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

46 files changed, 1997 insertions, 832 deletions

diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt
index 7c717699032..63392c9132b 100644
--- a/Documentation/DMA-mapping.txt
+++ b/Documentation/DMA-mapping.txt
@@ -698,12 +698,12 @@ these interfaces.  Remember that, as defined, consistent mappings are
 always going to be SAC addressable.
 
 The first thing your driver needs to do is query the PCI platform
-layer with your devices DAC addressing capabilities:
+layer if it is capable of handling your devices DAC addressing
+capabilities:
 
-	int pci_dac_set_dma_mask(struct pci_dev *pdev, u64 mask);
+	int pci_dac_dma_supported(struct pci_dev *hwdev, u64 mask);
 
-This routine behaves identically to pci_set_dma_mask.  You may not
-use the following interfaces if this routine fails.
+You may not use the following interfaces if this routine fails.
 
 Next, DMA addresses using this API are kept track of using the
 dma64_addr_t type.  It is guaranteed to be big enough to hold any
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 1ae4dc0fd85..f8fe882e33d 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -59,6 +59,9 @@
 !Iinclude/linux/hrtimer.h
 !Ekernel/hrtimer.c
      </sect1>
+     <sect1><title>Workqueues and Kevents</title>
+!Ekernel/workqueue.c
+     </sect1>
      <sect1><title>Internal Functions</title>
 !Ikernel/exit.c
 !Ikernel/signal.c
@@ -300,7 +303,7 @@ X!Ekernel/module.c
      </sect1>
 
      <sect1><title>Resources Management</title>
-!Ekernel/resource.c
+!Ikernel/resource.c
      </sect1>
 
      <sect1><title>MTRR Handling</title>
@@ -312,9 +315,7 @@ X!Ekernel/module.c
 !Edrivers/pci/pci-driver.c
 !Edrivers/pci/remove.c
 !Edrivers/pci/pci-acpi.c
-<!-- kerneldoc does not understand __devinit
-X!Edrivers/pci/search.c
- -->
+!Edrivers/pci/search.c
 !Edrivers/pci/msi.c
 !Edrivers/pci/bus.c
 <!-- FIXME: Removed for now since no structured comments in source
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 4f41a60e511..318df44259b 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -687,8 +687,9 @@ diff shows how closely related RCU and reader-writer locking can be.
 	+	spin_lock(&listmutex);
 		list_for_each_entry(p, head, lp) {
 			if (p->key == key) {
-				list_del(&p->list);
+	-			list_del(&p->list);
 	-			write_unlock(&listmutex);
+	+			list_del_rcu(&p->list);
 	+			spin_unlock(&listmutex);
 	+			synchronize_rcu();
 				kfree(p);
@@ -736,7 +737,7 @@ Or, for those who prefer a side-by-side listing:
  5   write_lock(&listmutex);            5   spin_lock(&listmutex);
  6   list_for_each_entry(p, head, lp) { 6   list_for_each_entry(p, head, lp) {
  7     if (p->key == key) {             7     if (p->key == key) {
- 8       list_del(&p->list);            8       list_del(&p->list);
+ 8       list_del(&p->list);            8       list_del_rcu(&p->list);
  9       write_unlock(&listmutex);      9       spin_unlock(&listmutex);
                                        10       synchronize_rcu();
 10       kfree(p);                     11       kfree(p);
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index 8230098da52..a10bfb6ecd9 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -1,57 +1,63 @@
 Linux Kernel patch sumbittal checklist
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Here are some basic things that developers should do if they
-want to see their kernel patch submittals accepted quicker.
+Here are some basic things that developers should do if they want to see their
+kernel patch submissions accepted more quickly.
 
-These are all above and beyond the documentation that is provided
-in Documentation/SubmittingPatches and elsewhere about submitting
-Linux kernel patches.
+These are all above and beyond the documentation that is provided in
+Documentation/SubmittingPatches and elsewhere regarding submitting Linux
+kernel patches.
 
 
 
-- Builds cleanly with applicable or modified CONFIG options =y, =m, and =n.
-  No gcc warnings/errors, no linker warnings/errors.
+1: Builds cleanly with applicable or modified CONFIG options =y, =m, and
+   =n.  No gcc warnings/errors, no linker warnings/errors.
 
