt' for details.
+
+* Device model integration (as of 2.6.11)
+   A struct pcmcia_device is registered with the device model core,
+   and can be used (e.g. for SET_NETDEV_DEV) by using
+   handle_to_dev(client_handle_t * handle).
+
+* Convert internal I/O port addresses to unsigned long (as of 2.6.11)
+   ioaddr_t should be replaced by kio_addr_t in PCMCIA card drivers.
+
+* irq_mask and irq_list parameters (as of 2.6.11)
+   The irq_mask and irq_list parameters should no longer be used in
+   PCMCIA card drivers. Instead, it is the job of the PCMCIA core to
+   determine which IRQ should be used. Therefore, link->irq.IRQInfo2
+   is ignored.
+
+* client->PendingEvents is gone (as of 2.6.11)
+   client->PendingEvents is no longer available.
+
+* client->Attributes are gone (as of 2.6.11)
+   client->Attributes is unused, therefore it is removed from all
+   PCMCIA card drivers
+
+* core functions no longer available (as of 2.6.11)
+   The following functions have been removed from the kernel source
+   because they are unused by all in-kernel drivers, and no external
+   driver was reported to rely on them:
+	pcmcia_get_first_region()
+	pcmcia_get_next_region()
+	pcmcia_modify_window()
+	pcmcia_set_event_mask()
+	pcmcia_get_first_window()
+	pcmcia_get_next_window()
+
+* device list iteration upon module removal (as of 2.6.10)
+   It is no longer necessary to iterate on the driver's internal
+   client list and call the ->detach() function upon module removal.
+
+* Resource management. (as of 2.6.8)
+   Although the PCMCIA subsystem will allocate resources for cards,
+   it no longer marks these resources busy. This means that driver
+   authors are now responsible for claiming your resources as per
+   other drivers in Linux. You should use request_region() to mark
+   your IO regions in-use, and request_mem_region() to mark your
+   memory regions in-use. The name argument should be a pointer to
+   your driver name. Eg, for pcnet_cs, name should point to the
+   string "pcnet_cs".

MAINTAINERS

@@ -1149,7 +1149,7 @@ S:	Maintained
 
 INFINIBAND SUBSYSTEM
 P:	Roland Dreier
-M:	roland@topspin.com
+M:	rolandd@cisco.com
 P:	Sean Hefty
 M:	mshefty@ichips.intel.com
 P:	Hal Rosenstock

arch/arm/kernel/process.c

@@ -32,6 +32,7 @@
 #include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
+#include <asm/mach/time.h>
 
 extern const char *processor_modes[];
 extern void setup_mm_for_reboot(char mode);
@@ -85,8 +86,10 @@ EXPORT_SYMBOL(pm_power_off);
 void default_idle(void)
 {
 	local_irq_disable();
-	if (!need_resched() && !hlt_counter)
+	if (!need_resched() && !hlt_counter) {
+		timer_dyn_reprogram();
 		arch_idle();
+	}
 	local_irq_enable();
 }
 

arch/arm/kernel/time.c

@@ -424,15 +424,19 @@ static int timer_dyn_tick_disable(void)
 	return ret;
 }
 
+/*
+ * Reprogram the system timer for at least the calculated time interval.
+ * This function should be called from the idle thread with IRQs disabled,
+ * immediately before sleeping.
+ */
 void timer_dyn_reprogram(void)
 {
 	struct dyn_tick_timer *dyn_tick = system_timer->dyn_tick;
-	unsigned long flags;
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	write_seqlock(&xtime_lock);
 	if (dyn_tick->state & DYN_TICK_ENABLED)
 		dyn_tick->reprogram(next_timer_interrupt() - jiffies);
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_sequnlock(&xtime_lock);
 }
 
 static ssize_t timer_show_dyn_tick(struct sys_device *dev, char *buf)