-- Passes allnoconfig, allmodconfig
+2: Passes allnoconfig, allmodconfig
 
-- Builds on multiple CPU arch-es by using local cross-compile tools
-  or something like PLM at OSDL.
+3: Builds on multiple CPU architectures by using local cross-compile tools
+   or something like PLM at OSDL.
 
-- ppc64 is a good architecture for cross-compilation checking because it
-  tends to use `unsigned long' for 64-bit quantities.
+4: ppc64 is a good architecture for cross-compilation checking because it
+   tends to use `unsigned long' for 64-bit quantities.
 
-- Matches kernel coding style(!)
+5: Matches kernel coding style(!)
 
-- Any new or modified CONFIG options don't muck up the config menu.
+6: Any new or modified CONFIG options don't muck up the config menu.
 
-- All new Kconfig options have help text.
+7: All new Kconfig options have help text.
 
-- Has been carefully reviewed with respect to relevant Kconfig
-  combinations.  This is very hard to get right with testing --
-  brainpower pays off here.
+8: Has been carefully reviewed with respect to relevant Kconfig
+   combinations.  This is very hard to get right with testing -- brainpower
+   pays off here.
 
-- Check cleanly with sparse.
+9: Check cleanly with sparse.
 
-- Use 'make checkstack' and 'make namespacecheck' and fix any
-  problems that they find.  Note:  checkstack does not point out
-  problems explicitly, but any one function that uses more than
-  512 bytes on the stack is a candidate for change.
+10: Use 'make checkstack' and 'make namespacecheck' and fix any problems
+    that they find.  Note: checkstack does not point out problems explicitly,
+    but any one function that uses more than 512 bytes on the stack is a
+    candidate for change.
 
-- Include kernel-doc to document global kernel APIs.  (Not required
-  for static functions, but OK there also.)  Use 'make htmldocs'
-  or 'make mandocs' to check the kernel-doc and fix any issues.
+11: Include kernel-doc to document global kernel APIs.  (Not required for
+    static functions, but OK there also.) Use 'make htmldocs' or 'make
+    mandocs' to check the kernel-doc and fix any issues.
 
-- Has been tested with CONFIG_PREEMPT, CONFIG_DEBUG_PREEMPT,
-  CONFIG_DEBUG_SLAB, CONFIG_DEBUG_PAGEALLOC, CONFIG_DEBUG_MUTEXES,
-  CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_SPINLOCK_SLEEP all simultaneously
-  enabled.
+12: Has been tested with CONFIG_PREEMPT, CONFIG_DEBUG_PREEMPT,
+    CONFIG_DEBUG_SLAB, CONFIG_DEBUG_PAGEALLOC, CONFIG_DEBUG_MUTEXES,
+    CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_SPINLOCK_SLEEP all simultaneously
+    enabled.
 
-- Has been build- and runtime tested with and without CONFIG_SMP and
-  CONFIG_PREEMPT.
+13: Has been build- and runtime tested with and without CONFIG_SMP and
+    CONFIG_PREEMPT.
 
-- If the patch affects IO/Disk, etc: has been tested with and without
-  CONFIG_LBD.
+14: If the patch affects IO/Disk, etc: has been tested with and without
+    CONFIG_LBD.
 
+15: All codepaths have been exercised with all lockdep features enabled.
 
-2006-APR-27
+16: All new /proc entries are documented under Documentation/
+
+17: All new kernel boot parameters are documented in
+    Documentation/kernel-parameters.txt.
+
+18: All new module parameters are documented with MODULE_PARM_DESC()
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index c2c85bcb3d4..d42ab4c9e89 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -10,7 +10,9 @@ kernel, the process can sometimes be daunting if you're not familiar
 with "the system."  This text is a collection of suggestions which
 can greatly increase the chances of your change being accepted.
 
-If you are submitting a driver, also read Documentation/SubmittingDrivers.
+Read Documentation/SubmitChecklist for a list of items to check
+before submitting code.  If you are submitting a driver, also read
+Documentation/SubmittingDrivers.
 