arch/arm/mach-aaec2000/Makefile.boot

+	zreladdr-y := 0xf0008000

arch/arm/mach-omap/usb.c

@@ -288,8 +288,8 @@ static void usb_release(struct device *dev)
 static struct resource udc_resources[] = {
 	/* order is significant! */
 	{		/* registers */
-		.start		= IO_ADDRESS(UDC_BASE),
-		.end		= IO_ADDRESS(UDC_BASE + 0xff),
+		.start		= UDC_BASE,
+		.end		= UDC_BASE + 0xff,
 		.flags		= IORESOURCE_MEM,
 	}, {		/* general IRQ */
 		.start		= IH2_BASE + 20,
@@ -355,8 +355,8 @@ static struct platform_device ohci_device = {
 static struct resource otg_resources[] = {
 	/* order is significant! */
 	{
-		.start		= IO_ADDRESS(OTG_BASE),
-		.end		= IO_ADDRESS(OTG_BASE + 0xff),
+		.start		= OTG_BASE,
+		.end		= OTG_BASE + 0xff,
 		.flags		= IORESOURCE_MEM,
 	}, {
 		.start		= IH2_BASE + 8,

arch/arm/mm/init.c

@@ -522,6 +522,69 @@ static inline void free_area(unsigned long addr, unsigned long end, char *s)
 		printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
 }
 
+static inline void
+free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
+{
+	struct page *start_pg, *end_pg;
+	unsigned long pg, pgend;
+
+	/*
+	 * Convert start_pfn/end_pfn to a struct page pointer.
+	 */
+	start_pg = pfn_to_page(start_pfn);
+	end_pg = pfn_to_page(end_pfn);
+
+	/*
+	 * Convert to physical addresses, and
+	 * round start upwards and end downwards.
+	 */
+	pg = PAGE_ALIGN(__pa(start_pg));
+	pgend = __pa(end_pg) & PAGE_MASK;
+
+	/*
+	 * If there are free pages between these,
+	 * free the section of the memmap array.
+	 */
+	if (pg < pgend)
+		free_bootmem_node(NODE_DATA(node), pg, pgend - pg);
+}
+
+/*
+ * The mem_map array can get very big.  Free the unused area of the memory map.
+ */
+static void __init free_unused_memmap_node(int node, struct meminfo *mi)
+{
+	unsigned long bank_start, prev_bank_end = 0;
+	unsigned int i;
+
+	/*
+	 * [FIXME] This relies on each bank being in address order.  This
+	 * may not be the case, especially if the user has provided the
+	 * information on the command line.
+	 */
+	for (i = 0; i < mi->nr_banks; i++) {
+		if (mi->bank[i].size == 0 || mi->bank[i].node != node)
+			continue;
+
+		bank_start = mi->bank[i].start >> PAGE_SHIFT;
+		if (bank_start < prev_bank_end) {
+			printk(KERN_ERR "MEM: unordered memory banks.  "
+				"Not freeing memmap.\n");
+			break;
+		}
+
+		/*
+		 * If we had a previous bank, and there is a space
+		 * between the current bank and the previous, free it.
+		 */
+		if (prev_bank_end && prev_bank_end != bank_start)
+			free_memmap(node, prev_bank_end, bank_start);
+
+		prev_bank_end = (mi->bank[i].start +
+				 mi->bank[i].size) >> PAGE_SHIFT;
+	}
+}
+
 /*
  * mem_init() marks the free areas in the mem_map and tells us how much
  * memory is free.  This is done after various parts of the system have
@@ -540,16 +603,12 @@ void __init mem_init(void)
 	max_mapnr   = virt_to_page(high_memory) - mem_map;
 #endif
 
-	/*
-	 * We may have non-contiguous memory.
-	 */
-	if (meminfo.nr_banks != 1)
-		create_memmap_holes(&meminfo);
-
 	/* this will put all unused low memory onto the freelists */
 	for_each_online_node(node) {
 		pg_data_t *pgdat = NODE_DATA(node);
 
+		free_unused_memmap_node(node, &meminfo);
+
 		if (pgdat->node_spanned_pages != 0)
 			totalram_pages += free_all_bootmem_node(pgdat);
 	}

arch/arm/mm/mm-armv.c

@@ -169,7 +169,14 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 
 	memzero(new_pgd, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
 
+	/*
+	 * Copy over the kernel and IO PGD entries
+	 */
 	init_pgd = pgd_offset_k(0);
+	memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
+		       (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
+
+	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
 	if (!vectors_high()) {
 		/*
@@ -198,14 +205,6 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 		spin_unlock(&mm->page_table_lock);
 	}
 