 
 
@@ -74,9 +76,6 @@ There are a number of scripts which can aid in this:
 Quilt:
 http://savannah.nongnu.org/projects/quilt
 
-Randy Dunlap's patch scripts:
-http://www.xenotime.net/linux/scripts/patching-scripts-002.tar.gz
-
 Andrew Morton's patch scripts:
 http://www.zip.com.au/~akpm/linux/patches/
 Instead of these scripts, quilt is the recommended patch management
@@ -309,6 +308,8 @@ then you just add a line saying
 
 	Signed-off-by: Random J Developer <random@developer.example.org>
 
+using your real name (sorry, no pseudonyms or anonymous contributions.)
+
 Some people also put extra tags at the end.  They'll just be ignored for
 now, but you can do this to mark internal company procedures or just
 point out some special detail about the sign-off. 
@@ -484,7 +485,7 @@ Greg Kroah-Hartman "How to piss off a kernel subsystem maintainer".
   <http://www.kroah.com/log/2005/10/19/>
   <http://www.kroah.com/log/2006/01/11/>
 
-NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!.
+NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!
   <http://marc.theaimsgroup.com/?l=linux-kernel&m=112112749912944&w=2>
 
 Kernel Documentation/CodingStyle
@@ -493,4 +494,3 @@ Kernel Documentation/CodingStyle
 Linus Torvald's mail on the canonical patch format:
   <http://lkml.org/lkml/2005/4/7/183>
 --
-Last updated on 17 Nov 2005.
diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt
new file mode 100644
index 00000000000..1443cd71d26
--- /dev/null
+++ b/Documentation/accounting/delay-accounting.txt
@@ -0,0 +1,112 @@
+Delay accounting
+----------------
+
+Tasks encounter delays in execution when they wait
+for some kernel resource to become available e.g. a
+runnable task may wait for a free CPU to run on.
+
+The per-task delay accounting functionality measures
+the delays experienced by a task while
+
+a) waiting for a CPU (while being runnable)
+b) completion of synchronous block I/O initiated by the task
+c) swapping in pages
+
+and makes these statistics available to userspace through
+the taskstats interface.
+
+Such delays provide feedback for setting a task's cpu priority,
+io priority and rss limit values appropriately. Long delays for
+important tasks could be a trigger for raising its corresponding priority.
+
+The functionality, through its use of the taskstats interface, also provides
+delay statistics aggregated for all tasks (or threads) belonging to a
+thread group (corresponding to a traditional Unix process). This is a commonly
+needed aggregation that is more efficiently done by the kernel.
+
+Userspace utilities, particularly resource management applications, can also
+aggregate delay statistics into arbitrary groups. To enable this, delay
+statistics of a task are available both during its lifetime as well as on its
+exit, ensuring continuous and complete monitoring can be done.
+
+
+Interface
+---------
+
+Delay accounting uses the taskstats interface which is described
+in detail in a separate document in this directory. Taskstats returns a
+generic data structure to userspace corresponding to per-pid and per-tgid
+statistics. The delay accounting functionality populates specific fields of
+this structure. See
+     include/linux/taskstats.h
+for a description of the fields pertaining to delay accounting.
+It will generally be in the form of counters returning the cumulative
+delay seen for cpu, sync block I/O, swapin etc.
+
+Taking the difference of two successive readings of a given