-	/*
-	 * Copy over the kernel and IO PGD entries
-	 */
-	memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
-		       (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
-
-	clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
-
 	return new_pgd;
 
 no_pte:
@@ -698,75 +697,3 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	for (i = 0; i < nr; i++)
 		create_mapping(io_desc + i);
 }
-
-static inline void
-free_memmap(int node, unsigned long start_pfn, unsigned long end_pfn)
-{
-	struct page *start_pg, *end_pg;
-	unsigned long pg, pgend;
-
-	/*
-	 * Convert start_pfn/end_pfn to a struct page pointer.
-	 */
-	start_pg = pfn_to_page(start_pfn);
-	end_pg = pfn_to_page(end_pfn);
-
-	/*
-	 * Convert to physical addresses, and
-	 * round start upwards and end downwards.
-	 */
-	pg = PAGE_ALIGN(__pa(start_pg));
-	pgend = __pa(end_pg) & PAGE_MASK;
-
-	/*
-	 * If there are free pages between these,
-	 * free the section of the memmap array.
-	 */
-	if (pg < pgend)
-		free_bootmem_node(NODE_DATA(node), pg, pgend - pg);
-}
-
-static inline void free_unused_memmap_node(int node, struct meminfo *mi)
-{
-	unsigned long bank_start, prev_bank_end = 0;
-	unsigned int i;
-
-	/*
-	 * [FIXME] This relies on each bank being in address order.  This
-	 * may not be the case, especially if the user has provided the
-	 * information on the command line.
-	 */
-	for (i = 0; i < mi->nr_banks; i++) {
-		if (mi->bank[i].size == 0 || mi->bank[i].node != node)
-			continue;
-
-		bank_start = mi->bank[i].start >> PAGE_SHIFT;
-		if (bank_start < prev_bank_end) {
-			printk(KERN_ERR "MEM: unordered memory banks.  "
-				"Not freeing memmap.\n");
-			break;
-		}
-
-		/*
-		 * If we had a previous bank, and there is a space
-		 * between the current bank and the previous, free it.
-		 */
-		if (prev_bank_end && prev_bank_end != bank_start)
-			free_memmap(node, prev_bank_end, bank_start);
-
-		prev_bank_end = PAGE_ALIGN(mi->bank[i].start +
-					   mi->bank[i].size) >> PAGE_SHIFT;
-	}
-}
-
-/*
- * The mem_map array can get very big.  Free
- * the unused area of the memory map.
- */
-void __init create_memmap_holes(struct meminfo *mi)
-{
-	int node;
-
-	for_each_online_node(node)
-		free_unused_memmap_node(node, mi);
-}

arch/arm/tools/mach-types

@@ -6,7 +6,7 @@
 # To add an entry into this database, please see Documentation/arm/README,
 # or contact rmk@arm.linux.org.uk
 #
-# Last update: Thu Mar 24 14:34:50 2005
+# Last update: Thu Jun 23 20:19:33 2005
 #
 # machine_is_xxx	CONFIG_xxxx		MACH_TYPE_xxx		number
 #
@@ -243,7 +243,7 @@ yoho			ARCH_YOHO		YOHO			231
 jasper			ARCH_JASPER		JASPER			232
 dsc25			ARCH_DSC25		DSC25			233
 omap_innovator		MACH_OMAP_INNOVATOR	OMAP_INNOVATOR		234
-ramses			ARCH_RAMSES		RAMSES			235
+mnci			ARCH_RAMSES		RAMSES			235
 s28x			ARCH_S28X		S28X			236
 mport3			ARCH_MPORT3		MPORT3			237
 pxa_eagle250		ARCH_PXA_EAGLE250	PXA_EAGLE250		238
@@ -323,7 +323,7 @@ nimbra29x		ARCH_NIMBRA29X		NIMBRA29X		311
 nimbra210		ARCH_NIMBRA210		NIMBRA210		312
 hhp_d95xx		ARCH_HHP_D95XX		HHP_D95XX		313
 labarm			ARCH_LABARM		LABARM			314
-m825xx			ARCH_M825XX		M825XX			315
+comcerto		ARCH_M825XX		M825XX			315
 m7100			SA1100_M7100		M7100			316
 nipc2			ARCH_NIPC2		NIPC2			317
 fu7202			ARCH_FU7202		FU7202			318
@@ -724,3 +724,66 @@ lpc22xx			MACH_LPC22XX		LPC22XX			715
 omap_comet3		MACH_COMET3		COMET3			716
 omap_comet4		MACH_COMET4		COMET4			717
 csb625			MACH_CSB625		CSB625			718
+fortunet2		MACH_FORTUNET2		FORTUNET2		719
+s5h2200			MACH_S5H2200		S5H2200			720
+optorm920		MACH_OPTORM920		OPTORM920		721
+adsbitsyxb		MACH_ADSBITSYXB		ADSBITSYXB		722
+adssphere		MACH_ADSSPHERE		ADSSPHERE		723
+adsportal		MACH_ADSPORTAL		ADSPORTAL		724
+ln2410sbc		MACH_LN2410SBC		LN2410SBC		725
+cb3rufc			MACH_CB3RUFC		CB3RUFC			726
+mp2usb			MACH_MP2USB		MP2USB			727
+ntnp425c		MACH_NTNP425C		NTNP425C		728
+colibri			MACH_COLIBRI		COLIBRI			729
+pcm7220			MACH_PCM7220		PCM7220			730
+gateway7001		MACH_GATEWAY7001	GATEWAY7001		731
+pcm027			MACH_PCM027		PCM027			732
+cmpxa			MACH_CMPXA		CMPXA			733
+anubis			MACH_ANUBIS		ANUBIS			734
+ite8152			MACH_ITE8152		ITE8152			735
+lpc3xxx			MACH_LPC3XXX		LPC3XXX			736
+puppeteer		MACH_PUPPETEER		PUPPETEER		737
+vt001			MACH_MACH_VADATECH	MACH_VADATECH		738
+e570			MACH_E570		E570			739
+x50			MACH_X50		X50			740
+recon			MACH_RECON		RECON			741
+xboardgp8		MACH_XBOARDGP8		XBOARDGP8		742
+fpic2			MACH_FPIC2		FPIC2			743
+akita			MACH_AKITA		AKITA			744
+a81			MACH_A81		A81			745
+svm_sc25x		MACH_SVM_SC25X		SVM_SC25X		746
+vt020			MACH_VADATECH020	VADATECH020		747
+tli			MACH_TLI		TLI			748
+edb9315lc		MACH_EDB9315LC		EDB9315LC		749
+passec			MACH_PASSEC		PASSEC			750
+ds_tiger		MACH_DS_TIGER		DS_TIGER		751
+e310			MACH_E310		E310			752
+e330			MACH_E330		E330			753
+rt3000			MACH_RT3000		RT3000			754
+nokia770		MACH_NOKIA770		NOKIA770		755
+pnx0106			MACH_PNX0106		PNX0106			756
+hx21xx			MACH_HX21XX		HX21XX			757
+faraday			MACH_FARADAY		FARADAY			758
+sbc9312			MACH_SBC9312		SBC9312			759
+batman			MACH_BATMAN		BATMAN			760
+jpd201			MACH_JPD201		JPD201			761
+mipsa			MACH_MIPSA		MIPSA			762
+kacom			MACH_KACOM		KACOM			763
+swarcocpu		MACH_SWARCOCPU		SWARCOCPU		764
+swarcodsl		MACH_SWARCODSL		SWARCODSL		765
+blueangel		MACH_BLUEANGEL		BLUEANGEL		766
+hairygrama		MACH_HAIRYGRAMA		HAIRYGRAMA		767
+banff			MACH_BANFF		BANFF			768
+carmeva			MACH_CARMEVA		CARMEVA			769
+sam255			MACH_SAM255		SAM255			770
+ppm10			MACH_PPM10		PPM10			771
+edb9315a		MACH_EDB9315A		EDB9315A		772
+sunset			MACH_SUNSET		SUNSET			773
+stargate2		MACH_STARGATE2		STARGATE2		774
+intelmote2		MACH_INTELMOTE2		INTELMOTE2		775
+trizeps4		MACH_TRIZEPS4		TRIZEPS4		776
+mainstone2		MACH_MAINSTONE2		MAINSTONE2		777
+ez_ixp42x		MACH_EZ_IXP42X		EZ_IXP42X		778
+tapwave_zodiac		MACH_TAPWAVE_ZODIAC	TAPWAVE_ZODIAC		779
+universalmeter		MACH_UNIVERSALMETER	UNIVERSALMETER		780
+hicoarm9		MACH_HICOARM9		HICOARM9		781