+counter (say cpu_delay_total) for a task will give the delay
+experienced by the task waiting for the corresponding resource
+in that interval.
+
+When a task exits, records containing the per-task statistics
+are sent to userspace without requiring a command. If it is the last exiting
+task of a thread group, the per-tgid statistics are also sent. More details
+are given in the taskstats interface description.
+
+The getdelays.c userspace utility in this directory allows simple commands to
+be run and the corresponding delay statistics to be displayed. It also serves
+as an example of using the taskstats interface.
+
+Usage
+-----
+
+Compile the kernel with
+	CONFIG_TASK_DELAY_ACCT=y
+	CONFIG_TASKSTATS=y
+
+Delay accounting is enabled by default at boot up.
+To disable, add
+   nodelayacct
+to the kernel boot options. The rest of the instructions
+below assume this has not been done.
+
+After the system has booted up, use a utility
+similar to  getdelays.c to access the delays
+seen by a given task or a task group (tgid).
+The utility also allows a given command to be
+executed and the corresponding delays to be
+seen.
+
+General format of the getdelays command
+
+getdelays [-t tgid] [-p pid] [-c cmd...]
+
+
+Get delays, since system boot, for pid 10
+# ./getdelays -p 10
+(output similar to next case)
+
+Get sum of delays, since system boot, for all pids with tgid 5
+# ./getdelays -t 5
+
+
+CPU	count	real total	virtual total	delay total
+	7876	92005750	100000000	24001500
+IO	count	delay total
+	0	0
+MEM	count	delay total
+	0	0
+
+Get delays seen in executing a given simple command
+# ./getdelays -c ls /
+
+bin   data1  data3  data5  dev  home  media  opt   root  srv        sys  usr
+boot  data2  data4  data6  etc  lib   mnt    proc  sbin  subdomain  tmp  var
+
+
+CPU	count	real total	virtual total	delay total
+	6	4000250		4000000		0
+IO	count	delay total
+	0	0
+MEM	count	delay total
+	0	0
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
new file mode 100644
index 00000000000..795ca3911cc
--- /dev/null
+++ b/Documentation/accounting/getdelays.c
@@ -0,0 +1,396 @@
+/* getdelays.c
+ *
+ * Utility to get per-pid and per-tgid delay accounting statistics
+ * Also illustrates usage of the taskstats interface
+ *
+ * Copyright (C) Shailabh Nagar, IBM Corp. 2005
+ * Copyright (C) Balbir Singh, IBM Corp. 2006
+ * Copyright (c) Jay Lan, SGI. 2006
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <unistd.h>
+#include <poll.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <signal.h>
+
+#include <linux/genetlink.h>
+#include <linux/taskstats.h>
+
+/*
+ * Generic macros for dealing with netlink sockets. Might be duplicated
+ * elsewhere. It is recommended that commercial grade applications use
+ * libnl or libnetlink and use the interfaces provided by the library
+ */
+#define GENLMSG_DATA(glh)	((void *)(NLMSG_DATA(glh) + GENL_HDRLEN))
+#define GENLMSG_PAYLOAD(glh)	(NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN)
+#define NLA_DATA(na)		((void *)((char*)(na) + NLA_HDRLEN))
+#define NLA_PAYLOAD(len)	(len - NLA_HDRLEN)
+
+#define err(code, fmt, arg...) do { printf(fmt, ##arg); exit(code); } while (0)
+int done = 0;
+int rcvbufsz=0;
+
+    char name[100];
+int dbg=0, print_delays=0;
+__u64 stime, utime;
+#define PRINTF(fmt, arg...) {			\
+	    if (dbg) {				\
+		printf(fmt, ##arg);		\
+	    }					\
+	}
+
+/* Maximum size of response requested or message sent */
+#define MAX_MSG_SIZE	256
+/* Maximum number of cpus expected to be specified in a cpumask */