arch/i386/kernel/kprobes.c

@@ -127,48 +127,23 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->eip = (unsigned long)&p->ainsn.insn;
 }
 
-struct task_struct  *arch_get_kprobe_task(void *ptr)
-{
-	return ((struct thread_info *) (((unsigned long) ptr) &
-					(~(THREAD_SIZE -1))))->task;
-}
-
 void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
 {
 	unsigned long *sara = (unsigned long *)&regs->esp;
-	struct kretprobe_instance *ri;
-	static void *orig_ret_addr;
+        struct kretprobe_instance *ri;
+
+        if ((ri = get_free_rp_inst(rp)) != NULL) {
+                ri->rp = rp;
+                ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *) *sara;
 
-	/*
-	 * Save the return address when the return probe hits
-	 * the first time, and use it to populate the (krprobe
-	 * instance)->ret_addr for subsequent return probes at
-	 * the same addrress since stack address would have
-	 * the kretprobe_trampoline by then.
-	 */
-	if (((void*) *sara) != kretprobe_trampoline)
-		orig_ret_addr = (void*) *sara;
-
-	if ((ri = get_free_rp_inst(rp)) != NULL) {
-		ri->rp = rp;
-		ri->stack_addr = sara;
-		ri->ret_addr = orig_ret_addr;
-		add_rp_inst(ri);
 		/* Replace the return addr with trampoline addr */
 		*sara = (unsigned long) &kretprobe_trampoline;
-	} else {
-		rp->nmissed++;
-	}
-}
 
-void arch_kprobe_flush_task(struct task_struct *tk)
-{
-	struct kretprobe_instance *ri;
-	while ((ri = get_rp_inst_tsk(tk)) != NULL) {
-		*((unsigned long *)(ri->stack_addr)) =
-					(unsigned long) ri->ret_addr;
-		recycle_rp_inst(ri);
-	}
+                add_rp_inst(ri);
+        } else {
+                rp->nmissed++;
+        }
 }
 
 /*
@@ -286,36 +261,59 @@ static int kprobe_handler(struct pt_regs *regs)
  */
 int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 {
-	struct task_struct *tsk;
-	struct kretprobe_instance *ri;
-	struct hlist_head *head;
-	struct hlist_node *node;
-	unsigned long *sara = ((unsigned long *) &regs->esp) - 1;
-
-	tsk = arch_get_kprobe_task(sara);
-	head = kretprobe_inst_table_head(tsk);
-
-	hlist_for_each_entry(ri, node, head, hlist) {
-		if (ri->stack_addr == sara && ri->rp) {
-			if (ri->rp->handler)
-				ri->rp->handler(ri, regs);
-		}
-	}
-	return 0;
-}
+        struct kretprobe_instance *ri = NULL;
+        struct hlist_head *head;
+        struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =(unsigned long)&kretprobe_trampoline;
 
-void trampoline_post_handler(struct kprobe *p, struct pt_regs *regs,
-						unsigned long flags)
-{
-	struct kretprobe_instance *ri;
-	/* RA already popped */
-	unsigned long *sara = ((unsigned long *)&regs->esp) - 1;
+        head = kretprobe_inst_table_head(current);
 
-	while ((ri = get_rp_inst(sara))) {
-		regs->eip = (unsigned long)ri->ret_addr;
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+         *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
 	}
-	regs->eflags &= ~TF_MASK;
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->eip = orig_ret_address;
+
+	unlock_kprobes();
+	preempt_enable_no_resched();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
 }
 