+#define MAX_CPUS	32
+/* Maximum length of pathname to log file */
+#define MAX_FILENAME	256
+
+struct msgtemplate {
+	struct nlmsghdr n;
+	struct genlmsghdr g;
+	char buf[MAX_MSG_SIZE];
+};
+
+char cpumask[100+6*MAX_CPUS];
+
+/*
+ * Create a raw netlink socket and bind
+ */
+static int create_nl_socket(int protocol)
+{
+	int fd;
+	struct sockaddr_nl local;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, protocol);
+	if (fd < 0)
+		return -1;
+
+	if (rcvbufsz)
+		if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF,
+				&rcvbufsz, sizeof(rcvbufsz)) < 0) {
+			printf("Unable to set socket rcv buf size to %d\n",
+			       rcvbufsz);
+			return -1;
+		}
+
+	memset(&local, 0, sizeof(local));
+	local.nl_family = AF_NETLINK;
+
+	if (bind(fd, (struct sockaddr *) &local, sizeof(local)) < 0)
+		goto error;
+
+	return fd;
+error:
+	close(fd);
+	return -1;
+}
+
+
+int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid,
+	     __u8 genl_cmd, __u16 nla_type,
+	     void *nla_data, int nla_len)
+{
+	struct nlattr *na;
+	struct sockaddr_nl nladdr;
+	int r, buflen;
+	char *buf;
+
+	struct msgtemplate msg;
+
+	msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	msg.n.nlmsg_type = nlmsg_type;
+	msg.n.nlmsg_flags = NLM_F_REQUEST;
+	msg.n.nlmsg_seq = 0;
+	msg.n.nlmsg_pid = nlmsg_pid;
+	msg.g.cmd = genl_cmd;
+	msg.g.version = 0x1;
+	na = (struct nlattr *) GENLMSG_DATA(&msg);
+	na->nla_type = nla_type;
+	na->nla_len = nla_len + 1 + NLA_HDRLEN;
+	memcpy(NLA_DATA(na), nla_data, nla_len);
+	msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len);
+
+	buf = (char *) &msg;
+	buflen = msg.n.nlmsg_len ;
+	memset(&nladdr, 0, sizeof(nladdr));
+	nladdr.nl_family = AF_NETLINK;
+	while ((r = sendto(sd, buf, buflen, 0, (struct sockaddr *) &nladdr,
+			   sizeof(nladdr))) < buflen) {
+		if (r > 0) {
+			buf += r;
+			buflen -= r;
+		} else if (errno != EAGAIN)
+			return -1;
+	}
+	return 0;
+}
+
+
+/*
+ * Probe the controller in genetlink to find the family id
+ * for the TASKSTATS family
+ */
+int get_family_id(int sd)
+{
+	struct {
+		struct nlmsghdr n;
+		struct genlmsghdr g;
+		char buf[256];
+	} ans;
+
+	int id, rc;
+	struct nlattr *na;
+	int rep_len;
+
+	strcpy(name, TASKSTATS_GENL_NAME);
+	rc = send_cmd(sd, GENL_ID_CTRL, getpid(), CTRL_CMD_GETFAMILY,
+			CTRL_ATTR_FAMILY_NAME, (void *)name,
+			strlen(TASKSTATS_GENL_NAME)+1);
+
+	rep_len = recv(sd, &ans, sizeof(ans), 0);
+	if (ans.n.nlmsg_type == NLMSG_ERROR ||
+	    (rep_len < 0) || !NLMSG_OK((&ans.n), rep_len))
+		return 0;
+
+	na = (struct nlattr *) GENLMSG_DATA(&ans);
+	na = (struct nlattr *) ((char *) na + NLA_ALIGN(na->nla_len));
+	if (na->nla_type == CTRL_ATTR_FAMILY_ID) {
+		id = *(__u16 *) NLA_DATA(na);
+	}
+	return id;
+}
+
+void print_delayacct(struct taskstats *t)
+{
+	printf("\n\nCPU   %15s%15s%15s%15s\n"
+	       "      %15llu%15llu%15llu%15llu\n"
+	       "IO    %15s%15s\n"
+	       "      %15llu%15llu\n"
+	       "MEM   %15s%15s\n"
+	       "      %15llu%15llu\n\n",
+	       "count", "real total", "virtual total", "delay total",
+	       t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total,
+	       t->cpu_delay_total,
+	       "count", "delay total",
+	       t->blkio_count, t->blkio_delay_total,
+	       "count", "delay total", t->swapin_count, t->swapin_delay_total);
+}
+
+int main(int argc, char *argv[])
+{
+	int c, rc, rep_len, aggr_len, len2, cmd_type;
+	__u16 id;
+	__u32 mypid;
+
+	struct nlattr *na;