 /*
@@ -403,8 +401,7 @@ static inline int post_kprobe_handler(struct pt_regs *regs)
 		current_kprobe->post_handler(current_kprobe, regs, 0);
 	}
 
-	if (current_kprobe->post_handler != trampoline_post_handler)
-		resume_execution(current_kprobe, regs);
+	resume_execution(current_kprobe, regs);
 	regs->eflags |= kprobe_saved_eflags;
 
 	/*Restore back the original saved kprobes variables and continue. */
@@ -534,3 +531,13 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	return 0;
 }
+
+static struct kprobe trampoline_p = {
+	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init(void)
+{
+	return register_kprobe(&trampoline_p);
+}

arch/i386/kernel/process.c

@@ -616,6 +616,33 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss)
 	tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY;
 }
 
+/*
+ * This function selects if the context switch from prev to next
+ * has to tweak the TSC disable bit in the cr4.
+ */
+static inline void disable_tsc(struct task_struct *prev_p,
+			       struct task_struct *next_p)
+{
+	struct thread_info *prev, *next;
+
+	/*
+	 * gcc should eliminate the ->thread_info dereference if
+	 * has_secure_computing returns 0 at compile time (SECCOMP=n).
+	 */
+	prev = prev_p->thread_info;
+	next = next_p->thread_info;
+
+	if (has_secure_computing(prev) || has_secure_computing(next)) {
+		/* slow path here */
+		if (has_secure_computing(prev) &&
+		    !has_secure_computing(next)) {
+			write_cr4(read_cr4() & ~X86_CR4_TSD);
+		} else if (!has_secure_computing(prev) &&
+			   has_secure_computing(next))
+			write_cr4(read_cr4() | X86_CR4_TSD);
+	}
+}
+
 /*
  *	switch_to(x,yn) should switch tasks from x to y.
  *
@@ -695,6 +722,8 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr))
 		handle_io_bitmap(next, tss);
 
+	disable_tsc(prev_p, next_p);
+
 	return prev_p;
 }
 

arch/i386/kernel/syscall_table.S

@@ -289,3 +289,5 @@ ENTRY(sys_call_table)
 	.long sys_add_key
 	.long sys_request_key
 	.long sys_keyctl
+	.long sys_ioprio_set
+	.long sys_ioprio_get		/* 290 */

arch/ia64/kernel/entry.S

@@ -1577,8 +1577,8 @@ sys_call_table:
 	data8 sys_add_key
 	data8 sys_request_key
 	data8 sys_keyctl
-	data8 sys_ni_syscall
-	data8 sys_ni_syscall			// 1275
+	data8 sys_ioprio_set
+	data8 sys_ioprio_get			// 1275
 	data8 sys_set_zone_reclaim
 	data8 sys_ni_syscall
 	data8 sys_ni_syscall

arch/ia64/kernel/kprobes.c

@@ -34,6 +34,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/kdebug.h>
+#include <asm/sections.h>
 
 extern void jprobe_inst_return(void);
 
@@ -263,13 +264,33 @@ static inline void get_kprobe_inst(bundle_t *bundle, uint slot,
 	}
 }
 
+/* Returns non-zero if the addr is in the Interrupt Vector Table */
+static inline int in_ivt_functions(unsigned long addr)
+{
+	return (addr >= (unsigned long)__start_ivt_text
+		&& addr < (unsigned long)__end_ivt_text);
+}
+
 static int valid_kprobe_addr(int template, int slot, unsigned long addr)
 {
 	if ((slot > 2) || ((bundle_encoding[template][1] == L) && slot > 1)) {
-		printk(KERN_WARNING "Attempting to insert unaligned kprobe at 0x%lx\n",
-				addr);
+		printk(KERN_WARNING "Attempting to insert unaligned kprobe "
+				"at 0x%lx\n", addr);
 		return -EINVAL;
 	}
+
+ 	if (in_ivt_functions(addr)) {
+ 		printk(KERN_WARNING "Kprobes can't be inserted inside "
+				"IVT functions at 0x%lx\n", addr);
+ 		return -EINVAL;
+ 	}
+
+	if (slot == 1 && bundle_encoding[template][1] != L) {
+		printk(KERN_WARNING "Inserting kprobes on slot #1 "
+		       "is not supported\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -290,6 +311,94 @@ static inline void set_current_kprobe(struct kprobe *p)
 	current_kprobe = p;
 }
 