+	int nl_sd = -1;
+	int len = 0;
+	pid_t tid = 0;
+	pid_t rtid = 0;
+
+	int fd = 0;
+	int count = 0;
+	int write_file = 0;
+	int maskset = 0;
+	char logfile[128];
+	int loop = 0;
+
+	struct msgtemplate msg;
+
+	while (1) {
+		c = getopt(argc, argv, "dw:r:m:t:p:v:l");
+		if (c < 0)
+			break;
+
+		switch (c) {
+		case 'd':
+			printf("print delayacct stats ON\n");
+			print_delays = 1;
+			break;
+		case 'w':
+			strncpy(logfile, optarg, MAX_FILENAME);
+			printf("write to file %s\n", logfile);
+			write_file = 1;
+			break;
+		case 'r':
+			rcvbufsz = atoi(optarg);
+			printf("receive buf size %d\n", rcvbufsz);
+			if (rcvbufsz < 0)
+				err(1, "Invalid rcv buf size\n");
+			break;
+		case 'm':
+			strncpy(cpumask, optarg, sizeof(cpumask));
+			maskset = 1;
+			printf("cpumask %s maskset %d\n", cpumask, maskset);
+			break;
+		case 't':
+			tid = atoi(optarg);
+			if (!tid)
+				err(1, "Invalid tgid\n");
+			cmd_type = TASKSTATS_CMD_ATTR_TGID;
+			print_delays = 1;
+			break;
+		case 'p':
+			tid = atoi(optarg);
+			if (!tid)
+				err(1, "Invalid pid\n");
+			cmd_type = TASKSTATS_CMD_ATTR_PID;
+			print_delays = 1;
+			break;
+		case 'v':
+			printf("debug on\n");
+			dbg = 1;
+			break;
+		case 'l':
+			printf("listen forever\n");
+			loop = 1;
+			break;
+		default:
+			printf("Unknown option %d\n", c);
+			exit(-1);
+		}
+	}
+
+	if (write_file) {
+		fd = open(logfile, O_WRONLY | O_CREAT | O_TRUNC,
+			  S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH);
+		if (fd == -1) {
+			perror("Cannot open output file\n");
+			exit(1);
+		}
+	}
+
+	if ((nl_sd = create_nl_socket(NETLINK_GENERIC)) < 0)
+		err(1, "error creating Netlink socket\n");
+
+
+	mypid = getpid();
+	id = get_family_id(nl_sd);
+	if (!id) {
+		printf("Error getting family id, errno %d", errno);
+		goto err;
+	}
+	PRINTF("family id %d\n", id);
+
+	if (maskset) {
+		rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET,
+			      TASKSTATS_CMD_ATTR_REGISTER_CPUMASK,
+			      &cpumask, sizeof(cpumask));
+		PRINTF("Sent register cpumask, retval %d\n", rc);
+		if (rc < 0) {
+			printf("error sending register cpumask\n");
+			goto err;
+		}
+	}
+
+	if (tid) {
+		rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET,
+			      cmd_type, &tid, sizeof(__u32));
+		PRINTF("Sent pid/tgid, retval %d\n", rc);
+		if (rc < 0) {
+			printf("error sending tid/tgid cmd\n");
+			goto done;
+		}
+	}
+
+	do {
+		int i;
+
+		rep_len = recv(nl_sd, &msg, sizeof(msg), 0);
+		PRINTF("received %d bytes\n", rep_len);
+
+		if (rep_len < 0) {
+			printf("nonfatal reply error: errno %d\n", errno);
+			continue;
+		}
+		if (msg.n.nlmsg_type == NLMSG_ERROR ||
+		    !NLMSG_OK((&msg.n), rep_len)) {
+			printf("fatal reply error,  errno %d\n", errno);
+			goto done;
+		}
+
+		PRINTF("nlmsghdr size=%d, nlmsg_len=%d, rep_len=%d\n",
+		       sizeof(struct nlmsghdr), msg.n.nlmsg_len, rep_len);
+
+
+		rep_len = GENLMSG_PAYLOAD(&msg.n);
+
+		na = (struct nlattr *) GENLMSG_DATA(&msg);
+		len = 0;
+		i = 0;
+		while (len < rep_len) {
+			len += NLA_ALIGN(na->nla_len);
+			switch (na->nla_type) {
+			case TASKSTATS_TYPE_AGGR_TGID:
+				/* Fall through */
+			case TASKSTATS_TYPE_AGGR_PID:
+				aggr_len = NLA_PAYLOAD(na->nla_len);
+				len2 = 0;
+				/* For nested attributes, na follows */
+				na = (struct nlattr *) NLA_DATA(na);
+				done = 0;
+				while (len2 < aggr_len) {
+					switch (na->nla_type) {
+					case TASKSTATS_TYPE_PID:
+						rtid = *(int *) NLA_DATA(na);
+						if (pri