+static void kretprobe_trampoline(void)
+{
+}
+
+/*
+ * At this point the target function has been tricked into
+ * returning into our trampoline.  Lookup the associated instance
+ * and then:
+ *    - call the handler function
+ *    - cleanup by marking the instance as unused
+ *    - long jump back to the original return address
+ */
+int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri = NULL;
+	struct hlist_head *head;
+	struct hlist_node *node, *tmp;
+	unsigned long orig_ret_address = 0;
+	unsigned long trampoline_address =
+		((struct fnptr *)kretprobe_trampoline)->ip;
+
+        head = kretprobe_inst_table_head(current);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because an multiple functions in the call path
+	 * have a return probe installed on them, and/or more then one return
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always inserted at the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *       function, the first instance's ret_addr will point to the
+	 *       real return address, and all the rest will point to
+	 *       kretprobe_trampoline
+	 */
+	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+			/* another task is sharing our hash bucket */
+                        continue;
+
+		if (ri->rp && ri->rp->handler)
+			ri->rp->handler(ri, regs);
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
+		recycle_rp_inst(ri);
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
+	regs->cr_iip = orig_ret_address;
+
+	unlock_kprobes();
+	preempt_enable_no_resched();
+
+        /*
+         * By returning a non-zero value, we are telling
+         * kprobe_handler() that we have handled unlocking
+         * and re-enabling preemption.
+         */
+        return 1;
+}
+
+void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs)
+{
+	struct kretprobe_instance *ri;
+
+	if ((ri = get_free_rp_inst(rp)) != NULL) {
+		ri->rp = rp;
+		ri->task = current;
+		ri->ret_addr = (kprobe_opcode_t *)regs->b0;
+
+		/* Replace the return addr with trampoline addr */
+		regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
+
+		add_rp_inst(ri);
+	} else {
+		rp->nmissed++;
+	}
+}
+
 int arch_prepare_kprobe(struct kprobe *p)
 {
 	unsigned long addr = (unsigned long) p->addr;
@@ -492,8 +601,8 @@ static int pre_kprobes_handler(struct die_args *args)
 	if (p->pre_handler && p->pre_handler(p, regs))
 		/*
 		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is handling the case where the
-		 * pre-handler is really our special jprobe pre-handler.
+		 * do a return.  This is used for both the jprobe pre-handler
+		 * and the kretprobe trampoline
 		 */
 		return 1;
 
@@ -599,3 +708,14 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	*regs = jprobe_saved_regs;
 	return 1;
 }
+
+static struct kprobe trampoline_p = {
+	.pre_handler = trampoline_probe_handler
+};
+
+int __init arch_init(void)
+{
+	trampoline_p.addr =
+		(kprobe_opcode_t *)((struct fnptr *)kretprobe_trampoline)->ip;
+	return register_kprobe(&trampoline_p);
+}

arch/ia64/kernel/process.c

@@ -27,6 +27,7 @@
 #include <linux/efi.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/kprobes.h>
 
 #include <asm/cpu.h>
 #include <asm/delay.h>
@@ -707,6 +708,13 @@ kernel_thread_helper (int (*fn)(void *), void *arg)
 void
 flush_thread (void)
 {
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(current);
+
 	/* drop floating-point and debug-register state if it exists: */
 	current->thread.flags &= ~(IA64_THREAD_FPH_VALID | IA64_THREAD_DBG_VALID);
 	ia64_drop_fpu(current);
@@ -721,6 +729,14 @@ flush_thread (void)
 void
 exit_thread (void)
 {
+
+	/*
+	 * Remove function-return probe instances associated with this task
+	 * and put them back on the free list. Do not insert an exit probe for
+	 * this function, it will be disabled by kprobe_flush_task if you do.
+	 */
+	kprobe_flush_task(current);
+
 	ia64_drop_fpu(current);
 #ifdef CONFIG_PERFMON
        /* if needed, stop monitoring and flush state to perfmon context */